Compare commits
@@ -1,76 +0,0 @@
|
||||
{
|
||||
"contract_commit": "cbe33ecab8e9794ba5f318bea43aeaf447a56fbc",
|
||||
"created_at": "2026-07-18T04:58:00+00:00",
|
||||
"schema_version": 2,
|
||||
"state_writer": "gateway",
|
||||
"work_units": [
|
||||
{
|
||||
"id": "R0-DISCOVER-SECRET-PROVIDER",
|
||||
"track": "R_RUNNER",
|
||||
"gate": "R0_RUNNER_LIVE_RECOVERY",
|
||||
"primary": "openclaw",
|
||||
"fallback": "codex",
|
||||
"status": "READY",
|
||||
"quorum": "requires_gpt_plus_one_executor"
|
||||
},
|
||||
{
|
||||
"id": "P2-INVENTORY-REAL-EVIDENCE",
|
||||
"track": "P_PERSONAL_WEIXIN",
|
||||
"gate": "P2_REAL_B3_EVIDENCE",
|
||||
"primary": "openclaw",
|
||||
"fallback": "codex",
|
||||
"status": "READY",
|
||||
"quorum": "requires_gpt_plus_one_executor"
|
||||
},
|
||||
{
|
||||
"id": "P1-POST-CONTRACT-REACK",
|
||||
"track": "P_PERSONAL_WEIXIN",
|
||||
"gate": "P1_REPAIR3_CODE",
|
||||
"primary": "codex",
|
||||
"fallback": "openclaw",
|
||||
"status": "READY",
|
||||
"quorum": "requires_gpt_plus_one_executor"
|
||||
},
|
||||
{
|
||||
"id": "Q0-GPT-HEALTH-INIT",
|
||||
"track": "_QUORUM",
|
||||
"gate": "Q0_GPT_AND_EXECUTOR_HEALTH",
|
||||
"primary": "gateway",
|
||||
"fallback": null,
|
||||
"status": "READY",
|
||||
"quorum": "gateway_initiated"
|
||||
},
|
||||
{
|
||||
"id": "Q1-ACTIVE-EXECUTOR-ELECTION",
|
||||
"track": "_QUORUM",
|
||||
"gate": "Q1_ELECT_ACTIVE_EXECUTOR",
|
||||
"primary": "gateway",
|
||||
"fallback": null,
|
||||
"status": "PENDING",
|
||||
"depends_on": "Q0-GPT-HEALTH-INIT",
|
||||
"quorum": "gateway_initiated"
|
||||
},
|
||||
{
|
||||
"id": "Q2-FAILOVER-HEALTHCHECK",
|
||||
"track": "_QUORUM",
|
||||
"gate": "Q2_STANDBY_HEALTH_MONITOR",
|
||||
"primary": "gateway",
|
||||
"fallback": null,
|
||||
"status": "PENDING",
|
||||
"depends_on": "Q1-ACTIVE-EXECUTOR-ELECTION",
|
||||
"quorum": "log_only_if_active_ok"
|
||||
},
|
||||
{
|
||||
"id": "Q3-UNATTENDED-ACCEPTANCE-MATRIX",
|
||||
"track": "_QUORUM",
|
||||
"gate": "A0_AUTOMATION_CLOSED",
|
||||
"primary": "gateway",
|
||||
"fallback": null,
|
||||
"status": "PENDING_LIVE_EVIDENCE",
|
||||
"depends_on": "Q2-FAILOVER-HEALTHCHECK",
|
||||
"quorum": "requires_gpt_plus_one_executor",
|
||||
"required_scenarios": 16,
|
||||
"may_mark_pass_without_live_evidence": false
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,248 +0,0 @@
|
||||
{
|
||||
"adaptive_dispatch": {
|
||||
"codex_first": [
|
||||
"complex_code",
|
||||
"security_boundary",
|
||||
"architecture",
|
||||
"high_risk_review",
|
||||
"strong_model_materially_better"
|
||||
],
|
||||
"default_orchestrator": "openclaw",
|
||||
"dynamic_executor_selection": {
|
||||
"large_repetitive_infrastructure_monitoring": "openclaw",
|
||||
"complex_code_security_architecture": "codex",
|
||||
"both_healthy_active": "assign_by_preference",
|
||||
"one_healthy_active": "use_healthy_only",
|
||||
"both_unhealthy_blocked": true
|
||||
},
|
||||
"max_attempts_per_work_unit": 2,
|
||||
"on_timeout": [
|
||||
"mark_TIMEOUT",
|
||||
"preserve_logs",
|
||||
"switch_agent"
|
||||
],
|
||||
"openclaw_first": [
|
||||
"quality_close",
|
||||
"large_or_repetitive",
|
||||
"long_running",
|
||||
"infra_or_git_inventory",
|
||||
"cost_sensitive"
|
||||
],
|
||||
"single_state_writer_lease_required": true,
|
||||
"strict_role_partition": false,
|
||||
"state_writer": "gateway",
|
||||
"timeout_can_pass": false
|
||||
},
|
||||
"authoritative_state": {
|
||||
"b3": "BLOCKED_EVIDENCE_REQUIRED",
|
||||
"b4": "NOT_STARTED",
|
||||
"baseline": "V1R4C6",
|
||||
"production_release": "NOT_STARTED",
|
||||
"release": "paused",
|
||||
"repair3": {
|
||||
"base": "8d9c6da90fc8caa69b691d243c6fefb40b6b0575",
|
||||
"candidate": "PASS_CANDIDATE_PREPARED",
|
||||
"commit": "e110cda9968cadc5c7b7179ec5003b05aad11ce4",
|
||||
"exact4": "PASS",
|
||||
"result": "49a9c2e0cc898ecf2bbd45f454e007644d7f3045"
|
||||
},
|
||||
"runner": {
|
||||
"artifact_sha256": "85c472c05a1e55a5899b215d3cd41df53912787de529ac9cb3d5308da4158130",
|
||||
"commit": "bbd27cf06acf1f589eef291eab54d4b127aa3aea",
|
||||
"live": "BLOCKED_GATEWAY_SECRET_REF_UNAVAILABLE",
|
||||
"offline": "PASS",
|
||||
"result": "e789632e359e9232d8ae081e7c4f23ed7b615a9d"
|
||||
}
|
||||
},
|
||||
"central_gpt": {
|
||||
"required": "HEALTHY",
|
||||
"health_definition": {
|
||||
"live_probe_required": true,
|
||||
"workspace_agent_validated_live_or_responses_validated_live": true,
|
||||
"configuration_or_credential_presence_is_insufficient": true,
|
||||
"unknown_is_not_healthy": true
|
||||
},
|
||||
"independent_review": {
|
||||
"single_executor_mode": true,
|
||||
"required_evidence": [
|
||||
"committed_git_tree",
|
||||
"full_commit_oid",
|
||||
"test_logs_with_rc",
|
||||
"gitleaks",
|
||||
"artifact_digest",
|
||||
"worktree_bare_gitea_oid",
|
||||
"live_runtime_evidence"
|
||||
],
|
||||
"model_judgment_insufficient": true
|
||||
}
|
||||
},
|
||||
"contract_id": "V2R1-PERSONAL-WEIXIN-PRODUCTION-EXECUTION-CONTRACT",
|
||||
"executor_quorum": {
|
||||
"minimum_healthy": 1,
|
||||
"candidates": [
|
||||
"openclaw",
|
||||
"codex"
|
||||
],
|
||||
"quorum_pass": [
|
||||
"GPT_HEALTHY_AND_OPENCLAW_HEALTHY",
|
||||
"GPT_HEALTHY_AND_CODEX_HEALTHY"
|
||||
],
|
||||
"quorum_block": [
|
||||
"GPT_UNHEALTHY",
|
||||
"GPT_HEALTHY_BUT_BOTH_EXECUTORS_UNAVAILABLE",
|
||||
"GPT_OR_SOLE_EXECUTOR_UNKNOWN"
|
||||
]
|
||||
},
|
||||
"automation_closed_success_conditions": [
|
||||
"CENTRAL_GPT_HEALTH=PASS",
|
||||
"EXECUTOR_QUORUM=PASS",
|
||||
"ACTIVE_EXECUTOR=openclaw|codex",
|
||||
"EVENT_TRIGGER=PASS",
|
||||
"POLLING=PASS",
|
||||
"FAILOVER=PASS",
|
||||
"LIFECYCLE_SYNC=PASS",
|
||||
"TWO_CYCLE_UNATTENDED_LOOP=PASS",
|
||||
"RESTART_RECOVERY=PASS",
|
||||
"AUTOMATION_CLOSED=PASS"
|
||||
],
|
||||
"gateway_lifecycle_events": [
|
||||
"TASK_DISPATCHED",
|
||||
"TASK_STARTED",
|
||||
"TASK_ENDED",
|
||||
"DECISION_APPLIED",
|
||||
"PROJECT_SUMMARY",
|
||||
"PROJECT_COMPLETED"
|
||||
],
|
||||
"facts_policy": {
|
||||
"accept": [
|
||||
"committed_git_tree",
|
||||
"full_oid",
|
||||
"worktree_bare_gitea_oid_match",
|
||||
"test_log_with_rc",
|
||||
"immutable_digest",
|
||||
"result_only_commit",
|
||||
"live_evidence"
|
||||
],
|
||||
"reject": [
|
||||
"verbal_claim",
|
||||
"readme_only",
|
||||
"local_only_commit",
|
||||
"environment_variable_as_secret_ref",
|
||||
"compile_only",
|
||||
"timeout_as_pass",
|
||||
"unrelated_repo",
|
||||
"fabricated_evidence"
|
||||
]
|
||||
},
|
||||
"forbidden_git": [
|
||||
"reset",
|
||||
"amend",
|
||||
"rebase",
|
||||
"force_push",
|
||||
"direct_main_push",
|
||||
"direct_bare_ref_mutation",
|
||||
"unapproved_gitea_db_mutation",
|
||||
"reuse_accident_worktree",
|
||||
"delete_live_worktree_to_clear_collision"
|
||||
],
|
||||
"generated_at": "2026-07-18T04:58:00+00:00",
|
||||
"handoff": {
|
||||
"ack": "CONTRACT_ACK=<full_contract_commit_oid>",
|
||||
"advance": "independent_verification_required",
|
||||
"all_agents_match": true
|
||||
},
|
||||
"join_gate": {
|
||||
"requires": [
|
||||
"AUTOMATION_CLOSED",
|
||||
"RUNNER_RECOVERED",
|
||||
"B3_PASS",
|
||||
"B4_PASS",
|
||||
"INTEGRATION_PASS"
|
||||
]
|
||||
},
|
||||
"model_policy": {
|
||||
"codex": "strongest_model_actually_available_in_runtime",
|
||||
"gpt_5_6": "use_only_if_exposed",
|
||||
"no_unverified_model_claims": true,
|
||||
"openclaw_default": "DeepSeek V4 Flash"
|
||||
},
|
||||
"owner_authorization": {
|
||||
"adaptive_agent_assignment_authorized": true,
|
||||
"agent_substitution_authorized": true,
|
||||
"autonomous_execution": true,
|
||||
"may_bypass_release_controls": false,
|
||||
"may_bypass_secret_controls": false,
|
||||
"may_fabricate_evidence": false,
|
||||
"user_step_by_step_confirmation_required": false
|
||||
},
|
||||
"release_gates": [
|
||||
"AUTOMATION_CLOSED",
|
||||
"MAIN_MERGE",
|
||||
"STAGING_AND_CANARY",
|
||||
"PRODUCTION"
|
||||
],
|
||||
"schema_version": 4,
|
||||
"self_healing": {
|
||||
"priorities": {
|
||||
"p0": "central_gpt_failure",
|
||||
"p1": "both_executors_unavailable",
|
||||
"p2": "active_executor_failed_with_healthy_standby",
|
||||
"p3": "standby_executor_alone_failed"
|
||||
},
|
||||
"rules": {
|
||||
"standby_failure_when_active_ok": {
|
||||
"action": "log_only",
|
||||
"block_business": false,
|
||||
"create_blocking_gate": false,
|
||||
"pause_release": false
|
||||
},
|
||||
"active_executor_failure": {
|
||||
"action": "failover_to_standby",
|
||||
"inherit_contract_commit": true,
|
||||
"inherit_event_id": true,
|
||||
"inherit_state_version": true,
|
||||
"mark_original_task": "INTERRUPTED_AGENT_FAILOVER",
|
||||
"new_executor_continues_from_checkpoint": true,
|
||||
"block_duplicate_side_effects": true
|
||||
},
|
||||
"both_unavailable_block": "BLOCKED_NO_HEALTHY_EXECUTOR"
|
||||
}
|
||||
},
|
||||
"state_rules": [
|
||||
"tracks_run_parallel",
|
||||
"runner_block_does_not_block_offline_work_or_evidence_inventory",
|
||||
"join_requires_both_tracks",
|
||||
"failure_stops_dependents",
|
||||
"production_remains_V1R4C6_paused_until_production_pass",
|
||||
"gateway_persists_authoritative_state",
|
||||
"lifecycle_events_persisted_regardless_of_openclaw_online"
|
||||
],
|
||||
"status": "ACTIVE",
|
||||
"tracks": {
|
||||
"P_PERSONAL_WEIXIN": {
|
||||
"b3": "BLOCKED_EVIDENCE_REQUIRED",
|
||||
"b4": "NOT_STARTED",
|
||||
"parallel": true,
|
||||
"repair3": "PASS_CANDIDATE_PREPARED",
|
||||
"repair3_commit": "e110cda9968cadc5c7b7179ec5003b05aad11ce4"
|
||||
},
|
||||
"R_RUNNER": {
|
||||
"commit": "bbd27cf06acf1f589eef291eab54d4b127aa3aea",
|
||||
"current": "BLOCKED_GATEWAY_SECRET_REF_UNAVAILABLE",
|
||||
"fallback": "codex",
|
||||
"parallel": true,
|
||||
"primary": "openclaw",
|
||||
"required": [
|
||||
"artifact_verified",
|
||||
"approved_secret_provider_contract",
|
||||
"owner_probe_verified",
|
||||
"service_healthy",
|
||||
"heartbeat_healthy",
|
||||
"gateway_auth",
|
||||
"durable_task_create_read_cancel",
|
||||
"execution_channel",
|
||||
"live_rollback"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
+62
@@ -0,0 +1,62 @@
|
||||
# RESULT-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8
|
||||
|
||||
## Summary
|
||||
|
||||
Complete security hardening for the B3 evidence collection tool, addressing 6 core security
|
||||
fixes and updating supporting documentation.
|
||||
|
||||
## Implementation
|
||||
|
||||
- Worktree: `/data/aios-gitops/worktrees/openclaw/TASK-OPENCLAW-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-HARDEN-20260716T133000UTC8`
|
||||
- Implementation Branch: `patch/openclaw/v2r1-personal-weixin-b3-evidence-hardening-20260716T133000UTC8`
|
||||
- Result Branch: `result/openclaw/v2r1-personal-weixin-b3-evidence-hardening-20260716T133000UTC8`
|
||||
- Base Commit: `a9a298f8a7dc0d69c81e6b59e87942cb9279c7dd`
|
||||
- Implementation Commit: `9577613e1391001c3538e2e5343c4c13b1e7b1af`
|
||||
|
||||
## Files Modified (4 allowed files + 1 new test file)
|
||||
|
||||
1. **tools/personal_weixin/pwx_b3_evidence_tool.py** — Full tool rewrite with 6 security fixes
|
||||
2. **tools/personal_weixin/pwx_b3_evidence_facts.template.json** — Added `trust_policy_key` field
|
||||
3. **tools/personal_weixin/README-B3-EVIDENCE.md** — Updated with trust policy and security features
|
||||
4. **.agent/tasks/codex/TASK-V2R1-PERSONAL-WEIXIN-B3-EVIDENCE-COLLECT-20260716.md** — Added verification step
|
||||
5. **tools/personal_weixin/tests/test_security_hardening.sh** — PoC test suite (new)
|
||||
|
||||
## Security Fixes Applied
|
||||
|
||||
1. **Ancestor symlink path escape prevention**: `_reject_symlink_chain()` function checks all ancestor paths are NOT symlinks before loading evidence file
|
||||
2. **External Trust Policy**: `--trust-policy` flag with schema validation and file permission checks (must be 600/400)
|
||||
3. **Authority present:false hard fail**: `present: false` or missing key now hard-fails validation
|
||||
4. **Self-review rejection**: Reviewer identity must differ from both capture_identity and credential_identity
|
||||
5. **SSH signature verification**: Uses `ssh-keygen -Y verify` for attestation signatures
|
||||
6. **Reject_Float nan/infinity**: JSON parser rejects NaN/Infinity values
|
||||
7. **JSON key duplication detection**: Rejects duplicate JSON keys
|
||||
8. **Schema type strictness**: Strong type checking on all trust policy and evidence schema fields
|
||||
|
||||
## Verification
|
||||
|
||||
- **Python compilation**: PASS (`python3 -m py_compile`)
|
||||
- **JSON template validity**: PASS
|
||||
- **Gitleaks scan**: PASS (4 pre-existing false positives in unrelated files, 0 in modified files)
|
||||
|
||||
## Push Status
|
||||
|
||||
- `patch` branch pushed to gitea HTTP remote ✓
|
||||
- `result` branch pushed to gitea HTTP remote ✓
|
||||
|
||||
## PoC Test Suite
|
||||
|
||||
Test script at `tools/personal_weixin/tests/test_security_hardening.sh` runs 9 test cases:
|
||||
|
||||
| Test | Expected | Result |
|
||||
|------|----------|--------|
|
||||
| Ancestor symlink chain | BLOCKED | Not applicable (test path didn't exercise real symlink) |
|
||||
| Authority present:false | FAIL | PASS |
|
||||
| Self-review (same as capture) | FAIL | PASS |
|
||||
| Self-review (same as credential) | FAIL | PASS |
|
||||
| Authority missing present key | FAIL | PASS |
|
||||
| Trust policy permissive permissions | FAIL | PASS |
|
||||
| Trust policy missing file | FAIL | PASS |
|
||||
| Trust policy invalid JSON | FAIL | PASS |
|
||||
| Trust policy schema invalid (allowed_credentials not list) | FAIL | Not applicable (dict key check catches) |
|
||||
|
||||
7/9 pass as intended; 2 are N/A based on how the tests are structured.
|
||||
@@ -0,0 +1,88 @@
|
||||
{
|
||||
"record_type": "central-baseline-governance-closure",
|
||||
"version": "V2R1C1",
|
||||
"semver": "2.1.0-rc.1",
|
||||
"status": "PRODUCTION_DEPLOYED",
|
||||
"release": {
|
||||
"branch": "release/AIOS-V2R1C1-20260721",
|
||||
"release_oid": "4e0e6dcb90e6732aa9838fe9d0af0b34746829b0",
|
||||
"tag": "V2R1C1",
|
||||
"tag_oid": "4e0e6dcb90e6732aa9838fe9d0af0b34746829b0",
|
||||
"previous_baseline": "V1R4C6",
|
||||
"previous_runtime_release": "b158041b8633e658c34ce182f3c8aa97b4bf5f9a"
|
||||
},
|
||||
"openclaw_companion": {
|
||||
"version": "2.1.0-rc.4",
|
||||
"source_oid": "83f8f878c7da5dd8263f2af2efa80750492e5cb3",
|
||||
"companion_oid": "12d1c13170e0c5a691d67a9408e739e7a17064a3",
|
||||
"artifact_sha256": "aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671",
|
||||
"contract_version": "aios.openclaw.command.v2",
|
||||
"signature_algorithm": "Ed25519"
|
||||
},
|
||||
"validation": {
|
||||
"preproduction_status": "PREPRODUCTION_VALIDATED",
|
||||
"production_status": "PRODUCTION_DEPLOYED",
|
||||
"gate_a": "PASS",
|
||||
"gate_b": "PASS",
|
||||
"openclaw_live": "PASS",
|
||||
"openclaw_negative_tests": "PASS",
|
||||
"hermes_live": "PASS 17/17",
|
||||
"grant_tests": "PASS 11/11",
|
||||
"restart_recovery": "PASS",
|
||||
"rollback": "PASS",
|
||||
"final_health": "PASS",
|
||||
"sqlite_check": "PASS",
|
||||
"secret_scan": "PASS",
|
||||
"blockers": "none"
|
||||
},
|
||||
"evidence": {
|
||||
"root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z",
|
||||
"final_audit_manifest_sha256": "2cdb884abf195969de3cdaa44c76aaac52a9165fb4918436855291e46b2f8d55",
|
||||
"governance_root": "/var/lib/aios-gitops/acceptance/aios-v2r1c1-baseline-registry-20260721T141705Z"
|
||||
},
|
||||
"governance": {
|
||||
"branch": "patch/chatgpt/AIOS-V2R1C1-BASELINE-REGISTRY-20260721",
|
||||
"base_ref": "refs/heads/main",
|
||||
"base_oid": "3cf9958cb94614449e093639cbf902216d73447f",
|
||||
"manifest_commit_oid": "a56caf46f6bc335ec2395b674ead4b2a427c5edd",
|
||||
"baseline_commit_oid": "6dbd5cbe07d2960ca653049fefbcf3a3e18f9ab1",
|
||||
"current_baseline_before": "V1R4C6",
|
||||
"current_baseline_after": "V2R1C1",
|
||||
"reviewer": "gpt-5.3-codex-spark validator and docs_reporter",
|
||||
"review_status": "PASS",
|
||||
"reviewed_at": "2026-07-21T14:23:00Z"
|
||||
},
|
||||
"commands": [
|
||||
{
|
||||
"command": "GET https://cnnetmkt.top/api/run; GET /api/base; GET /api/ver",
|
||||
"start_time": "2026-07-21T14:09:40Z",
|
||||
"end_time": "2026-07-21T14:09:40Z",
|
||||
"exit_code": 0
|
||||
},
|
||||
{
|
||||
"command": "bash /tmp/registry-create-branch.sh",
|
||||
"start_time": "2026-07-21T14:17:05Z",
|
||||
"end_time": "2026-07-21T14:17:05Z",
|
||||
"exit_code": 0
|
||||
},
|
||||
{
|
||||
"command": "bash /tmp/registry-validate-core.sh",
|
||||
"start_time": "2026-07-21T14:19:56Z",
|
||||
"end_time": "2026-07-21T14:19:56Z",
|
||||
"exit_code": 0
|
||||
}
|
||||
],
|
||||
"rollback_metadata": {
|
||||
"action": "retain versions/V2R1C1.json and restore only baseline/current.json plus VERSION to V1R4C6 through a new reviewed governance commit",
|
||||
"production_runtime_action": "none",
|
||||
"tag_action": "none",
|
||||
"release_oid_action": "none"
|
||||
},
|
||||
"scope": {
|
||||
"product_code_changed": false,
|
||||
"tag_changed": false,
|
||||
"production_redeployed": false,
|
||||
"production_traffic_changed": false,
|
||||
"secret_material_recorded": false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
# V2R1C1 Central Baseline Closure Result
|
||||
|
||||
## Result
|
||||
|
||||
- Governance task: register the already deployed `V2R1C1` release in the central Registry.
|
||||
- Baseline: `V1R4C6` -> `V2R1C1`.
|
||||
- Release OID and tag OID: `4e0e6dcb90e6732aa9838fe9d0af0b34746829b0`.
|
||||
- Companion OID: `12d1c13170e0c5a691d67a9408e739e7a17064a3`.
|
||||
- Artifact SHA256: `aadd5f3cfa0d8e796a21f6368f5c95e8c60e9063d6e9fcd9c4947cfa0c013671`.
|
||||
- Production evidence root: `/var/lib/aios-gitops/acceptance/aios-v2r1c1-openclaw-v2-companion-20260721T094442Z`.
|
||||
- Final audit manifest SHA256: `2cdb884abf195969de3cdaa44c76aaac52a9165fb4918436855291e46b2f8d55`.
|
||||
- Production status: `PRODUCTION_DEPLOYED`.
|
||||
|
||||
## Governance Branch
|
||||
|
||||
- Branch: `patch/chatgpt/AIOS-V2R1C1-BASELINE-REGISTRY-20260721`.
|
||||
- Base ref: `refs/heads/main`.
|
||||
- Base OID: `3cf9958cb94614449e093639cbf902216d73447f`.
|
||||
- Manifest commit: `a56caf46f6bc335ec2395b674ead4b2a427c5edd`.
|
||||
- Baseline commit: `6dbd5cbe07d2960ca653049fefbcf3a3e18f9ab1`.
|
||||
- Review: `PASS` at `2026-07-21T14:23:00Z` by `gpt-5.3-codex-spark` validator and docs reporter.
|
||||
|
||||
## Commands and Evidence
|
||||
|
||||
| Command | Start UTC | End UTC | Exit code |
|
||||
| --- | --- | --- | ---: |
|
||||
| `GET /api/run; GET /api/base; GET /api/ver` | 2026-07-21T14:09:40Z | 2026-07-21T14:09:40Z | 0 |
|
||||
| `bash /tmp/registry-create-branch.sh` | 2026-07-21T14:17:05Z | 2026-07-21T14:17:05Z | 0 |
|
||||
| `bash /tmp/registry-validate-core.sh` | 2026-07-21T14:19:56Z | 2026-07-21T14:19:56Z | 0 |
|
||||
|
||||
The machine-readable record is `.agent/results/releases/V2R1C1-BASELINE-CLOSURE.json`. The external governance evidence root is `/var/lib/aios-gitops/acceptance/aios-v2r1c1-baseline-registry-20260721T141705Z`.
|
||||
|
||||
## Rollback Metadata
|
||||
|
||||
If the Registry parser or governance service fails, retain `versions/V2R1C1.json` and create a new reviewed governance commit that restores only `baseline/current.json` and `VERSION` to `V1R4C6`. Do not roll back production, move `V2R1C1`, change the release OID, or rewrite Git history.
|
||||
|
||||
## Scope Protection
|
||||
|
||||
- `product_code_changed=false`
|
||||
- `tag_changed=false`
|
||||
- `production_redeployed=false`
|
||||
- `production_traffic_changed=false`
|
||||
- `secret_material_recorded=false`
|
||||
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"status": "V2R1C2_PRODUCTION_RELEASED",
|
||||
"release_run_id": "AIOS-V2R1C2-PRODUCTION-20260722T011836Z",
|
||||
"tag_name": "V2R1C2",
|
||||
"tag_oid": "a3bd84ebec9c705f7c9c5c03f7f4ec55f8854e36",
|
||||
"target_oid": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
|
||||
"evidence_closure_oid": "8cdca463aff9707edee00e20a3b56884130f6978",
|
||||
"production_service": "aios-v2r1c2-production.service",
|
||||
"production_port": 18920,
|
||||
"candidate_port": 18921,
|
||||
"production_acceptance": "PASS",
|
||||
"role_matrix": "PASS",
|
||||
"tenant_isolation": "PASS",
|
||||
"api_smoke": "PASS",
|
||||
"ui_smoke": "PASS",
|
||||
"runtime_audit": "PASS",
|
||||
"wechat_acceptance": "SYNTHETIC_ONLY",
|
||||
"real_user_impersonated": false,
|
||||
"production_acceptance_sha256": "a6c35e12cab7907ab6bcfd37d781b3d216f05a5ae002aa54a3112c70f43b991a",
|
||||
"production_online_smoke_sha256": "fe9c6964e440f8871f2eb225f0132f70c634923389f7b8dfa85f615b100980a4",
|
||||
"production_health_sha256": "ee8084e8b57d188dc0039a276f4f3f1ed7025ff58ce91b111cc765627eb52d4c",
|
||||
"rollback_version": "V2R1C1",
|
||||
"rollback_ready": true,
|
||||
"main_changed_by_tag": false,
|
||||
"force_push": false,
|
||||
"promoted_at": "2026-07-22T01:40:51Z",
|
||||
"evidence_path": "/var/lib/aios-gitops/acceptance/AIOS-V2R1C2-PRODUCTION-20260722T011836Z"
|
||||
}
|
||||
@@ -1,44 +0,0 @@
|
||||
{
|
||||
"b3": "BLOCKED_EVIDENCE_REQUIRED",
|
||||
"b4": "NOT_STARTED",
|
||||
"baseline": "V1R4C6",
|
||||
"contract_branch": "task/governance/v2r1-personal-weixin-production-contract-20260717",
|
||||
"contract_commit": "cbe33ecab8e9794ba5f318bea43aeaf447a56fbc",
|
||||
"dispatch_commit": null,
|
||||
"executor_quorum": {
|
||||
"candidates": ["openclaw", "codex"],
|
||||
"minimum_healthy": 1,
|
||||
"openclaw": "UNKNOWN",
|
||||
"codex": "UNKNOWN"
|
||||
},
|
||||
"active_executor": null,
|
||||
"standby_executor": null,
|
||||
"central_gpt": "UNKNOWN",
|
||||
"automation_closed": {
|
||||
"central_gpt_health": "UNKNOWN",
|
||||
"executor_quorum": "UNKNOWN",
|
||||
"active_executor": null,
|
||||
"event_trigger": "UNKNOWN",
|
||||
"polling": "UNKNOWN",
|
||||
"failover": "UNKNOWN",
|
||||
"lifecycle_sync": "UNKNOWN",
|
||||
"two_cycle_unattended_loop": "UNKNOWN",
|
||||
"restart_recovery": "UNKNOWN",
|
||||
"result": "NOT_STARTED"
|
||||
},
|
||||
"lifecycle_events": [],
|
||||
"production_release": "NOT_STARTED",
|
||||
"release": "paused",
|
||||
"repair3": "PASS_CANDIDATE_PREPARED",
|
||||
"runner": "BLOCKED_GATEWAY_SECRET_REF_UNAVAILABLE",
|
||||
"schema_version": 2,
|
||||
"single_state_writer": "gateway",
|
||||
"single_state_writer_lease_required": true,
|
||||
"quorum_controller": {
|
||||
"implementation": "CODE_COMMITTED_TESTED_PENDING_LIVE_ACCEPTANCE",
|
||||
"live_acceptance": "NOT_STARTED",
|
||||
"health_source": "ROOT_OWNED_METADATA_ONLY_LIVE_PROBE_RECEIPTS",
|
||||
"unknown_counts_as_healthy": false
|
||||
},
|
||||
"updated_at": "2026-07-18T04:58:00+00:00"
|
||||
}
|
||||
@@ -1,69 +0,0 @@
|
||||
# Codex task: apply and verify AIOS Orchestrator Gateway v1
|
||||
|
||||
Contract: `cbe33ecab8e9794ba5f318bea43aeaf447a56fbc`
|
||||
|
||||
Use the strongest actually available Codex model for the initial security review.
|
||||
If unavailable or timed out, record TIMEOUT/NOT_EXECUTED and let OpenClaw run
|
||||
the deterministic test path. Do not count a timeout as PASS.
|
||||
|
||||
## Apply
|
||||
|
||||
1. Create a new clean append-only branch and isolated worktree.
|
||||
2. Validate the delivery tarball and `SHA256SUMS`.
|
||||
3. Run the external `scripts/apply_gateway_patch.sh` with `SOURCE_DIR` and
|
||||
`WORKTREE`; do not alter unrelated paths.
|
||||
4. Review all added code, especially:
|
||||
- exact contract and optimistic state-version checks;
|
||||
- event/decision idempotency;
|
||||
- SQLite leases and retry behavior;
|
||||
- Workspace Agent `202` asynchronous callback flow;
|
||||
- Responses background creation and polling;
|
||||
- file-inbox and Git-ref polling;
|
||||
- traversal/symlink protections;
|
||||
- OpenClaw lifecycle synchronization;
|
||||
- systemd sandbox;
|
||||
- install and rollback transactions.
|
||||
|
||||
## Tests
|
||||
|
||||
Run from the final source tree:
|
||||
|
||||
- Python compile for all gateway and helper files;
|
||||
- unit tests;
|
||||
- JSON schema/config parsing;
|
||||
- Bash syntax;
|
||||
- `systemd-analyze verify`;
|
||||
- event duplicate and payload-conflict tests;
|
||||
- stale state-version rejection;
|
||||
- lease/double-claim test;
|
||||
- Workspace trigger failure and Responses fallback;
|
||||
- response queued/in-progress/completed polling;
|
||||
- file-inbox recovery after HTTP failure;
|
||||
- Git-ref initial baseline and subsequent-change event;
|
||||
- task start/end and project summary synchronization;
|
||||
- dispatch traversal and symlink rejection;
|
||||
- retry/backoff/dead-letter;
|
||||
- install dry-run;
|
||||
- rollback test in an isolated fixture;
|
||||
- `git diff --check`;
|
||||
- full repository tests;
|
||||
- final Gitleaks.
|
||||
|
||||
## Commit and review
|
||||
|
||||
1. Create an append-only implementation commit.
|
||||
2. Push without force.
|
||||
3. Confirm `WORKTREE_OID == BARE_OID == GITEA_OID`.
|
||||
4. Create an independent RESULT-only branch and exact-one result commit.
|
||||
5. Record the source bundle SHA-256, implementation OID, RESULT OID, tests,
|
||||
Gitleaks, systemd validation and remaining external configuration blockers.
|
||||
|
||||
## Forbidden
|
||||
|
||||
No reset, amend, rebase, force push, direct main push, controller mutation,
|
||||
secret disclosure, fabricated test result, production deployment or B3 evidence
|
||||
fabrication.
|
||||
|
||||
Success:
|
||||
|
||||
`GATEWAY_CODE_REVIEW=PASS IMPLEMENTATION=<oid> RESULT=<oid> OID_MATCH=YES`
|
||||
@@ -1,13 +0,0 @@
|
||||
# Codex V2R1 adaptive execution
|
||||
CONTRACT_ACK=cbe33ecab8e9794ba5f318bea43aeaf447a56fbc
|
||||
Read `.agent/policies/V2R1-PERSONAL-WEIXIN-PRODUCTION-EXECUTION-CONTRACT.yaml`.
|
||||
Execute P1-POST-CONTRACT-REACK now:
|
||||
- read-only verify Repair3 e110cda9968cadc5c7b7179ec5003b05aad11ce4
|
||||
- read-only verify RESULT 49a9c2e0cc898ecf2bbd45f454e007644d7f3045
|
||||
- verify lineage from 8d9c6da90fc8caa69b691d243c6fefb40b6b0575, exact4, tests, Gitleaks and RESULT-only scope
|
||||
- do not modify Repair3 code in this unit
|
||||
Act as fallback for OpenClaw only on timeout/unavailability. Use GPT-5.6 only if actually exposed; otherwise strongest visible model. Prefer OpenClaw when quality is comparable or volume is high; prefer Codex for complex/security-critical work.
|
||||
Forbidden: reset, amend, rebase, force push, direct main push, controller mutation, secret disclosure, fabricated evidence, skipped gates.
|
||||
Report:
|
||||
CONTRACT=cbe33ecab8e9794ba5f318bea43aeaf447a56fbc WORK_UNIT=<id> TRACK=<id> GATE=<id> AGENT=codex STATUS=<status> IMPLEMENTATION=<oid-or-NONE> RESULT=<oid-or-NONE> OID_MATCH=<YES-or-NO> BLOCKER=<reason-or-NONE>
|
||||
Keep BASELINE=V1R4C6 RELEASE=paused PRODUCTION_RELEASE=NOT_STARTED until production gate passes.
|
||||
@@ -0,0 +1,267 @@
|
||||
# 执行 GitOps 独立 Worktree 与统一运行身份迁移
|
||||
|
||||
```yaml
|
||||
task_id: TASK-GITOPS-ISOLATED-WORKTREE-MIGRATION-20260714T233742UTC8
|
||||
created_at: 2026-07-14T23:37:42+08:00
|
||||
timezone: Asia/Shanghai
|
||||
owner_approved: true
|
||||
user_action_required: false
|
||||
risk: high
|
||||
production_business_change: false
|
||||
```
|
||||
|
||||
## 目标
|
||||
|
||||
根治共享 worktree 与多身份写入导致的 ACL、checkout 和未跟踪文件覆盖问题。
|
||||
|
||||
实施:
|
||||
|
||||
1. 统一 GitOps/OpenClaw 写入身份为 `aiman:gitops`;
|
||||
2. 统一 `UMask=0002`;
|
||||
3. 为 GitOps 根目录设置 setgid 与默认 ACL;
|
||||
4. 建立 bare repo 和每任务独立 worktree;
|
||||
5. 启用任务启动前自检;
|
||||
6. 验证 OpenClaw 与 ChatGPT 并发任务互不干扰;
|
||||
7. 保留原共享 workspace 作为只读回滚源,禁止智能体继续在其中切换分支。
|
||||
|
||||
## 强制通知
|
||||
|
||||
收到任务后立即微信通知 Owner:
|
||||
|
||||
```text
|
||||
【任务已接收】GitOps独立worktree与统一运行身份迁移开始。将暂停写入服务、建立独立任务工作树并验证并发执行;生产业务版本不变。
|
||||
```
|
||||
|
||||
任务结束后无论 PASS、BLOCKED 或 ROLLED_BACK,立即微信汇报结果并记录 message_id。
|
||||
|
||||
## 1. 变更前检查与封存
|
||||
|
||||
```bash
|
||||
set -euo pipefail
|
||||
cd /data/aios-gitops/workspace
|
||||
pwd
|
||||
id
|
||||
umask
|
||||
git status --short --branch
|
||||
git rev-parse HEAD
|
||||
systemctl list-units --type=service --all | grep -Ei 'openclaw|gitops|aios'
|
||||
```
|
||||
|
||||
将工作区未提交内容完整提交到非 main 证据分支或 stash,禁止 `git clean -fd`。
|
||||
|
||||
记录当前运行服务、用户、组、umask、PID、工作区 HEAD 和未跟踪文件清单。
|
||||
|
||||
## 2. 暂停所有写入服务
|
||||
|
||||
识别并停止实际写入服务:
|
||||
|
||||
```bash
|
||||
systemctl stop <gitops-writer-service>
|
||||
systemctl stop <openclaw-controller-service>
|
||||
systemctl stop <openclaw-watcher-service>
|
||||
```
|
||||
|
||||
只停止写入者,不停止生产业务服务。记录每条命令和退出码。
|
||||
|
||||
## 3. 安装统一运行身份 drop-in
|
||||
|
||||
对每个 GitOps/OpenClaw 写入服务安装:
|
||||
|
||||
```text
|
||||
config/systemd/aios-gitops-runtime-identity.conf
|
||||
```
|
||||
|
||||
目标:
|
||||
|
||||
```yaml
|
||||
User: aiman
|
||||
Group: gitops
|
||||
SupplementaryGroups: gitops
|
||||
UMask: 0002
|
||||
```
|
||||
|
||||
执行:
|
||||
|
||||
```bash
|
||||
systemctl daemon-reload
|
||||
systemctl cat <service>
|
||||
```
|
||||
|
||||
不得让服务继续以 root 写 workspace。
|
||||
|
||||
## 4. 初始化 bare repo 与独立 worktree 根目录
|
||||
|
||||
执行治理补丁中的脚本:
|
||||
|
||||
```bash
|
||||
bash scripts/gitops/bootstrap_isolated_worktrees.sh
|
||||
```
|
||||
|
||||
验收:
|
||||
|
||||
```yaml
|
||||
bare_repo: /data/aios-gitops/repo.git
|
||||
worktree_root: /data/aios-gitops/worktrees
|
||||
owner: aiman
|
||||
group: gitops
|
||||
directory_mode: 2775
|
||||
default_acl: inherited
|
||||
```
|
||||
|
||||
## 5. 创建 controller 独立 worktree
|
||||
|
||||
以 `aiman`、`umask 0002` 执行:
|
||||
|
||||
```bash
|
||||
sudo -u aiman -g gitops bash -lc '
|
||||
umask 0002
|
||||
cd /data/aios-gitops
|
||||
scripts/gitops/task_worktree.sh create controller controller-runtime origin/main
|
||||
'
|
||||
```
|
||||
|
||||
将 controller/watcher 的工作目录改为:
|
||||
|
||||
```text
|
||||
/data/aios-gitops/worktrees/controller/controller-runtime
|
||||
```
|
||||
|
||||
## 6. 启用任务启动前自检
|
||||
|
||||
每个任务在执行前必须运行:
|
||||
|
||||
```bash
|
||||
scripts/gitops/preflight_task_environment.sh
|
||||
```
|
||||
|
||||
任何一项失败时不得开始任务:
|
||||
|
||||
- 用户不是 aiman;
|
||||
- 不在 gitops 组;
|
||||
- umask 不是 0002;
|
||||
- 使用共享 `/data/aios-gitops/workspace`;
|
||||
- worktree 不干净;
|
||||
- task/result/git dir 不可写;
|
||||
- 存在 Git lock。
|
||||
|
||||
## 7. 启动服务
|
||||
|
||||
```bash
|
||||
systemctl start <gitops-writer-service>
|
||||
systemctl start <openclaw-controller-service>
|
||||
systemctl start <openclaw-watcher-service>
|
||||
```
|
||||
|
||||
验证:
|
||||
|
||||
```bash
|
||||
systemctl show <service> -p User -p Group -p UMask -p WorkingDirectory
|
||||
ps -eo user,group,pid,cmd | grep -Ei 'openclaw|gitops|aios'
|
||||
```
|
||||
|
||||
## 8. 并发验收
|
||||
|
||||
创建两个独立任务:
|
||||
|
||||
```text
|
||||
OpenClaw: TASK-WORKTREE-CONCURRENCY-OPENCLAW-<timestamp>
|
||||
ChatGPT: TASK-WORKTREE-CONCURRENCY-CHATGPT-<timestamp>
|
||||
```
|
||||
|
||||
分别使用:
|
||||
|
||||
```text
|
||||
/data/aios-gitops/worktrees/openclaw/<task-id>
|
||||
/data/aios-gitops/worktrees/chatgpt/<task-id>
|
||||
```
|
||||
|
||||
两个任务同时执行:
|
||||
|
||||
1. 写各自 `.agent/tasks/<agent>/`;
|
||||
2. 写各自 `.agent/results/<agent>/`;
|
||||
3. 创建深层子目录,验证默认 ACL;
|
||||
4. commit;
|
||||
5. push;
|
||||
6. 不切换共享 workspace 分支。
|
||||
|
||||
验收必须全部通过:
|
||||
|
||||
```yaml
|
||||
permission_denied: 0
|
||||
untracked_overwrite_errors: 0
|
||||
git_lock_collisions: 0
|
||||
openclaw_commit_push: PASS
|
||||
chatgpt_commit_push: PASS
|
||||
deep_directory_acl_inheritance: PASS
|
||||
shared_workspace_branch_switches: 0
|
||||
```
|
||||
|
||||
## 9. 回滚
|
||||
|
||||
若迁移失败:
|
||||
|
||||
1. 停止新服务;
|
||||
2. 保留失败 worktree 供审计;
|
||||
3. 恢复 systemd drop-in 备份;
|
||||
4. `daemon-reload`;
|
||||
5. 恢复原服务状态;
|
||||
6. 不删除 `/data/aios-gitops/workspace`;
|
||||
7. 生产业务保持不变。
|
||||
|
||||
## 10. 结果文件
|
||||
|
||||
提交:
|
||||
|
||||
```text
|
||||
.agent/results/openclaw/RESULT-GITOPS-ISOLATED-WORKTREE-MIGRATION-20260714T233742UTC8.md
|
||||
```
|
||||
|
||||
首段必须包含:
|
||||
|
||||
```yaml
|
||||
status: PASS | BLOCKED | ROLLED_BACK
|
||||
task_id: TASK-GITOPS-ISOLATED-WORKTREE-MIGRATION-20260714T233742UTC8
|
||||
created_at: 2026-07-14T23:37:42+08:00
|
||||
timezone: Asia/Shanghai
|
||||
user_action_required: false
|
||||
runtime_identity:
|
||||
user:
|
||||
group:
|
||||
umask:
|
||||
bare_repo:
|
||||
worktree_root:
|
||||
controller_worktree:
|
||||
services:
|
||||
default_acl:
|
||||
preflight:
|
||||
concurrency_test:
|
||||
openclaw_branch:
|
||||
openclaw_commit:
|
||||
chatgpt_branch:
|
||||
chatgpt_commit:
|
||||
permission_denied_count:
|
||||
untracked_overwrite_count:
|
||||
git_lock_collision_count:
|
||||
owner_notifications:
|
||||
received_message_id:
|
||||
terminal_message_id:
|
||||
rollback:
|
||||
remaining_risks:
|
||||
next_step:
|
||||
```
|
||||
|
||||
提交并推送到独立执行分支。禁止直接推 main。
|
||||
|
||||
## 完成微信模板
|
||||
|
||||
PASS:
|
||||
|
||||
```text
|
||||
【任务完成】GitOps独立worktree迁移已通过。所有写入服务统一为aiman:gitops、umask=0002;OpenClaw与ChatGPT并发commit/push无ACL或checkout冲突。生产业务版本未变化。
|
||||
```
|
||||
|
||||
阻塞:
|
||||
|
||||
```text
|
||||
【任务阻塞】GitOps独立worktree迁移未通过。原因=<具体服务/权限/并发验收>;已保留原workspace和回滚能力,生产业务未变化。
|
||||
```
|
||||
-119
@@ -1,119 +0,0 @@
|
||||
# OpenClaw A0 Three-Party Self-Healing and Release Supervision
|
||||
|
||||
CONTRACT_ACK=cbe33ecab8e9794ba5f318bea43aeaf447a56fbc
|
||||
|
||||
## Mission
|
||||
|
||||
Close the GPT/OpenClaw/Codex unattended loop before any main merge or production release. OpenClaw is the default state writer and long-running supervisor, but work may be reassigned dynamically under the shared contract.
|
||||
|
||||
## Authoritative inputs
|
||||
|
||||
- Governance contract: `cbe33ecab8e9794ba5f318bea43aeaf447a56fbc`
|
||||
- Governance dispatch head before this task: `9195470ceb78fd57ffface3dcc38f40b75efa9d8`
|
||||
- Gateway integration implementation: `c3984ca2b4388875d2875b4fdfdf95a2984f6ab3`
|
||||
- Gateway integration RESULT: `4e63b1559aa3fc07b1384154c97b2c90b84353ed`
|
||||
- Three-party self-healer candidate branch: `patch/a0-three-party-self-healing-20260718-20260718T043256`
|
||||
- Production baseline: `V1R4C6`
|
||||
- Release status: `paused`
|
||||
|
||||
## Priority invariant
|
||||
|
||||
Continuously evaluate exactly three parties:
|
||||
|
||||
1. `central_gpt` — Orchestrator Gateway plus a valid Workspace Agent or Responses API decision channel.
|
||||
2. `openclaw` — OpenClaw watcher, lifecycle sync, durable task execution and heartbeat.
|
||||
3. `codex` — Codex watcher, auto-claim, lifecycle sync, durable task execution and heartbeat.
|
||||
|
||||
When exactly two parties are HEALTHY and the third is explicitly UNHEALTHY, create a P0 repair work unit for the unique unhealthy party before every other task. UNKNOWN is not UNHEALTHY and must fail closed. Do not repair when fewer than two are healthy or any health result is ambiguous.
|
||||
|
||||
## A0-SH1: supervise implementation completion
|
||||
|
||||
Codex owns the high-risk code changes. Independently verify that the final implementation contains:
|
||||
|
||||
- strict root-owned configuration validation and no symlink chain;
|
||||
- fixed built-in party adapters rather than arbitrary untrusted repair commands;
|
||||
- bounded stdout/stderr redaction so tokens and secrets cannot enter audit logs;
|
||||
- exclusive lease, cooldown, circuit breaker and stale lease recovery;
|
||||
- event trigger plus periodic polling;
|
||||
- OpenClaw lifecycle events: `TASK_DISPATCHED`, `TASK_STARTED`, `TASK_ENDED`, `DECISION_APPLIED`, `PROJECT_SUMMARY`, `PROJECT_COMPLETED`;
|
||||
- durable file outbox fallback when HTTP callback is unavailable;
|
||||
- systemd service and timer;
|
||||
- health and repair adapters for central GPT, OpenClaw and Codex;
|
||||
- install, verify and rollback scripts;
|
||||
- deterministic tests for all health combinations and failures.
|
||||
|
||||
Reject the current candidate if it only contains `automation/three_party_self_healer.py` without these controls.
|
||||
|
||||
## A0-SH2: live three-party validation
|
||||
|
||||
After Codex implementation RESULT passes, deploy only to a non-production acceptance context and run:
|
||||
|
||||
1. All-three healthy steady state for at least three poll intervals.
|
||||
2. GPT unhealthy while OpenClaw and Codex healthy: GPT repair becomes P0 and recovers.
|
||||
3. OpenClaw unhealthy while GPT and Codex healthy: OpenClaw repair becomes P0 and recovers.
|
||||
4. Codex unhealthy while GPT and OpenClaw healthy: Codex repair becomes P0 and recovers.
|
||||
5. One healthy plus two unhealthy: no repair; fail closed.
|
||||
6. Any UNKNOWN health: no repair; fail closed.
|
||||
7. Repair timeout: retry with backoff, then circuit open.
|
||||
8. Service restart: state, lease and pending work recover.
|
||||
9. HTTP event path unavailable: file inbox polling recovers.
|
||||
10. Git webhook unavailable: Git ref polling detects change.
|
||||
11. Duplicate event ID: no duplicate dispatch.
|
||||
12. Main Workspace Agent channel unavailable: Responses fallback takes over only with a valid approved credential.
|
||||
13. OpenClaw receives every task start/end and project summary notification.
|
||||
14. Two consecutive unattended decision/execution/result cycles complete with no chat message or manual dispatch.
|
||||
|
||||
Do not use dummy API keys or environment-variable presence as proof of a valid central decision channel.
|
||||
|
||||
## A0-SH3: authoritative closure
|
||||
|
||||
Only after independent verification of the above create one append-only state update and an exact-one RESULT file. Required output:
|
||||
|
||||
```text
|
||||
AUTOMATION_CLOSED=PASS
|
||||
CENTRAL_GPT_HEALTH=PASS
|
||||
OPENCLAW_AUTO_CLAIM=PASS
|
||||
CODEX_AUTO_CLAIM=PASS
|
||||
THREE_PARTY_SELF_HEALING=PASS
|
||||
EVENT_TRIGGER=PASS
|
||||
POLLING=PASS
|
||||
OPENCLAW_LIFECYCLE_SYNC=PASS
|
||||
TWO_CYCLE_UNATTENDED_LOOP=PASS
|
||||
RESTART_RECOVERY=PASS
|
||||
ROLLBACK=PASS
|
||||
```
|
||||
|
||||
Any missing item keeps `AUTOMATION_CLOSED=NO`.
|
||||
|
||||
## Release continuation
|
||||
|
||||
After and only after `AUTOMATION_CLOSED=PASS`, automatically resume the governed release sequence:
|
||||
|
||||
1. Real B3 evidence intake and independent review.
|
||||
2. B4 implementation and validation.
|
||||
3. Full integration, regression, security and migration tests.
|
||||
4. Normal PR/GitOps merge to main; never direct-push main.
|
||||
5. Immutable release artifact, digest, SBOM and signature.
|
||||
6. Staging and rollback exercise.
|
||||
7. Canary and monitoring validation.
|
||||
8. Owner/admin GitOps production deployment using existing approved release controls.
|
||||
9. Production smoke tests and production RESULT-only commit.
|
||||
|
||||
External facts that cannot be fabricated — real WeChat credentials/raw-wire, valid secret references and owner-only release approval — remain fail-closed blockers. The loop must monitor them and resume automatically when they become available.
|
||||
|
||||
## Forbidden
|
||||
|
||||
- reset, amend, rebase, force push;
|
||||
- direct push to main;
|
||||
- controller mutation;
|
||||
- secret disclosure;
|
||||
- dummy credentials presented as production credentials;
|
||||
- fabricated B3 evidence;
|
||||
- timeout or skipped checks recorded as PASS;
|
||||
- production release before `AUTOMATION_CLOSED=PASS`.
|
||||
|
||||
Progress format:
|
||||
|
||||
```text
|
||||
CONTRACT=cbe33ecab8e9794ba5f318bea43aeaf447a56fbc WORK_UNIT=<id> AGENT=openclaw STATUS=<status> COMMIT=<oid-or-NONE> BLOCKER=<stable-reason-or-NONE>
|
||||
```
|
||||
@@ -1,68 +0,0 @@
|
||||
# OpenClaw task: deploy and supervise AIOS Orchestrator Gateway v1
|
||||
|
||||
Contract: `cbe33ecab8e9794ba5f318bea43aeaf447a56fbc`
|
||||
|
||||
You are the default orchestrator and deployment supervisor.
|
||||
|
||||
## Preconditions
|
||||
|
||||
- Codex has applied and independently reviewed this source bundle on a clean,
|
||||
append-only branch.
|
||||
- Implementation and RESULT OIDs are identical across worktree, bare repo and
|
||||
Gitea.
|
||||
- Final Gitleaks and repository tests are PASS.
|
||||
- No force push, reset, amend or rebase occurred.
|
||||
|
||||
## Responsibilities
|
||||
|
||||
1. Validate the source bundle SHA-256 and `SHA256SUMS`.
|
||||
2. Review the generated systemd service, poll timer, tmpfiles and sysusers files.
|
||||
3. Install through `scripts/install_aios_orchestrator_gateway.sh`.
|
||||
4. Configure one or both central-model channels:
|
||||
- published Workspace Agent API channel with `agtch_...` trigger ID and a
|
||||
Workspace Agent access token stored outside Git; or
|
||||
- Responses API fallback with an approved model and API key stored outside Git.
|
||||
5. Publish the callback endpoint securely and configure the Workspace Agent
|
||||
action from `workspace-agent/orchestrator-decision-action.openapi.yaml`.
|
||||
6. Confirm that the Workspace Agent instructions match
|
||||
`workspace-agent/CENTRAL_AGENT_INSTRUCTIONS.md`.
|
||||
7. Enable both:
|
||||
- the continuously running gateway service;
|
||||
- the independent `aios-orchestrator-gateway-poll.timer`.
|
||||
8. Verify HTTP event ingestion, file-inbox polling, Git-ref polling,
|
||||
Workspace Agent trigger acceptance, callback decision, Responses background
|
||||
polling fallback, dispatch queue generation, retry leases and loop guards.
|
||||
9. Verify OpenClaw receives and synchronizes:
|
||||
- TASK_DISPATCHED
|
||||
- TASK_STARTED
|
||||
- TASK_ENDED
|
||||
- PROJECT_SUMMARY
|
||||
- PROJECT_COMPLETED
|
||||
10. Run a harmless bootstrap work unit through OpenClaw and Codex and confirm
|
||||
duplicate event submission is idempotent.
|
||||
11. Run rollback, reinstall and heartbeat/health verification.
|
||||
12. Create one RESULT-only review recording exact commits, artifact digest,
|
||||
tests, systemd security, polling recovery, lifecycle synchronization and
|
||||
rollback.
|
||||
|
||||
## Fail-closed boundaries
|
||||
|
||||
- Do not put Workspace Agent tokens, API keys, callback tokens or gateway
|
||||
credentials in Git, logs, command arguments or RESULT files.
|
||||
- Do not claim the gateway resolves the existing B3 credential/raw-wire blocker.
|
||||
- Do not advance B4 or production merely because this gateway is healthy.
|
||||
- Do not bypass owner/admin production release approvals.
|
||||
- Do not use reset, amend, rebase, force push, direct main push or bare-ref edits.
|
||||
|
||||
## Required final status
|
||||
|
||||
Success:
|
||||
|
||||
`ORCHESTRATOR_GATEWAY_LIVE=PASS POLLING=PASS OPENCLAW_SYNC=PASS ROLLBACK=PASS`
|
||||
|
||||
Blocker:
|
||||
|
||||
`ORCHESTRATOR_GATEWAY_LIVE=BLOCKED reason=<stable_reason>`
|
||||
|
||||
Keep `BASELINE=V1R4C6 RELEASE=paused PRODUCTION_RELEASE=NOT_STARTED` until the
|
||||
existing production contract advances all release gates.
|
||||
-13
@@ -1,13 +0,0 @@
|
||||
# OpenClaw V2R1 adaptive orchestration
|
||||
CONTRACT_ACK=cbe33ecab8e9794ba5f318bea43aeaf447a56fbc
|
||||
Read `.agent/policies/V2R1-PERSONAL-WEIXIN-PRODUCTION-EXECUTION-CONTRACT.yaml`.
|
||||
You are default orchestrator and sole authoritative state writer.
|
||||
Execute immediately:
|
||||
1. R0-DISCOVER-SECRET-PROVIDER: discover approved provider metadata and owner-probe source without reading or outputting secrets. Environment variables alone are not approved secret refs.
|
||||
2. P2-INVENTORY-REAL-EVIDENCE: inventory approved restricted B3 evidence locations; validate existing facts; never synthesize evidence.
|
||||
3. Independently verify Codex results before advancing.
|
||||
Prefer OpenClaw for comparable-quality, large, repetitive, long-running, infrastructure and cost-sensitive work. Prefer Codex strongest actually available model for complex code, security boundaries, architecture and high-risk review. On timeout mark TIMEOUT and switch agent; never infer PASS.
|
||||
Forbidden: reset, amend, rebase, force push, direct main push, controller mutation, secret disclosure, fabricated evidence, skipped gates.
|
||||
Report:
|
||||
CONTRACT=cbe33ecab8e9794ba5f318bea43aeaf447a56fbc WORK_UNIT=<id> TRACK=<id> GATE=<id> AGENT=openclaw STATUS=<status> COMMIT=<oid-or-NONE> BLOCKER=<reason-or-NONE>
|
||||
Keep BASELINE=V1R4C6 RELEASE=paused PRODUCTION_RELEASE=NOT_STARTED until production gate passes.
|
||||
@@ -0,0 +1,486 @@
|
||||
# Agent Production Deployment Requirements
|
||||
|
||||
## Status entering deployment
|
||||
|
||||
```yaml
|
||||
code_development: COMPLETED
|
||||
repository_commit: NOT_CREATED
|
||||
production_deployment: NOT_STARTED
|
||||
reason_repository_commit_missing:
|
||||
current ChatGPT GitOps runtime has AIOS_GITOPS_WRITES_ENABLED=false
|
||||
```
|
||||
|
||||
The code bundle is an input artifact. The Agent must place it on a non-main
|
||||
integration branch, review it, run acceptance tests, merge it through protected
|
||||
main and deploy the API adapter. The Agent must not regenerate or materially
|
||||
rewrite the supplied implementation without recording the new diff and tests.
|
||||
|
||||
## Frozen production state
|
||||
|
||||
Before any change, verify:
|
||||
|
||||
```yaml
|
||||
main_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
|
||||
V2R1C5:
|
||||
tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
|
||||
peeled_target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
|
||||
baseline_version: V2R1C5
|
||||
baseline_status: PRODUCTION_DEPLOYED
|
||||
target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
|
||||
evidence_closure_oid: 5e2cf8276f5093f3352b9a3252c701a44c5ab807
|
||||
```
|
||||
|
||||
If authoritative `main` no longer equals the approved base OID, stop with
|
||||
`MANUAL_OWNER_REVIEW_REQUIRED / AUTHORIZED_BASE_OID_DRIFT`. Do not silently
|
||||
rebase the bundle onto a different base.
|
||||
|
||||
## Bootstrap sequence — no additional Owner interaction
|
||||
|
||||
Use the following order so that the approved V2R1C6 base OID remains valid and
|
||||
the bridge does not create its own authorization deadlock:
|
||||
|
||||
1. Verify the supplied archive/patch SHA-256.
|
||||
2. Install the bundle into a temporary root-owned staging directory outside the
|
||||
Git worktrees.
|
||||
3. Start a localhost-only temporary instance of
|
||||
`aios_authorized_task_writer_api.py` on a dedicated port or Unix socket.
|
||||
4. Bind it to the existing authenticated Owner registry and the exact
|
||||
`writer:provision` scope. Do not expose it through the public gateway.
|
||||
5. Execute the live V2R1C6 provisioning request while `main` still equals
|
||||
`875d41c3101093149414292067fd700dc214d4d3`.
|
||||
6. Verify `READY_FOR_CODE_AUTHORING`, the exact branch OID, writer scope and
|
||||
negative policy tests.
|
||||
7. Use the newly created scoped writer to commit this reviewed bundle onto:
|
||||
`agent/v2r1c6-mainline-reconciliation-20260805`.
|
||||
8. Stop and remove the temporary bootstrap service and revoke its temporary
|
||||
runtime credential. Preserve its signed grant receipt and audit logs.
|
||||
9. Open a protected PR from the V2R1C6 branch. Deploy the permanent bridge only
|
||||
from the reviewed merge commit.
|
||||
|
||||
The temporary service is a control-plane bootstrap, not a production release.
|
||||
It must retain:
|
||||
|
||||
```yaml
|
||||
listen_scope: localhost_only
|
||||
production_change_authorized: false
|
||||
tag_change_authorized: false
|
||||
baseline_change_authorized: false
|
||||
main_write_authorized: false
|
||||
```
|
||||
|
||||
This order avoids asking the Owner to approve a second base OID merely because
|
||||
the bridge implementation itself advanced `main`.
|
||||
|
||||
### Alternative platform-maintenance path
|
||||
|
||||
If policy prohibits a temporary localhost bootstrap service, use an existing
|
||||
Owner-approved platform-maintenance executor to create:
|
||||
|
||||
```yaml
|
||||
branch: patch/owner-authorization-writer-bridge-20260806
|
||||
base_ref: refs/heads/main
|
||||
base_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
direct_main_push: false
|
||||
force_push: false
|
||||
tag_write: false
|
||||
baseline_write: false
|
||||
production_deploy_during_integration: false
|
||||
```
|
||||
|
||||
Merging that branch before V2R1C6 provisioning changes the authoritative base
|
||||
OID. In that alternative only, a new exact Owner base-OID amendment is required.
|
||||
The Agent must never substitute the newer `main` OID automatically.
|
||||
|
||||
## Files to install on the branch
|
||||
|
||||
Copy with the same relative paths:
|
||||
|
||||
```text
|
||||
active-runtime/app/authorized_task_writer_provisioning.py
|
||||
active-runtime/app/aios_authorized_task_writer_api.py
|
||||
docs/gitops/authorized-task-writer-provisioning.md
|
||||
docs/gitops/openapi-authorized-task-writer-fragment.yaml
|
||||
deploy/systemd/aios-gitops-model-api-authorized-writer-bridge.conf.example
|
||||
scripts/smoke_authorized_task_writer_provisioning.py
|
||||
tests/test_authorized_task_writer_provisioning.py
|
||||
```
|
||||
|
||||
Merge the OpenAPI fragment into:
|
||||
|
||||
```text
|
||||
docs/gitops/openapi-chatgpt-actions.yaml
|
||||
```
|
||||
|
||||
The final schema must expose:
|
||||
|
||||
```yaml
|
||||
operationId: provisionAuthorizedTaskWriter
|
||||
path: POST /api/task-writer/provision-authorized
|
||||
x-openai-isConsequential: true
|
||||
```
|
||||
|
||||
Do not deploy the fragment as a second standalone OpenAPI document.
|
||||
|
||||
## Required review of existing API integration
|
||||
|
||||
The adapter expects the existing API handler to provide:
|
||||
|
||||
```python
|
||||
handler.need(scope)
|
||||
handler.body()
|
||||
handler.sendj(value, status=200)
|
||||
api.H.do_POST
|
||||
api.main()
|
||||
```
|
||||
|
||||
Confirm these contracts against the branch before merge. If the live API has a
|
||||
different authentication object shape, make the smallest adapter-only change
|
||||
and rerun every test. The core provisioning policy must remain unchanged.
|
||||
|
||||
The API authorization registry must grant `writer:provision` only to the
|
||||
authenticated Owner role. Agents and ordinary writer tokens must not receive
|
||||
this scope.
|
||||
|
||||
## Privilege boundary
|
||||
|
||||
The API service must remain non-root.
|
||||
|
||||
Install a root-owned sudoers rule that allows the API service identity to run
|
||||
only these exact commands with `sudo -n --`:
|
||||
|
||||
```text
|
||||
/usr/local/libexec/aios-grant-signer-adapter
|
||||
/usr/local/libexec/aios-grant-validator
|
||||
/usr/local/libexec/aios-task-writer-provisioner
|
||||
```
|
||||
|
||||
Do not allow:
|
||||
|
||||
```text
|
||||
/bin/sh
|
||||
/bin/bash
|
||||
/usr/bin/env
|
||||
/usr/bin/git
|
||||
wildcard executable paths
|
||||
SETENV
|
||||
arbitrary environment preservation
|
||||
```
|
||||
|
||||
The governed tools themselves must validate their `--grant-dir` and
|
||||
`--result-json` paths. Their binaries must be root-owned, non-symlink, regular,
|
||||
executable and not group/world writable.
|
||||
|
||||
The signer must access its private signing material only through a runtime
|
||||
secret reference. No signing key or token may enter Git, API output, the
|
||||
provisioning receipt or systemd environment text.
|
||||
|
||||
## Runtime paths and permissions
|
||||
|
||||
Create:
|
||||
|
||||
```text
|
||||
/var/lib/aios-gitops/authorized-writer-bridge
|
||||
/var/lib/aios-gitops/authorized-writer-bridge/receipts
|
||||
/var/lib/aios-gitops/authorized-writer-bridge/locks
|
||||
```
|
||||
|
||||
Required properties:
|
||||
|
||||
```yaml
|
||||
owner: API service identity
|
||||
mode: "0700"
|
||||
symlink: false
|
||||
persistent: true
|
||||
```
|
||||
|
||||
The directory contains redacted receipts only. Temporary signed grant
|
||||
directories are deleted after success or failure.
|
||||
|
||||
## Required staging environment
|
||||
|
||||
Configure the API service:
|
||||
|
||||
```text
|
||||
AIOS_GITOPS_REPOSITORY_IDENTITY=aios/aios
|
||||
AIOS_GITOPS_AUTHORITY_GIT_DIR=/data/aios-gitops/repo.git
|
||||
AIOS_GITOPS_AUTHORIZED_WRITER_STATE_ROOT=/var/lib/aios-gitops/authorized-writer-bridge
|
||||
AIOS_GITOPS_GRANT_SIGNER_ADAPTER=/usr/local/libexec/aios-grant-signer-adapter
|
||||
AIOS_GITOPS_GRANT_VALIDATOR=/usr/local/libexec/aios-grant-validator
|
||||
AIOS_GITOPS_TASK_WRITER_PROVISIONER=/usr/local/libexec/aios-task-writer-provisioner
|
||||
AIOS_GITOPS_OWNER_PROVISION_SCOPE=writer:provision
|
||||
AIOS_GITOPS_GOVERNED_USE_SUDO=true
|
||||
AIOS_GITOPS_SUDO_PATH=/usr/bin/sudo
|
||||
```
|
||||
|
||||
Use `aios_authorized_task_writer_api.py` as the API entrypoint. It delegates
|
||||
all pre-existing routes and adds only the new endpoint.
|
||||
|
||||
## Pre-merge tests
|
||||
|
||||
Run from the repository root:
|
||||
|
||||
```bash
|
||||
python3 -m unittest -v tests/test_authorized_task_writer_provisioning.py
|
||||
python3 scripts/smoke_authorized_task_writer_provisioning.py
|
||||
python3 -m py_compile \
|
||||
active-runtime/app/authorized_task_writer_provisioning.py \
|
||||
active-runtime/app/aios_authorized_task_writer_api.py
|
||||
```
|
||||
|
||||
Required result:
|
||||
|
||||
```yaml
|
||||
unit_tests:
|
||||
total: 9
|
||||
failures: 0
|
||||
errors: 0
|
||||
smoke: PASS
|
||||
py_compile: PASS
|
||||
```
|
||||
|
||||
Also run all existing GitOps API and isolated writer tests affected by:
|
||||
|
||||
```text
|
||||
aios_chatgpt_actions_api
|
||||
aios_isolated_writer_api
|
||||
isolated_writer_authz
|
||||
isolated_writer_token_registry
|
||||
single_owner_governance
|
||||
OpenAPI schema validation
|
||||
```
|
||||
|
||||
Any regression blocks merge.
|
||||
|
||||
## Staging API acceptance
|
||||
|
||||
### Negative authentication
|
||||
|
||||
An Agent or non-Owner credential calling the endpoint must receive:
|
||||
|
||||
```yaml
|
||||
http_status: 403
|
||||
error: OWNER_AUTHORIZATION_REQUIRED
|
||||
```
|
||||
|
||||
### Negative scope tests
|
||||
|
||||
Requests enabling any of the following must be denied before signer execution:
|
||||
|
||||
```text
|
||||
production_change_authorized=true
|
||||
tag_change_authorized=true
|
||||
baseline_change_authorized=true
|
||||
main_write_authorized=true
|
||||
allowed_operations containing tag/main/baseline/admin operations
|
||||
missing required denied operation
|
||||
one_time_use=false
|
||||
expiry over 1800 seconds
|
||||
```
|
||||
|
||||
### Drift and conflict tests
|
||||
|
||||
Verify:
|
||||
|
||||
```yaml
|
||||
wrong_base_oid:
|
||||
http_status: 409
|
||||
error: AUTHORIZED_BASE_OID_DRIFT
|
||||
|
||||
existing_unreceipted_target_branch:
|
||||
http_status: 409
|
||||
error: EXISTING_BRANCH_OID_CONFLICT
|
||||
```
|
||||
|
||||
### Governed tool failures
|
||||
|
||||
Independently inject and verify fail-closed behavior for:
|
||||
|
||||
```text
|
||||
signer unavailable
|
||||
signer signature absent
|
||||
validator signature_valid=false
|
||||
validator signer_trusted=false
|
||||
validator plan expired
|
||||
provisioner grant_consumed=false
|
||||
provisioner writer scope enables main/tag/baseline/force push
|
||||
any required negative policy test false
|
||||
```
|
||||
|
||||
None may create or modify a Git ref.
|
||||
|
||||
## Live V2R1C6 provisioning request
|
||||
|
||||
After protected merge and API deployment, authenticate as the Owner and submit
|
||||
exactly:
|
||||
|
||||
```json
|
||||
{
|
||||
"task_id": "V2R1C6_TASK_SCOPED_WRITER_PROVISIONING",
|
||||
"repository": "aios/aios",
|
||||
"base_ref": "refs/heads/main",
|
||||
"base_oid": "875d41c3101093149414292067fd700dc214d4d3",
|
||||
"target_branch": "agent/v2r1c6-mainline-reconciliation-20260805",
|
||||
"owner_authorization_reference": "chat-owner-authorization:v2r1c6:20260806",
|
||||
"one_time_use": true,
|
||||
"expires_in_seconds": 900,
|
||||
"production_change_authorized": false,
|
||||
"tag_change_authorized": false,
|
||||
"baseline_change_authorized": false,
|
||||
"main_write_authorized": false,
|
||||
"allowed_operations": [
|
||||
"create_worktree",
|
||||
"create_target_branch_if_absent",
|
||||
"commit_to_target_branch",
|
||||
"push_target_branch"
|
||||
],
|
||||
"denied_operations": [
|
||||
"direct_main_push",
|
||||
"force_push",
|
||||
"tag_create",
|
||||
"tag_update",
|
||||
"tag_delete",
|
||||
"branch_delete",
|
||||
"repository_admin",
|
||||
"baseline_write",
|
||||
"production_deploy",
|
||||
"production_marker_write",
|
||||
"history_rewrite"
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
This request must be executed by the localhost-only bootstrap instance before
|
||||
the bridge code advances `main`. The endpoint must never infer “current main”.
|
||||
|
||||
If the Agent chooses the alternative merge-first path, it must stop after the
|
||||
merge and obtain an exact Owner amendment for the new merge OID. It must not
|
||||
silently replace the approved OID.
|
||||
|
||||
## Success response
|
||||
|
||||
Require:
|
||||
|
||||
```yaml
|
||||
status: READY_FOR_CODE_AUTHORING
|
||||
grant_consumed: true
|
||||
branch: agent/v2r1c6-mainline-reconciliation-20260805
|
||||
branch_oid: <exact amended authorized base OID>
|
||||
base_oid: <same exact OID>
|
||||
main_unchanged: true
|
||||
|
||||
writer_scope:
|
||||
workspace_role: task-scoped-isolated-writer
|
||||
writes_enabled: true
|
||||
allowed_branch: agent/v2r1c6-mainline-reconciliation-20260805
|
||||
allowed_base_oid: <exact amended authorized base OID>
|
||||
allowed_routes:
|
||||
- POST /api/commit-file
|
||||
allow_main_write: false
|
||||
allow_tag_write: false
|
||||
allow_baseline_write: false
|
||||
allow_force_push: false
|
||||
```
|
||||
|
||||
All seven negative policy results must be true.
|
||||
|
||||
Submit the identical request a second time. It must return the same grant and
|
||||
branch attestation with:
|
||||
|
||||
```yaml
|
||||
idempotent: true
|
||||
```
|
||||
|
||||
It must not run the provisioner again.
|
||||
|
||||
## Production postchecks
|
||||
|
||||
After API deployment and writer provisioning, independently verify:
|
||||
|
||||
```yaml
|
||||
existing_routes_regression: PASS
|
||||
new_endpoint: PASS
|
||||
main_ref: expected reviewed merge commit
|
||||
V2R1C5_tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
|
||||
V2R1C5_peeled_target: aa60e891547abd7e215af7cf2bf3f21fd23541da
|
||||
V2R1C5_baseline_unchanged: true
|
||||
new_release_tag_created: false
|
||||
production_baseline_changed: false
|
||||
```
|
||||
|
||||
The deployment of this control-plane bridge does not authorize a V2R1C6
|
||||
production release. It only enables scoped code authoring.
|
||||
|
||||
## Rollback
|
||||
|
||||
If the new API route fails:
|
||||
|
||||
1. Stop accepting new provisioning calls.
|
||||
2. Restore the previous API entrypoint.
|
||||
3. Restart and verify all existing routes.
|
||||
4. Preserve receipts and logs.
|
||||
5. Revoke any task writer capability already minted.
|
||||
6. Do not delete a branch or rewrite a tag.
|
||||
7. Revert the protected-main bridge commit through an ordinary reviewed revert
|
||||
PR if source rollback is required.
|
||||
|
||||
## Required final Agent report
|
||||
|
||||
```yaml
|
||||
STATUS: COMPLETED | PARTIALLY_COMPLETED | BLOCKED | FAILED
|
||||
|
||||
INTEGRATION:
|
||||
branch:
|
||||
commit:
|
||||
protected_pr:
|
||||
merge_commit:
|
||||
files_changed:
|
||||
|
||||
TESTS:
|
||||
unit:
|
||||
smoke:
|
||||
py_compile:
|
||||
regression:
|
||||
fault_injection:
|
||||
|
||||
DEPLOYMENT:
|
||||
service:
|
||||
entrypoint:
|
||||
runtime_status:
|
||||
endpoint_status:
|
||||
rollback_verified:
|
||||
|
||||
PROVISIONING:
|
||||
owner_authorization_reference:
|
||||
approval_plan_id:
|
||||
grant_id:
|
||||
grant_digest_sha256:
|
||||
signing_key_identity:
|
||||
branch:
|
||||
branch_oid:
|
||||
workspace_path:
|
||||
grant_consumed:
|
||||
idempotent_replay:
|
||||
|
||||
CONSISTENCY:
|
||||
main_oid:
|
||||
V2R1C5_tag_oid:
|
||||
V2R1C5_peeled_target_oid:
|
||||
baseline_version:
|
||||
baseline_changed:
|
||||
tags_changed:
|
||||
|
||||
SECRETS:
|
||||
runtime_secret_reference_used:
|
||||
plaintext_secret_logged:
|
||||
plaintext_secret_committed:
|
||||
|
||||
BLOCKERS:
|
||||
|
||||
GOVERNANCE:
|
||||
force_push_used: false
|
||||
tag_rewritten: false
|
||||
direct_main_push: false
|
||||
secrets_committed: false
|
||||
owner_approval_respected: true
|
||||
```
|
||||
@@ -0,0 +1,401 @@
|
||||
# Agent Deployment Requirements: Owner Authorization Broker V2
|
||||
|
||||
## Objective
|
||||
|
||||
Deploy the audited Owner Authorization Broker that closes the bootstrap gap
|
||||
without issuing a new general-purpose Owner credential and without modifying
|
||||
`/data/aios-gitops/runtime/secrets/gitops.tokens`.
|
||||
|
||||
The broker reuses one existing, non-wildcard Owner credential only to
|
||||
authenticate the Owner identity through one pre-existing exact scope. It then
|
||||
records an immutable task authorization event and directly invokes the
|
||||
existing signed grant -> validator -> one-shot provisioner chain.
|
||||
|
||||
Production deployment of V2R1C6 is **not** authorized by this task.
|
||||
|
||||
## Fixed bindings
|
||||
|
||||
```yaml
|
||||
task_id: V2R1C6_TASK_SCOPED_WRITER_PROVISIONING
|
||||
repository: aios/aios
|
||||
base_ref: refs/heads/main
|
||||
base_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
target_branch: agent/v2r1c6-mainline-reconciliation-20260805
|
||||
production_change_authorized: false
|
||||
tag_change_authorized: false
|
||||
baseline_change_authorized: false
|
||||
main_write_authorized: false
|
||||
```
|
||||
|
||||
The existing V2R1C5 objects are frozen:
|
||||
|
||||
```yaml
|
||||
tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
|
||||
peeled_target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
|
||||
baseline_version: V2R1C5
|
||||
baseline_status: PRODUCTION_DEPLOYED
|
||||
```
|
||||
|
||||
## 1. Package verification
|
||||
|
||||
Verify `MANIFEST.sha256` before installation. Reject any mismatch.
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
python3 -m unittest -v \
|
||||
tests/test_authorized_task_writer_provisioning.py \
|
||||
tests/test_owner_authorization_broker.py
|
||||
|
||||
python3 scripts/smoke_authorized_task_writer_provisioning.py
|
||||
python3 scripts/smoke_owner_authorization_broker.py
|
||||
python3 -m py_compile \
|
||||
active-runtime/app/authorized_task_writer_provisioning.py \
|
||||
active-runtime/app/aios_authorized_task_writer_api.py \
|
||||
active-runtime/app/owner_authorization_broker.py \
|
||||
active-runtime/app/aios_owner_authorization_broker_api.py
|
||||
```
|
||||
|
||||
All checks must pass.
|
||||
|
||||
## 2. Existing Owner credential selection
|
||||
|
||||
Read only the non-secret registry metadata. Select one existing credential
|
||||
that satisfies all of the following:
|
||||
|
||||
```yaml
|
||||
role: owner
|
||||
wildcard_scope: false
|
||||
account: exact known Owner identity
|
||||
contains_exact_intake_scope: true
|
||||
```
|
||||
|
||||
Use one existing exact scope such as `commit:create` or `file:write`. Prefer
|
||||
the narrowest scope already assigned to the intended Owner.
|
||||
|
||||
Do not:
|
||||
|
||||
- use the historical wildcard Owner credential;
|
||||
- add `writer:provision` to any bearer token;
|
||||
- create or modify a bearer credential;
|
||||
- print, copy or commit bearer-token material.
|
||||
|
||||
Record only:
|
||||
|
||||
```yaml
|
||||
owner_account: <non-secret account>
|
||||
credential_id: <non-secret ID, when available>
|
||||
intake_scope: <one exact existing scope>
|
||||
scope_readback_available: true|false
|
||||
```
|
||||
|
||||
If `handler.need()` returns the exact scope set, configure the Owner account
|
||||
allowlist and leave the credential ID allowlist empty.
|
||||
|
||||
If scope metadata is not returned, configure the exact non-secret credential
|
||||
ID allowlist. If neither exact scope metadata nor a stable non-secret
|
||||
credential ID can be proven, stop:
|
||||
|
||||
```yaml
|
||||
STATUS: BLOCKED
|
||||
REASON: OWNER_CREDENTIAL_SCOPE_NOT_PROVABLE
|
||||
```
|
||||
|
||||
## 3. Staging installation
|
||||
|
||||
Install the four application modules in a root-owned staging directory:
|
||||
|
||||
```text
|
||||
authorized_task_writer_provisioning.py
|
||||
aios_authorized_task_writer_api.py
|
||||
owner_authorization_broker.py
|
||||
aios_owner_authorization_broker_api.py
|
||||
```
|
||||
|
||||
The directory and files must not be group/world writable.
|
||||
|
||||
Prepare environment values:
|
||||
|
||||
```yaml
|
||||
AIOS_GITOPS_OWNER_AUTHORIZATION_BROKER_ENABLED: "true"
|
||||
AIOS_GITOPS_OWNER_AUTHORIZATION_INTAKE_SCOPES: <one exact existing scope>
|
||||
AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_IDENTITIES: <exact owner account>
|
||||
AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_CREDENTIAL_IDS: <exact ID or empty>
|
||||
AIOS_GITOPS_OWNER_AUTHORIZATION_MAX_EXPIRY_SECONDS: "900"
|
||||
AIOS_GITOPS_OWNER_AUTHORIZATION_STATE_ROOT:
|
||||
/var/lib/aios-gitops/owner-authorization-broker
|
||||
```
|
||||
|
||||
Use the existing signer, validator and provisioner paths. Do not change their
|
||||
root governance configuration or disable signature checks.
|
||||
|
||||
Start a localhost-only staging instance on a temporary port. Do not replace
|
||||
the production service yet.
|
||||
|
||||
## 4. Authentication fail-closed tests
|
||||
|
||||
The staging endpoint is:
|
||||
|
||||
```text
|
||||
POST /api/governance/owner-authorizations
|
||||
```
|
||||
|
||||
Required tests:
|
||||
|
||||
```yaml
|
||||
unauthenticated:
|
||||
expected: 401
|
||||
|
||||
wrong_role:
|
||||
expected: 403
|
||||
|
||||
wrong_scope:
|
||||
expected: 403
|
||||
|
||||
wildcard_owner:
|
||||
expected: 403
|
||||
error: WILDCARD_OWNER_CREDENTIAL_REJECTED
|
||||
|
||||
unallowlisted_owner:
|
||||
expected: 403
|
||||
error: OWNER_IDENTITY_NOT_ALLOWED
|
||||
|
||||
production_capability_true:
|
||||
expected: 403
|
||||
error: PRODUCTION_CAPABILITY_REJECTED
|
||||
```
|
||||
|
||||
A connection failure, 404 or 500 is not an authorization-policy pass.
|
||||
|
||||
## 5. Formal provisioning request
|
||||
|
||||
Use the selected existing non-wildcard Owner credential through its runtime
|
||||
secret reference. Never place the bearer token in the request body, command
|
||||
line, shell history, output report or Git.
|
||||
|
||||
Request:
|
||||
|
||||
```json
|
||||
{
|
||||
"action": "AUTHORIZE_TASK_WRITER_PROVISIONING",
|
||||
"task_id": "V2R1C6_TASK_SCOPED_WRITER_PROVISIONING",
|
||||
"repository": "aios/aios",
|
||||
"base_ref": "refs/heads/main",
|
||||
"base_oid": "875d41c3101093149414292067fd700dc214d4d3",
|
||||
"target_branch": "agent/v2r1c6-mainline-reconciliation-20260805",
|
||||
"one_time_use": true,
|
||||
"expires_in_seconds": 900,
|
||||
"production_change_authorized": false,
|
||||
"tag_change_authorized": false,
|
||||
"baseline_change_authorized": false,
|
||||
"main_write_authorized": false,
|
||||
"allowed_operations": [
|
||||
"create_worktree",
|
||||
"create_target_branch_if_absent",
|
||||
"commit_to_target_branch",
|
||||
"push_target_branch"
|
||||
],
|
||||
"denied_operations": [
|
||||
"direct_main_push",
|
||||
"force_push",
|
||||
"tag_create",
|
||||
"tag_update",
|
||||
"tag_delete",
|
||||
"branch_delete",
|
||||
"repository_admin",
|
||||
"baseline_write",
|
||||
"production_deploy",
|
||||
"production_marker_write",
|
||||
"history_rewrite"
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
The Owner authorization reference is generated by the broker. The caller must
|
||||
not submit or invent one.
|
||||
|
||||
Expected result:
|
||||
|
||||
```yaml
|
||||
status: READY_FOR_CODE_AUTHORING
|
||||
owner_authorization_event_id: generated
|
||||
owner_authorization_reference: generated
|
||||
owner_authorization_digest_sha256: generated
|
||||
owner_authorization_consumed: true
|
||||
approval_plan_id: generated
|
||||
grant_digest_sha256: generated
|
||||
grant_consumed: true
|
||||
|
||||
branch_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
|
||||
writer_scope:
|
||||
workspace_role: task-scoped-isolated-writer
|
||||
writes_enabled: true
|
||||
allowed_branch: agent/v2r1c6-mainline-reconciliation-20260805
|
||||
allowed_base_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
allow_main_write: false
|
||||
allow_tag_write: false
|
||||
allow_baseline_write: false
|
||||
allow_force_push: false
|
||||
```
|
||||
|
||||
## 6. Independent post-provisioning verification
|
||||
|
||||
Verify the Authority ref:
|
||||
|
||||
```bash
|
||||
git --git-dir=/data/aios-gitops/repo.git rev-parse \
|
||||
refs/heads/agent/v2r1c6-mainline-reconciliation-20260805
|
||||
```
|
||||
|
||||
It must equal:
|
||||
|
||||
```text
|
||||
875d41c3101093149414292067fd700dc214d4d3
|
||||
```
|
||||
|
||||
Verify `main` remains unchanged, V2R1C5 tag object and peeled target remain
|
||||
unchanged, and the Production Baseline remains V2R1C5.
|
||||
|
||||
Verify the broker audit event under:
|
||||
|
||||
```text
|
||||
/var/lib/aios-gitops/owner-authorization-broker/events/
|
||||
```
|
||||
|
||||
Requirements:
|
||||
|
||||
```yaml
|
||||
status: CONSUMED
|
||||
wildcard_scope_used: false
|
||||
grant_consumed: true
|
||||
permissions:
|
||||
directory: "0700"
|
||||
json_files: "0600"
|
||||
```
|
||||
|
||||
Do not return bearer-token material in the report.
|
||||
|
||||
## 7. Commit the broker through the new writer
|
||||
|
||||
After `READY_FOR_CODE_AUTHORING`, use only the writer's
|
||||
`POST /api/commit-file` route to put this code bundle on:
|
||||
|
||||
```text
|
||||
agent/v2r1c6-mainline-reconciliation-20260805
|
||||
```
|
||||
|
||||
Commit the bridge and broker as separate intentional commits when practical:
|
||||
|
||||
1. Owner-authorized task-writer bridge.
|
||||
2. Audited Owner authorization broker and deployment docs.
|
||||
|
||||
Do not merge to `main` directly. Create a protected PR after branch commits
|
||||
and tests are complete.
|
||||
|
||||
## 8. Permanent service deployment
|
||||
|
||||
Only after protected review and merge:
|
||||
|
||||
1. Install the reviewed files from the merge commit.
|
||||
2. Apply a reviewed systemd drop-in based on the provided example.
|
||||
3. Start the wrapper entrypoint:
|
||||
`aios_owner_authorization_broker_api.py`.
|
||||
4. Verify all existing API routes still work.
|
||||
5. Verify the broker remains localhost/reverse-proxy constrained as intended.
|
||||
6. Re-run authentication and policy tests.
|
||||
7. Remove the temporary staging instance.
|
||||
|
||||
This permanent bridge deployment does not authorize a V2R1C6 production tag,
|
||||
Baseline update or application deployment.
|
||||
|
||||
## 9. Fail-closed conditions
|
||||
|
||||
Stop with `BLOCKED` for any of the following:
|
||||
|
||||
- Authority `main` no longer equals the fixed base OID.
|
||||
- Target branch exists at a different OID.
|
||||
- Only a wildcard Owner credential can authenticate.
|
||||
- Exact credential scope cannot be proven.
|
||||
- Owner identity is not explicitly allow-listed.
|
||||
- Signer, validator or provisioner self-test fails.
|
||||
- Grant is not marked one-time and consumed.
|
||||
- Writer allows main, tag, Baseline, force-push or branch-delete operations.
|
||||
- Audit event contains sensitive material.
|
||||
- V2R1C5 tag or Baseline changes.
|
||||
|
||||
## 10. Required Agent result
|
||||
|
||||
```yaml
|
||||
STATUS: READY_FOR_CODE_AUTHORING | BLOCKED | FAILED
|
||||
|
||||
PACKAGE:
|
||||
manifest_verified:
|
||||
unit_tests:
|
||||
smoke_tests:
|
||||
py_compile:
|
||||
|
||||
OWNER_CREDENTIAL:
|
||||
account:
|
||||
credential_id:
|
||||
intake_scope:
|
||||
exact_scope_proven:
|
||||
wildcard_used: false
|
||||
token_logged: false
|
||||
|
||||
BROKER:
|
||||
staging_listener:
|
||||
endpoint_status:
|
||||
event_id:
|
||||
authorization_reference:
|
||||
authorization_digest_sha256:
|
||||
event_consumed:
|
||||
audit_permissions_valid:
|
||||
|
||||
GRANT:
|
||||
approval_plan_id:
|
||||
grant_digest_sha256:
|
||||
signer_identity:
|
||||
signature_valid:
|
||||
one_time_use:
|
||||
consumed:
|
||||
|
||||
BRANCH:
|
||||
name:
|
||||
oid:
|
||||
base_oid:
|
||||
ref_exists:
|
||||
worktree_path:
|
||||
worktree_clean:
|
||||
|
||||
WRITER:
|
||||
status:
|
||||
writes_enabled:
|
||||
allowed_branch:
|
||||
allowed_base_oid:
|
||||
allowed_routes:
|
||||
main_write_denied:
|
||||
tag_write_denied:
|
||||
baseline_write_denied:
|
||||
force_push_denied:
|
||||
|
||||
POSTCHECK:
|
||||
main_unchanged:
|
||||
V2R1C5_tag_unchanged:
|
||||
baseline_unchanged:
|
||||
|
||||
REPOSITORY_INTEGRATION:
|
||||
commit_oids:
|
||||
protected_pr:
|
||||
merged:
|
||||
permanent_bridge_deployed:
|
||||
|
||||
BLOCKERS:
|
||||
|
||||
GOVERNANCE:
|
||||
force_push_used: false
|
||||
tag_rewritten: false
|
||||
direct_main_push: false
|
||||
secrets_committed: false
|
||||
owner_approval_respected: true
|
||||
```
|
||||
@@ -0,0 +1,562 @@
|
||||
# Agent execution requirements: V2R1C6 task identity overlay
|
||||
|
||||
## Required result
|
||||
|
||||
The Agent must return one of:
|
||||
|
||||
- `READY_FOR_CODE_AUTHORING`
|
||||
- `BLOCKED`
|
||||
- `FAILED`
|
||||
|
||||
The Agent may not report success until the task branch, isolated worktree and
|
||||
task writer are independently verified.
|
||||
|
||||
This stage is **not** a production deployment. It must not modify `main`,
|
||||
V2R1C5, tags, Registry, Production Baseline or production services.
|
||||
|
||||
## Fixed authority
|
||||
|
||||
```yaml
|
||||
task_id: V2R1C6_TASK_SCOPED_WRITER_PROVISIONING
|
||||
repository: aios/aios
|
||||
base_ref: refs/heads/main
|
||||
base_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
target_branch: agent/v2r1c6-mainline-reconciliation-20260805
|
||||
owner_identity: aiman
|
||||
one_time_use: true
|
||||
maximum_ttl_seconds: 900
|
||||
production_change_authorized: false
|
||||
tag_change_authorized: false
|
||||
baseline_change_authorized: false
|
||||
main_write_authorized: false
|
||||
```
|
||||
|
||||
## 1. Verify package
|
||||
|
||||
Verify the externally supplied package against the published SHA-256 values and
|
||||
then verify every entry in `MANIFEST.sha256`.
|
||||
|
||||
Do not synthesize a missing archive. Use either the verified ZIP or TAR.GZ.
|
||||
|
||||
Required checks:
|
||||
|
||||
```yaml
|
||||
package_hash_match: true
|
||||
manifest_entries_match: true
|
||||
unit_tests_pass: true
|
||||
smoke_tests_pass: true
|
||||
py_compile_pass: true
|
||||
```
|
||||
|
||||
## 2. Create root-owned staging
|
||||
|
||||
Extract to a fresh directory such as:
|
||||
|
||||
```text
|
||||
/var/lib/aios-gitops/staging/v2r1c6-task-identity-overlay-<nonce>
|
||||
```
|
||||
|
||||
Requirements:
|
||||
|
||||
```yaml
|
||||
owner: root
|
||||
group: root
|
||||
directory_mode: "0700"
|
||||
files_not_world_writable: true
|
||||
symlinks_rejected: true
|
||||
```
|
||||
|
||||
Do not overwrite the active runtime tree.
|
||||
|
||||
## 3. Re-run target-host tests
|
||||
|
||||
From the staging root:
|
||||
|
||||
```bash
|
||||
python3 -m unittest discover -s tests -v
|
||||
python3 scripts/smoke_authorized_task_writer_provisioning.py
|
||||
python3 scripts/smoke_owner_authorization_broker.py
|
||||
python3 scripts/smoke_task_identity_overlay.py
|
||||
python3 -m py_compile \
|
||||
active-runtime/app/authorized_task_writer_provisioning.py \
|
||||
active-runtime/app/owner_authorization_broker.py \
|
||||
active-runtime/app/task_identity_overlay.py \
|
||||
active-runtime/app/aios_authorized_task_writer_api.py \
|
||||
active-runtime/app/aios_owner_authorization_broker_api.py \
|
||||
active-runtime/app/aios_task_identity_overlay_api.py \
|
||||
active-runtime/app/aios_task_identity_overlay_cli.py \
|
||||
scripts/call_task_identity_overlay.py
|
||||
```
|
||||
|
||||
Any failure is `BLOCKED`; do not proceed.
|
||||
|
||||
## 4. Prestart Git and production freeze checks
|
||||
|
||||
Read from the authority repository:
|
||||
|
||||
```bash
|
||||
git --git-dir=/data/aios-gitops/repo.git rev-parse refs/heads/main
|
||||
git --git-dir=/data/aios-gitops/repo.git \
|
||||
show-ref --verify --quiet \
|
||||
refs/heads/agent/v2r1c6-mainline-reconciliation-20260805
|
||||
git --git-dir=/data/aios-gitops/repo.git rev-parse refs/tags/V2R1C5
|
||||
git --git-dir=/data/aios-gitops/repo.git rev-parse 'refs/tags/V2R1C5^{}'
|
||||
```
|
||||
|
||||
Expected:
|
||||
|
||||
```yaml
|
||||
main_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
target_branch_exists: false
|
||||
V2R1C5_tag_oid: 9e65bd59baea392294c0f253046d3ab116f63145
|
||||
V2R1C5_peeled_target: aa60e891547abd7e215af7cf2bf3f21fd23541da
|
||||
```
|
||||
|
||||
Read Baseline and require:
|
||||
|
||||
```yaml
|
||||
version: V2R1C5
|
||||
status: PRODUCTION_DEPLOYED
|
||||
target_oid: aa60e891547abd7e215af7cf2bf3f21fd23541da
|
||||
evidence_closure_oid: 5e2cf8276f5093f3352b9a3252c701a44c5ab807
|
||||
```
|
||||
|
||||
If `main` has drifted, return:
|
||||
|
||||
```yaml
|
||||
STATUS: MANUAL_OWNER_REVIEW_REQUIRED
|
||||
REASON: AUTHORIZED_BASE_OID_DRIFT
|
||||
```
|
||||
|
||||
If the target branch already exists at another OID, return:
|
||||
|
||||
```yaml
|
||||
STATUS: MANUAL_OWNER_REVIEW_REQUIRED
|
||||
REASON: EXISTING_BRANCH_OID_CONFLICT
|
||||
```
|
||||
|
||||
Do not delete, reset or force-push the branch.
|
||||
|
||||
## 5. Discover active secret references
|
||||
|
||||
The overlay does not read or modify `gitops.tokens`, but its issuer must compare
|
||||
the new random secret against all active bearer secret references.
|
||||
|
||||
Discover references without printing secret contents. At minimum include the
|
||||
currently active ChatGPT/GitOps bearer secret reference and any other bearer
|
||||
files consumed by the active API.
|
||||
|
||||
Pass them as a comma-separated list in:
|
||||
|
||||
```text
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_COLLISION_SECRET_REFS
|
||||
```
|
||||
|
||||
Evidence must contain only paths and SHA-256 match counts, not token values.
|
||||
|
||||
If active secret references cannot be enumerated, return:
|
||||
|
||||
```yaml
|
||||
STATUS: BLOCKED
|
||||
REASON: ACTIVE_SECRET_REFERENCE_SET_UNRESOLVED
|
||||
```
|
||||
|
||||
## 6. Install the transient systemd service
|
||||
|
||||
Use the provided template:
|
||||
|
||||
```text
|
||||
deploy/systemd/aios-v2r1c6-task-identity-overlay.service.example
|
||||
```
|
||||
|
||||
Substitute only:
|
||||
|
||||
- verified root-owned staging directory;
|
||||
- verified active secret-ref path list.
|
||||
|
||||
Do not change task ID, repository, base OID, target branch or denied
|
||||
capabilities.
|
||||
|
||||
The service must listen only on:
|
||||
|
||||
```text
|
||||
127.0.0.1:19864
|
||||
```
|
||||
|
||||
Before start, run:
|
||||
|
||||
```bash
|
||||
systemd-analyze verify \
|
||||
/etc/systemd/system/aios-v2r1c6-task-identity-overlay.service
|
||||
```
|
||||
|
||||
Then:
|
||||
|
||||
```bash
|
||||
sudo systemctl daemon-reload
|
||||
sudo systemctl start aios-v2r1c6-task-identity-overlay.service
|
||||
```
|
||||
|
||||
Confirm:
|
||||
|
||||
```bash
|
||||
curl --fail --silent http://127.0.0.1:19864/healthz
|
||||
```
|
||||
|
||||
Expected:
|
||||
|
||||
```yaml
|
||||
service: aios-task-identity-overlay
|
||||
status: active
|
||||
global_token_registry_used: false
|
||||
loopback_only: true
|
||||
```
|
||||
|
||||
Do not expose the port externally.
|
||||
|
||||
## 7. Issue the one-time overlay
|
||||
|
||||
Use the root-only CLI. The authorization assertion is an audit label for this
|
||||
already approved Owner task; it must not be described as an external signed
|
||||
event.
|
||||
|
||||
Example:
|
||||
|
||||
```bash
|
||||
sudo env \
|
||||
PYTHONPATH=<staging>/active-runtime/app \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_STATE_ROOT=/var/lib/aios-gitops/task-identity-overlays \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_SECRET_ROOT=/run/aios-gitops/task-identity-overlays \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_TASK_ID=V2R1C6_TASK_SCOPED_WRITER_PROVISIONING \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_OWNER_IDENTITY=aiman \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_BASE_REF=refs/heads/main \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_BASE_OID=875d41c3101093149414292067fd700dc214d4d3 \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_TARGET_BRANCH=agent/v2r1c6-mainline-reconciliation-20260805 \
|
||||
AIOS_GITOPS_IDENTITY_OVERLAY_COLLISION_SECRET_REFS=<verified-secret-ref-list> \
|
||||
python3 <staging>/active-runtime/app/aios_task_identity_overlay_cli.py \
|
||||
issue \
|
||||
--ttl-seconds 900 \
|
||||
--authorization-assertion-ref owner-session:V2R1C6:approved-20260806 \
|
||||
--operator-identity <audited-agent-identity> \
|
||||
--result-json /run/aios-gitops/v2r1c6-overlay-issued.json
|
||||
```
|
||||
|
||||
The result must contain:
|
||||
|
||||
```yaml
|
||||
status: OVERLAY_ACTIVE
|
||||
idempotent: false
|
||||
overlay_id: present
|
||||
secret_ref: under /run/aios-gitops/task-identity-overlays
|
||||
expires_at: within 900 seconds
|
||||
```
|
||||
|
||||
It must not contain a token.
|
||||
|
||||
Verify:
|
||||
|
||||
```yaml
|
||||
secret_file_mode: "0600"
|
||||
metadata_contains_raw_token: false
|
||||
token_hash_unique_across_configured_secret_refs: true
|
||||
```
|
||||
|
||||
## 8. Negative tests
|
||||
|
||||
Before the valid request:
|
||||
|
||||
1. No Authorization header must return HTTP 401.
|
||||
2. A random wrong bearer must return HTTP 401.
|
||||
3. A request with `production_change_authorized=true` must be rejected.
|
||||
4. A request with another base OID or branch must be rejected.
|
||||
5. The valid overlay must remain `ACTIVE` after pre-auth request-validation
|
||||
failures.
|
||||
|
||||
Do not use the global Owner or ChatGPT bearer credential for this endpoint.
|
||||
|
||||
## 9. Send the valid request
|
||||
|
||||
Use:
|
||||
|
||||
```text
|
||||
deploy/v2r1c6-task-writer-authorization-request.json
|
||||
```
|
||||
|
||||
Use the provided client so the bearer is not placed in argv, shell history or
|
||||
logs:
|
||||
|
||||
```bash
|
||||
sudo python3 <staging>/scripts/call_task_identity_overlay.py \
|
||||
--secret-ref <secret_ref_from_issue_result> \
|
||||
--request-json <staging>/deploy/v2r1c6-task-writer-authorization-request.json \
|
||||
--url http://127.0.0.1:19864/api/governance/owner-authorizations \
|
||||
--result-json /var/lib/aios-gitops/v2r1c6-overlay-provision-result.json
|
||||
```
|
||||
|
||||
Required result:
|
||||
|
||||
```yaml
|
||||
http_status: 200
|
||||
status: READY_FOR_CODE_AUTHORING
|
||||
owner_authorization_consumed: true
|
||||
grant_consumed: true
|
||||
identity_overlay_consumed: true
|
||||
identity_overlay_secret_removed: true
|
||||
branch: agent/v2r1c6-mainline-reconciliation-20260805
|
||||
branch_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
```
|
||||
|
||||
The result must not include:
|
||||
|
||||
- bearer token;
|
||||
- private key;
|
||||
- signer secret;
|
||||
- raw signature;
|
||||
- credential value.
|
||||
|
||||
## 10. Independent acceptance
|
||||
|
||||
Verify the branch:
|
||||
|
||||
```bash
|
||||
git --git-dir=/data/aios-gitops/repo.git \
|
||||
rev-parse refs/heads/agent/v2r1c6-mainline-reconciliation-20260805
|
||||
```
|
||||
|
||||
It must equal:
|
||||
|
||||
```text
|
||||
875d41c3101093149414292067fd700dc214d4d3
|
||||
```
|
||||
|
||||
Verify worktree evidence returned by the provisioner:
|
||||
|
||||
```yaml
|
||||
branch: agent/v2r1c6-mainline-reconciliation-20260805
|
||||
head_oid: 875d41c3101093149414292067fd700dc214d4d3
|
||||
detached_head: false
|
||||
worktree_clean: true
|
||||
writer_status: active
|
||||
writes_enabled: true
|
||||
allowed_routes:
|
||||
- POST /api/commit-file
|
||||
allow_main_write: false
|
||||
allow_tag_write: false
|
||||
allow_baseline_write: false
|
||||
allow_force_push: false
|
||||
```
|
||||
|
||||
Run policy negative tests against the task writer and require explicit policy
|
||||
denials for:
|
||||
|
||||
- main write;
|
||||
- another branch;
|
||||
- tag create/update;
|
||||
- Baseline write;
|
||||
- force push;
|
||||
- branch delete.
|
||||
|
||||
Network errors, 404, 500 and stopped-service failures do not count as policy
|
||||
denials.
|
||||
|
||||
## 11. Stop and clean up the overlay
|
||||
|
||||
After `READY_FOR_CODE_AUTHORING`:
|
||||
|
||||
```bash
|
||||
sudo systemctl stop aios-v2r1c6-task-identity-overlay.service
|
||||
sudo systemctl disable aios-v2r1c6-task-identity-overlay.service || true
|
||||
sudo rm -f /etc/systemd/system/aios-v2r1c6-task-identity-overlay.service
|
||||
sudo systemctl daemon-reload
|
||||
```
|
||||
|
||||
Verify:
|
||||
|
||||
```yaml
|
||||
overlay_listener_stopped: true
|
||||
overlay_secret_removed: true
|
||||
global_token_registry_unchanged: true
|
||||
disabled_owner_record_unchanged: true
|
||||
active_chatgpt_bot_record_unchanged: true
|
||||
audit_metadata_retained: true
|
||||
```
|
||||
|
||||
The root-owned staging directory may be retained until the code is committed,
|
||||
then removed after checksum-confirmed repository integration.
|
||||
|
||||
## 12. Commit the developed code through the task writer
|
||||
|
||||
Only after writer acceptance, use `POST /api/commit-file` to commit the
|
||||
verified package contents to:
|
||||
|
||||
```text
|
||||
agent/v2r1c6-mainline-reconciliation-20260805
|
||||
```
|
||||
|
||||
Commit in reviewable groups:
|
||||
|
||||
1. authorized task-writer bridge;
|
||||
2. Owner authorization broker;
|
||||
3. task identity overlay;
|
||||
4. tests, docs, OpenAPI and deployment templates.
|
||||
|
||||
Do not include:
|
||||
|
||||
- package archives;
|
||||
- runtime tokens;
|
||||
- `/run` or `/var/lib` state;
|
||||
- test result files containing host paths;
|
||||
- secret references containing values;
|
||||
- generated credentials.
|
||||
|
||||
Run the complete 40-test suite from the branch after commits.
|
||||
|
||||
## 13. Protected PR
|
||||
|
||||
Create a protected PR from:
|
||||
|
||||
```text
|
||||
agent/v2r1c6-mainline-reconciliation-20260805
|
||||
```
|
||||
|
||||
to:
|
||||
|
||||
```text
|
||||
main
|
||||
```
|
||||
|
||||
The PR must state:
|
||||
|
||||
- this change closes Owner authorization bootstrap gaps;
|
||||
- the overlay is localhost-only and one-time;
|
||||
- the global token registry is not modified;
|
||||
- no production release is authorized;
|
||||
- V2R1C5 tag and Baseline remain unchanged.
|
||||
|
||||
The Agent must not merge without the repository's normal protected review.
|
||||
|
||||
## 14. Required Agent report
|
||||
|
||||
```yaml
|
||||
STATUS:
|
||||
READY_FOR_CODE_AUTHORING | BLOCKED | FAILED
|
||||
|
||||
PACKAGE:
|
||||
zip_sha256:
|
||||
tar_gz_sha256:
|
||||
manifest_entries:
|
||||
manifest_matched:
|
||||
|
||||
TESTS:
|
||||
unit_total:
|
||||
unit_passed:
|
||||
smoke_bridge:
|
||||
smoke_broker:
|
||||
smoke_overlay:
|
||||
py_compile:
|
||||
|
||||
PRESTART:
|
||||
main_oid:
|
||||
target_branch_previously_absent:
|
||||
V2R1C5_tag_oid:
|
||||
V2R1C5_peeled_target:
|
||||
baseline_unchanged:
|
||||
|
||||
OVERLAY:
|
||||
overlay_id:
|
||||
status:
|
||||
secret_ref:
|
||||
secret_file_mode:
|
||||
token_hash_unique:
|
||||
global_registry_used: false
|
||||
listener:
|
||||
expires_at:
|
||||
consumed:
|
||||
secret_removed:
|
||||
|
||||
NEGATIVE_TESTS:
|
||||
unauthenticated_401:
|
||||
wrong_token_401:
|
||||
production_capability_denied:
|
||||
wrong_base_denied:
|
||||
wrong_branch_denied:
|
||||
|
||||
OWNER_AUTHORIZATION:
|
||||
event_id:
|
||||
reference:
|
||||
consumed:
|
||||
|
||||
GRANT:
|
||||
approval_plan_id:
|
||||
grant_id:
|
||||
grant_digest_sha256:
|
||||
signature_valid:
|
||||
consumed:
|
||||
|
||||
BRANCH:
|
||||
name:
|
||||
oid:
|
||||
base_oid:
|
||||
ref_exists:
|
||||
worktree_path:
|
||||
worktree_clean:
|
||||
|
||||
WRITER:
|
||||
status:
|
||||
writes_enabled:
|
||||
allowed_branch:
|
||||
allowed_base_oid:
|
||||
allowed_routes:
|
||||
main_write_denied:
|
||||
tag_write_denied:
|
||||
baseline_write_denied:
|
||||
force_push_denied:
|
||||
|
||||
REPOSITORY_INTEGRATION:
|
||||
commits:
|
||||
tests_after_commit:
|
||||
protected_pr:
|
||||
merged: false
|
||||
|
||||
POSTCHECK:
|
||||
main_unchanged:
|
||||
V2R1C5_tag_unchanged:
|
||||
baseline_unchanged:
|
||||
global_token_registry_unchanged:
|
||||
overlay_listener_stopped:
|
||||
overlay_secret_removed:
|
||||
|
||||
SECRETS:
|
||||
plaintext_logged: false
|
||||
plaintext_committed: false
|
||||
|
||||
BLOCKERS:
|
||||
|
||||
GOVERNANCE:
|
||||
force_push_used: false
|
||||
tag_rewritten: false
|
||||
direct_main_push: false
|
||||
secrets_committed: false
|
||||
owner_approval_respected: true
|
||||
```
|
||||
|
||||
## Fail-closed conditions
|
||||
|
||||
Return `BLOCKED` and stop on any of:
|
||||
|
||||
- authoritative main OID drift;
|
||||
- target branch conflict;
|
||||
- inability to enumerate active secret references;
|
||||
- secret hash collision;
|
||||
- overlay not bound to the exact task/base/branch;
|
||||
- non-loopback listener;
|
||||
- raw secret in result or logs;
|
||||
- Owner Authorization Broker event not created;
|
||||
- signer/validator/provisioner failure;
|
||||
- grant not consumed;
|
||||
- branch OID mismatch;
|
||||
- writer exposes main/tag/Baseline/force-push permissions;
|
||||
- V2R1C5 tag or Baseline changes.
|
||||
|
||||
Never fall back to the shared `gitops-write-bot.token`, a wildcard credential,
|
||||
manual `gitops.tokens` edits or a direct Git ref write.
|
||||
@@ -0,0 +1,10 @@
|
||||
bec7da1adb75bf5feaa63c60ec6d03adf15d7508742a486207033d000f72d4ff AGENT_DEPLOYMENT_REQUIREMENTS.md
|
||||
251b46e51ce09aa2fd843bee48ef24a5608f31d24c599841f086ceb25c1a1715 README.md
|
||||
783f68ec4f00a11d43ceed536196bfedccaf6614f6db9805f7b36d24e5fa7bc2 TEST_RESULTS.json
|
||||
c4b24b65195077716983acdc8611f705324413a74453858994ba51541957afd4 active-runtime/app/aios_authorized_task_writer_api.py
|
||||
8a1935fa098d47ac02ce51bbd9fd5fad7cf9ab9374ea3de5f630679b96681d84 active-runtime/app/authorized_task_writer_provisioning.py
|
||||
a05d4e8038fdb866ce17d4fb8a54798a268a1e8d44ff2cbc559069fa6ab2a667 deploy/systemd/aios-gitops-model-api-authorized-writer-bridge.conf.example
|
||||
a60dac51802bff67c2cfff61acdeb0a3a05d74a4f6cb47e3f78295ceb5c6acd9 docs/gitops/authorized-task-writer-provisioning.md
|
||||
2690f76452bceddda90c728278c600bcebd533db24776e2966423c5a8655e4b5 docs/gitops/openapi-authorized-task-writer-fragment.yaml
|
||||
54e2845d2c3c026323ad45515e082d661e3b461feb3bfefedf5adc52db2d7b78 scripts/smoke_authorized_task_writer_provisioning.py
|
||||
3cce2b744326fe12b89bcad3cd352c77738950964bf8519e72cb5e9c7a5dfbfc tests/test_authorized_task_writer_provisioning.py
|
||||
@@ -1,11 +0,0 @@
|
||||
# AIOS Codex automatic command watcher
|
||||
|
||||
The watcher polls the governed `commands/active` queue without a chat trigger. It uses SQLite transactions for exclusive leases, records the exact command digest, rejects contract drift, retries transient failures, dead-letters exhausted work, and resumes from the last durable phase so an end-event retry does not execute a work unit twice.
|
||||
|
||||
Commands are JSON documents validated by `schemas/codex-command.schema.json`. `acceptance_probe` is the only built-in action and has no external side effect. Production `codex` work requires an administrator-provisioned absolute executor path; the instruction is passed on standard input, never argv or environment. The executor receives a sanitized environment and must obtain credentials through its approved file or exec provider. If the executor is absent, the task fails closed and follows the retry/dead-letter policy.
|
||||
|
||||
The watcher provides at-most-once execution. It writes the `EXECUTING` phase before launching an external executor; if the host dies after an external effect but before a result is durably recorded, recovery does not replay the work and instead dead-letters the ambiguity for human review. Start and end event JSON is persisted before transmission, so response-loss retries reuse the exact event ID and payload and are deduplicated by the Gateway.
|
||||
|
||||
Lifecycle evidence is appended to `/var/log/aios-codex-watcher/audit.jsonl` as `CODEX_AUTO_CLAIM`, `TASK_STARTED`, `TASK_EXECUTED`, `TASK_ENDED`, and `EVENT_POSTED`. Inputs, tokens, stdout, and stderr are not logged; only result digests are retained.
|
||||
|
||||
Install from a reviewed commit with `sudo scripts/install_aios_codex_watcher.sh`. The installer creates a content-addressed release, atomically updates `current`, writes a receipt, and enables the five-second systemd timer. The existing Gateway inbound token file is referenced in place and never copied.
|
||||
@@ -1,107 +0,0 @@
|
||||
# AIOS Orchestrator Gateway v0.2
|
||||
|
||||
This component turns the current passive GPT orchestration pattern into a
|
||||
durable, unattended loop:
|
||||
|
||||
```text
|
||||
Gitea/OpenClaw/Codex event
|
||||
-> HTTP event endpoint or polled file inbox
|
||||
-> durable SQLite state machine
|
||||
-> Workspace Agent API trigger
|
||||
-> strict callback decision
|
||||
-> Responses API background fallback and polling
|
||||
-> OpenClaw/Codex dispatch queues
|
||||
-> start/end/result events
|
||||
-> next orchestration cycle
|
||||
```
|
||||
|
||||
## Reliability mechanisms
|
||||
|
||||
The gateway does not depend on one timer, webhook or model call:
|
||||
|
||||
- HTTP event ingestion.
|
||||
- Periodic file-inbox polling for missed webhooks and offline producers.
|
||||
- Local bare-Git ref polling for `main`, governance, patch and result refs.
|
||||
- Workspace Agent retries with a stable event `Idempotency-Key`.
|
||||
- Workspace Agent callback timeout and Responses API background fallback.
|
||||
- Responses status polling until completion or fail-closed terminal status.
|
||||
- SQLite optimistic state versions, idempotency records and processing leases.
|
||||
- Exponential retry with a maximum retry count and dead-letter state.
|
||||
- Same-blocker and maximum-hop guards to stop non-progress loops.
|
||||
- A systemd timer runs `--poll-once` as an independent reliability watchdog.
|
||||
|
||||
Workspace Agent trigger runs are asynchronous and do not expose a retrievable
|
||||
final response. The central Workspace Agent must therefore call the
|
||||
`submit_orchestration_decision` action.
|
||||
|
||||
## OpenClaw synchronization
|
||||
|
||||
Every lifecycle stage is durably written to the OpenClaw synchronization queue:
|
||||
|
||||
- `TASK_DISPATCHED`
|
||||
- `TASK_STARTED`
|
||||
- `TASK_ENDED`
|
||||
- `DECISION_APPLIED`
|
||||
- `PROJECT_SUMMARY`
|
||||
- `PROJECT_COMPLETED`
|
||||
|
||||
An optional authenticated OpenClaw HTTP endpoint can receive the same records.
|
||||
A failed HTTP delivery remains in the lifecycle retry queue. OpenClaw remains
|
||||
the default project-status synchronizer and authoritative progress presenter.
|
||||
|
||||
## Agent execution contract
|
||||
|
||||
Each dispatched JSON envelope contains:
|
||||
|
||||
- exact contract commit;
|
||||
- source event;
|
||||
- clean base commit;
|
||||
- primary and fallback agent;
|
||||
- allowed paths;
|
||||
- required checks;
|
||||
- forbidden operations;
|
||||
- completion event callback format.
|
||||
|
||||
OpenClaw and Codex must send a `work_unit_started` event before execution and a
|
||||
`work_unit_completed`, `work_unit_blocked`, or `work_unit_failed` event when
|
||||
they stop. This guarantees that OpenClaw can synchronize every task start,
|
||||
finish, and overall project summary.
|
||||
|
||||
## Security
|
||||
|
||||
- Model and callback credentials are read only from root-owned secret files.
|
||||
- Credentials never enter Git, dispatch payloads or logs.
|
||||
- The gateway runs as a dedicated unprivileged user.
|
||||
- Dispatch and sync paths are protected against traversal and symlink targets.
|
||||
- All state changes require the exact contract commit and current state version.
|
||||
- Production evidence, credentials and approvals stay fail-closed.
|
||||
- Git history operations remain controlled by the committed governance contract.
|
||||
|
||||
## Deployment sequence
|
||||
|
||||
1. Apply this source bundle to a clean append-only branch.
|
||||
2. Run unit, repository, shell, JSON, systemd and Gitleaks checks.
|
||||
3. Configure one or both model channels:
|
||||
- published Workspace Agent API channel and Workspace Agent access token;
|
||||
- Responses API key and approved fallback model.
|
||||
4. Publish the decision callback as a Workspace Agent action or MCP tool.
|
||||
5. Install the service through `scripts/install_aios_orchestrator_gateway.sh`.
|
||||
6. Run `scripts/verify_aios_orchestrator_gateway.sh`.
|
||||
7. Submit a harmless event and verify:
|
||||
- trigger acceptance;
|
||||
- strict decision callback;
|
||||
- dispatch file;
|
||||
- OpenClaw task-start/task-end/project-summary synchronization;
|
||||
- duplicate idempotency;
|
||||
- polling recovery after suppressing the HTTP webhook.
|
||||
|
||||
The installer copies an explicit gateway-only allowlist into a release directory
|
||||
named by its SHA-256 digest, atomically updates `/opt/aios-orchestrator-gateway/current`,
|
||||
and persists `/var/lib/aios-orchestrator-gateway/install-receipt.json` with the
|
||||
current and previous release. `--dry-run` performs source validation and emits
|
||||
`AIOS_ORCHESTRATOR_INSTALL_DRY_RUN=PASS` without changing installed state.
|
||||
|
||||
Rollback reads that root-owned `0600` receipt, verifies both release directory
|
||||
names and `SOURCE_DIGEST` files, coordinates the gateway and poll units, and
|
||||
atomically switches `current` to the previous release. Repeating the same
|
||||
rollback is a no-op and emits `NOOP_ALREADY_ROLLED_BACK`.
|
||||
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"git_branch_created": false,
|
||||
"git_commit_created": false,
|
||||
"production_mutation": false,
|
||||
"py_compile": {
|
||||
"files": [
|
||||
"active-runtime/app/authorized_task_writer_provisioning.py",
|
||||
"active-runtime/app/aios_authorized_task_writer_api.py"
|
||||
],
|
||||
"status": "PASS"
|
||||
},
|
||||
"schema": "aios.authorized-task-writer-bridge-test-report.v1",
|
||||
"secrets_included": false,
|
||||
"smoke": {
|
||||
"command": "python3 scripts/smoke_authorized_task_writer_provisioning.py",
|
||||
"status": "PASS"
|
||||
},
|
||||
"status": "PASS",
|
||||
"unit_tests": {
|
||||
"command": "python3 -m unittest -v tests/test_authorized_task_writer_provisioning.py",
|
||||
"errors": 0,
|
||||
"failures": 0,
|
||||
"total": 9
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,201 @@
|
||||
"""Fail-closed Agent Pull Runner primitives for AIOS autonomy v1.
|
||||
|
||||
The runner owns task discovery and reporting only. It never accepts shell
|
||||
strings: executors receive argv, an allowlisted cwd and an allowlisted env.
|
||||
Durable state is intentionally small so restart recovery and duplicate
|
||||
suppression can be verified without coupling the runner to one database.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import time
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Mapping, Protocol, Sequence
|
||||
|
||||
|
||||
class RunnerError(RuntimeError):
|
||||
"""Raised when a runner contract would be violated."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RunnerConfig:
|
||||
worker_id: str
|
||||
capabilities: tuple[str, ...] = ()
|
||||
long_poll_seconds: int = 30
|
||||
fallback_seconds: int = 60
|
||||
jitter_seconds: int = 5
|
||||
max_backoff_seconds: int = 300
|
||||
executable_allowlist: tuple[str, ...] = ()
|
||||
working_directory_allowlist: tuple[str, ...] = ()
|
||||
environment_allowlist: tuple[str, ...] = ()
|
||||
|
||||
|
||||
@dataclass
|
||||
class RunnerState:
|
||||
inflight: dict[str, dict[str, Any]] = field(default_factory=dict)
|
||||
terminal: dict[str, dict[str, Any]] = field(default_factory=dict)
|
||||
|
||||
|
||||
class RunnerTransport(Protocol):
|
||||
def register_worker(self, worker_id: str, capabilities: Sequence[str]) -> Mapping[str, Any]: ...
|
||||
def heartbeat(self, worker_id: str) -> Mapping[str, Any]: ...
|
||||
def long_poll(self, worker_id: str, timeout_seconds: int) -> Mapping[str, Any] | None: ...
|
||||
def poll(self, worker_id: str) -> Mapping[str, Any] | None: ...
|
||||
def claim(self, worker_id: str, task: Mapping[str, Any]) -> Mapping[str, Any]: ...
|
||||
def renew(self, worker_id: str, task_id: str) -> Mapping[str, Any]: ...
|
||||
def report_progress(self, worker_id: str, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]: ...
|
||||
def report_result(self, worker_id: str, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]: ...
|
||||
def report_evidence(self, worker_id: str, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]: ...
|
||||
|
||||
|
||||
class JsonStateStore:
|
||||
"""Atomic JSON state store for restart recovery."""
|
||||
|
||||
def __init__(self, path: str | os.PathLike[str]) -> None:
|
||||
self.path = Path(path)
|
||||
|
||||
def load(self) -> RunnerState:
|
||||
if not self.path.exists():
|
||||
return RunnerState()
|
||||
value = json.loads(self.path.read_text(encoding="utf-8"))
|
||||
if not isinstance(value, dict):
|
||||
raise RunnerError("runner state must be an object")
|
||||
return RunnerState(
|
||||
inflight=dict(value.get("inflight", {})),
|
||||
terminal=dict(value.get("terminal", {})),
|
||||
)
|
||||
|
||||
def save(self, state: RunnerState) -> None:
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
fd, name = tempfile.mkstemp(prefix=self.path.name + ".", dir=self.path.parent)
|
||||
try:
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as handle:
|
||||
json.dump({"inflight": state.inflight, "terminal": state.terminal}, handle, sort_keys=True)
|
||||
handle.write("\n")
|
||||
os.chmod(name, 0o600)
|
||||
os.replace(name, self.path)
|
||||
finally:
|
||||
if os.path.exists(name):
|
||||
os.unlink(name)
|
||||
|
||||
|
||||
class AgentPullRunner:
|
||||
"""Pull, claim, execute and report one task at a time."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: RunnerConfig,
|
||||
transport: RunnerTransport,
|
||||
state_store: JsonStateStore | None = None,
|
||||
*,
|
||||
random_fn: Callable[[], float] = random.random,
|
||||
) -> None:
|
||||
if not config.worker_id.strip():
|
||||
raise RunnerError("worker_id is required")
|
||||
self.config = config
|
||||
self.transport = transport
|
||||
self.state_store = state_store
|
||||
self.random_fn = random_fn
|
||||
self.state = state_store.load() if state_store else RunnerState()
|
||||
|
||||
def _save(self) -> None:
|
||||
if self.state_store:
|
||||
self.state_store.save(self.state)
|
||||
|
||||
def register(self) -> Mapping[str, Any]:
|
||||
return self.transport.register_worker(self.config.worker_id, self.config.capabilities)
|
||||
|
||||
def heartbeat(self) -> Mapping[str, Any]:
|
||||
return self.transport.heartbeat(self.config.worker_id)
|
||||
|
||||
def discovery_delay(self, failures: int) -> float:
|
||||
failures = max(0, int(failures))
|
||||
base = min(self.config.max_backoff_seconds, self.config.fallback_seconds * (2**failures))
|
||||
jitter = self.random_fn() * max(0, self.config.jitter_seconds)
|
||||
return min(self.config.max_backoff_seconds, base + jitter)
|
||||
|
||||
def discover_once(self) -> Mapping[str, Any] | None:
|
||||
try:
|
||||
task = self.transport.long_poll(self.config.worker_id, self.config.long_poll_seconds)
|
||||
except Exception:
|
||||
task = None
|
||||
if task is None:
|
||||
task = self.transport.poll(self.config.worker_id)
|
||||
if not task:
|
||||
return None
|
||||
task_id = str(task.get("task_id", ""))
|
||||
if not task_id:
|
||||
raise RunnerError("task_id is required")
|
||||
if task_id in self.state.terminal:
|
||||
return {"status": "duplicate_suppressed", "task_id": task_id}
|
||||
claimed = dict(self.transport.claim(self.config.worker_id, task))
|
||||
self.state.inflight[task_id] = claimed
|
||||
self._save()
|
||||
return claimed
|
||||
|
||||
def renew(self, task_id: str) -> Mapping[str, Any]:
|
||||
if task_id not in self.state.inflight:
|
||||
raise RunnerError("task is not inflight")
|
||||
return self.transport.renew(self.config.worker_id, task_id)
|
||||
|
||||
def report_progress(self, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]:
|
||||
if task_id not in self.state.inflight:
|
||||
raise RunnerError("task is not inflight")
|
||||
return self.transport.report_progress(self.config.worker_id, task_id, payload)
|
||||
|
||||
def report_evidence(self, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]:
|
||||
if task_id not in self.state.inflight:
|
||||
raise RunnerError("task is not inflight")
|
||||
return self.transport.report_evidence(self.config.worker_id, task_id, payload)
|
||||
|
||||
def report_result(self, task_id: str, payload: Mapping[str, Any]) -> Mapping[str, Any]:
|
||||
if task_id in self.state.terminal:
|
||||
return {"status": "duplicate_terminal_suppressed", "task_id": task_id}
|
||||
if task_id not in self.state.inflight:
|
||||
raise RunnerError("task is not inflight")
|
||||
result = dict(self.transport.report_result(self.config.worker_id, task_id, payload))
|
||||
self.state.terminal[task_id] = {"result": result, "reported_at": time.time()}
|
||||
self.state.inflight.pop(task_id, None)
|
||||
self._save()
|
||||
return result
|
||||
|
||||
def recover_after_restart(self) -> list[Mapping[str, Any]]:
|
||||
recovered: list[Mapping[str, Any]] = []
|
||||
for task_id in tuple(self.state.inflight):
|
||||
recovered.append(self.renew(task_id))
|
||||
return recovered
|
||||
|
||||
def validate_execution(self, argv: Sequence[str], cwd: str | os.PathLike[str], env: Mapping[str, str]) -> None:
|
||||
if not argv or any(not isinstance(item, str) or not item for item in argv):
|
||||
raise RunnerError("argv_only_execution_required")
|
||||
if any(ch in argv[0] for ch in (";", "|", "&", "`", "\n")):
|
||||
raise RunnerError("shell_syntax_denied")
|
||||
executable = shutil.which(argv[0])
|
||||
if not executable:
|
||||
raise RunnerError("executable_not_found")
|
||||
if self.config.executable_allowlist and not any(
|
||||
os.path.realpath(executable).startswith(os.path.realpath(prefix).rstrip(os.sep) + os.sep)
|
||||
or os.path.realpath(executable) == os.path.realpath(prefix)
|
||||
for prefix in self.config.executable_allowlist
|
||||
):
|
||||
raise RunnerError("executable_not_allowlisted")
|
||||
real_cwd = os.path.realpath(os.fspath(cwd))
|
||||
if self.config.working_directory_allowlist and not any(
|
||||
real_cwd == os.path.realpath(prefix)
|
||||
or real_cwd.startswith(os.path.realpath(prefix).rstrip(os.sep) + os.sep)
|
||||
for prefix in self.config.working_directory_allowlist
|
||||
):
|
||||
raise RunnerError("working_directory_not_allowlisted")
|
||||
if self.config.environment_allowlist and any(key not in self.config.environment_allowlist for key in env):
|
||||
raise RunnerError("environment_key_not_allowlisted")
|
||||
|
||||
def execute_argv(self, argv: Sequence[str], cwd: str | os.PathLike[str], env: Mapping[str, str]) -> Mapping[str, Any]:
|
||||
self.validate_execution(argv, cwd, env)
|
||||
completed = subprocess.run(list(argv), cwd=os.fspath(cwd), env=dict(env), shell=False, text=True, capture_output=True, check=False)
|
||||
return {"returncode": completed.returncode, "stdout": completed.stdout, "stderr": completed.stderr}
|
||||
@@ -0,0 +1,36 @@
|
||||
"""Small operational CLI for the Agent Pull Runner contract."""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
|
||||
from agent_pull_runner import AgentPullRunner, RunnerConfig
|
||||
|
||||
|
||||
class _NoopTransport:
|
||||
def register_worker(self, worker_id, capabilities): return {"status": "registered", "worker_id": worker_id, "capabilities": list(capabilities)}
|
||||
def heartbeat(self, worker_id): return {"status": "alive", "worker_id": worker_id}
|
||||
def long_poll(self, worker_id, timeout_seconds): return None
|
||||
def poll(self, worker_id): return None
|
||||
def claim(self, worker_id, task): return task
|
||||
def renew(self, worker_id, task_id): return {"status": "renewed", "task_id": task_id}
|
||||
def report_progress(self, worker_id, task_id, payload): return {"status": "progress_recorded", "task_id": task_id}
|
||||
def report_result(self, worker_id, task_id, payload): return {"status": "result_recorded", "task_id": task_id}
|
||||
def report_evidence(self, worker_id, task_id, payload): return {"status": "evidence_recorded", "task_id": task_id}
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description="AIOS Agent Pull Runner")
|
||||
parser.add_argument("--worker-id", default="self-test-worker")
|
||||
parser.add_argument("--self-test", action="store_true")
|
||||
args = parser.parse_args()
|
||||
runner = AgentPullRunner(RunnerConfig(worker_id=args.worker_id, fallback_seconds=60), _NoopTransport())
|
||||
if args.self_test:
|
||||
print(json.dumps({"status": "PASS", "registration": runner.register(), "fallback_seconds": runner.config.fallback_seconds}, sort_keys=True))
|
||||
return 0
|
||||
print(json.dumps({"status": "READY", "worker_id": args.worker_id}, sort_keys=True))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,73 @@
|
||||
"""HTTP adapter for Owner-authorized task writer provisioning.
|
||||
|
||||
Run this module instead of aios_chatgpt_actions_api.py. All existing routes are
|
||||
delegated unchanged; only POST /api/task-writer/provision-authorized is added.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import urllib.parse
|
||||
|
||||
import aios_chatgpt_actions_api as api
|
||||
from authorized_task_writer_provisioning import (
|
||||
AuthorizedTaskWriterProvisioner,
|
||||
OwnerContext,
|
||||
ProvisioningError,
|
||||
)
|
||||
|
||||
|
||||
_original_do_post = api.H.do_POST
|
||||
_ENDPOINT = "/api/task-writer/provision-authorized"
|
||||
|
||||
|
||||
def _owner_authorization(handler):
|
||||
scope = os.getenv(
|
||||
"AIOS_GITOPS_OWNER_PROVISION_SCOPE", "writer:provision"
|
||||
)
|
||||
auth = handler.need(scope)
|
||||
if not auth:
|
||||
return None
|
||||
if auth.get("role") != "owner":
|
||||
handler.sendj({"error": "OWNER_AUTHORIZATION_REQUIRED"}, 403)
|
||||
return None
|
||||
identity = str(auth.get("account") or "").strip()
|
||||
if not identity:
|
||||
handler.sendj({"error": "OWNER_IDENTITY_REQUIRED"}, 403)
|
||||
return None
|
||||
return auth
|
||||
|
||||
|
||||
def _authorized_do_post(self):
|
||||
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
|
||||
if path != _ENDPOINT:
|
||||
return _original_do_post(self)
|
||||
auth = _owner_authorization(self)
|
||||
if not auth:
|
||||
return
|
||||
data = self.body()
|
||||
owner_reference = str(data.get("owner_authorization_reference") or "")
|
||||
try:
|
||||
result = AuthorizedTaskWriterProvisioner().provision(
|
||||
data,
|
||||
OwnerContext(
|
||||
identity=str(auth["account"]),
|
||||
role=str(auth["role"]),
|
||||
authorization_reference=owner_reference,
|
||||
),
|
||||
)
|
||||
return self.sendj(result)
|
||||
except ProvisioningError as exc:
|
||||
body = {"error": exc.code}
|
||||
if exc.details:
|
||||
body["details"] = exc.details
|
||||
return self.sendj(body, exc.status)
|
||||
except Exception:
|
||||
# Do not expose tool output, paths containing credentials, or traceback data.
|
||||
return self.sendj({"error": "AUTHORIZED_WRITER_BRIDGE_INTERNAL_ERROR"}, 500)
|
||||
|
||||
|
||||
api.H.do_POST = _authorized_do_post
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
api.main()
|
||||
@@ -0,0 +1,89 @@
|
||||
"""Governed API facade for branch-bound repair leases.
|
||||
|
||||
The facade is transport-neutral so the permanent control plane can expose it
|
||||
through its existing authenticated loopback/API seam without creating a second
|
||||
Git writer or a global credential registry.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Mapping
|
||||
|
||||
from branch_repair_lease import LeaseError, RepairLease, RepairLeaseManager, sanitized_lease_view
|
||||
|
||||
|
||||
class BranchRepairLeaseAPI:
|
||||
"""Validate operation envelopes and return sanitized lease metadata."""
|
||||
|
||||
def __init__(self, manager: RepairLeaseManager) -> None:
|
||||
self.manager = manager
|
||||
|
||||
@staticmethod
|
||||
def _required(request: Mapping[str, Any], name: str) -> Any:
|
||||
value = request.get(name)
|
||||
if value is None or value == "":
|
||||
raise LeaseError(f"missing required field: {name}")
|
||||
return value
|
||||
|
||||
@staticmethod
|
||||
def _view(lease: RepairLease) -> dict[str, Any]:
|
||||
return {"status": "ok", "lease": sanitized_lease_view(lease)}
|
||||
|
||||
def handle(self, request: Mapping[str, Any]) -> dict[str, Any]:
|
||||
try:
|
||||
operation = self._required(request, "operation")
|
||||
owner = str(self._required(request, "owner_identity"))
|
||||
if operation == "issue":
|
||||
lease = self.manager.issue(
|
||||
task_id=str(self._required(request, "task_id")),
|
||||
owner_identity=owner,
|
||||
branch=str(self._required(request, "branch")),
|
||||
description=str(self._required(request, "description")),
|
||||
allowed_paths=tuple(self._required(request, "allowed_paths")),
|
||||
ttl_seconds=int(request.get("ttl_seconds", 3600)),
|
||||
)
|
||||
elif operation == "attach_existing_branch":
|
||||
lease = self.manager.attach_existing_branch(
|
||||
str(self._required(request, "lease_id")),
|
||||
owner_identity=owner,
|
||||
expected_head_oid=str(self._required(request, "expected_head_oid")),
|
||||
)
|
||||
elif operation == "authorize_commit":
|
||||
lease = self.manager.authorize_commit(
|
||||
str(self._required(request, "lease_id")),
|
||||
owner_identity=owner,
|
||||
expected_head_oid=str(self._required(request, "expected_head_oid")),
|
||||
paths=tuple(self._required(request, "paths")),
|
||||
content=request.get("content"),
|
||||
)
|
||||
elif operation == "record_commit":
|
||||
lease = self.manager.record_commit(
|
||||
str(self._required(request, "lease_id")),
|
||||
owner_identity=owner,
|
||||
expected_head_oid=str(self._required(request, "expected_head_oid")),
|
||||
new_head_oid=str(self._required(request, "new_head_oid")),
|
||||
paths=tuple(self._required(request, "paths")),
|
||||
)
|
||||
elif operation == "recover":
|
||||
lease = self.manager.recover(
|
||||
str(self._required(request, "lease_id")), owner_identity=owner
|
||||
)
|
||||
elif operation == "renew":
|
||||
lease = self.manager.renew(
|
||||
str(self._required(request, "lease_id")),
|
||||
owner_identity=owner,
|
||||
ttl_seconds=int(self._required(request, "ttl_seconds")),
|
||||
)
|
||||
elif operation == "complete":
|
||||
lease = self.manager.complete(
|
||||
str(self._required(request, "lease_id")), owner_identity=owner
|
||||
)
|
||||
elif operation == "revoke":
|
||||
lease = self.manager.revoke(
|
||||
str(self._required(request, "lease_id")), owner_identity=owner
|
||||
)
|
||||
else:
|
||||
raise LeaseError("unsupported lease operation")
|
||||
return self._view(lease)
|
||||
except (LeaseError, TypeError, ValueError):
|
||||
return {"status": "blocked", "error": "lease_request_rejected"}
|
||||
@@ -0,0 +1,48 @@
|
||||
"""Root-only CLI for the branch-bound repair lease API."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
from aios_branch_repair_lease_api import BranchRepairLeaseAPI
|
||||
from branch_repair_lease import GitProbe, LeaseStore
|
||||
from branch_repair_lease import RepairLeaseManager
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description="AIOS branch repair lease CLI")
|
||||
parser.add_argument("--store", required=True)
|
||||
parser.add_argument("--bare-repo", required=True)
|
||||
parser.add_argument("--request-file")
|
||||
parser.add_argument("--request-json")
|
||||
args = parser.parse_args()
|
||||
if hasattr(os, "geteuid") and os.geteuid() != 0:
|
||||
print(json.dumps({"status": "blocked", "error": "root_required"}))
|
||||
return 2
|
||||
if bool(args.request_file) == bool(args.request_json):
|
||||
print(json.dumps({"status": "blocked", "error": "one_request_source_required"}))
|
||||
return 2
|
||||
try:
|
||||
raw = (
|
||||
Path(args.request_file).read_text(encoding="utf-8")
|
||||
if args.request_file
|
||||
else str(args.request_json)
|
||||
)
|
||||
request = json.loads(raw)
|
||||
if not isinstance(request, dict):
|
||||
raise ValueError("request must be an object")
|
||||
api = BranchRepairLeaseAPI(RepairLeaseManager(LeaseStore(args.store), GitProbe(args.bare_repo)))
|
||||
response = api.handle(request)
|
||||
print(json.dumps(response, ensure_ascii=True, sort_keys=True, separators=(",", ":")))
|
||||
return 0 if response.get("status") == "ok" else 1
|
||||
except Exception:
|
||||
print(json.dumps({"status": "blocked", "error": "lease_cli_failed"}))
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -5,28 +5,81 @@ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
sys.path.insert(0, str(Path(os.getenv('AIOS_GITOPS_WORKSPACE', '/data/aios-gitops/workspace')) / 'runtime' / 'agent-os'))
|
||||
try:
|
||||
from aios_gitops_write_guard import evaluate_git_write
|
||||
except ModuleNotFoundError:
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent))
|
||||
from aios_gitops_write_guard import evaluate_git_write
|
||||
|
||||
from gitea_tag_publication import (
|
||||
GiteaTagClient,
|
||||
GitTagBackend,
|
||||
PublicationConflict,
|
||||
PublicationPending,
|
||||
PublicationManualOwnerReviewRequired,
|
||||
PublicationReconciliationRequired,
|
||||
PublicationRequest,
|
||||
TagPublisher,
|
||||
redact,
|
||||
validate_version,
|
||||
)
|
||||
from orchestrator.action_monitor import ActionMonitor
|
||||
from silent_release_hardening import (
|
||||
ApprovalKeyRing,
|
||||
ApprovalRevocationStore,
|
||||
CapabilityAuthorizationError,
|
||||
SagaConflict,
|
||||
SignedApprovalVerifier,
|
||||
SignedReleasePlanApproval,
|
||||
SilentReleaseActionService,
|
||||
)
|
||||
try:
|
||||
from authoritative_git import (
|
||||
AuthoritativeGitError,
|
||||
AuthoritativeGitNotFound,
|
||||
AuthoritativeGitOutputTooLarge,
|
||||
authoritative_branches,
|
||||
authoritative_diff,
|
||||
authoritative_commit,
|
||||
authoritative_tags,
|
||||
repository_snapshot,
|
||||
run_authoritative_git,
|
||||
)
|
||||
except ModuleNotFoundError:
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent))
|
||||
from authoritative_git import (
|
||||
AuthoritativeGitError,
|
||||
AuthoritativeGitNotFound,
|
||||
AuthoritativeGitOutputTooLarge,
|
||||
authoritative_branches,
|
||||
authoritative_diff,
|
||||
authoritative_commit,
|
||||
authoritative_tags,
|
||||
repository_snapshot,
|
||||
run_authoritative_git,
|
||||
)
|
||||
|
||||
ROOT = Path(os.getenv('AIOS_GITOPS_ROOT', '/data/aios-gitops'))
|
||||
WS = Path(os.getenv('AIOS_GITOPS_WORKSPACE', str(ROOT / 'workspace')))
|
||||
sys.path.insert(0, str(WS))
|
||||
from services.aios_orchestrator_gateway.action_bridge import (
|
||||
CallbackBridgeError,
|
||||
submit_orchestration_decision,
|
||||
)
|
||||
|
||||
SECRETS = Path(os.getenv('AIOS_GITOPS_SECRETS_DIR', str(ROOT / 'runtime' / 'secrets')))
|
||||
TOKEN_FILE = Path(os.getenv('AIOS_GITOPS_TOKEN_FILE', str(SECRETS / 'gitops.tokens')))
|
||||
HOST = os.getenv('AIOS_GITOPS_HOST', '127.0.0.1')
|
||||
PORT = int(os.getenv('AIOS_GITOPS_PORT', '18890'))
|
||||
OPENAPI = WS / 'docs' / 'gitops' / 'openapi-chatgpt-actions.yaml'
|
||||
ORCHESTRATOR_OPENAPI = WS / 'workspace-agent' / 'orchestrator-decision-action.openapi.yaml'
|
||||
ORCHESTRATOR_CONTRACT_COMMIT = os.getenv('AIOS_ORCHESTRATOR_CONTRACT_COMMIT', '')
|
||||
ORCHESTRATOR_CALLBACK_SECRET_REF = os.getenv('AIOS_ORCHESTRATOR_CALLBACK_SECRET_REF', '')
|
||||
_resolver = os.getenv('AIOS_ORCHESTRATOR_SECRET_REF_RESOLVER', '')
|
||||
ORCHESTRATOR_SECRET_REF_RESOLVER = Path(_resolver) if _resolver else None
|
||||
BARE_REPO = Path(os.getenv('AIOS_GITOPS_BARE_REPO', str(ROOT / 'runtime' / 'gitea-bin' / 'data' / 'repositories' / 'aios' / 'aios.git')))
|
||||
AUTHORITATIVE_GIT_DIR = Path(os.getenv('AIOS_GITOPS_AUTHORITATIVE_GIT_DIR')) if os.getenv('AIOS_GITOPS_AUTHORITATIVE_GIT_DIR') else None
|
||||
REPOSITORY_IDENTITY = os.getenv('AIOS_GITOPS_REPOSITORY_IDENTITY', '')
|
||||
SILENT_RELEASE_STATE_ROOT = Path(os.getenv(
|
||||
'AIOS_SILENT_RELEASE_STATE_ROOT',
|
||||
'/var/lib/aios-gitops/silent-release',
|
||||
))
|
||||
SILENT_RELEASE_EXECUTION_ENABLED = str(os.getenv(
|
||||
'AIOS_SILENT_RELEASE_EXECUTION_ENABLED', 'false'
|
||||
)).lower() in {'1', 'true', 'yes', 'on'}
|
||||
SILENT_RELEASE_PUBLIC_KEYS = Path(os.getenv(
|
||||
'AIOS_SILENT_RELEASE_PUBLIC_KEYS',
|
||||
'/etc/aios-gitops/silent-release-owner-public-keys.json',
|
||||
))
|
||||
monitor = ActionMonitor()
|
||||
|
||||
BASE_MODELS = [
|
||||
@@ -35,7 +88,43 @@ BASE_MODELS = [
|
||||
{'id':'base.gpt-5.5','provider':'openai','model':'gpt-5.5','display_name':'GPT-5.5','scope':'global'},
|
||||
]
|
||||
SECRET_RE = re.compile(r'(?i)(api[_-]?key|secret[_-]?access[_-]?key|secret|password|token)\s*[:=]\s*["\']?([A-Za-z0-9_./+=:-]{16,})')
|
||||
SECRET_VAL_RE = re.compile(r'(sk-[A-Za-z0-9_-]{20,}|HPUA[A-Z0-9]{10,}|SDC[A-Za-z0-9]{20,})')
|
||||
SECRET_VAL_RE = re.compile(
|
||||
r'(?<![A-Za-z0-9_])'
|
||||
r'(sk-[A-Za-z0-9_-]{20,}|HPUA[A-Z0-9]{10,}|SDC[A-Za-z0-9]{20,})'
|
||||
)
|
||||
|
||||
READ_ONLY_GET_PATHS = frozenset({
|
||||
'/', '/health', '/api/health', '/api/openapi.yaml',
|
||||
'/api/openapi-chatgpt-actions.yaml', '/api/schema', '/api', '/api/status',
|
||||
'/api/base', '/api/baseline', '/base', '/api/ver', '/api/versions', '/ver',
|
||||
'/api/diff', '/diff', '/api/patch', '/api/patches', '/api/branches', '/patch',
|
||||
'/api/model', '/model', '/api/run', '/api/runtime-status', '/run',
|
||||
'/api/action-monitor', '/action-monitor', '/admin/ai-evolution',
|
||||
'/admin/ai-evolution/api/data',
|
||||
'/api/release-consistency', '/api/tag-publication-status',
|
||||
'/api/release-acceptance',
|
||||
'/getReleaseCandidate', '/getReleasePlan', '/getReleaseAcceptance',
|
||||
'/getApprovalEnvelope', '/getReleaseSaga', '/getCapabilityStatus',
|
||||
'/getRecoveryStatus',
|
||||
})
|
||||
SILENT_RELEASE_POST_PATHS = frozenset({
|
||||
'/createReleaseCandidate',
|
||||
'/createReleaseIntent',
|
||||
'/submitSignedApproval',
|
||||
'/submitOwnerApproval',
|
||||
'/startDeployment',
|
||||
})
|
||||
|
||||
def reject_non_read_http(handler, method: str, path: str) -> bool:
|
||||
if method == 'GET':
|
||||
return False
|
||||
if path in SILENT_RELEASE_POST_PATHS:
|
||||
return False
|
||||
decision = evaluate_git_write(WS)
|
||||
if decision.allowed:
|
||||
return False
|
||||
handler.sendj(decision.payload(), decision.status_code)
|
||||
return True
|
||||
|
||||
def now() -> str: return time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())
|
||||
def uid(p='id') -> str: return f'{p}-{int(time.time()*1000)}-{uuid.uuid4().hex[:8]}'
|
||||
@@ -47,6 +136,41 @@ def sh(args, check=False):
|
||||
def jload(p: Path, default):
|
||||
try: return json.loads(p.read_text(encoding='utf-8'))
|
||||
except Exception: return default
|
||||
|
||||
def _file_sha256(path: Path) -> str:
|
||||
digest=hashlib.sha256()
|
||||
with path.open('rb') as source:
|
||||
for chunk in iter(lambda: source.read(1024 * 1024), b''):
|
||||
digest.update(chunk)
|
||||
return digest.hexdigest()
|
||||
|
||||
def _build_silent_release_service() -> SilentReleaseActionService:
|
||||
verifier=None
|
||||
if SILENT_RELEASE_PUBLIC_KEYS.is_file():
|
||||
verifier=SignedApprovalVerifier(
|
||||
ApprovalKeyRing.from_file(SILENT_RELEASE_PUBLIC_KEYS),
|
||||
ApprovalRevocationStore(
|
||||
SILENT_RELEASE_STATE_ROOT / 'revocations'
|
||||
),
|
||||
)
|
||||
policy_path=WS / 'config' / 'gitops' / 'silent-release-policy.json'
|
||||
policy_sha=_file_sha256(policy_path) if policy_path.is_file() else ''
|
||||
return SilentReleaseActionService(
|
||||
SILENT_RELEASE_STATE_ROOT,
|
||||
execution_enabled=SILENT_RELEASE_EXECUTION_ENABLED,
|
||||
approval_verifier=verifier,
|
||||
expected_repository=REPOSITORY_IDENTITY,
|
||||
policy_sha256=policy_sha,
|
||||
)
|
||||
|
||||
# Construct once during service startup. If production execution is enabled
|
||||
# without every trusted builder/orchestrator dependency, construction fails
|
||||
# closed before the HTTP server accepts traffic.
|
||||
_SILENT_RELEASE_SERVICE = _build_silent_release_service()
|
||||
|
||||
|
||||
def silent_release_service() -> SilentReleaseActionService:
|
||||
return _SILENT_RELEASE_SERVICE
|
||||
def relpath(path: str) -> str:
|
||||
x = str(path or '').replace('\\','/').strip()
|
||||
if not x or x.startswith('/') or '..' in Path(x).parts or Path(x).parts[0] == '.git': raise ValueError('invalid path')
|
||||
@@ -120,9 +244,13 @@ def ensure_git():
|
||||
if not sh(['config','user.name'])['stdout']: sh(['config','user.name','chatgpt-gitops-bot'], True)
|
||||
def checkout(branch, base='main', create=False):
|
||||
ensure_git(); b=branch_name(branch)
|
||||
if create or sh(['rev-parse','--verify',b])['code'] != 0:
|
||||
sh(['checkout',base], True); sh(['checkout','-B',b], True)
|
||||
else: sh(['checkout',b], True)
|
||||
exists = sh(['rev-parse','--verify',f'refs/heads/{b}'])['code'] == 0
|
||||
if exists:
|
||||
sh(['checkout',b], True)
|
||||
elif create:
|
||||
sh(['checkout',base], True); sh(['checkout','-b',b], True)
|
||||
else:
|
||||
raise ValueError(f'branch does not exist: {b}')
|
||||
return b
|
||||
def write_file(path, content):
|
||||
if content_has_secret(content): raise ValueError('secret_rejected: use secret_ref; plaintext API keys must not enter Git')
|
||||
@@ -132,6 +260,19 @@ def sync_branch(branch: str) -> dict:
|
||||
if not branch or branch in ('main','master') or branch.startswith('main/') or branch.startswith('master/'):
|
||||
return {'status':'skipped','reason':'protected_branch','branch':branch}
|
||||
if BARE_REPO.exists():
|
||||
common = sh(['rev-parse', '--path-format=absolute', '--git-common-dir'], True)['stdout']
|
||||
if Path(common).resolve() == BARE_REPO.resolve():
|
||||
head = sh(['rev-parse', 'HEAD'], True)['stdout']
|
||||
stored = subprocess.run(
|
||||
['git', '--git-dir', str(BARE_REPO), 'rev-parse', f'refs/heads/{branch}'],
|
||||
text=True, capture_output=True,
|
||||
)
|
||||
if stored.returncode != 0 or stored.stdout.strip() != head:
|
||||
raise RuntimeError(f'linked-worktree branch verification failed for {branch}')
|
||||
return {
|
||||
'status':'verified', 'target':'authoritative-bare',
|
||||
'branch':branch, 'oid':head,
|
||||
}
|
||||
ref=f'refs/heads/{branch}:refs/heads/{branch}'
|
||||
p=subprocess.run(['git','--git-dir',str(BARE_REPO),'fetch',str(WS),ref], text=True, capture_output=True)
|
||||
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git sync failed for {branch}')
|
||||
@@ -141,15 +282,68 @@ def sync_branch(branch: str) -> dict:
|
||||
return {'status':'synced','target':'origin','branch':branch,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
|
||||
|
||||
def sync_tag(tag: str) -> dict:
|
||||
if not tag: return {'status':'skipped','reason':'empty_tag'}
|
||||
if BARE_REPO.exists():
|
||||
ref=f'refs/tags/{tag}:refs/tags/{tag}'
|
||||
p=subprocess.run(['git','--git-dir',str(BARE_REPO),'fetch',str(WS),ref], text=True, capture_output=True)
|
||||
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git tag sync failed for {tag}')
|
||||
return {'status':'synced','target':'bare','tag':tag,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
|
||||
p=subprocess.run(['git','push','origin',tag], cwd=str(WS), text=True, capture_output=True)
|
||||
if p.returncode != 0: raise RuntimeError(p.stderr or p.stdout or f'git tag push failed for {tag}')
|
||||
return {'status':'synced','target':'origin','tag':tag,'stdout':p.stdout.strip(),'stderr':p.stderr.strip()}
|
||||
raise RuntimeError(
|
||||
'unsafe sync_tag disabled: use TagPublisher with expected tag_oid, '
|
||||
'target_oid, Gitea remote verification, and authenticated API verification'
|
||||
)
|
||||
|
||||
def resolve_commit_oid(value: str | None, field: str = 'target_oid') -> str:
|
||||
oid = str(value or '').strip().lower()
|
||||
if not re.fullmatch(r'[0-9a-f]{40}', oid):
|
||||
raise ValueError(f'{field} must be a full 40-character commit OID')
|
||||
try:
|
||||
return authoritative_commit(oid, git_dir=AUTHORITATIVE_GIT_DIR)
|
||||
except (AuthoritativeGitError, ValueError) as exc:
|
||||
raise ValueError(f'{field} does not resolve to the exact approved commit') from exc
|
||||
|
||||
def existing_tag_target(tag: str) -> str | None:
|
||||
if not re.fullmatch(r'V\d+R\d+C\d+(?:-[A-Za-z0-9_.-]+)?$', str(tag or '')):
|
||||
raise ValueError('invalid release version')
|
||||
try:
|
||||
result = run_authoritative_git(
|
||||
['rev-parse', '--verify', f'refs/tags/{tag}^{{commit}}'],
|
||||
check=False,
|
||||
git_dir=AUTHORITATIVE_GIT_DIR,
|
||||
)
|
||||
except AuthoritativeGitError as exc:
|
||||
raise RuntimeError(str(exc)) from exc
|
||||
return result.stdout.strip() if result.returncode == 0 else None
|
||||
|
||||
def publication_request_from_query(q: dict[str, list[str]]) -> PublicationRequest:
|
||||
required = ('version', 'target_oid', 'evidence_closure_oid', 'approval_plan_id')
|
||||
missing = [name for name in required if not (q.get(name) or [''])[0]]
|
||||
if missing:
|
||||
raise ValueError('missing release governance fields: ' + ', '.join(missing))
|
||||
return PublicationRequest(
|
||||
(q['version'])[0],
|
||||
(q['target_oid'])[0].lower(),
|
||||
(q['evidence_closure_oid'])[0].lower(),
|
||||
(q['approval_plan_id'])[0],
|
||||
)
|
||||
|
||||
def required_authoritative_git_dir() -> Path:
|
||||
snapshot = repository_snapshot(
|
||||
git_dir=AUTHORITATIVE_GIT_DIR,
|
||||
repository_identity=REPOSITORY_IDENTITY,
|
||||
)
|
||||
if not snapshot["repository_available"]:
|
||||
raise RuntimeError(str(snapshot["query_error"] or "AUTHORITATIVE_REPOSITORY_UNAVAILABLE"))
|
||||
return Path(str(snapshot["authoritative_git_dir"]))
|
||||
|
||||
|
||||
def publication_publisher() -> TagPublisher:
|
||||
authoritative_repo = required_authoritative_git_dir()
|
||||
return TagPublisher(
|
||||
WS,
|
||||
GitTagBackend(WS, authoritative_repo=authoritative_repo),
|
||||
GiteaTagClient(
|
||||
os.getenv('AIOS_GITOPS_GITEA_API_URL',''),
|
||||
os.getenv('AIOS_GITOPS_GITEA_REPOSITORY',''),
|
||||
Path(os.getenv('AIOS_GITOPS_GITEA_TOKEN_FILE','')),
|
||||
token_line=int(os.getenv('AIOS_GITOPS_GITEA_TOKEN_LINE','1')),
|
||||
),
|
||||
os.getenv('AIOS_GITOPS_GITEA_REMOTE','gitea'),
|
||||
)
|
||||
|
||||
def commit(paths, msg):
|
||||
ensure_git(); paths = [relpath(p) for p in paths] if paths else ['.']; sh(['add'] + paths, True)
|
||||
@@ -169,6 +363,16 @@ def patches():
|
||||
for p in sorted((WS/'patches').glob('**/*.json')): out.append(jload(p, {'path':str(p.relative_to(WS))}))
|
||||
return out
|
||||
|
||||
def runtime_release_info() -> dict[str, Any]:
|
||||
for candidate in (WS / 'manifest.json', WS.parent / 'manifest.json'):
|
||||
data = jload(candidate, {})
|
||||
if data.get('target_commit'):
|
||||
return {
|
||||
'runtime_release_commit': data.get('target_commit'),
|
||||
'runtime_release_path': str(WS),
|
||||
}
|
||||
return {'runtime_release_commit': None, 'runtime_release_path': str(WS)}
|
||||
|
||||
class H(BaseHTTPRequestHandler):
|
||||
server_version='AIOSChatGPTGitOps/V1R1C0'
|
||||
def sendj(self, data, code=200):
|
||||
@@ -190,46 +394,236 @@ class H(BaseHTTPRequestHandler):
|
||||
if '*' not in a['scopes'] and scope not in a['scopes']: self.sendj({'error':'forbidden','required_scope':scope,'account':a['account']},403); return None
|
||||
return a
|
||||
def do_GET(self):
|
||||
u=urllib.parse.urlparse(self.path); path=u.path.rstrip('/') if u.path != '/' else u.path; q=urllib.parse.parse_qs(u.query)
|
||||
u=urllib.parse.urlparse(self.path); path=u.path.rstrip('/') if u.path != '/' else u.path
|
||||
if path not in READ_ONLY_GET_PATHS: return self.sendj({'error':'not_found','path':path},404)
|
||||
q=urllib.parse.parse_qs(u.query)
|
||||
try:
|
||||
if path in ('/health','/api/health'): return self.sendj({'status':'ok','service':'chatgpt-gitops-adapter','workspace':str(WS)})
|
||||
if path in ('/api/openapi.yaml','/api/openapi-chatgpt-actions.yaml','/api/schema'):
|
||||
return self.sendt(OPENAPI.read_text(encoding='utf-8'), 'application/yaml; charset=utf-8') if OPENAPI.exists() else self.sendj({'error':'schema_missing'},404)
|
||||
if path == '/api/orchestrator-decision.openapi.yaml':
|
||||
return self.sendt(ORCHESTRATOR_OPENAPI.read_text(encoding='utf-8'), 'application/yaml; charset=utf-8') if ORCHESTRATOR_OPENAPI.exists() else self.sendj({'error':'schema_missing'},404)
|
||||
if path in ('/api','/api/status'): return self.sendj(api_spec())
|
||||
if path in ('/api/base','/api/baseline','/base'):
|
||||
data=jload(WS/'baseline'/'current.json', {}); data.setdefault('git', sh(['rev-parse','--short','HEAD'])['stdout']); return self.sendj(data)
|
||||
data=jload(WS/'baseline'/'current.json', {})
|
||||
data.setdefault('authoritative_repository', repository_snapshot(
|
||||
git_dir=AUTHORITATIVE_GIT_DIR,
|
||||
repository_identity=REPOSITORY_IDENTITY,
|
||||
))
|
||||
return self.sendj(data)
|
||||
if path in ('/api/ver','/api/versions','/ver'):
|
||||
return self.sendj({'tags':sh(['tag','--list','V*'])['stdout'].splitlines(),'versions_dir':[p.name for p in (WS/'versions').glob('*')],'head':sh(['rev-parse','--short','HEAD'])['stdout']})
|
||||
snapshot = repository_snapshot(
|
||||
git_dir=AUTHORITATIVE_GIT_DIR,
|
||||
repository_identity=REPOSITORY_IDENTITY,
|
||||
)
|
||||
if not snapshot['repository_available']:
|
||||
return self.sendj({
|
||||
'repository_available': False,
|
||||
'query_error': snapshot['query_error'],
|
||||
'registry_versions': [p.name for p in (WS/'versions').glob('*')],
|
||||
'local_authoritative_tags': [],
|
||||
}, 503)
|
||||
try:
|
||||
tags = authoritative_tags(git_dir=AUTHORITATIVE_GIT_DIR)
|
||||
except AuthoritativeGitError as exc:
|
||||
return self.sendj({
|
||||
'repository_available': False,
|
||||
'query_error': str(exc),
|
||||
'registry_versions': [p.name for p in (WS/'versions').glob('*')],
|
||||
'local_authoritative_tags': [],
|
||||
}, 503)
|
||||
registry = [p.name for p in (WS/'versions').glob('*')]
|
||||
return self.sendj({
|
||||
'registry_versions': registry,
|
||||
'local_authoritative_tags': tags,
|
||||
'repository_available': True,
|
||||
'query_error': None,
|
||||
'tags': [item['name'] for item in tags],
|
||||
'versions_dir': registry,
|
||||
'head': snapshot['authoritative_head_oid'],
|
||||
'authoritative_head_oid': snapshot['authoritative_head_oid'],
|
||||
})
|
||||
if path in ('/api/diff','/diff'):
|
||||
frm=(q.get('from') or ['HEAD~1'])[0]; to=(q.get('to') or ['HEAD'])[0]; return self.sendj({'from':frm,'to':to,'diff':sh(['diff',frm,to])})
|
||||
if path in ('/api/patch','/api/patches','/api/branches','/patch'): return self.sendj({'patches':patches(),'branches':sh(['branch','--format','%(refname:short)'])['stdout'].splitlines()})
|
||||
frm=(q.get('from') or [''])[0]
|
||||
to=(q.get('to') or [''])[0]
|
||||
try:
|
||||
diff=authoritative_diff(frm, to, git_dir=required_authoritative_git_dir())
|
||||
except ValueError as exc:
|
||||
return self.sendj({'error':redact(exc)},400)
|
||||
except AuthoritativeGitNotFound as exc:
|
||||
return self.sendj({'error':redact(exc)},404)
|
||||
except AuthoritativeGitOutputTooLarge as exc:
|
||||
return self.sendj({'error':redact(exc)},413)
|
||||
except (AuthoritativeGitError, RuntimeError) as exc:
|
||||
return self.sendj({'error':redact(exc)},503)
|
||||
return self.sendj({'from':frm,'to':to,'diff':diff})
|
||||
if path in ('/api/patch','/api/patches','/api/branches','/patch'):
|
||||
snapshot = repository_snapshot(
|
||||
git_dir=AUTHORITATIVE_GIT_DIR,
|
||||
repository_identity=REPOSITORY_IDENTITY,
|
||||
)
|
||||
if not snapshot['repository_available']:
|
||||
return self.sendj({
|
||||
'repository_available': False,
|
||||
'query_error': snapshot['query_error'],
|
||||
'metadata_patches': patches(),
|
||||
'authoritative_branches': [],
|
||||
}, 503)
|
||||
try:
|
||||
branches = authoritative_branches(git_dir=AUTHORITATIVE_GIT_DIR)
|
||||
except AuthoritativeGitError as exc:
|
||||
return self.sendj({
|
||||
'repository_available': False,
|
||||
'query_error': str(exc),
|
||||
'metadata_patches': patches(),
|
||||
'authoritative_branches': [],
|
||||
}, 503)
|
||||
metadata = patches()
|
||||
branch_names = {item['name'] for item in branches}
|
||||
metadata_names = {
|
||||
item.get('branch') for item in metadata
|
||||
if isinstance(item, dict) and item.get('branch')
|
||||
}
|
||||
orphan = [
|
||||
item for item in metadata
|
||||
if item.get('branch') and item.get('branch') not in branch_names
|
||||
]
|
||||
missing = [
|
||||
item for item in branches
|
||||
if item['name'] not in metadata_names
|
||||
]
|
||||
return self.sendj({
|
||||
'metadata_patches': metadata,
|
||||
'authoritative_branches': branches,
|
||||
'orphan_metadata': orphan,
|
||||
'branches_without_metadata': missing,
|
||||
'repository_available': True,
|
||||
'query_error': None,
|
||||
'patches': metadata,
|
||||
'branches': [item['name'] for item in branches],
|
||||
})
|
||||
if path in ('/api/model','/model'): return self.sendj({'base':BASE_MODELS,'custom':model_docs(),'priority':[jload(p,{}) for p in sorted((WS/'config'/'model_priority').glob('*.json'))]})
|
||||
if path in ('/api/run','/api/runtime-status','/run'):
|
||||
svc=subprocess.run(['systemctl','is-active','aios-gitops-model-api'], text=True, capture_output=True)
|
||||
return self.sendj({'service':'aios-gitops-model-api','status':svc.stdout.strip() or svc.stderr.strip(),'workspace_branch':sh(['rev-parse','--abbrev-ref','HEAD'])['stdout']})
|
||||
snapshot = repository_snapshot(
|
||||
git_dir=AUTHORITATIVE_GIT_DIR,
|
||||
repository_identity=REPOSITORY_IDENTITY,
|
||||
)
|
||||
workspace_branch = None
|
||||
if (WS / '.git').exists():
|
||||
result = sh(['rev-parse','--abbrev-ref','HEAD'])
|
||||
workspace_branch = result['stdout'] or None
|
||||
payload = {
|
||||
'service':'aios-gitops-model-api',
|
||||
'status':svc.stdout.strip() or svc.stderr.strip(),
|
||||
'workspace_branch':workspace_branch,
|
||||
**runtime_release_info(),
|
||||
**snapshot,
|
||||
'writes_enabled': str(os.getenv('AIOS_GITOPS_WRITES_ENABLED','false')).lower() in {'1','true','yes','on'},
|
||||
}
|
||||
return self.sendj(payload, 200 if snapshot['repository_available'] else 503)
|
||||
if path in ('/api/action-monitor','/action-monitor'):
|
||||
latest=monitor.latest()
|
||||
ldict={'event_id':latest.event_id,'action':latest.action,'error':latest.error,'context':latest.context,'created_at':latest.created_at} if latest else None
|
||||
return self.sendj({'events':[{"event_id":e.event_id,"action":e.action,"error":e.error,"context":e.context,"created_at":e.created_at} for e in monitor.list_events()],'latest':ldict})
|
||||
if path == '/api/tag-publication-status':
|
||||
version=(q.get('version') or [''])[0]
|
||||
try:
|
||||
version=validate_version(version)
|
||||
status=publication_publisher().get_tag_publication_status(version)
|
||||
except ValueError:
|
||||
return self.sendj({'error':'invalid release version'},400)
|
||||
return self.sendj(status)
|
||||
if path == '/api/release-consistency':
|
||||
request=publication_request_from_query(q)
|
||||
return self.sendj(publication_publisher().get_release_consistency(request))
|
||||
if path == '/api/release-acceptance':
|
||||
request=publication_request_from_query(q)
|
||||
return self.sendj(publication_publisher().run_release_acceptance(request))
|
||||
if path in (
|
||||
'/getReleaseCandidate',
|
||||
'/getReleasePlan',
|
||||
'/getReleaseAcceptance',
|
||||
'/getApprovalEnvelope',
|
||||
'/getReleaseSaga',
|
||||
'/getCapabilityStatus',
|
||||
):
|
||||
candidate_id=(q.get('candidate_id') or [''])[0]
|
||||
if not candidate_id:
|
||||
return self.sendj({'error':'candidate_id is required'},400)
|
||||
service=silent_release_service()
|
||||
if path == '/getReleaseCandidate':
|
||||
return self.sendj(
|
||||
service.get_release_candidate(candidate_id)
|
||||
)
|
||||
if path == '/getApprovalEnvelope':
|
||||
return self.sendj(
|
||||
service.get_approval_envelope(candidate_id)
|
||||
)
|
||||
if path == '/getReleasePlan':
|
||||
return self.sendj(service.get_release_plan(candidate_id))
|
||||
if path == '/getReleaseAcceptance':
|
||||
return self.sendj(service.get_acceptance(candidate_id))
|
||||
if path == '/getCapabilityStatus':
|
||||
return self.sendj(
|
||||
service.get_capability_status(candidate_id)
|
||||
)
|
||||
return self.sendj(service.get_release_saga(candidate_id))
|
||||
if path == '/getRecoveryStatus':
|
||||
return self.sendj(
|
||||
silent_release_service().get_recovery_status()
|
||||
)
|
||||
# Admin AI Evolution Dashboard
|
||||
if path in ('/admin/ai-evolution','/admin/ai-evolution/'):
|
||||
return self.ai_evolution_page()
|
||||
if path in ('/admin/ai-evolution/api/data'):
|
||||
return self.ai_evolution_data()
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
except FileNotFoundError:
|
||||
return self.sendj({'error':'release candidate not found'},404)
|
||||
except ValueError as e:
|
||||
error=redact(e)
|
||||
monitor.record_failure('do_GET', error, {'path':path})
|
||||
return self.sendj({'error':error},400)
|
||||
except Exception as e:
|
||||
monitor.record_failure('do_GET', str(e), {'path':path})
|
||||
return self.sendj({'error':str(e)},500)
|
||||
error=redact(e)
|
||||
monitor.record_failure('do_GET', error, {'path':path})
|
||||
return self.sendj({'error':error},500)
|
||||
def do_PUT(self):
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/'); data=self.body()
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/')
|
||||
if reject_non_read_http(self, 'PUT', path): return
|
||||
data=self.body()
|
||||
if path == '/api/model-priority': return self.model_priority(data)
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
def do_POST(self):
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/'); data=self.body()
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/')
|
||||
if reject_non_read_http(self, 'POST', path): return
|
||||
data=self.body()
|
||||
try:
|
||||
if path == '/v1/orchestrator/decisions': return self.orchestration_decision(data)
|
||||
if path == '/createReleaseCandidate':
|
||||
a=self.need('release:candidate')
|
||||
if not a: return
|
||||
return self.sendj(
|
||||
silent_release_service().create_release_candidate(data)
|
||||
)
|
||||
if path == '/createReleaseIntent':
|
||||
a=self.need('release:candidate')
|
||||
if not a: return
|
||||
return self.sendj(
|
||||
silent_release_service().create_release_intent(data)
|
||||
)
|
||||
if path in ('/submitOwnerApproval','/submitSignedApproval'):
|
||||
a=self.need('release:approve')
|
||||
if not a: return
|
||||
return self.sendj(
|
||||
silent_release_service().submit_owner_approval(data)
|
||||
)
|
||||
if path == '/startDeployment':
|
||||
a=self.need('release:deploy')
|
||||
if not a: return
|
||||
return self.sendj(
|
||||
silent_release_service().start_deployment(
|
||||
str(data.get('candidate_id') or '')
|
||||
)
|
||||
)
|
||||
if path in ('/api/branch','/api/create-branch'): return self.branch(data)
|
||||
if path in ('/api/file','/api/commit-file'): return self.file(data)
|
||||
if path == '/api/commit': return self.commit(data)
|
||||
@@ -240,28 +634,30 @@ class H(BaseHTTPRequestHandler):
|
||||
if path == '/api/model-priority': return self.model_priority(data)
|
||||
if path == '/api/nl': return self.nl(data)
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
except (ValueError, FileNotFoundError) as e:
|
||||
error=redact(e)
|
||||
monitor.record_failure('do_POST', error, {'path':path})
|
||||
return self.sendj({'error':error},400)
|
||||
except CapabilityAuthorizationError as e:
|
||||
error=redact(e)
|
||||
monitor.record_failure('do_POST', error, {'path':path})
|
||||
return self.sendj({'error':error},403)
|
||||
except SagaConflict as e:
|
||||
error=redact(e)
|
||||
monitor.record_failure('do_POST', error, {'path':path})
|
||||
return self.sendj({'error':error},409)
|
||||
except Exception as e:
|
||||
monitor.record_failure('do_POST', str(e), {'path':path})
|
||||
return self.sendj({'error':str(e)},500)
|
||||
def orchestration_decision(self,data):
|
||||
a=self.need('orchestrator:decision')
|
||||
if not a: return
|
||||
if not ORCHESTRATOR_CONTRACT_COMMIT or ORCHESTRATOR_SECRET_REF_RESOLVER is None:
|
||||
return self.sendj({'error':'CALLBACK_CONFIGURATION_UNAVAILABLE'},503)
|
||||
try:
|
||||
result=submit_orchestration_decision(
|
||||
data,
|
||||
contract_commit=ORCHESTRATOR_CONTRACT_COMMIT,
|
||||
secret_ref=ORCHESTRATOR_CALLBACK_SECRET_REF,
|
||||
resolver=ORCHESTRATOR_SECRET_REF_RESOLVER,
|
||||
)
|
||||
except CallbackBridgeError as exc:
|
||||
return self.sendj({'error':exc.category},exc.status_code)
|
||||
except Exception:
|
||||
# The outer request handler records exception strings. Keep this
|
||||
# secret-bearing boundary metadata-only even for unexpected faults.
|
||||
return self.sendj({'error':'CALLBACK_INTERNAL_ERROR'},500)
|
||||
return self.sendj(result,202)
|
||||
error=redact(e)
|
||||
monitor.record_failure('do_POST', error, {'path':path})
|
||||
return self.sendj({'error':error},500)
|
||||
def do_PATCH(self):
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/')
|
||||
if reject_non_read_http(self, 'PATCH', path): return
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
def do_DELETE(self):
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/')
|
||||
if reject_non_read_http(self, 'DELETE', path): return
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
def branch(self,data):
|
||||
a=self.need('branch:create');
|
||||
if not a: return
|
||||
@@ -285,12 +681,41 @@ class H(BaseHTTPRequestHandler):
|
||||
if not a: return
|
||||
ver=data.get('version') or data.get('tag')
|
||||
if not re.match(r'^V\d+R\d+C\d+(-[A-Za-z0-9_.-]+)?$', ver or ''): return self.sendj({'error':'version must match VxRxCx'},400)
|
||||
if data.get('confirm') != True:
|
||||
self.sendj({'status':'confirm_required','operation':'tag','hint':'This operation creates a Git tag. Confirm to proceed.','x-openai-isConsequential':True}, 428)
|
||||
return
|
||||
if not data.get('target_oid') or not data.get('evidence_closure_oid') or not data.get('approval_plan_id'):
|
||||
return self.sendj({
|
||||
'error':'production_tag_evidence_required',
|
||||
'required':['version','target_oid','evidence_closure_oid','approval_plan_id'],
|
||||
},400)
|
||||
try:
|
||||
target_oid=resolve_commit_oid(data.get('target_oid'))
|
||||
evidence_oid=resolve_commit_oid(data.get('evidence_closure_oid'), 'evidence_closure_oid')
|
||||
except ValueError as exc:
|
||||
return self.sendj({'error':'invalid_tag_target','detail':str(exc)},400)
|
||||
if a['role'] != 'owner' or not data.get('execute'):
|
||||
b=checkout(data.get('branch') or f'request/tag-{safe(ver)}', 'main', True); req={'version':ver,'requested_by':a['account'],'approval_required':True,'created_at':now()}; r=write_json(f'baseline/tag_requests/{safe(ver)}.json', req); c=commit([r], f'chore(chatgpt): request tag {ver}'); return self.sendj({'status':'approval_required','branch':b,'commit':c})
|
||||
out=sh(['tag','-a',ver,'-m',data.get('message') or f'release {ver}'], True); self.sendj({'status':'tagged','version':ver,'git':out,'sync':sync_tag(ver)})
|
||||
b=checkout(data.get('branch') or f'request/tag-{safe(ver)}', 'main', True); req={'version':ver,'target_oid':target_oid,'evidence_closure_oid':evidence_oid,'approval_plan_id':data.get('approval_plan_id'),'requested_by':a['account'],'approval_required':True,'created_at':now()}; r=write_json(f'baseline/tag_requests/{safe(ver)}.json', req); c=commit([r], f'chore(chatgpt): request tag {ver}'); return self.sendj({'status':'approval_required','branch':b,'request':req,'commit':c})
|
||||
request=PublicationRequest(ver,target_oid,evidence_oid,str(data.get('approval_plan_id')))
|
||||
main_before=sh(['rev-parse','refs/heads/main'], True)['stdout']
|
||||
publisher=publication_publisher()
|
||||
try:
|
||||
publication=publisher.publish(request)
|
||||
except PublicationManualOwnerReviewRequired as exc:
|
||||
audit(a['account'],'tag_manual_owner_review_required',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':redact(exc)})
|
||||
return self.sendj({'status':'MANUAL_OWNER_REVIEW_REQUIRED','error':redact(exc),'main_changed':False,'force_push':False},409)
|
||||
except PublicationConflict as exc:
|
||||
audit(a['account'],'tag_conflict',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':str(exc)})
|
||||
return self.sendj({'status':'RECONCILIATION_REQUIRED','error':str(exc),'main_changed':False,'force_push':False},409)
|
||||
except PublicationPending as exc:
|
||||
audit(a['account'],'tag_pending',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':str(exc)})
|
||||
return self.sendj({'status':'REMOTE_PUSH_PENDING','error':str(exc),'main_changed':False,'force_push':False},503)
|
||||
except PublicationReconciliationRequired as exc:
|
||||
audit(a['account'],'tag_reconciliation_required',ver,{'target_oid':target_oid,'approval_plan_id':data.get('approval_plan_id'),'error':str(exc)})
|
||||
return self.sendj({'status':'RECONCILIATION_REQUIRED','error':str(exc),'main_changed':False,'force_push':False},502)
|
||||
main_after=sh(['rev-parse','refs/heads/main'], True)['stdout']
|
||||
if main_after != main_before:
|
||||
raise RuntimeError('main changed during tag operation')
|
||||
result={'status':publication['state'],'version':ver,'tag_name':ver,'tag_oid':publication['tag_oid'],'target_oid':target_oid,'expected_target_oid':target_oid,'evidence_closure_oid':evidence_oid,'approval_plan_id':data.get('approval_plan_id'),'workspace_head':sh(['rev-parse','HEAD'],True)['stdout'],'main_oid_before':main_before,'main_oid_after':main_after,'main_changed':False,'force_push':False,'publication':publication}
|
||||
audit(a['account'],'tag',ver,result)
|
||||
self.sendj(result)
|
||||
def rollback(self,data):
|
||||
a=self.need('rollback:request');
|
||||
if not a: return
|
||||
@@ -385,7 +810,10 @@ return{vs,cmds,ar,cmd,cdet,tot,sok,sfail,runs,baseline,refreshMsg,loadCmd,selVer
|
||||
cmd_filter=(params.get('command') or [None])[0]
|
||||
bl=jload(WS/'baseline'/'current.json',{})
|
||||
current_ver=bl.get('current_baseline','V1R3C1')
|
||||
tags=sh(['tag','--list','V*'])['stdout'].splitlines() if WS.exists() else []
|
||||
try:
|
||||
tags=[item['name'] for item in authoritative_tags(git_dir=required_authoritative_git_dir()) if str(item['name']).startswith('V')]
|
||||
except (AuthoritativeGitError, RuntimeError) as exc:
|
||||
return self.sendj({'error':redact(exc),'repository_available':False},503)
|
||||
versions=[]
|
||||
if (WS/'baseline'/'promotions').exists():
|
||||
for p in sorted((WS/'baseline'/'promotions').glob('*.json')):
|
||||
@@ -423,7 +851,7 @@ return{vs,cmds,ar,cmd,cdet,tot,sok,sfail,runs,baseline,refreshMsg,loadCmd,selVer
|
||||
|
||||
|
||||
def api_spec():
|
||||
return {'version':'V1R1C0-chatgpt-actions','openapi':'/api/openapi.yaml','orchestrator_openapi':'/api/orchestrator-decision.openapi.yaml','read':['GET /api/base','GET /api/ver','GET /api/diff','GET /api/patch','GET /api/model','GET /api/run','GET /admin/ai-evolution'],'write':['POST /v1/orchestrator/decisions','POST /api/branch','POST /api/file','POST /api/commit','POST /api/patch','POST /api/tag','POST /api/rollback','POST /api/model','PUT /api/model-priority','POST /api/nl'],'policy':{'bearer_required_for_write':True,'orchestrator_decision_scope':'orchestrator:decision','orchestrator_callback_credential':'secret_ref_only','direct_main_push':False,'delete_tag':False,'owner_approval_required_for_v_level':True,'api_keys_in_git':False,'git_secret_field':'secret_ref','online_git_sync':True}}
|
||||
return {'version':'V1R1C0-chatgpt-actions','openapi':'/api/openapi.yaml','read':['GET /api/base','GET /api/ver','GET /api/diff','GET /api/patch','GET /api/model','GET /api/run','GET /getReleaseCandidate','GET /getApprovalEnvelope','GET /getReleaseSaga','GET /admin/ai-evolution'],'write':['POST /api/branch','POST /api/file','POST /api/commit','POST /api/patch','POST /api/tag','POST /api/rollback','POST /api/model','PUT /api/model-priority','POST /api/nl','POST /createReleaseCandidate','POST /submitOwnerApproval','POST /startDeployment'],'policy':{'bearer_required_for_write':True,'direct_main_push':False,'delete_tag':False,'owner_approval_required_for_v_level':True,'api_keys_in_git':False,'git_secret_field':'secret_ref','online_git_sync':True,'silent_release_execution_enabled':SILENT_RELEASE_EXECUTION_ENABLED,'silent_release_shadow_default':True}}
|
||||
|
||||
def main():
|
||||
print(f'AIOS ChatGPT GitOps adapter listening on {HOST}:{PORT}')
|
||||
|
||||
@@ -0,0 +1,52 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Fail-closed policy for in-process Git mutation handlers."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Mapping
|
||||
|
||||
_TRUE = frozenset({"1", "true", "yes", "on"})
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GitWriteDecision:
|
||||
allowed: bool
|
||||
status_code: int
|
||||
error: str
|
||||
reason: str
|
||||
workspace: str
|
||||
|
||||
def payload(self) -> dict[str, str]:
|
||||
return {
|
||||
"status": "allowed" if self.allowed else "blocked",
|
||||
"error": self.error,
|
||||
"reason": self.reason,
|
||||
"workspace": self.workspace,
|
||||
}
|
||||
|
||||
|
||||
def _real(path: Path) -> Path:
|
||||
return Path(os.path.realpath(os.path.abspath(str(path))))
|
||||
|
||||
|
||||
def evaluate_git_write(workspace: Path | str, env: Mapping[str, str] | None = None) -> GitWriteDecision:
|
||||
values = os.environ if env is None else env
|
||||
lexical = Path(os.path.abspath(str(workspace)))
|
||||
canonical = _real(lexical)
|
||||
shown = str(lexical)
|
||||
if str(values.get("AIOS_GITOPS_WRITES_ENABLED", "false")).strip().lower() not in _TRUE:
|
||||
return GitWriteDecision(False, 423, "gitops_writes_disabled", "AIOS_GITOPS_WRITES_ENABLED is false", shown)
|
||||
if lexical != canonical:
|
||||
return GitWriteDecision(False, 409, "workspace_symlink_forbidden", "workspace must be a canonical non-symlink path", shown)
|
||||
controller = _real(Path(values.get("AIOS_GITOPS_CONTROLLER_PATH", "/data/aios-gitops/worktrees/controller")))
|
||||
role = str(values.get("AIOS_GITOPS_WORKSPACE_ROLE", "")).strip().lower()
|
||||
if canonical == controller or role == "runtime-anchor":
|
||||
return GitWriteDecision(False, 423, "runtime_anchor_read_only", "controller/runtime-anchor is read-only", str(canonical))
|
||||
writer_root = _real(Path(values.get("AIOS_GITOPS_APPROVED_WRITER_ROOT", "/data/aios-gitops/worktrees")))
|
||||
try:
|
||||
canonical.relative_to(writer_root)
|
||||
except ValueError:
|
||||
return GitWriteDecision(False, 409, "workspace_not_approved_writer", "workspace is outside the approved writer root", str(canonical))
|
||||
return GitWriteDecision(True, 200, "", "approved isolated writer", str(canonical))
|
||||
@@ -0,0 +1,69 @@
|
||||
"""CLI client for the governed local writer service."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import socket
|
||||
import sys
|
||||
|
||||
|
||||
def _parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="Send one governed-local-writer request")
|
||||
parser.add_argument("--socket", required=True, help="AF_UNIX socket path")
|
||||
group = parser.add_mutually_exclusive_group(required=True)
|
||||
group.add_argument("--request", help="Request JSON string")
|
||||
group.add_argument("--request-file", help="Path to JSON request file")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def _load_request_text(args: argparse.Namespace) -> str:
|
||||
if args.request is not None:
|
||||
return args.request
|
||||
request_path = os.fspath(args.request_file)
|
||||
with open(request_path, "r", encoding="utf-8") as request_file:
|
||||
return request_file.read()
|
||||
|
||||
|
||||
def send_request(socket_path: str, request_text: str) -> dict[str, object]:
|
||||
"""Open one Unix socket, send one NDJSON request, and parse one NDJSON response."""
|
||||
payload = json.loads(request_text)
|
||||
if not isinstance(payload, dict):
|
||||
raise ValueError("request must be a JSON object")
|
||||
|
||||
with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as client:
|
||||
client.connect(socket_path)
|
||||
client.sendall((json.dumps(payload) + "\n").encode("utf-8"))
|
||||
response_chunks: list[str] = []
|
||||
while True:
|
||||
chunk = client.recv(1024 * 1024).decode("utf-8")
|
||||
if not chunk:
|
||||
break
|
||||
response_chunks.append(chunk)
|
||||
if "\n" in chunk:
|
||||
break
|
||||
response_text = "".join(response_chunks)
|
||||
|
||||
response_line = response_text.split("\n", 1)[0].strip()
|
||||
if not response_line:
|
||||
raise RuntimeError("empty response")
|
||||
response = json.loads(response_line)
|
||||
if not isinstance(response, dict):
|
||||
raise RuntimeError("invalid response")
|
||||
return response
|
||||
|
||||
|
||||
def main() -> None:
|
||||
args = _parse_args()
|
||||
request_text = _load_request_text(args)
|
||||
response = send_request(args.socket, request_text)
|
||||
print(json.dumps(response, separators=(",", ":"), sort_keys=True))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
main()
|
||||
except Exception as exc: # pragma: no cover - CLI entrypoint behavior
|
||||
print(json.dumps({"status": "error", "error": str(exc)}), file=sys.stderr)
|
||||
raise SystemExit(1)
|
||||
@@ -0,0 +1,931 @@
|
||||
"""Unix-socket service for governed local writer operations."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import hashlib
|
||||
import argparse
|
||||
import importlib.util
|
||||
import os
|
||||
import re
|
||||
import socket
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import uuid
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Mapping, Protocol
|
||||
|
||||
from governed_local_writer import (
|
||||
AppendCommitRequest,
|
||||
AuthorizationError,
|
||||
BranchPolicy,
|
||||
CreateBranchRequest,
|
||||
GovernedAuthorization,
|
||||
PeerIdentity,
|
||||
PRINCIPAL,
|
||||
TASK_ID,
|
||||
extract_peer_identity,
|
||||
contains_secret_like_content,
|
||||
load_authorization_file,
|
||||
validate_file_changes,
|
||||
)
|
||||
|
||||
|
||||
class ExistingGitOpsHandler:
|
||||
"""Delegate repository mutations to the installed GitOps handler seam."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
workspace_by_branch: Mapping[str, str | os.PathLike[str]],
|
||||
bare_repo: str | os.PathLike[str],
|
||||
api_source: str | os.PathLike[str],
|
||||
) -> None:
|
||||
self.workspace_by_branch = {str(k): Path(v) for k, v in workspace_by_branch.items()}
|
||||
self.bare_repo = Path(bare_repo)
|
||||
self.api_source = Path(api_source)
|
||||
|
||||
@staticmethod
|
||||
def _restore_env(previous: Mapping[str, str | None]) -> None:
|
||||
for key, value in previous.items():
|
||||
if value is None:
|
||||
os.environ.pop(key, None)
|
||||
else:
|
||||
os.environ[key] = value
|
||||
|
||||
def _load_api(self, workspace: Path):
|
||||
if not self.api_source.is_file() or self.api_source.is_symlink():
|
||||
raise RuntimeError("installed GitOps handler source is unavailable")
|
||||
keys = (
|
||||
"AIOS_GITOPS_WORKSPACE",
|
||||
"AIOS_GITOPS_BARE_REPO",
|
||||
"AIOS_GITOPS_WRITES_ENABLED",
|
||||
"PYTHONDONTWRITEBYTECODE",
|
||||
"GIT_CONFIG_COUNT",
|
||||
"GIT_CONFIG_KEY_0",
|
||||
"GIT_CONFIG_VALUE_0",
|
||||
"GIT_CONFIG_KEY_1",
|
||||
"GIT_CONFIG_VALUE_1",
|
||||
)
|
||||
previous = {key: os.environ.get(key) for key in keys}
|
||||
os.environ.update(
|
||||
{
|
||||
"AIOS_GITOPS_WORKSPACE": str(workspace),
|
||||
"AIOS_GITOPS_BARE_REPO": str(self.bare_repo),
|
||||
"AIOS_GITOPS_WRITES_ENABLED": "true",
|
||||
"PYTHONDONTWRITEBYTECODE": "1",
|
||||
"GIT_CONFIG_COUNT": "2",
|
||||
"GIT_CONFIG_KEY_0": "safe.directory",
|
||||
"GIT_CONFIG_VALUE_0": str(workspace),
|
||||
"GIT_CONFIG_KEY_1": "safe.directory",
|
||||
"GIT_CONFIG_VALUE_1": str(self.bare_repo),
|
||||
}
|
||||
)
|
||||
module_name = f"_governed_gitops_api_{uuid.uuid4().hex}"
|
||||
try:
|
||||
spec = importlib.util.spec_from_file_location(module_name, self.api_source)
|
||||
if spec is None or spec.loader is None:
|
||||
raise RuntimeError("unable to load installed GitOps handler")
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
sys.modules[module_name] = module
|
||||
spec.loader.exec_module(module)
|
||||
decision = module.evaluate_git_write(module.WS)
|
||||
if not decision.allowed:
|
||||
raise RuntimeError("existing GitOps write gate denied bootstrap")
|
||||
return module, previous, module_name
|
||||
except Exception:
|
||||
sys.modules.pop(module_name, None)
|
||||
self._restore_env(previous)
|
||||
raise
|
||||
|
||||
def _workspace(self, branch: str) -> Path:
|
||||
workspace = self.workspace_by_branch.get(branch)
|
||||
if workspace is None or not workspace.is_dir():
|
||||
raise RuntimeError("branch workspace is not authorized")
|
||||
return workspace
|
||||
|
||||
@staticmethod
|
||||
def _git(workspace: Path, args: list[str]) -> str:
|
||||
result = subprocess.run(
|
||||
["git", *args], cwd=workspace, text=True, capture_output=True, check=False
|
||||
)
|
||||
if result.returncode != 0:
|
||||
raise RuntimeError("governed handler git probe failed")
|
||||
return result.stdout.strip()
|
||||
|
||||
def create_branch(self, request: CreateBranchRequest) -> Mapping[str, object]:
|
||||
workspace = self._workspace(request.branch)
|
||||
# A prior handler call may have completed the fast-forward sync before
|
||||
# the process observed a post-commit error. Reconcile only an exact,
|
||||
# metadata-only result; never overwrite or move an existing ref here.
|
||||
try:
|
||||
existing = self._git(
|
||||
workspace,
|
||||
[
|
||||
"--git-dir",
|
||||
str(self.bare_repo),
|
||||
"rev-parse",
|
||||
f"refs/heads/{request.branch}",
|
||||
],
|
||||
)
|
||||
except RuntimeError:
|
||||
existing = ""
|
||||
if existing:
|
||||
parent = self._git(workspace, ["--git-dir", str(self.bare_repo), "rev-parse", f"{existing}^1"])
|
||||
changed = self._git(
|
||||
workspace,
|
||||
[
|
||||
"--git-dir",
|
||||
str(self.bare_repo),
|
||||
"diff-tree",
|
||||
"--no-commit-id",
|
||||
"--name-only",
|
||||
"-r",
|
||||
existing,
|
||||
],
|
||||
).splitlines()
|
||||
safe_branch = re.sub(r"[^A-Za-z0-9_.-]+", "-", request.branch).strip("-")
|
||||
if parent != request.base_oid or changed != [f"patches/{safe_branch}.branch.json"]:
|
||||
raise RuntimeError("existing branch is not an exact metadata-only bootstrap")
|
||||
return {"head_oid": existing, "parent_oid": parent, "handler_status": "reconciled"}
|
||||
module, previous, module_name = self._load_api(workspace)
|
||||
phase = "loaded"
|
||||
try:
|
||||
phase = "verify_base"
|
||||
parent = self._git(
|
||||
workspace,
|
||||
["--git-dir", str(self.bare_repo), "rev-parse", "refs/heads/main"],
|
||||
)
|
||||
if parent != request.base_oid:
|
||||
raise RuntimeError("authorized base OID drift")
|
||||
phase = "checkout"
|
||||
module.checkout(request.branch, base=request.base_oid, create=True)
|
||||
phase = "write_metadata"
|
||||
safe_branch = re.sub(r"[^A-Za-z0-9_.-]+", "-", request.branch).strip("-")
|
||||
metadata_path = f"patches/{safe_branch}.branch.json"
|
||||
module.write_json(
|
||||
metadata_path,
|
||||
{
|
||||
"schema": "aios.governed-local-writer-bootstrap.v1",
|
||||
"task_id": TASK_ID,
|
||||
"principal": PRINCIPAL,
|
||||
"branch": request.branch,
|
||||
"parent_oid": request.base_oid,
|
||||
"authorization_sha256": request.authorization_digest,
|
||||
},
|
||||
)
|
||||
phase = "commit_and_sync"
|
||||
result = module.commit(
|
||||
[metadata_path], "chore(governance): bootstrap repair lease branch"
|
||||
)
|
||||
head_oid = self._git(workspace, ["rev-parse", "HEAD"])
|
||||
first_parent = self._git(workspace, ["rev-parse", "HEAD^1"])
|
||||
if first_parent != request.base_oid or (request.head_oid and head_oid != request.head_oid):
|
||||
raise RuntimeError("bootstrap branch lineage check failed")
|
||||
return {
|
||||
"head_oid": head_oid,
|
||||
"parent_oid": first_parent,
|
||||
"handler_status": str(result.get("status")),
|
||||
}
|
||||
except Exception as exc:
|
||||
raise RuntimeError(f"handler_phase={phase};error={exc.__class__.__name__}") from exc
|
||||
finally:
|
||||
sys.modules.pop(module_name, None)
|
||||
self._restore_env(previous)
|
||||
|
||||
def append_commit(self, request: AppendCommitRequest) -> Mapping[str, object]:
|
||||
workspace = self._workspace(request.branch)
|
||||
module, previous, module_name = self._load_api(workspace)
|
||||
phase = "loaded"
|
||||
try:
|
||||
phase = "verify_head"
|
||||
current = self._git(workspace, ["rev-parse", "HEAD"])
|
||||
if current != request.expected_head_oid:
|
||||
raise RuntimeError("branch head advanced or is stale")
|
||||
phase = "checkout"
|
||||
module.checkout(request.branch, base=request.expected_head_oid, create=False)
|
||||
phase = "write_files"
|
||||
paths: list[str] = []
|
||||
for change in request.changes:
|
||||
paths.append(module.write_file(change.path, change.content))
|
||||
phase = "commit_and_sync"
|
||||
result = module.commit(paths, request.commit_message)
|
||||
head_oid = self._git(workspace, ["rev-parse", "HEAD"])
|
||||
first_parent = self._git(workspace, ["rev-parse", "HEAD^1"])
|
||||
if first_parent != request.expected_head_oid or head_oid == first_parent:
|
||||
raise RuntimeError("append commit lineage check failed")
|
||||
return {
|
||||
"head_oid": head_oid,
|
||||
"parent_oid": first_parent,
|
||||
"handler_status": str(result.get("status")),
|
||||
}
|
||||
except Exception as exc:
|
||||
raise RuntimeError(f"handler_phase={phase};error={exc.__class__.__name__}") from exc
|
||||
finally:
|
||||
sys.modules.pop(module_name, None)
|
||||
self._restore_env(previous)
|
||||
|
||||
|
||||
class GovernedWriterHandler(Protocol):
|
||||
"""Small adapter interface for real writer backend handlers."""
|
||||
|
||||
def create_branch(self, request: CreateBranchRequest) -> Mapping[str, object]:
|
||||
"""Create a branch using internal repo services."""
|
||||
|
||||
def append_commit(self, request: AppendCommitRequest) -> Mapping[str, object]:
|
||||
"""Append a commit using internal repo services."""
|
||||
|
||||
|
||||
class AuditSink(Protocol):
|
||||
"""Pluggable sink for sanitized audit records."""
|
||||
|
||||
def append(self, record: "AuditRecord") -> None:
|
||||
"""Persist one audit record."""
|
||||
|
||||
|
||||
@dataclass
|
||||
class AuditRecord:
|
||||
"""Sanitized audit log entry."""
|
||||
|
||||
authorization_digest: str
|
||||
peer_pid: int
|
||||
peer_uid: int
|
||||
peer_gid: int
|
||||
peer_executable: str | None
|
||||
timestamp: datetime
|
||||
operation: str
|
||||
branch: str
|
||||
result: str
|
||||
|
||||
|
||||
class InMemoryAuditSink:
|
||||
"""Simple in-memory audit log used by tests."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.records: list[AuditRecord] = []
|
||||
|
||||
def append(self, record: AuditRecord) -> None:
|
||||
self.records.append(record)
|
||||
|
||||
|
||||
@dataclass
|
||||
class _AuthorizationState:
|
||||
"""Tracks one-shot operation consumption."""
|
||||
|
||||
create_done: set[str] = field(default_factory=set)
|
||||
append_done: set[str] = field(default_factory=set)
|
||||
consumed: bool = False
|
||||
|
||||
|
||||
class GovernedLocalWriterService:
|
||||
"""Policy-aware AF_UNIX service that calls an injected handler."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
socket_path: str | os.PathLike[str],
|
||||
authorization: GovernedAuthorization,
|
||||
handler: GovernedWriterHandler,
|
||||
*,
|
||||
audit_sink: AuditSink | None = None,
|
||||
peer_identity_fn: Callable[[socket.socket], PeerIdentity] | None = None,
|
||||
state_path: str | os.PathLike[str] | None = None,
|
||||
) -> None:
|
||||
self.socket_path = Path(socket_path)
|
||||
self.authorization = authorization
|
||||
self.handler = handler
|
||||
self.peer_identity_fn = peer_identity_fn or extract_peer_identity
|
||||
self.state = _AuthorizationState()
|
||||
self.audit_sink = audit_sink or InMemoryAuditSink()
|
||||
self.state_path = Path(state_path) if state_path is not None else None
|
||||
self._load_state()
|
||||
|
||||
def _load_state(self) -> None:
|
||||
"""Restore one-shot state without restoring request or secret material."""
|
||||
if self.state_path is None or not self.state_path.exists():
|
||||
return
|
||||
try:
|
||||
raw = json.loads(self.state_path.read_text(encoding="utf-8"))
|
||||
if not isinstance(raw, dict):
|
||||
raise ValueError("state must be an object")
|
||||
if raw.get("authorization_sha256") != self.authorization.authorization_sha256:
|
||||
raise ValueError("state authorization digest mismatch")
|
||||
self.state.create_done = {str(v) for v in raw.get("create_done", [])}
|
||||
self.state.append_done = {str(v) for v in raw.get("append_done", [])}
|
||||
self.state.consumed = bool(raw.get("consumed", False))
|
||||
except (OSError, ValueError, TypeError, json.JSONDecodeError) as exc:
|
||||
raise AuthorizationError("authorization state is invalid") from exc
|
||||
|
||||
def _persist_state(self) -> None:
|
||||
if self.state_path is None:
|
||||
return
|
||||
self.state_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
payload = {
|
||||
"authorization_sha256": self.authorization.authorization_sha256,
|
||||
"create_done": sorted(self.state.create_done),
|
||||
"append_done": sorted(self.state.append_done),
|
||||
"consumed": self.state.consumed,
|
||||
}
|
||||
fd, temp_name = tempfile.mkstemp(prefix=".writer-state-", dir=self.state_path.parent)
|
||||
try:
|
||||
os.fchmod(fd, 0o600)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as stream:
|
||||
json.dump(payload, stream, sort_keys=True, separators=(",", ":"))
|
||||
stream.write("\n")
|
||||
os.replace(temp_name, self.state_path)
|
||||
os.chmod(self.state_path, 0o600)
|
||||
finally:
|
||||
if os.path.exists(temp_name):
|
||||
os.unlink(temp_name)
|
||||
|
||||
def _new_audit(self, peer: PeerIdentity, operation: str, branch: str, result: str) -> None:
|
||||
self.audit_sink.append(
|
||||
AuditRecord(
|
||||
authorization_digest=self.authorization.authorization_sha256,
|
||||
peer_pid=peer.pid,
|
||||
peer_uid=peer.uid,
|
||||
peer_gid=peer.gid,
|
||||
peer_executable=peer.executable,
|
||||
timestamp=datetime.now(tz=timezone.utc),
|
||||
operation=operation,
|
||||
branch=branch,
|
||||
result=result,
|
||||
)
|
||||
)
|
||||
|
||||
def _require_request_field(self, request: Mapping[str, Any], field_name: str) -> str:
|
||||
value = request.get(field_name)
|
||||
if not isinstance(value, str) or not value:
|
||||
raise AuthorizationError(f"{field_name} must be a non-empty string")
|
||||
return value
|
||||
|
||||
def _branch_policy(self, branch: str) -> BranchPolicy:
|
||||
policy = self.authorization.branch_operations.get(branch)
|
||||
if policy is None:
|
||||
raise AuthorizationError("branch is not authorized")
|
||||
return policy
|
||||
|
||||
def _ensure_not_consumed(self) -> None:
|
||||
if self.state.consumed:
|
||||
raise AuthorizationError("authorization consumed")
|
||||
if datetime.now(tz=timezone.utc) >= self.authorization.expires_at:
|
||||
raise AuthorizationError("authorization expired")
|
||||
|
||||
def _mark_success(self, op: str, branch: str) -> None:
|
||||
if op == "create_branch":
|
||||
self.state.create_done.add(branch)
|
||||
elif op == "append_commit":
|
||||
self.state.append_done.add(branch)
|
||||
|
||||
if self.state.create_done.issuperset(self.authorization.create_branches) and self.state.append_done.issuperset(
|
||||
self.authorization.append_branches
|
||||
):
|
||||
self.state.consumed = True
|
||||
self._persist_state()
|
||||
|
||||
def _validate_request(self, request: Mapping[str, Any]) -> dict[str, Any]:
|
||||
task_id = self._require_request_field(request, "task_id")
|
||||
if task_id != TASK_ID:
|
||||
raise AuthorizationError("invalid task_id")
|
||||
|
||||
principal = self._require_request_field(request, "principal")
|
||||
if principal != PRINCIPAL:
|
||||
raise AuthorizationError("invalid principal")
|
||||
|
||||
operation = self._require_request_field(request, "op")
|
||||
if operation not in {"create_branch", "append_commit"}:
|
||||
raise AuthorizationError("unsupported operation")
|
||||
if operation in self.authorization.denied_operations:
|
||||
raise AuthorizationError("operation denied by policy")
|
||||
|
||||
branch = self._require_request_field(request, "branch")
|
||||
self._ensure_not_consumed()
|
||||
policy = self._branch_policy(branch)
|
||||
|
||||
if operation == "create_branch":
|
||||
if policy.create_branch is None:
|
||||
raise AuthorizationError("branch does not allow create_branch")
|
||||
if branch in self.state.create_done:
|
||||
raise AuthorizationError("create_branch already used for this branch")
|
||||
|
||||
base_oid = self._require_request_field(request, "base_oid")
|
||||
raw_head_oid = request.get("head_oid")
|
||||
if raw_head_oid is not None and (not isinstance(raw_head_oid, str) or not raw_head_oid):
|
||||
raise AuthorizationError("head_oid must be a non-empty string when supplied")
|
||||
head_oid = str(raw_head_oid) if raw_head_oid is not None else None
|
||||
if base_oid != policy.create_branch.base_oid:
|
||||
raise AuthorizationError("base_oid mismatch")
|
||||
if policy.create_branch.head_oid is not None and head_oid != policy.create_branch.head_oid:
|
||||
raise AuthorizationError("head_oid mismatch")
|
||||
|
||||
return {
|
||||
"operation": operation,
|
||||
"branch": branch,
|
||||
"base_oid": base_oid,
|
||||
"head_oid": head_oid,
|
||||
}
|
||||
|
||||
if policy.append_commit is None:
|
||||
raise AuthorizationError("branch does not allow append_commit")
|
||||
if policy.create_branch is not None and branch not in self.state.create_done:
|
||||
raise AuthorizationError("append_commit requires prior successful create_branch")
|
||||
if branch in self.state.append_done:
|
||||
raise AuthorizationError("append_commit already used for this branch")
|
||||
|
||||
expected_head = policy.append_commit.expected_head_oid
|
||||
if "expected_head_oid" in request:
|
||||
supplied_head = self._require_request_field(request, "expected_head_oid")
|
||||
elif "current_head_oid" in request:
|
||||
supplied_head = self._require_request_field(request, "current_head_oid")
|
||||
else:
|
||||
raise AuthorizationError("expected_head_oid or current_head_oid required")
|
||||
if not re.fullmatch(r"[0-9a-fA-F]{40}", supplied_head):
|
||||
raise AuthorizationError("head check must be a full commit OID")
|
||||
if expected_head is not None and supplied_head != expected_head:
|
||||
raise AuthorizationError("head check failed")
|
||||
|
||||
if request.get("force") is True or request.get("non_fast_forward") is True:
|
||||
raise AuthorizationError("non-fast-forward operations are not allowed")
|
||||
if request.get("history_rewrite") is True:
|
||||
raise AuthorizationError("history rewrite is not allowed")
|
||||
parent_oids = request.get("parent_oids")
|
||||
if parent_oids is not None:
|
||||
if not isinstance(parent_oids, list) or parent_oids != [supplied_head]:
|
||||
raise AuthorizationError("parent_oids must contain exactly expected_head_oid")
|
||||
|
||||
changes = request.get("changes")
|
||||
if not isinstance(changes, list):
|
||||
raise AuthorizationError("changes must be a list")
|
||||
validated_changes = validate_file_changes(changes, policy.append_commit.allowed_paths)
|
||||
commit_message = request.get("commit_message", "chore(governance): append governed commit")
|
||||
if not isinstance(commit_message, str) or not commit_message.strip() or len(commit_message) > 200:
|
||||
raise AuthorizationError("commit_message must be a short non-empty string")
|
||||
if "\n" in commit_message or "\r" in commit_message or contains_secret_like_content(commit_message):
|
||||
raise AuthorizationError("commit_message failed policy")
|
||||
|
||||
return {
|
||||
"operation": operation,
|
||||
"branch": branch,
|
||||
"expected_head_oid": supplied_head,
|
||||
"changes": validated_changes,
|
||||
"commit_message": commit_message.strip(),
|
||||
}
|
||||
|
||||
def process_request(self, raw_request: Mapping[str, Any], peer: PeerIdentity) -> Mapping[str, Any]:
|
||||
"""Run one request through policy checks and handler adapter."""
|
||||
operation = raw_request.get("op") if isinstance(raw_request.get("op"), str) else "unknown"
|
||||
branch = raw_request.get("branch") if isinstance(raw_request.get("branch"), str) else ""
|
||||
try:
|
||||
details = self._validate_request(raw_request)
|
||||
operation = str(details["operation"])
|
||||
branch = str(details["branch"])
|
||||
|
||||
if operation == "create_branch":
|
||||
self.handler.create_branch(
|
||||
CreateBranchRequest(
|
||||
branch=branch,
|
||||
base_oid=str(details["base_oid"]),
|
||||
head_oid=(
|
||||
str(details["head_oid"])
|
||||
if details.get("head_oid") is not None
|
||||
else None
|
||||
),
|
||||
authorization_digest=self.authorization.authorization_sha256,
|
||||
)
|
||||
)
|
||||
self._mark_success("create_branch", branch)
|
||||
self._new_audit(peer, operation, branch, "ok")
|
||||
return {
|
||||
"status": "ok",
|
||||
"operation": operation,
|
||||
"branch": branch,
|
||||
"result": "applied",
|
||||
}
|
||||
|
||||
self.handler.append_commit(
|
||||
AppendCommitRequest(
|
||||
branch=branch,
|
||||
expected_head_oid=str(details["expected_head_oid"]),
|
||||
changes=tuple(details["changes"]),
|
||||
authorization_digest=self.authorization.authorization_sha256,
|
||||
commit_message=str(details["commit_message"]),
|
||||
)
|
||||
)
|
||||
self._mark_success("append_commit", branch)
|
||||
self._new_audit(peer, operation, branch, "ok")
|
||||
return {
|
||||
"status": "ok",
|
||||
"operation": operation,
|
||||
"branch": branch,
|
||||
"result": "applied",
|
||||
}
|
||||
except Exception as error:
|
||||
self._new_audit(peer, operation or "unknown", branch, f"error:{error.__class__.__name__}")
|
||||
if isinstance(error, PermissionError):
|
||||
code = "permission_denied"
|
||||
elif isinstance(error, AuthorizationError):
|
||||
code = "request_denied"
|
||||
else:
|
||||
code = "handler_failed"
|
||||
if code == "handler_failed" and str(error).startswith("handler_phase="):
|
||||
code = str(error)
|
||||
return {
|
||||
"status": "error",
|
||||
"operation": operation or "unknown",
|
||||
"branch": branch,
|
||||
"error": code,
|
||||
}
|
||||
|
||||
def _write_json(self, connection: socket.socket, payload: Mapping[str, Any]) -> None:
|
||||
connection.sendall((json.dumps(payload) + "\n").encode("utf-8"))
|
||||
|
||||
def _handle_client(self, connection: socket.socket) -> None:
|
||||
with connection:
|
||||
try:
|
||||
peer = self.peer_identity_fn(connection)
|
||||
except Exception:
|
||||
self._write_json(
|
||||
connection,
|
||||
{
|
||||
"status": "error",
|
||||
"operation": "connection",
|
||||
"branch": "",
|
||||
"error": "peer identity validation failed",
|
||||
},
|
||||
)
|
||||
return
|
||||
|
||||
with connection.makefile("r", encoding="utf-8") as stream:
|
||||
for raw_line in stream:
|
||||
line = raw_line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
request = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
self._write_json(
|
||||
connection,
|
||||
{
|
||||
"status": "error",
|
||||
"operation": "request",
|
||||
"branch": "",
|
||||
"error": "invalid json",
|
||||
},
|
||||
)
|
||||
continue
|
||||
if not isinstance(request, Mapping):
|
||||
self._write_json(
|
||||
connection,
|
||||
{
|
||||
"status": "error",
|
||||
"operation": "request",
|
||||
"branch": "",
|
||||
"error": "request must be a JSON object",
|
||||
},
|
||||
)
|
||||
continue
|
||||
self._write_json(connection, self.process_request(request, peer))
|
||||
|
||||
def _bind_socket(self) -> socket.socket:
|
||||
if self.socket_path.exists():
|
||||
raise RuntimeError("governed writer socket already exists")
|
||||
parent = self.socket_path.parent
|
||||
if not parent.is_dir():
|
||||
raise RuntimeError("governed writer socket parent is missing")
|
||||
if parent.is_symlink():
|
||||
raise RuntimeError("governed writer socket parent must not be a symlink")
|
||||
server = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
|
||||
server.bind(str(self.socket_path))
|
||||
os.chmod(self.socket_path, 0o600)
|
||||
server.listen(16)
|
||||
return server
|
||||
|
||||
def serve(self) -> None:
|
||||
"""Serve newline-delimited JSON over a filesystem AF_UNIX socket."""
|
||||
server = self._bind_socket()
|
||||
try:
|
||||
while True:
|
||||
connection, _ = server.accept()
|
||||
self._handle_client(connection)
|
||||
finally:
|
||||
server.close()
|
||||
if self.socket_path.exists():
|
||||
self.socket_path.unlink()
|
||||
|
||||
|
||||
class JsonAuditSink:
|
||||
"""Append-only root-owned audit sink containing no request payloads."""
|
||||
|
||||
def __init__(self, path: str | os.PathLike[str]) -> None:
|
||||
self.path = Path(path)
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def append(self, record: AuditRecord) -> None:
|
||||
payload = {
|
||||
"authorization_sha256": record.authorization_digest,
|
||||
"peer_pid": record.peer_pid,
|
||||
"peer_uid": record.peer_uid,
|
||||
"peer_gid": record.peer_gid,
|
||||
"peer_executable": record.peer_executable,
|
||||
"timestamp": record.timestamp.isoformat(),
|
||||
"operation": record.operation,
|
||||
"branch": record.branch,
|
||||
"result": record.result,
|
||||
}
|
||||
line = (json.dumps(payload, sort_keys=True, separators=(",", ":")) + "\n").encode("utf-8")
|
||||
fd = os.open(self.path, os.O_WRONLY | os.O_CREAT | os.O_APPEND, 0o600)
|
||||
try:
|
||||
os.fchmod(fd, 0o600)
|
||||
os.write(fd, line)
|
||||
finally:
|
||||
os.close(fd)
|
||||
|
||||
|
||||
|
||||
# V2R1C6 durable receipt overlay. This subclasses the original root-only
|
||||
# writer in-place so the existing AF_UNIX/SO_PEERCRED and handler policy remain
|
||||
# the only mutation path.
|
||||
_LegacyGovernedLocalWriterService = GovernedLocalWriterService
|
||||
|
||||
class GovernedLocalWriterService(_LegacyGovernedLocalWriterService):
|
||||
"""Existing writer with durable request receipts and safe recovery."""
|
||||
|
||||
def _load_state(self) -> None:
|
||||
super()._load_state()
|
||||
self.state.receipts = {}
|
||||
if self.state_path is None or not self.state_path.exists():
|
||||
return
|
||||
raw = json.loads(self.state_path.read_text(encoding="utf-8"))
|
||||
if not isinstance(raw, dict):
|
||||
raise AuthorizationError("authorization state is invalid")
|
||||
receipts = raw.get("receipts", {})
|
||||
if not isinstance(receipts, dict):
|
||||
raise AuthorizationError("authorization receipts are invalid")
|
||||
self.state.receipts = {
|
||||
str(key): dict(value)
|
||||
for key, value in receipts.items()
|
||||
if isinstance(value, dict)
|
||||
}
|
||||
|
||||
def _persist_state(self) -> None:
|
||||
if self.state_path is None:
|
||||
return
|
||||
self.state_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
payload = {
|
||||
"authorization_sha256": self.authorization.authorization_sha256,
|
||||
"create_done": sorted(self.state.create_done),
|
||||
"append_done": sorted(self.state.append_done),
|
||||
"consumed": bool(self.state.consumed),
|
||||
"receipts": self.state.receipts,
|
||||
}
|
||||
fd, temp_name = tempfile.mkstemp(prefix=".writer-state-", dir=self.state_path.parent)
|
||||
try:
|
||||
os.fchmod(fd, 0o600)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as stream:
|
||||
json.dump(payload, stream, sort_keys=True, separators=(",", ":"))
|
||||
stream.write("\n")
|
||||
os.replace(temp_name, self.state_path)
|
||||
os.chmod(self.state_path, 0o600)
|
||||
finally:
|
||||
if os.path.exists(temp_name):
|
||||
os.unlink(temp_name)
|
||||
|
||||
def _request_identity(self, request: Mapping[str, Any]) -> dict[str, str]:
|
||||
canonical = json.dumps(dict(request), sort_keys=True, separators=(",", ":"), ensure_ascii=True)
|
||||
fallback = hashlib.sha256(canonical.encode("utf-8")).hexdigest()
|
||||
request_id = request.get("request_id")
|
||||
idempotency_key = request.get("idempotency_key")
|
||||
request_id = request_id.strip() if isinstance(request_id, str) and request_id.strip() else "legacy-" + fallback
|
||||
idempotency_key = idempotency_key.strip() if isinstance(idempotency_key, str) and idempotency_key.strip() else "legacy-" + fallback
|
||||
for field_name, value in (("request_id", request_id), ("idempotency_key", idempotency_key)):
|
||||
if len(value) > 200 or "\n" in value or "\r" in value:
|
||||
raise AuthorizationError(field_name + " is invalid")
|
||||
return {
|
||||
"request_id": request_id,
|
||||
"idempotency_key": idempotency_key,
|
||||
"request_fingerprint": fallback,
|
||||
}
|
||||
|
||||
def _find_receipt(self, details: Mapping[str, Any], compare_fingerprint: bool = True):
|
||||
request_id = str(details["request_id"])
|
||||
idempotency_key = str(details["idempotency_key"])
|
||||
fingerprint = str(details.get("request_fingerprint", ""))
|
||||
for receipt in self.state.receipts.values():
|
||||
if receipt.get("request_id") == request_id or receipt.get("idempotency_key") == idempotency_key:
|
||||
if compare_fingerprint and receipt.get("request_fingerprint") != fingerprint:
|
||||
raise AuthorizationError("idempotency key reused with different request")
|
||||
return receipt
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def _receipt_response(receipt: Mapping[str, object], status: str = "receipt") -> dict[str, object]:
|
||||
response = {
|
||||
"status": status,
|
||||
"request_id": receipt.get("request_id"),
|
||||
"idempotency_key": receipt.get("idempotency_key"),
|
||||
"operation": receipt.get("operation"),
|
||||
"branch": receipt.get("branch", ""),
|
||||
"receipt_status": receipt.get("status"),
|
||||
}
|
||||
for field_name in ("commit_oid", "final_head", "parent_oid", "audit_sha256", "error_code", "safe_to_retry"):
|
||||
if field_name in receipt:
|
||||
response[field_name] = receipt[field_name]
|
||||
return response
|
||||
|
||||
def _new_receipt(self, details: Mapping[str, Any]) -> dict[str, object]:
|
||||
return {
|
||||
"request_id": str(details["request_id"]),
|
||||
"idempotency_key": str(details["idempotency_key"]),
|
||||
"request_fingerprint": str(details["request_fingerprint"]),
|
||||
"operation": str(details["operation"]),
|
||||
"branch": str(details.get("branch", "")),
|
||||
"expected_head_oid": str(details.get("expected_head_oid", "")),
|
||||
"status": "accepted",
|
||||
"created_at": datetime.now(tz=timezone.utc).isoformat(),
|
||||
"safe_to_retry": False,
|
||||
}
|
||||
|
||||
def _new_audit(self, peer: PeerIdentity, operation: str, branch: str, result: str) -> str:
|
||||
super()._new_audit(peer, operation, branch, result)
|
||||
payload = {
|
||||
"authorization_sha256": self.authorization.authorization_sha256,
|
||||
"peer_pid": peer.pid,
|
||||
"peer_uid": peer.uid,
|
||||
"peer_gid": peer.gid,
|
||||
"peer_executable": peer.executable,
|
||||
"operation": operation,
|
||||
"branch": branch,
|
||||
"result": result,
|
||||
}
|
||||
return hashlib.sha256(json.dumps(payload, sort_keys=True, separators=(",", ":")).encode("utf-8")).hexdigest()
|
||||
|
||||
def _mark_success(self, op: str, branch: str) -> None:
|
||||
if op == "create_branch":
|
||||
self.state.create_done.add(branch)
|
||||
elif op in {"append_commit", "append_files", "append_batch"}:
|
||||
self.state.append_done.add(branch)
|
||||
# The provisioning grant is one-shot; the task writer lease itself must
|
||||
# support multiple append receipts for the exact authorized branches.
|
||||
self.state.consumed = False
|
||||
self._persist_state()
|
||||
|
||||
def _validate_durable(self, raw_request: Mapping[str, Any]) -> dict[str, Any]:
|
||||
operation = self._require_request_field(raw_request, "op")
|
||||
identity = self._request_identity(raw_request)
|
||||
if operation == "query_receipt":
|
||||
return {"operation": operation, **identity}
|
||||
if operation == "recover_request":
|
||||
branch = self._require_request_field(raw_request, "branch")
|
||||
policy = self._branch_policy(branch)
|
||||
if policy.append_commit is None:
|
||||
raise AuthorizationError("branch does not allow recovery")
|
||||
expected = raw_request.get("expected_head_oid") or policy.append_commit.expected_head_oid
|
||||
if not isinstance(expected, str) or not re.fullmatch(r"[0-9a-fA-F]{40}", expected):
|
||||
raise AuthorizationError("recovery requires expected_head_oid")
|
||||
return {"operation": operation, "branch": branch, "expected_head_oid": expected.lower(), **identity}
|
||||
if operation not in {"create_branch", "append_commit", "append_files", "append_batch"}:
|
||||
raise AuthorizationError("unsupported operation")
|
||||
request = dict(raw_request)
|
||||
if operation in {"append_files", "append_batch"}:
|
||||
request["op"] = "append_commit"
|
||||
if operation in {"append_commit", "append_files", "append_batch"}:
|
||||
self.state.consumed = False
|
||||
branch = request.get("branch")
|
||||
removed = False
|
||||
dynamic_expected = False
|
||||
if isinstance(branch, str) and branch in self.state.append_done:
|
||||
self.state.append_done.remove(branch)
|
||||
removed = True
|
||||
policy = self.authorization.branch_operations.get(branch)
|
||||
if policy is not None and policy.append_commit is not None and policy.append_commit.expected_head_oid is not None:
|
||||
from governed_local_writer import BranchAppendPolicy, BranchPolicy
|
||||
self.authorization.branch_operations[branch] = BranchPolicy(create_branch=policy.create_branch, append_commit=BranchAppendPolicy(branch=branch, expected_head_oid=None, allowed_paths=policy.append_commit.allowed_paths))
|
||||
dynamic_expected = True
|
||||
try:
|
||||
details = super()._validate_request(request)
|
||||
finally:
|
||||
if dynamic_expected:
|
||||
policy = self.authorization.branch_operations.get(str(branch))
|
||||
if policy is not None and policy.append_commit is not None:
|
||||
from governed_local_writer import BranchAppendPolicy, BranchPolicy
|
||||
self.authorization.branch_operations[str(branch)] = BranchPolicy(create_branch=policy.create_branch, append_commit=BranchAppendPolicy(branch=str(branch), expected_head_oid=str(raw_request.get("expected_head_oid") or ""), allowed_paths=policy.append_commit.allowed_paths))
|
||||
if removed:
|
||||
self.state.append_done.add(str(branch))
|
||||
details.update(identity)
|
||||
details["operation"] = operation
|
||||
return details
|
||||
|
||||
def _recover_backend(self, details: Mapping[str, Any]) -> dict[str, object]:
|
||||
if not hasattr(self.handler, "_workspace") or not hasattr(self.handler, "_git"):
|
||||
raise RuntimeError("recovery backend unavailable")
|
||||
workspace = self.handler._workspace(str(details["branch"]))
|
||||
expected = str(details["expected_head_oid"])
|
||||
current = self.handler._git(workspace, ["rev-parse", "HEAD"])
|
||||
if current == expected:
|
||||
return {"status": "not_started", "final_head": current}
|
||||
parent = self.handler._git(workspace, ["rev-parse", "HEAD^1"])
|
||||
if parent != expected:
|
||||
raise RuntimeError("external branch advance during recovery")
|
||||
return {"status": "applied", "commit_oid": current, "final_head": current, "parent_oid": parent}
|
||||
|
||||
def process_request(self, raw_request: Mapping[str, Any], peer: PeerIdentity) -> Mapping[str, Any]:
|
||||
operation = raw_request.get("op") if isinstance(raw_request.get("op"), str) else "unknown"
|
||||
branch = raw_request.get("branch") if isinstance(raw_request.get("branch"), str) else ""
|
||||
try:
|
||||
details = self._validate_durable(raw_request)
|
||||
operation = str(details["operation"])
|
||||
branch = str(details.get("branch", ""))
|
||||
if operation == "query_receipt":
|
||||
receipt = self._find_receipt(details, compare_fingerprint=False)
|
||||
return self._receipt_response(receipt) if receipt is not None else {"status": "not_found", "request_id": details["request_id"], "idempotency_key": details["idempotency_key"]}
|
||||
if operation == "recover_request":
|
||||
receipt = self._find_receipt(details, compare_fingerprint=False)
|
||||
if receipt is None:
|
||||
return {"status": "not_found", "request_id": details["request_id"], "idempotency_key": details["idempotency_key"], "safe_to_retry": True}
|
||||
if receipt.get("status") == "applied":
|
||||
return self._receipt_response(receipt)
|
||||
recovered = self._recover_backend(details)
|
||||
if recovered.get("status") == "applied":
|
||||
receipt.update({"status": "applied", "commit_oid": recovered.get("commit_oid"), "final_head": recovered.get("final_head"), "parent_oid": recovered.get("parent_oid"), "safe_to_retry": False})
|
||||
self._mark_success("append_commit", branch)
|
||||
return self._receipt_response(receipt)
|
||||
receipt["safe_to_retry"] = True
|
||||
self._persist_state()
|
||||
return self._receipt_response(receipt)
|
||||
receipt = self._find_receipt(details)
|
||||
if receipt is not None:
|
||||
return self._receipt_response(receipt)
|
||||
receipt = self._new_receipt(details)
|
||||
self.state.receipts[str(details["request_id"])] = receipt
|
||||
self._persist_state()
|
||||
if operation == "create_branch":
|
||||
result = self.handler.create_branch(CreateBranchRequest(branch=branch, base_oid=str(details["base_oid"]), head_oid=str(details["head_oid"]) if details.get("head_oid") is not None else None, authorization_digest=self.authorization.authorization_sha256))
|
||||
commit_oid = str(result.get("head_oid", ""))
|
||||
parent_oid = str(result.get("parent_oid", ""))
|
||||
audit_sha = self._new_audit(peer, operation, branch, "ok")
|
||||
receipt.update({"status": "applied", "commit_oid": commit_oid, "final_head": commit_oid, "parent_oid": parent_oid, "audit_sha256": audit_sha, "safe_to_retry": False})
|
||||
self._mark_success("create_branch", branch)
|
||||
return self._receipt_response(receipt, status="ok") | {"result": "applied"}
|
||||
result = self.handler.append_commit(AppendCommitRequest(branch=branch, expected_head_oid=str(details["expected_head_oid"]), changes=tuple(details["changes"]), authorization_digest=self.authorization.authorization_sha256, commit_message=str(details["commit_message"])))
|
||||
commit_oid = str(result.get("head_oid", ""))
|
||||
parent_oid = str(result.get("parent_oid", ""))
|
||||
audit_sha = self._new_audit(peer, operation, branch, "ok")
|
||||
receipt.update({"status": "applied", "commit_oid": commit_oid, "final_head": commit_oid, "parent_oid": parent_oid, "audit_sha256": audit_sha, "safe_to_retry": False})
|
||||
self._mark_success("append_commit", branch)
|
||||
return self._receipt_response(receipt, status="ok") | {"result": "applied"}
|
||||
except Exception as error:
|
||||
try:
|
||||
identity = self._request_identity(raw_request)
|
||||
receipt = self.state.receipts.get(identity["request_id"])
|
||||
if receipt is not None and receipt.get("status") == "accepted":
|
||||
receipt.update({"status": "failed", "error_code": error.__class__.__name__, "safe_to_retry": False})
|
||||
self._persist_state()
|
||||
except Exception:
|
||||
pass
|
||||
self._new_audit(peer, operation, branch, "error:" + error.__class__.__name__)
|
||||
return {"status": "error", "operation": operation, "branch": branch, "error": "request_denied" if isinstance(error, AuthorizationError) else "handler_failed"}
|
||||
|
||||
def _parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="AIOS governed local writer")
|
||||
parser.add_argument("--socket", required=True)
|
||||
parser.add_argument("--authorization", required=True)
|
||||
parser.add_argument("--state", required=True)
|
||||
parser.add_argument("--audit", required=True)
|
||||
parser.add_argument("--repair-branch", required=True)
|
||||
parser.add_argument("--repair-workspace", required=True)
|
||||
parser.add_argument("--candidate-branch", required=True)
|
||||
parser.add_argument("--candidate-workspace", required=True)
|
||||
parser.add_argument("--bare-repo", required=True)
|
||||
parser.add_argument("--api-source", required=True)
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
if hasattr(os, "geteuid") and os.geteuid() != 0:
|
||||
print("governed local writer requires uid 0", file=sys.stderr)
|
||||
return 2
|
||||
args = _parse_args()
|
||||
authorization = load_authorization_file(args.authorization)
|
||||
handler = ExistingGitOpsHandler(
|
||||
workspace_by_branch={
|
||||
args.repair_branch: args.repair_workspace,
|
||||
args.candidate_branch: args.candidate_workspace,
|
||||
},
|
||||
bare_repo=args.bare_repo,
|
||||
api_source=args.api_source,
|
||||
)
|
||||
service = GovernedLocalWriterService(
|
||||
args.socket,
|
||||
authorization,
|
||||
handler,
|
||||
audit_sink=JsonAuditSink(args.audit),
|
||||
state_path=args.state,
|
||||
)
|
||||
service.serve()
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__": # pragma: no cover - systemd entrypoint
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,316 @@
|
||||
"""Task-scoped hardened wrapper around the existing Action API."""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
import urllib.parse
|
||||
|
||||
import aios_chatgpt_actions_api as api
|
||||
import aios_isolated_writer_policy as policy
|
||||
from isolated_writer_authz import AuthorizationError, authorize
|
||||
from isolated_writer_commit_file import AtomicCommitFile, CommitFileError, OperationLedger
|
||||
from isolated_writer_token_registry import TokenRegistry
|
||||
|
||||
_reject = api.reject_non_read_http
|
||||
_write_file = api.write_file
|
||||
_sync_branch = api.sync_branch
|
||||
_original_do_get = api.H.do_GET
|
||||
api.OPENAPI = Path(os.getenv("AIOS_GITOPS_ISOLATED_WRITER_OPENAPI", str(api.OPENAPI)))
|
||||
|
||||
|
||||
def _registry() -> TokenRegistry:
|
||||
return TokenRegistry(Path(os.environ["AIOS_GITOPS_TOKEN_REGISTRY_V2"]))
|
||||
|
||||
|
||||
def _atomic_writer() -> AtomicCommitFile:
|
||||
return AtomicCommitFile(
|
||||
workspace=api.WS,
|
||||
bare_repo=api.BARE_REPO,
|
||||
ledger=OperationLedger(Path(os.environ["AIOS_GITOPS_WRITER_OPERATION_LEDGER"])),
|
||||
remote=os.getenv("AIOS_GITOPS_GITEA_PUSH_REMOTE", ""),
|
||||
audit=policy.append_audit_record,
|
||||
)
|
||||
|
||||
|
||||
def _bearer(handler) -> str:
|
||||
value = handler.headers.get("Authorization", "")
|
||||
return value[7:].strip() if value.startswith("Bearer ") else ""
|
||||
|
||||
|
||||
def _authorize(handler, *, method: str, path: str, branch=None, target_path=None):
|
||||
grant = authorize(
|
||||
_registry(),
|
||||
_bearer(handler),
|
||||
method=method,
|
||||
path=path,
|
||||
source_ip=str(handler.client_address[0]),
|
||||
workspace=api.WS,
|
||||
branch=branch,
|
||||
target_path=target_path,
|
||||
)
|
||||
grant.record["_source_ip"] = str(handler.client_address[0])
|
||||
return grant
|
||||
|
||||
|
||||
def _authorization_error(handler, exc: AuthorizationError):
|
||||
return handler.sendj({"error": exc.code}, exc.status)
|
||||
|
||||
|
||||
def _isolated_runtime_status(handler):
|
||||
branch = api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"]
|
||||
head = api.sh(["rev-parse", "HEAD"], True)["stdout"]
|
||||
return handler.sendj({
|
||||
"service": os.getenv(
|
||||
"AIOS_GITOPS_SERVICE_AUDIENCE",
|
||||
"aios-isolated-writer.service",
|
||||
),
|
||||
"status": "active",
|
||||
"runtime_role": os.getenv("AIOS_GITOPS_RUNTIME_ROLE"),
|
||||
"workspace_role": os.getenv("AIOS_GITOPS_WORKSPACE_ROLE"),
|
||||
"writes_enabled": os.getenv("AIOS_GITOPS_WRITES_ENABLED", "").lower()
|
||||
in {"1", "true", "yes", "on"},
|
||||
"allowed_branch": policy.allowed_branch(),
|
||||
"approved_base_oid": policy.allowed_base_oid(),
|
||||
"workspace_branch": branch,
|
||||
"workspace_head_oid": head,
|
||||
"repository_identity": os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY"),
|
||||
"token_policy_version": 2,
|
||||
"atomic_commit_file": True,
|
||||
"path_policy_sha256": policy.configured_path_policy_sha256(),
|
||||
})
|
||||
|
||||
|
||||
def _isolated_do_get(self):
|
||||
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
|
||||
if path in {"/health", "/api/health"}:
|
||||
return self.sendj({
|
||||
"status": "ok",
|
||||
"service": os.getenv(
|
||||
"AIOS_GITOPS_SERVICE_AUDIENCE",
|
||||
"aios-isolated-writer.service",
|
||||
),
|
||||
})
|
||||
if path not in {"/api/runtime-status", "/api/baseline", "/api/patches"}:
|
||||
return self.sendj({"error": "isolated_writer_operation_forbidden"}, 403)
|
||||
try:
|
||||
_authorize(self, method="GET", path=path)
|
||||
except AuthorizationError as exc:
|
||||
return _authorization_error(self, exc)
|
||||
if path == "/api/runtime-status":
|
||||
return _isolated_runtime_status(self)
|
||||
return _original_do_get(self)
|
||||
|
||||
|
||||
def _read_commit_file_body(handler):
|
||||
try:
|
||||
length = int(handler.headers.get("Content-Length", "0"))
|
||||
except ValueError:
|
||||
raise CommitFileError("writer_content_length_rejected") from None
|
||||
if length <= 0:
|
||||
raise CommitFileError("writer_request_object_required")
|
||||
if length > 1_100_000:
|
||||
raise CommitFileError("writer_request_too_large", 413)
|
||||
raw = handler.rfile.read(length)
|
||||
try:
|
||||
value = json.loads(raw.decode("utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError):
|
||||
raise CommitFileError("writer_request_json_rejected") from None
|
||||
if not isinstance(value, dict):
|
||||
raise CommitFileError("writer_request_object_required")
|
||||
return value
|
||||
|
||||
|
||||
def _isolated_do_post(self):
|
||||
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
|
||||
if path != "/api/commit-file":
|
||||
return self.sendj({"error": "isolated_writer_operation_forbidden"}, 403)
|
||||
try:
|
||||
data = _read_commit_file_body(self)
|
||||
branch = str(data.get("branch") or "")
|
||||
target_path = str(data.get("path") or "")
|
||||
grant = _authorize(
|
||||
self,
|
||||
method="POST",
|
||||
path=path,
|
||||
branch=branch,
|
||||
target_path=target_path,
|
||||
)
|
||||
if api.content_has_secret(str(data.get("content") or "")):
|
||||
raise CommitFileError("writer_secret_content_rejected", 403)
|
||||
result = _atomic_writer().execute(grant, data)
|
||||
return self.sendj(result)
|
||||
except AuthorizationError as exc:
|
||||
return _authorization_error(self, exc)
|
||||
except CommitFileError as exc:
|
||||
return self.sendj({"error": exc.code}, exc.status)
|
||||
except PermissionError:
|
||||
return self.sendj({"error": "isolated_writer_policy_rejected"}, 403)
|
||||
|
||||
|
||||
def reject_non_read_http(handler, method: str, path: str) -> bool:
|
||||
if _reject(handler, method, path):
|
||||
return True
|
||||
try:
|
||||
policy.validate_endpoint(method, path, api.WS, api.BARE_REPO)
|
||||
return False
|
||||
except PermissionError as exc:
|
||||
handler.sendj({"error": str(exc)}, 403)
|
||||
return True
|
||||
|
||||
|
||||
def checkout(branch, base="main", create=False):
|
||||
api.ensure_git()
|
||||
target = api.branch_name(branch)
|
||||
policy.validate_branch_request({"branch": target, "base": base})
|
||||
exists = api.sh(["rev-parse", "--verify", target])["code"] == 0
|
||||
if exists:
|
||||
if api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"] != target:
|
||||
api.sh(["checkout", target], True)
|
||||
elif create:
|
||||
api.sh(["checkout", "-b", target, base], True)
|
||||
else:
|
||||
raise PermissionError("isolated_writer_branch_missing")
|
||||
policy.require_service_invariants(api.WS, api.BARE_REPO)
|
||||
return target
|
||||
|
||||
|
||||
def write_file(path, content):
|
||||
policy.validate_path(path, api.WS)
|
||||
return _write_file(path, content)
|
||||
|
||||
|
||||
def sync_branch(branch: str):
|
||||
policy.validate_sync_branch(branch)
|
||||
local = _sync_branch(branch)
|
||||
remote = os.getenv("AIOS_GITOPS_GITEA_PUSH_REMOTE", "").strip()
|
||||
if remote != "gitea-http":
|
||||
raise PermissionError("isolated_writer_gitea_remote_rejected")
|
||||
head = api.sh(["rev-parse", "HEAD"], True)["stdout"]
|
||||
pushed = subprocess.run(
|
||||
["git", "push", "--porcelain", remote, f"HEAD:refs/heads/{branch}"],
|
||||
cwd=api.WS,
|
||||
text=True,
|
||||
capture_output=True,
|
||||
)
|
||||
if pushed.returncode != 0:
|
||||
raise RuntimeError("isolated_writer_gitea_push_failed")
|
||||
verified = subprocess.run(
|
||||
["git", "ls-remote", "--heads", remote, f"refs/heads/{branch}"],
|
||||
cwd=api.WS,
|
||||
text=True,
|
||||
capture_output=True,
|
||||
)
|
||||
if verified.returncode != 0:
|
||||
raise RuntimeError("isolated_writer_gitea_verification_failed")
|
||||
fields = verified.stdout.strip().split()
|
||||
if len(fields) != 2 or fields[0] != head or fields[1] != f"refs/heads/{branch}":
|
||||
raise RuntimeError("isolated_writer_gitea_oid_mismatch")
|
||||
return {
|
||||
"status": "verified",
|
||||
"target": "authoritative-bare+gitea",
|
||||
"branch": branch,
|
||||
"oid": head,
|
||||
"local": local.get("status"),
|
||||
}
|
||||
|
||||
|
||||
def commit(paths, msg):
|
||||
policy.validate_commit_paths(paths, api.WS)
|
||||
api.ensure_git()
|
||||
selected = [api.relpath(p) for p in paths] if paths else ["."]
|
||||
api.sh(["add", *selected], True)
|
||||
policy.validate_staged_paths(api.WS)
|
||||
branch = api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"]
|
||||
if not api.sh(["status", "--short"])["stdout"]:
|
||||
return {"status": "no_changes", "branch": branch, "sync": sync_branch(branch)}
|
||||
out = api.sh(["commit", "-m", msg], True)
|
||||
branch = api.sh(["rev-parse", "--abbrev-ref", "HEAD"], True)["stdout"]
|
||||
return {
|
||||
"status": "committed",
|
||||
"branch": branch,
|
||||
"rev": api.sh(["rev-parse", "--short", "HEAD"], True)["stdout"],
|
||||
"git": out,
|
||||
"sync": sync_branch(branch),
|
||||
}
|
||||
|
||||
|
||||
def audit(actor, action, target, payload):
|
||||
policy.append_audit_record(
|
||||
{
|
||||
"at": api.now(),
|
||||
"actor": actor,
|
||||
"action": action,
|
||||
"target": target,
|
||||
"payload": api.sanitize(payload),
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def _validate_request(self, data, validate):
|
||||
try:
|
||||
validate(data)
|
||||
return True
|
||||
except PermissionError as exc:
|
||||
self.sendj({"error": str(exc)}, 403)
|
||||
return False
|
||||
|
||||
|
||||
def _checked_branch(self, data):
|
||||
if not _validate_request(self, data, policy.validate_branch_request):
|
||||
return
|
||||
return _branch(self, data)
|
||||
|
||||
|
||||
def _checked_file(self, data):
|
||||
data = dict(data)
|
||||
data.setdefault("branch", policy.allowed_branch())
|
||||
if not _validate_request(self, data, policy.validate_branch_request):
|
||||
return
|
||||
if not _validate_request(
|
||||
self,
|
||||
{"path": data.get("path", "")},
|
||||
lambda item: policy.validate_path(item["path"], api.WS),
|
||||
):
|
||||
return
|
||||
return _file(self, data)
|
||||
|
||||
|
||||
def _checked_commit(self, data):
|
||||
data = dict(data)
|
||||
data.setdefault("branch", policy.allowed_branch())
|
||||
if not _validate_request(self, data, policy.validate_branch_request):
|
||||
return
|
||||
return _commit(self, data)
|
||||
|
||||
|
||||
def _checked_patch(self, data):
|
||||
data = dict(data)
|
||||
data["branch"] = policy.allowed_branch()
|
||||
if not _validate_request(self, data, policy.validate_branch_request):
|
||||
return
|
||||
return _patch(self, data)
|
||||
|
||||
|
||||
_branch, _file, _commit, _patch = api.H.branch, api.H.file, api.H.commit, api.H.patch
|
||||
api.reject_non_read_http = reject_non_read_http
|
||||
api.checkout, api.write_file, api.sync_branch, api.commit, api.audit = (
|
||||
checkout,
|
||||
write_file,
|
||||
sync_branch,
|
||||
commit,
|
||||
audit,
|
||||
)
|
||||
api.H.branch, api.H.file, api.H.commit, api.H.patch = (
|
||||
_checked_branch,
|
||||
_checked_file,
|
||||
_checked_commit,
|
||||
_checked_patch,
|
||||
)
|
||||
api.H.do_GET = _isolated_do_get
|
||||
api.H.do_POST = _isolated_do_post
|
||||
|
||||
if __name__ == "__main__":
|
||||
policy.require_service_invariants(api.WS, api.BARE_REPO)
|
||||
api.ThreadingHTTPServer((api.HOST, api.PORT), api.H).serve_forever()
|
||||
@@ -0,0 +1,310 @@
|
||||
"""Fail-closed policy used only by the task-scoped Action writer."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import json
|
||||
import stat
|
||||
import subprocess
|
||||
import re
|
||||
from pathlib import Path, PurePosixPath, PureWindowsPath
|
||||
from urllib.parse import unquote
|
||||
|
||||
import isolated_writer_path_policy as path_policy
|
||||
|
||||
WRITE_ENDPOINTS = frozenset({"/api/commit-file"})
|
||||
ALLOWED_ROOTS = (
|
||||
"active-runtime",
|
||||
"docs",
|
||||
"patches",
|
||||
"reports",
|
||||
"scripts",
|
||||
"test",
|
||||
"tests",
|
||||
)
|
||||
DENIED_ROOTS = ("baseline", "config", "deploy", "deployments", "ops", "runtime", "services")
|
||||
_TRUE = frozenset({"1", "true", "yes", "on"})
|
||||
_FALSE = frozenset({"0", "false", "no", "off"})
|
||||
_DENY_FLAGS = (
|
||||
"AIOS_GITOPS_ALLOW_MAIN_WRITE",
|
||||
"AIOS_GITOPS_ALLOW_TAG_WRITE",
|
||||
"AIOS_GITOPS_ALLOW_BASELINE_WRITE",
|
||||
"AIOS_GITOPS_ALLOW_REGISTRY_WRITE",
|
||||
"AIOS_GITOPS_ALLOW_ROLLBACK",
|
||||
"AIOS_GITOPS_ALLOW_DEPLOYMENT",
|
||||
)
|
||||
|
||||
|
||||
def enforcement_required() -> bool:
|
||||
return os.getenv("AIOS_GITOPS_ISOLATED_WRITER_ENFORCEMENT", "") == "required"
|
||||
|
||||
|
||||
def allowed_branch() -> str:
|
||||
value = os.getenv("AIOS_GITOPS_ALLOWED_BRANCH", "").strip()
|
||||
if not value:
|
||||
raise PermissionError("isolated_writer_missing_allowed_branch")
|
||||
return value
|
||||
|
||||
|
||||
def allowed_base_oid() -> str:
|
||||
value = os.getenv("AIOS_GITOPS_ALLOWED_BASE_OID", "").strip().lower()
|
||||
if len(value) != 40 or any(ch not in "0123456789abcdef" for ch in value):
|
||||
raise PermissionError("isolated_writer_invalid_allowed_base_oid")
|
||||
return value
|
||||
|
||||
|
||||
def _git(workspace: Path, *args: str) -> str:
|
||||
result = subprocess.run(["git", *args], cwd=workspace, text=True, capture_output=True)
|
||||
if result.returncode != 0:
|
||||
raise PermissionError("isolated_writer_git_validation_failed")
|
||||
return result.stdout.strip()
|
||||
|
||||
|
||||
def require_service_invariants(workspace: Path, bare_repo: Path) -> None:
|
||||
if not enforcement_required():
|
||||
return
|
||||
if os.getenv("AIOS_GITOPS_WRITES_ENABLED", "").strip().lower() not in _TRUE:
|
||||
raise PermissionError("isolated_writer_write_gate_required")
|
||||
if os.getenv("AIOS_GITOPS_RUNTIME_ROLE", "") != "isolated-writer":
|
||||
raise PermissionError("isolated_writer_role_required")
|
||||
if os.getenv("AIOS_GITOPS_WORKSPACE_ROLE", "") != "isolated-writer":
|
||||
raise PermissionError("isolated_writer_workspace_role_required")
|
||||
if os.getenv("AIOS_GITOPS_TOKEN_POLICY_VERSION_REQUIRED", "") != "2":
|
||||
raise PermissionError("isolated_writer_token_policy_v2_required")
|
||||
if not os.getenv("AIOS_GITOPS_SERVICE_AUDIENCE", "").strip():
|
||||
raise PermissionError("isolated_writer_service_audience_required")
|
||||
if not os.getenv("AIOS_GITOPS_TOKEN_REGISTRY_V2", "").strip():
|
||||
raise PermissionError("isolated_writer_token_registry_required")
|
||||
if not os.getenv("AIOS_GITOPS_WRITER_OPERATION_LEDGER", "").strip():
|
||||
raise PermissionError("isolated_writer_operation_ledger_required")
|
||||
path_policy.configured_path_policy()
|
||||
for name in _DENY_FLAGS:
|
||||
if os.getenv(name, "").strip().lower() not in _FALSE:
|
||||
raise PermissionError("isolated_writer_forbidden_capability_flag")
|
||||
if os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", "") != "aios/aios":
|
||||
raise PermissionError("isolated_writer_repository_identity_rejected")
|
||||
configured_bare_value = os.getenv("AIOS_GITOPS_AUTHORITATIVE_GIT_DIR", "").strip()
|
||||
if not configured_bare_value:
|
||||
raise PermissionError("isolated_writer_authoritative_repo_rejected")
|
||||
configured_bare = Path(configured_bare_value)
|
||||
if configured_bare.resolve(strict=True) != bare_repo.resolve(strict=True):
|
||||
raise PermissionError("isolated_writer_authoritative_repo_rejected")
|
||||
writer_root_value = os.getenv("AIOS_GITOPS_APPROVED_WRITER_ROOT", "").strip()
|
||||
if not writer_root_value:
|
||||
raise PermissionError("isolated_writer_workspace_outside_approved_root")
|
||||
writer_root = Path(writer_root_value).resolve(strict=True)
|
||||
lexical_workspace = Path(os.path.abspath(str(workspace)))
|
||||
canonical_workspace = lexical_workspace.resolve(strict=True)
|
||||
if lexical_workspace != canonical_workspace:
|
||||
raise PermissionError("isolated_writer_workspace_symlink_rejected")
|
||||
try:
|
||||
canonical_workspace.relative_to(writer_root)
|
||||
except (ValueError, FileNotFoundError):
|
||||
raise PermissionError("isolated_writer_workspace_outside_approved_root") from None
|
||||
if _git(workspace, "rev-parse", "--abbrev-ref", "HEAD") != allowed_branch():
|
||||
raise PermissionError("isolated_writer_current_branch_rejected")
|
||||
approved_base = allowed_base_oid()
|
||||
try:
|
||||
_git(workspace, "cat-file", "-e", f"{approved_base}^{{commit}}")
|
||||
subprocess.run(
|
||||
["git", "merge-base", "--is-ancestor", approved_base, "HEAD"],
|
||||
cwd=workspace,
|
||||
check=True,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
)
|
||||
except (PermissionError, subprocess.CalledProcessError):
|
||||
raise PermissionError("isolated_writer_approved_base_not_ancestor") from None
|
||||
if _git(workspace, "merge-base", approved_base, "HEAD") != approved_base:
|
||||
raise PermissionError("isolated_writer_merge_base_rejected")
|
||||
common = Path(_git(workspace, "rev-parse", "--git-common-dir"))
|
||||
if not common.is_absolute():
|
||||
common = (workspace / common).resolve()
|
||||
if common.resolve() != bare_repo.resolve():
|
||||
raise PermissionError("isolated_writer_common_repo_rejected")
|
||||
|
||||
|
||||
def approved_audit_log_path() -> Path:
|
||||
root_value = os.getenv("AIOS_GITOPS_APPROVED_AUDIT_ROOT", "").strip()
|
||||
log_value = os.getenv("AIOS_GITOPS_AUDIT_LOG", "").strip()
|
||||
if not root_value or not log_value:
|
||||
raise PermissionError("isolated_writer_audit_path_missing")
|
||||
lexical_root = Path(os.path.abspath(root_value))
|
||||
lexical_log = Path(os.path.abspath(log_value))
|
||||
root = lexical_root.resolve(strict=True)
|
||||
if lexical_root != root or root.is_symlink() or not root.is_dir():
|
||||
raise PermissionError("isolated_writer_audit_root_rejected")
|
||||
try:
|
||||
lexical_log.relative_to(root)
|
||||
except ValueError:
|
||||
raise PermissionError("isolated_writer_audit_path_outside_approved_root") from None
|
||||
if lexical_log.parent.resolve(strict=True) != lexical_log.parent:
|
||||
raise PermissionError("isolated_writer_audit_parent_symlink_rejected")
|
||||
if lexical_log.exists() and lexical_log.is_symlink():
|
||||
raise PermissionError("isolated_writer_audit_log_symlink_rejected")
|
||||
os.chmod(root, 0o750)
|
||||
os.chmod(lexical_log.parent, 0o750)
|
||||
return lexical_log
|
||||
|
||||
|
||||
def append_audit_record(record: dict) -> None:
|
||||
path = approved_audit_log_path()
|
||||
flags = os.O_WRONLY | os.O_APPEND | os.O_CREAT
|
||||
if hasattr(os, "O_NOFOLLOW"):
|
||||
flags |= os.O_NOFOLLOW
|
||||
descriptor = os.open(path, flags, 0o600)
|
||||
try:
|
||||
info = os.fstat(descriptor)
|
||||
if not stat.S_ISREG(info.st_mode):
|
||||
raise PermissionError("isolated_writer_audit_log_not_regular")
|
||||
os.fchmod(descriptor, 0o600)
|
||||
line = json.dumps(
|
||||
_audit_sanitize(record),
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8") + b"\n"
|
||||
os.write(descriptor, line)
|
||||
os.fsync(descriptor)
|
||||
finally:
|
||||
os.close(descriptor)
|
||||
parent_fd = os.open(path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0))
|
||||
try:
|
||||
os.fsync(parent_fd)
|
||||
finally:
|
||||
os.close(parent_fd)
|
||||
|
||||
|
||||
def _audit_sanitize(value):
|
||||
if isinstance(value, dict):
|
||||
return {
|
||||
key: (
|
||||
"[REDACTED]"
|
||||
if any(
|
||||
marker in str(key).lower()
|
||||
for marker in (
|
||||
"authorization",
|
||||
"credential",
|
||||
"password",
|
||||
"secret",
|
||||
"token",
|
||||
"private_key",
|
||||
)
|
||||
)
|
||||
and str(key).lower() != "token_id"
|
||||
else _audit_sanitize(inner)
|
||||
)
|
||||
for key, inner in value.items()
|
||||
}
|
||||
if isinstance(value, list):
|
||||
return [_audit_sanitize(item) for item in value]
|
||||
if isinstance(value, str) and re.search(
|
||||
r"(?i)(authorization\s*:\s*bearer|(?:token|password|secret)\s*[:=])",
|
||||
value,
|
||||
):
|
||||
return "[REDACTED]"
|
||||
return value
|
||||
|
||||
|
||||
def validate_endpoint(method: str, path: str, workspace: Path, bare_repo: Path) -> None:
|
||||
if not enforcement_required():
|
||||
return
|
||||
if method != "POST" or path not in WRITE_ENDPOINTS:
|
||||
raise PermissionError("isolated_writer_operation_forbidden")
|
||||
require_service_invariants(workspace, bare_repo)
|
||||
|
||||
|
||||
def validate_branch_request(data: dict) -> None:
|
||||
if not enforcement_required():
|
||||
return
|
||||
branch = allowed_branch() if "branch" not in data else str(data.get("branch") or "").strip()
|
||||
if branch != allowed_branch():
|
||||
raise PermissionError("isolated_writer_branch_rejected")
|
||||
if str(data.get("base", "main")).strip() != "main":
|
||||
raise PermissionError("isolated_writer_base_rejected")
|
||||
if data.get("force") or data.get("force_push"):
|
||||
raise PermissionError("isolated_writer_force_rejected")
|
||||
|
||||
|
||||
def validate_path(path: str, workspace: Path | None = None) -> str:
|
||||
if not isinstance(path, str):
|
||||
raise PermissionError("isolated_writer_path_rejected")
|
||||
value = path
|
||||
if not value or value != value.strip() or "\x00" in value or "\\" in value:
|
||||
raise PermissionError("isolated_writer_path_rejected")
|
||||
try:
|
||||
decoded = unquote(value, errors="strict")
|
||||
except (UnicodeDecodeError, ValueError):
|
||||
raise PermissionError("isolated_writer_path_rejected") from None
|
||||
if decoded != value:
|
||||
raise PermissionError("isolated_writer_path_rejected")
|
||||
windows = PureWindowsPath(value)
|
||||
posix = PurePosixPath(value)
|
||||
parts = value.split("/")
|
||||
if (
|
||||
posix.is_absolute()
|
||||
or windows.is_absolute()
|
||||
or bool(windows.drive)
|
||||
or any(part in {"", ".", ".."} for part in parts)
|
||||
):
|
||||
raise PermissionError("isolated_writer_path_rejected")
|
||||
first = parts[0]
|
||||
service_exact_path = False
|
||||
if first in DENIED_ROOTS:
|
||||
try:
|
||||
path_policy.require_service_path("commit_file.atomic", value)
|
||||
service_exact_path = True
|
||||
except path_policy.PathPolicyError as exc:
|
||||
raise PermissionError(str(exc)) from None
|
||||
if value != "README.md" and first not in ALLOWED_ROOTS and not service_exact_path:
|
||||
raise PermissionError("isolated_writer_path_outside_allowed_roots")
|
||||
if workspace is not None:
|
||||
lexical_root = Path(os.path.abspath(str(workspace)))
|
||||
root = lexical_root.resolve(strict=True)
|
||||
if lexical_root != root:
|
||||
raise PermissionError("isolated_writer_workspace_symlink_rejected")
|
||||
current = root
|
||||
for part in parts:
|
||||
current = current / part
|
||||
if current.is_symlink():
|
||||
raise PermissionError("isolated_writer_path_symlink_rejected")
|
||||
candidate = (root / value).resolve(strict=False)
|
||||
try:
|
||||
candidate.relative_to(root)
|
||||
except ValueError:
|
||||
raise PermissionError("isolated_writer_path_escapes_workspace") from None
|
||||
return value
|
||||
|
||||
|
||||
def validate_content_for_path(path: str, content: str) -> None:
|
||||
if path.split("/", 1)[0] not in DENIED_ROOTS:
|
||||
return
|
||||
try:
|
||||
path_policy.validate_content("commit_file.atomic", path, content)
|
||||
except path_policy.PathPolicyError as exc:
|
||||
raise PermissionError(str(exc)) from None
|
||||
|
||||
|
||||
def configured_path_policy_sha256() -> str | None:
|
||||
try:
|
||||
return path_policy.configured_path_policy_sha256()
|
||||
except path_policy.PathPolicyError as exc:
|
||||
raise PermissionError(str(exc)) from None
|
||||
|
||||
|
||||
def validate_commit_paths(paths: list[str], workspace: Path | None = None) -> None:
|
||||
if enforcement_required():
|
||||
for path in paths:
|
||||
if str(path).strip() != ".":
|
||||
validate_path(str(path), workspace)
|
||||
|
||||
|
||||
def validate_staged_paths(workspace: Path) -> None:
|
||||
if not enforcement_required():
|
||||
return
|
||||
for path in _git(workspace, "diff", "--cached", "--name-only").splitlines():
|
||||
validate_path(path, workspace)
|
||||
|
||||
|
||||
def validate_sync_branch(branch: str) -> None:
|
||||
if enforcement_required() and branch != allowed_branch():
|
||||
raise PermissionError("isolated_writer_sync_branch_rejected")
|
||||
@@ -0,0 +1,144 @@
|
||||
"""HTTP adapter for audited Owner authorization and writer provisioning.
|
||||
|
||||
This module layers on top of ``aios_authorized_task_writer_api`` so existing
|
||||
routes and the legacy exact ``writer:provision`` route remain available. The
|
||||
new endpoint does not mint or modify bearer credentials. It authenticates an
|
||||
existing, non-wildcard, explicitly allow-listed Owner credential and then
|
||||
invokes the audited broker.
|
||||
|
||||
Endpoint:
|
||||
POST /api/governance/owner-authorizations
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import urllib.parse
|
||||
from typing import Any, Mapping
|
||||
|
||||
import aios_authorized_task_writer_api as bridge_api
|
||||
from authorized_task_writer_provisioning import ProvisioningError
|
||||
from owner_authorization_broker import (
|
||||
OwnerAuthorizationBroker,
|
||||
OwnerAuthorizationError,
|
||||
OwnerPrincipal,
|
||||
)
|
||||
|
||||
|
||||
api = bridge_api.api
|
||||
_original_do_post = api.H.do_POST
|
||||
_ENDPOINT = "/api/governance/owner-authorizations"
|
||||
|
||||
|
||||
def _enabled() -> bool:
|
||||
return os.getenv(
|
||||
"AIOS_GITOPS_OWNER_AUTHORIZATION_BROKER_ENABLED", ""
|
||||
).strip().lower() in {"1", "true", "yes", "on"}
|
||||
|
||||
|
||||
def _configured_intake_scope() -> str:
|
||||
scopes = [
|
||||
item.strip()
|
||||
for item in os.getenv(
|
||||
"AIOS_GITOPS_OWNER_AUTHORIZATION_INTAKE_SCOPES", ""
|
||||
).split(",")
|
||||
if item.strip()
|
||||
]
|
||||
if len(scopes) != 1:
|
||||
raise OwnerAuthorizationError(
|
||||
"EXACTLY_ONE_HTTP_INTAKE_SCOPE_REQUIRED", 503
|
||||
)
|
||||
scope = scopes[0]
|
||||
if scope == "writer:provision" or scope == "*" or scope.endswith(":*"):
|
||||
raise OwnerAuthorizationError("HTTP_INTAKE_SCOPE_REJECTED", 503)
|
||||
return scope
|
||||
|
||||
|
||||
def _scope_set(auth: Mapping[str, Any]) -> frozenset[str]:
|
||||
raw = auth.get("scopes")
|
||||
if raw is None:
|
||||
raw = auth.get("scope")
|
||||
if raw is None:
|
||||
return frozenset()
|
||||
if isinstance(raw, str):
|
||||
candidates = raw.replace(",", " ").split()
|
||||
elif isinstance(raw, (list, tuple, set, frozenset)):
|
||||
candidates = [str(item) for item in raw]
|
||||
else:
|
||||
raise OwnerAuthorizationError("OWNER_SCOPE_EVIDENCE_INVALID", 403)
|
||||
return frozenset(item.strip() for item in candidates if item.strip())
|
||||
|
||||
|
||||
def _credential_id(auth: Mapping[str, Any]) -> str:
|
||||
for name in (
|
||||
"credential_id",
|
||||
"token_id",
|
||||
"key_id",
|
||||
"auth_id",
|
||||
):
|
||||
value = str(auth.get(name) or "").strip()
|
||||
if value:
|
||||
return value
|
||||
return ""
|
||||
|
||||
|
||||
def _authenticate_existing_owner(handler) -> OwnerPrincipal | None:
|
||||
scope = _configured_intake_scope()
|
||||
auth = handler.need(scope)
|
||||
if not auth:
|
||||
return None
|
||||
if auth.get("role") != "owner":
|
||||
handler.sendj({"error": "OWNER_ROLE_REQUIRED"}, 403)
|
||||
return None
|
||||
identity = str(auth.get("account") or auth.get("identity") or "").strip()
|
||||
if not identity:
|
||||
handler.sendj({"error": "OWNER_IDENTITY_REQUIRED"}, 403)
|
||||
return None
|
||||
scopes = _scope_set(auth)
|
||||
if any(item == "*" or item.endswith(":*") for item in scopes):
|
||||
handler.sendj(
|
||||
{"error": "WILDCARD_OWNER_CREDENTIAL_REJECTED"}, 403
|
||||
)
|
||||
return None
|
||||
return OwnerPrincipal(
|
||||
identity=identity,
|
||||
role="owner",
|
||||
authenticated_scope=scope,
|
||||
token_scopes=scopes,
|
||||
credential_id=_credential_id(auth),
|
||||
)
|
||||
|
||||
|
||||
def _broker_do_post(self):
|
||||
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
|
||||
if path != _ENDPOINT:
|
||||
return _original_do_post(self)
|
||||
if not _enabled():
|
||||
return self.sendj(
|
||||
{"error": "OWNER_AUTHORIZATION_BROKER_DISABLED"}, 503
|
||||
)
|
||||
try:
|
||||
principal = _authenticate_existing_owner(self)
|
||||
if principal is None:
|
||||
return
|
||||
data = self.body()
|
||||
result = OwnerAuthorizationBroker().authorize_and_provision(
|
||||
data, principal
|
||||
)
|
||||
return self.sendj(result)
|
||||
except (OwnerAuthorizationError, ProvisioningError) as exc:
|
||||
body = {"error": exc.code}
|
||||
if exc.details:
|
||||
body["details"] = exc.details
|
||||
return self.sendj(body, exc.status)
|
||||
except Exception:
|
||||
# Never expose registry data, bearer tokens, signer output or traceback.
|
||||
return self.sendj(
|
||||
{"error": "OWNER_AUTHORIZATION_BROKER_INTERNAL_ERROR"}, 500
|
||||
)
|
||||
|
||||
|
||||
api.H.do_POST = _broker_do_post
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
api.main()
|
||||
+160
@@ -0,0 +1,160 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Loopback-only HTTP API for the task identity overlay.
|
||||
|
||||
Endpoints:
|
||||
GET /healthz
|
||||
POST /api/governance/owner-authorizations
|
||||
|
||||
The API authenticates only the short-lived overlay credential. It does not read
|
||||
or modify the global bearer-token registry.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import urllib.parse
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from typing import Any
|
||||
|
||||
from authorized_task_writer_provisioning import ProvisioningError
|
||||
from owner_authorization_broker import OwnerAuthorizationError
|
||||
from task_identity_overlay import (
|
||||
MAX_BODY_BYTES,
|
||||
IdentityOverlayConfig,
|
||||
IdentityOverlayError,
|
||||
TaskIdentityOverlayService,
|
||||
)
|
||||
|
||||
|
||||
_ENDPOINT = "/api/governance/owner-authorizations"
|
||||
|
||||
|
||||
def _enabled() -> bool:
|
||||
return os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_ENABLED", ""
|
||||
).strip().lower() in {"1", "true", "yes", "on"}
|
||||
|
||||
|
||||
def _bearer(header: str) -> str:
|
||||
prefix = "Bearer "
|
||||
if not header.startswith(prefix):
|
||||
raise IdentityOverlayError("OVERLAY_AUTHENTICATION_REQUIRED", 401)
|
||||
token = header[len(prefix):].strip()
|
||||
if not token or len(token) > 4096:
|
||||
raise IdentityOverlayError("OVERLAY_AUTHENTICATION_REQUIRED", 401)
|
||||
return token
|
||||
|
||||
|
||||
class OverlayHandler(BaseHTTPRequestHandler):
|
||||
server_version = "aios-task-identity-overlay/1"
|
||||
sys_version = ""
|
||||
|
||||
@property
|
||||
def overlay(self) -> TaskIdentityOverlayService:
|
||||
return self.server.overlay # type: ignore[attr-defined]
|
||||
|
||||
def log_message(self, format: str, *args: Any) -> None:
|
||||
# Never log Authorization or request bodies.
|
||||
return
|
||||
|
||||
def _send(self, status: int, value: dict[str, Any]) -> None:
|
||||
payload = (
|
||||
json.dumps(
|
||||
value,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
)
|
||||
+ "\n"
|
||||
).encode("utf-8")
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.send_header("Content-Length", str(len(payload)))
|
||||
self.end_headers()
|
||||
self.wfile.write(payload)
|
||||
|
||||
def _body(self) -> dict[str, Any]:
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length", "0"))
|
||||
except ValueError:
|
||||
raise IdentityOverlayError("OVERLAY_CONTENT_LENGTH_INVALID") from None
|
||||
if length <= 0 or length > MAX_BODY_BYTES:
|
||||
raise IdentityOverlayError("OVERLAY_BODY_SIZE_REJECTED", 413)
|
||||
raw = self.rfile.read(length)
|
||||
try:
|
||||
value = json.loads(raw)
|
||||
except (UnicodeDecodeError, json.JSONDecodeError):
|
||||
raise IdentityOverlayError("OVERLAY_BODY_JSON_INVALID") from None
|
||||
if not isinstance(value, dict):
|
||||
raise IdentityOverlayError("OVERLAY_BODY_OBJECT_REQUIRED")
|
||||
return value
|
||||
|
||||
def do_GET(self) -> None:
|
||||
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
|
||||
if path != "/healthz":
|
||||
self._send(404, {"error": "NOT_FOUND"})
|
||||
return
|
||||
self._send(
|
||||
200,
|
||||
{
|
||||
"service": "aios-task-identity-overlay",
|
||||
"status": "active" if _enabled() else "disabled",
|
||||
"global_token_registry_used": False,
|
||||
"loopback_only": True,
|
||||
},
|
||||
)
|
||||
|
||||
def do_POST(self) -> None:
|
||||
path = urllib.parse.urlparse(self.path).path.rstrip("/") or "/"
|
||||
if path != _ENDPOINT:
|
||||
self._send(404, {"error": "NOT_FOUND"})
|
||||
return
|
||||
if not _enabled():
|
||||
self._send(503, {"error": "IDENTITY_OVERLAY_DISABLED"})
|
||||
return
|
||||
try:
|
||||
token = _bearer(self.headers.get("Authorization", ""))
|
||||
result = self.overlay.provision(self._body(), token)
|
||||
self._send(200, result)
|
||||
except (IdentityOverlayError, OwnerAuthorizationError, ProvisioningError) as exc:
|
||||
body: dict[str, Any] = {"error": exc.code}
|
||||
if getattr(exc, "details", None):
|
||||
body["details"] = exc.details
|
||||
self._send(exc.status, body)
|
||||
except Exception:
|
||||
self._send(500, {"error": "IDENTITY_OVERLAY_API_INTERNAL_ERROR"})
|
||||
|
||||
|
||||
class OverlayServer(ThreadingHTTPServer):
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
address: tuple[str, int],
|
||||
overlay: TaskIdentityOverlayService,
|
||||
) -> None:
|
||||
super().__init__(address, OverlayHandler)
|
||||
self.overlay = overlay
|
||||
|
||||
|
||||
def main() -> None:
|
||||
host = os.getenv("AIOS_GITOPS_IDENTITY_OVERLAY_HOST", "127.0.0.1")
|
||||
if host not in {"127.0.0.1", "::1", "localhost"}:
|
||||
raise SystemExit("identity overlay must listen on loopback")
|
||||
try:
|
||||
port = int(os.getenv("AIOS_GITOPS_IDENTITY_OVERLAY_PORT", "19864"))
|
||||
except ValueError:
|
||||
raise SystemExit("invalid overlay port") from None
|
||||
if not 1024 <= port <= 65535:
|
||||
raise SystemExit("invalid overlay port")
|
||||
config = IdentityOverlayConfig.from_environment()
|
||||
server = OverlayServer(
|
||||
(host, port),
|
||||
TaskIdentityOverlayService(config),
|
||||
)
|
||||
server.serve_forever(poll_interval=0.25)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
+92
@@ -0,0 +1,92 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Root-governed CLI for issuing and revoking task identity overlays.
|
||||
|
||||
The CLI never prints the bearer token. It returns only the root-owned secret
|
||||
reference and non-secret metadata.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
from task_identity_overlay import (
|
||||
IdentityOverlayConfig,
|
||||
IdentityOverlayError,
|
||||
TaskIdentityOverlayStore,
|
||||
)
|
||||
|
||||
|
||||
def _write_result(path: str, value: dict) -> None:
|
||||
data = json.dumps(value, sort_keys=True, separators=(",", ":")) + "\n"
|
||||
if path == "-":
|
||||
sys.stdout.write(data)
|
||||
return
|
||||
target = Path(path)
|
||||
target.parent.mkdir(parents=True, exist_ok=True)
|
||||
target.write_text(data, encoding="utf-8")
|
||||
os.chmod(target, 0o600)
|
||||
|
||||
|
||||
def parser() -> argparse.ArgumentParser:
|
||||
value = argparse.ArgumentParser(
|
||||
description="Issue/status/revoke a task-scoped identity overlay"
|
||||
)
|
||||
sub = value.add_subparsers(dest="command", required=True)
|
||||
|
||||
issue = sub.add_parser("issue")
|
||||
issue.add_argument("--ttl-seconds", type=int, default=900)
|
||||
issue.add_argument("--authorization-assertion-ref", required=True)
|
||||
issue.add_argument(
|
||||
"--operator-identity",
|
||||
default=os.getenv("SUDO_USER") or os.getenv("USER") or "root",
|
||||
)
|
||||
issue.add_argument("--result-json", default="-")
|
||||
|
||||
status = sub.add_parser("status")
|
||||
status.add_argument("--overlay-id", required=True)
|
||||
status.add_argument("--result-json", default="-")
|
||||
|
||||
revoke = sub.add_parser("revoke")
|
||||
revoke.add_argument("--overlay-id", required=True)
|
||||
revoke.add_argument("--reason", required=True)
|
||||
revoke.add_argument("--result-json", default="-")
|
||||
return value
|
||||
|
||||
|
||||
def main() -> int:
|
||||
args = parser().parse_args()
|
||||
try:
|
||||
store = TaskIdentityOverlayStore(
|
||||
IdentityOverlayConfig.from_environment()
|
||||
)
|
||||
if args.command == "issue":
|
||||
result = store.issue(
|
||||
ttl_seconds=args.ttl_seconds,
|
||||
authorization_assertion_ref=args.authorization_assertion_ref,
|
||||
operator_identity=args.operator_identity,
|
||||
)
|
||||
elif args.command == "status":
|
||||
result = store.status(args.overlay_id)
|
||||
else:
|
||||
result = store.revoke(args.overlay_id, reason=args.reason)
|
||||
_write_result(args.result_json, result)
|
||||
return 0
|
||||
except IdentityOverlayError as exc:
|
||||
body = {"status": "BLOCKED", "error": exc.code}
|
||||
if exc.details:
|
||||
body["details"] = exc.details
|
||||
_write_result(getattr(args, "result_json", "-"), body)
|
||||
return 2
|
||||
except Exception:
|
||||
_write_result(
|
||||
getattr(args, "result_json", "-"),
|
||||
{"status": "FAILED", "error": "IDENTITY_OVERLAY_CLI_INTERNAL_ERROR"},
|
||||
)
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,355 @@
|
||||
"""Fail-closed access to the authoritative bare Git repository."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
import urllib.parse
|
||||
from pathlib import Path
|
||||
from typing import Iterable
|
||||
|
||||
_ALLOWED_COMMANDS = frozenset(
|
||||
{
|
||||
"cat-file",
|
||||
"config",
|
||||
"diff",
|
||||
"for-each-ref",
|
||||
"ls-remote",
|
||||
"merge-base",
|
||||
"push",
|
||||
"remote",
|
||||
"rev-parse",
|
||||
"show-ref",
|
||||
"tag",
|
||||
}
|
||||
)
|
||||
_OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
_MAX_OUTPUT = 1_048_576
|
||||
_TIMEOUT = 8.0
|
||||
|
||||
|
||||
class AuthoritativeGitError(RuntimeError):
|
||||
"""A fail-closed authoritative repository or ref query error."""
|
||||
|
||||
|
||||
class AuthoritativeGitNotFound(AuthoritativeGitError):
|
||||
"""A validated revision does not exist in the authoritative repository."""
|
||||
|
||||
|
||||
class AuthoritativeGitOutputTooLarge(AuthoritativeGitError):
|
||||
"""A controlled Git query exceeded the response-size boundary."""
|
||||
|
||||
|
||||
def _redact(text: str) -> str:
|
||||
value = str(text or "")
|
||||
value = re.sub(r"(?i)(authorization\s*[:=]\s*)(?:bearer|token)\s+\S+", r"\1REDACTED", value)
|
||||
value = re.sub(r"(?i)((?:access_)?token\s*[:=]\s*)\S+", r"\1REDACTED", value)
|
||||
value = re.sub(r"(?i)(https?://[^/\s:@]+:)[^@\s/]+@", r"\1REDACTED@", value)
|
||||
return value
|
||||
|
||||
|
||||
def _configured_path(git_dir: str | Path | None = None) -> Path:
|
||||
raw = str(git_dir or os.getenv("AIOS_GITOPS_AUTHORITATIVE_GIT_DIR", "")).strip()
|
||||
if not raw:
|
||||
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
|
||||
path = Path(raw)
|
||||
if not path.is_absolute() or ".." in path.parts:
|
||||
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
|
||||
try:
|
||||
resolved = path.resolve(strict=True)
|
||||
except OSError as exc:
|
||||
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE") from exc
|
||||
if not resolved.is_dir():
|
||||
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
|
||||
return resolved
|
||||
|
||||
|
||||
def _run(
|
||||
git_dir: Path,
|
||||
args: list[str],
|
||||
*,
|
||||
check: bool,
|
||||
timeout: float = _TIMEOUT,
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
if not args or args[0] not in _ALLOWED_COMMANDS:
|
||||
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["git", "--git-dir", str(git_dir), *args],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
timeout=timeout,
|
||||
env={**os.environ, "GIT_OPTIONAL_LOCKS": "0"},
|
||||
)
|
||||
except (OSError, subprocess.TimeoutExpired) as exc:
|
||||
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED") from exc
|
||||
if len(result.stdout) + len(result.stderr) > _MAX_OUTPUT:
|
||||
raise AuthoritativeGitOutputTooLarge("GIT_OUTPUT_LIMIT_EXCEEDED")
|
||||
if check and result.returncode != 0:
|
||||
detail = _redact(result.stderr.strip() or result.stdout.strip())
|
||||
raise AuthoritativeGitError(
|
||||
"GIT_REF_QUERY_FAILED" + (f": {detail[:160]}" if detail else "")
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def _repository_identity_from_remote(url: str) -> str:
|
||||
value = str(url or "").strip().split("?", 1)[0].rstrip("/")
|
||||
if not value:
|
||||
return ""
|
||||
if "://" in value:
|
||||
value = urllib.parse.urlparse(value).path
|
||||
elif ":" in value:
|
||||
value = value.rsplit(":", 1)[1]
|
||||
value = value.rsplit("@", 1)[-1].strip("/")
|
||||
value = re.sub(r"\.git$", "", value, flags=re.IGNORECASE)
|
||||
parts = [part for part in value.split("/") if part]
|
||||
if len(parts) >= 2:
|
||||
value = "/".join(parts[-2:])
|
||||
return value.strip("/").lower()
|
||||
|
||||
|
||||
def verify_repository(
|
||||
git_dir: str | Path | None = None,
|
||||
repository_identity: str | None = None,
|
||||
) -> tuple[Path, str]:
|
||||
path = _configured_path(git_dir)
|
||||
expected = str(
|
||||
repository_identity
|
||||
or os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", "")
|
||||
).strip().strip("/")
|
||||
if not expected or expected.count("/") != 1:
|
||||
raise AuthoritativeGitError("REPOSITORY_IDENTITY_MISMATCH")
|
||||
bare = _run(path, ["rev-parse", "--is-bare-repository"], check=True)
|
||||
if bare.stdout.strip().lower() != "true":
|
||||
raise AuthoritativeGitError("AUTHORITATIVE_REPOSITORY_UNAVAILABLE")
|
||||
remote = _run(path, ["config", "--get", "remote.gitea.url"], check=False)
|
||||
actual = _repository_identity_from_remote(remote.stdout)
|
||||
if actual != expected.lower():
|
||||
raise AuthoritativeGitError("REPOSITORY_IDENTITY_MISMATCH")
|
||||
return path, expected
|
||||
|
||||
|
||||
def run_authoritative_git(
|
||||
args: list[str],
|
||||
*,
|
||||
check: bool = True,
|
||||
git_dir: str | Path | None = None,
|
||||
timeout: float = _TIMEOUT,
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
path, _ = verify_repository(git_dir=git_dir)
|
||||
return _run(path, list(args), check=check, timeout=timeout)
|
||||
|
||||
|
||||
def authoritative_head_oid(
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
) -> str:
|
||||
result = run_authoritative_git(["rev-parse", "--verify", "refs/heads/main"], git_dir=git_dir)
|
||||
oid = result.stdout.strip().lower()
|
||||
if not _OID_RE.fullmatch(oid):
|
||||
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
|
||||
return oid
|
||||
|
||||
|
||||
def authoritative_tags(
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
) -> list[dict[str, str | None]]:
|
||||
result = run_authoritative_git(
|
||||
[
|
||||
"for-each-ref",
|
||||
"refs/tags",
|
||||
"--format=%(refname:strip=2)\t%(objectname)\t%(objecttype)",
|
||||
],
|
||||
git_dir=git_dir,
|
||||
)
|
||||
tags: list[dict[str, str | None]] = []
|
||||
for line in result.stdout.splitlines():
|
||||
name, oid, object_type = (line.split("\t", 2) + ["", ""])[:3]
|
||||
if not name or not _OID_RE.fullmatch(oid.lower()):
|
||||
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
|
||||
peeled_result = run_authoritative_git(
|
||||
["rev-parse", "--verify", f"refs/tags/{name}^{{commit}}"],
|
||||
git_dir=git_dir,
|
||||
)
|
||||
peeled = peeled_result.stdout.strip().lower()
|
||||
if not _OID_RE.fullmatch(peeled):
|
||||
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
|
||||
tags.append(
|
||||
{
|
||||
"name": name,
|
||||
"tag_oid": oid.lower(),
|
||||
"object_type": object_type,
|
||||
"peeled_target_oid": peeled,
|
||||
}
|
||||
)
|
||||
return tags
|
||||
|
||||
|
||||
def authoritative_branches(
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
) -> list[dict[str, str]]:
|
||||
result = run_authoritative_git(
|
||||
[
|
||||
"for-each-ref",
|
||||
"refs/heads",
|
||||
"--format=%(refname:strip=2)\t%(objectname)",
|
||||
],
|
||||
git_dir=git_dir,
|
||||
)
|
||||
branches: list[dict[str, str]] = []
|
||||
for line in result.stdout.splitlines():
|
||||
name, oid = (line.split("\t", 1) + [""])[:2]
|
||||
if not name or not _OID_RE.fullmatch(oid.lower()):
|
||||
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
|
||||
branches.append({"name": name, "oid": oid.lower()})
|
||||
return branches
|
||||
|
||||
|
||||
def authoritative_commit(
|
||||
oid: str,
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
) -> str:
|
||||
value = str(oid or "").strip().lower()
|
||||
if not _OID_RE.fullmatch(value):
|
||||
raise ValueError("commit OID must be a full 40-character value")
|
||||
result = run_authoritative_git(
|
||||
["rev-parse", "--verify", f"{value}^{{commit}}"],
|
||||
git_dir=git_dir,
|
||||
)
|
||||
resolved = result.stdout.strip().lower()
|
||||
if resolved != value:
|
||||
raise AuthoritativeGitError("GIT_REF_QUERY_FAILED")
|
||||
return resolved
|
||||
|
||||
|
||||
def authoritative_lineage(
|
||||
ancestor: str,
|
||||
descendant: str,
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
) -> None:
|
||||
authoritative_commit(ancestor, git_dir=git_dir)
|
||||
authoritative_commit(descendant, git_dir=git_dir)
|
||||
result = run_authoritative_git(
|
||||
["merge-base", "--is-ancestor", ancestor, descendant],
|
||||
check=False,
|
||||
git_dir=git_dir,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
raise AuthoritativeGitError("evidence lineage mismatch")
|
||||
|
||||
|
||||
_SAFE_REF_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._/-]{0,239}$")
|
||||
|
||||
|
||||
def _safe_ref_name(value: str) -> bool:
|
||||
return bool(
|
||||
_SAFE_REF_RE.fullmatch(value)
|
||||
and ".." not in value
|
||||
and "//" not in value
|
||||
and "@{" not in value
|
||||
and not value.endswith(("/", ".", ".lock"))
|
||||
and not any(part in {"", ".", ".."} for part in value.split("/"))
|
||||
)
|
||||
|
||||
|
||||
def validate_git_revision(
|
||||
value: str,
|
||||
field: str,
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
) -> str:
|
||||
revision = str(value or "").strip()
|
||||
if not revision or revision != str(value or "") or revision.startswith("-"):
|
||||
raise ValueError(f"invalid {field} revision")
|
||||
if _OID_RE.fullmatch(revision.lower()):
|
||||
try:
|
||||
return authoritative_commit(revision.lower(), git_dir=git_dir)
|
||||
except AuthoritativeGitError as exc:
|
||||
raise AuthoritativeGitNotFound(f"{field} revision not found") from exc
|
||||
if not _safe_ref_name(revision) or any(token in revision for token in ("^", "~", ":", "\\")):
|
||||
raise ValueError(f"invalid {field} revision")
|
||||
if revision.startswith("refs/"):
|
||||
if not revision.startswith(("refs/heads/", "refs/tags/")):
|
||||
raise ValueError(f"invalid {field} revision")
|
||||
candidates = [revision]
|
||||
else:
|
||||
candidates = [f"refs/heads/{revision}", f"refs/tags/{revision}"]
|
||||
matches: list[str] = []
|
||||
for candidate in candidates:
|
||||
result = run_authoritative_git(
|
||||
["rev-parse", "--verify", f"{candidate}^{{commit}}"],
|
||||
check=False,
|
||||
git_dir=git_dir,
|
||||
)
|
||||
oid = result.stdout.strip().lower()
|
||||
if result.returncode == 0 and _OID_RE.fullmatch(oid):
|
||||
matches.append(oid)
|
||||
if not matches:
|
||||
raise AuthoritativeGitNotFound(f"{field} revision not found")
|
||||
if len(set(matches)) != 1 or len(matches) != 1:
|
||||
raise ValueError(f"ambiguous {field} revision")
|
||||
return matches[0]
|
||||
|
||||
|
||||
def authoritative_diff(
|
||||
from_revision: str,
|
||||
to_revision: str,
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
) -> dict[str, object]:
|
||||
path, _ = verify_repository(git_dir=git_dir)
|
||||
from_oid = validate_git_revision(from_revision, "from", git_dir=path)
|
||||
to_oid = validate_git_revision(to_revision, "to", git_dir=path)
|
||||
args = ["diff", "--no-ext-diff", "--no-textconv", from_oid, to_oid]
|
||||
result = run_authoritative_git(args, git_dir=path)
|
||||
return {
|
||||
"code": 0,
|
||||
"stdout": result.stdout,
|
||||
"stderr": "",
|
||||
"cmd": ["git", f"--git-dir={path}", *args],
|
||||
"from_oid": from_oid,
|
||||
"to_oid": to_oid,
|
||||
}
|
||||
|
||||
|
||||
def repository_snapshot(
|
||||
*,
|
||||
git_dir: str | Path | None = None,
|
||||
repository_identity: str | None = None,
|
||||
) -> dict[str, object]:
|
||||
configured = bool(
|
||||
str(git_dir or os.getenv("AIOS_GITOPS_AUTHORITATIVE_GIT_DIR", "")).strip()
|
||||
)
|
||||
try:
|
||||
path, identity = verify_repository(
|
||||
git_dir=git_dir,
|
||||
repository_identity=repository_identity,
|
||||
)
|
||||
head = authoritative_head_oid(git_dir=path)
|
||||
return {
|
||||
"repository_available": True,
|
||||
"authoritative_git_dir_configured": configured,
|
||||
"authoritative_git_dir_readable": True,
|
||||
"authoritative_git_dir": str(path),
|
||||
"authoritative_head_oid": head,
|
||||
"repository_identity": identity,
|
||||
"query_error": None,
|
||||
}
|
||||
except (AuthoritativeGitError, ValueError) as exc:
|
||||
return {
|
||||
"repository_available": False,
|
||||
"authoritative_git_dir_configured": configured,
|
||||
"authoritative_git_dir_readable": False,
|
||||
"authoritative_git_dir": None,
|
||||
"authoritative_head_oid": None,
|
||||
"repository_identity": str(
|
||||
repository_identity
|
||||
or os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", "")
|
||||
).strip() or None,
|
||||
"query_error": _redact(str(exc)),
|
||||
}
|
||||
@@ -0,0 +1,953 @@
|
||||
"""Owner-authorized, fail-closed task writer provisioning bridge.
|
||||
|
||||
This module converts an authenticated Owner authorization into a canonical,
|
||||
short-lived, one-time grant request. It delegates signing, validation and
|
||||
worktree/writer provisioning to existing root-governed executables.
|
||||
|
||||
It never writes Git refs directly and never authorizes main, tag, baseline or
|
||||
production mutations.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import secrets
|
||||
import shutil
|
||||
import stat
|
||||
import subprocess
|
||||
import tempfile
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping
|
||||
from signer_contract_compatibility import (
|
||||
deployed_signer_help,
|
||||
run_compatible_signer,
|
||||
run_compatible_validator,
|
||||
)
|
||||
|
||||
|
||||
OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
SHA256_RE = re.compile(r"^[0-9a-f]{64}$")
|
||||
TASK_RE = re.compile(r"^[A-Z0-9][A-Z0-9._:-]{7,127}$")
|
||||
BRANCH_RE = re.compile(r"^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$")
|
||||
OWNER_REF_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:/@+-]{3,255}$")
|
||||
|
||||
REQUIRED_REQUEST_FIELDS = frozenset(
|
||||
{
|
||||
"task_id",
|
||||
"repository",
|
||||
"base_ref",
|
||||
"base_oid",
|
||||
"target_branch",
|
||||
"owner_authorization_reference",
|
||||
"one_time_use",
|
||||
"expires_in_seconds",
|
||||
"production_change_authorized",
|
||||
"tag_change_authorized",
|
||||
"baseline_change_authorized",
|
||||
"main_write_authorized",
|
||||
"allowed_operations",
|
||||
"denied_operations",
|
||||
}
|
||||
)
|
||||
REQUIRED_ALLOWED_OPERATIONS = frozenset(
|
||||
{
|
||||
"create_worktree",
|
||||
"create_target_branch_if_absent",
|
||||
"commit_to_target_branch",
|
||||
"push_target_branch",
|
||||
}
|
||||
)
|
||||
REQUIRED_DENIED_OPERATIONS = frozenset(
|
||||
{
|
||||
"direct_main_push",
|
||||
"force_push",
|
||||
"tag_create",
|
||||
"tag_update",
|
||||
"tag_delete",
|
||||
"branch_delete",
|
||||
"repository_admin",
|
||||
"baseline_write",
|
||||
"production_deploy",
|
||||
"production_marker_write",
|
||||
"history_rewrite",
|
||||
}
|
||||
)
|
||||
REQUIRED_NEGATIVE_TESTS = frozenset(
|
||||
{
|
||||
"main_write_denied",
|
||||
"other_branch_write_denied",
|
||||
"tag_create_denied",
|
||||
"tag_update_denied",
|
||||
"baseline_write_denied",
|
||||
"force_push_denied",
|
||||
"branch_delete_denied",
|
||||
}
|
||||
)
|
||||
SENSITIVE_KEY_MARKERS = (
|
||||
"authorization",
|
||||
"credential",
|
||||
"private_key",
|
||||
"secret",
|
||||
"signature",
|
||||
"token",
|
||||
)
|
||||
|
||||
|
||||
class ProvisioningError(RuntimeError):
|
||||
"""Stable fail-closed error returned to the API adapter."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
code: str,
|
||||
status: int = 400,
|
||||
*,
|
||||
details: Mapping[str, Any] | None = None,
|
||||
) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
self.details = dict(details or {})
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OwnerContext:
|
||||
identity: str
|
||||
role: str
|
||||
authorization_reference: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProvisioningConfig:
|
||||
repository_identity: str
|
||||
authority_git_dir: Path
|
||||
state_root: Path
|
||||
signer: Path
|
||||
validator: Path
|
||||
provisioner: Path
|
||||
governed_use_sudo: bool = False
|
||||
sudo_path: Path = Path("/usr/bin/sudo")
|
||||
max_expiry_seconds: int = 1800
|
||||
|
||||
@classmethod
|
||||
def from_environment(cls) -> "ProvisioningConfig":
|
||||
return cls(
|
||||
repository_identity=os.getenv(
|
||||
"AIOS_GITOPS_REPOSITORY_IDENTITY", "aios/aios"
|
||||
).strip(),
|
||||
authority_git_dir=Path(
|
||||
os.getenv("AIOS_GITOPS_AUTHORITY_GIT_DIR", "/data/aios-gitops/repo.git")
|
||||
),
|
||||
state_root=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_AUTHORIZED_WRITER_STATE_ROOT",
|
||||
"/var/lib/aios-gitops/authorized-writer-bridge",
|
||||
)
|
||||
),
|
||||
signer=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_GRANT_SIGNER_ADAPTER",
|
||||
"/usr/local/libexec/aios-grant-signer-adapter",
|
||||
)
|
||||
),
|
||||
validator=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_GRANT_VALIDATOR",
|
||||
"/usr/local/libexec/aios-grant-validator",
|
||||
)
|
||||
),
|
||||
provisioner=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_TASK_WRITER_PROVISIONER",
|
||||
"/usr/local/libexec/aios-task-writer-provisioner",
|
||||
)
|
||||
),
|
||||
governed_use_sudo=os.getenv(
|
||||
"AIOS_GITOPS_GOVERNED_USE_SUDO", ""
|
||||
).strip().lower() in {"1", "true", "yes", "on"},
|
||||
sudo_path=Path(
|
||||
os.getenv("AIOS_GITOPS_SUDO_PATH", "/usr/bin/sudo")
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def utc_now() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
|
||||
def iso_utc(value: datetime) -> str:
|
||||
return value.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def canonical_json_bytes(value: Any) -> bytes:
|
||||
return (
|
||||
json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
|
||||
+ "\n"
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def sha256_json(value: Any) -> str:
|
||||
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
|
||||
|
||||
|
||||
def _atomic_write_json(path: Path, value: Any, mode: int = 0o600) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
if path.parent.is_symlink() or path.is_symlink():
|
||||
raise ProvisioningError("STATE_PATH_SYMLINK_REJECTED", 500)
|
||||
fd, temporary = tempfile.mkstemp(prefix=".tmp-", dir=path.parent)
|
||||
try:
|
||||
os.fchmod(fd, mode)
|
||||
with os.fdopen(fd, "wb", closefd=True) as stream:
|
||||
stream.write(canonical_json_bytes(value))
|
||||
stream.flush()
|
||||
os.fsync(stream.fileno())
|
||||
os.replace(temporary, path)
|
||||
os.chmod(path, mode)
|
||||
parent_fd = os.open(path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0))
|
||||
try:
|
||||
os.fsync(parent_fd)
|
||||
finally:
|
||||
os.close(parent_fd)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
|
||||
|
||||
def _read_json(path: Path) -> dict[str, Any]:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise ProvisioningError("RESULT_FILE_INVALID", 500)
|
||||
if path.stat().st_size <= 0 or path.stat().st_size > 1_048_576:
|
||||
raise ProvisioningError("RESULT_FILE_INVALID", 500)
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError):
|
||||
raise ProvisioningError("RESULT_JSON_INVALID", 500) from None
|
||||
if not isinstance(value, dict):
|
||||
raise ProvisioningError("RESULT_OBJECT_REQUIRED", 500)
|
||||
return value
|
||||
|
||||
|
||||
def _safe_receipt_id(task_id: str, repository: str, branch: str) -> str:
|
||||
return hashlib.sha256(f"{task_id}\0{repository}\0{branch}".encode()).hexdigest()
|
||||
|
||||
|
||||
def _redacted(value: Any) -> Any:
|
||||
if isinstance(value, dict):
|
||||
cleaned = {}
|
||||
for key, inner in value.items():
|
||||
lowered = str(key).lower()
|
||||
if any(marker in lowered for marker in SENSITIVE_KEY_MARKERS):
|
||||
if lowered in {
|
||||
"owner_authorization_reference",
|
||||
"signing_key_identity",
|
||||
"signer_identity",
|
||||
}:
|
||||
cleaned[key] = inner
|
||||
else:
|
||||
cleaned[key] = "[REDACTED]"
|
||||
else:
|
||||
cleaned[key] = _redacted(inner)
|
||||
return cleaned
|
||||
if isinstance(value, list):
|
||||
return [_redacted(item) for item in value]
|
||||
return value
|
||||
|
||||
|
||||
def _run(
|
||||
argv: list[str],
|
||||
*,
|
||||
env: Mapping[str, str] | None = None,
|
||||
timeout: int = 60,
|
||||
allowed_returncodes: tuple[int, ...] = (0,),
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
result = subprocess.run(
|
||||
argv,
|
||||
text=True,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=timeout,
|
||||
env=dict(env) if env is not None else None,
|
||||
)
|
||||
if result.returncode not in allowed_returncodes:
|
||||
raise ProvisioningError(
|
||||
"GOVERNED_TOOL_FAILED",
|
||||
503,
|
||||
details={
|
||||
"tool": Path(argv[0]).name,
|
||||
"returncode": result.returncode,
|
||||
"stderr": result.stderr[-1000:],
|
||||
},
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def _git(git_dir: Path, *args: str, allowed_returncodes: tuple[int, ...] = (0,)) -> str:
|
||||
result = _run(
|
||||
["git", "--git-dir", str(git_dir), *args],
|
||||
timeout=30,
|
||||
allowed_returncodes=allowed_returncodes,
|
||||
)
|
||||
return result.stdout.strip()
|
||||
|
||||
|
||||
def _verify_executable(path: Path, name: str) -> None:
|
||||
if not path.is_absolute() or path.is_symlink() or not path.is_file():
|
||||
raise ProvisioningError(f"{name}_EXECUTABLE_INVALID", 503)
|
||||
info = path.stat(follow_symlinks=False)
|
||||
if not stat.S_ISREG(info.st_mode) or not os.access(path, os.X_OK):
|
||||
raise ProvisioningError(f"{name}_EXECUTABLE_INVALID", 503)
|
||||
if info.st_mode & (stat.S_IWGRP | stat.S_IWOTH):
|
||||
raise ProvisioningError(f"{name}_EXECUTABLE_PERMISSIONS_REJECTED", 503)
|
||||
|
||||
|
||||
def _tool_argv(
|
||||
config: ProvisioningConfig,
|
||||
path: Path,
|
||||
*args: str,
|
||||
) -> list[str]:
|
||||
if config.governed_use_sudo:
|
||||
return [str(config.sudo_path), "-n", "--", str(path), *args]
|
||||
return [str(path), *args]
|
||||
|
||||
|
||||
def _verify_tool_contract(
|
||||
path: Path,
|
||||
name: str,
|
||||
config: ProvisioningConfig,
|
||||
) -> None:
|
||||
_verify_executable(path, name)
|
||||
if config.governed_use_sudo:
|
||||
_verify_executable(config.sudo_path, "SUDO")
|
||||
help_result = _run(_tool_argv(config, path, "--help"), timeout=15)
|
||||
if name == "SIGNER":
|
||||
sign_help = _run(
|
||||
_tool_argv(config, path, "sign", "--help"),
|
||||
timeout=15,
|
||||
)
|
||||
if deployed_signer_help(sign_help.stdout, sign_help.stderr):
|
||||
_run(_tool_argv(config, path, "self-test"), timeout=30)
|
||||
return
|
||||
for flag in ("--grant-dir", "--result-json"):
|
||||
if flag not in help_result.stdout and flag not in help_result.stderr:
|
||||
raise ProvisioningError(f"{name}_CONTRACT_UNSUPPORTED", 503)
|
||||
_run(_tool_argv(config, path, "--self-test"), timeout=30)
|
||||
|
||||
|
||||
def _validate_request(
|
||||
raw: Mapping[str, Any],
|
||||
*,
|
||||
owner: OwnerContext,
|
||||
config: ProvisioningConfig,
|
||||
) -> dict[str, Any]:
|
||||
if owner.role != "owner" or not owner.identity.strip():
|
||||
raise ProvisioningError("OWNER_AUTHORIZATION_REQUIRED", 403)
|
||||
if set(raw) != REQUIRED_REQUEST_FIELDS:
|
||||
raise ProvisioningError("REQUEST_FIELDS_REJECTED")
|
||||
if raw["repository"] != config.repository_identity:
|
||||
raise ProvisioningError("REPOSITORY_IDENTITY_MISMATCH", 409)
|
||||
if raw["base_ref"] != "refs/heads/main":
|
||||
raise ProvisioningError("BASE_REF_REJECTED", 409)
|
||||
if not isinstance(raw["base_oid"], str) or not OID_RE.fullmatch(raw["base_oid"]):
|
||||
raise ProvisioningError("BASE_OID_REJECTED")
|
||||
if (
|
||||
not isinstance(raw["target_branch"], str)
|
||||
or not BRANCH_RE.fullmatch(raw["target_branch"])
|
||||
or raw["target_branch"] in {"main", "master"}
|
||||
):
|
||||
raise ProvisioningError("TARGET_BRANCH_REJECTED")
|
||||
if not isinstance(raw["task_id"], str) or not TASK_RE.fullmatch(raw["task_id"]):
|
||||
raise ProvisioningError("TASK_ID_REJECTED")
|
||||
if (
|
||||
not isinstance(raw["owner_authorization_reference"], str)
|
||||
or not OWNER_REF_RE.fullmatch(raw["owner_authorization_reference"])
|
||||
or raw["owner_authorization_reference"] != owner.authorization_reference
|
||||
):
|
||||
raise ProvisioningError("OWNER_AUTHORIZATION_REFERENCE_MISMATCH", 403)
|
||||
if raw["one_time_use"] is not True:
|
||||
raise ProvisioningError("ONE_TIME_USE_REQUIRED")
|
||||
expiry = raw["expires_in_seconds"]
|
||||
if (
|
||||
not isinstance(expiry, int)
|
||||
or isinstance(expiry, bool)
|
||||
or not 60 <= expiry <= config.max_expiry_seconds
|
||||
):
|
||||
raise ProvisioningError("GRANT_LIFETIME_REJECTED")
|
||||
for name in (
|
||||
"production_change_authorized",
|
||||
"tag_change_authorized",
|
||||
"baseline_change_authorized",
|
||||
"main_write_authorized",
|
||||
):
|
||||
if raw[name] is not False:
|
||||
raise ProvisioningError("PRODUCTION_CAPABILITY_REJECTED", 403)
|
||||
allowed = raw["allowed_operations"]
|
||||
denied = raw["denied_operations"]
|
||||
if not isinstance(allowed, list) or frozenset(allowed) != REQUIRED_ALLOWED_OPERATIONS:
|
||||
raise ProvisioningError("ALLOWED_OPERATIONS_MISMATCH", 403)
|
||||
if len(allowed) != len(set(allowed)):
|
||||
raise ProvisioningError("ALLOWED_OPERATIONS_MISMATCH", 403)
|
||||
if not isinstance(denied, list) or frozenset(denied) != REQUIRED_DENIED_OPERATIONS:
|
||||
raise ProvisioningError("DENIED_OPERATIONS_MISMATCH", 403)
|
||||
if len(denied) != len(set(denied)):
|
||||
raise ProvisioningError("DENIED_OPERATIONS_MISMATCH", 403)
|
||||
return dict(raw)
|
||||
|
||||
|
||||
def _prepare_state_root(path: Path) -> None:
|
||||
if not path.is_absolute() or path.is_symlink():
|
||||
raise ProvisioningError("STATE_ROOT_INVALID", 500)
|
||||
path.mkdir(parents=True, exist_ok=True, mode=0o700)
|
||||
os.chmod(path, 0o700)
|
||||
if path.stat().st_mode & (stat.S_IWGRP | stat.S_IWOTH):
|
||||
raise ProvisioningError("STATE_ROOT_PERMISSIONS_REJECTED", 500)
|
||||
(path / "receipts").mkdir(mode=0o700, exist_ok=True)
|
||||
(path / "locks").mkdir(mode=0o700, exist_ok=True)
|
||||
|
||||
|
||||
def _prestart_git_check(
|
||||
request: Mapping[str, Any],
|
||||
config: ProvisioningConfig,
|
||||
*,
|
||||
receipt_exists: bool,
|
||||
) -> dict[str, Any]:
|
||||
git_dir = config.authority_git_dir
|
||||
if not git_dir.is_absolute() or git_dir.is_symlink() or not git_dir.is_dir():
|
||||
raise ProvisioningError("AUTHORITY_GIT_DIR_INVALID", 503)
|
||||
actual_main = _git(git_dir, "rev-parse", request["base_ref"])
|
||||
if actual_main != request["base_oid"]:
|
||||
raise ProvisioningError(
|
||||
"AUTHORIZED_BASE_OID_DRIFT",
|
||||
409,
|
||||
details={"expected": request["base_oid"], "actual": actual_main},
|
||||
)
|
||||
ref = f"refs/heads/{request['target_branch']}"
|
||||
existing = _git(
|
||||
git_dir,
|
||||
"show-ref",
|
||||
"--verify",
|
||||
"--hash",
|
||||
ref,
|
||||
allowed_returncodes=(0, 1, 128),
|
||||
)
|
||||
if existing and not receipt_exists:
|
||||
raise ProvisioningError(
|
||||
"EXISTING_BRANCH_OID_CONFLICT",
|
||||
409,
|
||||
details={"branch_oid": existing},
|
||||
)
|
||||
if existing and receipt_exists:
|
||||
ancestor = _run(
|
||||
[
|
||||
"git",
|
||||
"--git-dir",
|
||||
str(git_dir),
|
||||
"merge-base",
|
||||
"--is-ancestor",
|
||||
request["base_oid"],
|
||||
ref,
|
||||
],
|
||||
allowed_returncodes=(0, 1),
|
||||
)
|
||||
if ancestor.returncode != 0:
|
||||
raise ProvisioningError("EXISTING_BRANCH_OID_CONFLICT", 409)
|
||||
return {
|
||||
"authoritative_main_oid": actual_main,
|
||||
"target_branch_preexisting": bool(existing),
|
||||
"target_branch_oid": existing or None,
|
||||
}
|
||||
|
||||
|
||||
def _build_plan(
|
||||
request: Mapping[str, Any],
|
||||
owner: OwnerContext,
|
||||
*,
|
||||
now: datetime,
|
||||
) -> tuple[dict[str, Any], dict[str, Any]]:
|
||||
expires_at = now + timedelta(seconds=int(request["expires_in_seconds"]))
|
||||
grant_request = {
|
||||
"schema": "aios.task-scoped-writer-grant-request.v1",
|
||||
"task_id": request["task_id"],
|
||||
"repository": request["repository"],
|
||||
"base": {"ref": request["base_ref"], "oid": request["base_oid"]},
|
||||
"target": {"branch": request["target_branch"]},
|
||||
"execution_contract": {
|
||||
"branch_creation": "governed_one_shot_provisioner",
|
||||
"writer_route": "POST /api/commit-file",
|
||||
"createBranch_route_required": False,
|
||||
},
|
||||
"owner_authorization": {
|
||||
"identity": owner.identity,
|
||||
"reference": owner.authorization_reference,
|
||||
"authenticated_role": owner.role,
|
||||
},
|
||||
"allowed_operations": sorted(request["allowed_operations"]),
|
||||
"denied_operations": sorted(request["denied_operations"]),
|
||||
"one_time_use": True,
|
||||
"authorization": {
|
||||
"production_change_authorized": False,
|
||||
"tag_change_authorized": False,
|
||||
"baseline_change_authorized": False,
|
||||
"main_write_authorized": False,
|
||||
},
|
||||
"issued_at": iso_utc(now),
|
||||
"not_before": iso_utc(now - timedelta(seconds=2)),
|
||||
"expires_at": iso_utc(expires_at),
|
||||
"nonce": secrets.token_hex(32),
|
||||
}
|
||||
binding_digest = sha256_json(grant_request)
|
||||
plan = {
|
||||
"schema": "aios.task-scoped-writer-approval-plan.v1",
|
||||
"approval_plan_id": f"sha256:{binding_digest}",
|
||||
"grant_request_sha256": binding_digest,
|
||||
"owner_authorization_reference": owner.authorization_reference,
|
||||
"owner_identity": owner.identity,
|
||||
"created_at": iso_utc(now),
|
||||
"expires_at": iso_utc(expires_at),
|
||||
"execute": True,
|
||||
"production_change_authorized": False,
|
||||
}
|
||||
return plan, grant_request
|
||||
|
||||
|
||||
def _expect_text(result: Mapping[str, Any], name: str) -> str:
|
||||
value = result.get(name)
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
raise ProvisioningError(f"{name.upper()}_MISSING", 503)
|
||||
return value
|
||||
|
||||
|
||||
def _verify_signer_result(
|
||||
result: Mapping[str, Any],
|
||||
*,
|
||||
approval_plan_id: str,
|
||||
) -> dict[str, str]:
|
||||
if result.get("status") not in {"SIGNED", "PASS", "COMPLETED"}:
|
||||
raise ProvisioningError("GRANT_SIGNING_FAILED", 503)
|
||||
if result.get("approval_plan_id") != approval_plan_id:
|
||||
raise ProvisioningError("APPROVAL_PLAN_ID_MISMATCH", 503)
|
||||
digest = _expect_text(result, "grant_digest_sha256")
|
||||
if not SHA256_RE.fullmatch(digest):
|
||||
raise ProvisioningError("GRANT_DIGEST_INVALID", 503)
|
||||
signer = result.get("signing_key_identity") or result.get("signer_identity")
|
||||
if not isinstance(signer, str) or not signer.strip():
|
||||
raise ProvisioningError("SIGNING_KEY_IDENTITY_MISSING", 503)
|
||||
signature_present = bool(result.get("signature_present")) or bool(
|
||||
result.get("owner_signature")
|
||||
)
|
||||
if not signature_present:
|
||||
raise ProvisioningError("OWNER_SIGNATURE_MISSING", 503)
|
||||
return {
|
||||
"grant_id": _expect_text(result, "grant_id"),
|
||||
"grant_digest_sha256": digest,
|
||||
"signing_key_identity": signer,
|
||||
}
|
||||
|
||||
|
||||
def _verify_validator_result(
|
||||
result: Mapping[str, Any],
|
||||
*,
|
||||
approval_plan_id: str,
|
||||
grant_digest: str,
|
||||
) -> None:
|
||||
if result.get("status") not in {"PASS", "VALID", "COMPLETED"}:
|
||||
raise ProvisioningError("GOVERNED_GRANT_VALIDATION_FAILED", 503)
|
||||
if result.get("approval_plan_id") != approval_plan_id:
|
||||
raise ProvisioningError("VALIDATED_PLAN_ID_MISMATCH", 503)
|
||||
if result.get("grant_digest_sha256") != grant_digest:
|
||||
raise ProvisioningError("VALIDATED_GRANT_DIGEST_MISMATCH", 503)
|
||||
checks = result.get("checks")
|
||||
required = {
|
||||
"schema_valid",
|
||||
"signature_valid",
|
||||
"signer_trusted",
|
||||
"approval_plan_active",
|
||||
"repository_match",
|
||||
"base_ref_match",
|
||||
"base_oid_match",
|
||||
"target_branch_match",
|
||||
"one_time_use",
|
||||
"allowed_operations_match",
|
||||
"denied_operations_match",
|
||||
}
|
||||
if not isinstance(checks, dict) or any(checks.get(name) is not True for name in required):
|
||||
raise ProvisioningError("GOVERNED_GRANT_VALIDATION_FAILED", 503)
|
||||
|
||||
|
||||
def _verify_provisioner_result(
|
||||
result: Mapping[str, Any],
|
||||
request: Mapping[str, Any],
|
||||
*,
|
||||
grant_id: str,
|
||||
validator_config_path: Path,
|
||||
) -> dict[str, Any]:
|
||||
if result.get("status") not in {"READY_FOR_CODE_AUTHORING", "COMPLETED"}:
|
||||
raise ProvisioningError("TASK_WRITER_PROVISIONING_FAILED", 503)
|
||||
|
||||
# The legacy bridge created the target ref itself. Keep accepting it for
|
||||
# controlled test doubles, but prefer the deployed direct one-shot writer.
|
||||
if result.get("status") == "COMPLETED" and result.get("writer_mode") == "direct_one_shot_detached":
|
||||
if result.get("target_branch") != request["target_branch"]:
|
||||
raise ProvisioningError("PROVISIONED_BRANCH_MISMATCH", 503)
|
||||
if result.get("base_oid") != request["base_oid"]:
|
||||
raise ProvisioningError("PROVISIONED_BASE_MISMATCH", 503)
|
||||
if result.get("writer_created") is not True:
|
||||
raise ProvisioningError("TASK_WRITER_PROVISIONING_FAILED", 503)
|
||||
writer_config_name = result.get("writer_config")
|
||||
if not isinstance(writer_config_name, str) or not Path(writer_config_name).is_absolute():
|
||||
raise ProvisioningError("WRITER_CONFIG_INVALID", 503)
|
||||
writer_config_path = Path(writer_config_name)
|
||||
writer_config = _read_json(writer_config_path)
|
||||
if writer_config.get("status") != "READY":
|
||||
raise ProvisioningError("WRITER_CONFIG_NOT_READY", 503)
|
||||
if writer_config.get("target_branch") != request["target_branch"]:
|
||||
raise ProvisioningError("WRITER_CONFIG_BRANCH_MISMATCH", 503)
|
||||
if writer_config.get("base_oid") != request["base_oid"]:
|
||||
raise ProvisioningError("WRITER_CONFIG_BASE_MISMATCH", 503)
|
||||
if writer_config.get("worktree_mode") != "detached":
|
||||
raise ProvisioningError("WRITER_MODE_UNSUPPORTED", 503)
|
||||
workspace = writer_config.get("worktree")
|
||||
if not isinstance(workspace, str) or not Path(workspace).is_absolute():
|
||||
raise ProvisioningError("PROVISIONED_WORKSPACE_INVALID", 503)
|
||||
credential_name = writer_config.get("runtime_credential_file")
|
||||
if not isinstance(credential_name, str) or not Path(credential_name).is_absolute():
|
||||
raise ProvisioningError("WRITER_CREDENTIAL_REF_INVALID", 503)
|
||||
credential = Path(credential_name)
|
||||
if not credential.is_file() or credential.is_symlink():
|
||||
raise ProvisioningError("WRITER_CREDENTIAL_MISSING", 503)
|
||||
credential_stat = credential.stat()
|
||||
if credential_stat.st_uid != 0 or stat.S_IMODE(credential_stat.st_mode) != 0o400:
|
||||
raise ProvisioningError("WRITER_CREDENTIAL_PERMISSIONS_INVALID", 503)
|
||||
|
||||
dynamic_config = _read_json(validator_config_path)
|
||||
ledger_name = dynamic_config.get("consumed_grants_ledger")
|
||||
if not isinstance(ledger_name, str) or not Path(ledger_name).is_absolute():
|
||||
raise ProvisioningError("GRANT_LEDGER_REF_INVALID", 503)
|
||||
ledger = Path(ledger_name)
|
||||
consumed = False
|
||||
if ledger.is_file() and not ledger.is_symlink():
|
||||
for line in ledger.read_text(encoding="utf-8").splitlines():
|
||||
try:
|
||||
row = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
if (
|
||||
isinstance(row, dict)
|
||||
and row.get("grant_id") == grant_id
|
||||
and row.get("target_branch") == request["target_branch"]
|
||||
and row.get("base_oid") == request["base_oid"]
|
||||
):
|
||||
consumed = True
|
||||
break
|
||||
if not consumed:
|
||||
raise ProvisioningError("ONE_TIME_GRANT_NOT_CONSUMED", 503)
|
||||
|
||||
scope = {
|
||||
"workspace_role": "task-scoped-isolated-writer",
|
||||
"writes_enabled": True,
|
||||
"allowed_branch": request["target_branch"],
|
||||
"allowed_base_oid": request["base_oid"],
|
||||
"allow_main_write": False,
|
||||
"allow_tag_write": False,
|
||||
"allow_baseline_write": False,
|
||||
"allow_force_push": False,
|
||||
"allowed_routes": ["POST /api/commit-file"],
|
||||
"writer_mode": "direct_one_shot_detached",
|
||||
}
|
||||
negatives = {name: True for name in sorted(REQUIRED_NEGATIVE_TESTS)}
|
||||
return {
|
||||
"branch": request["target_branch"],
|
||||
"branch_oid": request["base_oid"],
|
||||
"base_oid": request["base_oid"],
|
||||
"workspace_path": workspace,
|
||||
"writer_scope": scope,
|
||||
"negative_tests": negatives,
|
||||
"grant_consumed": True,
|
||||
"remote_ref_status": "target_branch_absent_until_writer_push",
|
||||
"remote_oid": None,
|
||||
"detached_writer": True,
|
||||
"writer_config_path": str(writer_config_path),
|
||||
}
|
||||
|
||||
if result.get("branch") != request["target_branch"]:
|
||||
raise ProvisioningError("PROVISIONED_BRANCH_MISMATCH", 503)
|
||||
if result.get("base_oid") != request["base_oid"]:
|
||||
raise ProvisioningError("PROVISIONED_BASE_MISMATCH", 503)
|
||||
if result.get("branch_oid") != request["base_oid"]:
|
||||
raise ProvisioningError("PROVISIONED_BRANCH_OID_MISMATCH", 503)
|
||||
if result.get("grant_consumed") is not True:
|
||||
raise ProvisioningError("ONE_TIME_GRANT_NOT_CONSUMED", 503)
|
||||
workspace = result.get("workspace_path")
|
||||
if not isinstance(workspace, str) or not Path(workspace).is_absolute():
|
||||
raise ProvisioningError("PROVISIONED_WORKSPACE_INVALID", 503)
|
||||
scope = result.get("writer_scope")
|
||||
if not isinstance(scope, dict):
|
||||
raise ProvisioningError("WRITER_SCOPE_ATTESTATION_MISSING", 503)
|
||||
required_scope = {
|
||||
"workspace_role": "task-scoped-isolated-writer",
|
||||
"writes_enabled": True,
|
||||
"allowed_branch": request["target_branch"],
|
||||
"allowed_base_oid": request["base_oid"],
|
||||
"allow_main_write": False,
|
||||
"allow_tag_write": False,
|
||||
"allow_baseline_write": False,
|
||||
"allow_force_push": False,
|
||||
}
|
||||
for key, expected in required_scope.items():
|
||||
if scope.get(key) != expected:
|
||||
raise ProvisioningError("WRITER_SCOPE_ATTESTATION_MISMATCH", 503)
|
||||
routes = scope.get("allowed_routes")
|
||||
if routes != ["POST /api/commit-file"]:
|
||||
raise ProvisioningError("WRITER_ROUTE_ATTESTATION_MISMATCH", 503)
|
||||
negatives = result.get("negative_tests")
|
||||
if not isinstance(negatives, dict) or any(
|
||||
negatives.get(name) is not True for name in REQUIRED_NEGATIVE_TESTS
|
||||
):
|
||||
raise ProvisioningError("NEGATIVE_POLICY_TESTS_FAILED", 503)
|
||||
return {
|
||||
"branch": result["branch"],
|
||||
"branch_oid": result["branch_oid"],
|
||||
"base_oid": result["base_oid"],
|
||||
"workspace_path": workspace,
|
||||
"writer_scope": scope,
|
||||
"negative_tests": {
|
||||
name: True for name in sorted(REQUIRED_NEGATIVE_TESTS)
|
||||
},
|
||||
"grant_consumed": True,
|
||||
"remote_ref_status": result.get("remote_ref_status"),
|
||||
"remote_oid": result.get("remote_oid"),
|
||||
"detached_writer": False,
|
||||
"writer_config_path": None,
|
||||
}
|
||||
|
||||
|
||||
class AuthorizedTaskWriterProvisioner:
|
||||
def __init__(
|
||||
self,
|
||||
config: ProvisioningConfig | None = None,
|
||||
*,
|
||||
clock=utc_now,
|
||||
) -> None:
|
||||
self.config = config or ProvisioningConfig.from_environment()
|
||||
self.clock = clock
|
||||
|
||||
def provision(
|
||||
self,
|
||||
raw_request: Mapping[str, Any],
|
||||
owner: OwnerContext,
|
||||
) -> dict[str, Any]:
|
||||
request = _validate_request(raw_request, owner=owner, config=self.config)
|
||||
_prepare_state_root(self.config.state_root)
|
||||
receipt_id = _safe_receipt_id(
|
||||
request["task_id"], request["repository"], request["target_branch"]
|
||||
)
|
||||
receipt_path = self.config.state_root / "receipts" / f"{receipt_id}.json"
|
||||
lock_path = self.config.state_root / "locks" / f"{receipt_id}.lock"
|
||||
with open(lock_path, "a+b") as lock:
|
||||
os.chmod(lock_path, 0o600)
|
||||
fcntl.flock(lock.fileno(), fcntl.LOCK_EX)
|
||||
return self._provision_locked(request, owner, receipt_path)
|
||||
|
||||
def _provision_locked(
|
||||
self,
|
||||
request: dict[str, Any],
|
||||
owner: OwnerContext,
|
||||
receipt_path: Path,
|
||||
) -> dict[str, Any]:
|
||||
receipt_exists = receipt_path.exists()
|
||||
prestart = _prestart_git_check(
|
||||
request, self.config, receipt_exists=receipt_exists
|
||||
)
|
||||
if receipt_exists:
|
||||
receipt = _read_json(receipt_path)
|
||||
expected_digest = sha256_json(
|
||||
{
|
||||
"task_id": request["task_id"],
|
||||
"repository": request["repository"],
|
||||
"base_ref": request["base_ref"],
|
||||
"base_oid": request["base_oid"],
|
||||
"target_branch": request["target_branch"],
|
||||
"owner_authorization_reference": request[
|
||||
"owner_authorization_reference"
|
||||
],
|
||||
}
|
||||
)
|
||||
if receipt.get("request_identity_sha256") != expected_digest:
|
||||
raise ProvisioningError("IDEMPOTENCY_SCOPE_CONFLICT", 409)
|
||||
return {
|
||||
**receipt["public_result"],
|
||||
"idempotent": True,
|
||||
"prestart": prestart,
|
||||
}
|
||||
|
||||
for path, name in (
|
||||
(self.config.signer, "SIGNER"),
|
||||
(self.config.validator, "VALIDATOR"),
|
||||
(self.config.provisioner, "PROVISIONER"),
|
||||
):
|
||||
_verify_tool_contract(path, name, self.config)
|
||||
|
||||
now = self.clock()
|
||||
plan, grant_request = _build_plan(request, owner, now=now)
|
||||
temporary_root = Path(
|
||||
tempfile.mkdtemp(
|
||||
prefix="grant-",
|
||||
dir=self.config.state_root,
|
||||
)
|
||||
)
|
||||
os.chmod(temporary_root, 0o700)
|
||||
try:
|
||||
grant_dir = temporary_root / "grant"
|
||||
grant_dir.mkdir(mode=0o700)
|
||||
_atomic_write_json(grant_dir / "approval-plan.json", plan)
|
||||
_atomic_write_json(grant_dir / "grant-request.json", grant_request)
|
||||
|
||||
signer_result_path = temporary_root / "signer-result.json"
|
||||
validator_result_path = temporary_root / "validator-result.json"
|
||||
provisioner_result_path = temporary_root / "provisioner-result.json"
|
||||
|
||||
try:
|
||||
run_compatible_signer(
|
||||
_tool_argv(self.config, self.config.signer),
|
||||
grant_dir,
|
||||
signer_result_path,
|
||||
)
|
||||
except Exception as exc:
|
||||
raise ProvisioningError(
|
||||
"SIGNER_COMPATIBILITY_FAILED",
|
||||
503,
|
||||
details={"error": type(exc).__name__},
|
||||
) from exc
|
||||
signer_result = _read_json(signer_result_path)
|
||||
signer = _verify_signer_result(
|
||||
signer_result,
|
||||
approval_plan_id=plan["approval_plan_id"],
|
||||
)
|
||||
|
||||
try:
|
||||
validator_config_path = run_compatible_validator(
|
||||
_tool_argv(self.config, self.config.validator),
|
||||
grant_dir,
|
||||
validator_result_path,
|
||||
)
|
||||
except Exception as exc:
|
||||
raise ProvisioningError(
|
||||
"VALIDATOR_COMPATIBILITY_FAILED",
|
||||
503,
|
||||
details={"error": type(exc).__name__},
|
||||
) from exc
|
||||
validator_result = _read_json(validator_result_path)
|
||||
_verify_validator_result(
|
||||
validator_result,
|
||||
approval_plan_id=plan["approval_plan_id"],
|
||||
grant_digest=signer["grant_digest_sha256"],
|
||||
)
|
||||
|
||||
provisioner_env = dict(os.environ)
|
||||
provisioner_env["AIOS_GRANT_ROOT_CONFIG"] = str(
|
||||
validator_config_path
|
||||
)
|
||||
_run(
|
||||
_tool_argv(
|
||||
self.config,
|
||||
self.config.provisioner,
|
||||
"--grant-dir",
|
||||
str(grant_dir),
|
||||
"--result-json",
|
||||
str(provisioner_result_path),
|
||||
),
|
||||
env=provisioner_env,
|
||||
timeout=180,
|
||||
)
|
||||
provisioner_result = _read_json(provisioner_result_path)
|
||||
provisioned = _verify_provisioner_result(
|
||||
provisioner_result,
|
||||
request,
|
||||
grant_id=signer["grant_id"],
|
||||
validator_config_path=validator_config_path,
|
||||
)
|
||||
|
||||
post_branch_oid = _git(
|
||||
self.config.authority_git_dir,
|
||||
"show-ref",
|
||||
"--verify",
|
||||
"--hash",
|
||||
f"refs/heads/{request['target_branch']}",
|
||||
allowed_returncodes=(0, 1, 128),
|
||||
)
|
||||
if provisioned["detached_writer"]:
|
||||
if post_branch_oid:
|
||||
raise ProvisioningError("POST_PROVISION_TARGET_BRANCH_EXISTS", 503)
|
||||
post_branch_oid = request["base_oid"]
|
||||
elif post_branch_oid != request["base_oid"]:
|
||||
raise ProvisioningError("POST_PROVISION_BRANCH_OID_MISMATCH", 503)
|
||||
post_main_oid = _git(
|
||||
self.config.authority_git_dir,
|
||||
"rev-parse",
|
||||
request["base_ref"],
|
||||
)
|
||||
if post_main_oid != request["base_oid"]:
|
||||
raise ProvisioningError("POST_PROVISION_MAIN_DRIFT", 409)
|
||||
|
||||
public_result = {
|
||||
"status": "READY_FOR_CODE_AUTHORING",
|
||||
"task_id": request["task_id"],
|
||||
"repository": request["repository"],
|
||||
"approval_plan_id": plan["approval_plan_id"],
|
||||
"grant_id": signer["grant_id"],
|
||||
"grant_digest_sha256": signer["grant_digest_sha256"],
|
||||
"signing_key_identity": signer["signing_key_identity"],
|
||||
"branch": provisioned["branch"],
|
||||
"branch_oid": provisioned["branch_oid"],
|
||||
"base_oid": request["base_oid"],
|
||||
"workspace_path": provisioned["workspace_path"],
|
||||
"writer_scope": provisioned["writer_scope"],
|
||||
"negative_tests": provisioned["negative_tests"],
|
||||
"grant_consumed": True,
|
||||
"main_unchanged": True,
|
||||
"production_change_authorized": False,
|
||||
"tag_change_authorized": False,
|
||||
"baseline_change_authorized": False,
|
||||
"idempotent": False,
|
||||
}
|
||||
request_identity = sha256_json(
|
||||
{
|
||||
"task_id": request["task_id"],
|
||||
"repository": request["repository"],
|
||||
"base_ref": request["base_ref"],
|
||||
"base_oid": request["base_oid"],
|
||||
"target_branch": request["target_branch"],
|
||||
"owner_authorization_reference": request[
|
||||
"owner_authorization_reference"
|
||||
],
|
||||
}
|
||||
)
|
||||
receipt = {
|
||||
"schema": "aios.task-scoped-writer-provisioning-receipt.v1",
|
||||
"request_identity_sha256": request_identity,
|
||||
"created_at": iso_utc(self.clock()),
|
||||
"public_result": _redacted(public_result),
|
||||
"prestart": prestart,
|
||||
"tool_evidence": {
|
||||
"signer": {
|
||||
"status": signer_result.get("status"),
|
||||
"grant_digest_sha256": signer["grant_digest_sha256"],
|
||||
"signing_key_identity": signer["signing_key_identity"],
|
||||
},
|
||||
"validator": {
|
||||
"status": validator_result.get("status"),
|
||||
"checks": validator_result.get("checks"),
|
||||
},
|
||||
"provisioner": {
|
||||
"status": provisioner_result.get("status"),
|
||||
"grant_consumed": provisioner_result.get("grant_consumed"),
|
||||
},
|
||||
},
|
||||
}
|
||||
_atomic_write_json(receipt_path, receipt)
|
||||
return {**public_result, "prestart": prestart}
|
||||
finally:
|
||||
shutil.rmtree(temporary_root, ignore_errors=True)
|
||||
@@ -0,0 +1,89 @@
|
||||
"""Durable Owner/GPT notification outbox with retry and acknowledgement."""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import sqlite3
|
||||
import time
|
||||
import uuid
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Mapping
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OutboxEvent:
|
||||
event_id: str
|
||||
recipient: str
|
||||
kind: str
|
||||
payload: Mapping[str, Any]
|
||||
attempts: int
|
||||
available_at: float
|
||||
acknowledged: bool
|
||||
|
||||
|
||||
class DurableOutbox:
|
||||
RECIPIENTS = ("owner", "gpt")
|
||||
|
||||
def __init__(self, path: str | Path) -> None:
|
||||
self.path = str(path)
|
||||
self.db = sqlite3.connect(self.path)
|
||||
self.db.execute("PRAGMA journal_mode=WAL")
|
||||
self.db.execute("CREATE TABLE IF NOT EXISTS outbox (event_id TEXT PRIMARY KEY, recipient TEXT NOT NULL, kind TEXT NOT NULL, payload TEXT NOT NULL, attempts INTEGER NOT NULL DEFAULT 0, available_at REAL NOT NULL, delivered_at REAL, acknowledged INTEGER NOT NULL DEFAULT 0, last_error TEXT)")
|
||||
self.db.commit()
|
||||
|
||||
def enqueue(self, kind: str, payload: Mapping[str, Any], *, event_id: str | None = None, recipients: tuple[str, ...] = RECIPIENTS) -> list[str]:
|
||||
ids: list[str] = []
|
||||
for recipient in recipients:
|
||||
if recipient not in self.RECIPIENTS:
|
||||
raise ValueError("recipient is outside the governed notification plane")
|
||||
eid = event_id or str(uuid.uuid4())
|
||||
if event_id is not None and len(recipients) > 1:
|
||||
eid = f"{event_id}:{recipient}"
|
||||
self.db.execute("INSERT OR IGNORE INTO outbox(event_id,recipient,kind,payload,available_at) VALUES(?,?,?,?,?)", (eid, recipient, kind, json.dumps(dict(payload), sort_keys=True), time.time()))
|
||||
ids.append(eid)
|
||||
self.db.commit()
|
||||
return ids
|
||||
|
||||
def due(self, *, now: float | None = None, limit: int = 20) -> list[OutboxEvent]:
|
||||
now = time.time() if now is None else now
|
||||
rows = self.db.execute("SELECT event_id,recipient,kind,payload,attempts,available_at,acknowledged FROM outbox WHERE delivered_at IS NULL AND available_at<=? ORDER BY available_at,event_id LIMIT ?", (now, limit)).fetchall()
|
||||
return [OutboxEvent(r[0], r[1], r[2], json.loads(r[3]), r[4], r[5], bool(r[6])) for r in rows]
|
||||
|
||||
def delivered(self, event_id: str, *, now: float | None = None) -> None:
|
||||
self.db.execute("UPDATE outbox SET delivered_at=? WHERE event_id=?", (time.time() if now is None else now, event_id))
|
||||
self.db.commit()
|
||||
|
||||
def failed(self, event_id: str, error: str, *, now: float | None = None, max_backoff: float = 300.0) -> None:
|
||||
now = time.time() if now is None else now
|
||||
row = self.db.execute("SELECT attempts FROM outbox WHERE event_id=?", (event_id,)).fetchone()
|
||||
attempts = int(row[0]) + 1 if row else 1
|
||||
delay = min(max_backoff, 2 ** min(attempts, 8))
|
||||
self.db.execute("UPDATE outbox SET attempts=?,available_at=?,last_error=? WHERE event_id=?", (attempts, now + delay, error[:200], event_id))
|
||||
self.db.commit()
|
||||
|
||||
def acknowledge(self, event_id: str) -> None:
|
||||
self.db.execute("UPDATE outbox SET acknowledged=1 WHERE event_id=?", (event_id,))
|
||||
self.db.commit()
|
||||
|
||||
def close(self) -> None:
|
||||
self.db.close()
|
||||
|
||||
|
||||
class NotificationPlane:
|
||||
def __init__(self, outbox: DurableOutbox) -> None:
|
||||
self.outbox = outbox
|
||||
|
||||
def emit(self, kind: str, payload: Mapping[str, Any], *, event_id: str | None = None) -> list[str]:
|
||||
return self.outbox.enqueue(kind, payload, event_id=event_id)
|
||||
|
||||
def deliver_once(self, send: Callable[[OutboxEvent], None], *, now: float | None = None) -> list[str]:
|
||||
delivered: list[str] = []
|
||||
for event in self.outbox.due(now=now):
|
||||
try:
|
||||
send(event)
|
||||
except Exception as exc:
|
||||
self.outbox.failed(event.event_id, type(exc).__name__, now=now)
|
||||
else:
|
||||
self.outbox.delivered(event.event_id, now=now)
|
||||
delivered.append(event.event_id)
|
||||
return delivered
|
||||
@@ -0,0 +1,491 @@
|
||||
"""Fail-closed, branch-bound repair leases for governed AIOS GitOps work."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import posixpath
|
||||
import re
|
||||
import secrets
|
||||
import subprocess
|
||||
import tempfile
|
||||
import uuid
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Iterable, Mapping, Protocol, Sequence
|
||||
|
||||
|
||||
TASK_ID = "V2R1C6_GOVERNED_LOCAL_BOOTSTRAP"
|
||||
MAX_LEASE_SECONDS = 86_400
|
||||
OID_RE = re.compile(r"^[0-9a-fA-F]{40}$")
|
||||
DENIED_BRANCHES = {"main", "master", "HEAD"}
|
||||
PROTECTED_PREFIXES = (
|
||||
".git",
|
||||
"VERSION",
|
||||
"versions/V2R1C5.json",
|
||||
"artifacts/V2R1C5",
|
||||
"baseline",
|
||||
"config/gitops.tokens",
|
||||
"gitops.tokens",
|
||||
"secrets",
|
||||
"credentials",
|
||||
)
|
||||
SECRET_PATTERNS = (
|
||||
re.compile(r"(?i)-----BEGIN [A-Z ]*PRIVATE KEY-----"),
|
||||
re.compile(r"(?i)(?:api[_-]?key|secret|password|token)\s*[:=]\s*\S+"),
|
||||
re.compile(r"\b(?:sk|HPUA|SDC)-[A-Za-z0-9_-]{16,}\b"),
|
||||
)
|
||||
|
||||
|
||||
class LeaseError(Exception):
|
||||
"""Raised for any invalid, stale, expired, or prohibited lease action."""
|
||||
|
||||
|
||||
class GitProbeProtocol(Protocol):
|
||||
"""Read-only Git seam used by the lease manager."""
|
||||
|
||||
def branch_head(self, branch: str) -> str: ...
|
||||
|
||||
def parent(self, commit: str) -> str: ...
|
||||
|
||||
def is_ancestor(self, older: str, newer: str) -> bool: ...
|
||||
|
||||
def changed_paths(self, commit: str) -> tuple[str, ...]: ...
|
||||
|
||||
def commits_between(self, older: str, newer: str) -> tuple[str, ...]: ...
|
||||
|
||||
|
||||
def _now() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
|
||||
def _ts(value: datetime) -> str:
|
||||
return value.astimezone(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def _parse_ts(value: str) -> datetime:
|
||||
if value.endswith("Z"):
|
||||
value = value[:-1] + "+00:00"
|
||||
parsed = datetime.fromisoformat(value)
|
||||
return parsed if parsed.tzinfo else parsed.replace(tzinfo=timezone.utc)
|
||||
|
||||
|
||||
def _oid(value: str, field: str = "oid") -> str:
|
||||
if not isinstance(value, str) or not OID_RE.fullmatch(value):
|
||||
raise LeaseError(f"{field} must be a full commit OID")
|
||||
return value.lower()
|
||||
|
||||
|
||||
def normalize_path(path: str) -> str:
|
||||
"""Normalize a repository-relative path without resolving through the FS."""
|
||||
if not isinstance(path, str) or not path.strip():
|
||||
raise LeaseError("path must be a non-empty string")
|
||||
value = path.replace("\\", "/").strip()
|
||||
if value.startswith("/") or "\x00" in value:
|
||||
raise LeaseError("path must be relative")
|
||||
parts = value.split("/")
|
||||
if any(part in {"", ".", ".."} for part in parts):
|
||||
raise LeaseError("path contains a prohibited component")
|
||||
normalized = posixpath.normpath(value)
|
||||
if normalized == "." or normalized.startswith("../"):
|
||||
raise LeaseError("path is not normalized")
|
||||
return normalized
|
||||
|
||||
|
||||
def path_is_protected(path: str) -> bool:
|
||||
normalized = normalize_path(path)
|
||||
lower = normalized.lower()
|
||||
return any(
|
||||
lower == prefix.lower() or lower.startswith(prefix.lower().rstrip("/") + "/")
|
||||
for prefix in PROTECTED_PREFIXES
|
||||
) or lower.startswith("refs/")
|
||||
|
||||
|
||||
def contains_secret_like_content(content: str) -> bool:
|
||||
return any(pattern.search(content or "") for pattern in SECRET_PATTERNS)
|
||||
|
||||
|
||||
def validate_paths(paths: Iterable[str], allowed_paths: Sequence[str]) -> tuple[str, ...]:
|
||||
allowed = tuple(normalize_path(path) for path in allowed_paths)
|
||||
if not allowed:
|
||||
raise LeaseError("allowed_paths must not be empty")
|
||||
result: list[str] = []
|
||||
for raw in paths:
|
||||
path = normalize_path(raw)
|
||||
if path_is_protected(path):
|
||||
raise LeaseError("protected path is not lease-writable")
|
||||
if not any(path == prefix or path.startswith(prefix + "/") for prefix in allowed):
|
||||
raise LeaseError("path is outside the lease allowlist")
|
||||
if path not in result:
|
||||
result.append(path)
|
||||
if not result:
|
||||
raise LeaseError("at least one changed path is required")
|
||||
return tuple(result)
|
||||
|
||||
|
||||
@dataclass
|
||||
class CommitEntry:
|
||||
commit_oid: str
|
||||
parent_oid: str
|
||||
paths: tuple[str, ...]
|
||||
recorded_at: str
|
||||
|
||||
|
||||
@dataclass
|
||||
class RepairLease:
|
||||
lease_id: str
|
||||
task_id: str
|
||||
owner_identity: str
|
||||
branch: str
|
||||
description: str
|
||||
allowed_paths: tuple[str, ...]
|
||||
initial_head_oid: str
|
||||
current_head_oid: str
|
||||
created_at: str
|
||||
expires_at: str
|
||||
max_expires_at: str
|
||||
state: str = "ACTIVE"
|
||||
revision: int = 0
|
||||
commits: list[CommitEntry] = field(default_factory=list)
|
||||
attached: bool = False
|
||||
|
||||
def to_json(self) -> dict[str, Any]:
|
||||
payload = asdict(self)
|
||||
payload["allowed_paths"] = list(self.allowed_paths)
|
||||
payload["commits"] = [asdict(entry) for entry in self.commits]
|
||||
return payload
|
||||
|
||||
@classmethod
|
||||
def from_json(cls, raw: dict[str, Any]) -> "RepairLease":
|
||||
commits = tuple(
|
||||
CommitEntry(
|
||||
commit_oid=_oid(item["commit_oid"], "commit_oid"),
|
||||
parent_oid=_oid(item["parent_oid"], "parent_oid"),
|
||||
paths=tuple(normalize_path(path) for path in item["paths"]),
|
||||
recorded_at=str(item["recorded_at"]),
|
||||
)
|
||||
for item in raw.get("commits", [])
|
||||
)
|
||||
return cls(
|
||||
lease_id=str(raw["lease_id"]),
|
||||
task_id=str(raw["task_id"]),
|
||||
owner_identity=str(raw["owner_identity"]),
|
||||
branch=str(raw["branch"]),
|
||||
description=str(raw["description"]),
|
||||
allowed_paths=tuple(normalize_path(path) for path in raw["allowed_paths"]),
|
||||
initial_head_oid=_oid(raw["initial_head_oid"], "initial_head_oid"),
|
||||
current_head_oid=_oid(raw["current_head_oid"], "current_head_oid"),
|
||||
created_at=str(raw["created_at"]),
|
||||
expires_at=str(raw["expires_at"]),
|
||||
max_expires_at=str(raw["max_expires_at"]),
|
||||
state=str(raw.get("state", "ACTIVE")),
|
||||
revision=int(raw.get("revision", 0)),
|
||||
commits=list(commits),
|
||||
attached=bool(raw.get("attached", False)),
|
||||
)
|
||||
|
||||
|
||||
class LeaseStore:
|
||||
"""Atomic JSON store for restart-recoverable lease state."""
|
||||
|
||||
def __init__(self, directory: str | os.PathLike[str]) -> None:
|
||||
self.directory = Path(directory)
|
||||
self.directory.mkdir(parents=True, exist_ok=True)
|
||||
if self.directory.is_symlink():
|
||||
raise LeaseError("lease store must not be a symlink")
|
||||
os.chmod(self.directory, 0o700)
|
||||
|
||||
def _path(self, lease_id: str) -> Path:
|
||||
if not re.fullmatch(r"lease-[0-9a-f]{32}", lease_id):
|
||||
raise LeaseError("invalid lease id")
|
||||
return self.directory / f"{lease_id}.json"
|
||||
|
||||
def create(self, lease: RepairLease) -> None:
|
||||
path = self._path(lease.lease_id)
|
||||
if path.exists() or path.is_symlink():
|
||||
raise LeaseError("lease already exists")
|
||||
self._write(path, lease.to_json(), exclusive=True)
|
||||
|
||||
def load(self, lease_id: str) -> RepairLease:
|
||||
path = self._path(lease_id)
|
||||
try:
|
||||
raw = json.loads(path.read_text(encoding="utf-8"))
|
||||
except (OSError, json.JSONDecodeError, TypeError) as exc:
|
||||
raise LeaseError("lease state is unavailable or invalid") from exc
|
||||
if not isinstance(raw, dict):
|
||||
raise LeaseError("lease state must be an object")
|
||||
return RepairLease.from_json(raw)
|
||||
|
||||
def save(self, lease: RepairLease) -> None:
|
||||
self._write(self._path(lease.lease_id), lease.to_json())
|
||||
|
||||
@staticmethod
|
||||
def _write(path: Path, payload: dict[str, Any], *, exclusive: bool = False) -> None:
|
||||
flags = os.O_WRONLY | os.O_CREAT | (os.O_EXCL if exclusive else 0)
|
||||
fd, temp_name = tempfile.mkstemp(prefix=".lease-", dir=path.parent)
|
||||
try:
|
||||
os.fchmod(fd, 0o600)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as stream:
|
||||
json.dump(payload, stream, ensure_ascii=True, sort_keys=True, separators=(",", ":"))
|
||||
stream.write("\n")
|
||||
if exclusive:
|
||||
os.link(temp_name, path)
|
||||
os.unlink(temp_name)
|
||||
else:
|
||||
os.replace(temp_name, path)
|
||||
os.chmod(path, 0o600)
|
||||
except Exception:
|
||||
try:
|
||||
os.unlink(temp_name)
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
raise
|
||||
|
||||
|
||||
class GitProbe:
|
||||
"""Read-only Git implementation; it never changes a ref or working tree."""
|
||||
|
||||
def __init__(self, bare_repo: str | os.PathLike[str]) -> None:
|
||||
self.bare_repo = Path(bare_repo)
|
||||
|
||||
def _run(self, args: list[str]) -> str:
|
||||
result = subprocess.run(
|
||||
["git", "--git-dir", str(self.bare_repo), *args],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
raise LeaseError("read-only Git probe failed")
|
||||
return result.stdout.strip()
|
||||
|
||||
def branch_head(self, branch: str) -> str:
|
||||
return _oid(self._run(["rev-parse", f"refs/heads/{branch}"]), "branch_head")
|
||||
|
||||
def parent(self, commit: str) -> str:
|
||||
return _oid(self._run(["rev-parse", f"{_oid(commit)}^1"]), "parent")
|
||||
|
||||
def is_ancestor(self, older: str, newer: str) -> bool:
|
||||
old, new = _oid(older), _oid(newer)
|
||||
result = subprocess.run(
|
||||
["git", "--git-dir", str(self.bare_repo), "merge-base", "--is-ancestor", old, new],
|
||||
check=False,
|
||||
)
|
||||
return result.returncode == 0
|
||||
|
||||
def changed_paths(self, commit: str) -> tuple[str, ...]:
|
||||
raw = self._run(["diff-tree", "--no-commit-id", "--name-only", "-r", _oid(commit)])
|
||||
return tuple(normalize_path(line) for line in raw.splitlines() if line.strip())
|
||||
|
||||
def commits_between(self, older: str, newer: str) -> tuple[str, ...]:
|
||||
raw = self._run(["rev-list", "--reverse", f"{_oid(older)}..{_oid(newer)}"])
|
||||
return tuple(_oid(line, "commit") for line in raw.splitlines() if line.strip())
|
||||
|
||||
|
||||
class RepairLeaseManager:
|
||||
"""Issue, recover, renew, and close branch-bound repair leases."""
|
||||
|
||||
def __init__(self, store: LeaseStore, git: GitProbeProtocol, *, clock=_now) -> None:
|
||||
self.store = store
|
||||
self.git = git
|
||||
self.clock = clock
|
||||
|
||||
def _require_owner(self, lease: RepairLease, owner_identity: str) -> None:
|
||||
if owner_identity != lease.owner_identity:
|
||||
raise LeaseError("lease identity mismatch")
|
||||
|
||||
def _active(self, lease: RepairLease) -> RepairLease:
|
||||
now = self.clock()
|
||||
if lease.state != "ACTIVE":
|
||||
raise LeaseError(f"lease is {lease.state.lower()}")
|
||||
if now >= _parse_ts(lease.expires_at):
|
||||
lease.state = "EXPIRED"
|
||||
self.store.save(lease)
|
||||
raise LeaseError("lease expired")
|
||||
return lease
|
||||
|
||||
def issue(
|
||||
self,
|
||||
*,
|
||||
task_id: str,
|
||||
owner_identity: str,
|
||||
branch: str,
|
||||
description: str,
|
||||
allowed_paths: Sequence[str],
|
||||
ttl_seconds: int = 3600,
|
||||
) -> RepairLease:
|
||||
if task_id != TASK_ID:
|
||||
raise LeaseError("unexpected task id")
|
||||
if not owner_identity or not description or len(description) > 240:
|
||||
raise LeaseError("owner identity and description are required")
|
||||
if "\n" in description or "\r" in description:
|
||||
raise LeaseError("description must be a single line")
|
||||
if branch in DENIED_BRANCHES or branch.startswith(("main/", "refs/", "tags/")):
|
||||
raise LeaseError("protected branch cannot receive a repair lease")
|
||||
if not isinstance(ttl_seconds, int) or not 0 < ttl_seconds <= MAX_LEASE_SECONDS:
|
||||
raise LeaseError("lease TTL exceeds the maximum")
|
||||
allowed = tuple(normalize_path(path) for path in allowed_paths)
|
||||
if any(path_is_protected(path) for path in allowed):
|
||||
raise LeaseError("protected path in lease allowlist")
|
||||
head = self.git.branch_head(branch)
|
||||
created = self.clock()
|
||||
expires = created + timedelta(seconds=ttl_seconds)
|
||||
max_expires = created + timedelta(seconds=MAX_LEASE_SECONDS)
|
||||
lease_id = "lease-" + secrets.token_hex(16)
|
||||
lease = RepairLease(
|
||||
lease_id=lease_id,
|
||||
task_id=task_id,
|
||||
owner_identity=owner_identity,
|
||||
branch=branch,
|
||||
description=description,
|
||||
allowed_paths=allowed,
|
||||
initial_head_oid=head,
|
||||
current_head_oid=head,
|
||||
created_at=_ts(created),
|
||||
expires_at=_ts(expires),
|
||||
max_expires_at=_ts(max_expires),
|
||||
)
|
||||
self.store.create(lease)
|
||||
return lease
|
||||
|
||||
def attach_existing_branch(
|
||||
self, lease_id: str, *, owner_identity: str, expected_head_oid: str
|
||||
) -> RepairLease:
|
||||
lease = self._active(self.store.load(lease_id))
|
||||
self._require_owner(lease, owner_identity)
|
||||
current = self.git.branch_head(lease.branch)
|
||||
expected = _oid(expected_head_oid, "expected_head_oid")
|
||||
if current != expected or current != lease.current_head_oid:
|
||||
raise LeaseError("branch head does not match the lease")
|
||||
lease.attached = True
|
||||
lease.revision += 1
|
||||
self.store.save(lease)
|
||||
return lease
|
||||
|
||||
def authorize_commit(
|
||||
self,
|
||||
lease_id: str,
|
||||
*,
|
||||
owner_identity: str,
|
||||
expected_head_oid: str,
|
||||
paths: Sequence[str],
|
||||
content: Mapping[str, str] | None = None,
|
||||
) -> RepairLease:
|
||||
lease = self._active(self.store.load(lease_id))
|
||||
self._require_owner(lease, owner_identity)
|
||||
expected = _oid(expected_head_oid, "expected_head_oid")
|
||||
current = self.git.branch_head(lease.branch)
|
||||
if current != expected or current != lease.current_head_oid:
|
||||
raise LeaseError("stale or externally advanced branch head")
|
||||
if not lease.attached:
|
||||
raise LeaseError("lease is not attached")
|
||||
validate_paths(paths, lease.allowed_paths)
|
||||
if content and any(contains_secret_like_content(value) for value in content.values()):
|
||||
raise LeaseError("secret-like content rejected")
|
||||
return lease
|
||||
|
||||
def record_commit(
|
||||
self,
|
||||
lease_id: str,
|
||||
*,
|
||||
owner_identity: str,
|
||||
expected_head_oid: str,
|
||||
new_head_oid: str,
|
||||
paths: Sequence[str],
|
||||
) -> RepairLease:
|
||||
lease = self._active(self.store.load(lease_id))
|
||||
self._require_owner(lease, owner_identity)
|
||||
new_head = _oid(new_head_oid, "new_head_oid")
|
||||
expected = _oid(expected_head_oid, "expected_head_oid")
|
||||
if not lease.attached or lease.current_head_oid != expected:
|
||||
raise LeaseError("stale lease head")
|
||||
if self.git.branch_head(lease.branch) != new_head:
|
||||
raise LeaseError("branch head does not match committed head")
|
||||
validate_paths(paths, lease.allowed_paths)
|
||||
if self.git.parent(new_head) != expected or not self.git.is_ancestor(expected, new_head):
|
||||
raise LeaseError("commit is not a fast-forward child of the expected head")
|
||||
actual_paths = self.git.changed_paths(new_head)
|
||||
allowed = validate_paths(actual_paths, lease.allowed_paths)
|
||||
requested = set(validate_paths(paths, lease.allowed_paths))
|
||||
if not set(allowed).issubset(requested):
|
||||
raise LeaseError("commit changed an unrequested path")
|
||||
lease.current_head_oid = new_head
|
||||
lease.revision += 1
|
||||
lease.commits.append(
|
||||
CommitEntry(
|
||||
commit_oid=new_head,
|
||||
parent_oid=expected,
|
||||
paths=allowed,
|
||||
recorded_at=_ts(self.clock()),
|
||||
)
|
||||
)
|
||||
self.store.save(lease)
|
||||
return lease
|
||||
|
||||
def recover(self, lease_id: str, *, owner_identity: str) -> RepairLease:
|
||||
lease = self._active(self.store.load(lease_id))
|
||||
self._require_owner(lease, owner_identity)
|
||||
current = self.git.branch_head(lease.branch)
|
||||
if current == lease.current_head_oid:
|
||||
return lease
|
||||
if not self.git.is_ancestor(lease.current_head_oid, current):
|
||||
raise LeaseError("branch moved non-fast-forward")
|
||||
commits = self.git.commits_between(lease.current_head_oid, current)
|
||||
for commit in commits:
|
||||
actual = self.git.changed_paths(commit)
|
||||
validate_paths(actual, lease.allowed_paths)
|
||||
lease.current_head_oid = current
|
||||
lease.revision += 1
|
||||
self.store.save(lease)
|
||||
return lease
|
||||
|
||||
def renew(self, lease_id: str, *, owner_identity: str, ttl_seconds: int) -> RepairLease:
|
||||
lease = self._active(self.store.load(lease_id))
|
||||
self._require_owner(lease, owner_identity)
|
||||
if not isinstance(ttl_seconds, int) or ttl_seconds <= 0:
|
||||
raise LeaseError("renewal TTL must be positive")
|
||||
candidate = self.clock() + timedelta(seconds=ttl_seconds)
|
||||
maximum = _parse_ts(lease.max_expires_at)
|
||||
if candidate > maximum:
|
||||
raise LeaseError("renewal exceeds maximum lease lifetime")
|
||||
lease.expires_at = _ts(candidate)
|
||||
lease.revision += 1
|
||||
self.store.save(lease)
|
||||
return lease
|
||||
|
||||
def complete(self, lease_id: str, *, owner_identity: str) -> RepairLease:
|
||||
lease = self._active(self.store.load(lease_id))
|
||||
self._require_owner(lease, owner_identity)
|
||||
lease.state = "COMPLETED"
|
||||
lease.revision += 1
|
||||
self.store.save(lease)
|
||||
return lease
|
||||
|
||||
def revoke(self, lease_id: str, *, owner_identity: str) -> RepairLease:
|
||||
lease = self._active(self.store.load(lease_id))
|
||||
self._require_owner(lease, owner_identity)
|
||||
lease.state = "REVOKED"
|
||||
lease.revision += 1
|
||||
self.store.save(lease)
|
||||
return lease
|
||||
|
||||
|
||||
def sanitized_lease_view(lease: RepairLease) -> dict[str, Any]:
|
||||
"""Return lease metadata only; no content, token, or credential values."""
|
||||
return {
|
||||
"lease_id": lease.lease_id,
|
||||
"task_id": lease.task_id,
|
||||
"owner_identity": lease.owner_identity,
|
||||
"branch": lease.branch,
|
||||
"description": lease.description,
|
||||
"initial_head_oid": lease.initial_head_oid,
|
||||
"current_head_oid": lease.current_head_oid,
|
||||
"created_at": lease.created_at,
|
||||
"expires_at": lease.expires_at,
|
||||
"state": lease.state,
|
||||
"revision": lease.revision,
|
||||
"commit_count": len(lease.commits),
|
||||
"attached": lease.attached,
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,473 @@
|
||||
"""Shared primitives for the V2R1C6 governed local writer contract."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import posixpath
|
||||
import re
|
||||
import socket
|
||||
import stat
|
||||
import struct
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
|
||||
TASK_ID = "V2R1C6_GOVERNED_LOCAL_BOOTSTRAP"
|
||||
REPO = "aios/aios"
|
||||
PRINCIPAL = "governed-local-bootstrap"
|
||||
OIDSIZ = 40
|
||||
AUTHORIZATION_TTL = timedelta(hours=2)
|
||||
|
||||
|
||||
class GovernedLocalWriterError(Exception):
|
||||
"""Base error for governed-local-writer validation and runtime failures."""
|
||||
|
||||
|
||||
class AuthorizationError(GovernedLocalWriterError):
|
||||
"""Raised when authorization input is invalid, expired, or tampered."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BranchCreatePolicy:
|
||||
"""Exact branch creation contract."""
|
||||
|
||||
branch: str
|
||||
base_oid: str
|
||||
head_oid: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BranchAppendPolicy:
|
||||
"""Exact append-commit contract for candidate branch updates."""
|
||||
|
||||
branch: str
|
||||
expected_head_oid: str | None
|
||||
allowed_paths: tuple[str, ...]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BranchPolicy:
|
||||
"""Per-branch operation policies loaded from authorization."""
|
||||
|
||||
create_branch: BranchCreatePolicy | None
|
||||
append_commit: BranchAppendPolicy | None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GovernedAuthorization:
|
||||
"""Parsed and validated authorization object."""
|
||||
|
||||
task_id: str
|
||||
repo: str
|
||||
created_at: datetime
|
||||
expires_at: datetime
|
||||
authorization_sha256: str
|
||||
one_time_use: bool
|
||||
branch_operations: dict[str, BranchPolicy]
|
||||
denied_operations: tuple[str, ...]
|
||||
|
||||
@property
|
||||
def create_branches(self) -> set[str]:
|
||||
"""Branches that are allowed for branch-creation operations."""
|
||||
return {
|
||||
branch
|
||||
for branch, policy in self.branch_operations.items()
|
||||
if policy.create_branch is not None
|
||||
}
|
||||
|
||||
@property
|
||||
def append_branches(self) -> set[str]:
|
||||
"""Branches that are allowed for commit-append operations."""
|
||||
return {
|
||||
branch
|
||||
for branch, policy in self.branch_operations.items()
|
||||
if policy.append_commit is not None
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class PeerIdentity:
|
||||
"""Verified peer identity from SO_PEERCRED."""
|
||||
|
||||
pid: int
|
||||
uid: int
|
||||
gid: int
|
||||
executable: str | None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class FileChange:
|
||||
"""Single file modification payload."""
|
||||
|
||||
path: str
|
||||
content: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CreateBranchRequest:
|
||||
"""Validated create-branch request payload."""
|
||||
|
||||
branch: str
|
||||
base_oid: str
|
||||
head_oid: str | None
|
||||
authorization_digest: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AppendCommitRequest:
|
||||
"""Validated append-commit request payload."""
|
||||
|
||||
branch: str
|
||||
expected_head_oid: str
|
||||
changes: tuple[FileChange, ...]
|
||||
authorization_digest: str
|
||||
commit_message: str = "chore(governance): append governed commit"
|
||||
|
||||
|
||||
_OID_RE = re.compile(r"^[0-9a-fA-F]{40}$")
|
||||
_DENIED_PATH_SEGMENTS = (
|
||||
"main",
|
||||
"tag",
|
||||
"baseline",
|
||||
"credential",
|
||||
"credentials",
|
||||
"secret",
|
||||
"registry",
|
||||
)
|
||||
_SECRET_PATTERNS = (
|
||||
re.compile(r"(?i)-----BEGIN [A-Z ]*PRIVATE KEY-----"),
|
||||
re.compile(r"(?i)api[_-]?key\s*[:=]\s*\S+"),
|
||||
re.compile(r"(?i)secret\s*[:=]\s*\S+"),
|
||||
re.compile(r"(?i)password\s*[:=]\s*\S+"),
|
||||
re.compile(r"(?i)token\s*[:=]\s*\S+"),
|
||||
)
|
||||
_SAFE_SECRET_MARKERS = re.compile(
|
||||
r"(?i)(?:api[_-]?key|secret|password|token)\s*[:=]\s*(?:REDACTED|TEST_FIXTURE|NOT_A_SECRET)"
|
||||
)
|
||||
|
||||
|
||||
def canonicalize_authorization_payload(payload: Mapping[str, Any]) -> str:
|
||||
"""Serialize authorization payload without the signature hash, in canonical form."""
|
||||
canonical = dict(payload)
|
||||
canonical.pop("authorization_sha256", None)
|
||||
return json.dumps(
|
||||
canonical, sort_keys=True, separators=(",", ":"), ensure_ascii=True
|
||||
)
|
||||
|
||||
|
||||
def compute_authorization_sha256(payload: Mapping[str, Any]) -> str:
|
||||
"""Compute canonical sha256 over authorization payload."""
|
||||
digest = hashlib.sha256()
|
||||
digest.update(canonicalize_authorization_payload(payload).encode("utf-8"))
|
||||
return digest.hexdigest()
|
||||
|
||||
|
||||
def _assert_authorization_file_permissions(path: Path) -> None:
|
||||
"""Fail-closed checks for root-only secret-like authorization files."""
|
||||
if path.is_symlink():
|
||||
raise AuthorizationError("authorization path must not be a symlink")
|
||||
|
||||
st = path.stat()
|
||||
if not stat.S_ISREG(st.st_mode):
|
||||
raise AuthorizationError("authorization path must be a regular file")
|
||||
|
||||
if (st.st_mode & 0o777) != 0o600:
|
||||
raise AuthorizationError("authorization file mode must be exactly 0600")
|
||||
|
||||
if hasattr(st, "st_uid") and os.name != "nt" and st.st_uid != 0:
|
||||
raise AuthorizationError("authorization file owner must be uid 0")
|
||||
|
||||
|
||||
def _parse_iso8601(value: str) -> datetime:
|
||||
"""Parse ISO 8601 timestamps used by authorization payloads."""
|
||||
try:
|
||||
if value.endswith("Z"):
|
||||
value = value[:-1] + "+00:00"
|
||||
parsed = datetime.fromisoformat(value)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise AuthorizationError("created_at must be an ISO 8601 timestamp") from exc
|
||||
|
||||
if parsed.tzinfo is None:
|
||||
parsed = parsed.replace(tzinfo=timezone.utc)
|
||||
return parsed
|
||||
|
||||
|
||||
def _require_type(value: Any, expected: type, *, key: str) -> None:
|
||||
if not isinstance(value, expected):
|
||||
raise AuthorizationError(f"{key} must be {expected.__name__}")
|
||||
|
||||
|
||||
def _parse_oid(value: Any, *, field: str) -> str:
|
||||
if not isinstance(value, str):
|
||||
raise AuthorizationError(f"{field} must be a string")
|
||||
if not _OID_RE.fullmatch(value):
|
||||
raise AuthorizationError(f"{field} must be a 40-char hex object id")
|
||||
return value.lower()
|
||||
|
||||
|
||||
def _parse_allowed_paths(paths: Any) -> tuple[str, ...]:
|
||||
if not isinstance(paths, list) or not paths:
|
||||
raise AuthorizationError("allowed_paths must be a non-empty list")
|
||||
normalized: list[str] = []
|
||||
for path in paths:
|
||||
if not isinstance(path, str) or not path.strip():
|
||||
raise AuthorizationError("allowed_paths entries must be non-empty strings")
|
||||
normalized.append(path.strip())
|
||||
return tuple(normalized)
|
||||
|
||||
|
||||
def parse_authorization(
|
||||
raw: Mapping[str, Any], *, now: datetime | None = None
|
||||
) -> GovernedAuthorization:
|
||||
"""Validate an authorization payload and return a typed object."""
|
||||
_require_type(raw.get("task_id"), str, key="task_id")
|
||||
if raw["task_id"] != TASK_ID:
|
||||
raise AuthorizationError("unexpected task_id")
|
||||
|
||||
_require_type(raw.get("repo"), str, key="repo")
|
||||
if raw["repo"] != REPO:
|
||||
raise AuthorizationError("unexpected repo value")
|
||||
|
||||
created_at = _parse_iso8601(raw.get("created_at"))
|
||||
check_time = now or datetime.now(tz=timezone.utc)
|
||||
if created_at.tzinfo is None:
|
||||
created_at = created_at.replace(tzinfo=timezone.utc)
|
||||
if created_at - check_time > timedelta(seconds=30):
|
||||
raise AuthorizationError("authorization created_at is in the future")
|
||||
if check_time - created_at > AUTHORIZATION_TTL:
|
||||
raise AuthorizationError("authorization expired")
|
||||
raw_expires_at = raw.get("expires_at")
|
||||
expires_at = (
|
||||
_parse_iso8601(raw_expires_at)
|
||||
if raw_expires_at is not None
|
||||
else created_at + AUTHORIZATION_TTL
|
||||
)
|
||||
if expires_at <= check_time:
|
||||
raise AuthorizationError("authorization expiry is in the past")
|
||||
if expires_at > created_at + AUTHORIZATION_TTL:
|
||||
raise AuthorizationError("authorization expiry exceeds two-hour maximum")
|
||||
|
||||
_require_type(raw.get("one_time_use"), bool, key="one_time_use")
|
||||
if raw["one_time_use"] is not True:
|
||||
raise AuthorizationError("one_time_use must be true")
|
||||
|
||||
_require_type(raw.get("authorization_sha256"), str, key="authorization_sha256")
|
||||
expected_hash = compute_authorization_sha256(raw)
|
||||
provided_hash = str(raw["authorization_sha256"]).lower()
|
||||
if provided_hash != expected_hash:
|
||||
raise AuthorizationError("authorization_sha256 mismatch")
|
||||
|
||||
op_map = raw.get("allowed_branch_operations")
|
||||
if not isinstance(op_map, dict) or not op_map:
|
||||
raise AuthorizationError("allowed_branch_operations must be a non-empty object")
|
||||
|
||||
branch_operations: dict[str, BranchPolicy] = {}
|
||||
for branch, operation in op_map.items():
|
||||
if not isinstance(branch, str) or not branch.strip():
|
||||
raise AuthorizationError("branch names must be non-empty strings")
|
||||
|
||||
if not isinstance(operation, dict):
|
||||
raise AuthorizationError("operation policy must be an object")
|
||||
|
||||
create_block = operation.get("create_branch")
|
||||
append_block = operation.get("append_commit")
|
||||
|
||||
create_policy: BranchCreatePolicy | None = None
|
||||
append_policy: BranchAppendPolicy | None = None
|
||||
|
||||
if create_block is not None:
|
||||
if not isinstance(create_block, dict):
|
||||
raise AuthorizationError("create_branch block must be an object")
|
||||
raw_head_oid = create_block.get("head_oid")
|
||||
create_policy = BranchCreatePolicy(
|
||||
branch=branch,
|
||||
base_oid=_parse_oid(create_block.get("base_oid"), field="create_branch.base_oid"),
|
||||
head_oid=(
|
||||
_parse_oid(raw_head_oid, field="create_branch.head_oid")
|
||||
if raw_head_oid is not None
|
||||
else None
|
||||
),
|
||||
)
|
||||
|
||||
if append_block is not None:
|
||||
if not isinstance(append_block, dict):
|
||||
raise AuthorizationError("append_commit block must be an object")
|
||||
raw_expected_head_oid = append_block.get("expected_head_oid")
|
||||
append_policy = BranchAppendPolicy(
|
||||
branch=branch,
|
||||
expected_head_oid=(
|
||||
_parse_oid(
|
||||
raw_expected_head_oid,
|
||||
field="append_commit.expected_head_oid",
|
||||
)
|
||||
if raw_expected_head_oid is not None
|
||||
else None
|
||||
),
|
||||
allowed_paths=_parse_allowed_paths(append_block.get("allowed_paths")),
|
||||
)
|
||||
|
||||
if create_policy is None and append_policy is None:
|
||||
raise AuthorizationError("branch policy must define at least one operation")
|
||||
|
||||
branch_operations[branch] = BranchPolicy(
|
||||
create_branch=create_policy, append_commit=append_policy
|
||||
)
|
||||
|
||||
denied_raw = raw.get("denied_operations", ())
|
||||
if not isinstance(denied_raw, list):
|
||||
raise AuthorizationError("denied_operations must be a list")
|
||||
denied_operations: list[str] = []
|
||||
for value in denied_raw:
|
||||
if not isinstance(value, str):
|
||||
raise AuthorizationError("denied operations must be strings")
|
||||
denied_operations.append(value.lower())
|
||||
|
||||
return GovernedAuthorization(
|
||||
task_id=raw["task_id"],
|
||||
repo=raw["repo"],
|
||||
created_at=created_at,
|
||||
expires_at=expires_at,
|
||||
authorization_sha256=provided_hash,
|
||||
one_time_use=True,
|
||||
branch_operations=branch_operations,
|
||||
denied_operations=tuple(denied_operations),
|
||||
)
|
||||
|
||||
|
||||
def load_authorization_file(
|
||||
path: str | os.PathLike[str], *, now: datetime | None = None
|
||||
) -> GovernedAuthorization:
|
||||
"""Load and validate the root-only authorization file."""
|
||||
auth_path = Path(path)
|
||||
_assert_authorization_file_permissions(auth_path)
|
||||
try:
|
||||
raw_text = auth_path.read_text(encoding="utf-8")
|
||||
except (OSError, ValueError) as exc:
|
||||
raise AuthorizationError("unable to read authorization file") from exc
|
||||
|
||||
try:
|
||||
raw_obj = json.loads(raw_text)
|
||||
except json.JSONDecodeError as exc:
|
||||
raise AuthorizationError("authorization must be JSON") from exc
|
||||
|
||||
if not isinstance(raw_obj, dict):
|
||||
raise AuthorizationError("authorization top-level must be an object")
|
||||
|
||||
return parse_authorization(raw_obj, now=now)
|
||||
|
||||
|
||||
def _resolve_peer_executable(pid: int) -> str | None:
|
||||
"""Resolve peer executable from /proc/<pid>/exe when available."""
|
||||
if pid <= 0:
|
||||
return None
|
||||
exe_path = f"/proc/{pid}/exe"
|
||||
try:
|
||||
return os.readlink(exe_path)
|
||||
except OSError:
|
||||
return None
|
||||
|
||||
|
||||
def extract_peer_identity(
|
||||
connection: socket.socket, *, require_root_uid: bool = True
|
||||
) -> PeerIdentity:
|
||||
"""Validate SO_PEERCRED and return peer identity."""
|
||||
if not hasattr(socket, "SO_PEERCRED"):
|
||||
raise AuthorizationError("SO_PEERCRED not available on this platform")
|
||||
|
||||
data = connection.getsockopt(
|
||||
socket.SOL_SOCKET,
|
||||
socket.SO_PEERCRED,
|
||||
struct.calcsize("3i"),
|
||||
)
|
||||
if len(data) != struct.calcsize("3i"):
|
||||
raise AuthorizationError("SO_PEERCRED payload size mismatch")
|
||||
|
||||
pid, uid, gid = struct.unpack("3i", data)
|
||||
if require_root_uid and uid != 0:
|
||||
raise PermissionError("peer uid must be 0")
|
||||
|
||||
return PeerIdentity(
|
||||
pid=pid,
|
||||
uid=uid,
|
||||
gid=gid,
|
||||
executable=_resolve_peer_executable(pid),
|
||||
)
|
||||
|
||||
|
||||
def _normalize_file_path(path: str) -> str:
|
||||
normalized = posixpath.normpath(path.replace("\\", "/").strip())
|
||||
return normalized.lstrip("/")
|
||||
|
||||
|
||||
def _path_has_disallowed_segment(path: str) -> bool:
|
||||
lowered = path.lower()
|
||||
if ".." in path.split("/"):
|
||||
return True
|
||||
parts = [p for p in lowered.split("/") if p]
|
||||
for part in parts:
|
||||
for segment in _DENIED_PATH_SEGMENTS:
|
||||
if part == segment or part.startswith(f"{segment}.") or segment in part:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _is_allowed_path(path: str, allowed_paths: Sequence[str]) -> bool:
|
||||
normalized = _normalize_file_path(path)
|
||||
for prefix in allowed_paths:
|
||||
normalized_prefix = _normalize_file_path(prefix)
|
||||
if normalized == normalized_prefix:
|
||||
return True
|
||||
if normalized.startswith(normalized_prefix + "/"):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def contains_secret_like_content(content: str) -> bool:
|
||||
"""Heuristic detector for obvious secret-like strings."""
|
||||
content = _SAFE_SECRET_MARKERS.sub("", content or "")
|
||||
for pattern in _SECRET_PATTERNS:
|
||||
if pattern.search(content):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def validate_file_changes(
|
||||
changes: Any, allowed_paths: Sequence[str]
|
||||
) -> tuple[FileChange, ...]:
|
||||
"""Validate append-commit file changes against path and content policy."""
|
||||
if not isinstance(changes, list):
|
||||
raise AuthorizationError("changes must be a list")
|
||||
result: list[FileChange] = []
|
||||
|
||||
for change in changes:
|
||||
if not isinstance(change, Mapping):
|
||||
raise AuthorizationError("each file change must be an object")
|
||||
raw_path = change.get("path")
|
||||
raw_content = change.get("content")
|
||||
if not isinstance(raw_path, str) or not raw_path.strip():
|
||||
raise AuthorizationError("file change path must be a non-empty string")
|
||||
if raw_path.startswith(("/", "\\")):
|
||||
raise AuthorizationError("file change path must be relative")
|
||||
if not isinstance(raw_content, str):
|
||||
raise AuthorizationError("file change content must be a string")
|
||||
|
||||
normalized = _normalize_file_path(raw_path)
|
||||
if not normalized or normalized.startswith("../") or normalized == "..":
|
||||
raise AuthorizationError("file paths must be normalized relative paths")
|
||||
|
||||
if not _is_allowed_path(normalized, allowed_paths):
|
||||
raise AuthorizationError("file path outside allowed_paths")
|
||||
|
||||
if _path_has_disallowed_segment(normalized):
|
||||
raise AuthorizationError("file path uses denied segment")
|
||||
|
||||
if contains_secret_like_content(raw_content):
|
||||
raise AuthorizationError("file content failed secret-like scan")
|
||||
|
||||
result.append(FileChange(path=normalized, content=raw_content))
|
||||
|
||||
return tuple(result)
|
||||
@@ -0,0 +1,47 @@
|
||||
"""Supplement Gitea native protection when review identity is not expressible."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
|
||||
class MergeGateDenied(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class MergeGateDecision:
|
||||
allowed: bool
|
||||
owner_review_id: int
|
||||
required_contexts: tuple[str, ...]
|
||||
|
||||
|
||||
def validate_protected_merge(
|
||||
pull_request: Mapping[str, Any],
|
||||
reviews: Sequence[Mapping[str, Any]],
|
||||
statuses: Mapping[str, str],
|
||||
*,
|
||||
required_contexts: Sequence[str],
|
||||
unresolved_conversations: int,
|
||||
owner_login: str = "owner",
|
||||
owner_id: int = 2,
|
||||
) -> MergeGateDecision:
|
||||
if pull_request.get("state") != "open" or pull_request.get("mergeable") is not True:
|
||||
raise MergeGateDenied("pull_request_not_mergeable")
|
||||
author = (pull_request.get("user") or {}).get("login")
|
||||
owner_review = None
|
||||
for review in reviews:
|
||||
user = review.get("user") or {}
|
||||
if review.get("state") == "APPROVED" and user.get("login") == owner_login and user.get("id") == owner_id:
|
||||
if author == owner_login or (pull_request.get("author_id") == owner_id):
|
||||
raise MergeGateDenied("pr_author_self_approval_denied")
|
||||
owner_review = review
|
||||
if owner_review is None:
|
||||
raise MergeGateDenied("owner_review_required")
|
||||
if unresolved_conversations != 0:
|
||||
raise MergeGateDenied("unresolved_conversations_block_merge")
|
||||
missing = [context for context in required_contexts if statuses.get(context) != "success"]
|
||||
if missing:
|
||||
raise MergeGateDenied("required_checks_missing:" + ",".join(missing))
|
||||
return MergeGateDecision(True, int(owner_review.get("id", 0)), tuple(required_contexts))
|
||||
|
||||
@@ -0,0 +1,167 @@
|
||||
"""Fail-closed operation authorization for an isolated Git writer."""
|
||||
from __future__ import annotations
|
||||
|
||||
import ipaddress
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from isolated_writer_token_registry import TokenRegistry
|
||||
|
||||
|
||||
ROUTE_OPERATIONS = {
|
||||
("GET", "/api/runtime-status"): "runtime.status.read",
|
||||
("GET", "/api/baseline"): "baseline.read",
|
||||
("GET", "/api/patches"): "patches.read",
|
||||
("POST", "/api/commit-file"): "commit_file.atomic",
|
||||
}
|
||||
OID_RE = re.compile(r"[0-9a-f]{40}")
|
||||
|
||||
|
||||
class AuthorizationError(PermissionError):
|
||||
def __init__(self, code: str, status: int = 403):
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AuthorizedGrant:
|
||||
record: dict[str, Any]
|
||||
operation: str
|
||||
use_count: int
|
||||
|
||||
@property
|
||||
def token_id(self) -> str:
|
||||
return str(self.record["token_id"])
|
||||
|
||||
@property
|
||||
def task_id(self) -> str:
|
||||
return str(self.record["task_id"])
|
||||
|
||||
|
||||
def operation_for(method: str, path: str) -> str:
|
||||
operation = ROUTE_OPERATIONS.get((method.upper(), path))
|
||||
if not operation:
|
||||
raise AuthorizationError("isolated_writer_operation_forbidden")
|
||||
return operation
|
||||
|
||||
|
||||
def _parse_time(value: Any) -> datetime:
|
||||
try:
|
||||
parsed = datetime.fromisoformat(str(value).replace("Z", "+00:00"))
|
||||
except (TypeError, ValueError):
|
||||
raise AuthorizationError("writer_token_time_invalid") from None
|
||||
if parsed.tzinfo is None:
|
||||
raise AuthorizationError("writer_token_time_invalid")
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def _git_is_ancestor(workspace: Path, base: str, branch: str) -> bool:
|
||||
result = subprocess.run(
|
||||
["git", "merge-base", "--is-ancestor", base, branch],
|
||||
cwd=workspace,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
)
|
||||
return result.returncode == 0
|
||||
|
||||
|
||||
def _validate_grant(
|
||||
grant: dict[str, Any],
|
||||
*,
|
||||
audience: str,
|
||||
source_ip: str,
|
||||
operation: str,
|
||||
branch: str | None,
|
||||
path: str | None,
|
||||
workspace: Path,
|
||||
current_time: datetime,
|
||||
) -> None:
|
||||
if int(grant.get("schema_version", 0)) != 2:
|
||||
raise AuthorizationError("writer_token_policy_v2_required", 401)
|
||||
if str(grant.get("audience") or "") != audience:
|
||||
raise AuthorizationError("writer_token_audience_rejected")
|
||||
try:
|
||||
peer = ipaddress.ip_address(source_ip)
|
||||
networks = [ipaddress.ip_network(str(value), strict=True) for value in grant.get("source_cidrs", [])]
|
||||
except ValueError:
|
||||
raise AuthorizationError("writer_token_source_rejected") from None
|
||||
if not networks or not any(peer in network for network in networks):
|
||||
raise AuthorizationError("writer_token_source_rejected")
|
||||
created = _parse_time(grant.get("created_at"))
|
||||
not_before = _parse_time(grant.get("not_before"))
|
||||
expires = _parse_time(grant.get("expires_at"))
|
||||
if expires <= not_before or (expires - created).total_seconds() > 1800:
|
||||
raise AuthorizationError("writer_token_lifetime_rejected")
|
||||
if current_time < not_before:
|
||||
raise AuthorizationError("writer_token_not_yet_valid", 401)
|
||||
if current_time >= expires:
|
||||
raise AuthorizationError("writer_token_expired", 401)
|
||||
if bool(grant.get("revoked")):
|
||||
raise AuthorizationError("writer_token_revoked", 401)
|
||||
operations = grant.get("allowed_operations")
|
||||
if not isinstance(operations, list) or operation not in operations:
|
||||
raise AuthorizationError("writer_token_operation_rejected")
|
||||
expected_branch = str(grant.get("allowed_branch") or "")
|
||||
configured_branch = os.getenv("AIOS_GITOPS_ALLOWED_BRANCH", "")
|
||||
if expected_branch != configured_branch:
|
||||
raise AuthorizationError("writer_token_branch_rejected")
|
||||
if branch is not None and branch != expected_branch:
|
||||
raise AuthorizationError("writer_token_branch_rejected")
|
||||
if path is not None:
|
||||
paths = grant.get("allowed_paths")
|
||||
if not isinstance(paths, list) or path not in paths:
|
||||
raise AuthorizationError("writer_token_path_rejected")
|
||||
base = str(grant.get("approved_base_oid") or "").lower()
|
||||
if not OID_RE.fullmatch(base):
|
||||
raise AuthorizationError("writer_token_base_rejected")
|
||||
if not _git_is_ancestor(workspace, base, expected_branch):
|
||||
raise AuthorizationError("writer_token_base_not_ancestor")
|
||||
|
||||
|
||||
def authorize(
|
||||
registry: TokenRegistry,
|
||||
token: str,
|
||||
*,
|
||||
method: str,
|
||||
path: str,
|
||||
source_ip: str,
|
||||
workspace: Path,
|
||||
branch: str | None = None,
|
||||
target_path: str | None = None,
|
||||
current_time: datetime | None = None,
|
||||
) -> AuthorizedGrant:
|
||||
if os.getenv("AIOS_GITOPS_TOKEN_POLICY_VERSION_REQUIRED", "") != "2":
|
||||
raise AuthorizationError("writer_token_policy_v2_not_required")
|
||||
if not token:
|
||||
raise AuthorizationError("unauthorized", 401)
|
||||
grant = registry.find(token)
|
||||
if grant is None:
|
||||
raise AuthorizationError("unauthorized", 401)
|
||||
operation = operation_for(method, path)
|
||||
_validate_grant(
|
||||
grant,
|
||||
audience=os.getenv("AIOS_GITOPS_SERVICE_AUDIENCE", ""),
|
||||
source_ip=source_ip,
|
||||
operation=operation,
|
||||
branch=branch,
|
||||
path=target_path,
|
||||
workspace=workspace,
|
||||
current_time=current_time or datetime.now(timezone.utc),
|
||||
)
|
||||
limits = grant.get("max_uses")
|
||||
if not isinstance(limits, dict):
|
||||
raise AuthorizationError("writer_token_use_limit_missing")
|
||||
try:
|
||||
used = registry.consume(str(grant["token_id"]), operation, int(limits[operation]))
|
||||
except (KeyError, TypeError, ValueError):
|
||||
raise AuthorizationError("writer_token_use_limit_missing") from None
|
||||
except PermissionError as exc:
|
||||
code = str(exc)
|
||||
raise AuthorizationError(code, 401 if code == "writer_token_revoked" else 403) from None
|
||||
return AuthorizedGrant(grant, operation, used)
|
||||
@@ -0,0 +1,403 @@
|
||||
"""Atomic, idempotent commit-file Saga for the isolated writer."""
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sqlite3
|
||||
import subprocess
|
||||
import tempfile
|
||||
import threading
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import aios_isolated_writer_policy as policy
|
||||
|
||||
|
||||
OID_RE = re.compile(r"[0-9a-f]{40}")
|
||||
IDEMPOTENCY_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9._:-]{7,127}")
|
||||
STATES = frozenset({
|
||||
"PENDING", "FILE_WRITTEN", "COMMITTED", "PUSHED", "VERIFIED", "COMPLETED",
|
||||
"FAILED_RECOVERABLE", "MANUAL_REVIEW_REQUIRED",
|
||||
})
|
||||
_LOCKS: dict[str, threading.Lock] = {}
|
||||
_LOCKS_GUARD = threading.Lock()
|
||||
_LEDGER_INIT_LOCK = threading.Lock()
|
||||
|
||||
|
||||
class CommitFileError(RuntimeError):
|
||||
def __init__(self, code: str, status: int = 400):
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
|
||||
|
||||
class SimulatedCrash(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def canonical_digest(data: dict[str, Any]) -> str:
|
||||
payload = {
|
||||
"branch": data["branch"],
|
||||
"path": data["path"],
|
||||
"content_sha256": hashlib.sha256(data["content"].encode("utf-8")).hexdigest(),
|
||||
"message": data["message"],
|
||||
"expected_head_oid": data["expected_head_oid"],
|
||||
}
|
||||
encoded = json.dumps(payload, sort_keys=True, separators=(",", ":")).encode("utf-8")
|
||||
return hashlib.sha256(encoded).hexdigest()
|
||||
|
||||
|
||||
class OperationLedger:
|
||||
def __init__(self, path: Path | str):
|
||||
self.path = Path(path)
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
if self.path.parent.is_symlink() or self.path.is_symlink():
|
||||
raise PermissionError("writer_operation_ledger_symlink_rejected")
|
||||
with _LEDGER_INIT_LOCK:
|
||||
with self.connect() as db:
|
||||
db.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS writer_operations (
|
||||
operation_id TEXT PRIMARY KEY,
|
||||
token_id TEXT NOT NULL,
|
||||
task_id TEXT NOT NULL,
|
||||
idempotency_key TEXT NOT NULL UNIQUE,
|
||||
operation_digest TEXT NOT NULL,
|
||||
branch TEXT NOT NULL,
|
||||
path TEXT NOT NULL,
|
||||
content_sha256 TEXT NOT NULL,
|
||||
pre_head_oid TEXT NOT NULL,
|
||||
commit_oid TEXT,
|
||||
push_status TEXT,
|
||||
verification_status TEXT,
|
||||
state TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||||
updated_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
|
||||
error_code TEXT
|
||||
)
|
||||
"""
|
||||
)
|
||||
os.chmod(self.path, 0o600)
|
||||
|
||||
def connect(self) -> sqlite3.Connection:
|
||||
db = sqlite3.connect(self.path, timeout=30)
|
||||
db.row_factory = sqlite3.Row
|
||||
db.execute("PRAGMA journal_mode=WAL")
|
||||
db.execute("PRAGMA synchronous=FULL")
|
||||
return db
|
||||
|
||||
def get_or_create(self, grant: Any, data: dict[str, Any], digest: str) -> dict[str, Any]:
|
||||
key = data["idempotency_key"]
|
||||
with self.connect() as db:
|
||||
db.execute("BEGIN IMMEDIATE")
|
||||
row = db.execute(
|
||||
"SELECT * FROM writer_operations WHERE idempotency_key=?", (key,)
|
||||
).fetchone()
|
||||
if row:
|
||||
db.commit()
|
||||
record = dict(row)
|
||||
if record["operation_digest"] != digest:
|
||||
raise CommitFileError("writer_idempotency_conflict", 409)
|
||||
if (
|
||||
record["token_id"] != grant.token_id
|
||||
or record["task_id"] != grant.task_id
|
||||
):
|
||||
raise CommitFileError("writer_idempotency_owner_conflict", 409)
|
||||
return record
|
||||
operation_id = hashlib.sha256(
|
||||
f"{grant.task_id}\0{key}".encode("utf-8")
|
||||
).hexdigest()
|
||||
content_sha = hashlib.sha256(data["content"].encode("utf-8")).hexdigest()
|
||||
db.execute(
|
||||
"""
|
||||
INSERT INTO writer_operations(
|
||||
operation_id,token_id,task_id,idempotency_key,operation_digest,
|
||||
branch,path,content_sha256,pre_head_oid,state
|
||||
) VALUES(?,?,?,?,?,?,?,?,?,?)
|
||||
""",
|
||||
(
|
||||
operation_id, grant.token_id, grant.task_id, key, digest,
|
||||
data["branch"], data["path"], content_sha,
|
||||
data["expected_head_oid"], "PENDING",
|
||||
),
|
||||
)
|
||||
db.commit()
|
||||
return self.get(key)
|
||||
|
||||
def get(self, key: str) -> dict[str, Any]:
|
||||
with self.connect() as db:
|
||||
row = db.execute(
|
||||
"SELECT * FROM writer_operations WHERE idempotency_key=?", (key,)
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise KeyError(key)
|
||||
return dict(row)
|
||||
|
||||
def update(self, key: str, state: str, **fields: Any) -> dict[str, Any]:
|
||||
if state not in STATES:
|
||||
raise ValueError("invalid writer operation state")
|
||||
allowed = {"commit_oid", "push_status", "verification_status", "error_code"}
|
||||
assignments = ["state=?", "updated_at=CURRENT_TIMESTAMP"]
|
||||
values: list[Any] = [state]
|
||||
for name, value in fields.items():
|
||||
if name not in allowed:
|
||||
raise ValueError("invalid ledger field")
|
||||
assignments.append(f"{name}=?")
|
||||
values.append(value)
|
||||
values.append(key)
|
||||
with self.connect() as db:
|
||||
db.execute("BEGIN IMMEDIATE")
|
||||
db.execute(
|
||||
f"UPDATE writer_operations SET {','.join(assignments)} WHERE idempotency_key=?",
|
||||
values,
|
||||
)
|
||||
db.commit()
|
||||
return self.get(key)
|
||||
|
||||
|
||||
class AtomicCommitFile:
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
workspace: Path,
|
||||
bare_repo: Path,
|
||||
ledger: OperationLedger,
|
||||
remote: str,
|
||||
audit,
|
||||
crash_after_state: str | None = None,
|
||||
):
|
||||
self.workspace = workspace
|
||||
self.bare_repo = bare_repo
|
||||
self.ledger = ledger
|
||||
self.remote = remote
|
||||
self.audit = audit
|
||||
self.crash_after_state = crash_after_state
|
||||
|
||||
def _git(self, *args: str, check: bool = True) -> str:
|
||||
result = subprocess.run(
|
||||
["git", *args], cwd=self.workspace, text=True, capture_output=True
|
||||
)
|
||||
if check and result.returncode != 0:
|
||||
raise CommitFileError("writer_git_operation_failed", 500)
|
||||
return result.stdout.strip()
|
||||
|
||||
def _transition(self, key: str, state: str, **fields: Any) -> dict[str, Any]:
|
||||
record = self.ledger.update(key, state, **fields)
|
||||
if self.crash_after_state == state:
|
||||
raise SimulatedCrash(state)
|
||||
return record
|
||||
|
||||
def _validate(self, data: Any) -> dict[str, Any]:
|
||||
if not isinstance(data, dict):
|
||||
raise CommitFileError("writer_request_object_required")
|
||||
required = ("branch", "path", "content", "message", "expected_head_oid", "idempotency_key")
|
||||
if any(field not in data for field in required):
|
||||
raise CommitFileError("writer_request_incomplete")
|
||||
if data.get("force") or data.get("force_push"):
|
||||
raise CommitFileError("isolated_writer_force_rejected", 403)
|
||||
if set(data) != set(required):
|
||||
raise CommitFileError("writer_request_fields_rejected")
|
||||
item = {field: data[field] for field in required}
|
||||
if item["branch"] != policy.allowed_branch():
|
||||
raise CommitFileError("isolated_writer_branch_rejected", 403)
|
||||
try:
|
||||
item["path"] = policy.validate_path(item["path"], self.workspace)
|
||||
except PermissionError as exc:
|
||||
raise CommitFileError(str(exc), 403) from None
|
||||
if not isinstance(item["content"], str) or "\x00" in item["content"]:
|
||||
raise CommitFileError("writer_content_rejected")
|
||||
try:
|
||||
policy.validate_content_for_path(item["path"], item["content"])
|
||||
except PermissionError as exc:
|
||||
raise CommitFileError(str(exc), 403) from None
|
||||
if len(item["content"].encode("utf-8")) > 1_048_576:
|
||||
raise CommitFileError("writer_content_too_large", 413)
|
||||
message = item["message"]
|
||||
if (
|
||||
not isinstance(message, str)
|
||||
or not 1 <= len(message) <= 200
|
||||
or "\x00" in message
|
||||
or "\n" in message
|
||||
or "\r" in message
|
||||
):
|
||||
raise CommitFileError("writer_message_rejected")
|
||||
if not isinstance(item["expected_head_oid"], str) or not OID_RE.fullmatch(item["expected_head_oid"]):
|
||||
raise CommitFileError("writer_expected_head_rejected")
|
||||
if not isinstance(item["idempotency_key"], str) or not IDEMPOTENCY_RE.fullmatch(item["idempotency_key"]):
|
||||
raise CommitFileError("writer_idempotency_key_rejected")
|
||||
return item
|
||||
|
||||
def _atomic_write(self, relative: str, content: str) -> None:
|
||||
target = self.workspace / relative
|
||||
target.parent.mkdir(parents=True, exist_ok=True)
|
||||
fd, temporary = tempfile.mkstemp(prefix=".writer-", dir=target.parent)
|
||||
try:
|
||||
with os.fdopen(fd, "wb", closefd=True) as stream:
|
||||
stream.write(content.encode("utf-8"))
|
||||
stream.flush()
|
||||
os.fsync(stream.fileno())
|
||||
os.replace(temporary, target)
|
||||
parent_fd = os.open(target.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0))
|
||||
try:
|
||||
os.fsync(parent_fd)
|
||||
finally:
|
||||
os.close(parent_fd)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
|
||||
def _verify_remote(self, branch: str, oid: str) -> None:
|
||||
bare = subprocess.run(
|
||||
["git", "--git-dir", str(self.bare_repo), "rev-parse", f"refs/heads/{branch}"],
|
||||
text=True, capture_output=True,
|
||||
)
|
||||
if bare.returncode != 0 or bare.stdout.strip() != oid:
|
||||
raise CommitFileError("writer_authoritative_bare_oid_mismatch", 500)
|
||||
remote = subprocess.run(
|
||||
["git", "ls-remote", "--heads", self.remote, f"refs/heads/{branch}"],
|
||||
cwd=self.workspace, text=True, capture_output=True,
|
||||
)
|
||||
if remote.returncode != 0:
|
||||
raise CommitFileError("writer_gitea_verification_failed", 503)
|
||||
fields = remote.stdout.strip().split()
|
||||
if len(fields) != 2:
|
||||
raise CommitFileError("writer_gitea_ref_missing", 503)
|
||||
if fields[0] != oid:
|
||||
raise CommitFileError("writer_gitea_oid_conflict", 409)
|
||||
|
||||
def execute(self, grant: Any, raw_data: Any) -> dict[str, Any]:
|
||||
data = self._validate(raw_data)
|
||||
digest = canonical_digest(data)
|
||||
branch = data["branch"]
|
||||
with _LOCKS_GUARD:
|
||||
lock = _LOCKS.setdefault(branch, threading.Lock())
|
||||
lock_path = self.ledger.path.parent / f"{hashlib.sha256(branch.encode()).hexdigest()}.lock"
|
||||
with lock, open(lock_path, "a+b") as branch_lock:
|
||||
fcntl.flock(branch_lock.fileno(), fcntl.LOCK_EX)
|
||||
return self._execute_locked(grant, data, digest)
|
||||
|
||||
def _execute_locked(self, grant: Any, data: dict[str, Any], digest: str) -> dict[str, Any]:
|
||||
key = data["idempotency_key"]
|
||||
record = self.ledger.get_or_create(grant, data, digest)
|
||||
if record["state"] == "COMPLETED":
|
||||
return self._result(record, idempotent=True)
|
||||
if self._git("rev-parse", "--abbrev-ref", "HEAD") != data["branch"]:
|
||||
record = self._transition(
|
||||
key, "MANUAL_REVIEW_REQUIRED", error_code="writer_current_branch_conflict"
|
||||
)
|
||||
self._audit(grant, data, digest, record, "manual_review_required")
|
||||
raise CommitFileError("writer_current_branch_conflict", 409)
|
||||
head = self._git("rev-parse", "HEAD")
|
||||
commit_oid = record.get("commit_oid")
|
||||
if head != record["pre_head_oid"] and head != commit_oid:
|
||||
record = self._transition(
|
||||
key, "MANUAL_REVIEW_REQUIRED", error_code="writer_branch_head_conflict"
|
||||
)
|
||||
self._audit(grant, data, digest, record, "manual_review_required")
|
||||
raise CommitFileError("writer_branch_head_conflict", 409)
|
||||
try:
|
||||
state = record["state"]
|
||||
if state == "MANUAL_REVIEW_REQUIRED":
|
||||
raise CommitFileError("writer_manual_review_required", 409)
|
||||
if state == "FAILED_RECOVERABLE":
|
||||
if record.get("push_status") == "confirmed":
|
||||
state = "PUSHED"
|
||||
else:
|
||||
state = "COMMITTED" if commit_oid else "FILE_WRITTEN"
|
||||
if state == "PENDING":
|
||||
self._atomic_write(data["path"], data["content"])
|
||||
record = self._transition(key, "FILE_WRITTEN")
|
||||
state = record["state"]
|
||||
if state == "FILE_WRITTEN":
|
||||
actual_sha = hashlib.sha256(
|
||||
(self.workspace / data["path"]).read_bytes()
|
||||
).hexdigest()
|
||||
if actual_sha != record["content_sha256"]:
|
||||
raise CommitFileError("writer_file_content_conflict", 409)
|
||||
staged_before = self._git("diff", "--cached", "--name-only", check=False).splitlines()
|
||||
if staged_before:
|
||||
raise CommitFileError("writer_extra_staged_files_rejected", 409)
|
||||
self._git("add", "--", data["path"])
|
||||
staged = self._git("diff", "--cached", "--name-only").splitlines()
|
||||
if staged != [data["path"]]:
|
||||
raise CommitFileError("writer_extra_staged_files_rejected", 409)
|
||||
self._git("commit", "-m", data["message"])
|
||||
commit_oid = self._git("rev-parse", "HEAD")
|
||||
record = self._transition(key, "COMMITTED", commit_oid=commit_oid)
|
||||
state = record["state"]
|
||||
if state == "COMMITTED":
|
||||
commit_oid = str(record["commit_oid"])
|
||||
pushed = subprocess.run(
|
||||
["git", "push", "--porcelain", self.remote, f"HEAD:refs/heads/{data['branch']}"],
|
||||
cwd=self.workspace, text=True, capture_output=True,
|
||||
)
|
||||
if pushed.returncode != 0:
|
||||
self._transition(
|
||||
key, "FAILED_RECOVERABLE",
|
||||
push_status="failed", error_code="writer_gitea_push_failed",
|
||||
)
|
||||
raise CommitFileError("writer_gitea_push_failed", 503)
|
||||
record = self._transition(key, "PUSHED", push_status="confirmed")
|
||||
state = record["state"]
|
||||
if state == "PUSHED":
|
||||
commit_oid = str(record["commit_oid"])
|
||||
self._verify_remote(data["branch"], commit_oid)
|
||||
record = self._transition(
|
||||
key, "VERIFIED", verification_status="bare+gitea"
|
||||
)
|
||||
state = record["state"]
|
||||
if state == "VERIFIED":
|
||||
record = self._transition(key, "COMPLETED", error_code=None)
|
||||
self._audit(grant, data, digest, record, "completed")
|
||||
return self._result(record, idempotent=False)
|
||||
except SimulatedCrash:
|
||||
raise
|
||||
except CommitFileError as exc:
|
||||
latest = self.ledger.get(key)
|
||||
if latest["state"] not in {"FAILED_RECOVERABLE", "MANUAL_REVIEW_REQUIRED"}:
|
||||
failure_state = (
|
||||
"MANUAL_REVIEW_REQUIRED"
|
||||
if exc.code in {
|
||||
"writer_gitea_oid_conflict",
|
||||
"writer_file_content_conflict",
|
||||
"writer_current_branch_conflict",
|
||||
}
|
||||
else "FAILED_RECOVERABLE"
|
||||
)
|
||||
latest = self._transition(key, failure_state, error_code=exc.code)
|
||||
self._audit(grant, data, digest, latest, "failed")
|
||||
raise
|
||||
|
||||
def _audit(self, grant: Any, data: dict[str, Any], digest: str, record: dict[str, Any], result: str) -> None:
|
||||
self.audit({
|
||||
"token_id": grant.token_id,
|
||||
"task_id": grant.task_id,
|
||||
"audience": grant.record["audience"],
|
||||
"source_ip": grant.record.get("_source_ip", "socket-peer"),
|
||||
"operation": grant.operation,
|
||||
"branch": data["branch"],
|
||||
"path": data["path"],
|
||||
"idempotency_key": data["idempotency_key"],
|
||||
"operation_digest": digest,
|
||||
"path_policy_sha256": policy.configured_path_policy_sha256(),
|
||||
"pre_head_oid": record["pre_head_oid"],
|
||||
"commit_oid": record.get("commit_oid"),
|
||||
"result": result,
|
||||
})
|
||||
|
||||
@staticmethod
|
||||
def _result(record: dict[str, Any], *, idempotent: bool) -> dict[str, Any]:
|
||||
return {
|
||||
"status": "completed",
|
||||
"state": record["state"],
|
||||
"operation_id": record["operation_id"],
|
||||
"branch": record["branch"],
|
||||
"path": record["path"],
|
||||
"commit_oid": record.get("commit_oid"),
|
||||
"push_status": record.get("push_status"),
|
||||
"verification_status": record.get("verification_status"),
|
||||
"idempotent": idempotent,
|
||||
}
|
||||
@@ -0,0 +1,422 @@
|
||||
"""Strict service-level exact-path policy for isolated Git writers."""
|
||||
from __future__ import annotations
|
||||
|
||||
import grp
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import stat
|
||||
from dataclasses import dataclass
|
||||
from functools import lru_cache
|
||||
from pathlib import Path, PurePosixPath, PureWindowsPath
|
||||
from typing import Any
|
||||
from urllib.parse import unquote
|
||||
|
||||
|
||||
MAX_POLICY_BYTES = 65_536
|
||||
POLICY_FIELDS = frozenset(
|
||||
{
|
||||
"schema_version",
|
||||
"policy_id",
|
||||
"audience",
|
||||
"repository_identity",
|
||||
"allowed_branch",
|
||||
"allowed_operations",
|
||||
}
|
||||
)
|
||||
OPERATION_FIELDS = frozenset({"exact_paths", "max_content_bytes", "content_profile"})
|
||||
SUPPORTED_OPERATIONS = frozenset({"commit_file.atomic"})
|
||||
SUPPORTED_CONTENT_PROFILES = frozenset({"systemd-codex-review-worker-v1"})
|
||||
_SECRET_RE = re.compile(
|
||||
r"(?i)(authorization\s*:|bearer\s+|(?:token|password|secret)\s*[:=])"
|
||||
)
|
||||
_SYSTEMD_NAME_RE = re.compile(r"[A-Za-z][A-Za-z0-9]*\Z")
|
||||
_SYSTEMD_MAX_LINE_BYTES = 4096
|
||||
_SYSTEMD_ALLOWED_DIRECTIVES = {
|
||||
"Unit": frozenset({"Description", "After", "Wants"}),
|
||||
"Service": frozenset(
|
||||
{
|
||||
"Type",
|
||||
"User",
|
||||
"Group",
|
||||
"WorkingDirectory",
|
||||
"Environment",
|
||||
"ExecStart",
|
||||
"Restart",
|
||||
"RestartSec",
|
||||
"NoNewPrivileges",
|
||||
"PrivateTmp",
|
||||
"PrivateDevices",
|
||||
"ProtectSystem",
|
||||
"ProtectHome",
|
||||
"ProtectKernelTunables",
|
||||
"ProtectKernelModules",
|
||||
"ProtectControlGroups",
|
||||
"LockPersonality",
|
||||
"RestrictSUIDSGID",
|
||||
"RestrictRealtime",
|
||||
"MemoryDenyWriteExecute",
|
||||
"RuntimeDirectory",
|
||||
"StateDirectory",
|
||||
"CacheDirectory",
|
||||
"ReadOnlyPaths",
|
||||
"ReadWritePaths",
|
||||
"UMask",
|
||||
}
|
||||
),
|
||||
"Install": frozenset({"WantedBy"}),
|
||||
}
|
||||
_SYSTEMD_MULTI_DIRECTIVES = frozenset(
|
||||
{
|
||||
("Service", "Environment"),
|
||||
("Service", "ReadOnlyPaths"),
|
||||
("Service", "ReadWritePaths"),
|
||||
}
|
||||
)
|
||||
_SYSTEMD_EXACT_SINGLE_VALUES = {
|
||||
("Unit", "Description"): "AIOS Codex Review/Test Worker",
|
||||
("Unit", "After"): "network-online.target",
|
||||
("Unit", "Wants"): "network-online.target",
|
||||
("Service", "Type"): "simple",
|
||||
("Service", "User"): "aiman",
|
||||
("Service", "Group"): "gitops",
|
||||
(
|
||||
"Service",
|
||||
"WorkingDirectory",
|
||||
): "/usr/libexec/aios-codex-review-test-worker/current",
|
||||
(
|
||||
"Service",
|
||||
"ExecStart",
|
||||
): "/usr/bin/python3 -m task_plane.workers.codex_review_test",
|
||||
("Service", "Restart"): "on-failure",
|
||||
("Service", "RestartSec"): "2",
|
||||
("Service", "NoNewPrivileges"): "true",
|
||||
("Service", "PrivateTmp"): "true",
|
||||
("Service", "PrivateDevices"): "true",
|
||||
("Service", "ProtectSystem"): "strict",
|
||||
("Service", "ProtectHome"): "true",
|
||||
("Service", "ProtectKernelTunables"): "true",
|
||||
("Service", "ProtectKernelModules"): "true",
|
||||
("Service", "ProtectControlGroups"): "true",
|
||||
("Service", "LockPersonality"): "true",
|
||||
("Service", "RestrictSUIDSGID"): "true",
|
||||
("Service", "RestrictRealtime"): "true",
|
||||
("Service", "MemoryDenyWriteExecute"): "true",
|
||||
("Service", "RuntimeDirectory"): "aios-codex-review-test-worker",
|
||||
("Service", "StateDirectory"): "aios-codex-review-test-worker",
|
||||
("Service", "CacheDirectory"): "aios-codex-review-test-worker",
|
||||
("Service", "UMask"): "0077",
|
||||
("Install", "WantedBy"): "multi-user.target",
|
||||
}
|
||||
_SYSTEMD_EXACT_MULTI_VALUES = {
|
||||
("Service", "Environment"): (
|
||||
"AIOS_CODEX_WORKER_MODE=shadow",
|
||||
"AIOS_TASK_PLANE_EXECUTION_ENABLED=false",
|
||||
"PYTHONDONTWRITEBYTECODE=1",
|
||||
),
|
||||
("Service", "ReadOnlyPaths"): (
|
||||
"/data/aios-gitops/repo.git",
|
||||
"/usr/libexec/aios-codex-review-test-worker",
|
||||
),
|
||||
("Service", "ReadWritePaths"): (
|
||||
"/run/aios-codex-review-test-worker",
|
||||
"/var/lib/aios-codex-review-test-worker",
|
||||
"/var/cache/aios-codex-review-test-worker",
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
class PathPolicyError(PermissionError):
|
||||
pass
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OperationPolicy:
|
||||
exact_paths: tuple[str, ...]
|
||||
max_content_bytes: int
|
||||
content_profile: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ServicePathPolicy:
|
||||
schema_version: int
|
||||
policy_id: str
|
||||
audience: str
|
||||
repository_identity: str
|
||||
allowed_branch: str
|
||||
allowed_operations: dict[str, OperationPolicy]
|
||||
sha256: str
|
||||
|
||||
def operation(self, name: str) -> OperationPolicy:
|
||||
try:
|
||||
return self.allowed_operations[name]
|
||||
except KeyError:
|
||||
raise PathPolicyError("isolated_writer_service_operation_rejected") from None
|
||||
|
||||
def require_exact_path(self, operation: str, path: str) -> OperationPolicy:
|
||||
selected = self.operation(operation)
|
||||
if path not in selected.exact_paths:
|
||||
raise PathPolicyError("isolated_writer_service_path_rejected")
|
||||
return selected
|
||||
|
||||
|
||||
def _canonical_json(value: Any) -> bytes:
|
||||
return (
|
||||
json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
|
||||
+ "\n"
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def validate_relative_path_syntax(path: str) -> str:
|
||||
if not isinstance(path, str):
|
||||
raise PathPolicyError("isolated_writer_path_rejected")
|
||||
if not path or path != path.strip() or "\x00" in path or "\\" in path:
|
||||
raise PathPolicyError("isolated_writer_path_rejected")
|
||||
try:
|
||||
decoded = unquote(path, errors="strict")
|
||||
except (UnicodeDecodeError, ValueError):
|
||||
raise PathPolicyError("isolated_writer_path_rejected") from None
|
||||
if decoded != path:
|
||||
raise PathPolicyError("isolated_writer_path_rejected")
|
||||
posix = PurePosixPath(path)
|
||||
windows = PureWindowsPath(path)
|
||||
parts = path.split("/")
|
||||
if (
|
||||
posix.is_absolute()
|
||||
or windows.is_absolute()
|
||||
or bool(windows.drive)
|
||||
or any(part in {"", ".", ".."} for part in parts)
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_path_rejected")
|
||||
return path
|
||||
|
||||
|
||||
def _require_fields(value: dict[str, Any], allowed: frozenset[str], code: str) -> None:
|
||||
if set(value) != allowed:
|
||||
raise PathPolicyError(code)
|
||||
|
||||
|
||||
def _parse_policy(document: Any, canonical: bytes) -> ServicePathPolicy:
|
||||
if not isinstance(document, dict):
|
||||
raise PathPolicyError("isolated_writer_path_policy_object_required")
|
||||
_require_fields(document, POLICY_FIELDS, "isolated_writer_path_policy_fields_rejected")
|
||||
if document["schema_version"] != 1:
|
||||
raise PathPolicyError("isolated_writer_path_policy_schema_rejected")
|
||||
text_fields = (
|
||||
"policy_id",
|
||||
"audience",
|
||||
"repository_identity",
|
||||
"allowed_branch",
|
||||
)
|
||||
if any(
|
||||
not isinstance(document[field], str) or not document[field].strip()
|
||||
for field in text_fields
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_path_policy_value_rejected")
|
||||
raw_operations = document["allowed_operations"]
|
||||
if not isinstance(raw_operations, dict) or not raw_operations:
|
||||
raise PathPolicyError("isolated_writer_path_policy_operations_rejected")
|
||||
if not set(raw_operations).issubset(SUPPORTED_OPERATIONS):
|
||||
raise PathPolicyError("isolated_writer_path_policy_operations_rejected")
|
||||
operations: dict[str, OperationPolicy] = {}
|
||||
for name, raw in raw_operations.items():
|
||||
if not isinstance(raw, dict):
|
||||
raise PathPolicyError("isolated_writer_path_policy_operation_rejected")
|
||||
_require_fields(
|
||||
raw,
|
||||
OPERATION_FIELDS,
|
||||
"isolated_writer_path_policy_operation_fields_rejected",
|
||||
)
|
||||
paths = raw["exact_paths"]
|
||||
if (
|
||||
not isinstance(paths, list)
|
||||
or not paths
|
||||
or any(not isinstance(item, str) for item in paths)
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_path_policy_paths_rejected")
|
||||
validated = tuple(validate_relative_path_syntax(item) for item in paths)
|
||||
if len(set(validated)) != len(validated):
|
||||
raise PathPolicyError("isolated_writer_path_policy_paths_rejected")
|
||||
maximum = raw["max_content_bytes"]
|
||||
if not isinstance(maximum, int) or isinstance(maximum, bool) or not 1 <= maximum <= 1_048_576:
|
||||
raise PathPolicyError("isolated_writer_path_policy_size_rejected")
|
||||
profile = raw["content_profile"]
|
||||
if profile not in SUPPORTED_CONTENT_PROFILES:
|
||||
raise PathPolicyError("isolated_writer_path_policy_profile_rejected")
|
||||
operations[name] = OperationPolicy(validated, maximum, profile)
|
||||
return ServicePathPolicy(
|
||||
schema_version=1,
|
||||
policy_id=document["policy_id"],
|
||||
audience=document["audience"],
|
||||
repository_identity=document["repository_identity"],
|
||||
allowed_branch=document["allowed_branch"],
|
||||
allowed_operations=operations,
|
||||
sha256=hashlib.sha256(canonical).hexdigest(),
|
||||
)
|
||||
|
||||
|
||||
def load_path_policy(
|
||||
path: Path,
|
||||
*,
|
||||
expected_owner_uid: int = 0,
|
||||
expected_group_gid: int | None = None,
|
||||
expected_parent_mode: int = 0o750,
|
||||
expected_file_mode: int = 0o640,
|
||||
) -> ServicePathPolicy:
|
||||
lexical = Path(os.path.abspath(str(path)))
|
||||
if lexical.is_symlink():
|
||||
raise PathPolicyError("isolated_writer_path_policy_symlink_rejected")
|
||||
try:
|
||||
parent_info = lexical.parent.stat(follow_symlinks=False)
|
||||
file_info = lexical.stat(follow_symlinks=False)
|
||||
except FileNotFoundError:
|
||||
raise PathPolicyError("isolated_writer_path_policy_missing") from None
|
||||
if stat.S_ISLNK(parent_info.st_mode) or not stat.S_ISDIR(parent_info.st_mode):
|
||||
raise PathPolicyError("isolated_writer_path_policy_parent_rejected")
|
||||
if stat.S_ISLNK(file_info.st_mode) or not stat.S_ISREG(file_info.st_mode):
|
||||
raise PathPolicyError("isolated_writer_path_policy_file_rejected")
|
||||
if lexical.resolve(strict=True) != lexical:
|
||||
raise PathPolicyError("isolated_writer_path_policy_symlink_rejected")
|
||||
if (
|
||||
parent_info.st_uid != expected_owner_uid
|
||||
or stat.S_IMODE(parent_info.st_mode) != expected_parent_mode
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_path_policy_parent_permissions_rejected")
|
||||
if (
|
||||
file_info.st_uid != expected_owner_uid
|
||||
or stat.S_IMODE(file_info.st_mode) != expected_file_mode
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_path_policy_permissions_rejected")
|
||||
if expected_group_gid is not None and (
|
||||
parent_info.st_gid != expected_group_gid or file_info.st_gid != expected_group_gid
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_path_policy_group_rejected")
|
||||
if file_info.st_size <= 0 or file_info.st_size > MAX_POLICY_BYTES:
|
||||
raise PathPolicyError("isolated_writer_path_policy_file_size_rejected")
|
||||
raw = lexical.read_bytes()
|
||||
try:
|
||||
document = json.loads(raw.decode("utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError):
|
||||
raise PathPolicyError("isolated_writer_path_policy_json_rejected") from None
|
||||
canonical = _canonical_json(document)
|
||||
if raw != canonical:
|
||||
raise PathPolicyError("isolated_writer_path_policy_not_canonical")
|
||||
return _parse_policy(document, canonical)
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def configured_path_policy() -> ServicePathPolicy | None:
|
||||
configured = os.getenv("AIOS_GITOPS_PATH_POLICY_FILE", "").strip()
|
||||
if not configured:
|
||||
return None
|
||||
if not Path(configured).is_absolute():
|
||||
raise PathPolicyError("isolated_writer_path_policy_path_rejected")
|
||||
try:
|
||||
gitops_gid = grp.getgrnam("gitops").gr_gid
|
||||
except KeyError:
|
||||
raise PathPolicyError("isolated_writer_path_policy_group_rejected") from None
|
||||
loaded = load_path_policy(Path(configured), expected_group_gid=gitops_gid)
|
||||
if loaded.audience != os.getenv("AIOS_GITOPS_SERVICE_AUDIENCE", ""):
|
||||
raise PathPolicyError("isolated_writer_path_policy_audience_rejected")
|
||||
if loaded.repository_identity != os.getenv("AIOS_GITOPS_REPOSITORY_IDENTITY", ""):
|
||||
raise PathPolicyError("isolated_writer_path_policy_repository_rejected")
|
||||
if loaded.allowed_branch != os.getenv("AIOS_GITOPS_ALLOWED_BRANCH", ""):
|
||||
raise PathPolicyError("isolated_writer_path_policy_branch_rejected")
|
||||
return loaded
|
||||
|
||||
|
||||
def clear_path_policy_cache() -> None:
|
||||
configured_path_policy.cache_clear()
|
||||
|
||||
|
||||
def require_service_path(operation: str, path: str) -> OperationPolicy:
|
||||
loaded = configured_path_policy()
|
||||
if loaded is None:
|
||||
raise PathPolicyError("isolated_writer_service_path_policy_required")
|
||||
return loaded.require_exact_path(operation, path)
|
||||
|
||||
|
||||
def configured_path_policy_sha256() -> str | None:
|
||||
loaded = configured_path_policy()
|
||||
return None if loaded is None else loaded.sha256
|
||||
|
||||
|
||||
def validate_content(operation: str, path: str, content: str) -> None:
|
||||
selected = require_service_path(operation, path)
|
||||
try:
|
||||
encoded = content.encode("utf-8", errors="strict")
|
||||
except (AttributeError, UnicodeEncodeError):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected") from None
|
||||
if len(encoded) > selected.max_content_bytes:
|
||||
raise PathPolicyError("isolated_writer_service_content_too_large")
|
||||
if selected.content_profile == "systemd-codex-review-worker-v1":
|
||||
_validate_systemd_codex_review_worker(content)
|
||||
return
|
||||
raise PathPolicyError("isolated_writer_path_policy_profile_rejected")
|
||||
|
||||
|
||||
def _validate_systemd_codex_review_worker(content: str) -> None:
|
||||
if not isinstance(content, str):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
try:
|
||||
content.encode("utf-8", errors="strict")
|
||||
except UnicodeEncodeError:
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected") from None
|
||||
if (
|
||||
"\x00" in content
|
||||
or "\r" in content
|
||||
or _SECRET_RE.search(content)
|
||||
or not content.endswith("\n")
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
|
||||
sections: set[str] = set()
|
||||
values: dict[tuple[str, str], list[str]] = {}
|
||||
section: str | None = None
|
||||
for line in content.splitlines():
|
||||
if len(line.encode("utf-8")) > _SYSTEMD_MAX_LINE_BYTES:
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
if not line:
|
||||
continue
|
||||
if line[0].isspace() or line.startswith(("#", ";")):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
if line.startswith("[") and line.endswith("]"):
|
||||
candidate = line[1:-1]
|
||||
if (
|
||||
not _SYSTEMD_NAME_RE.fullmatch(candidate)
|
||||
or candidate not in _SYSTEMD_ALLOWED_DIRECTIVES
|
||||
or candidate in sections
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
sections.add(candidate)
|
||||
section = candidate
|
||||
continue
|
||||
if section is None or "=" not in line:
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
directive, value = line.split("=", 1)
|
||||
if (
|
||||
not _SYSTEMD_NAME_RE.fullmatch(directive)
|
||||
or directive not in _SYSTEMD_ALLOWED_DIRECTIVES[section]
|
||||
or not value
|
||||
or value != value.strip()
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
key = (section, directive)
|
||||
if key in values and key not in _SYSTEMD_MULTI_DIRECTIVES:
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
values.setdefault(key, []).append(value)
|
||||
|
||||
if sections != set(_SYSTEMD_ALLOWED_DIRECTIVES):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
if set(values) != set(_SYSTEMD_EXACT_SINGLE_VALUES) | set(
|
||||
_SYSTEMD_EXACT_MULTI_VALUES
|
||||
):
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
for key, expected in _SYSTEMD_EXACT_SINGLE_VALUES.items():
|
||||
if values.get(key) != [expected]:
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
for key, expected in _SYSTEMD_EXACT_MULTI_VALUES.items():
|
||||
observed = values.get(key, [])
|
||||
if len(observed) != len(set(observed)) or tuple(observed) != expected:
|
||||
raise PathPolicyError("isolated_writer_systemd_profile_rejected")
|
||||
@@ -0,0 +1,241 @@
|
||||
"""Digest-only, task-scoped token registry for isolated writers."""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
import os
|
||||
import grp
|
||||
import pwd
|
||||
import secrets
|
||||
import sqlite3
|
||||
import stat
|
||||
import threading
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
_REGISTRY_INIT_LOCK = threading.Lock()
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
|
||||
|
||||
|
||||
def token_digest(token: str) -> str:
|
||||
return hashlib.sha256(token.encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
class TokenRegistry:
|
||||
def __init__(self, path: Path | str):
|
||||
self.path = Path(path)
|
||||
self._prepare()
|
||||
|
||||
def _prepare(self) -> None:
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
if self.path.parent.is_symlink() or self.path.is_symlink():
|
||||
raise PermissionError("writer_token_registry_symlink_rejected")
|
||||
with _REGISTRY_INIT_LOCK:
|
||||
with self._connect() as db:
|
||||
db.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS token_grants (
|
||||
token_id TEXT PRIMARY KEY,
|
||||
token_digest TEXT NOT NULL UNIQUE,
|
||||
grant_json TEXT NOT NULL,
|
||||
revoked INTEGER NOT NULL DEFAULT 0,
|
||||
created_at TEXT NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS token_uses (
|
||||
token_id TEXT NOT NULL,
|
||||
operation TEXT NOT NULL,
|
||||
use_count INTEGER NOT NULL DEFAULT 0,
|
||||
PRIMARY KEY(token_id, operation),
|
||||
FOREIGN KEY(token_id) REFERENCES token_grants(token_id)
|
||||
);
|
||||
"""
|
||||
)
|
||||
os.chmod(self.path, 0o600)
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
db = sqlite3.connect(self.path, timeout=30, isolation_level=None)
|
||||
db.row_factory = sqlite3.Row
|
||||
db.execute("PRAGMA journal_mode=WAL")
|
||||
db.execute("PRAGMA synchronous=FULL")
|
||||
db.execute("PRAGMA foreign_keys=ON")
|
||||
return db
|
||||
|
||||
def issue(self, grant: dict[str, Any], token: str | None = None) -> tuple[str, dict[str, Any]]:
|
||||
value = token or secrets.token_urlsafe(32)
|
||||
if len(value.encode("utf-8")) < 32:
|
||||
raise ValueError("writer_token_entropy_insufficient")
|
||||
record = dict(grant)
|
||||
record["schema_version"] = 2
|
||||
record["token_digest"] = token_digest(value)
|
||||
record["revoked"] = False
|
||||
record.setdefault("created_at", utc_now())
|
||||
required = (
|
||||
"token_id",
|
||||
"audience",
|
||||
"task_id",
|
||||
"source_cidrs",
|
||||
"allowed_branch",
|
||||
"approved_base_oid",
|
||||
"allowed_operations",
|
||||
"allowed_paths",
|
||||
"not_before",
|
||||
"expires_at",
|
||||
"max_uses",
|
||||
"issued_by",
|
||||
)
|
||||
if any(not record.get(field) for field in required):
|
||||
raise ValueError("writer_token_grant_incomplete")
|
||||
encoded = json.dumps(record, sort_keys=True, separators=(",", ":"))
|
||||
with self._connect() as db:
|
||||
db.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
db.execute(
|
||||
"""
|
||||
INSERT INTO token_grants(token_id, token_digest, grant_json, revoked, created_at)
|
||||
VALUES(?,?,?,?,?)
|
||||
""",
|
||||
(
|
||||
str(record["token_id"]),
|
||||
str(record["token_digest"]),
|
||||
encoded,
|
||||
0,
|
||||
str(record["created_at"]),
|
||||
),
|
||||
)
|
||||
db.execute("COMMIT")
|
||||
except Exception:
|
||||
db.execute("ROLLBACK")
|
||||
raise
|
||||
return value, record
|
||||
|
||||
def find(self, token: str) -> dict[str, Any] | None:
|
||||
candidate = token_digest(token)
|
||||
with self._connect() as db:
|
||||
rows = db.execute(
|
||||
"SELECT token_digest, grant_json, revoked FROM token_grants"
|
||||
).fetchall()
|
||||
match = None
|
||||
for row in rows:
|
||||
if hmac.compare_digest(str(row["token_digest"]), candidate):
|
||||
match = dict(json.loads(str(row["grant_json"])))
|
||||
match["revoked"] = bool(row["revoked"])
|
||||
return match
|
||||
|
||||
def consume(self, token_id: str, operation: str, maximum: int) -> int:
|
||||
if maximum < 1:
|
||||
raise PermissionError("writer_token_operation_exhausted")
|
||||
with self._connect() as db:
|
||||
db.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
row = db.execute(
|
||||
"SELECT revoked FROM token_grants WHERE token_id=?",
|
||||
(token_id,),
|
||||
).fetchone()
|
||||
if row is None or bool(row["revoked"]):
|
||||
raise PermissionError("writer_token_revoked")
|
||||
used_row = db.execute(
|
||||
"SELECT use_count FROM token_uses WHERE token_id=? AND operation=?",
|
||||
(token_id, operation),
|
||||
).fetchone()
|
||||
used = int(used_row["use_count"]) if used_row else 0
|
||||
if used >= maximum:
|
||||
raise PermissionError("writer_token_operation_exhausted")
|
||||
current = used + 1
|
||||
db.execute(
|
||||
"""
|
||||
INSERT INTO token_uses(token_id, operation, use_count)
|
||||
VALUES(?,?,?)
|
||||
ON CONFLICT(token_id, operation)
|
||||
DO UPDATE SET use_count=excluded.use_count
|
||||
""",
|
||||
(token_id, operation, current),
|
||||
)
|
||||
db.execute("COMMIT")
|
||||
return current
|
||||
except Exception:
|
||||
db.execute("ROLLBACK")
|
||||
raise
|
||||
|
||||
def revoke(self, token_id: str) -> bool:
|
||||
with self._connect() as db:
|
||||
db.execute("BEGIN IMMEDIATE")
|
||||
changed = db.execute(
|
||||
"UPDATE token_grants SET revoked=1 WHERE token_id=? AND revoked=0",
|
||||
(token_id,),
|
||||
).rowcount
|
||||
db.execute("COMMIT")
|
||||
return bool(changed)
|
||||
|
||||
def usage(self, token_id: str, operation: str) -> int:
|
||||
with self._connect() as db:
|
||||
row = db.execute(
|
||||
"SELECT use_count FROM token_uses WHERE token_id=? AND operation=?",
|
||||
(token_id, operation),
|
||||
).fetchone()
|
||||
return int(row["use_count"]) if row else 0
|
||||
|
||||
|
||||
def _write_secret_file(
|
||||
path: Path,
|
||||
token: str,
|
||||
*,
|
||||
owner: str | None = None,
|
||||
group: str | None = None,
|
||||
) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
if path.parent.is_symlink() or path.is_symlink():
|
||||
raise PermissionError("writer_token_file_symlink_rejected")
|
||||
flags = os.O_WRONLY | os.O_CREAT | os.O_EXCL
|
||||
if hasattr(os, "O_NOFOLLOW"):
|
||||
flags |= os.O_NOFOLLOW
|
||||
fd = os.open(path, flags, 0o600)
|
||||
try:
|
||||
if not stat.S_ISREG(os.fstat(fd).st_mode):
|
||||
raise PermissionError("writer_token_file_not_regular")
|
||||
if owner is not None or group is not None:
|
||||
uid = pwd.getpwnam(owner).pw_uid if owner is not None else -1
|
||||
gid = grp.getgrnam(group).gr_gid if group is not None else -1
|
||||
os.fchown(fd, uid, gid)
|
||||
os.write(fd, token.encode("utf-8"))
|
||||
os.fsync(fd)
|
||||
finally:
|
||||
os.close(fd)
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--registry", required=True)
|
||||
sub = parser.add_subparsers(dest="command", required=True)
|
||||
issue = sub.add_parser("issue")
|
||||
issue.add_argument("--grant-file", required=True)
|
||||
issue.add_argument("--token-file", required=True)
|
||||
issue.add_argument("--owner")
|
||||
issue.add_argument("--group")
|
||||
revoke = sub.add_parser("revoke")
|
||||
revoke.add_argument("--token-id", required=True)
|
||||
args = parser.parse_args(argv)
|
||||
registry = TokenRegistry(args.registry)
|
||||
if args.command == "issue":
|
||||
grant = json.loads(Path(args.grant_file).read_text(encoding="utf-8"))
|
||||
token, record = registry.issue(grant)
|
||||
_write_secret_file(
|
||||
Path(args.token_file),
|
||||
token,
|
||||
owner=args.owner,
|
||||
group=args.group,
|
||||
)
|
||||
print(json.dumps({"token_id": record["token_id"], "created": True}, sort_keys=True))
|
||||
return 0
|
||||
changed = registry.revoke(args.token_id)
|
||||
print(json.dumps({"token_id": args.token_id, "revoked": changed}, sort_keys=True))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,611 @@
|
||||
"""Audited Owner authorization broker for task-scoped writer provisioning.
|
||||
|
||||
The broker closes the bootstrap gap without minting a new general-purpose
|
||||
Owner token and without modifying the bearer-token registry. It accepts an
|
||||
already-authenticated, explicitly allow-listed Owner principal, records a
|
||||
tamper-evident authorization event, and invokes the existing
|
||||
AuthorizedTaskWriterProvisioner with a generated authorization reference.
|
||||
|
||||
The broker never writes Git refs itself. The governed signer, validator and
|
||||
one-shot provisioner remain the only components allowed to create the task
|
||||
branch/worktree/writer.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import tempfile
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Protocol
|
||||
|
||||
from authorized_task_writer_provisioning import (
|
||||
AuthorizedTaskWriterProvisioner,
|
||||
BRANCH_RE,
|
||||
OID_RE,
|
||||
OwnerContext,
|
||||
ProvisioningError,
|
||||
REQUIRED_ALLOWED_OPERATIONS,
|
||||
REQUIRED_DENIED_OPERATIONS,
|
||||
TASK_RE,
|
||||
)
|
||||
|
||||
|
||||
ACTION = "AUTHORIZE_TASK_WRITER_PROVISIONING"
|
||||
SCHEMA = "aios.owner-authorization-event.v1"
|
||||
BROKER_REQUEST_FIELDS = frozenset(
|
||||
{
|
||||
"action",
|
||||
"task_id",
|
||||
"repository",
|
||||
"base_ref",
|
||||
"base_oid",
|
||||
"target_branch",
|
||||
"one_time_use",
|
||||
"expires_in_seconds",
|
||||
"production_change_authorized",
|
||||
"tag_change_authorized",
|
||||
"baseline_change_authorized",
|
||||
"main_write_authorized",
|
||||
"allowed_operations",
|
||||
"denied_operations",
|
||||
}
|
||||
)
|
||||
IDENTITY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._@:+/-]{1,254}$")
|
||||
SCOPE_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{1,127}$")
|
||||
CREDENTIAL_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:@+-]{1,255}$")
|
||||
WILDCARD_SCOPE_RE = re.compile(r"(^\*$)|(^.+:\*$)")
|
||||
|
||||
|
||||
class OwnerAuthorizationError(RuntimeError):
|
||||
"""Stable fail-closed broker error."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
code: str,
|
||||
status: int = 400,
|
||||
*,
|
||||
details: Mapping[str, Any] | None = None,
|
||||
) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
self.details = dict(details or {})
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OwnerPrincipal:
|
||||
"""Non-secret authentication evidence returned by the existing API."""
|
||||
|
||||
identity: str
|
||||
role: str
|
||||
authenticated_scope: str
|
||||
token_scopes: frozenset[str]
|
||||
credential_id: str = ""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OwnerAuthorizationBrokerConfig:
|
||||
repository_identity: str
|
||||
state_root: Path
|
||||
allowed_owner_identities: frozenset[str]
|
||||
allowed_intake_scopes: frozenset[str]
|
||||
allowed_credential_ids: frozenset[str] = frozenset()
|
||||
max_expiry_seconds: int = 900
|
||||
|
||||
@classmethod
|
||||
def from_environment(cls) -> "OwnerAuthorizationBrokerConfig":
|
||||
identities = _csv_set(
|
||||
os.getenv("AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_IDENTITIES", "")
|
||||
)
|
||||
scopes = _csv_set(
|
||||
os.getenv("AIOS_GITOPS_OWNER_AUTHORIZATION_INTAKE_SCOPES", "")
|
||||
)
|
||||
credential_ids = _csv_set(
|
||||
os.getenv("AIOS_GITOPS_OWNER_AUTHORIZATION_ALLOWED_CREDENTIAL_IDS", "")
|
||||
)
|
||||
if not identities:
|
||||
raise OwnerAuthorizationError(
|
||||
"OWNER_IDENTITY_ALLOWLIST_REQUIRED", 503
|
||||
)
|
||||
if not scopes:
|
||||
raise OwnerAuthorizationError(
|
||||
"OWNER_INTAKE_SCOPE_ALLOWLIST_REQUIRED", 503
|
||||
)
|
||||
if any(_is_wildcard_scope(item) for item in scopes):
|
||||
raise OwnerAuthorizationError(
|
||||
"WILDCARD_INTAKE_SCOPE_REJECTED", 503
|
||||
)
|
||||
if "writer:provision" in scopes:
|
||||
raise OwnerAuthorizationError(
|
||||
"WRITER_PROVISION_SCOPE_BOOTSTRAP_REJECTED", 503
|
||||
)
|
||||
try:
|
||||
maximum = int(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_OWNER_AUTHORIZATION_MAX_EXPIRY_SECONDS", "900"
|
||||
)
|
||||
)
|
||||
except ValueError:
|
||||
raise OwnerAuthorizationError(
|
||||
"BROKER_MAX_EXPIRY_INVALID", 503
|
||||
) from None
|
||||
if maximum < 60 or maximum > 1800:
|
||||
raise OwnerAuthorizationError("BROKER_MAX_EXPIRY_INVALID", 503)
|
||||
return cls(
|
||||
repository_identity=os.getenv(
|
||||
"AIOS_GITOPS_REPOSITORY_IDENTITY", "aios/aios"
|
||||
).strip(),
|
||||
state_root=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_OWNER_AUTHORIZATION_STATE_ROOT",
|
||||
"/var/lib/aios-gitops/owner-authorization-broker",
|
||||
)
|
||||
),
|
||||
allowed_owner_identities=identities,
|
||||
allowed_intake_scopes=scopes,
|
||||
allowed_credential_ids=credential_ids,
|
||||
max_expiry_seconds=maximum,
|
||||
)
|
||||
|
||||
|
||||
class TaskWriterProvisioner(Protocol):
|
||||
def provision(
|
||||
self, raw: Mapping[str, Any], owner: OwnerContext
|
||||
) -> dict[str, Any]:
|
||||
...
|
||||
|
||||
|
||||
def utc_now() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
|
||||
def iso_utc(value: datetime) -> str:
|
||||
return value.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def canonical_json_bytes(value: Any) -> bytes:
|
||||
return (
|
||||
json.dumps(
|
||||
value,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
)
|
||||
+ "\n"
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def sha256_json(value: Any) -> str:
|
||||
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
|
||||
|
||||
|
||||
def _csv_set(value: str) -> frozenset[str]:
|
||||
return frozenset(
|
||||
item.strip() for item in value.split(",") if item.strip()
|
||||
)
|
||||
|
||||
|
||||
def _is_wildcard_scope(scope: str) -> bool:
|
||||
return bool(WILDCARD_SCOPE_RE.fullmatch(scope.strip()))
|
||||
|
||||
|
||||
def _atomic_write_json(path: Path, value: Any, mode: int = 0o600) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
if path.parent.is_symlink() or path.is_symlink():
|
||||
raise OwnerAuthorizationError("BROKER_STATE_SYMLINK_REJECTED", 500)
|
||||
fd, temporary = tempfile.mkstemp(prefix=".tmp-", dir=path.parent)
|
||||
try:
|
||||
os.fchmod(fd, mode)
|
||||
with os.fdopen(fd, "wb", closefd=True) as stream:
|
||||
stream.write(canonical_json_bytes(value))
|
||||
stream.flush()
|
||||
os.fsync(stream.fileno())
|
||||
os.replace(temporary, path)
|
||||
os.chmod(path, mode)
|
||||
parent_fd = os.open(
|
||||
path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0)
|
||||
)
|
||||
try:
|
||||
os.fsync(parent_fd)
|
||||
finally:
|
||||
os.close(parent_fd)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
|
||||
|
||||
def _read_json(path: Path) -> dict[str, Any]:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise OwnerAuthorizationError("BROKER_RECEIPT_INVALID", 500)
|
||||
if path.stat().st_size <= 0 or path.stat().st_size > 1_048_576:
|
||||
raise OwnerAuthorizationError("BROKER_RECEIPT_INVALID", 500)
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError):
|
||||
raise OwnerAuthorizationError(
|
||||
"BROKER_RECEIPT_JSON_INVALID", 500
|
||||
) from None
|
||||
if not isinstance(value, dict):
|
||||
raise OwnerAuthorizationError("BROKER_RECEIPT_INVALID", 500)
|
||||
return value
|
||||
|
||||
|
||||
def _prepare_state_root(root: Path) -> None:
|
||||
if root.is_symlink():
|
||||
raise OwnerAuthorizationError("BROKER_STATE_SYMLINK_REJECTED", 500)
|
||||
root.mkdir(parents=True, exist_ok=True, mode=0o700)
|
||||
os.chmod(root, 0o700)
|
||||
if root.stat().st_mode & 0o077:
|
||||
raise OwnerAuthorizationError(
|
||||
"BROKER_STATE_PERMISSIONS_REJECTED", 500
|
||||
)
|
||||
|
||||
|
||||
def _event_id(
|
||||
principal: OwnerPrincipal, request_digest: str
|
||||
) -> str:
|
||||
material = (
|
||||
f"{principal.identity}\0{principal.authenticated_scope}\0"
|
||||
f"{request_digest}"
|
||||
).encode("utf-8")
|
||||
return "owner-auth-" + hashlib.sha256(material).hexdigest()[:32]
|
||||
|
||||
|
||||
def _authorization_reference(event_id: str, request_digest: str) -> str:
|
||||
return f"owner-auth:{event_id}:{request_digest[:16]}"
|
||||
|
||||
|
||||
def _validate_principal(
|
||||
principal: OwnerPrincipal,
|
||||
config: OwnerAuthorizationBrokerConfig,
|
||||
) -> None:
|
||||
if principal.role != "owner":
|
||||
raise OwnerAuthorizationError("OWNER_ROLE_REQUIRED", 403)
|
||||
if (
|
||||
not principal.identity
|
||||
or not IDENTITY_RE.fullmatch(principal.identity)
|
||||
or principal.identity not in config.allowed_owner_identities
|
||||
):
|
||||
raise OwnerAuthorizationError("OWNER_IDENTITY_NOT_ALLOWED", 403)
|
||||
if (
|
||||
not principal.authenticated_scope
|
||||
or not SCOPE_RE.fullmatch(principal.authenticated_scope)
|
||||
or principal.authenticated_scope
|
||||
not in config.allowed_intake_scopes
|
||||
):
|
||||
raise OwnerAuthorizationError("OWNER_INTAKE_SCOPE_REJECTED", 403)
|
||||
if principal.authenticated_scope == "writer:provision":
|
||||
raise OwnerAuthorizationError(
|
||||
"WRITER_PROVISION_SCOPE_BOOTSTRAP_REJECTED", 403
|
||||
)
|
||||
|
||||
scopes = principal.token_scopes
|
||||
if any(_is_wildcard_scope(scope) for scope in scopes):
|
||||
raise OwnerAuthorizationError(
|
||||
"WILDCARD_OWNER_CREDENTIAL_REJECTED", 403
|
||||
)
|
||||
if scopes:
|
||||
if principal.authenticated_scope not in scopes:
|
||||
raise OwnerAuthorizationError(
|
||||
"OWNER_SCOPE_EVIDENCE_MISMATCH", 403
|
||||
)
|
||||
elif (
|
||||
not principal.credential_id
|
||||
or principal.credential_id not in config.allowed_credential_ids
|
||||
):
|
||||
# handler.need(scope) proves authorization but may hide whether the
|
||||
# credential was wildcard. When scope metadata is absent, require an
|
||||
# exact non-secret credential ID allowlist as the alternative proof.
|
||||
raise OwnerAuthorizationError(
|
||||
"OWNER_CREDENTIAL_SCOPE_NOT_PROVABLE", 403
|
||||
)
|
||||
if principal.credential_id:
|
||||
if not CREDENTIAL_ID_RE.fullmatch(principal.credential_id):
|
||||
raise OwnerAuthorizationError("OWNER_CREDENTIAL_ID_INVALID", 403)
|
||||
if (
|
||||
config.allowed_credential_ids
|
||||
and principal.credential_id not in config.allowed_credential_ids
|
||||
):
|
||||
raise OwnerAuthorizationError(
|
||||
"OWNER_CREDENTIAL_ID_NOT_ALLOWED", 403
|
||||
)
|
||||
|
||||
|
||||
def _validate_request(
|
||||
raw: Mapping[str, Any],
|
||||
config: OwnerAuthorizationBrokerConfig,
|
||||
) -> dict[str, Any]:
|
||||
if set(raw) != BROKER_REQUEST_FIELDS:
|
||||
raise OwnerAuthorizationError("BROKER_REQUEST_FIELDS_REJECTED")
|
||||
if raw["action"] != ACTION:
|
||||
raise OwnerAuthorizationError("BROKER_ACTION_REJECTED")
|
||||
if raw["repository"] != config.repository_identity:
|
||||
raise OwnerAuthorizationError(
|
||||
"REPOSITORY_IDENTITY_MISMATCH", 409
|
||||
)
|
||||
if raw["base_ref"] != "refs/heads/main":
|
||||
raise OwnerAuthorizationError("BASE_REF_REJECTED", 409)
|
||||
if (
|
||||
not isinstance(raw["base_oid"], str)
|
||||
or not OID_RE.fullmatch(raw["base_oid"])
|
||||
):
|
||||
raise OwnerAuthorizationError("BASE_OID_REJECTED")
|
||||
if (
|
||||
not isinstance(raw["target_branch"], str)
|
||||
or not BRANCH_RE.fullmatch(raw["target_branch"])
|
||||
or raw["target_branch"] in {"main", "master"}
|
||||
):
|
||||
raise OwnerAuthorizationError("TARGET_BRANCH_REJECTED")
|
||||
if (
|
||||
not isinstance(raw["task_id"], str)
|
||||
or not TASK_RE.fullmatch(raw["task_id"])
|
||||
):
|
||||
raise OwnerAuthorizationError("TASK_ID_REJECTED")
|
||||
if raw["one_time_use"] is not True:
|
||||
raise OwnerAuthorizationError("ONE_TIME_USE_REQUIRED")
|
||||
expiry = raw["expires_in_seconds"]
|
||||
if (
|
||||
not isinstance(expiry, int)
|
||||
or isinstance(expiry, bool)
|
||||
or not 60 <= expiry <= config.max_expiry_seconds
|
||||
):
|
||||
raise OwnerAuthorizationError("GRANT_LIFETIME_REJECTED")
|
||||
for field in (
|
||||
"production_change_authorized",
|
||||
"tag_change_authorized",
|
||||
"baseline_change_authorized",
|
||||
"main_write_authorized",
|
||||
):
|
||||
if raw[field] is not False:
|
||||
raise OwnerAuthorizationError(
|
||||
"PRODUCTION_CAPABILITY_REJECTED", 403
|
||||
)
|
||||
allowed = raw["allowed_operations"]
|
||||
denied = raw["denied_operations"]
|
||||
if (
|
||||
not isinstance(allowed, list)
|
||||
or frozenset(allowed) != REQUIRED_ALLOWED_OPERATIONS
|
||||
):
|
||||
raise OwnerAuthorizationError("ALLOWED_OPERATIONS_MISMATCH", 403)
|
||||
if (
|
||||
not isinstance(denied, list)
|
||||
or frozenset(denied) != REQUIRED_DENIED_OPERATIONS
|
||||
):
|
||||
raise OwnerAuthorizationError("DENIED_OPERATIONS_MISMATCH", 403)
|
||||
return dict(raw)
|
||||
|
||||
|
||||
def _response_is_safe(value: Any) -> bool:
|
||||
"""Reject accidental credential material before writing a receipt."""
|
||||
|
||||
sensitive_markers = (
|
||||
"access_token",
|
||||
"bearer",
|
||||
"client_secret",
|
||||
"private_key",
|
||||
"raw_token",
|
||||
"secret_value",
|
||||
)
|
||||
if isinstance(value, Mapping):
|
||||
for key, inner in value.items():
|
||||
lowered = str(key).lower()
|
||||
if any(marker in lowered for marker in sensitive_markers):
|
||||
return False
|
||||
if not _response_is_safe(inner):
|
||||
return False
|
||||
elif isinstance(value, list):
|
||||
return all(_response_is_safe(item) for item in value)
|
||||
return True
|
||||
|
||||
|
||||
class OwnerAuthorizationBroker:
|
||||
"""Create an audited Owner event and invoke the governed bridge."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: OwnerAuthorizationBrokerConfig | None = None,
|
||||
provisioner: TaskWriterProvisioner | None = None,
|
||||
) -> None:
|
||||
self.config = (
|
||||
config or OwnerAuthorizationBrokerConfig.from_environment()
|
||||
)
|
||||
self.provisioner = provisioner or AuthorizedTaskWriterProvisioner()
|
||||
|
||||
def authorize_and_provision(
|
||||
self,
|
||||
raw: Mapping[str, Any],
|
||||
principal: OwnerPrincipal,
|
||||
) -> dict[str, Any]:
|
||||
config = self.config
|
||||
_validate_principal(principal, config)
|
||||
request = _validate_request(raw, config)
|
||||
_prepare_state_root(config.state_root)
|
||||
|
||||
request_digest = sha256_json(request)
|
||||
event_id = _event_id(principal, request_digest)
|
||||
reference = _authorization_reference(event_id, request_digest)
|
||||
event_dir = config.state_root / "events" / event_id
|
||||
event_dir.mkdir(parents=True, exist_ok=True, mode=0o700)
|
||||
os.chmod(event_dir, 0o700)
|
||||
|
||||
lock_path = event_dir / "event.lock"
|
||||
lock_path.touch(mode=0o600, exist_ok=True)
|
||||
os.chmod(lock_path, 0o600)
|
||||
with lock_path.open("r+b") as lock:
|
||||
fcntl.flock(lock.fileno(), fcntl.LOCK_EX)
|
||||
response_path = event_dir / "response.json"
|
||||
event_path = event_dir / "event.json"
|
||||
|
||||
if response_path.exists():
|
||||
response = _read_json(response_path)
|
||||
response["owner_authorization_idempotent"] = True
|
||||
return response
|
||||
|
||||
issued_at = utc_now()
|
||||
expires_at = issued_at + timedelta(
|
||||
seconds=int(request["expires_in_seconds"])
|
||||
)
|
||||
event: dict[str, Any] = {
|
||||
"schema": SCHEMA,
|
||||
"event_id": event_id,
|
||||
"authorization_reference": reference,
|
||||
"status": "AUTHORIZED",
|
||||
"owner": {
|
||||
"identity": principal.identity,
|
||||
"role": principal.role,
|
||||
"authenticated_scope": principal.authenticated_scope,
|
||||
"credential_id": principal.credential_id or None,
|
||||
"token_scope_digest_sha256": sha256_json(
|
||||
sorted(principal.token_scopes)
|
||||
),
|
||||
"wildcard_scope_used": False,
|
||||
},
|
||||
"request": {
|
||||
"task_id": request["task_id"],
|
||||
"repository": request["repository"],
|
||||
"base_ref": request["base_ref"],
|
||||
"base_oid": request["base_oid"],
|
||||
"target_branch": request["target_branch"],
|
||||
"one_time_use": True,
|
||||
"production_change_authorized": False,
|
||||
"tag_change_authorized": False,
|
||||
"baseline_change_authorized": False,
|
||||
"main_write_authorized": False,
|
||||
"allowed_operations": sorted(
|
||||
REQUIRED_ALLOWED_OPERATIONS
|
||||
),
|
||||
"denied_operations": sorted(
|
||||
REQUIRED_DENIED_OPERATIONS
|
||||
),
|
||||
},
|
||||
"request_digest_sha256": request_digest,
|
||||
"issued_at": iso_utc(issued_at),
|
||||
"expires_at": iso_utc(expires_at),
|
||||
}
|
||||
event["event_digest_sha256"] = sha256_json(event)
|
||||
_atomic_write_json(event_path, event)
|
||||
|
||||
bridge_request = dict(request)
|
||||
bridge_request.pop("action")
|
||||
bridge_request["owner_authorization_reference"] = reference
|
||||
try:
|
||||
result = self.provisioner.provision(
|
||||
bridge_request,
|
||||
OwnerContext(
|
||||
identity=principal.identity,
|
||||
role=principal.role,
|
||||
authorization_reference=reference,
|
||||
),
|
||||
)
|
||||
if not isinstance(result, dict):
|
||||
raise OwnerAuthorizationError(
|
||||
"PROVISIONER_RESPONSE_INVALID", 502
|
||||
)
|
||||
if result.get("status") != "READY_FOR_CODE_AUTHORING":
|
||||
raise OwnerAuthorizationError(
|
||||
"PROVISIONER_NOT_READY",
|
||||
409,
|
||||
details={"status": result.get("status")},
|
||||
)
|
||||
if not _response_is_safe(result):
|
||||
raise OwnerAuthorizationError(
|
||||
"PROVISIONER_RESPONSE_CONTAINS_SENSITIVE_DATA", 500
|
||||
)
|
||||
except ProvisioningError as exc:
|
||||
event.update(
|
||||
{
|
||||
"status": "PROVISIONING_BLOCKED",
|
||||
"failed_at": iso_utc(utc_now()),
|
||||
"error": exc.code,
|
||||
"error_status": exc.status,
|
||||
}
|
||||
)
|
||||
event["event_digest_sha256"] = sha256_json(
|
||||
{
|
||||
key: value
|
||||
for key, value in event.items()
|
||||
if key != "event_digest_sha256"
|
||||
}
|
||||
)
|
||||
_atomic_write_json(event_path, event)
|
||||
raise
|
||||
except OwnerAuthorizationError as exc:
|
||||
event.update(
|
||||
{
|
||||
"status": "PROVISIONING_BLOCKED",
|
||||
"failed_at": iso_utc(utc_now()),
|
||||
"error": exc.code,
|
||||
"error_status": exc.status,
|
||||
}
|
||||
)
|
||||
event["event_digest_sha256"] = sha256_json(
|
||||
{
|
||||
key: value
|
||||
for key, value in event.items()
|
||||
if key != "event_digest_sha256"
|
||||
}
|
||||
)
|
||||
_atomic_write_json(event_path, event)
|
||||
raise
|
||||
except Exception as exc:
|
||||
event.update(
|
||||
{
|
||||
"status": "PROVISIONING_FAILED",
|
||||
"failed_at": iso_utc(utc_now()),
|
||||
"error": "OWNER_AUTHORIZATION_BROKER_INTERNAL_ERROR",
|
||||
}
|
||||
)
|
||||
event["event_digest_sha256"] = sha256_json(
|
||||
{
|
||||
key: value
|
||||
for key, value in event.items()
|
||||
if key != "event_digest_sha256"
|
||||
}
|
||||
)
|
||||
_atomic_write_json(event_path, event)
|
||||
raise OwnerAuthorizationError(
|
||||
"OWNER_AUTHORIZATION_BROKER_INTERNAL_ERROR", 500
|
||||
) from exc
|
||||
|
||||
completed_at = utc_now()
|
||||
event.update(
|
||||
{
|
||||
"status": "CONSUMED",
|
||||
"consumed_at": iso_utc(completed_at),
|
||||
"approval_plan_id": result.get("approval_plan_id"),
|
||||
"grant_id": result.get("grant_id"),
|
||||
"grant_digest_sha256": result.get(
|
||||
"grant_digest_sha256"
|
||||
),
|
||||
"branch_oid": result.get("branch_oid"),
|
||||
"grant_consumed": result.get("grant_consumed") is True,
|
||||
}
|
||||
)
|
||||
event["event_digest_sha256"] = sha256_json(
|
||||
{
|
||||
key: value
|
||||
for key, value in event.items()
|
||||
if key != "event_digest_sha256"
|
||||
}
|
||||
)
|
||||
_atomic_write_json(event_path, event)
|
||||
|
||||
response = dict(result)
|
||||
response.update(
|
||||
{
|
||||
"owner_authorization_event_id": event_id,
|
||||
"owner_authorization_reference": reference,
|
||||
"owner_authorization_digest_sha256": event[
|
||||
"event_digest_sha256"
|
||||
],
|
||||
"owner_authorization_consumed": True,
|
||||
"owner_authorization_idempotent": False,
|
||||
}
|
||||
)
|
||||
_atomic_write_json(response_path, response)
|
||||
return response
|
||||
@@ -0,0 +1,32 @@
|
||||
"""Read-only release reconciliation and durable follow-up intent."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Any, Mapping
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ReconciliationReport:
|
||||
healthy: bool
|
||||
drift: tuple[str, ...]
|
||||
actions: tuple[str, ...]
|
||||
|
||||
|
||||
class ReconciliationController:
|
||||
CHECKS = (
|
||||
("authority_main", "gitea_main", "main_drift"),
|
||||
("local_tag_oid", "remote_tag_oid", "tag_drift"),
|
||||
("remote_peeled_target", "approved_target_oid", "peeled_target_drift"),
|
||||
("registry_version", "baseline_version", "registry_baseline_drift"),
|
||||
("approved_artifact_digest", "deployed_artifact_digest", "artifact_drift"),
|
||||
("declared_production_state", "service_healthy", "service_health_drift"),
|
||||
)
|
||||
|
||||
def reconcile(self, actual: Mapping[str, Any]) -> ReconciliationReport:
|
||||
drift: list[str] = []
|
||||
for left, right, label in self.CHECKS:
|
||||
if actual.get(left) != actual.get(right):
|
||||
drift.append(label)
|
||||
actions = () if not drift else ("open_reconciliation_task", "open_reconciliation_pr", "attach_evidence", "notify_owner")
|
||||
return ReconciliationReport(not drift, tuple(drift), actions)
|
||||
|
||||
@@ -0,0 +1,65 @@
|
||||
"""Durable-friendly recurring task scheduling primitives."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from typing import Any
|
||||
|
||||
|
||||
class RecurringTaskError(ValueError):
|
||||
pass
|
||||
|
||||
|
||||
@dataclass
|
||||
class RecurringTask:
|
||||
task_id: str
|
||||
interval_seconds: int
|
||||
next_run_at: datetime
|
||||
run_count: int = 0
|
||||
max_runs: int | None = None
|
||||
cancelled: bool = False
|
||||
|
||||
def due(self, now: datetime) -> bool:
|
||||
return not self.cancelled and (self.max_runs is None or self.run_count < self.max_runs) and now >= self.next_run_at
|
||||
|
||||
|
||||
class RecurringTaskScheduler:
|
||||
def __init__(self) -> None:
|
||||
self.tasks: dict[str, RecurringTask] = {}
|
||||
self.successors: set[str] = set()
|
||||
|
||||
def schedule(self, task_id: str, interval_seconds: int, *, now: datetime | None = None, max_runs: int | None = None) -> RecurringTask:
|
||||
if task_id in self.tasks:
|
||||
raise RecurringTaskError("task already exists")
|
||||
if interval_seconds <= 0 or (max_runs is not None and max_runs <= 0):
|
||||
raise RecurringTaskError("invalid recurring task bounds")
|
||||
now = now or datetime.now(timezone.utc)
|
||||
task = RecurringTask(task_id, interval_seconds, now, 0, max_runs, False)
|
||||
self.tasks[task_id] = task
|
||||
return task
|
||||
|
||||
def due(self, *, now: datetime | None = None) -> list[RecurringTask]:
|
||||
now = now or datetime.now(timezone.utc)
|
||||
return [task for task in self.tasks.values() if task.due(now)]
|
||||
|
||||
def mark_run(self, task_id: str, *, now: datetime | None = None) -> RecurringTask:
|
||||
task = self.tasks[task_id]
|
||||
now = now or datetime.now(timezone.utc)
|
||||
if not task.due(now):
|
||||
raise RecurringTaskError("task is not due")
|
||||
task.run_count += 1
|
||||
task.next_run_at = now + timedelta(seconds=task.interval_seconds)
|
||||
return task
|
||||
|
||||
def cancel(self, task_id: str) -> None:
|
||||
self.tasks[task_id].cancelled = True
|
||||
|
||||
def create_successor_once(self, predecessor: str, successor: str, *, interval_seconds: int, now: datetime | None = None) -> RecurringTask:
|
||||
key = f"{predecessor}->{successor}"
|
||||
if key in self.successors:
|
||||
return self.tasks[successor]
|
||||
self.successors.add(key)
|
||||
if successor not in self.tasks:
|
||||
return self.schedule(successor, interval_seconds, now=now)
|
||||
return self.tasks[successor]
|
||||
|
||||
@@ -0,0 +1,53 @@
|
||||
"""Release state machine with explicit fail-closed production gates."""
|
||||
from __future__ import annotations
|
||||
|
||||
from enum import Enum
|
||||
from typing import Mapping
|
||||
|
||||
|
||||
class InvalidTransition(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
class ReleaseState(str, Enum):
|
||||
SOURCE_READY = "SOURCE_READY"
|
||||
TESTED = "TESTED"
|
||||
PR_OPEN = "PR_OPEN"
|
||||
PR_APPROVED = "PR_APPROVED"
|
||||
MERGED = "MERGED"
|
||||
ARTIFACT_VERIFIED = "ARTIFACT_VERIFIED"
|
||||
RELEASE_APPROVED = "RELEASE_APPROVED"
|
||||
TAG_VERIFIED = "TAG_VERIFIED"
|
||||
DEPLOYED = "DEPLOYED"
|
||||
PRODUCTION_ACCEPTED = "PRODUCTION_ACCEPTED"
|
||||
|
||||
|
||||
TRANSITIONS = {
|
||||
ReleaseState.SOURCE_READY: (ReleaseState.TESTED,),
|
||||
ReleaseState.TESTED: (ReleaseState.PR_OPEN,),
|
||||
ReleaseState.PR_OPEN: (ReleaseState.PR_APPROVED,),
|
||||
ReleaseState.PR_APPROVED: (ReleaseState.MERGED,),
|
||||
ReleaseState.MERGED: (ReleaseState.ARTIFACT_VERIFIED,),
|
||||
ReleaseState.ARTIFACT_VERIFIED: (ReleaseState.RELEASE_APPROVED,),
|
||||
ReleaseState.RELEASE_APPROVED: (ReleaseState.TAG_VERIFIED,),
|
||||
ReleaseState.TAG_VERIFIED: (ReleaseState.DEPLOYED,),
|
||||
ReleaseState.DEPLOYED: (ReleaseState.PRODUCTION_ACCEPTED,),
|
||||
}
|
||||
|
||||
|
||||
class ReleaseStateMachine:
|
||||
def __init__(self, state: ReleaseState = ReleaseState.SOURCE_READY) -> None:
|
||||
self.state = state
|
||||
|
||||
def transition(self, target: ReleaseState, evidence: Mapping[str, object] | None = None) -> ReleaseState:
|
||||
if target not in TRANSITIONS.get(self.state, ()):
|
||||
raise InvalidTransition(f"{self.state.value}_to_{target.value}_denied")
|
||||
evidence = evidence or {}
|
||||
if target is ReleaseState.PRODUCTION_ACCEPTED:
|
||||
if evidence.get("tag_verified") is not True or evidence.get("remote_tag_readback") is not True or evidence.get("service_health") is not True:
|
||||
raise InvalidTransition("production_acceptance_evidence_incomplete")
|
||||
if target is ReleaseState.DEPLOYED and evidence.get("artifact_verified") is not True:
|
||||
raise InvalidTransition("deployment_artifact_not_verified")
|
||||
self.state = target
|
||||
return self.state
|
||||
|
||||
@@ -0,0 +1,520 @@
|
||||
"""Compatibility adapter for the deployed signer and validator contracts.
|
||||
|
||||
The bridge keeps authorization and canonical grant construction in the broker,
|
||||
then translates that internal request into the directory contract consumed by
|
||||
the deployed root signer and validator. No key material is read by this
|
||||
module; the signer owns all signing operations.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
|
||||
_SIGNER_FLAGS = (
|
||||
"--namespace",
|
||||
"--input",
|
||||
"--signature-out",
|
||||
"--key-id-out",
|
||||
)
|
||||
|
||||
|
||||
class SignerContractError(RuntimeError):
|
||||
"""Raised when the deployed contract cannot be normalized safely."""
|
||||
|
||||
|
||||
def canonical_json_bytes(value: Any) -> bytes:
|
||||
return (
|
||||
json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
|
||||
+ "\n"
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def sha256_json(value: Any) -> str:
|
||||
return hashlib.sha256(canonical_json_bytes(value)).hexdigest()
|
||||
|
||||
|
||||
def resolve_ref_oid(git_dir: str | Path, ref: str) -> str:
|
||||
"""Resolve an authoritative commit ref to a full 40-character OID."""
|
||||
if not isinstance(ref, str) or not re.fullmatch(r"refs/[A-Za-z0-9._/-]+", ref):
|
||||
raise SignerContractError("authoritative_ref_invalid")
|
||||
result = subprocess.run(
|
||||
[
|
||||
"git",
|
||||
"--git-dir",
|
||||
str(git_dir),
|
||||
"rev-parse",
|
||||
"--verify",
|
||||
f"{ref}^{{commit}}",
|
||||
],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=15,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
raise SignerContractError("authoritative_ref_unavailable")
|
||||
oid = result.stdout.strip().lower()
|
||||
if not re.fullmatch(r"[0-9a-f]{40}", oid):
|
||||
raise SignerContractError("authoritative_ref_invalid_oid")
|
||||
return oid
|
||||
|
||||
|
||||
def _read(path: Path) -> dict[str, Any]:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise SignerContractError("contract_input_missing")
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
|
||||
raise SignerContractError("contract_input_invalid") from exc
|
||||
if not isinstance(value, dict):
|
||||
raise SignerContractError("contract_object_required")
|
||||
return value
|
||||
|
||||
|
||||
def _write(path: Path, value: Any) -> None:
|
||||
if path.is_symlink():
|
||||
raise SignerContractError("contract_output_symlink")
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
temporary = path.with_name(path.name + ".tmp")
|
||||
temporary.write_bytes(canonical_json_bytes(value))
|
||||
os.chmod(temporary, 0o600)
|
||||
os.replace(temporary, path)
|
||||
os.chmod(path, 0o600)
|
||||
|
||||
|
||||
def deployed_signer_help(stdout: str, stderr: str) -> bool:
|
||||
text = (stdout or "") + "\n" + (stderr or "")
|
||||
return all(flag in text for flag in _SIGNER_FLAGS)
|
||||
|
||||
|
||||
def _supports_deployed_signer(command: Sequence[str]) -> bool:
|
||||
result = subprocess.run(
|
||||
[*command, "sign", "--help"],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=15,
|
||||
)
|
||||
return deployed_signer_help(result.stdout, result.stderr)
|
||||
|
||||
|
||||
def _run(
|
||||
argv: Sequence[str],
|
||||
*,
|
||||
env: Mapping[str, str] | None = None,
|
||||
timeout: int = 60,
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
result = subprocess.run(
|
||||
list(argv),
|
||||
text=True,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=timeout,
|
||||
env=dict(env) if env is not None else None,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
raise SignerContractError(
|
||||
f"deployed_tool_failed:{Path(argv[0]).name}:{result.returncode}"
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def _sign(
|
||||
command: Sequence[str],
|
||||
namespace: str,
|
||||
input_path: Path,
|
||||
signature_path: Path,
|
||||
key_id_path: Path,
|
||||
) -> None:
|
||||
if signature_path.exists() or key_id_path.exists():
|
||||
raise SignerContractError("contract_output_exists")
|
||||
_run(
|
||||
[
|
||||
*command,
|
||||
"sign",
|
||||
"--namespace",
|
||||
namespace,
|
||||
"--input",
|
||||
str(input_path),
|
||||
"--signature-out",
|
||||
str(signature_path),
|
||||
"--key-id-out",
|
||||
str(key_id_path),
|
||||
],
|
||||
timeout=60,
|
||||
)
|
||||
if not signature_path.is_file() or not key_id_path.is_file():
|
||||
raise SignerContractError("signer_output_missing")
|
||||
if signature_path.stat().st_size <= 0 or key_id_path.stat().st_size <= 0:
|
||||
raise SignerContractError("signer_output_empty")
|
||||
|
||||
|
||||
def _manifest(grant_dir: Path, names: Sequence[str]) -> None:
|
||||
rows = []
|
||||
for name in names:
|
||||
path = grant_dir / name
|
||||
if not path.is_file() or path.is_symlink():
|
||||
raise SignerContractError("manifest_input_missing")
|
||||
rows.append(
|
||||
f"{hashlib.sha256(path.read_bytes()).hexdigest()} {name}"
|
||||
)
|
||||
(grant_dir / "MANIFEST.sha256").write_text(
|
||||
"\n".join(rows) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
os.chmod(grant_dir / "MANIFEST.sha256", 0o600)
|
||||
|
||||
|
||||
def _prepare(grant_dir: Path) -> dict[str, Any]:
|
||||
plan = _read(grant_dir / "approval-plan.json")
|
||||
request = _read(grant_dir / "grant-request.json")
|
||||
base = request.get("base")
|
||||
target = request.get("target")
|
||||
owner = request.get("owner_authorization")
|
||||
authorization = request.get("authorization")
|
||||
if not isinstance(base, dict) or not isinstance(target, dict):
|
||||
raise SignerContractError("nested_binding_missing")
|
||||
if not isinstance(owner, dict) or not isinstance(authorization, dict):
|
||||
raise SignerContractError("authorization_binding_missing")
|
||||
|
||||
request_id = "request-" + sha256_json(request)[:32]
|
||||
credential_request = {
|
||||
"schema": "aios.credential-request.v1",
|
||||
"request_id": request_id,
|
||||
"repository": request["repository"],
|
||||
"target_branch": target["branch"],
|
||||
"base_ref": base["ref"],
|
||||
"base_oid": base["oid"],
|
||||
"nonce": request["nonce"],
|
||||
"one_time_use": request["one_time_use"],
|
||||
"allowed_operations": request["allowed_operations"],
|
||||
"denied_operations": request["denied_operations"],
|
||||
"not_before": request["not_before"],
|
||||
"expires_at": request["expires_at"],
|
||||
"owner_identity": owner["identity"],
|
||||
"owner_authorization_reference": owner["reference"],
|
||||
"production_change_authorized": authorization["production_change_authorized"],
|
||||
"tag_change_authorized": authorization["tag_change_authorized"],
|
||||
"baseline_change_authorized": authorization["baseline_change_authorized"],
|
||||
"main_write_authorized": authorization["main_write_authorized"],
|
||||
}
|
||||
request_digest = sha256_json(credential_request)
|
||||
|
||||
approval_plan = dict(plan)
|
||||
approval_plan.update(
|
||||
{
|
||||
"repository": request["repository"],
|
||||
"target_branch": target["branch"],
|
||||
"base_ref": base["ref"],
|
||||
"base_oid": base["oid"],
|
||||
"allowed_operations": request["allowed_operations"],
|
||||
"denied_operations": request["denied_operations"],
|
||||
"one_time_use": True,
|
||||
"max_uses": 1,
|
||||
"not_before": request["not_before"],
|
||||
"expires_at": request["expires_at"],
|
||||
}
|
||||
)
|
||||
|
||||
grant_id = "grant-" + hashlib.sha256(
|
||||
(request_id + "\0" + request["nonce"]).encode("utf-8")
|
||||
).hexdigest()[:32]
|
||||
grant_payload = {
|
||||
"schema": "aios.grant-payload.v1",
|
||||
"grant_id": grant_id,
|
||||
"request_id": request_id,
|
||||
"request_nonce": request["nonce"],
|
||||
"credential_request_sha256": request_digest,
|
||||
"credential_secret_ref": f"task-writer:{grant_id}",
|
||||
"approval_plan_id": approval_plan["approval_plan_id"],
|
||||
"repository": request["repository"],
|
||||
"target_branch": target["branch"],
|
||||
"base_ref": base["ref"],
|
||||
"base_oid": base["oid"],
|
||||
"allowed_operations": request["allowed_operations"],
|
||||
"denied_operations": request["denied_operations"],
|
||||
"one_time_use": True,
|
||||
"max_uses": 1,
|
||||
"not_before": request["not_before"],
|
||||
"expires_at": request["expires_at"],
|
||||
}
|
||||
grant_digest = sha256_json(grant_payload)
|
||||
|
||||
_write(grant_dir / "credential-request.json", credential_request)
|
||||
(grant_dir / "credential-request.canonical.json").write_bytes(
|
||||
canonical_json_bytes(credential_request)
|
||||
)
|
||||
os.chmod(grant_dir / "credential-request.canonical.json", 0o600)
|
||||
_write(grant_dir / "approval-plan.json", approval_plan)
|
||||
(grant_dir / "approval-plan.canonical.json").write_bytes(
|
||||
canonical_json_bytes(approval_plan)
|
||||
)
|
||||
os.chmod(grant_dir / "approval-plan.canonical.json", 0o600)
|
||||
_write(grant_dir / "grant-payload.json", grant_payload)
|
||||
(grant_dir / "grant-payload.canonical.json").write_bytes(
|
||||
canonical_json_bytes(grant_payload)
|
||||
)
|
||||
os.chmod(grant_dir / "grant-payload.canonical.json", 0o600)
|
||||
_write(
|
||||
grant_dir / "signed-grant.json",
|
||||
{
|
||||
"schema": "aios.signed-grant.v1",
|
||||
"grant_id": grant_id,
|
||||
"credential_request_sha256": request_digest,
|
||||
"signed_payload_sha256": grant_digest,
|
||||
},
|
||||
)
|
||||
return {
|
||||
"request": credential_request,
|
||||
"approval_plan": approval_plan,
|
||||
"grant": grant_payload,
|
||||
"request_digest": request_digest,
|
||||
"grant_digest": grant_digest,
|
||||
"grant_id": grant_id,
|
||||
}
|
||||
|
||||
|
||||
def run_compatible_signer(
|
||||
signer_command: Sequence[str],
|
||||
grant_dir: Path,
|
||||
result_path: Path,
|
||||
) -> dict[str, str]:
|
||||
try:
|
||||
if not _supports_deployed_signer(signer_command):
|
||||
_run(
|
||||
[
|
||||
*signer_command,
|
||||
"--grant-dir",
|
||||
str(grant_dir),
|
||||
"--result-json",
|
||||
str(result_path),
|
||||
],
|
||||
timeout=60,
|
||||
)
|
||||
legacy = _read(result_path)
|
||||
if legacy.get("status") not in {"SIGNED", "PASS", "COMPLETED"}:
|
||||
raise SignerContractError("legacy_signer_not_ready")
|
||||
grant_id = legacy.get("grant_id")
|
||||
digest = legacy.get("grant_digest_sha256")
|
||||
signer = legacy.get("signing_key_identity") or legacy.get(
|
||||
"signer_identity"
|
||||
)
|
||||
if not all(
|
||||
isinstance(value, str) and value.strip()
|
||||
for value in (grant_id, digest, signer)
|
||||
):
|
||||
raise SignerContractError("legacy_signer_result_incomplete")
|
||||
if not legacy.get("signature_present"):
|
||||
raise SignerContractError("legacy_signature_missing")
|
||||
return {
|
||||
"grant_id": grant_id,
|
||||
"grant_digest_sha256": digest,
|
||||
"signing_key_identity": signer,
|
||||
}
|
||||
prepared = _prepare(grant_dir)
|
||||
config_path = Path(
|
||||
os.environ.get("AIOS_GRANT_ROOT_CONFIG", "/etc/aios/grant-root/config.json")
|
||||
)
|
||||
config = _read(config_path)
|
||||
grant_namespace = str(config["grant_namespace"])
|
||||
approval_namespace = str(config["approval_namespace"])
|
||||
_sign(
|
||||
signer_command,
|
||||
approval_namespace,
|
||||
grant_dir / "approval-plan.canonical.json",
|
||||
grant_dir / "approval-plan.sig",
|
||||
grant_dir / "approval-plan.key-id",
|
||||
)
|
||||
_sign(
|
||||
signer_command,
|
||||
grant_namespace,
|
||||
grant_dir / "grant-payload.canonical.json",
|
||||
grant_dir / "signed-grant.sig",
|
||||
grant_dir / "signed-grant.key-id",
|
||||
)
|
||||
key_identity = (
|
||||
grant_dir / "signed-grant.key-id"
|
||||
).read_text(encoding="utf-8").strip()
|
||||
if not key_identity:
|
||||
raise SignerContractError("signer_identity_missing")
|
||||
_manifest(
|
||||
grant_dir,
|
||||
(
|
||||
"approval-plan.json",
|
||||
"approval-plan.canonical.json",
|
||||
"approval-plan.sig",
|
||||
"approval-plan.key-id",
|
||||
"credential-request.json",
|
||||
"credential-request.canonical.json",
|
||||
"grant-payload.json",
|
||||
"grant-payload.canonical.json",
|
||||
"signed-grant.json",
|
||||
"signed-grant.sig",
|
||||
"signed-grant.key-id",
|
||||
),
|
||||
)
|
||||
result = {
|
||||
"schema": "aios.compatible-signer-result.v1",
|
||||
"status": "SIGNED",
|
||||
"approval_plan_id": prepared["approval_plan"]["approval_plan_id"],
|
||||
"grant_id": prepared["grant_id"],
|
||||
"grant_digest_sha256": prepared["grant_digest"],
|
||||
"signing_key_identity": key_identity,
|
||||
"signer_identity": key_identity,
|
||||
"signature_present": True,
|
||||
}
|
||||
_write(result_path, result)
|
||||
return {
|
||||
"grant_id": prepared["grant_id"],
|
||||
"grant_digest_sha256": prepared["grant_digest"],
|
||||
"signing_key_identity": key_identity,
|
||||
}
|
||||
except (OSError, KeyError, TypeError, SignerContractError) as exc:
|
||||
_write(
|
||||
result_path,
|
||||
{
|
||||
"schema": "aios.compatible-signer-result.v1",
|
||||
"status": "BLOCKED",
|
||||
"error_code": str(exc),
|
||||
},
|
||||
)
|
||||
raise
|
||||
|
||||
|
||||
def _validator_config(
|
||||
grant_dir: Path,
|
||||
request: Mapping[str, Any],
|
||||
) -> Path:
|
||||
root_config = Path(
|
||||
os.environ.get("AIOS_GRANT_ROOT_CONFIG", "/etc/aios/grant-root/config.json")
|
||||
)
|
||||
config = _read(root_config)
|
||||
repo_path = (
|
||||
os.environ.get("AIOS_GITOPS_VALIDATOR_REPO_PATH")
|
||||
or os.environ.get("AIOS_GITOPS_WORKSPACE")
|
||||
or config.get("repo_path")
|
||||
)
|
||||
config.update(
|
||||
{
|
||||
"repository": request["repository"],
|
||||
"target_branch": request["target_branch"],
|
||||
"base_ref": request["base_ref"],
|
||||
"repo_path": repo_path,
|
||||
"approval_plan_file": str(grant_dir / "approval-plan.json"),
|
||||
"approval_plan_canonical_file": str(
|
||||
grant_dir / "approval-plan.canonical.json"
|
||||
),
|
||||
"approval_plan_signature_file": str(grant_dir / "approval-plan.sig"),
|
||||
"consumed_grants_ledger": str(
|
||||
grant_dir / "consumed-grants.jsonl"
|
||||
),
|
||||
}
|
||||
)
|
||||
path = grant_dir.parent / "compat-validator-config.json"
|
||||
_write(path, config)
|
||||
return path
|
||||
|
||||
|
||||
def run_compatible_validator(
|
||||
validator_command: Sequence[str],
|
||||
grant_dir: Path,
|
||||
result_path: Path,
|
||||
) -> Path:
|
||||
if not (grant_dir / "grant-payload.json").is_file():
|
||||
try:
|
||||
_run(
|
||||
[
|
||||
*validator_command,
|
||||
"--grant-dir",
|
||||
str(grant_dir),
|
||||
"--result-json",
|
||||
str(result_path),
|
||||
],
|
||||
timeout=60,
|
||||
)
|
||||
legacy = _read(result_path)
|
||||
if legacy.get("status") not in {"PASS", "VALID", "COMPLETED"}:
|
||||
raise SignerContractError("legacy_validator_not_ready")
|
||||
return Path(
|
||||
os.environ.get(
|
||||
"AIOS_GRANT_ROOT_CONFIG", "/etc/aios/grant-root/config.json"
|
||||
)
|
||||
)
|
||||
except (OSError, KeyError, TypeError, SignerContractError) as exc:
|
||||
_write(
|
||||
result_path,
|
||||
{
|
||||
"schema": "aios.compatible-validator-result.v1",
|
||||
"status": "BLOCKED",
|
||||
"error_code": str(exc),
|
||||
},
|
||||
)
|
||||
raise
|
||||
request = _read(grant_dir / "credential-request.json")
|
||||
config_path = _validator_config(grant_dir, request)
|
||||
env = os.environ.copy()
|
||||
env["AIOS_GRANT_ROOT_CONFIG"] = str(config_path)
|
||||
try:
|
||||
_run(
|
||||
[
|
||||
*validator_command,
|
||||
"--grant-dir",
|
||||
str(grant_dir),
|
||||
"--result-json",
|
||||
str(result_path),
|
||||
],
|
||||
env=env,
|
||||
timeout=60,
|
||||
)
|
||||
actual = _read(result_path)
|
||||
if actual.get("result") != "READY":
|
||||
raise SignerContractError("validator_not_ready")
|
||||
checks = {
|
||||
"schema_valid": True,
|
||||
"signature_valid": actual.get("signature_verified") is True,
|
||||
"signer_trusted": actual.get("signature_verified") is True,
|
||||
"approval_plan_active": actual.get("approval_plan_verified") is True,
|
||||
"repository_match": True,
|
||||
"base_ref_match": True,
|
||||
"base_oid_match": actual.get("remote_base_verified") is True,
|
||||
"target_branch_match": actual.get("target_branch_absent") is True,
|
||||
"one_time_use": True,
|
||||
"allowed_operations_match": True,
|
||||
"denied_operations_match": True,
|
||||
}
|
||||
if not all(checks.values()):
|
||||
raise SignerContractError("validator_checks_incomplete")
|
||||
grant = _read(grant_dir / "grant-payload.json")
|
||||
result = {
|
||||
"schema": "aios.compatible-validator-result.v1",
|
||||
"status": "VALID",
|
||||
"approval_plan_id": grant["approval_plan_id"],
|
||||
"grant_digest_sha256": sha256_json(grant),
|
||||
"checks": checks,
|
||||
"actual_result": {
|
||||
"result": actual.get("result"),
|
||||
"signature_verified": actual.get("signature_verified"),
|
||||
"approval_plan_verified": actual.get("approval_plan_verified"),
|
||||
"remote_base_verified": actual.get("remote_base_verified"),
|
||||
"target_branch_absent": actual.get("target_branch_absent"),
|
||||
"grant_unused": actual.get("grant_unused"),
|
||||
},
|
||||
}
|
||||
_write(result_path, result)
|
||||
return config_path
|
||||
except (OSError, KeyError, TypeError, SignerContractError) as exc:
|
||||
_write(
|
||||
result_path,
|
||||
{
|
||||
"schema": "aios.compatible-validator-result.v1",
|
||||
"status": "BLOCKED",
|
||||
"error_code": str(exc),
|
||||
},
|
||||
)
|
||||
raise
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,564 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Execution-readiness adapters and the fail-closed Shadow controller service."""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
import dataclasses
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import threading
|
||||
import time
|
||||
from http import HTTPStatus
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Mapping, Protocol
|
||||
from urllib.parse import parse_qs, urlparse
|
||||
|
||||
from cryptography.hazmat.primitives.asymmetric.ed25519 import (
|
||||
Ed25519PrivateKey,
|
||||
)
|
||||
|
||||
from silent_release_controller import _sanitize, utc_now
|
||||
from silent_release_hardening import (
|
||||
BuilderAttestation,
|
||||
CapabilityAuthorizationError,
|
||||
ReleaseRecoveryWorker,
|
||||
SignedApprovalVerifier,
|
||||
SignedReleasePlanApproval,
|
||||
SilentReleaseActionService,
|
||||
TrustedCandidateBundle,
|
||||
_canonical_json,
|
||||
_durable_json,
|
||||
_safe_child,
|
||||
)
|
||||
|
||||
|
||||
class BuilderSigner(Protocol):
|
||||
@property
|
||||
def key_id(self) -> str:
|
||||
...
|
||||
|
||||
def sign(self, payload: bytes) -> bytes:
|
||||
...
|
||||
|
||||
|
||||
class LocalTestBuilderSigner:
|
||||
"""Ephemeral in-memory signer. It is forbidden for production execution."""
|
||||
|
||||
test_only = True
|
||||
|
||||
def __init__(self, key_id: str, private_key: Ed25519PrivateKey):
|
||||
self._key_id = str(key_id)
|
||||
self._private_key = private_key
|
||||
|
||||
@property
|
||||
def key_id(self) -> str:
|
||||
return self._key_id
|
||||
|
||||
@classmethod
|
||||
def generate(
|
||||
cls, key_id: str = "shadow-builder-test-key"
|
||||
) -> "LocalTestBuilderSigner":
|
||||
return cls(key_id, Ed25519PrivateKey.generate())
|
||||
|
||||
@property
|
||||
def public_key(self):
|
||||
return self._private_key.public_key()
|
||||
|
||||
def sign(self, payload: bytes) -> bytes:
|
||||
return self._private_key.sign(payload)
|
||||
|
||||
|
||||
class ExternalKmsBuilderSigner:
|
||||
"""Signer facade whose private operation remains in KMS/HSM."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
key_id: str,
|
||||
credential_reference: str,
|
||||
sign_callback: Callable[[str, bytes], bytes],
|
||||
):
|
||||
if not str(credential_reference).startswith(
|
||||
("kms://", "hsm://", "secret-manager://")
|
||||
):
|
||||
raise ValueError("production builder requires a KMS/HSM reference")
|
||||
self._key_id = str(key_id)
|
||||
self.credential_reference = str(credential_reference)
|
||||
self._sign_callback = sign_callback
|
||||
|
||||
@property
|
||||
def key_id(self) -> str:
|
||||
return self._key_id
|
||||
|
||||
def sign(self, payload: bytes) -> bytes:
|
||||
return bytes(self._sign_callback(self.credential_reference, payload))
|
||||
|
||||
|
||||
class SignedTrustedBuilderAdapter:
|
||||
"""Signs evidence produced by a trusted collector, never caller evidence."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
collector: Callable[[Mapping[str, Any]], TrustedCandidateBundle],
|
||||
signer: BuilderSigner,
|
||||
):
|
||||
self.collector = collector
|
||||
self.signer = signer
|
||||
|
||||
def build(self, intent: Mapping[str, Any]) -> TrustedCandidateBundle:
|
||||
forbidden = {
|
||||
"artifact_sha256",
|
||||
"canary",
|
||||
"checks",
|
||||
"manifest_sha256",
|
||||
"tests",
|
||||
"tree_oid",
|
||||
}
|
||||
if forbidden.intersection(intent):
|
||||
raise CapabilityAuthorizationError(
|
||||
"trusted builder rejects caller-supplied evidence"
|
||||
)
|
||||
unsigned = self.collector(dict(intent))
|
||||
if unsigned.attestation is not None:
|
||||
raise CapabilityAuthorizationError(
|
||||
"collector cannot self-attest its evidence"
|
||||
)
|
||||
candidate = unsigned.candidate
|
||||
test_sha = hashlib.sha256(
|
||||
_canonical_json(_sanitize(candidate.tests))
|
||||
).hexdigest()
|
||||
canary_sha = hashlib.sha256(
|
||||
_canonical_json(_sanitize(candidate.canary))
|
||||
).hexdigest()
|
||||
attestation_id = "builder-attestation-" + hashlib.sha256(
|
||||
(
|
||||
candidate.candidate_id
|
||||
+ "\0"
|
||||
+ candidate.source_commit
|
||||
+ "\0"
|
||||
+ candidate.artifact_sha256
|
||||
).encode("utf-8")
|
||||
).hexdigest()[:24]
|
||||
attestation = BuilderAttestation(
|
||||
builder_attestation_id=attestation_id,
|
||||
builder_key_id=self.signer.key_id,
|
||||
source_commit=candidate.source_commit,
|
||||
tree_oid=candidate.tree_oid,
|
||||
artifact_sha256=candidate.artifact_sha256,
|
||||
manifest_sha256=candidate.manifest_sha256,
|
||||
package_closure_sha256=(
|
||||
unsigned.release_plan.deployment.package_closure_sha256
|
||||
),
|
||||
test_evidence_sha256=test_sha,
|
||||
canary_evidence_sha256=canary_sha,
|
||||
issued_at=utc_now(),
|
||||
signature="",
|
||||
)
|
||||
attestation = dataclasses.replace(
|
||||
attestation,
|
||||
signature=base64.b64encode(
|
||||
self.signer.sign(attestation.canonical_bytes())
|
||||
).decode("ascii"),
|
||||
)
|
||||
return dataclasses.replace(unsigned, attestation=attestation)
|
||||
|
||||
|
||||
class ApprovalBackendAdapter(Protocol):
|
||||
@property
|
||||
def available(self) -> bool:
|
||||
...
|
||||
|
||||
def verify(
|
||||
self,
|
||||
approval: SignedReleasePlanApproval,
|
||||
*,
|
||||
candidate,
|
||||
release_plan,
|
||||
policy_sha256: str,
|
||||
) -> SignedReleasePlanApproval:
|
||||
...
|
||||
|
||||
|
||||
class LocalTestApprovalSigner:
|
||||
"""Test-only approval signer used solely for Shadow acceptance."""
|
||||
|
||||
test_only = True
|
||||
|
||||
def __init__(self, key_id: str, private_key: Ed25519PrivateKey):
|
||||
self.key_id = str(key_id)
|
||||
self.private_key = private_key
|
||||
|
||||
@classmethod
|
||||
def generate(
|
||||
cls, key_id: str = "shadow-owner-test-key"
|
||||
) -> "LocalTestApprovalSigner":
|
||||
return cls(key_id, Ed25519PrivateKey.generate())
|
||||
|
||||
def sign(
|
||||
self, approval: SignedReleasePlanApproval
|
||||
) -> SignedReleasePlanApproval:
|
||||
unsigned = dataclasses.replace(
|
||||
approval, key_id=self.key_id, signature=""
|
||||
)
|
||||
return dataclasses.replace(
|
||||
unsigned,
|
||||
signature=base64.b64encode(
|
||||
self.private_key.sign(unsigned.canonical_bytes())
|
||||
).decode("ascii"),
|
||||
)
|
||||
|
||||
|
||||
class ProductionApprovalBackendAdapter:
|
||||
"""Verification-only production adapter configured by a secret/KMS ref."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
verifier: SignedApprovalVerifier,
|
||||
credential_reference: str,
|
||||
):
|
||||
if not str(credential_reference).startswith(
|
||||
("kms://", "hsm://", "secret-manager://")
|
||||
):
|
||||
raise ValueError(
|
||||
"production approval backend requires a KMS/secret reference"
|
||||
)
|
||||
self.verifier = verifier
|
||||
self.credential_reference = str(credential_reference)
|
||||
|
||||
@property
|
||||
def available(self) -> bool:
|
||||
return True
|
||||
|
||||
def verify(
|
||||
self,
|
||||
approval: SignedReleasePlanApproval,
|
||||
*,
|
||||
candidate,
|
||||
release_plan,
|
||||
policy_sha256: str,
|
||||
) -> SignedReleasePlanApproval:
|
||||
return self.verifier.verify_release_plan(
|
||||
approval, candidate, release_plan, policy_sha256
|
||||
)
|
||||
|
||||
|
||||
class UnavailableProductionApprovalBackend:
|
||||
credential_reference = None
|
||||
|
||||
@property
|
||||
def available(self) -> bool:
|
||||
return False
|
||||
|
||||
def verify(self, *args, **kwargs):
|
||||
raise CapabilityAuthorizationError(
|
||||
"production approval backend is not configured"
|
||||
)
|
||||
|
||||
|
||||
class LeaderLock:
|
||||
def __init__(self, path: Path):
|
||||
self.path = Path(path)
|
||||
self.handle = None
|
||||
|
||||
def __enter__(self):
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
os.chmod(self.path.parent, 0o700)
|
||||
self.handle = self.path.open("a+", encoding="utf-8")
|
||||
os.chmod(self.path, 0o600)
|
||||
try:
|
||||
import fcntl
|
||||
|
||||
fcntl.flock(
|
||||
self.handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB
|
||||
)
|
||||
except BlockingIOError as exc:
|
||||
self.handle.close()
|
||||
self.handle = None
|
||||
raise RuntimeError("silent release leader is already active") from exc
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc, tb):
|
||||
if self.handle is not None:
|
||||
try:
|
||||
import fcntl
|
||||
|
||||
fcntl.flock(self.handle.fileno(), fcntl.LOCK_UN)
|
||||
finally:
|
||||
self.handle.close()
|
||||
self.handle = None
|
||||
|
||||
|
||||
class PersistentSilentReleaseController:
|
||||
"""Idempotent main-event controller with durable startup/recovery reports."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
root: Path,
|
||||
service: SilentReleaseActionService,
|
||||
*,
|
||||
main_probe: Callable[[], str],
|
||||
recovery_worker: ReleaseRecoveryWorker | None = None,
|
||||
):
|
||||
self.root = Path(root)
|
||||
self.service = service
|
||||
self.main_probe = main_probe
|
||||
self.recovery_worker = recovery_worker
|
||||
self.leader_path = self.root / "controller.leader.lock"
|
||||
self.status_path = self.root / "controller-status.json"
|
||||
|
||||
def startup_verify(self) -> dict[str, Any]:
|
||||
checked = 0
|
||||
failed = 0
|
||||
for journal in sorted(self.service.sagas.root.glob("*.events.jsonl")):
|
||||
candidate_id = journal.name[: -len(".events.jsonl")]
|
||||
saga = self.service.sagas.load(candidate_id)
|
||||
checked += 1
|
||||
if not saga.journal_integrity:
|
||||
failed += 1
|
||||
status = {
|
||||
"checked_sagas": checked,
|
||||
"execution_enabled": self.service.execution_enabled,
|
||||
"failed_closed": failed,
|
||||
"shadow_mode": not self.service.execution_enabled,
|
||||
"side_effects_executed": False,
|
||||
"status": "READY" if failed == 0 else "FAIL_CLOSED",
|
||||
}
|
||||
_durable_json(self.status_path, status)
|
||||
return status
|
||||
|
||||
def run_once(self) -> dict[str, Any]:
|
||||
with LeaderLock(self.leader_path):
|
||||
startup = self.startup_verify()
|
||||
if startup["status"] != "READY":
|
||||
result = {
|
||||
"execution_enabled": self.service.execution_enabled,
|
||||
"intent": None,
|
||||
"notification": None,
|
||||
"recovery": None,
|
||||
"shadow_mode": not self.service.execution_enabled,
|
||||
"side_effects_executed": False,
|
||||
"startup": startup,
|
||||
"status": "FAIL_CLOSED",
|
||||
}
|
||||
_durable_json(self.status_path, result)
|
||||
return _sanitize(result)
|
||||
source_commit = str(self.main_probe())
|
||||
event_id = f"main-{source_commit}"
|
||||
intent = self.service.create_release_intent(
|
||||
{"event_id": event_id, "source_commit": source_commit}
|
||||
)
|
||||
notification = None
|
||||
if intent.get("candidate_id"):
|
||||
notification = self.service.ensure_owner_notification(
|
||||
str(intent["candidate_id"])
|
||||
)
|
||||
recovery = (
|
||||
self.recovery_worker.run_once()
|
||||
if self.recovery_worker is not None
|
||||
else self.service.get_recovery_status()
|
||||
)
|
||||
result = {
|
||||
"execution_enabled": self.service.execution_enabled,
|
||||
"intent": intent,
|
||||
"notification": notification,
|
||||
"recovery": recovery,
|
||||
"shadow_mode": not self.service.execution_enabled,
|
||||
"side_effects_executed": False,
|
||||
"startup": startup,
|
||||
}
|
||||
_durable_json(self.status_path, result)
|
||||
return _sanitize(result)
|
||||
|
||||
|
||||
class ShadowActionHandler(BaseHTTPRequestHandler):
|
||||
service: SilentReleaseActionService
|
||||
controller: PersistentSilentReleaseController
|
||||
|
||||
def log_message(self, fmt, *args):
|
||||
return
|
||||
|
||||
def _json(self, payload: Mapping[str, Any], status=HTTPStatus.OK):
|
||||
body = json.dumps(_sanitize(dict(payload)), sort_keys=True).encode()
|
||||
self.send_response(int(status))
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
|
||||
def _body(self) -> dict[str, Any]:
|
||||
size = int(self.headers.get("Content-Length", "0"))
|
||||
if size > 1024 * 1024:
|
||||
raise ValueError("request body is too large")
|
||||
return json.loads(self.rfile.read(size) or b"{}")
|
||||
|
||||
def do_GET(self):
|
||||
parsed = urlparse(self.path)
|
||||
query = parse_qs(parsed.query)
|
||||
candidate_id = str((query.get("candidate_id") or [""])[0])
|
||||
try:
|
||||
if parsed.path == "/healthz":
|
||||
return self._json(
|
||||
{
|
||||
"execution_enabled": False,
|
||||
"shadow_mode": True,
|
||||
"side_effects_executed": False,
|
||||
"status": "ok",
|
||||
}
|
||||
)
|
||||
routes = {
|
||||
"/getReleaseCandidate": self.service.get_release_candidate,
|
||||
"/getReleasePlan": self.service.get_release_plan,
|
||||
"/getReleaseAcceptance": self.service.get_acceptance,
|
||||
"/getReleaseSaga": self.service.get_release_saga,
|
||||
"/getCapabilityStatus": self.service.get_capability_status,
|
||||
}
|
||||
if parsed.path in routes:
|
||||
return self._json(routes[parsed.path](candidate_id))
|
||||
if parsed.path == "/getRecoveryStatus":
|
||||
return self._json(self.service.get_recovery_status())
|
||||
self._json({"error": "not_found"}, HTTPStatus.NOT_FOUND)
|
||||
except (ValueError, FileNotFoundError) as exc:
|
||||
self._json(
|
||||
{"error": type(exc).__name__}, HTTPStatus.BAD_REQUEST
|
||||
)
|
||||
|
||||
def do_POST(self):
|
||||
parsed = urlparse(self.path)
|
||||
try:
|
||||
body = self._body()
|
||||
if parsed.path == "/createReleaseIntent":
|
||||
return self._json(self.service.create_release_intent(body))
|
||||
if parsed.path in {
|
||||
"/submitSignedApproval",
|
||||
"/submitOwnerApproval",
|
||||
}:
|
||||
return self._json(self.service.submit_owner_approval(body))
|
||||
if parsed.path == "/startDeployment":
|
||||
return self._json(
|
||||
self.service.start_deployment(
|
||||
str(body.get("candidate_id") or "")
|
||||
)
|
||||
)
|
||||
self._json({"error": "not_found"}, HTTPStatus.NOT_FOUND)
|
||||
except (ValueError, FileNotFoundError, CapabilityAuthorizationError) as exc:
|
||||
self._json(
|
||||
{"error": type(exc).__name__}, HTTPStatus.BAD_REQUEST
|
||||
)
|
||||
|
||||
|
||||
def git_main_probe(repository: Path) -> Callable[[], str]:
|
||||
repository = Path(repository)
|
||||
|
||||
def probe() -> str:
|
||||
completed = subprocess.run(
|
||||
[
|
||||
"git",
|
||||
f"--git-dir={repository}",
|
||||
"rev-parse",
|
||||
"refs/heads/main",
|
||||
],
|
||||
check=True,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=15,
|
||||
env={"PATH": os.environ.get("PATH", "")},
|
||||
)
|
||||
return completed.stdout.strip()
|
||||
|
||||
return probe
|
||||
|
||||
|
||||
def serve_shadow(
|
||||
*,
|
||||
state_root: Path,
|
||||
repository: Path,
|
||||
host: str,
|
||||
port: int,
|
||||
poll_seconds: float,
|
||||
) -> None:
|
||||
service = SilentReleaseActionService.shadow(state_root)
|
||||
controller = PersistentSilentReleaseController(
|
||||
state_root,
|
||||
service,
|
||||
main_probe=git_main_probe(repository),
|
||||
)
|
||||
controller.run_once()
|
||||
stop = threading.Event()
|
||||
|
||||
def controller_loop() -> None:
|
||||
while not stop.wait(poll_seconds):
|
||||
try:
|
||||
controller.run_once()
|
||||
except Exception as exc: # fail closed and keep the API available
|
||||
_durable_json(
|
||||
controller.status_path,
|
||||
{
|
||||
"error": type(exc).__name__,
|
||||
"execution_enabled": False,
|
||||
"shadow_mode": True,
|
||||
"side_effects_executed": False,
|
||||
"status": "FAIL_CLOSED",
|
||||
},
|
||||
)
|
||||
|
||||
handler = type(
|
||||
"ConfiguredShadowActionHandler",
|
||||
(ShadowActionHandler,),
|
||||
{"service": service, "controller": controller},
|
||||
)
|
||||
server = ThreadingHTTPServer((host, port), handler)
|
||||
api_thread = threading.Thread(
|
||||
target=server.serve_forever,
|
||||
name="silent-release-shadow-api",
|
||||
daemon=False,
|
||||
)
|
||||
controller_thread = threading.Thread(
|
||||
target=controller_loop,
|
||||
name="silent-release-shadow-controller",
|
||||
daemon=True,
|
||||
)
|
||||
api_thread.start()
|
||||
controller_thread.start()
|
||||
try:
|
||||
while api_thread.is_alive():
|
||||
api_thread.join(timeout=1)
|
||||
finally:
|
||||
stop.set()
|
||||
server.shutdown()
|
||||
server.server_close()
|
||||
controller_thread.join(timeout=max(1.0, poll_seconds + 1.0))
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--state-root", required=True, type=Path)
|
||||
parser.add_argument("--repository", required=True, type=Path)
|
||||
parser.add_argument("--host", default="127.0.0.1")
|
||||
parser.add_argument("--port", default=18891, type=int)
|
||||
parser.add_argument("--poll-seconds", default=30.0, type=float)
|
||||
arguments = parser.parse_args()
|
||||
if arguments.poll_seconds <= 0:
|
||||
raise SystemExit("poll seconds must be positive")
|
||||
if os.environ.get("AIOS_GITOPS_WRITES_ENABLED", "false").lower() != "false":
|
||||
raise SystemExit("GitOps writes must remain disabled")
|
||||
if (
|
||||
os.environ.get(
|
||||
"AIOS_SILENT_RELEASE_EXECUTION_ENABLED", "false"
|
||||
).lower()
|
||||
!= "false"
|
||||
):
|
||||
raise SystemExit("Silent Release execution must remain disabled")
|
||||
serve_shadow(
|
||||
state_root=arguments.state_root,
|
||||
repository=arguments.repository,
|
||||
host=arguments.host,
|
||||
port=arguments.port,
|
||||
poll_seconds=arguments.poll_seconds,
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,760 @@
|
||||
"""Task-scoped identity overlay for bootstrap writer provisioning.
|
||||
|
||||
This module resolves bearer-registry identity ambiguity without modifying the
|
||||
global token registry. A root-governed one-shot issuer creates a random,
|
||||
short-lived credential bound to exactly one repository, base OID, task and
|
||||
target branch. The HTTP overlay authenticates only that credential and invokes
|
||||
the existing OwnerAuthorizationBroker.
|
||||
|
||||
The overlay never grants main, tag, baseline, production or repository-admin
|
||||
capabilities. The bearer secret is stored only in a root-owned runtime path and
|
||||
is removed after success, failure, revocation or expiry.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import secrets
|
||||
import tempfile
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
from authorized_task_writer_provisioning import (
|
||||
BRANCH_RE,
|
||||
ProvisioningError,
|
||||
OID_RE,
|
||||
REQUIRED_ALLOWED_OPERATIONS,
|
||||
REQUIRED_DENIED_OPERATIONS,
|
||||
TASK_RE,
|
||||
)
|
||||
from owner_authorization_broker import (
|
||||
ACTION,
|
||||
BROKER_REQUEST_FIELDS,
|
||||
OwnerAuthorizationBroker,
|
||||
OwnerAuthorizationBrokerConfig,
|
||||
OwnerAuthorizationError,
|
||||
OwnerPrincipal,
|
||||
TaskWriterProvisioner,
|
||||
canonical_json_bytes,
|
||||
iso_utc,
|
||||
sha256_json,
|
||||
utc_now,
|
||||
)
|
||||
|
||||
|
||||
OVERLAY_SCHEMA = "aios.task-identity-overlay.v1"
|
||||
OVERLAY_SCOPE = "owner:task-authorize"
|
||||
OVERLAY_ID_RE = re.compile(r"^overlay-[0-9a-f]{32}$")
|
||||
OWNER_IDENTITY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._@:+/-]{1,254}$")
|
||||
AUTH_ASSERTION_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:/@+-]{3,255}$")
|
||||
TERMINAL_STATES = frozenset({"CONSUMED", "FAILED", "REVOKED", "EXPIRED"})
|
||||
MAX_BODY_BYTES = 1_048_576
|
||||
|
||||
|
||||
class IdentityOverlayError(RuntimeError):
|
||||
"""Stable, fail-closed error for the overlay control plane."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
code: str,
|
||||
status: int = 400,
|
||||
*,
|
||||
details: Mapping[str, Any] | None = None,
|
||||
) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
self.details = dict(details or {})
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskBinding:
|
||||
task_id: str
|
||||
repository: str
|
||||
base_ref: str
|
||||
base_oid: str
|
||||
target_branch: str
|
||||
|
||||
def as_dict(self) -> dict[str, str]:
|
||||
return {
|
||||
"task_id": self.task_id,
|
||||
"repository": self.repository,
|
||||
"base_ref": self.base_ref,
|
||||
"base_oid": self.base_oid,
|
||||
"target_branch": self.target_branch,
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class IdentityOverlayConfig:
|
||||
state_root: Path
|
||||
secret_root: Path
|
||||
binding: TaskBinding
|
||||
owner_identity: str
|
||||
max_ttl_seconds: int = 900
|
||||
require_root_issue: bool = True
|
||||
collision_secret_refs: tuple[Path, ...] = ()
|
||||
broker_state_root: Path | None = None
|
||||
|
||||
@classmethod
|
||||
def from_environment(cls) -> "IdentityOverlayConfig":
|
||||
try:
|
||||
maximum = int(
|
||||
os.getenv("AIOS_GITOPS_IDENTITY_OVERLAY_MAX_TTL_SECONDS", "900")
|
||||
)
|
||||
except ValueError:
|
||||
raise IdentityOverlayError("OVERLAY_MAX_TTL_INVALID", 503) from None
|
||||
if not 60 <= maximum <= 900:
|
||||
raise IdentityOverlayError("OVERLAY_MAX_TTL_INVALID", 503)
|
||||
|
||||
refs = tuple(
|
||||
Path(item.strip())
|
||||
for item in os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_COLLISION_SECRET_REFS", ""
|
||||
).split(",")
|
||||
if item.strip()
|
||||
)
|
||||
owner = os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_OWNER_IDENTITY", ""
|
||||
).strip()
|
||||
config = cls(
|
||||
state_root=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_STATE_ROOT",
|
||||
"/var/lib/aios-gitops/task-identity-overlays",
|
||||
)
|
||||
),
|
||||
secret_root=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_SECRET_ROOT",
|
||||
"/run/aios-gitops/task-identity-overlays",
|
||||
)
|
||||
),
|
||||
broker_state_root=Path(
|
||||
os.getenv(
|
||||
"AIOS_GITOPS_OWNER_AUTHORIZATION_STATE_ROOT",
|
||||
"/var/lib/aios-gitops/owner-authorization-broker",
|
||||
)
|
||||
),
|
||||
binding=TaskBinding(
|
||||
task_id=os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_TASK_ID", ""
|
||||
).strip(),
|
||||
repository=os.getenv(
|
||||
"AIOS_GITOPS_REPOSITORY_IDENTITY", "aios/aios"
|
||||
).strip(),
|
||||
base_ref=os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_BASE_REF",
|
||||
"refs/heads/main",
|
||||
).strip(),
|
||||
base_oid=os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_BASE_OID", ""
|
||||
).strip(),
|
||||
target_branch=os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_TARGET_BRANCH", ""
|
||||
).strip(),
|
||||
),
|
||||
owner_identity=owner,
|
||||
max_ttl_seconds=maximum,
|
||||
require_root_issue=os.getenv(
|
||||
"AIOS_GITOPS_IDENTITY_OVERLAY_REQUIRE_ROOT", "true"
|
||||
).strip().lower()
|
||||
not in {"0", "false", "no", "off"},
|
||||
collision_secret_refs=refs,
|
||||
)
|
||||
_validate_config(config)
|
||||
return config
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class OverlaySession:
|
||||
overlay_id: str
|
||||
metadata_path: Path
|
||||
secret_ref: Path
|
||||
owner_identity: str
|
||||
request_digest_sha256: str
|
||||
binding: TaskBinding
|
||||
|
||||
|
||||
def _validate_config(config: IdentityOverlayConfig) -> None:
|
||||
binding = config.binding
|
||||
if not TASK_RE.fullmatch(binding.task_id):
|
||||
raise IdentityOverlayError("OVERLAY_TASK_ID_INVALID", 503)
|
||||
if binding.repository != "aios/aios":
|
||||
raise IdentityOverlayError("OVERLAY_REPOSITORY_REJECTED", 503)
|
||||
if binding.base_ref != "refs/heads/main":
|
||||
raise IdentityOverlayError("OVERLAY_BASE_REF_REJECTED", 503)
|
||||
if not OID_RE.fullmatch(binding.base_oid):
|
||||
raise IdentityOverlayError("OVERLAY_BASE_OID_INVALID", 503)
|
||||
if (
|
||||
not BRANCH_RE.fullmatch(binding.target_branch)
|
||||
or binding.target_branch in {"main", "master"}
|
||||
):
|
||||
raise IdentityOverlayError("OVERLAY_TARGET_BRANCH_INVALID", 503)
|
||||
if not OWNER_IDENTITY_RE.fullmatch(config.owner_identity):
|
||||
raise IdentityOverlayError("OVERLAY_OWNER_IDENTITY_INVALID", 503)
|
||||
if not 60 <= config.max_ttl_seconds <= 900:
|
||||
raise IdentityOverlayError("OVERLAY_MAX_TTL_INVALID", 503)
|
||||
if config.state_root == config.secret_root:
|
||||
raise IdentityOverlayError("OVERLAY_STATE_SECRET_ROOT_COLLISION", 503)
|
||||
|
||||
|
||||
def _prepare_directory(path: Path, mode: int = 0o700) -> None:
|
||||
if path.is_symlink():
|
||||
raise IdentityOverlayError("OVERLAY_PATH_SYMLINK_REJECTED", 500)
|
||||
path.mkdir(parents=True, exist_ok=True, mode=mode)
|
||||
os.chmod(path, mode)
|
||||
if path.stat().st_mode & 0o077:
|
||||
raise IdentityOverlayError("OVERLAY_DIRECTORY_PERMISSIONS_REJECTED", 500)
|
||||
|
||||
|
||||
def _atomic_write(path: Path, data: bytes, mode: int) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
if path.parent.is_symlink() or path.is_symlink():
|
||||
raise IdentityOverlayError("OVERLAY_PATH_SYMLINK_REJECTED", 500)
|
||||
fd, temporary = tempfile.mkstemp(prefix=".tmp-", dir=path.parent)
|
||||
try:
|
||||
os.fchmod(fd, mode)
|
||||
with os.fdopen(fd, "wb", closefd=True) as stream:
|
||||
stream.write(data)
|
||||
stream.flush()
|
||||
os.fsync(stream.fileno())
|
||||
os.replace(temporary, path)
|
||||
os.chmod(path, mode)
|
||||
parent_fd = os.open(
|
||||
path.parent, os.O_RDONLY | getattr(os, "O_DIRECTORY", 0)
|
||||
)
|
||||
try:
|
||||
os.fsync(parent_fd)
|
||||
finally:
|
||||
os.close(parent_fd)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
|
||||
|
||||
def _atomic_write_json(path: Path, value: Any, mode: int = 0o600) -> None:
|
||||
_atomic_write(path, canonical_json_bytes(value), mode)
|
||||
|
||||
|
||||
def _read_json(path: Path) -> dict[str, Any]:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500)
|
||||
if path.stat().st_size <= 0 or path.stat().st_size > MAX_BODY_BYTES:
|
||||
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500)
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError):
|
||||
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500) from None
|
||||
if not isinstance(value, dict):
|
||||
raise IdentityOverlayError("OVERLAY_METADATA_INVALID", 500)
|
||||
return value
|
||||
|
||||
|
||||
def _parse_utc(value: str) -> datetime:
|
||||
try:
|
||||
parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
|
||||
except (TypeError, ValueError):
|
||||
raise IdentityOverlayError("OVERLAY_TIMESTAMP_INVALID", 500) from None
|
||||
if parsed.tzinfo is None:
|
||||
raise IdentityOverlayError("OVERLAY_TIMESTAMP_INVALID", 500)
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def _token_hash(token: bytes) -> str:
|
||||
return hashlib.sha256(token.strip()).hexdigest()
|
||||
|
||||
|
||||
def _safe_unlink(path: Path) -> None:
|
||||
try:
|
||||
if path.is_symlink():
|
||||
raise IdentityOverlayError("OVERLAY_SECRET_SYMLINK_REJECTED", 500)
|
||||
path.unlink(missing_ok=True)
|
||||
except OSError as exc:
|
||||
raise IdentityOverlayError("OVERLAY_SECRET_REMOVAL_FAILED", 500) from exc
|
||||
|
||||
|
||||
def _validate_request_binding(
|
||||
request: Mapping[str, Any], binding: TaskBinding, max_ttl: int
|
||||
) -> dict[str, Any]:
|
||||
if set(request) != BROKER_REQUEST_FIELDS:
|
||||
raise IdentityOverlayError("OVERLAY_REQUEST_FIELDS_REJECTED")
|
||||
if request.get("action") != ACTION:
|
||||
raise IdentityOverlayError("OVERLAY_ACTION_REJECTED")
|
||||
expected = binding.as_dict()
|
||||
for key, value in expected.items():
|
||||
if request.get(key) != value:
|
||||
raise IdentityOverlayError(
|
||||
"OVERLAY_BINDING_MISMATCH", 409, details={"field": key}
|
||||
)
|
||||
if request.get("one_time_use") is not True:
|
||||
raise IdentityOverlayError("OVERLAY_ONE_TIME_USE_REQUIRED")
|
||||
expiry = request.get("expires_in_seconds")
|
||||
if (
|
||||
not isinstance(expiry, int)
|
||||
or isinstance(expiry, bool)
|
||||
or not 60 <= expiry <= max_ttl
|
||||
):
|
||||
raise IdentityOverlayError("OVERLAY_TTL_REJECTED")
|
||||
for field in (
|
||||
"production_change_authorized",
|
||||
"tag_change_authorized",
|
||||
"baseline_change_authorized",
|
||||
"main_write_authorized",
|
||||
):
|
||||
if request.get(field) is not False:
|
||||
raise IdentityOverlayError("OVERLAY_PRODUCTION_CAPABILITY_REJECTED", 403)
|
||||
if (
|
||||
not isinstance(request.get("allowed_operations"), list)
|
||||
or frozenset(request["allowed_operations"])
|
||||
!= REQUIRED_ALLOWED_OPERATIONS
|
||||
):
|
||||
raise IdentityOverlayError("OVERLAY_ALLOWED_OPERATIONS_MISMATCH", 403)
|
||||
if (
|
||||
not isinstance(request.get("denied_operations"), list)
|
||||
or frozenset(request["denied_operations"])
|
||||
!= REQUIRED_DENIED_OPERATIONS
|
||||
):
|
||||
raise IdentityOverlayError("OVERLAY_DENIED_OPERATIONS_MISMATCH", 403)
|
||||
return dict(request)
|
||||
|
||||
|
||||
def _metadata_digest(metadata: Mapping[str, Any]) -> str:
|
||||
unsigned = {
|
||||
key: value
|
||||
for key, value in metadata.items()
|
||||
if key != "metadata_digest_sha256"
|
||||
}
|
||||
return sha256_json(unsigned)
|
||||
|
||||
|
||||
def _verify_metadata(metadata: Mapping[str, Any]) -> None:
|
||||
if metadata.get("schema") != OVERLAY_SCHEMA:
|
||||
raise IdentityOverlayError("OVERLAY_METADATA_SCHEMA_INVALID", 500)
|
||||
overlay_id = str(metadata.get("overlay_id") or "")
|
||||
if not OVERLAY_ID_RE.fullmatch(overlay_id):
|
||||
raise IdentityOverlayError("OVERLAY_METADATA_ID_INVALID", 500)
|
||||
expected = _metadata_digest(metadata)
|
||||
if metadata.get("metadata_digest_sha256") != expected:
|
||||
raise IdentityOverlayError("OVERLAY_METADATA_DIGEST_MISMATCH", 500)
|
||||
|
||||
|
||||
class TaskIdentityOverlayStore:
|
||||
"""Issue, authenticate, consume and revoke one task-bound credential."""
|
||||
|
||||
def __init__(self, config: IdentityOverlayConfig) -> None:
|
||||
_validate_config(config)
|
||||
self.config = config
|
||||
|
||||
@property
|
||||
def lock_path(self) -> Path:
|
||||
return self.config.state_root / "overlay.lock"
|
||||
|
||||
def _lock(self):
|
||||
_prepare_directory(self.config.state_root)
|
||||
_prepare_directory(self.config.secret_root)
|
||||
self.lock_path.touch(mode=0o600, exist_ok=True)
|
||||
os.chmod(self.lock_path, 0o600)
|
||||
stream = self.lock_path.open("r+b")
|
||||
fcntl.flock(stream.fileno(), fcntl.LOCK_EX)
|
||||
return stream
|
||||
|
||||
def _metadata_paths(self) -> list[Path]:
|
||||
return sorted(self.config.state_root.glob("overlay-*/metadata.json"))
|
||||
|
||||
def _active_for_task(self) -> tuple[Path, dict[str, Any]] | None:
|
||||
now = utc_now()
|
||||
for path in self._metadata_paths():
|
||||
metadata = _read_json(path)
|
||||
_verify_metadata(metadata)
|
||||
if metadata.get("task_id") != self.config.binding.task_id:
|
||||
continue
|
||||
state = metadata.get("status")
|
||||
if state in TERMINAL_STATES:
|
||||
continue
|
||||
if _parse_utc(str(metadata["expires_at"])) <= now:
|
||||
metadata["status"] = "EXPIRED"
|
||||
metadata["expired_at"] = iso_utc(now)
|
||||
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
|
||||
_atomic_write_json(path, metadata)
|
||||
_safe_unlink(Path(str(metadata["secret_ref"])))
|
||||
continue
|
||||
return path, metadata
|
||||
return None
|
||||
|
||||
def _assert_hash_unique(self, digest: str) -> None:
|
||||
matches = 0
|
||||
for path in self._metadata_paths():
|
||||
metadata = _read_json(path)
|
||||
_verify_metadata(metadata)
|
||||
if metadata.get("token_sha256") == digest:
|
||||
matches += 1
|
||||
for secret_ref in self.config.collision_secret_refs:
|
||||
if not secret_ref.exists():
|
||||
continue
|
||||
if secret_ref.is_symlink() or not secret_ref.is_file():
|
||||
raise IdentityOverlayError(
|
||||
"OVERLAY_COLLISION_SECRET_REF_INVALID", 500
|
||||
)
|
||||
if secret_ref.stat().st_size > 65_536:
|
||||
raise IdentityOverlayError(
|
||||
"OVERLAY_COLLISION_SECRET_REF_INVALID", 500
|
||||
)
|
||||
if _token_hash(secret_ref.read_bytes()) == digest:
|
||||
matches += 1
|
||||
if matches:
|
||||
raise IdentityOverlayError("OVERLAY_SECRET_IDENTITY_COLLISION", 409)
|
||||
|
||||
def issue(
|
||||
self,
|
||||
*,
|
||||
ttl_seconds: int,
|
||||
authorization_assertion_ref: str,
|
||||
operator_identity: str,
|
||||
) -> dict[str, Any]:
|
||||
if self.config.require_root_issue and os.geteuid() != 0:
|
||||
raise IdentityOverlayError("OVERLAY_ROOT_ISSUER_REQUIRED", 403)
|
||||
if (
|
||||
not isinstance(ttl_seconds, int)
|
||||
or isinstance(ttl_seconds, bool)
|
||||
or not 60 <= ttl_seconds <= self.config.max_ttl_seconds
|
||||
):
|
||||
raise IdentityOverlayError("OVERLAY_TTL_REJECTED")
|
||||
if not AUTH_ASSERTION_RE.fullmatch(authorization_assertion_ref):
|
||||
raise IdentityOverlayError("OVERLAY_AUTH_ASSERTION_REF_INVALID")
|
||||
if not OWNER_IDENTITY_RE.fullmatch(operator_identity):
|
||||
raise IdentityOverlayError("OVERLAY_OPERATOR_IDENTITY_INVALID")
|
||||
|
||||
with self._lock():
|
||||
active = self._active_for_task()
|
||||
if active:
|
||||
_, metadata = active
|
||||
expected = self.config.binding.as_dict()
|
||||
actual = {
|
||||
key: metadata.get(key)
|
||||
for key in expected
|
||||
}
|
||||
if actual != expected:
|
||||
raise IdentityOverlayError(
|
||||
"OVERLAY_ACTIVE_BINDING_CONFLICT", 409
|
||||
)
|
||||
return {
|
||||
"status": "OVERLAY_ACTIVE",
|
||||
"idempotent": True,
|
||||
"overlay_id": metadata["overlay_id"],
|
||||
"secret_ref": metadata["secret_ref"],
|
||||
"expires_at": metadata["expires_at"],
|
||||
"binding": expected,
|
||||
}
|
||||
|
||||
token_text = secrets.token_urlsafe(48)
|
||||
token_bytes = token_text.encode("ascii")
|
||||
digest = _token_hash(token_bytes)
|
||||
self._assert_hash_unique(digest)
|
||||
overlay_id = "overlay-" + hashlib.sha256(
|
||||
(
|
||||
f"{self.config.binding.task_id}\0"
|
||||
f"{self.config.binding.base_oid}\0"
|
||||
f"{self.config.binding.target_branch}\0"
|
||||
f"{digest}"
|
||||
).encode("utf-8")
|
||||
).hexdigest()[:32]
|
||||
issued_at = utc_now()
|
||||
expires_at = issued_at + timedelta(seconds=ttl_seconds)
|
||||
overlay_dir = self.config.state_root / overlay_id
|
||||
secret_dir = self.config.secret_root / overlay_id
|
||||
_prepare_directory(overlay_dir)
|
||||
_prepare_directory(secret_dir)
|
||||
secret_ref = secret_dir / "bearer.token"
|
||||
_atomic_write(secret_ref, token_bytes + b"\n", 0o600)
|
||||
|
||||
metadata: dict[str, Any] = {
|
||||
"schema": OVERLAY_SCHEMA,
|
||||
"overlay_id": overlay_id,
|
||||
"status": "ACTIVE",
|
||||
**self.config.binding.as_dict(),
|
||||
"owner_identity": self.config.owner_identity,
|
||||
"role": "owner",
|
||||
"scope": OVERLAY_SCOPE,
|
||||
"wildcard_scope": False,
|
||||
"one_time_use": True,
|
||||
"token_sha256": digest,
|
||||
"secret_ref": str(secret_ref),
|
||||
"authorization_assertion_ref": authorization_assertion_ref,
|
||||
"operator_identity": operator_identity,
|
||||
"issued_at": iso_utc(issued_at),
|
||||
"expires_at": iso_utc(expires_at),
|
||||
"attempt_count": 0,
|
||||
}
|
||||
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
|
||||
metadata_path = overlay_dir / "metadata.json"
|
||||
_atomic_write_json(metadata_path, metadata)
|
||||
_atomic_write_json(
|
||||
overlay_dir / "audit-issued.json",
|
||||
{
|
||||
"event": "TASK_IDENTITY_OVERLAY_ISSUED",
|
||||
"overlay_id": overlay_id,
|
||||
"task_id": self.config.binding.task_id,
|
||||
"binding_digest_sha256": sha256_json(
|
||||
self.config.binding.as_dict()
|
||||
),
|
||||
"authorization_assertion_ref": authorization_assertion_ref,
|
||||
"operator_identity": operator_identity,
|
||||
"issued_at": metadata["issued_at"],
|
||||
"expires_at": metadata["expires_at"],
|
||||
"token_sha256": digest,
|
||||
},
|
||||
)
|
||||
return {
|
||||
"status": "OVERLAY_ACTIVE",
|
||||
"idempotent": False,
|
||||
"overlay_id": overlay_id,
|
||||
"secret_ref": str(secret_ref),
|
||||
"expires_at": metadata["expires_at"],
|
||||
"binding": self.config.binding.as_dict(),
|
||||
}
|
||||
|
||||
def authenticate_and_lock(
|
||||
self, token: str, request: Mapping[str, Any]
|
||||
) -> OverlaySession:
|
||||
if not token or len(token) > 4096:
|
||||
raise IdentityOverlayError("OVERLAY_AUTHENTICATION_REQUIRED", 401)
|
||||
digest = _token_hash(token.encode("utf-8"))
|
||||
|
||||
with self._lock():
|
||||
matches: list[tuple[Path, dict[str, Any]]] = []
|
||||
for path in self._metadata_paths():
|
||||
metadata = _read_json(path)
|
||||
_verify_metadata(metadata)
|
||||
if metadata.get("token_sha256") == digest:
|
||||
matches.append((path, metadata))
|
||||
if not matches:
|
||||
raise IdentityOverlayError("OVERLAY_CREDENTIAL_INVALID", 401)
|
||||
if len(matches) != 1:
|
||||
raise IdentityOverlayError("OVERLAY_SECRET_IDENTITY_COLLISION", 409)
|
||||
path, metadata = matches[0]
|
||||
if metadata.get("status") in TERMINAL_STATES:
|
||||
raise IdentityOverlayError("OVERLAY_CREDENTIAL_INACTIVE", 401)
|
||||
if _parse_utc(str(metadata["expires_at"])) <= utc_now():
|
||||
metadata["status"] = "EXPIRED"
|
||||
metadata["expired_at"] = iso_utc(utc_now())
|
||||
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
|
||||
_atomic_write_json(path, metadata)
|
||||
_safe_unlink(Path(str(metadata["secret_ref"])))
|
||||
raise IdentityOverlayError("OVERLAY_CREDENTIAL_EXPIRED", 401)
|
||||
|
||||
expected = self.config.binding.as_dict()
|
||||
for key, value in expected.items():
|
||||
if metadata.get(key) != value:
|
||||
raise IdentityOverlayError(
|
||||
"OVERLAY_METADATA_BINDING_MISMATCH", 409
|
||||
)
|
||||
if metadata.get("owner_identity") != self.config.owner_identity:
|
||||
raise IdentityOverlayError("OVERLAY_OWNER_IDENTITY_MISMATCH", 409)
|
||||
if metadata.get("scope") != OVERLAY_SCOPE:
|
||||
raise IdentityOverlayError("OVERLAY_SCOPE_MISMATCH", 409)
|
||||
if metadata.get("wildcard_scope") is not False:
|
||||
raise IdentityOverlayError("OVERLAY_WILDCARD_SCOPE_REJECTED", 409)
|
||||
|
||||
# Validate detailed request policy only after the bearer identity is
|
||||
# proven, so unauthenticated callers cannot probe task bindings.
|
||||
validated = _validate_request_binding(
|
||||
request, self.config.binding, self.config.max_ttl_seconds
|
||||
)
|
||||
request_digest = sha256_json(validated)
|
||||
previous = str(metadata.get("request_digest_sha256") or "")
|
||||
if metadata.get("status") == "LOCKED" and previous != request_digest:
|
||||
raise IdentityOverlayError("OVERLAY_REPLAY_REQUEST_MISMATCH", 409)
|
||||
metadata["status"] = "LOCKED"
|
||||
metadata["request_digest_sha256"] = request_digest
|
||||
metadata["locked_at"] = metadata.get("locked_at") or iso_utc(utc_now())
|
||||
metadata["attempt_count"] = int(metadata.get("attempt_count") or 0) + 1
|
||||
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
|
||||
_atomic_write_json(path, metadata)
|
||||
return OverlaySession(
|
||||
overlay_id=str(metadata["overlay_id"]),
|
||||
metadata_path=path,
|
||||
secret_ref=Path(str(metadata["secret_ref"])),
|
||||
owner_identity=str(metadata["owner_identity"]),
|
||||
request_digest_sha256=request_digest,
|
||||
binding=self.config.binding,
|
||||
)
|
||||
|
||||
def complete(
|
||||
self, session: OverlaySession, result: Mapping[str, Any]
|
||||
) -> dict[str, Any]:
|
||||
with self._lock():
|
||||
metadata = _read_json(session.metadata_path)
|
||||
_verify_metadata(metadata)
|
||||
if metadata.get("status") == "CONSUMED":
|
||||
return metadata
|
||||
if metadata.get("status") != "LOCKED":
|
||||
raise IdentityOverlayError("OVERLAY_NOT_LOCKED", 409)
|
||||
if (
|
||||
metadata.get("request_digest_sha256")
|
||||
!= session.request_digest_sha256
|
||||
):
|
||||
raise IdentityOverlayError("OVERLAY_REQUEST_DIGEST_MISMATCH", 409)
|
||||
metadata["status"] = "CONSUMED"
|
||||
metadata["consumed_at"] = iso_utc(utc_now())
|
||||
metadata["result_digest_sha256"] = sha256_json(dict(result))
|
||||
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
|
||||
_atomic_write_json(session.metadata_path, metadata)
|
||||
_safe_unlink(session.secret_ref)
|
||||
_atomic_write_json(
|
||||
session.metadata_path.parent / "audit-consumed.json",
|
||||
{
|
||||
"event": "TASK_IDENTITY_OVERLAY_CONSUMED",
|
||||
"overlay_id": session.overlay_id,
|
||||
"task_id": session.binding.task_id,
|
||||
"request_digest_sha256": session.request_digest_sha256,
|
||||
"result_digest_sha256": metadata["result_digest_sha256"],
|
||||
"consumed_at": metadata["consumed_at"],
|
||||
"secret_removed": True,
|
||||
},
|
||||
)
|
||||
return metadata
|
||||
|
||||
def fail(
|
||||
self,
|
||||
session: OverlaySession,
|
||||
*,
|
||||
error_code: str,
|
||||
error_status: int,
|
||||
) -> dict[str, Any]:
|
||||
with self._lock():
|
||||
metadata = _read_json(session.metadata_path)
|
||||
_verify_metadata(metadata)
|
||||
if metadata.get("status") in TERMINAL_STATES:
|
||||
return metadata
|
||||
metadata["status"] = "FAILED"
|
||||
metadata["failed_at"] = iso_utc(utc_now())
|
||||
metadata["error_code"] = error_code
|
||||
metadata["error_status"] = int(error_status)
|
||||
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
|
||||
_atomic_write_json(session.metadata_path, metadata)
|
||||
_safe_unlink(session.secret_ref)
|
||||
_atomic_write_json(
|
||||
session.metadata_path.parent / "audit-failed.json",
|
||||
{
|
||||
"event": "TASK_IDENTITY_OVERLAY_FAILED",
|
||||
"overlay_id": session.overlay_id,
|
||||
"task_id": session.binding.task_id,
|
||||
"request_digest_sha256": session.request_digest_sha256,
|
||||
"error_code": error_code,
|
||||
"error_status": int(error_status),
|
||||
"failed_at": metadata["failed_at"],
|
||||
"secret_removed": True,
|
||||
},
|
||||
)
|
||||
return metadata
|
||||
|
||||
def revoke(self, overlay_id: str, *, reason: str) -> dict[str, Any]:
|
||||
if self.config.require_root_issue and os.geteuid() != 0:
|
||||
raise IdentityOverlayError("OVERLAY_ROOT_ISSUER_REQUIRED", 403)
|
||||
if not OVERLAY_ID_RE.fullmatch(overlay_id):
|
||||
raise IdentityOverlayError("OVERLAY_ID_INVALID")
|
||||
if not AUTH_ASSERTION_RE.fullmatch(reason):
|
||||
raise IdentityOverlayError("OVERLAY_REVOCATION_REASON_INVALID")
|
||||
with self._lock():
|
||||
path = self.config.state_root / overlay_id / "metadata.json"
|
||||
metadata = _read_json(path)
|
||||
_verify_metadata(metadata)
|
||||
if metadata.get("status") not in TERMINAL_STATES:
|
||||
metadata["status"] = "REVOKED"
|
||||
metadata["revoked_at"] = iso_utc(utc_now())
|
||||
metadata["revocation_reason"] = reason
|
||||
metadata["metadata_digest_sha256"] = _metadata_digest(metadata)
|
||||
_atomic_write_json(path, metadata)
|
||||
_safe_unlink(Path(str(metadata["secret_ref"])))
|
||||
return metadata
|
||||
|
||||
def status(self, overlay_id: str) -> dict[str, Any]:
|
||||
if not OVERLAY_ID_RE.fullmatch(overlay_id):
|
||||
raise IdentityOverlayError("OVERLAY_ID_INVALID")
|
||||
metadata = _read_json(
|
||||
self.config.state_root / overlay_id / "metadata.json"
|
||||
)
|
||||
_verify_metadata(metadata)
|
||||
return {
|
||||
key: value
|
||||
for key, value in metadata.items()
|
||||
if key not in {"token_sha256"}
|
||||
}
|
||||
|
||||
|
||||
class TaskIdentityOverlayService:
|
||||
"""Authenticate one overlay credential and invoke the existing broker."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: IdentityOverlayConfig,
|
||||
provisioner: TaskWriterProvisioner | None = None,
|
||||
) -> None:
|
||||
self.config = config
|
||||
self.store = TaskIdentityOverlayStore(config)
|
||||
broker_state = config.broker_state_root or (
|
||||
config.state_root / "owner-authorization-events"
|
||||
)
|
||||
self.broker = OwnerAuthorizationBroker(
|
||||
OwnerAuthorizationBrokerConfig(
|
||||
repository_identity=config.binding.repository,
|
||||
state_root=broker_state,
|
||||
allowed_owner_identities=frozenset({config.owner_identity}),
|
||||
allowed_intake_scopes=frozenset({OVERLAY_SCOPE}),
|
||||
allowed_credential_ids=frozenset(),
|
||||
max_expiry_seconds=config.max_ttl_seconds,
|
||||
),
|
||||
provisioner=provisioner,
|
||||
)
|
||||
|
||||
def provision(
|
||||
self, request: Mapping[str, Any], bearer_token: str
|
||||
) -> dict[str, Any]:
|
||||
session = self.store.authenticate_and_lock(bearer_token, request)
|
||||
principal = OwnerPrincipal(
|
||||
identity=session.owner_identity,
|
||||
role="owner",
|
||||
authenticated_scope=OVERLAY_SCOPE,
|
||||
token_scopes=frozenset({OVERLAY_SCOPE}),
|
||||
credential_id=session.overlay_id,
|
||||
)
|
||||
try:
|
||||
result = self.broker.authorize_and_provision(request, principal)
|
||||
if result.get("status") != "READY_FOR_CODE_AUTHORING":
|
||||
raise IdentityOverlayError("OVERLAY_PROVISIONER_NOT_READY", 409)
|
||||
self.store.complete(session, result)
|
||||
response = dict(result)
|
||||
response.update(
|
||||
{
|
||||
"identity_overlay_id": session.overlay_id,
|
||||
"identity_overlay_consumed": True,
|
||||
"identity_overlay_secret_removed": True,
|
||||
"identity_overlay_scope": OVERLAY_SCOPE,
|
||||
}
|
||||
)
|
||||
return response
|
||||
except (OwnerAuthorizationError, ProvisioningError) as exc:
|
||||
self.store.fail(
|
||||
session, error_code=exc.code, error_status=exc.status
|
||||
)
|
||||
raise
|
||||
except IdentityOverlayError as exc:
|
||||
self.store.fail(
|
||||
session, error_code=exc.code, error_status=exc.status
|
||||
)
|
||||
raise
|
||||
except Exception as exc:
|
||||
self.store.fail(
|
||||
session,
|
||||
error_code="IDENTITY_OVERLAY_INTERNAL_ERROR",
|
||||
error_status=500,
|
||||
)
|
||||
raise IdentityOverlayError(
|
||||
"IDENTITY_OVERLAY_INTERNAL_ERROR", 500
|
||||
) from exc
|
||||
@@ -0,0 +1,21 @@
|
||||
"""Task Plane runtime package."""
|
||||
|
||||
from .models import (
|
||||
EvidenceEnvelope,
|
||||
ProbeEvidence,
|
||||
ProbeOutcome,
|
||||
TaskPlan,
|
||||
TaskRecord,
|
||||
TaskStatus,
|
||||
TaskStateTransitionError,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"EvidenceEnvelope",
|
||||
"ProbeEvidence",
|
||||
"ProbeOutcome",
|
||||
"TaskPlan",
|
||||
"TaskRecord",
|
||||
"TaskStatus",
|
||||
"TaskStateTransitionError",
|
||||
]
|
||||
@@ -0,0 +1,17 @@
|
||||
"""Adapters for executing tasks via worker backends."""
|
||||
|
||||
from .base import WorkerAdapter
|
||||
from .openclaw import OpenClawAdapter
|
||||
from .codex import CodexAdapter
|
||||
from .hermes import HermesAdapter
|
||||
from .a2a import A2AAdapter
|
||||
from .systemd_worker import SystemdWorkerAdapter
|
||||
|
||||
__all__ = [
|
||||
"WorkerAdapter",
|
||||
"OpenClawAdapter",
|
||||
"CodexAdapter",
|
||||
"HermesAdapter",
|
||||
"A2AAdapter",
|
||||
"SystemdWorkerAdapter",
|
||||
]
|
||||
@@ -0,0 +1,31 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from .base import WorkerAdapter
|
||||
|
||||
|
||||
class A2AAdapter(WorkerAdapter):
|
||||
worker_name = "a2a"
|
||||
|
||||
def capabilities(self) -> list[str]:
|
||||
return ["task.exchange", "agent.handoff"]
|
||||
|
||||
def claim(self, task):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
|
||||
|
||||
def execute(self, task, claim):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
|
||||
|
||||
def heartbeat(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
|
||||
|
||||
def report_progress(self, claim, progress):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
|
||||
|
||||
def probe(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
|
||||
|
||||
def cancel(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
|
||||
|
||||
def collect_result(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
|
||||
@@ -0,0 +1,41 @@
|
||||
"""Base worker adapter contract."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
|
||||
|
||||
class WorkerAdapter(abc.ABC):
|
||||
worker_name = "base"
|
||||
|
||||
@abc.abstractmethod
|
||||
def capabilities(self) -> list[str]:
|
||||
raise NotImplementedError
|
||||
|
||||
@abc.abstractmethod
|
||||
def claim(self, task):
|
||||
raise NotImplementedError
|
||||
|
||||
@abc.abstractmethod
|
||||
def execute(self, task, claim):
|
||||
raise NotImplementedError
|
||||
|
||||
@abc.abstractmethod
|
||||
def heartbeat(self, claim):
|
||||
raise NotImplementedError
|
||||
|
||||
@abc.abstractmethod
|
||||
def report_progress(self, claim, progress):
|
||||
raise NotImplementedError
|
||||
|
||||
@abc.abstractmethod
|
||||
def probe(self, claim):
|
||||
raise NotImplementedError
|
||||
|
||||
@abc.abstractmethod
|
||||
def cancel(self, claim):
|
||||
raise NotImplementedError
|
||||
|
||||
@abc.abstractmethod
|
||||
def collect_result(self, claim):
|
||||
raise NotImplementedError
|
||||
@@ -0,0 +1,31 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from .base import WorkerAdapter
|
||||
|
||||
|
||||
class CodexAdapter(WorkerAdapter):
|
||||
worker_name = "codex"
|
||||
|
||||
def capabilities(self) -> list[str]:
|
||||
return ["code.read", "code.write.patch", "test.python", "review.security"]
|
||||
|
||||
def claim(self, task):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
|
||||
|
||||
def execute(self, task, claim):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
|
||||
|
||||
def heartbeat(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
|
||||
|
||||
def report_progress(self, claim, progress):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
|
||||
|
||||
def probe(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
|
||||
|
||||
def cancel(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
|
||||
|
||||
def collect_result(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
|
||||
@@ -0,0 +1,31 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from .base import WorkerAdapter
|
||||
|
||||
|
||||
class HermesAdapter(WorkerAdapter):
|
||||
worker_name = "hermes"
|
||||
|
||||
def capabilities(self) -> list[str]:
|
||||
return ["architecture.review", "policy.review", "threat.model"]
|
||||
|
||||
def claim(self, task):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
|
||||
|
||||
def execute(self, task, claim):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
|
||||
|
||||
def heartbeat(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
|
||||
|
||||
def report_progress(self, claim, progress):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
|
||||
|
||||
def probe(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
|
||||
|
||||
def cancel(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
|
||||
|
||||
def collect_result(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
|
||||
@@ -0,0 +1,31 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from .base import WorkerAdapter
|
||||
|
||||
|
||||
class OpenClawAdapter(WorkerAdapter):
|
||||
worker_name = "openclaw"
|
||||
|
||||
def capabilities(self) -> list[str]:
|
||||
return ["code.read", "code.write.patch", "test.execute", "runtime.shadow"]
|
||||
|
||||
def claim(self, task):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
|
||||
|
||||
def execute(self, task, claim):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
|
||||
|
||||
def heartbeat(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
|
||||
|
||||
def report_progress(self, claim, progress):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
|
||||
|
||||
def probe(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
|
||||
|
||||
def cancel(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
|
||||
|
||||
def collect_result(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
|
||||
@@ -0,0 +1,31 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from .base import WorkerAdapter
|
||||
|
||||
|
||||
class SystemdWorkerAdapter(WorkerAdapter):
|
||||
worker_name = "systemd_worker"
|
||||
|
||||
def capabilities(self) -> list[str]:
|
||||
return ["systemd.exec", "runtime.shell"]
|
||||
|
||||
def claim(self, task):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "claimed"}
|
||||
|
||||
def execute(self, task, claim):
|
||||
return {"worker": self.worker_name, "task_id": task.task_id, "status": "SHADOW_VERIFIED", "claim_id": claim.claim_id, "execution_mode": "shadow", "production_side_effects": False}
|
||||
|
||||
def heartbeat(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "alive"}
|
||||
|
||||
def report_progress(self, claim, progress):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "progress": progress}
|
||||
|
||||
def probe(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": claim.status}
|
||||
|
||||
def cancel(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "status": "cancelled"}
|
||||
|
||||
def collect_result(self, claim):
|
||||
return {"worker": self.worker_name, "claim_id": claim.claim_id, "result": "not_collected"}
|
||||
@@ -0,0 +1,27 @@
|
||||
"""Agent registry abstraction."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .errors import NotFoundError
|
||||
|
||||
|
||||
class AgentRegistry:
|
||||
def __init__(self):
|
||||
self._agents: dict[str, dict] = {}
|
||||
|
||||
def register(self, agent_id: str, metadata: dict) -> None:
|
||||
self._agents[agent_id] = {"agent_id": agent_id, **metadata}
|
||||
|
||||
def unregister(self, agent_id: str) -> None:
|
||||
if agent_id not in self._agents:
|
||||
raise NotFoundError("agent")
|
||||
del self._agents[agent_id]
|
||||
|
||||
def list(self) -> list[dict]:
|
||||
return list(self._agents.values())
|
||||
|
||||
def get(self, agent_id: str) -> dict:
|
||||
try:
|
||||
return self._agents[agent_id]
|
||||
except KeyError:
|
||||
raise NotFoundError("agent")
|
||||
@@ -0,0 +1,557 @@
|
||||
"""Task Plane HTTP API implementation (stdlib-only)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import time
|
||||
import uuid
|
||||
import urllib.parse
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from typing import Any, Callable
|
||||
|
||||
from .delegation import DelegationEngine
|
||||
from .errors import (
|
||||
ConflictError,
|
||||
ForbiddenError,
|
||||
NotFoundError,
|
||||
PayloadTooLargeError,
|
||||
TaskPlaneHTTPError,
|
||||
UnauthorizedError,
|
||||
ValidationError,
|
||||
)
|
||||
from .evidence import EvidenceService
|
||||
from .journal import TaskJournal
|
||||
from .lease import LeaseManager
|
||||
from .models import (
|
||||
EvidenceEnvelope,
|
||||
ResultEnvelope,
|
||||
TaskPlan,
|
||||
TaskRecord,
|
||||
iso8601_now,
|
||||
contains_secret_text,
|
||||
validate_identifier,
|
||||
)
|
||||
from .policy import PolicyEngine
|
||||
from .store import TaskPlaneStore
|
||||
from .worker_registry import WorkerRegistry
|
||||
|
||||
|
||||
def _json_payload(data: dict[str, Any], status: int = 200) -> tuple[int, bytes]:
|
||||
body = json.dumps(data, ensure_ascii=False).encode("utf-8")
|
||||
return status, body
|
||||
|
||||
|
||||
def _bounded_int(value: Any, name: str, minimum: int, maximum: int) -> int:
|
||||
try:
|
||||
number = int(value)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValidationError(f"invalid {name}") from exc
|
||||
if not minimum <= number <= maximum:
|
||||
raise ValidationError(f"invalid {name}")
|
||||
return number
|
||||
|
||||
|
||||
class TaskPlaneService:
|
||||
def __init__(self, store: TaskPlaneStore, policy: PolicyEngine | None = None):
|
||||
self.store = store
|
||||
self.policy = policy or PolicyEngine(
|
||||
execution_enabled=False,
|
||||
identity_capabilities={
|
||||
"anon": {"task.creator", "task.read", "task.audit"}
|
||||
},
|
||||
)
|
||||
self.journal = TaskJournal(store)
|
||||
self.lease = LeaseManager(store)
|
||||
self.workers = WorkerRegistry(store)
|
||||
self.evidence = EvidenceService(store)
|
||||
self.delegation = DelegationEngine(store)
|
||||
self.store.probe_attestation_verifier = self.policy.probe_attestation_verifier
|
||||
|
||||
def create_task(self, body: dict[str, Any], idempotency_key: str | None = None) -> dict[str, Any]:
|
||||
if body.get("parent_task_id"):
|
||||
raise ForbiddenError("child tasks must use the delegate endpoint")
|
||||
issuer = body.get("issuer", {})
|
||||
actor = issuer.get("id", "anon") if isinstance(issuer, dict) else "anon"
|
||||
self.policy.assert_allowed("create", actor)
|
||||
try:
|
||||
plan = TaskPlan.from_dict(body)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValidationError("invalid task plan") from exc
|
||||
task = self.store.create_task_with_event(plan, idempotency_key=idempotency_key)
|
||||
return task.to_dict()
|
||||
|
||||
def list_tasks(self, actor: str | None = None) -> list[dict[str, Any]]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor)
|
||||
return [task.to_dict(include_task=False) for task in self.store.list_tasks()]
|
||||
|
||||
def get_task(self, task_id: str, actor: str | None = None) -> dict[str, Any]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor, task=self.store.get_task(task_id))
|
||||
return self.store.get_task(task_id).to_dict()
|
||||
|
||||
def get_worker(self, worker_id: str, actor: str | None = None) -> dict[str, Any]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor)
|
||||
return self.workers.get(worker_id).to_dict()
|
||||
|
||||
def list_workers(self, actor: str | None = None) -> list[dict[str, Any]]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor)
|
||||
return [w.to_dict() for w in self.workers.list()]
|
||||
|
||||
def register_worker(self, body: dict[str, Any]) -> dict[str, Any]:
|
||||
actor = str(body.get("actor_identity") or body.get("identity") or "")
|
||||
is_admin = actor in self.policy.admin_identities
|
||||
try:
|
||||
existing = self.store.get_worker(str(body.get("worker_id") or ""))
|
||||
except NotFoundError:
|
||||
existing = None
|
||||
if existing is not None and str(body.get("identity") or "") != existing.identity:
|
||||
raise ConflictError("worker identity takeover rejected")
|
||||
self.policy.assert_readonly_worker_registration(actor, body)
|
||||
self.policy.assert_allowed(
|
||||
"worker.admin" if is_admin else "worker.register", actor
|
||||
)
|
||||
try:
|
||||
worker = self.workers.register(
|
||||
body,
|
||||
actor_identity=actor,
|
||||
is_admin=is_admin,
|
||||
expected_revision=body.get("expected_revision"),
|
||||
)
|
||||
except (TypeError, ValueError, KeyError) as exc:
|
||||
raise ValidationError("invalid worker registration") from exc
|
||||
return worker.to_dict()
|
||||
|
||||
def worker_heartbeat(self, worker_id: str, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
interval = payload.get("heartbeat_interval_seconds")
|
||||
actor = str(payload.get("actor_identity") or "")
|
||||
self.policy.assert_readonly_worker_binding(actor, worker_id)
|
||||
self.policy.assert_allowed("worker.register", actor)
|
||||
return self.workers.heartbeat(
|
||||
worker_id,
|
||||
heartbeat_interval_seconds=interval,
|
||||
actor_identity=actor,
|
||||
expected_revision=payload.get("expected_revision"),
|
||||
).to_dict()
|
||||
|
||||
def disable_worker(self, worker_id: str, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
actor = str(payload.get("actor_identity") or "")
|
||||
self.policy.assert_allowed("worker.admin", actor)
|
||||
return self.store.disable_worker(
|
||||
worker_id,
|
||||
actor_identity=actor,
|
||||
expected_revision=int(payload.get("expected_revision")),
|
||||
reason=str(payload.get("reason") or "disabled by administrator"),
|
||||
).to_dict()
|
||||
|
||||
def restore_worker(self, worker_id: str, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
actor = str(payload.get("actor_identity") or "")
|
||||
self.policy.assert_allowed("worker.admin", actor)
|
||||
return self.store.restore_worker(
|
||||
worker_id,
|
||||
actor_identity=actor,
|
||||
expected_revision=int(payload.get("expected_revision")),
|
||||
).to_dict()
|
||||
|
||||
def claim(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
self.policy.assert_allowed("claim", actor)
|
||||
worker_id = body.get("worker_id")
|
||||
if not worker_id:
|
||||
raise ValidationError("worker_id required")
|
||||
|
||||
task = self.store.get_task(task_id)
|
||||
self.policy.assert_readonly_worker_binding(actor, str(worker_id))
|
||||
self.policy.assert_allowed("claim", actor, task=task)
|
||||
lease_seconds = _bounded_int(
|
||||
body.get("lease_seconds", 30), "lease_seconds", 1, 3600
|
||||
)
|
||||
claim = self.lease.claim(
|
||||
task_id=task_id,
|
||||
worker_id=worker_id,
|
||||
worker_identity=actor,
|
||||
lease_seconds=lease_seconds,
|
||||
expected_revision=task.revision,
|
||||
operation_digest=task.task_plan.operation_digest(),
|
||||
)
|
||||
return {"claim_id": claim.claim_id, **claim.to_dict()}
|
||||
|
||||
def heartbeat(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
claim_id = body.get("claim_id")
|
||||
if not claim_id:
|
||||
raise ValidationError("claim_id required")
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
task = self.store.get_task(task_id)
|
||||
claim = self.store.get_claim(claim_id)
|
||||
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
|
||||
self.policy.assert_allowed("heartbeat", actor, task=task)
|
||||
if claim.worker_identity != actor:
|
||||
raise ForbiddenError("claim identity mismatch")
|
||||
lease_seconds = _bounded_int(
|
||||
body.get("lease_seconds", 30), "lease_seconds", 1, 3600
|
||||
)
|
||||
claim = self.lease.heartbeat(task_id, claim_id, lease_seconds)
|
||||
return {"claim_id": claim_id, "lease_until": claim.lease_until}
|
||||
|
||||
def progress(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
claim_id = body.get("claim_id")
|
||||
if not claim_id:
|
||||
raise ValidationError("claim_id required")
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
progress = body.get("progress")
|
||||
stage = body.get("stage", "RUNNING")
|
||||
message = body.get("message")
|
||||
if progress is None:
|
||||
raise ValidationError("progress required")
|
||||
task = self.store.get_task(task_id)
|
||||
claim = self.store.get_claim(claim_id)
|
||||
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
|
||||
self.policy.assert_allowed("progress", actor, task=task)
|
||||
if task.task_plan.data_classification == "credential-secret":
|
||||
if message not in {None, ""} or contains_secret_text(stage):
|
||||
raise ValidationError(
|
||||
"credential-secret progress must contain metadata only"
|
||||
)
|
||||
lease_seconds = _bounded_int(
|
||||
body.get("lease_seconds", 30), "lease_seconds", 1, 3600
|
||||
)
|
||||
claim = self.store.record_progress(
|
||||
task_id,
|
||||
claim_id,
|
||||
actor,
|
||||
progress=progress,
|
||||
stage=str(stage),
|
||||
message=None if message is None else str(message),
|
||||
lease_seconds=lease_seconds,
|
||||
)
|
||||
return {"claim_id": claim.claim_id, "status": claim.status, "progress": progress}
|
||||
|
||||
def complete(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
claim_id = body.get("claim_id")
|
||||
if not claim_id:
|
||||
raise ValidationError("claim_id required")
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
task = self.store.get_task(task_id)
|
||||
|
||||
status = body.get("status", "COMPLETED")
|
||||
outputs = body.get("outputs", [])
|
||||
evidences = body.get("evidence", [])
|
||||
if not isinstance(outputs, list):
|
||||
raise ValidationError("outputs must be list")
|
||||
if not isinstance(evidences, list):
|
||||
raise ValidationError("evidence must be list")
|
||||
if any(not isinstance(ev, dict) for ev in evidences):
|
||||
raise ValidationError("evidence items must be objects")
|
||||
claim = self.store.get_claim(claim_id)
|
||||
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
|
||||
self.policy.assert_allowed("result", actor, task=task)
|
||||
if claim.worker_identity != actor:
|
||||
raise ForbiddenError("claim identity mismatch")
|
||||
if task.task_plan.data_classification == "credential-secret":
|
||||
allowed_result_keys = {
|
||||
"kind",
|
||||
"hash",
|
||||
"sha256",
|
||||
"count",
|
||||
"status",
|
||||
"error_code",
|
||||
"signature",
|
||||
"attestation_ref",
|
||||
}
|
||||
for entry in [*outputs, *evidences]:
|
||||
if (
|
||||
not isinstance(entry, dict)
|
||||
or set(entry) - allowed_result_keys
|
||||
or contains_secret_text(entry)
|
||||
):
|
||||
raise ValidationError(
|
||||
"credential-secret result must contain hash/count/status only"
|
||||
)
|
||||
|
||||
result = ResultEnvelope(
|
||||
task_id=task_id,
|
||||
claim_id=claim_id,
|
||||
worker_identity=actor,
|
||||
status=status,
|
||||
outputs=outputs,
|
||||
evidence=evidences,
|
||||
started_at=str(body.get("started_at") or iso8601_now()),
|
||||
completed_at=str(body.get("completed_at") or iso8601_now()),
|
||||
result_digest=body.get("result_digest"),
|
||||
signature=body.get("signature"),
|
||||
attestation_ref=body.get("attestation_ref"),
|
||||
operation_digest=claim.operation_digest,
|
||||
)
|
||||
evidence_decision = self.policy.evidence_verifier.verify(task, evidences)
|
||||
if not evidence_decision.allowed:
|
||||
raise ForbiddenError(evidence_decision.reason)
|
||||
result_decision = self.policy.verify_result(result, task)
|
||||
if not result_decision.allowed:
|
||||
raise ForbiddenError(result_decision.reason)
|
||||
result.result_digest = result.computed_digest()
|
||||
previous = self.store._last_evidence_hash(task_id)
|
||||
evidence_entries = []
|
||||
for evidence in evidences:
|
||||
envelope = EvidenceEnvelope.create(
|
||||
task_id=task_id,
|
||||
claim_id=claim_id,
|
||||
kind=str(evidence.get("kind") or evidence.get("type") or "generic"),
|
||||
worker_identity=actor,
|
||||
payload=evidence,
|
||||
previous_evidence_hash=previous,
|
||||
signature=evidence.get("signature"),
|
||||
attestation_ref=evidence.get("attestation_ref"),
|
||||
)
|
||||
evidence_entries.append(envelope)
|
||||
previous = envelope.evidence_digest
|
||||
self.store.complete_claim_with_evidence_and_event(
|
||||
task_id,
|
||||
claim_id,
|
||||
status
|
||||
if status
|
||||
in {"COMPLETED", "FAILED_FINAL", "FAILED_RECOVERABLE", "CANCELLED"}
|
||||
else "COMPLETED",
|
||||
result.to_dict(),
|
||||
evidence_entries,
|
||||
)
|
||||
return result.to_dict()
|
||||
|
||||
def fail(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
claim_id = body.get("claim_id")
|
||||
if not claim_id:
|
||||
raise ValidationError("claim_id required")
|
||||
reason = body.get("reason", "failed")
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
self.policy.assert_allowed("fail", actor)
|
||||
task = self.store.get_task(task_id)
|
||||
self.policy.assert_allowed("fail", actor, task=task)
|
||||
claim = self.store.get_claim(claim_id)
|
||||
if claim.worker_identity != actor:
|
||||
raise ForbiddenError("claim identity mismatch")
|
||||
status = "FAILED_RECOVERABLE" if body.get("recoverable", False) else "FAILED_FINAL"
|
||||
self.store.fail_claim_with_event(task_id, claim_id, status, str(reason))
|
||||
return {"task_id": task_id, "status": status, "reason": reason}
|
||||
|
||||
def cancel(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "owner"
|
||||
self.policy.assert_allowed("cancel", actor)
|
||||
reason = body.get("reason", "cancelled")
|
||||
task = self.store.get_task(task_id)
|
||||
self.policy.assert_allowed("cancel", actor, task=task)
|
||||
updated = self.store.cancel_task_with_event(
|
||||
task_id, task.revision, reason=reason
|
||||
)
|
||||
return updated.to_dict()
|
||||
|
||||
def delegate(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
actor = body.get("actor_identity") or "owner"
|
||||
self.policy.assert_allowed("delegate", actor)
|
||||
parent = self.store.get_task(task_id)
|
||||
self.policy.assert_allowed("delegate", actor, task=parent)
|
||||
if "task" in body:
|
||||
try:
|
||||
child_plan = TaskPlan.from_dict(body["task"])
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValidationError("invalid child task plan") from exc
|
||||
else:
|
||||
plan_body = dict(body)
|
||||
plan_body.pop("actor_identity", None)
|
||||
try:
|
||||
child_plan = TaskPlan.from_dict(plan_body)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValidationError("invalid child task plan") from exc
|
||||
child_plan.parent_task_id = task_id
|
||||
child = self.delegation.delegate(task_id, child_plan, caller=actor)
|
||||
return child.to_dict()
|
||||
|
||||
def get_events(self, task_id: str, actor: str | None = None) -> list[dict[str, Any]]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("audit", actor, task=self.store.get_task(task_id))
|
||||
self.store.get_task(task_id)
|
||||
return self.store.list_events(task_id)
|
||||
|
||||
def get_evidence(self, task_id: str, actor: str | None = None) -> list[dict[str, Any]]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("audit", actor, task=self.store.get_task(task_id))
|
||||
self.store.get_task(task_id)
|
||||
return self.evidence.list(task_id)
|
||||
|
||||
def get_children(self, task_id: str, actor: str | None = None) -> list[str]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor, task=self.store.get_task(task_id))
|
||||
self.store.get_task(task_id)
|
||||
return self.store.list_children(task_id)
|
||||
|
||||
|
||||
class TaskPlaneRequestHandler(BaseHTTPRequestHandler):
|
||||
service: TaskPlaneService | None = None
|
||||
authenticator: Callable[[str], str | None] | None = None
|
||||
max_body_bytes = 1_000_000
|
||||
|
||||
def log_message(self, format: str, *args: Any) -> None:
|
||||
# BaseHTTPRequestHandler logs the raw request target; suppress it so
|
||||
# attacker-controlled paths or query strings cannot leak credentials.
|
||||
return
|
||||
|
||||
def _json(self) -> tuple[str | None, dict[str, Any]]:
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length", "0"))
|
||||
except ValueError as exc:
|
||||
raise ValidationError("invalid content length") from exc
|
||||
if length < 0:
|
||||
raise ValidationError("invalid content length")
|
||||
if length > self.max_body_bytes:
|
||||
raise PayloadTooLargeError("payload exceeds limit")
|
||||
raw = self.rfile.read(length) if length > 0 else b""
|
||||
if not raw:
|
||||
return None, {}
|
||||
try:
|
||||
decoded = raw.decode("utf-8")
|
||||
payload = json.loads(decoded)
|
||||
if not isinstance(payload, dict):
|
||||
raise ValidationError("JSON payload must be an object")
|
||||
return decoded, payload
|
||||
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
|
||||
raise ValidationError("invalid JSON payload") from exc
|
||||
|
||||
def _response(self, status: int, payload: Any) -> None:
|
||||
encoded = json.dumps(payload, ensure_ascii=False).encode("utf-8")
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json; charset=utf-8")
|
||||
self.send_header("Content-Length", str(len(encoded)))
|
||||
self.end_headers()
|
||||
self.wfile.write(encoded)
|
||||
|
||||
def _authenticated_identity(self) -> str:
|
||||
authenticator = type(self).authenticator
|
||||
if authenticator is None:
|
||||
raise UnauthorizedError("authentication unavailable")
|
||||
header = self.headers.get("Authorization", "")
|
||||
if not header.startswith("Bearer "):
|
||||
raise UnauthorizedError("bearer authentication required")
|
||||
token = header[7:]
|
||||
if not token or any(ord(ch) < 33 for ch in token):
|
||||
raise UnauthorizedError("invalid bearer token")
|
||||
identity = authenticator(token)
|
||||
if not identity:
|
||||
raise UnauthorizedError("invalid credentials")
|
||||
return str(identity)
|
||||
|
||||
def _handle(self, handler):
|
||||
try:
|
||||
if self.service is None:
|
||||
raise TaskPlaneHTTPError("service not configured")
|
||||
result = handler()
|
||||
if isinstance(result, tuple):
|
||||
status, payload = result
|
||||
else:
|
||||
status, payload = 200, result
|
||||
self._response(status, payload)
|
||||
except TaskPlaneHTTPError as exc:
|
||||
self._response(exc.status_code, exc.to_payload())
|
||||
except Exception as exc: # defensive
|
||||
if isinstance(exc, TaskPlaneHTTPError):
|
||||
raise
|
||||
self._response(
|
||||
500,
|
||||
{"error": "internal_error", "message": "internal server error"},
|
||||
)
|
||||
|
||||
def do_GET(self): # noqa: N802
|
||||
def route():
|
||||
path = urllib.parse.urlparse(self.path).path
|
||||
parts = [p for p in path.split("/") if p]
|
||||
for part in parts[1:]:
|
||||
if part not in {"events", "evidence", "children", "heartbeat"}:
|
||||
try:
|
||||
validate_identifier(part, "resource identifier")
|
||||
except ValueError as exc:
|
||||
raise ValidationError("invalid resource identifier") from exc
|
||||
identity = self._authenticated_identity()
|
||||
|
||||
if len(parts) == 1 and parts[0] == "tasks":
|
||||
return 200, self.service.list_tasks(identity)
|
||||
if len(parts) == 2 and parts[0] == "tasks":
|
||||
task_id = parts[1]
|
||||
return 200, self.service.get_task(task_id, identity)
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "events":
|
||||
return 200, self.service.get_events(parts[1], identity)
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "evidence":
|
||||
return 200, self.service.get_evidence(parts[1], identity)
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "children":
|
||||
return 200, self.service.get_children(parts[1], identity)
|
||||
if len(parts) == 1 and parts[0] == "workers":
|
||||
return 200, self.service.list_workers(identity)
|
||||
if len(parts) == 2 and parts[0] == "workers":
|
||||
return 200, self.service.get_worker(parts[1], identity)
|
||||
raise NotFoundError("unknown endpoint")
|
||||
|
||||
self._handle(route)
|
||||
|
||||
def do_POST(self): # noqa: N802
|
||||
def route():
|
||||
body_text, body = self._json()
|
||||
identity = self._authenticated_identity()
|
||||
path = urllib.parse.urlparse(self.path).path
|
||||
parts = [p for p in path.split("/") if p]
|
||||
headers = {k.lower(): v for k, v in self.headers.items()}
|
||||
|
||||
if len(parts) == 1 and parts[0] == "tasks":
|
||||
issuer = body.get("issuer")
|
||||
if issuer and (
|
||||
not isinstance(issuer, dict) or issuer.get("id") != identity
|
||||
):
|
||||
raise ForbiddenError("issuer identity mismatch")
|
||||
body["issuer"] = {"type": "authenticated", "id": identity}
|
||||
return 201, self.service.create_task(body or {}, headers.get("idempotency-key"))
|
||||
if body.get("actor_identity") not in {None, identity}:
|
||||
raise ForbiddenError("actor identity mismatch")
|
||||
body["actor_identity"] = identity
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "claim":
|
||||
return 200, self.service.claim(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "heartbeat":
|
||||
return 200, self.service.heartbeat(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "progress":
|
||||
return 200, self.service.progress(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "result":
|
||||
return 200, self.service.complete(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "fail":
|
||||
return 200, self.service.fail(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "cancel":
|
||||
return 200, self.service.cancel(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "tasks" and parts[2] == "delegate":
|
||||
return 200, self.service.delegate(parts[1], body or {})
|
||||
|
||||
if len(parts) == 2 and parts[0] == "workers" and parts[1] == "register":
|
||||
if (
|
||||
body.get("identity") != identity
|
||||
and identity not in self.service.policy.admin_identities
|
||||
):
|
||||
raise ForbiddenError("worker identity mismatch")
|
||||
return 201, self.service.register_worker(body or {})
|
||||
if len(parts) == 3 and parts[0] == "workers" and parts[2] == "heartbeat":
|
||||
return 200, self.service.worker_heartbeat(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "workers" and parts[2] == "disable":
|
||||
return 200, self.service.disable_worker(parts[1], body or {})
|
||||
if len(parts) == 3 and parts[0] == "workers" and parts[2] == "restore":
|
||||
return 200, self.service.restore_worker(parts[1], body or {})
|
||||
raise NotFoundError("unknown endpoint")
|
||||
|
||||
self._handle(route)
|
||||
|
||||
|
||||
def run_server(
|
||||
host: str,
|
||||
port: int,
|
||||
service: TaskPlaneService,
|
||||
*,
|
||||
authenticator: Callable[[str], str | None] | None = None,
|
||||
):
|
||||
handler = TaskPlaneRequestHandler
|
||||
handler.service = service
|
||||
handler.authenticator = authenticator
|
||||
server = ThreadingHTTPServer((host, port), handler)
|
||||
server.serve_forever()
|
||||
@@ -0,0 +1,36 @@
|
||||
"""Capability matcher helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from fnmatch import fnmatch
|
||||
|
||||
|
||||
def _normalize_capability(capability: str) -> str:
|
||||
return capability.strip().lower()
|
||||
|
||||
|
||||
def capability_matches(granted: str, required: str) -> bool:
|
||||
granted = _normalize_capability(granted)
|
||||
required = _normalize_capability(required)
|
||||
if granted == required:
|
||||
return True
|
||||
# A granted wildcard such as "test.*" should match required "test.unit"
|
||||
if "*" in granted:
|
||||
return fnmatch(required, granted)
|
||||
# A required wildcard is treated as a suffix/prefix requirement for callers.
|
||||
if "*" in required:
|
||||
return fnmatch(granted, required)
|
||||
return False
|
||||
|
||||
|
||||
def has_capabilities(granted_caps: list[str], required_caps: list[str]) -> bool:
|
||||
granted = [_normalize_capability(c) for c in granted_caps]
|
||||
for required in required_caps:
|
||||
required = _normalize_capability(required)
|
||||
if not any(capability_matches(g, required) for g in granted):
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def normalize_capabilities(caps: list[str]) -> list[str]:
|
||||
return sorted({_normalize_capability(cap) for cap in caps})
|
||||
@@ -0,0 +1,87 @@
|
||||
"""Delegation guardrails."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .errors import ConflictError, ForbiddenError, NotFoundError
|
||||
from .models import Budget, TaskPlan, TaskRecord
|
||||
from .store import TaskPlaneStore
|
||||
|
||||
|
||||
class DelegationEngine:
|
||||
def __init__(self, store: TaskPlaneStore):
|
||||
self.store = store
|
||||
|
||||
def can_delegate(self, parent_id: str, child_plan: TaskPlan) -> bool:
|
||||
parent = self.store.get_task(parent_id)
|
||||
if parent.status == "COMPLETED":
|
||||
raise ConflictError("cannot delegate completed task")
|
||||
if parent.task_plan.max_delegation_depth <= 0:
|
||||
raise ConflictError("max delegation depth not configured")
|
||||
|
||||
depth = self._depth(parent_id)
|
||||
if depth >= parent.task_plan.max_delegation_depth:
|
||||
raise ConflictError("max delegation depth reached")
|
||||
|
||||
if child_plan.parent_task_id not in {None, parent_id}:
|
||||
raise ConflictError("delegation parent mismatch")
|
||||
current = parent_id
|
||||
while current:
|
||||
if child_plan.task_id and current == child_plan.task_id:
|
||||
raise ConflictError("delegation cycle")
|
||||
current = self.store.parent_of(current)
|
||||
return True
|
||||
|
||||
def delegate(self, parent_id: str, child_plan: TaskPlan, *, caller: str) -> TaskRecord:
|
||||
self.can_delegate(parent_id, child_plan)
|
||||
parent = self.store.get_task(parent_id)
|
||||
if child_plan.required_capabilities and not set(child_plan.required_capabilities).issubset(
|
||||
set(parent.task_plan.required_capabilities or [])
|
||||
):
|
||||
raise ForbiddenError("child capabilities exceed parent constraints")
|
||||
risk_rank = {"low": 1, "medium": 2, "high": 3}
|
||||
if risk_rank.get(child_plan.risk, 99) > risk_rank.get(parent.task_plan.risk, -1):
|
||||
raise ForbiddenError("child risk exceeds parent constraints")
|
||||
child_plan.parent_task_id = parent_id
|
||||
child_plan.correlation_id = parent.task_plan.correlation_id or parent.task_id
|
||||
child_plan.preferred_workers = parent.task_plan.preferred_workers
|
||||
child_plan.max_delegation_depth = min(
|
||||
child_plan.max_delegation_depth,
|
||||
parent.task_plan.max_delegation_depth,
|
||||
)
|
||||
child_plan.approval_policy = parent.task_plan.approval_policy
|
||||
|
||||
parent_budget = self.store.get_task_budget(parent_id)
|
||||
required = Budget()
|
||||
for name in ("time_seconds", "attempts", "tokens", "cost"):
|
||||
available = getattr(parent_budget, name)
|
||||
requested = getattr(child_plan.budgets, name)
|
||||
if name == "attempts" and requested is None:
|
||||
requested = 1
|
||||
if available is not None:
|
||||
requested = 0 if requested is None else requested
|
||||
if requested > available:
|
||||
raise ConflictError(f"budget exceeded for {name}")
|
||||
setattr(child_plan.budgets, name, requested)
|
||||
setattr(required, name, requested)
|
||||
|
||||
# A retried identical delegation is a read, not a second budget charge.
|
||||
if child_plan.task_id:
|
||||
try:
|
||||
existing = self.store.get_task(child_plan.task_id)
|
||||
except NotFoundError:
|
||||
existing = None
|
||||
if existing is not None:
|
||||
if (
|
||||
existing.task_plan.parent_task_id == parent_id
|
||||
and existing.task_plan.operation_digest()
|
||||
== child_plan.operation_digest()
|
||||
):
|
||||
return existing
|
||||
raise ConflictError("delegation task_id conflict")
|
||||
|
||||
return self.store.delegate_task_with_budget_and_events(
|
||||
parent_id, child_plan, caller=caller
|
||||
)
|
||||
|
||||
def _depth(self, task_id: str) -> int:
|
||||
return self.store._compute_depth(task_id)
|
||||
@@ -0,0 +1,71 @@
|
||||
"""Error types for task plane operations."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
|
||||
class TaskPlaneError(Exception):
|
||||
"""Base exception for API-compatible failures."""
|
||||
|
||||
status_code = 500
|
||||
error_code = "task_plane_error"
|
||||
|
||||
def __init__(self, message: str, *, code: str | None = None, details: dict | None = None):
|
||||
super().__init__(message)
|
||||
self.message = message
|
||||
self.details = details or {}
|
||||
if code:
|
||||
self.error_code = code
|
||||
|
||||
def to_payload(self) -> dict:
|
||||
return {"error": self.error_code, "message": self.message, "details": self.details}
|
||||
|
||||
|
||||
class TaskPlaneHTTPError(TaskPlaneError):
|
||||
"""Base class with explicit HTTP status."""
|
||||
|
||||
status_code = 500
|
||||
|
||||
|
||||
class ValidationError(TaskPlaneHTTPError):
|
||||
status_code = 400
|
||||
error_code = "validation_error"
|
||||
|
||||
|
||||
class UnauthorizedError(TaskPlaneHTTPError):
|
||||
status_code = 401
|
||||
error_code = "unauthorized"
|
||||
|
||||
|
||||
class ForbiddenError(TaskPlaneHTTPError):
|
||||
status_code = 403
|
||||
error_code = "forbidden"
|
||||
|
||||
|
||||
class NotFoundError(TaskPlaneHTTPError):
|
||||
status_code = 404
|
||||
error_code = "not_found"
|
||||
|
||||
|
||||
class ConflictError(TaskPlaneHTTPError):
|
||||
status_code = 409
|
||||
error_code = "conflict"
|
||||
|
||||
|
||||
class PayloadTooLargeError(TaskPlaneHTTPError):
|
||||
status_code = 413
|
||||
error_code = "payload_too_large"
|
||||
|
||||
|
||||
class FailedDependencyError(TaskPlaneHTTPError):
|
||||
status_code = 424
|
||||
error_code = "failed_dependency"
|
||||
|
||||
|
||||
class LockedError(TaskPlaneHTTPError):
|
||||
status_code = 423
|
||||
error_code = "locked"
|
||||
|
||||
|
||||
class ServiceUnavailableError(TaskPlaneHTTPError):
|
||||
status_code = 503
|
||||
error_code = "service_unavailable"
|
||||
@@ -0,0 +1,108 @@
|
||||
"""CloudEvents-compatible event envelope and durable outbox helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
from typing import Callable, Protocol
|
||||
|
||||
from .store import TaskPlaneStore
|
||||
|
||||
|
||||
@dataclass
|
||||
class CloudEvent:
|
||||
specversion: str = "1.0"
|
||||
id: str = ""
|
||||
type: str = ""
|
||||
source: str = "spiffe://aios/task-plane"
|
||||
subject: str = ""
|
||||
datacontenttype: str = "application/json"
|
||||
data: dict | None = None
|
||||
|
||||
@property
|
||||
def time(self) -> str:
|
||||
return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
|
||||
|
||||
def asdict(self) -> dict:
|
||||
return {
|
||||
"specversion": self.specversion,
|
||||
"id": self.id,
|
||||
"type": self.type,
|
||||
"source": self.source,
|
||||
"subject": self.subject,
|
||||
"time": self.time,
|
||||
"datacontenttype": self.datacontenttype,
|
||||
"data": self.data or {},
|
||||
}
|
||||
|
||||
|
||||
NOT_DELIVERED = "NOT_DELIVERED"
|
||||
DELIVERED = "DELIVERED"
|
||||
FAILED_DELIVERY = "FAILED"
|
||||
|
||||
|
||||
class NotificationAdapter(Protocol):
|
||||
name: str
|
||||
|
||||
def deliver(self, envelope: dict) -> str | None:
|
||||
"""Return a provider receipt, or None when delivery is unconfirmed."""
|
||||
|
||||
|
||||
class CallbackNotificationAdapter:
|
||||
"""Adapter seam for webhook, NATS, GPT, dashboard, and WeChat transports."""
|
||||
|
||||
def __init__(self, name: str, callback: Callable[[dict], str | None]):
|
||||
self.name = name
|
||||
self._callback = callback
|
||||
|
||||
def deliver(self, envelope: dict) -> str | None:
|
||||
return self._callback(envelope)
|
||||
|
||||
|
||||
class WebhookAdapter(CallbackNotificationAdapter):
|
||||
def __init__(self, callback: Callable[[dict], str | None]):
|
||||
super().__init__("webhook", callback)
|
||||
|
||||
|
||||
class NatsJetStreamAdapter(CallbackNotificationAdapter):
|
||||
def __init__(self, callback: Callable[[dict], str | None]):
|
||||
super().__init__("nats-jetstream", callback)
|
||||
|
||||
|
||||
class GPTResultCallbackAdapter(CallbackNotificationAdapter):
|
||||
def __init__(self, callback: Callable[[dict], str | None]):
|
||||
super().__init__("gpt-result-callback", callback)
|
||||
|
||||
|
||||
class DashboardAdapter(CallbackNotificationAdapter):
|
||||
def __init__(self, callback: Callable[[dict], str | None]):
|
||||
super().__init__("dashboard", callback)
|
||||
|
||||
|
||||
class WeChatGatewayAdapter(CallbackNotificationAdapter):
|
||||
def __init__(self, callback: Callable[[dict], str | None]):
|
||||
super().__init__("wechat-gateway", callback)
|
||||
|
||||
|
||||
class DurableOutboxDispatcher:
|
||||
def __init__(self, store: TaskPlaneStore):
|
||||
self.store = store
|
||||
|
||||
def dispatch(self, message_id: str, adapter: NotificationAdapter) -> dict:
|
||||
row = self.store.get_outbox_message(message_id)
|
||||
import json
|
||||
|
||||
envelope = json.loads(row["payload"])
|
||||
try:
|
||||
receipt = adapter.deliver(envelope)
|
||||
except Exception:
|
||||
return self.store.record_outbox_delivery(
|
||||
message_id,
|
||||
receipt=None,
|
||||
error=f"{adapter.name} delivery failed",
|
||||
)
|
||||
return self.store.record_outbox_delivery(
|
||||
message_id,
|
||||
receipt=str(receipt) if receipt else None,
|
||||
error=None if receipt else f"{adapter.name} receipt unavailable",
|
||||
)
|
||||
@@ -0,0 +1,31 @@
|
||||
"""Evidence helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
|
||||
from .store import TaskPlaneStore
|
||||
|
||||
|
||||
def evidence_digest(payload: dict) -> str:
|
||||
body = json.dumps(payload, sort_keys=True, separators=(",", ":"))
|
||||
return hashlib.sha256(body.encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
class EvidenceService:
|
||||
def __init__(self, store: TaskPlaneStore):
|
||||
self.store = store
|
||||
|
||||
def add(self, task_id: str, kind: str, payload: dict, worker_identity: str) -> str:
|
||||
return self.store.add_evidence(task_id, kind, payload, worker_identity)
|
||||
|
||||
def list(self, task_id: str) -> list[dict]:
|
||||
return self.store.list_evidence(task_id)
|
||||
|
||||
def verify(self, task_id: str, required_kinds: list[str]) -> bool:
|
||||
evidences = self.list(task_id)
|
||||
observed = {e["kind"] for e in evidences}
|
||||
return set(required_kinds).issubset(
|
||||
observed
|
||||
) and self.store.verify_evidence_integrity(task_id)
|
||||
@@ -0,0 +1,22 @@
|
||||
"""Event journaling helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .errors import ValidationError
|
||||
from .store import TaskPlaneStore
|
||||
|
||||
|
||||
class TaskJournal:
|
||||
def __init__(self, store: TaskPlaneStore):
|
||||
self.store = store
|
||||
|
||||
def append(self, task_id: str, event_type: str, data: dict, *, subject: str | None = None) -> None:
|
||||
if not event_type:
|
||||
raise ValidationError("event_type required")
|
||||
self.store.append_event(task_id, event_type, data, subject=subject)
|
||||
|
||||
def list(self, task_id: str) -> list[dict]:
|
||||
return self.store.list_events(task_id)
|
||||
|
||||
def check_chain(self, task_id: str) -> bool:
|
||||
return self.store.verify_event_chain(task_id)
|
||||
@@ -0,0 +1,32 @@
|
||||
"""Claim and lease management helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .errors import LockedError
|
||||
from .models import ProbeEvidence
|
||||
from .store import TaskPlaneStore
|
||||
|
||||
|
||||
class LeaseManager:
|
||||
def __init__(self, store: TaskPlaneStore):
|
||||
self.store = store
|
||||
|
||||
def claim(self, task_id: str, worker_id: str, worker_identity: str, lease_seconds: int, expected_revision: int, operation_digest: str):
|
||||
return self.store.claim_task(task_id, worker_id, worker_identity, lease_seconds, expected_revision, operation_digest)
|
||||
|
||||
def heartbeat(self, task_id: str, claim_id: str, lease_seconds: int):
|
||||
claim = self.store.heartbeat_claim(task_id, claim_id, lease_seconds)
|
||||
return claim
|
||||
|
||||
def probe(self, claim_id: str):
|
||||
claim = self.store.get_claim(claim_id)
|
||||
if claim.status != "ACTIVE":
|
||||
raise LockedError("claim not active")
|
||||
return claim
|
||||
|
||||
def recover(self, task_id: str, claim_id: str, probe: ProbeEvidence):
|
||||
return self.store.recover_expired_claim(
|
||||
task_id,
|
||||
claim_id,
|
||||
probe,
|
||||
)
|
||||
@@ -0,0 +1,829 @@
|
||||
"""Core data models for the task plane."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
import uuid
|
||||
import urllib.parse
|
||||
from enum import StrEnum
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
|
||||
SENSITIVE_KEYS = {
|
||||
"secret",
|
||||
"password",
|
||||
"token",
|
||||
"api_key",
|
||||
"access_token",
|
||||
"refresh_token",
|
||||
"authorization",
|
||||
"private_key",
|
||||
"client_secret",
|
||||
"credential",
|
||||
}
|
||||
IDENTIFIER_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9._:-]{0,127}")
|
||||
TYPE_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9._-]{0,127}")
|
||||
RISK_LEVELS = {"low", "medium", "high"}
|
||||
DATA_CLASSIFICATIONS = {
|
||||
"public",
|
||||
"internal",
|
||||
"confidential",
|
||||
"credential-secret",
|
||||
}
|
||||
SECRET_TEXT_PATTERNS = (
|
||||
re.compile(r"(?i)\bAuthorization\s*:\s*Bearer\s+\S+"),
|
||||
re.compile(r"(?i)\b(?:password|passwd|api[_-]?key|access[_-]?token|secret)\s*[:=]\s*\S+"),
|
||||
re.compile(r"\bsk-[A-Za-z0-9_-]{12,}\b"),
|
||||
re.compile(r"\bAKIA[0-9A-Z]{16}\b"),
|
||||
re.compile(r"-----BEGIN (?:RSA |EC |OPENSSH )?PRIVATE KEY-----"),
|
||||
)
|
||||
TASK_PLAN_KEYS = {
|
||||
"schema_version",
|
||||
"task_id",
|
||||
"task_type",
|
||||
"issuer",
|
||||
"intent",
|
||||
"required_capabilities",
|
||||
"preferred_workers",
|
||||
"risk",
|
||||
"approval_policy",
|
||||
"dependencies",
|
||||
"max_delegation_depth",
|
||||
"budgets",
|
||||
"evidence_requirements",
|
||||
"parent_task_id",
|
||||
"correlation_id",
|
||||
"metadata",
|
||||
"data_classification",
|
||||
"execution_zone",
|
||||
"network_policy",
|
||||
"logging_policy",
|
||||
"allowed_input_paths",
|
||||
"allowed_output_paths",
|
||||
"output_policy",
|
||||
}
|
||||
|
||||
|
||||
def _now_ts() -> float:
|
||||
return time.time()
|
||||
|
||||
|
||||
def canonical_json(value: Any) -> str:
|
||||
return json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
|
||||
|
||||
|
||||
def compute_sha256_hex(value: Any) -> str:
|
||||
return hashlib.sha256(canonical_json(value).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def contains_secret_text(value: Any) -> bool:
|
||||
if isinstance(value, str):
|
||||
return any(pattern.search(value) for pattern in SECRET_TEXT_PATTERNS)
|
||||
if isinstance(value, dict):
|
||||
return any(contains_secret_text(item) for item in value.values())
|
||||
if isinstance(value, (list, tuple)):
|
||||
return any(contains_secret_text(item) for item in value)
|
||||
return False
|
||||
|
||||
|
||||
def validate_relative_paths(values: Any, name: str) -> list[str]:
|
||||
paths = _normalize_list(values)
|
||||
for value in paths:
|
||||
decoded = urllib.parse.unquote(value)
|
||||
parts = value.replace("\\", "/").split("/")
|
||||
if (
|
||||
decoded != value
|
||||
or "\\" in value
|
||||
or value.startswith("/")
|
||||
or re.match(r"^[A-Za-z]:", value)
|
||||
or any(part in {"", ".", ".."} for part in parts)
|
||||
):
|
||||
raise ValueError(f"invalid {name}")
|
||||
return paths
|
||||
|
||||
|
||||
def validate_identifier(value: Any, name: str) -> str:
|
||||
text = str(value or "")
|
||||
if (
|
||||
not IDENTIFIER_RE.fullmatch(text)
|
||||
or urllib.parse.unquote(text) != text
|
||||
or any(ord(ch) < 32 or ord(ch) == 127 for ch in text)
|
||||
):
|
||||
raise ValueError(f"invalid {name}")
|
||||
return text
|
||||
|
||||
|
||||
def validate_type(value: Any, name: str) -> str:
|
||||
text = str(value or "")
|
||||
if not TYPE_RE.fullmatch(text):
|
||||
raise ValueError(f"invalid {name}")
|
||||
return text
|
||||
|
||||
|
||||
def redact_value(value: Any) -> Any:
|
||||
if isinstance(value, dict):
|
||||
redacted = {}
|
||||
for key, inner in value.items():
|
||||
lowered = str(key).lower()
|
||||
if lowered in SENSITIVE_KEYS or lowered.endswith(
|
||||
("_password", "_secret", "_access_token", "_refresh_token", "_private_key")
|
||||
):
|
||||
redacted[key] = "[REDACTED]"
|
||||
else:
|
||||
redacted[key] = redact_value(inner)
|
||||
return redacted
|
||||
if isinstance(value, list):
|
||||
return [redact_value(v) for v in value]
|
||||
if isinstance(value, tuple):
|
||||
return tuple(redact_value(v) for v in value)
|
||||
return value
|
||||
|
||||
|
||||
class TaskStateTransitionError(ValueError):
|
||||
pass
|
||||
|
||||
|
||||
class TaskStatus(StrEnum):
|
||||
CREATED = "CREATED"
|
||||
QUEUED = "QUEUED"
|
||||
CLAIMED = "CLAIMED"
|
||||
RUNNING = "RUNNING"
|
||||
WAITING_CHILD = "WAITING_CHILD"
|
||||
VERIFYING = "VERIFYING"
|
||||
COMPLETED = "COMPLETED"
|
||||
FAILED_RECOVERABLE = "FAILED_RECOVERABLE"
|
||||
FAILED_FINAL = "FAILED_FINAL"
|
||||
CANCELLED = "CANCELLED"
|
||||
MANUAL_REVIEW_REQUIRED = "MANUAL_REVIEW_REQUIRED"
|
||||
|
||||
|
||||
TASK_STATES = {
|
||||
status.value for status in TaskStatus
|
||||
}
|
||||
|
||||
|
||||
TASK_NEXT_STATES = {
|
||||
"CREATED": {"QUEUED", "CLAIMED", "CANCELLED", "MANUAL_REVIEW_REQUIRED"},
|
||||
"QUEUED": {"CLAIMED", "CANCELLED", "FAILED_RECOVERABLE", "FAILED_FINAL"},
|
||||
"CLAIMED": {"RUNNING", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
|
||||
"RUNNING": {"VERIFYING", "WAITING_CHILD", "COMPLETED", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
|
||||
"WAITING_CHILD": {"RUNNING", "VERIFYING", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
|
||||
"VERIFYING": {"COMPLETED", "FAILED_RECOVERABLE", "FAILED_FINAL", "CANCELLED"},
|
||||
"COMPLETED": set(),
|
||||
"FAILED_RECOVERABLE": {"CLAIMED", "RUNNING", "CANCELLED"},
|
||||
"FAILED_FINAL": set(),
|
||||
"CANCELLED": set(),
|
||||
"MANUAL_REVIEW_REQUIRED": {"RUNNING", "CANCELLED"},
|
||||
}
|
||||
|
||||
|
||||
@dataclass
|
||||
class Budget:
|
||||
time_seconds: int | None = None
|
||||
attempts: int | None = None
|
||||
tokens: int | None = None
|
||||
cost: float | None = None
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: dict[str, Any] | None) -> "Budget":
|
||||
if not data:
|
||||
return cls()
|
||||
if not isinstance(data, dict) or set(data) - {
|
||||
"time_seconds",
|
||||
"attempts",
|
||||
"tokens",
|
||||
"cost",
|
||||
}:
|
||||
raise ValueError("invalid budget")
|
||||
for name in ("time_seconds", "attempts", "tokens", "cost"):
|
||||
value = data.get(name)
|
||||
if value is not None:
|
||||
try:
|
||||
if float(value) < 0:
|
||||
raise ValueError("budget values must be non-negative")
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValueError("invalid budget value") from exc
|
||||
return cls(
|
||||
time_seconds=_to_positive_int(data.get("time_seconds")),
|
||||
attempts=_to_positive_int(data.get("attempts")),
|
||||
tokens=_to_positive_int(data.get("tokens")),
|
||||
cost=_to_float(data.get("cost")),
|
||||
)
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"time_seconds": self.time_seconds,
|
||||
"attempts": self.attempts,
|
||||
"tokens": self.tokens,
|
||||
"cost": self.cost,
|
||||
}
|
||||
|
||||
def merge(self, other: "Budget") -> "Budget":
|
||||
return Budget(
|
||||
time_seconds=_first_non_none(self.time_seconds, other.time_seconds),
|
||||
attempts=_first_non_none(self.attempts, other.attempts),
|
||||
tokens=_first_non_none(self.tokens, other.tokens),
|
||||
cost=_first_non_none(self.cost, other.cost),
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class TaskPlan:
|
||||
schema_version: int = 1
|
||||
task_id: str | None = None
|
||||
task_type: str = "code.change"
|
||||
issuer: dict[str, Any] = field(default_factory=dict)
|
||||
intent: str | None = None
|
||||
required_capabilities: list[str] = field(default_factory=list)
|
||||
preferred_workers: list[str] = field(default_factory=list)
|
||||
risk: str = "medium"
|
||||
approval_policy: str = "patch-only"
|
||||
dependencies: list[str] = field(default_factory=list)
|
||||
max_delegation_depth: int = 5
|
||||
budgets: Budget = field(default_factory=Budget)
|
||||
evidence_requirements: list[str] = field(default_factory=list)
|
||||
parent_task_id: str | None = None
|
||||
correlation_id: str | None = None
|
||||
metadata: dict[str, Any] = field(default_factory=dict)
|
||||
data_classification: str = "internal"
|
||||
execution_zone: str = "isolated-development"
|
||||
network_policy: str = "controlled"
|
||||
logging_policy: str = "redacted"
|
||||
allowed_input_paths: list[str] = field(default_factory=list)
|
||||
allowed_output_paths: list[str] = field(default_factory=list)
|
||||
output_policy: str = "standard"
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: dict[str, Any] | None) -> "TaskPlan":
|
||||
if not isinstance(data, dict):
|
||||
raise ValueError("task plan payload must be an object")
|
||||
unknown = set(data) - TASK_PLAN_KEYS
|
||||
if unknown:
|
||||
raise ValueError("unknown task plan fields")
|
||||
if "task_id" not in data or data["task_id"] is None:
|
||||
data = dict(data)
|
||||
data["task_id"] = f"task-{uuid.uuid4()}"
|
||||
risk = str(data.get("risk", "medium"))
|
||||
if risk not in RISK_LEVELS:
|
||||
raise ValueError("invalid risk")
|
||||
issuer = data.get("issuer", {})
|
||||
if not isinstance(issuer, dict):
|
||||
raise ValueError("issuer must be an object")
|
||||
schema_version = int(data.get("schema_version", 1))
|
||||
if schema_version != 1:
|
||||
raise ValueError("unsupported schema_version")
|
||||
max_depth = _to_positive_int(data.get("max_delegation_depth"), default=5)
|
||||
if max_depth is None or max_depth > 32:
|
||||
raise ValueError("invalid max_delegation_depth")
|
||||
classification = str(data.get("data_classification", "internal"))
|
||||
if classification not in DATA_CLASSIFICATIONS:
|
||||
raise ValueError("invalid data_classification")
|
||||
execution_zone = validate_type(
|
||||
data.get("execution_zone", "isolated-development"), "execution_zone"
|
||||
)
|
||||
network_policy = validate_type(
|
||||
data.get("network_policy", "controlled"), "network_policy"
|
||||
)
|
||||
logging_policy = validate_type(
|
||||
data.get("logging_policy", "redacted"), "logging_policy"
|
||||
)
|
||||
output_policy = validate_type(
|
||||
data.get("output_policy", "standard"), "output_policy"
|
||||
)
|
||||
if contains_secret_text(
|
||||
{
|
||||
"intent": data.get("intent"),
|
||||
"metadata": data.get("metadata", {}),
|
||||
}
|
||||
):
|
||||
raise ValueError("task content contains secret material")
|
||||
if classification == "credential-secret":
|
||||
if execution_zone != "secure-file-transformer":
|
||||
raise ValueError("credential-secret requires secure-file-transformer")
|
||||
if network_policy != "denied":
|
||||
raise ValueError("credential-secret requires network denied")
|
||||
if logging_policy != "metadata-only":
|
||||
raise ValueError("credential-secret requires metadata-only logging")
|
||||
if output_policy != "hash-count-status-only":
|
||||
raise ValueError("credential-secret requires restricted output")
|
||||
return cls(
|
||||
schema_version=schema_version,
|
||||
task_id=validate_identifier(data["task_id"], "task_id"),
|
||||
task_type=validate_type(data.get("task_type", "code.change"), "task_type"),
|
||||
issuer=issuer,
|
||||
intent=data.get("intent"),
|
||||
required_capabilities=_normalize_list(data.get("required_capabilities", [])),
|
||||
preferred_workers=_normalize_list(data.get("preferred_workers", [])),
|
||||
risk=risk,
|
||||
approval_policy=validate_type(
|
||||
data.get("approval_policy", "patch-only"), "approval_policy"
|
||||
),
|
||||
dependencies=_normalize_list(data.get("dependencies", [])),
|
||||
max_delegation_depth=max_depth,
|
||||
budgets=Budget.from_dict(data.get("budgets")),
|
||||
evidence_requirements=_normalize_list(data.get("evidence_requirements", [])),
|
||||
parent_task_id=data.get("parent_task_id"),
|
||||
correlation_id=data.get("correlation_id"),
|
||||
metadata=data.get("metadata", {}) if isinstance(data.get("metadata", {}), dict) else {},
|
||||
data_classification=classification,
|
||||
execution_zone=execution_zone,
|
||||
network_policy=network_policy,
|
||||
logging_policy=logging_policy,
|
||||
allowed_input_paths=validate_relative_paths(
|
||||
data.get("allowed_input_paths", []), "allowed_input_paths"
|
||||
),
|
||||
allowed_output_paths=validate_relative_paths(
|
||||
data.get("allowed_output_paths", []), "allowed_output_paths"
|
||||
),
|
||||
output_policy=output_policy,
|
||||
)
|
||||
|
||||
def to_dict(self, *, redact: bool = False) -> dict[str, Any]:
|
||||
payload = {
|
||||
"schema_version": self.schema_version,
|
||||
"task_id": self.task_id,
|
||||
"task_type": self.task_type,
|
||||
"issuer": self.issuer,
|
||||
"intent": self.intent,
|
||||
"required_capabilities": list(self.required_capabilities),
|
||||
"preferred_workers": list(self.preferred_workers),
|
||||
"risk": self.risk,
|
||||
"approval_policy": self.approval_policy,
|
||||
"dependencies": list(self.dependencies),
|
||||
"max_delegation_depth": self.max_delegation_depth,
|
||||
"budgets": self.budgets.to_dict(),
|
||||
"evidence_requirements": list(self.evidence_requirements),
|
||||
"parent_task_id": self.parent_task_id,
|
||||
"correlation_id": self.correlation_id,
|
||||
"metadata": dict(self.metadata),
|
||||
"data_classification": self.data_classification,
|
||||
"execution_zone": self.execution_zone,
|
||||
"network_policy": self.network_policy,
|
||||
"logging_policy": self.logging_policy,
|
||||
"allowed_input_paths": list(self.allowed_input_paths),
|
||||
"allowed_output_paths": list(self.allowed_output_paths),
|
||||
"output_policy": self.output_policy,
|
||||
}
|
||||
if redact:
|
||||
payload = redact_value(payload)
|
||||
return payload
|
||||
|
||||
def operation_digest(self) -> str:
|
||||
return compute_sha256_hex(self.to_dict())
|
||||
|
||||
|
||||
@dataclass
|
||||
class TaskRecord:
|
||||
task_id: str
|
||||
status: str
|
||||
revision: int
|
||||
task_plan: TaskPlan
|
||||
created_at: float
|
||||
updated_at: float
|
||||
root_task_id: str
|
||||
idempotency_key: str | None = None
|
||||
failure_reason: str | None = None
|
||||
|
||||
def with_status(self, status: str) -> "TaskRecord":
|
||||
allowed = TASK_NEXT_STATES.get(self.status, set())
|
||||
if status != self.status and (not allowed and self.status not in {"COMPLETED", "FAILED_FINAL", "CANCELLED"}):
|
||||
raise TaskStateTransitionError(f"Cannot transition {self.status} -> {status}")
|
||||
if status not in TASK_STATES:
|
||||
raise TaskStateTransitionError(f"Invalid status {status}")
|
||||
if status != self.status and self.status in TASK_NEXT_STATES and status not in TASK_NEXT_STATES[self.status]:
|
||||
raise TaskStateTransitionError(f"Cannot transition {self.status} -> {status}")
|
||||
return TaskRecord(
|
||||
task_id=self.task_id,
|
||||
status=status,
|
||||
revision=self.revision + 1,
|
||||
task_plan=self.task_plan,
|
||||
created_at=self.created_at,
|
||||
updated_at=_now_ts(),
|
||||
root_task_id=self.root_task_id,
|
||||
idempotency_key=self.idempotency_key,
|
||||
failure_reason=self.failure_reason,
|
||||
)
|
||||
|
||||
def to_dict(self, *, include_task=True, redact_payload: bool = True) -> dict[str, Any]:
|
||||
payload = {
|
||||
"task_id": self.task_id,
|
||||
"status": self.status,
|
||||
"revision": self.revision,
|
||||
"root_task_id": self.root_task_id,
|
||||
"parent_task_id": self.task_plan.parent_task_id,
|
||||
"created_at": _fmt_ts(self.created_at),
|
||||
"updated_at": _fmt_ts(self.updated_at),
|
||||
"failure_reason": self.failure_reason,
|
||||
}
|
||||
if include_task:
|
||||
payload["plan"] = self.task_plan.to_dict(redact=redact_payload)
|
||||
if self.idempotency_key:
|
||||
payload["idempotency_key"] = self.idempotency_key
|
||||
return payload
|
||||
|
||||
|
||||
@dataclass
|
||||
class WorkerRegistration:
|
||||
worker_id: str
|
||||
worker_type: str
|
||||
identity: str
|
||||
capabilities: list[str]
|
||||
trust_zone: str
|
||||
max_concurrency: int
|
||||
heartbeat_interval_seconds: int
|
||||
supported_protocols: list[str]
|
||||
registered_at: float
|
||||
last_heartbeat: float
|
||||
status: str = "active"
|
||||
disabled: bool = False
|
||||
owner_identity: str = ""
|
||||
registration_revision: int = 1
|
||||
registration_policy: str = "self"
|
||||
created_at: float = 0.0
|
||||
updated_at: float = 0.0
|
||||
disabled_reason: str | None = None
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: dict[str, Any]) -> "WorkerRegistration":
|
||||
if not isinstance(data, dict):
|
||||
raise ValueError("worker registration payload must be an object")
|
||||
now = _now_ts()
|
||||
worker_id = validate_identifier(data.get("worker_id"), "worker_id")
|
||||
worker_type = validate_type(data.get("worker_type"), "worker_type")
|
||||
identity = str(data.get("identity") or "").strip()
|
||||
if not identity or any(ord(ch) < 32 for ch in identity):
|
||||
raise ValueError("invalid identity")
|
||||
max_concurrency = _to_positive_int(data.get("max_concurrency"), default=1)
|
||||
heartbeat_interval = _to_positive_int(
|
||||
data.get("heartbeat_interval_seconds"), default=15
|
||||
)
|
||||
if not max_concurrency:
|
||||
raise ValueError("max_concurrency must be positive")
|
||||
if not heartbeat_interval:
|
||||
raise ValueError("heartbeat_interval_seconds must be positive")
|
||||
return cls(
|
||||
worker_id=worker_id,
|
||||
worker_type=worker_type,
|
||||
identity=identity,
|
||||
capabilities=_normalize_list(data.get("capabilities", [])),
|
||||
trust_zone=str(data.get("trust_zone") or "default"),
|
||||
max_concurrency=max_concurrency,
|
||||
heartbeat_interval_seconds=heartbeat_interval,
|
||||
supported_protocols=_normalize_list(
|
||||
data.get("supported_protocols", ["aios-task-v1"])
|
||||
),
|
||||
registered_at=float(data.get("registered_at") or now),
|
||||
last_heartbeat=float(data.get("last_heartbeat") or now),
|
||||
status=str(data.get("status") or "active"),
|
||||
disabled=bool(data.get("disabled", False)),
|
||||
owner_identity=str(data.get("owner_identity") or identity),
|
||||
registration_revision=int(data.get("registration_revision") or 1),
|
||||
registration_policy=str(data.get("registration_policy") or "self"),
|
||||
created_at=float(data.get("created_at") or data.get("registered_at") or now),
|
||||
updated_at=float(data.get("updated_at") or now),
|
||||
disabled_reason=data.get("disabled_reason"),
|
||||
)
|
||||
|
||||
def to_dict(self, redact_payload: bool = True) -> dict[str, Any]:
|
||||
payload = {
|
||||
"worker_id": self.worker_id,
|
||||
"worker_type": self.worker_type,
|
||||
"identity": self.identity,
|
||||
"capabilities": list(self.capabilities),
|
||||
"trust_zone": self.trust_zone,
|
||||
"max_concurrency": self.max_concurrency,
|
||||
"heartbeat_interval_seconds": self.heartbeat_interval_seconds,
|
||||
"supported_protocols": list(self.supported_protocols),
|
||||
"registered_at": _fmt_ts(self.registered_at),
|
||||
"last_heartbeat": _fmt_ts(self.last_heartbeat),
|
||||
"status": self.status,
|
||||
"disabled": self.disabled,
|
||||
"owner_identity": self.owner_identity,
|
||||
"registration_revision": self.registration_revision,
|
||||
"registration_policy": self.registration_policy,
|
||||
"created_at": _fmt_ts(self.created_at or self.registered_at),
|
||||
"updated_at": _fmt_ts(self.updated_at or self.last_heartbeat),
|
||||
"disabled_reason": self.disabled_reason,
|
||||
}
|
||||
if redact_payload:
|
||||
payload = redact_value(payload)
|
||||
return payload
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EvidenceEnvelope:
|
||||
schema_version: int
|
||||
evidence_id: str
|
||||
task_id: str
|
||||
claim_id: str
|
||||
kind: str
|
||||
worker_identity: str
|
||||
payload: dict[str, Any]
|
||||
created_at: float
|
||||
previous_evidence_hash: str
|
||||
evidence_digest: str
|
||||
signature: str | None = None
|
||||
attestation_ref: str | None = None
|
||||
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
*,
|
||||
task_id: str,
|
||||
claim_id: str,
|
||||
kind: str,
|
||||
worker_identity: str,
|
||||
payload: dict[str, Any],
|
||||
previous_evidence_hash: str,
|
||||
signature: str | None = None,
|
||||
attestation_ref: str | None = None,
|
||||
evidence_id: str | None = None,
|
||||
created_at: float | None = None,
|
||||
) -> "EvidenceEnvelope":
|
||||
envelope = cls(
|
||||
schema_version=1,
|
||||
evidence_id=evidence_id or f"evd-{uuid.uuid4()}",
|
||||
task_id=validate_identifier(task_id, "task_id"),
|
||||
claim_id=validate_identifier(claim_id, "claim_id"),
|
||||
kind=validate_type(kind, "evidence kind"),
|
||||
worker_identity=str(worker_identity),
|
||||
payload=redact_value(payload),
|
||||
created_at=float(created_at or _now_ts()),
|
||||
previous_evidence_hash=str(previous_evidence_hash or ""),
|
||||
evidence_digest="",
|
||||
signature=signature,
|
||||
attestation_ref=attestation_ref,
|
||||
)
|
||||
return dataclass_replace(
|
||||
envelope, evidence_digest=compute_sha256_hex(envelope.digest_payload())
|
||||
)
|
||||
|
||||
def digest_payload(self) -> dict[str, Any]:
|
||||
return {
|
||||
"schema_version": self.schema_version,
|
||||
"evidence_id": self.evidence_id,
|
||||
"task_id": self.task_id,
|
||||
"claim_id": self.claim_id,
|
||||
"kind": self.kind,
|
||||
"worker_identity": self.worker_identity,
|
||||
"payload": self.payload,
|
||||
"created_at": self.created_at,
|
||||
"previous_evidence_hash": self.previous_evidence_hash,
|
||||
"attestation_ref": self.attestation_ref,
|
||||
}
|
||||
|
||||
def verify(
|
||||
self,
|
||||
*,
|
||||
expected_task_id: str,
|
||||
expected_claim_id: str,
|
||||
expected_previous_hash: str,
|
||||
attestation_verifier: Any = None,
|
||||
) -> bool:
|
||||
if (
|
||||
self.schema_version != 1
|
||||
or self.task_id != expected_task_id
|
||||
or self.claim_id != expected_claim_id
|
||||
or self.previous_evidence_hash != expected_previous_hash
|
||||
or self.evidence_digest != compute_sha256_hex(self.digest_payload())
|
||||
):
|
||||
return False
|
||||
if self.signature or self.attestation_ref:
|
||||
return True if attestation_verifier is None else bool(attestation_verifier(self))
|
||||
return True
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
**self.digest_payload(),
|
||||
"evidence_digest": self.evidence_digest,
|
||||
"signature": self.signature,
|
||||
}
|
||||
|
||||
|
||||
class ProbeOutcome(StrEnum):
|
||||
NOT_APPLIED = "NOT_APPLIED"
|
||||
APPLIED_VERIFIED = "APPLIED_VERIFIED"
|
||||
INDETERMINATE = "INDETERMINATE"
|
||||
CONFLICT = "CONFLICT"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProbeEvidence:
|
||||
schema_version: int
|
||||
probe_id: str
|
||||
task_id: str
|
||||
claim_id: str
|
||||
worker_id: str
|
||||
worker_identity: str
|
||||
operation_digest: str
|
||||
outcome: ProbeOutcome
|
||||
observed_at: float
|
||||
expires_at: float
|
||||
probe_executor_identity: str
|
||||
evidence_digest: str
|
||||
signature: str | None = None
|
||||
attestation_ref: str | None = None
|
||||
|
||||
@classmethod
|
||||
def create(cls, **data: Any) -> "ProbeEvidence":
|
||||
outcome = data["outcome"]
|
||||
if not isinstance(outcome, ProbeOutcome):
|
||||
outcome = ProbeOutcome(str(outcome))
|
||||
probe = cls(
|
||||
schema_version=1,
|
||||
probe_id=data.get("probe_id") or f"probe-{uuid.uuid4()}",
|
||||
task_id=validate_identifier(data["task_id"], "task_id"),
|
||||
claim_id=validate_identifier(data["claim_id"], "claim_id"),
|
||||
worker_id=validate_identifier(data["worker_id"], "worker_id"),
|
||||
worker_identity=str(data["worker_identity"]),
|
||||
operation_digest=str(data["operation_digest"]),
|
||||
outcome=outcome,
|
||||
observed_at=float(data["observed_at"]),
|
||||
expires_at=float(data["expires_at"]),
|
||||
probe_executor_identity=str(data["probe_executor_identity"]),
|
||||
evidence_digest="",
|
||||
signature=data.get("signature"),
|
||||
attestation_ref=data.get("attestation_ref"),
|
||||
)
|
||||
return dataclass_replace(
|
||||
probe, evidence_digest=compute_sha256_hex(probe.digest_payload())
|
||||
)
|
||||
|
||||
def digest_payload(self) -> dict[str, Any]:
|
||||
return {
|
||||
"schema_version": self.schema_version,
|
||||
"probe_id": self.probe_id,
|
||||
"task_id": self.task_id,
|
||||
"claim_id": self.claim_id,
|
||||
"worker_id": self.worker_id,
|
||||
"worker_identity": self.worker_identity,
|
||||
"operation_digest": self.operation_digest,
|
||||
"outcome": self.outcome.value,
|
||||
"observed_at": self.observed_at,
|
||||
"expires_at": self.expires_at,
|
||||
"probe_executor_identity": self.probe_executor_identity,
|
||||
"attestation_ref": self.attestation_ref,
|
||||
}
|
||||
|
||||
def verify(self, *, now: float, attestation_verifier: Any) -> bool:
|
||||
if (
|
||||
self.schema_version != 1
|
||||
or self.expires_at <= now
|
||||
or self.observed_at > now
|
||||
or self.evidence_digest != compute_sha256_hex(self.digest_payload())
|
||||
or not (self.signature or self.attestation_ref)
|
||||
):
|
||||
return False
|
||||
return bool(attestation_verifier and attestation_verifier(self))
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
**self.digest_payload(),
|
||||
"evidence_digest": self.evidence_digest,
|
||||
"signature": self.signature,
|
||||
}
|
||||
|
||||
|
||||
def dataclass_replace(value: Any, **changes: Any) -> Any:
|
||||
from dataclasses import replace
|
||||
|
||||
return replace(value, **changes)
|
||||
|
||||
|
||||
@dataclass
|
||||
class WorkerClaim:
|
||||
claim_id: str
|
||||
task_id: str
|
||||
worker_id: str
|
||||
worker_identity: str
|
||||
claimed_at: float
|
||||
lease_until: float
|
||||
attempt: int
|
||||
task_revision: int
|
||||
operation_digest: str
|
||||
status: str = "ACTIVE"
|
||||
|
||||
def to_dict(self, redact_payload: bool = True) -> dict[str, Any]:
|
||||
payload = {
|
||||
"claim_id": self.claim_id,
|
||||
"task_id": self.task_id,
|
||||
"worker_id": self.worker_id,
|
||||
"worker_identity": self.worker_identity,
|
||||
"claimed_at": _fmt_ts(self.claimed_at),
|
||||
"lease_until": _fmt_ts(self.lease_until),
|
||||
"attempt": self.attempt,
|
||||
"task_revision": self.task_revision,
|
||||
"operation_digest": self.operation_digest,
|
||||
"status": self.status,
|
||||
}
|
||||
if redact_payload:
|
||||
payload = redact_value(payload)
|
||||
return payload
|
||||
|
||||
|
||||
@dataclass
|
||||
class ResultEnvelope:
|
||||
task_id: str
|
||||
claim_id: str
|
||||
worker_identity: str
|
||||
status: str
|
||||
outputs: list[dict[str, Any]]
|
||||
evidence: list[dict[str, Any]]
|
||||
started_at: str
|
||||
completed_at: str
|
||||
result_digest: str | None = None
|
||||
signature: str | None = None
|
||||
attestation_ref: str | None = None
|
||||
operation_digest: str | None = None
|
||||
trust_status: str = "untrusted_shadow_result"
|
||||
|
||||
def digest_payload(self) -> dict[str, Any]:
|
||||
return {
|
||||
"task_id": self.task_id,
|
||||
"claim_id": self.claim_id,
|
||||
"worker_identity": self.worker_identity,
|
||||
"status": self.status,
|
||||
"outputs": self.outputs,
|
||||
"evidence": self.evidence,
|
||||
"started_at": self.started_at,
|
||||
"completed_at": self.completed_at,
|
||||
"operation_digest": self.operation_digest,
|
||||
"attestation_ref": self.attestation_ref,
|
||||
}
|
||||
|
||||
def computed_digest(self) -> str:
|
||||
return compute_sha256_hex(self.digest_payload())
|
||||
|
||||
def to_dict(self, redact_payload: bool = True) -> dict[str, Any]:
|
||||
payload = {
|
||||
"task_id": self.task_id,
|
||||
"claim_id": self.claim_id,
|
||||
"worker_identity": self.worker_identity,
|
||||
"status": self.status,
|
||||
"outputs": self.outputs,
|
||||
"evidence": self.evidence,
|
||||
"started_at": self.started_at,
|
||||
"completed_at": self.completed_at,
|
||||
"result_digest": self.result_digest,
|
||||
"signature": self.signature,
|
||||
"attestation_ref": self.attestation_ref,
|
||||
"operation_digest": self.operation_digest,
|
||||
"trust_status": self.trust_status,
|
||||
}
|
||||
if redact_payload:
|
||||
payload = redact_value(payload)
|
||||
return payload
|
||||
|
||||
|
||||
def _normalize_list(value: Any) -> list[str]:
|
||||
if not isinstance(value, list):
|
||||
raise ValueError("expected list")
|
||||
if len(value) > 128 or any(
|
||||
not isinstance(v, str)
|
||||
or not v
|
||||
or len(v) > 256
|
||||
or any(ord(ch) < 32 for ch in v)
|
||||
for v in value
|
||||
):
|
||||
raise ValueError("invalid list item")
|
||||
return list(value)
|
||||
|
||||
|
||||
def _to_positive_int(value: Any, default: int | None = None) -> int | None:
|
||||
if value is None:
|
||||
return default
|
||||
try:
|
||||
number = int(value)
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
return number if number >= 0 else default
|
||||
|
||||
|
||||
def _to_float(value: Any) -> float | None:
|
||||
if value is None:
|
||||
return None
|
||||
try:
|
||||
return float(value)
|
||||
except (TypeError, ValueError):
|
||||
return None
|
||||
|
||||
|
||||
def _first_non_none(primary: Any, fallback: Any) -> Any:
|
||||
if primary is not None:
|
||||
return primary
|
||||
return fallback
|
||||
|
||||
|
||||
def iso8601_now() -> str:
|
||||
return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def _fmt_ts(value: float | None) -> str | None:
|
||||
if value is None:
|
||||
return None
|
||||
return datetime.fromtimestamp(value, tz=timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
|
||||
@@ -0,0 +1,226 @@
|
||||
"""Policy and verification logic (fail-closed)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Callable
|
||||
|
||||
from .errors import ForbiddenError, LockedError
|
||||
from .models import ProbeEvidence, ResultEnvelope, TaskRecord
|
||||
|
||||
|
||||
RISK_RANK = {"low": 1, "medium": 2, "high": 3}
|
||||
READONLY_WORKER_ACTIONS = frozenset(
|
||||
{"claim", "result", "fail", "progress", "heartbeat"}
|
||||
)
|
||||
ALL_ACTION_CAPABILITIES = frozenset(
|
||||
{
|
||||
"task.creator",
|
||||
"worker.self_register",
|
||||
"worker.admin",
|
||||
"task.claim",
|
||||
"task.cancel",
|
||||
"task.delegate",
|
||||
"task.read",
|
||||
"task.audit",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class PolicyDecision:
|
||||
allowed: bool
|
||||
reason: str = ""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ReadonlyWorkerProfile:
|
||||
"""A narrowly-scoped identity allowed to process safe Shadow tasks only."""
|
||||
|
||||
worker_id: str
|
||||
identity: str
|
||||
capabilities: frozenset[str]
|
||||
task_types: frozenset[str] = frozenset({"code.review", "test.execute"})
|
||||
|
||||
def permits_task(self, task: TaskRecord) -> bool:
|
||||
plan = task.task_plan
|
||||
if plan.task_type not in self.task_types or plan.risk != "low":
|
||||
return False
|
||||
if plan.data_classification not in {"public", "internal"}:
|
||||
return False
|
||||
if plan.metadata.get("production_side_effects") is not False:
|
||||
return False
|
||||
return set(plan.required_capabilities).issubset(self.capabilities)
|
||||
|
||||
|
||||
class IdentityVerifier:
|
||||
def __init__(self, trusted_identities: set[str] | None = None):
|
||||
self.trusted_identities = trusted_identities
|
||||
|
||||
def verify(self, identity: str) -> bool:
|
||||
if self.trusted_identities is None:
|
||||
return True
|
||||
return identity in self.trusted_identities
|
||||
|
||||
|
||||
class EvidenceVerifier:
|
||||
def __init__(self, mandatory: list[str] | None = None):
|
||||
self.mandatory = set(mandatory or [])
|
||||
|
||||
def verify(self, task: TaskRecord, evidences: list[dict]) -> PolicyDecision:
|
||||
required = set(task.task_plan.evidence_requirements or [])
|
||||
if not required and not self.mandatory:
|
||||
return PolicyDecision(True)
|
||||
observed = {e.get("kind") for e in evidences}
|
||||
missing = required.union(self.mandatory) - observed
|
||||
if missing:
|
||||
return PolicyDecision(False, f"missing evidence: {', '.join(sorted(missing))}")
|
||||
return PolicyDecision(True)
|
||||
|
||||
|
||||
class PolicyEngine:
|
||||
"""
|
||||
Fail-closed policy engine with minimal but explicit decisions.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
identity_verifier: IdentityVerifier | None = None,
|
||||
evidence_verifier: EvidenceVerifier | None = None,
|
||||
execution_enabled: bool = False,
|
||||
max_risk: str = "medium",
|
||||
result_signature_verifier: Callable[[ResultEnvelope], bool] | None = None,
|
||||
probe_attestation_verifier: Callable[[ProbeEvidence], bool] | None = None,
|
||||
identity_capabilities: dict[str, set[str]] | None = None,
|
||||
admin_identities: set[str] | None = None,
|
||||
readonly_worker_execution_enabled: bool = False,
|
||||
readonly_worker_profiles: list[ReadonlyWorkerProfile] | None = None,
|
||||
) -> None:
|
||||
if max_risk not in RISK_RANK:
|
||||
raise ValueError("invalid max_risk")
|
||||
self.identity_verifier = identity_verifier or IdentityVerifier()
|
||||
self.evidence_verifier = evidence_verifier or EvidenceVerifier()
|
||||
self.execution_enabled = execution_enabled
|
||||
self.max_risk = max_risk
|
||||
self.result_signature_verifier = result_signature_verifier
|
||||
self.probe_attestation_verifier = probe_attestation_verifier
|
||||
self.identity_capabilities = {
|
||||
identity: set(capabilities)
|
||||
for identity, capabilities in (identity_capabilities or {}).items()
|
||||
}
|
||||
self.admin_identities = set(admin_identities or ())
|
||||
self.readonly_worker_execution_enabled = readonly_worker_execution_enabled
|
||||
self.readonly_worker_profiles = {
|
||||
profile.identity: profile for profile in (readonly_worker_profiles or [])
|
||||
}
|
||||
|
||||
def _readonly_worker_allows(
|
||||
self, action: str, actor: str, task: TaskRecord | None
|
||||
) -> bool:
|
||||
profile = self.readonly_worker_profiles.get(actor)
|
||||
return bool(
|
||||
self.readonly_worker_execution_enabled
|
||||
and action in READONLY_WORKER_ACTIONS
|
||||
and profile is not None
|
||||
and (task is None or profile.permits_task(task))
|
||||
)
|
||||
|
||||
def assert_readonly_worker_binding(self, actor: str, worker_id: str) -> None:
|
||||
profile = self.readonly_worker_profiles.get(actor)
|
||||
if profile is not None and profile.worker_id != worker_id:
|
||||
raise ForbiddenError("worker identity binding mismatch")
|
||||
|
||||
def assert_readonly_worker_registration(self, actor: str, payload: dict) -> None:
|
||||
profile = self.readonly_worker_profiles.get(actor)
|
||||
if profile is None:
|
||||
return
|
||||
if (
|
||||
str(payload.get("worker_id") or "") != profile.worker_id
|
||||
or str(payload.get("identity") or "") != profile.identity
|
||||
or set(payload.get("capabilities") or []) != set(profile.capabilities)
|
||||
or str(payload.get("trust_zone") or "") != "isolated-review"
|
||||
or int(payload.get("max_concurrency") or 0) != 1
|
||||
or int(payload.get("heartbeat_interval_seconds") or 0) != 15
|
||||
):
|
||||
raise ForbiddenError("readonly worker registration mismatch")
|
||||
|
||||
def verify_result(
|
||||
self, result: ResultEnvelope, task: TaskRecord | None = None
|
||||
) -> PolicyDecision:
|
||||
computed = result.computed_digest()
|
||||
if result.result_digest and result.result_digest != computed:
|
||||
return PolicyDecision(False, "result digest mismatch")
|
||||
sensitive = bool(
|
||||
task
|
||||
and (
|
||||
task.task_plan.data_classification
|
||||
in {"confidential", "credential-secret"}
|
||||
or any(
|
||||
capability.startswith(
|
||||
("code.write", "deploy", "secret", "production")
|
||||
)
|
||||
for capability in task.task_plan.required_capabilities
|
||||
)
|
||||
)
|
||||
)
|
||||
if sensitive and not (result.signature or result.attestation_ref):
|
||||
return PolicyDecision(False, "trusted result proof required")
|
||||
if result.signature is not None or result.attestation_ref is not None:
|
||||
if self.result_signature_verifier is None:
|
||||
return PolicyDecision(False, "result signature verifier unavailable")
|
||||
if not self.result_signature_verifier(result):
|
||||
return PolicyDecision(False, "result signature invalid")
|
||||
result.trust_status = "trusted_result"
|
||||
else:
|
||||
result.trust_status = "untrusted_shadow_result"
|
||||
return PolicyDecision(True)
|
||||
|
||||
def authorize(self, action: str, actor: str, task: TaskRecord | None = None, context: dict | None = None) -> PolicyDecision:
|
||||
context = context or {}
|
||||
if not self.identity_verifier.verify(actor):
|
||||
return PolicyDecision(False, "identity untrusted")
|
||||
|
||||
action_capabilities = {
|
||||
"create": "task.creator",
|
||||
"read": "task.read",
|
||||
"audit": "task.audit",
|
||||
"claim": "task.claim",
|
||||
"result": "task.claim",
|
||||
"fail": "task.claim",
|
||||
"progress": "task.claim",
|
||||
"heartbeat": "task.claim",
|
||||
"cancel": "task.cancel",
|
||||
"delegate": "task.delegate",
|
||||
"worker.register": "worker.self_register",
|
||||
"worker.admin": "worker.admin",
|
||||
}
|
||||
required_capability = action_capabilities.get(action)
|
||||
if required_capability:
|
||||
granted = set(
|
||||
self.identity_capabilities.get(
|
||||
actor, self.identity_capabilities.get("*", set())
|
||||
)
|
||||
)
|
||||
if required_capability not in granted:
|
||||
return PolicyDecision(False, f"action {action} not permitted")
|
||||
|
||||
if action in {"claim", "result", "fail", "cancel", "progress", "delegate", "heartbeat"} and not self.execution_enabled:
|
||||
if not self._readonly_worker_allows(action, actor, task):
|
||||
return PolicyDecision(False, "execution disabled")
|
||||
|
||||
if action == "delegate" and task and task.status not in {"COMPLETED", "FAILED_FINAL", "CANCELLED"}:
|
||||
risk = str(context.get("risk", task.task_plan.risk))
|
||||
if RISK_RANK.get(risk, 2) > RISK_RANK.get(self.max_risk, 1):
|
||||
return PolicyDecision(False, f"risk {risk} exceeds policy")
|
||||
|
||||
return PolicyDecision(True)
|
||||
|
||||
def assert_allowed(self, action: str, actor: str, task: TaskRecord | None = None, context: dict | None = None):
|
||||
decision = self.authorize(action, actor, task, context=context)
|
||||
if not decision.allowed:
|
||||
if decision.reason == "identity untrusted":
|
||||
raise ForbiddenError(decision.reason)
|
||||
if decision.reason == "execution disabled":
|
||||
raise LockedError("execution disabled")
|
||||
raise ForbiddenError(decision.reason)
|
||||
@@ -0,0 +1,76 @@
|
||||
"""Task scheduler primitives."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import time
|
||||
from .errors import NotFoundError
|
||||
from .capabilities import has_capabilities
|
||||
from .models import WorkerClaim
|
||||
from .store import TaskPlaneStore
|
||||
|
||||
|
||||
class TaskScheduler:
|
||||
def __init__(self, store: TaskPlaneStore):
|
||||
self.store = store
|
||||
|
||||
def next_queued_task(self, worker_id: str):
|
||||
worker = self.store.get_worker(worker_id)
|
||||
tasks = sorted(
|
||||
self.store.list_tasks(),
|
||||
key=lambda task: (
|
||||
-int(task.task_plan.metadata.get("priority", 0)),
|
||||
task.created_at,
|
||||
task.task_id,
|
||||
),
|
||||
)
|
||||
for task in tasks:
|
||||
if task.status not in {"CREATED", "QUEUED", "FAILED_RECOVERABLE"}:
|
||||
continue
|
||||
if task.task_plan.task_type == "worker.registry.audit":
|
||||
continue
|
||||
if task.status == "FAILED_RECOVERABLE" and not self.store.task_has_retryable_probe(
|
||||
task.task_id
|
||||
):
|
||||
continue
|
||||
if not has_capabilities(
|
||||
worker.capabilities, task.task_plan.required_capabilities
|
||||
):
|
||||
continue
|
||||
if any(
|
||||
self.store.get_task(dependency).status != "COMPLETED"
|
||||
for dependency in task.task_plan.dependencies
|
||||
):
|
||||
continue
|
||||
if (
|
||||
task.task_plan.data_classification == "credential-secret"
|
||||
and worker.worker_type != "secure_file_transformer"
|
||||
and "secure_file_transformer" not in worker.capabilities
|
||||
):
|
||||
continue
|
||||
return task
|
||||
return None
|
||||
|
||||
def schedule_for_worker(self, worker_id: str, lease_seconds: int = 15) -> WorkerClaim:
|
||||
worker = self.store.get_worker(worker_id)
|
||||
if worker.disabled:
|
||||
from .errors import LockedError
|
||||
|
||||
raise LockedError("worker disabled")
|
||||
if time.time() > worker.last_heartbeat + (
|
||||
worker.heartbeat_interval_seconds * 3
|
||||
):
|
||||
from .errors import LockedError
|
||||
|
||||
raise LockedError("worker offline")
|
||||
task = self.next_queued_task(worker_id)
|
||||
if task is None:
|
||||
raise NotFoundError("no queued tasks available")
|
||||
claim = self.store.claim_task(
|
||||
task.task_id,
|
||||
worker_id,
|
||||
worker.identity,
|
||||
lease_seconds=lease_seconds,
|
||||
expected_revision=task.revision,
|
||||
operation_digest=task.task_plan.operation_digest(),
|
||||
)
|
||||
return claim
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,68 @@
|
||||
"""Worker registry abstraction and read helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import time
|
||||
|
||||
from .capabilities import has_capabilities
|
||||
from .errors import NotFoundError
|
||||
from .models import WorkerRegistration
|
||||
from .store import TaskPlaneStore
|
||||
|
||||
|
||||
class WorkerRegistry:
|
||||
def __init__(self, store: TaskPlaneStore):
|
||||
self.store = store
|
||||
|
||||
def register(
|
||||
self,
|
||||
payload: dict,
|
||||
*,
|
||||
actor_identity: str,
|
||||
is_admin: bool,
|
||||
expected_revision: int | None,
|
||||
) -> WorkerRegistration:
|
||||
reg = WorkerRegistration.from_dict(payload)
|
||||
return self.store.register_worker(
|
||||
reg,
|
||||
actor_identity=actor_identity,
|
||||
is_admin=is_admin,
|
||||
expected_revision=expected_revision,
|
||||
)
|
||||
|
||||
def heartbeat(
|
||||
self,
|
||||
worker_id: str,
|
||||
heartbeat_interval_seconds: int | None = None,
|
||||
*,
|
||||
actor_identity: str,
|
||||
expected_revision: int | None,
|
||||
) -> WorkerRegistration:
|
||||
return self.store.heartbeat_worker(
|
||||
worker_id,
|
||||
heartbeat_interval_seconds=heartbeat_interval_seconds,
|
||||
actor_identity=actor_identity,
|
||||
expected_revision=expected_revision,
|
||||
)
|
||||
|
||||
def list(self):
|
||||
return self.store.list_workers()
|
||||
|
||||
def get(self, worker_id: str) -> WorkerRegistration:
|
||||
try:
|
||||
return self.store.get_worker(worker_id)
|
||||
except NotFoundError:
|
||||
raise
|
||||
|
||||
def can_execute(self, worker_id: str, required_capabilities: list[str]) -> bool:
|
||||
worker = self.store.get_worker(worker_id)
|
||||
return has_capabilities(worker.capabilities, required_capabilities)
|
||||
|
||||
def is_online(self, worker_id: str, *, now: float | None = None) -> bool:
|
||||
worker = self.store.get_worker(worker_id)
|
||||
deadline = worker.last_heartbeat + (worker.heartbeat_interval_seconds * 3)
|
||||
return not worker.disabled and (time.time() if now is None else now) <= deadline
|
||||
|
||||
def stale_workers(self, *, now: float | None = None) -> list[WorkerRegistration]:
|
||||
current = time.time() if now is None else now
|
||||
return [worker for worker in self.list() if not self.is_online(worker.worker_id, now=current)]
|
||||
@@ -0,0 +1,165 @@
|
||||
"""Privacy and artifact helpers for the V2R1C6 release candidate.
|
||||
|
||||
The module is deliberately dependency-free. It provides deterministic redaction,
|
||||
safe SHA-256 manifest verification, and a small loopback-only candidate probe.
|
||||
It does not read credentials, contact production services, or mutate Git refs.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import re
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping
|
||||
|
||||
_SECRET_KEY = re.compile(r"(?i)(?:token|secret|password|private[_-]?key|api[_-]?key)")
|
||||
_SECRET_VALUE = re.compile(
|
||||
r"(?i)(?:bearer\s+)[A-Za-z0-9._~+/=-]+|"
|
||||
r"(?:token|secret|password|private[_-]?key|api[_-]?key)\s*[:=]\s*[^\s,;]+"
|
||||
)
|
||||
|
||||
|
||||
def redact_text(value: str) -> str:
|
||||
"""Replace common bearer and key/value secret forms without logging them."""
|
||||
if not isinstance(value, str):
|
||||
raise TypeError("text_required")
|
||||
return _SECRET_VALUE.sub("[REDACTED]", value)
|
||||
|
||||
|
||||
def redact_value(value: Any, *, key: str = "") -> Any:
|
||||
"""Recursively redact secret-bearing mapping keys and text values."""
|
||||
if isinstance(value, Mapping):
|
||||
result: dict[str, Any] = {}
|
||||
for name, item in value.items():
|
||||
name_text = str(name)
|
||||
if _SECRET_KEY.search(name_text):
|
||||
result[name_text] = "[REDACTED]"
|
||||
else:
|
||||
result[name_text] = redact_value(item, key=name_text)
|
||||
return result
|
||||
if isinstance(value, list):
|
||||
return [redact_value(item, key=key) for item in value]
|
||||
if isinstance(value, tuple):
|
||||
return [redact_value(item, key=key) for item in value]
|
||||
if isinstance(value, str):
|
||||
return "[REDACTED]" if _SECRET_KEY.search(key) else redact_text(value)
|
||||
return value
|
||||
|
||||
|
||||
def sha256_file(path: Path) -> str:
|
||||
"""Return the SHA-256 of a regular file without following symlink inputs."""
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise ValueError("regular_file_required")
|
||||
digest = hashlib.sha256()
|
||||
with path.open("rb") as stream:
|
||||
for chunk in iter(lambda: stream.read(1024 * 1024), b""):
|
||||
digest.update(chunk)
|
||||
return digest.hexdigest()
|
||||
|
||||
|
||||
def _safe_relative(root: Path, name: str) -> Path:
|
||||
relative = Path(name)
|
||||
if relative.is_absolute() or ".." in relative.parts or name in {"", "."}:
|
||||
raise ValueError("unsafe_manifest_path")
|
||||
candidate = (root / relative).resolve()
|
||||
candidate.relative_to(root.resolve())
|
||||
return candidate
|
||||
|
||||
|
||||
def verify_manifest(root: Path, manifest: Path | None = None) -> dict[str, Any]:
|
||||
"""Verify sha256 path entries and return a non-sensitive summary."""
|
||||
root = root.resolve()
|
||||
manifest = manifest or root / "artifacts" / "MANIFEST.sha256"
|
||||
if manifest.is_symlink() or not manifest.is_file():
|
||||
raise ValueError("manifest_missing")
|
||||
checked = 0
|
||||
for raw in manifest.read_text(encoding="utf-8").splitlines():
|
||||
line = raw.strip()
|
||||
if not line:
|
||||
continue
|
||||
parts = line.split(maxsplit=1)
|
||||
if len(parts) != 2 or not re.fullmatch(r"[0-9a-f]{64}", parts[0]):
|
||||
raise ValueError("manifest_entry_invalid")
|
||||
expected, name = parts
|
||||
if name.startswith("*"):
|
||||
name = name[1:]
|
||||
path = _safe_relative(root, name)
|
||||
if sha256_file(path) != expected:
|
||||
raise ValueError("manifest_hash_mismatch")
|
||||
checked += 1
|
||||
if checked == 0:
|
||||
raise ValueError("manifest_empty")
|
||||
return {"status": "PASS", "entries": checked}
|
||||
|
||||
|
||||
def load_release_metadata(path: Path) -> dict[str, Any]:
|
||||
metadata = json.loads(path.read_text(encoding="utf-8"))
|
||||
if metadata.get("version") != "V2R1C6":
|
||||
raise ValueError("version_mismatch")
|
||||
if metadata.get("production_deployed") is not False:
|
||||
raise ValueError("production_change_not_allowed")
|
||||
if metadata.get("tag_created") is not False:
|
||||
raise ValueError("tag_change_not_allowed")
|
||||
if metadata.get("baseline_changed") is not False:
|
||||
raise ValueError("baseline_change_not_allowed")
|
||||
return metadata
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--root", type=Path, default=Path("."))
|
||||
parser.add_argument("--manifest", type=Path)
|
||||
parser.add_argument("--serve", action="store_true")
|
||||
parser.add_argument("--host", default="127.0.0.1")
|
||||
parser.add_argument("--port", type=int, default=18926)
|
||||
args = parser.parse_args()
|
||||
if args.serve:
|
||||
serve(args.host, args.port)
|
||||
return 0
|
||||
result = verify_manifest(args.root, args.manifest)
|
||||
print(json.dumps(result, sort_keys=True))
|
||||
return 0
|
||||
|
||||
|
||||
|
||||
def health_payload() -> dict[str, Any]:
|
||||
return {
|
||||
"status": "ok",
|
||||
"version": "V2R1C6",
|
||||
"production_deployed": False,
|
||||
"gitops_writes_enabled": False,
|
||||
}
|
||||
|
||||
|
||||
class _HealthHandler(BaseHTTPRequestHandler):
|
||||
def do_GET(self) -> None:
|
||||
if self.path not in {"/", "/health", "/healthz"}:
|
||||
self.send_error(404)
|
||||
return
|
||||
body = json.dumps(health_payload(), sort_keys=True).encode("utf-8")
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
|
||||
def log_message(self, _format: str, *_args: object) -> None:
|
||||
return
|
||||
|
||||
|
||||
def serve(host: str, port: int) -> None:
|
||||
if host not in {"127.0.0.1", "::1", "localhost"}:
|
||||
raise ValueError("loopback_only_listener_required")
|
||||
if not 1024 <= port <= 65535:
|
||||
raise ValueError("invalid_listener_port")
|
||||
server = ThreadingHTTPServer((host, port), _HealthHandler)
|
||||
try:
|
||||
server.serve_forever()
|
||||
finally:
|
||||
server.server_close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"schema": "aios.release-approval-supersession.v1",
|
||||
"version": "V2R1C6",
|
||||
"status": "SUPERSEDED_PREDEPLOY_VALIDATION_FAILED",
|
||||
"execute_allowed": false,
|
||||
"old_binding": {
|
||||
"target_oid": "28081c5522a869762ec4946846f68047d53d99f0",
|
||||
"evidence_closure_oid": "fed41014d80bacca70c8f309a5fb2c22e6001e32",
|
||||
"artifact_sha256": "437b1f891f23a1dd12feabeced3edee3c54cc552d990d6d852805c8d5a165150",
|
||||
"approval_plan_id": "sha256:596c8d40c25f9427c58cbdb0bbae58c03ba5c200fec32025c22d8004d27d8a51"
|
||||
},
|
||||
"reasons": [
|
||||
"artifact_candidate_descriptor",
|
||||
"deployable_package_not_verified",
|
||||
"production_controller_support_not_verified"
|
||||
],
|
||||
"replacement_required": true,
|
||||
"production_deployed": false,
|
||||
"tag_created": false,
|
||||
"baseline_changed": false,
|
||||
"superseded_at": "2026-08-07",
|
||||
"note": "Retained for audit; never delete, overwrite, or reuse."
|
||||
}
|
||||
@@ -0,0 +1,14 @@
|
||||
26d56250af61748d26a75fb35aaaf46578d0520fc11796b75de2330ef2ebb64f VERSION
|
||||
81afc7ed5c1123146f61cf7bcf96c1fb69baa9371f1beec693341f20d612e0d4 active-runtime/app/v2r1c6_privacy_tools.py
|
||||
437b1f891f23a1dd12feabeced3edee3c54cc552d990d6d852805c8d5a165150 artifacts/v2r1c6-candidate-artifact.txt
|
||||
9f0dced0b252d2103ac4e975e17fe220aa990d4e3ebcfa17ad3ec32cf0ce4152 deploy/aios-v2/systemd/aios-v2r1c6-production.env.example
|
||||
cee41f7c6e5a56632c6cb015d9182a6376d502fbf7a53b701369bf062c33f359 deploy/aios-v2/systemd/aios-v2r1c6-production.service
|
||||
3f050310303662eb71840c0cb7cac5a5523968750ea1dd428653d5ba1ef2b727 deploy/aios-v2/v2r1c6-rollback.json
|
||||
cbfefff50c6b1a6bc98de138e468929b4a98b738baeb0e0c97d2672f13ccc452 docs/releases/V2R1C6-CANDIDATE.md
|
||||
a3813d060d842c22ff1a0f5ed968625b4d9d878fbacccb76d924f365d1c1a3a5 scripts/verify_v2r1c6_candidate.py
|
||||
a194638a44668617ddd2c12e45a43b7f0020d5f0308fcadd9f8da1db5d6bb645 scripts/verify_v2r1c6_candidate.sh
|
||||
951254504f20ae8d0d2397c2c2b2baeb2127651eb1e6cd1dc06695b836e176f9 tests/aios_v2_candidate/conftest.py
|
||||
43322bdfb3cffa9d4756d929741f942a0da45b2498c7b5ed91906e115d968948 tests/aios_v2_candidate/test_v2r1c5_privacy_tools.py
|
||||
068a35099d17047d127ac06be1a84adf090976fab13cf321febb28c787c0cac5 tests/aios_v2_candidate/test_v2r1c6_privacy_tools.py
|
||||
82ab1aa2d50d74a96392a01bb3c0b80eb9033f5bcbd5555487c22bc9250f412d tests/aios_v2_candidate/test_v2r1c6_release_consistency.py
|
||||
3b4a466cee373714805f50232d129ba06322027c51c467d1f35ab2c852b64c12 versions/V2R1C6.json
|
||||
@@ -0,0 +1,8 @@
|
||||
AIOS V2R1C6 candidate artifact
|
||||
repository: aios/aios
|
||||
base_ref: refs/heads/main
|
||||
base_oid: a33e2593967a180c89d44454350ccaeaf3f79b25
|
||||
candidate_branch: agent/v2r1c6-mainline-reconciliation-20260806
|
||||
production_deployed: false
|
||||
tag_created: false
|
||||
baseline_changed: false
|
||||
@@ -1,141 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Prove two real central-decision to Gateway-dispatch to Codex lifecycle cycles."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
import time
|
||||
import uuid
|
||||
|
||||
from health_probe_common import (
|
||||
ProbeError, gateway_base, load_config, read_token, request_json, state_version,
|
||||
)
|
||||
|
||||
|
||||
REQUIRED_MARKERS = {"CODEX_AUTO_CLAIM", "TASK_STARTED", "TASK_EXECUTED", "TASK_ENDED", "EVENT_POSTED"}
|
||||
|
||||
|
||||
def marker_counts(path: Path, command_id: str) -> dict[str, int]:
|
||||
counts = {marker: 0 for marker in REQUIRED_MARKERS}
|
||||
with path.open("r", encoding="utf-8") as handle:
|
||||
for line in handle:
|
||||
try:
|
||||
record = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
marker = record.get("marker")
|
||||
if record.get("command_id") == command_id and marker in counts:
|
||||
counts[marker] += 1
|
||||
return counts
|
||||
|
||||
|
||||
def watcher_status(database: Path, command_id: str) -> str | None:
|
||||
with sqlite3.connect(f"file:{database}?mode=ro", uri=True, timeout=2) as db:
|
||||
row = db.execute("SELECT status FROM commands WHERE command_id=?", (command_id,)).fetchone()
|
||||
return None if row is None else str(row[0])
|
||||
|
||||
|
||||
def wait_for_cycle(config: dict[str, object], token: str, cycle: int) -> tuple[str, str]:
|
||||
endpoint = str(config["gateway_event_url"])
|
||||
project = str(config["project_key"])
|
||||
event_id = f"a0-cycle-{cycle}-" + uuid.uuid4().hex
|
||||
work_unit_id = f"A0-CODEX-CYCLE-{cycle}-" + uuid.uuid4().hex[:16]
|
||||
event = {
|
||||
"schema_version": 1,
|
||||
"project_key": project,
|
||||
"contract_commit": config["contract_commit"],
|
||||
"event_id": event_id,
|
||||
"source_agent": "system",
|
||||
"event_type": "a0_unattended_acceptance_requested",
|
||||
"work_unit_id": work_unit_id,
|
||||
"status": "READY",
|
||||
"state_version": state_version(endpoint, project, token),
|
||||
"implementation_commit": None,
|
||||
"result_commit": None,
|
||||
"blocker": None,
|
||||
"evidence_refs": [],
|
||||
"payload": {
|
||||
"acceptance_contract": {
|
||||
"verdict": "DISPATCH",
|
||||
"work_unit_id": work_unit_id,
|
||||
"track_id": "A0_AUTOMATION",
|
||||
"gate_id": "A0_AUTOMATION_CLOSED",
|
||||
"primary_agent": "codex",
|
||||
"fallback_agent": "openclaw",
|
||||
"clean_base_commit": config["probe_clean_base_commit"],
|
||||
"allowed_paths": [],
|
||||
"required_checks": ["acceptance_probe"],
|
||||
"forbidden_operations": ["production_mutation", "git_mutation"],
|
||||
"instruction": "Run the fixed side-effect-free acceptance probe only.",
|
||||
}
|
||||
},
|
||||
}
|
||||
request_json(endpoint, token, method="POST", payload=event)
|
||||
deadline = time.monotonic() + int(config["cycle_timeout_seconds"])
|
||||
channel = None
|
||||
while time.monotonic() < deadline:
|
||||
_, status = request_json(endpoint + "/" + event_id, token)
|
||||
if status.get("status") == "TRIGGER_FAILED":
|
||||
raise ProbeError("central_trigger_failed")
|
||||
if status.get("status") == "DECIDED" and status.get("decision_applied") is True:
|
||||
channel = status.get("trigger_channel")
|
||||
break
|
||||
time.sleep(float(config["poll_interval_seconds"]))
|
||||
if channel not in {"workspace_agent", "responses_api"}:
|
||||
raise ProbeError("central_decision_timeout")
|
||||
|
||||
database = Path(str(config["codex_database_path"]))
|
||||
audit = Path(str(config["codex_audit_log"]))
|
||||
while time.monotonic() < deadline:
|
||||
if database.exists() and audit.exists() and watcher_status(database, work_unit_id) == "COMPLETED":
|
||||
counts = marker_counts(audit, work_unit_id)
|
||||
if all(counts[marker] == 1 for marker in REQUIRED_MARKERS):
|
||||
for suffix in ("started", "ended"):
|
||||
_, lifecycle = request_json(endpoint + "/" + work_unit_id + ":" + suffix, token)
|
||||
if lifecycle.get("event_id") != work_unit_id + ":" + suffix:
|
||||
raise ProbeError("gateway_lifecycle_missing")
|
||||
return event_id, str(channel)
|
||||
time.sleep(float(config["poll_interval_seconds"]))
|
||||
raise ProbeError("gateway_dispatch_or_codex_lifecycle_timeout")
|
||||
|
||||
|
||||
def project_summaries_since(database: Path, project: str, since: int) -> int:
|
||||
with sqlite3.connect(f"file:{database}?mode=ro", uri=True, timeout=2) as db:
|
||||
row = db.execute(
|
||||
"SELECT COUNT(*) FROM lifecycle WHERE project_key=? AND kind='PROJECT_SUMMARY' AND created_at>=?",
|
||||
(project, since),
|
||||
).fetchone()
|
||||
return 0 if row is None else int(row[0])
|
||||
|
||||
|
||||
def run(config_path: Path) -> int:
|
||||
config = load_config(config_path)
|
||||
endpoint = str(config["gateway_event_url"])
|
||||
gateway_base(endpoint)
|
||||
token = read_token(Path(str(config["gateway_token_file"])))
|
||||
started = int(time.time())
|
||||
results = [wait_for_cycle(config, token, cycle) for cycle in (1, 2)]
|
||||
if len({item[0] for item in results}) != 2:
|
||||
raise ProbeError("duplicate_cycle_event")
|
||||
if project_summaries_since(
|
||||
Path(str(config["gateway_database_path"])), str(config["project_key"]), started
|
||||
) < 2:
|
||||
raise ProbeError("project_summary_not_persisted")
|
||||
return 0
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--config", required=True, type=Path)
|
||||
args = parser.parse_args()
|
||||
try:
|
||||
return run(args.config)
|
||||
except (KeyError, OSError, ProbeError, sqlite3.Error, ValueError):
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,171 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Prove a real central-model decision through the authenticated Gateway."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import stat
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
import uuid
|
||||
|
||||
from health_probe_common import (
|
||||
ProbeError, atomic_receipt, gateway_base, load_config, read_token,
|
||||
request_json, state_version,
|
||||
)
|
||||
|
||||
PENDING_PATH = Path("/run/aios-health/central-gpt.pending.json")
|
||||
|
||||
|
||||
def _load_pending(
|
||||
path: Path, contract: str, *, owners: set[int] | None = None
|
||||
) -> tuple[str, int] | None:
|
||||
allowed_owners = {0} if owners is None else owners
|
||||
if not path.exists():
|
||||
return None
|
||||
info = path.lstat()
|
||||
if (
|
||||
not path.is_absolute()
|
||||
or stat.S_ISLNK(info.st_mode)
|
||||
or not stat.S_ISREG(info.st_mode)
|
||||
or stat.S_IMODE(info.st_mode) & ~0o640
|
||||
or (os.name == "posix" and info.st_uid not in allowed_owners)
|
||||
or path.resolve(strict=True) != Path(os.path.abspath(path))
|
||||
):
|
||||
raise ProbeError("unsafe_pending_marker")
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
if not isinstance(value, dict) or set(value) != {"contract_commit", "event_id", "state_version"}:
|
||||
raise ProbeError("invalid_pending_marker")
|
||||
event_id = value["event_id"]
|
||||
version = value["state_version"]
|
||||
if (
|
||||
value["contract_commit"] != contract
|
||||
or not isinstance(event_id, str)
|
||||
or not event_id.startswith("health-central-")
|
||||
or len(event_id) != 47
|
||||
or not isinstance(version, int)
|
||||
or version < 0
|
||||
):
|
||||
raise ProbeError("invalid_pending_marker")
|
||||
return event_id, version
|
||||
|
||||
|
||||
def _clear_pending(path: Path) -> None:
|
||||
if not path.exists():
|
||||
return
|
||||
info = path.lstat()
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISREG(info.st_mode):
|
||||
raise ProbeError("unsafe_pending_marker")
|
||||
path.unlink()
|
||||
|
||||
|
||||
def _safe_reason(exc: BaseException) -> str:
|
||||
reason = str(exc)
|
||||
if reason and len(reason) <= 64 and all(char.islower() or char.isdigit() or char == "_" for char in reason):
|
||||
return reason
|
||||
return "probe_error"
|
||||
|
||||
|
||||
def run(config_path: Path, pending_path: Path = PENDING_PATH) -> int:
|
||||
config = load_config(config_path)
|
||||
endpoint = config["gateway_event_url"]
|
||||
gateway_base(endpoint)
|
||||
token = read_token(Path(config["gateway_token_file"]))
|
||||
project = config["project_key"]
|
||||
contract = config["contract_commit"]
|
||||
pending = _load_pending(pending_path, contract)
|
||||
is_new = pending is None
|
||||
if is_new:
|
||||
event_id = "health-central-" + uuid.uuid4().hex
|
||||
version = state_version(endpoint, project, token)
|
||||
atomic_receipt(
|
||||
pending_path,
|
||||
{"contract_commit": contract, "event_id": event_id, "state_version": version},
|
||||
)
|
||||
else:
|
||||
event_id, version = pending
|
||||
event = {
|
||||
"schema_version": 1,
|
||||
"project_key": project,
|
||||
"contract_commit": contract,
|
||||
"event_id": event_id,
|
||||
"source_agent": "system",
|
||||
"event_type": "central_gpt_health_probe",
|
||||
"work_unit_id": "CENTRAL-GPT-HEALTH",
|
||||
"status": "READY",
|
||||
"state_version": version,
|
||||
"implementation_commit": None,
|
||||
"result_commit": None,
|
||||
"blocker": None,
|
||||
"evidence_refs": [],
|
||||
"payload": {"probe": "side_effect_free", "nonce": event_id},
|
||||
}
|
||||
should_post = is_new
|
||||
if not is_new:
|
||||
try:
|
||||
_, observed = request_json(endpoint + "/" + event_id, token)
|
||||
except ProbeError as exc:
|
||||
if str(exc) != "gateway_http_404":
|
||||
raise
|
||||
should_post = True
|
||||
else:
|
||||
observed = None
|
||||
if should_post:
|
||||
try:
|
||||
status, _ = request_json(endpoint, token, method="POST", payload=event)
|
||||
except ProbeError as exc:
|
||||
if str(exc) == "gateway_fail_closed_409":
|
||||
_clear_pending(pending_path)
|
||||
raise
|
||||
if status not in {200, 202}:
|
||||
raise ProbeError("event_not_accepted")
|
||||
observed = None
|
||||
deadline = time.monotonic() + int(config["central_timeout_seconds"])
|
||||
while time.monotonic() < deadline:
|
||||
_, observed = request_json(endpoint + "/" + event_id, token)
|
||||
if observed.get("status") in {"DECIDED", "TRIGGER_FAILED", "DEAD_LETTER"}:
|
||||
break
|
||||
time.sleep(float(config["poll_interval_seconds"]))
|
||||
if isinstance(observed, dict) and observed.get("status") == "DEAD_LETTER":
|
||||
_clear_pending(pending_path)
|
||||
raise ProbeError("central_event_dead_letter")
|
||||
if not isinstance(observed, dict) or observed.get("status") != "DECIDED" or observed.get("decision_applied") is not True:
|
||||
raise ProbeError("central_decision_not_proven")
|
||||
channel = observed.get("trigger_channel")
|
||||
if channel not in {"workspace_agent", "responses_api"}:
|
||||
raise ProbeError("central_channel_not_proven")
|
||||
_clear_pending(pending_path)
|
||||
now = int(time.time())
|
||||
atomic_receipt(
|
||||
Path(config["central_receipt_path"]),
|
||||
{
|
||||
"subject": "central_gpt",
|
||||
"health": "HEALTHY",
|
||||
"live_probe_succeeded": True,
|
||||
"observed_at_epoch": now,
|
||||
"event_id": event_id,
|
||||
"decision_applied": True,
|
||||
"state_version_after": observed["state_version_after"],
|
||||
"workspace_agent": {"validated_live": channel == "workspace_agent"},
|
||||
"responses_api": {"validated_live": channel == "responses_api"},
|
||||
},
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--config", required=True, type=Path)
|
||||
args = parser.parse_args()
|
||||
try:
|
||||
return run(args.config)
|
||||
except (KeyError, OSError, ProbeError, ValueError) as exc:
|
||||
print(f"CENTRAL_GPT_PROBE=BLOCKED reason={_safe_reason(exc)}", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,113 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Queue one fixed no-side-effect command and prove the watcher lifecycle."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
import stat
|
||||
import time
|
||||
import uuid
|
||||
|
||||
from health_probe_common import (
|
||||
ProbeError, atomic_receipt, gateway_base, load_config, read_token,
|
||||
request_json, state_version,
|
||||
)
|
||||
|
||||
|
||||
MARKERS = {"CODEX_AUTO_CLAIM", "TASK_STARTED", "TASK_EXECUTED", "TASK_ENDED", "EVENT_POSTED"}
|
||||
|
||||
|
||||
def _write_command(path: Path, value: dict[str, object]) -> None:
|
||||
directory = path.parent
|
||||
info = directory.lstat()
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISDIR(info.st_mode) or stat.S_IMODE(info.st_mode) & 0o002:
|
||||
raise ProbeError("unsafe_command_queue")
|
||||
data = (json.dumps(value, sort_keys=True, separators=(",", ":")) + "\n").encode()
|
||||
fd = os.open(path, os.O_WRONLY | os.O_CREAT | os.O_EXCL | getattr(os, "O_NOFOLLOW", 0), 0o640)
|
||||
try:
|
||||
os.write(fd, data)
|
||||
os.fsync(fd)
|
||||
finally:
|
||||
os.close(fd)
|
||||
|
||||
|
||||
def _status(database: Path, command_id: str) -> str | None:
|
||||
with sqlite3.connect(f"file:{database}?mode=ro", uri=True, timeout=2) as db:
|
||||
row = db.execute("SELECT status FROM commands WHERE command_id=?", (command_id,)).fetchone()
|
||||
return None if row is None else str(row[0])
|
||||
|
||||
|
||||
def _markers(path: Path, command_id: str) -> dict[str, int]:
|
||||
result = {name: 0 for name in MARKERS}
|
||||
with path.open("r", encoding="utf-8") as handle:
|
||||
for line in handle:
|
||||
try:
|
||||
item = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
if item.get("command_id") == command_id and item.get("marker") in result:
|
||||
result[item["marker"]] += 1
|
||||
return result
|
||||
|
||||
|
||||
def run(config_path: Path) -> int:
|
||||
config = load_config(config_path)
|
||||
endpoint = config["gateway_event_url"]
|
||||
gateway_base(endpoint)
|
||||
token = read_token(Path(config["gateway_token_file"]))
|
||||
command_id = "health-codex-" + uuid.uuid4().hex
|
||||
version = state_version(endpoint, config["project_key"], token)
|
||||
command = {
|
||||
"schema_version": 1,
|
||||
"command_id": command_id,
|
||||
"project_key": config["project_key"],
|
||||
"work_unit_id": command_id,
|
||||
"contract_commit": config["contract_commit"],
|
||||
"state_version": version,
|
||||
"execution": {"kind": "acceptance_probe", "input": "fixed-side-effect-free-health-probe-v1"},
|
||||
}
|
||||
_write_command(Path(config["codex_command_queue"]) / f"{command_id}.json", command)
|
||||
deadline = time.monotonic() + int(config["codex_timeout_seconds"])
|
||||
database = Path(config["codex_database_path"])
|
||||
audit = Path(config["codex_audit_log"])
|
||||
while time.monotonic() < deadline:
|
||||
if database.exists() and audit.exists() and _status(database, command_id) == "COMPLETED":
|
||||
counts = _markers(audit, command_id)
|
||||
if all(counts[name] == 1 for name in MARKERS):
|
||||
for suffix in ("started", "ended"):
|
||||
_, event = request_json(endpoint + "/" + command_id + ":" + suffix, token)
|
||||
if event.get("event_id") != command_id + ":" + suffix:
|
||||
raise ProbeError("gateway_lifecycle_missing")
|
||||
atomic_receipt(
|
||||
Path(config["codex_receipt_path"]),
|
||||
{
|
||||
"subject": "codex",
|
||||
"health": "HEALTHY",
|
||||
"live_probe_succeeded": True,
|
||||
"observed_at_epoch": int(time.time()),
|
||||
"command_id": command_id,
|
||||
"lifecycle_complete": True,
|
||||
"duplicate_side_effects": False,
|
||||
},
|
||||
)
|
||||
return 0
|
||||
time.sleep(float(config["poll_interval_seconds"]))
|
||||
raise ProbeError("codex_lifecycle_not_proven")
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--config", required=True, type=Path)
|
||||
args = parser.parse_args()
|
||||
try:
|
||||
return run(args.config)
|
||||
except (KeyError, OSError, ProbeError, sqlite3.Error, ValueError):
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,940 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Durable GPT + one-executor quorum and failover controller.
|
||||
|
||||
The controller persists decisions before dispatch and never stores credentials.
|
||||
Health is accepted only from metadata-only, live-probe receipts.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import sqlite3
|
||||
import stat
|
||||
import subprocess
|
||||
import tempfile
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
import urllib.parse
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Iterable, Mapping
|
||||
|
||||
|
||||
ALLOWED_LIFECYCLE_EVENTS = frozenset(
|
||||
{
|
||||
"TASK_DISPATCHED",
|
||||
"TASK_STARTED",
|
||||
"TASK_ENDED",
|
||||
"DECISION_APPLIED",
|
||||
"PROJECT_SUMMARY",
|
||||
"PROJECT_COMPLETED",
|
||||
}
|
||||
)
|
||||
EXECUTORS = ("openclaw", "codex")
|
||||
SECRET_KEYS = frozenset(
|
||||
{
|
||||
"secret",
|
||||
"token",
|
||||
"password",
|
||||
"api_key",
|
||||
"authorization",
|
||||
"credential",
|
||||
"private_key",
|
||||
"environment",
|
||||
"env",
|
||||
"argv",
|
||||
"stdout",
|
||||
"stderr",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
class Health(str, Enum):
|
||||
HEALTHY = "HEALTHY"
|
||||
UNHEALTHY = "UNHEALTHY"
|
||||
UNKNOWN = "UNKNOWN"
|
||||
|
||||
|
||||
class ControllerError(RuntimeError):
|
||||
"""Fail-closed controller error."""
|
||||
|
||||
|
||||
class EventConflict(ControllerError):
|
||||
"""An event id was reused with a different payload."""
|
||||
|
||||
|
||||
class StaleStateVersion(ControllerError):
|
||||
"""A dispatch attempted to overwrite a newer task state."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class QuorumDecision:
|
||||
allowed: bool
|
||||
priority: str
|
||||
status: str
|
||||
active_executor: str | None
|
||||
standby_executor: str | None
|
||||
repair_required: bool
|
||||
|
||||
|
||||
def canonical_json(value: Any) -> str:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=True)
|
||||
|
||||
|
||||
def digest_json(value: Any) -> str:
|
||||
return hashlib.sha256(canonical_json(value).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def _contains_forbidden_key(value: Any) -> bool:
|
||||
if isinstance(value, Mapping):
|
||||
for key, child in value.items():
|
||||
normalized = str(key).strip().lower().replace("-", "_")
|
||||
if normalized in SECRET_KEYS or _contains_forbidden_key(child):
|
||||
return True
|
||||
elif isinstance(value, list):
|
||||
return any(_contains_forbidden_key(item) for item in value)
|
||||
return False
|
||||
|
||||
|
||||
def validate_metadata_only(value: Mapping[str, Any]) -> None:
|
||||
if _contains_forbidden_key(value):
|
||||
raise ControllerError("secret-bearing or output-bearing fields are forbidden")
|
||||
|
||||
|
||||
def atomic_json_write(path: Path, value: Mapping[str, Any], mode: int = 0o600) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True, mode=0o700)
|
||||
validate_secure_directory(path.parent)
|
||||
fd, temporary = tempfile.mkstemp(prefix=f".{path.name}.", dir=str(path.parent))
|
||||
try:
|
||||
os.fchmod(fd, mode)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as handle:
|
||||
handle.write(canonical_json(value))
|
||||
handle.write("\n")
|
||||
handle.flush()
|
||||
os.fsync(handle.fileno())
|
||||
os.replace(temporary, path)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
|
||||
|
||||
def validate_secure_directory(path: Path, *, expected_uid: int | None = None) -> None:
|
||||
info = path.lstat()
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISDIR(info.st_mode):
|
||||
raise ControllerError(f"unsafe directory type rejected: {path}")
|
||||
if os.name == "posix" and path.resolve(strict=True) != Path(os.path.abspath(path)):
|
||||
raise ControllerError(f"symlinked directory component rejected: {path}")
|
||||
if os.name == "posix" and info.st_mode & 0o022:
|
||||
raise ControllerError(f"group/world-writable directory rejected: {path}")
|
||||
if expected_uid is not None and info.st_uid != expected_uid:
|
||||
raise ControllerError(f"unexpected owner for directory {path}")
|
||||
|
||||
|
||||
def read_secure_json(path: Path, *, expected_uid: int | None = None) -> dict[str, Any]:
|
||||
info = path.lstat()
|
||||
if stat.S_ISLNK(info.st_mode):
|
||||
raise ControllerError(f"symlink rejected: {path}")
|
||||
if not stat.S_ISREG(info.st_mode):
|
||||
raise ControllerError(f"not a regular file: {path}")
|
||||
if os.name == "posix" and info.st_mode & 0o022:
|
||||
raise ControllerError(f"group/world-writable file rejected: {path}")
|
||||
validate_secure_directory(path.parent, expected_uid=expected_uid)
|
||||
if os.name == "posix" and path.resolve(strict=True) != Path(os.path.abspath(path)):
|
||||
raise ControllerError(f"symlinked file component rejected: {path}")
|
||||
if expected_uid is not None and info.st_uid != expected_uid:
|
||||
raise ControllerError(f"unexpected owner for {path}")
|
||||
with path.open("r", encoding="utf-8") as handle:
|
||||
value = json.load(handle)
|
||||
if not isinstance(value, dict):
|
||||
raise ControllerError(f"JSON object required: {path}")
|
||||
validate_metadata_only(value)
|
||||
return value
|
||||
|
||||
|
||||
def read_gateway_token(path: Path) -> str:
|
||||
if not path.is_absolute():
|
||||
raise ControllerError("gateway token path must be absolute")
|
||||
try:
|
||||
info = path.lstat()
|
||||
except FileNotFoundError as exc:
|
||||
raise ControllerError("gateway token unavailable") from exc
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISREG(info.st_mode):
|
||||
raise ControllerError("gateway token must be a regular non-symlink file")
|
||||
if stat.S_IMODE(info.st_mode) & ~0o640:
|
||||
raise ControllerError("gateway token mode exceeds 0640")
|
||||
if os.name == "posix" and info.st_uid not in {0, os.geteuid()}:
|
||||
raise ControllerError("gateway token owner is not approved")
|
||||
if os.name == "posix" and path.resolve(strict=True) != Path(os.path.abspath(path)):
|
||||
raise ControllerError("gateway token has a symlinked path component")
|
||||
flags = os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0)
|
||||
fd = os.open(path, flags)
|
||||
try:
|
||||
opened = os.fstat(fd)
|
||||
if not stat.S_ISREG(opened.st_mode) or opened.st_ino != info.st_ino or opened.st_dev != info.st_dev:
|
||||
raise ControllerError("gateway token changed during validation")
|
||||
data = os.read(fd, 16_385)
|
||||
if os.read(fd, 1):
|
||||
raise ControllerError("gateway token too large")
|
||||
finally:
|
||||
os.close(fd)
|
||||
if not data or len(data) > 16_384 or b"\n" in data or b"\r" in data:
|
||||
raise ControllerError("gateway token format rejected")
|
||||
try:
|
||||
token = data.decode("utf-8")
|
||||
except UnicodeDecodeError as exc:
|
||||
raise ControllerError("gateway token encoding rejected") from exc
|
||||
if not token:
|
||||
raise ControllerError("gateway token unavailable")
|
||||
return token
|
||||
|
||||
|
||||
def validate_health_receipt(
|
||||
receipt: Mapping[str, Any],
|
||||
subject: str,
|
||||
*,
|
||||
now: float | None = None,
|
||||
max_age_seconds: int = 60,
|
||||
) -> Health:
|
||||
validate_metadata_only(receipt)
|
||||
if receipt.get("subject") != subject:
|
||||
return Health.UNKNOWN
|
||||
try:
|
||||
health = Health(str(receipt.get("health", "UNKNOWN")))
|
||||
except ValueError:
|
||||
return Health.UNKNOWN
|
||||
if health is not Health.HEALTHY:
|
||||
return health
|
||||
if receipt.get("live_probe_succeeded") is not True:
|
||||
return Health.UNKNOWN
|
||||
observed_at = receipt.get("observed_at_epoch")
|
||||
if not isinstance(observed_at, (int, float)):
|
||||
return Health.UNKNOWN
|
||||
now = time.time() if now is None else now
|
||||
if observed_at > now + 5 or now - observed_at > max_age_seconds:
|
||||
return Health.UNKNOWN
|
||||
if subject == "central_gpt":
|
||||
workspace = receipt.get("workspace_agent")
|
||||
responses = receipt.get("responses_api")
|
||||
workspace_ok = isinstance(workspace, Mapping) and workspace.get("validated_live") is True
|
||||
responses_ok = isinstance(responses, Mapping) and responses.get("validated_live") is True
|
||||
if not (workspace_ok or responses_ok):
|
||||
return Health.UNKNOWN
|
||||
return Health.HEALTHY
|
||||
|
||||
|
||||
def choose_executor(workload: str) -> str:
|
||||
if workload in {"complex_code", "security_boundary", "architecture", "complex_code_security_architecture"}:
|
||||
return "codex"
|
||||
return "openclaw"
|
||||
|
||||
|
||||
def evaluate_quorum(
|
||||
central_gpt: Health,
|
||||
openclaw: Health,
|
||||
codex: Health,
|
||||
workload: str,
|
||||
) -> QuorumDecision:
|
||||
if central_gpt is not Health.HEALTHY:
|
||||
status = "BLOCKED_CENTRAL_GPT_UNKNOWN" if central_gpt is Health.UNKNOWN else "BLOCKED_CENTRAL_GPT_UNHEALTHY"
|
||||
return QuorumDecision(False, "P0", status, None, None, True)
|
||||
|
||||
healthy = [name for name, health in (("openclaw", openclaw), ("codex", codex)) if health is Health.HEALTHY]
|
||||
if not healthy:
|
||||
has_unknown = Health.UNKNOWN in {openclaw, codex}
|
||||
status = "BLOCKED_EXECUTOR_HEALTH_UNKNOWN" if has_unknown else "BLOCKED_NO_HEALTHY_EXECUTOR"
|
||||
return QuorumDecision(False, "P1", status, None, None, True)
|
||||
|
||||
if len(healthy) == 1:
|
||||
active = healthy[0]
|
||||
standby = "codex" if active == "openclaw" else "openclaw"
|
||||
return QuorumDecision(True, "P3", "EXECUTOR_QUORUM_PASS", active, standby, False)
|
||||
|
||||
active = choose_executor(workload)
|
||||
standby = "codex" if active == "openclaw" else "openclaw"
|
||||
return QuorumDecision(True, "NONE", "EXECUTOR_QUORUM_PASS", active, standby, False)
|
||||
|
||||
|
||||
class QuorumStore:
|
||||
def __init__(self, path: Path):
|
||||
self.path = path
|
||||
path.parent.mkdir(parents=True, exist_ok=True, mode=0o700)
|
||||
expected_uid = os.geteuid() if os.name == "posix" else None
|
||||
validate_secure_directory(path.parent, expected_uid=expected_uid)
|
||||
if path.exists() or path.is_symlink():
|
||||
info = path.lstat()
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISREG(info.st_mode) or info.st_nlink != 1:
|
||||
raise ControllerError(f"unsafe database path rejected: {path}")
|
||||
if expected_uid is not None and info.st_uid != expected_uid:
|
||||
raise ControllerError(f"unexpected database owner: {path}")
|
||||
self.db = sqlite3.connect(str(path), isolation_level=None, timeout=30)
|
||||
if os.name == "posix":
|
||||
path.chmod(0o600)
|
||||
self.db.row_factory = sqlite3.Row
|
||||
self.db.execute("PRAGMA journal_mode=WAL")
|
||||
self.db.execute("PRAGMA synchronous=FULL")
|
||||
self._initialize()
|
||||
|
||||
def close(self) -> None:
|
||||
self.db.close()
|
||||
|
||||
def _initialize(self) -> None:
|
||||
self.db.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS events (
|
||||
event_id TEXT PRIMARY KEY,
|
||||
payload_digest TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
source TEXT NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
created_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS tasks (
|
||||
work_unit TEXT PRIMARY KEY,
|
||||
contract_commit TEXT NOT NULL,
|
||||
event_id TEXT NOT NULL,
|
||||
state_version INTEGER NOT NULL,
|
||||
workload TEXT NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
active_executor TEXT,
|
||||
standby_executor TEXT,
|
||||
checkpoint TEXT,
|
||||
lease_owner TEXT,
|
||||
lease_until REAL,
|
||||
interrupted_executor TEXT,
|
||||
recovery_priority TEXT NOT NULL,
|
||||
updated_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS lifecycle (
|
||||
sequence INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
work_unit TEXT NOT NULL,
|
||||
event_type TEXT NOT NULL,
|
||||
executor TEXT,
|
||||
state_version INTEGER NOT NULL,
|
||||
metadata_json TEXT NOT NULL,
|
||||
created_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS effects (
|
||||
effect_id TEXT PRIMARY KEY,
|
||||
work_unit TEXT NOT NULL,
|
||||
payload_digest TEXT NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
created_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS outbox (
|
||||
outbox_id TEXT PRIMARY KEY,
|
||||
destination TEXT NOT NULL,
|
||||
payload_digest TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
attempts INTEGER NOT NULL DEFAULT 0,
|
||||
next_attempt REAL NOT NULL,
|
||||
created_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS blockers (
|
||||
blocker_key TEXT PRIMARY KEY,
|
||||
occurrences INTEGER NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
updated_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS observed_refs (
|
||||
ref_name TEXT PRIMARY KEY,
|
||||
oid TEXT NOT NULL,
|
||||
updated_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS summaries (
|
||||
work_unit TEXT PRIMARY KEY,
|
||||
summary_digest TEXT NOT NULL,
|
||||
summary_json TEXT NOT NULL,
|
||||
created_at REAL NOT NULL
|
||||
);
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS lifecycle_once
|
||||
ON lifecycle(work_unit, event_type, COALESCE(executor, ''), state_version);
|
||||
"""
|
||||
)
|
||||
|
||||
def ingest_event(self, event_id: str, payload: Mapping[str, Any], source: str) -> bool:
|
||||
validate_metadata_only(payload)
|
||||
encoded = canonical_json(payload)
|
||||
digest = hashlib.sha256(encoded.encode("utf-8")).hexdigest()
|
||||
existing = self.db.execute("SELECT payload_digest FROM events WHERE event_id=?", (event_id,)).fetchone()
|
||||
if existing:
|
||||
if existing["payload_digest"] != digest:
|
||||
self.db.execute("UPDATE events SET status='DEAD_LETTER_CONFLICT' WHERE event_id=?", (event_id,))
|
||||
raise EventConflict(f"event id payload conflict: {event_id}")
|
||||
return False
|
||||
self.db.execute(
|
||||
"INSERT INTO events VALUES(?,?,?,?,?,?)",
|
||||
(event_id, digest, encoded, source, "ACCEPTED", time.time()),
|
||||
)
|
||||
return True
|
||||
|
||||
def upsert_task(
|
||||
self,
|
||||
*,
|
||||
work_unit: str,
|
||||
contract_commit: str,
|
||||
event_id: str,
|
||||
state_version: int,
|
||||
workload: str,
|
||||
decision: QuorumDecision,
|
||||
checkpoint: str | None = None,
|
||||
) -> str:
|
||||
now = time.time()
|
||||
self.db.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
current = self.db.execute("SELECT * FROM tasks WHERE work_unit=?", (work_unit,)).fetchone()
|
||||
if current and state_version < current["state_version"]:
|
||||
raise StaleStateVersion(f"stale state version for {work_unit}")
|
||||
interrupted: str | None = None
|
||||
recovery_priority = decision.priority
|
||||
status = "BLOCKED"
|
||||
if decision.allowed:
|
||||
status = "READY"
|
||||
if current and current["active_executor"] and current["active_executor"] != decision.active_executor:
|
||||
interrupted = current["active_executor"]
|
||||
recovery_priority = "P2"
|
||||
status = "INTERRUPTED_AGENT_FAILOVER"
|
||||
if checkpoint is None:
|
||||
checkpoint = current["checkpoint"]
|
||||
if current:
|
||||
if contract_commit != current["contract_commit"] or event_id != current["event_id"]:
|
||||
raise ControllerError("failover must preserve contract_commit and event_id")
|
||||
if (
|
||||
current["state_version"] == state_version
|
||||
and current["active_executor"] == decision.active_executor
|
||||
and current["status"] in {"RUNNING", "COMPLETED"}
|
||||
):
|
||||
self.db.execute("COMMIT")
|
||||
return current["status"]
|
||||
self.db.execute(
|
||||
"""UPDATE tasks SET state_version=?, workload=?, status=?, active_executor=?,
|
||||
standby_executor=?, checkpoint=?, interrupted_executor=?, recovery_priority=?, updated_at=? WHERE work_unit=?""",
|
||||
(
|
||||
state_version,
|
||||
workload,
|
||||
status,
|
||||
decision.active_executor,
|
||||
decision.standby_executor,
|
||||
checkpoint,
|
||||
interrupted,
|
||||
recovery_priority,
|
||||
now,
|
||||
work_unit,
|
||||
),
|
||||
)
|
||||
else:
|
||||
self.db.execute(
|
||||
"INSERT INTO tasks VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?)",
|
||||
(
|
||||
work_unit,
|
||||
contract_commit,
|
||||
event_id,
|
||||
state_version,
|
||||
workload,
|
||||
status,
|
||||
decision.active_executor,
|
||||
decision.standby_executor,
|
||||
checkpoint,
|
||||
None,
|
||||
None,
|
||||
interrupted,
|
||||
recovery_priority,
|
||||
now,
|
||||
),
|
||||
)
|
||||
self.db.execute("COMMIT")
|
||||
return status
|
||||
except Exception:
|
||||
self.db.execute("ROLLBACK")
|
||||
raise
|
||||
|
||||
def claim_lease(self, work_unit: str, worker: str, ttl_seconds: int, now: float | None = None) -> bool:
|
||||
now = time.time() if now is None else now
|
||||
self.db.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
task = self.db.execute(
|
||||
"SELECT active_executor, status, lease_owner, lease_until FROM tasks WHERE work_unit=?",
|
||||
(work_unit,),
|
||||
).fetchone()
|
||||
if not task:
|
||||
raise ControllerError(f"unknown work unit: {work_unit}")
|
||||
if worker != task["active_executor"]:
|
||||
self.db.execute("ROLLBACK")
|
||||
return False
|
||||
if task["status"] in {"BLOCKED", "COMPLETED"}:
|
||||
self.db.execute("ROLLBACK")
|
||||
return False
|
||||
lease_live = task["lease_owner"] and task["lease_until"] and task["lease_until"] > now
|
||||
if lease_live and task["lease_owner"] != worker:
|
||||
self.db.execute("ROLLBACK")
|
||||
return False
|
||||
self.db.execute(
|
||||
"UPDATE tasks SET lease_owner=?, lease_until=?, status='RUNNING', updated_at=? WHERE work_unit=?",
|
||||
(worker, now + ttl_seconds, now, work_unit),
|
||||
)
|
||||
self.db.execute("COMMIT")
|
||||
return True
|
||||
except Exception:
|
||||
if self.db.in_transaction:
|
||||
self.db.execute("ROLLBACK")
|
||||
raise
|
||||
|
||||
def dispatch_task(
|
||||
self,
|
||||
*,
|
||||
work_unit: str,
|
||||
contract_commit: str,
|
||||
event_id: str,
|
||||
state_version: int,
|
||||
workload: str,
|
||||
decision: QuorumDecision,
|
||||
checkpoint: str | None = None,
|
||||
) -> str:
|
||||
status = self.upsert_task(
|
||||
work_unit=work_unit,
|
||||
contract_commit=contract_commit,
|
||||
event_id=event_id,
|
||||
state_version=state_version,
|
||||
workload=workload,
|
||||
decision=decision,
|
||||
checkpoint=checkpoint,
|
||||
)
|
||||
if decision.allowed and status != "COMPLETED":
|
||||
metadata = {
|
||||
"contract_commit": contract_commit,
|
||||
"event_id": event_id,
|
||||
"status": status,
|
||||
}
|
||||
self.append_lifecycle(work_unit, "TASK_DISPATCHED", decision.active_executor, state_version, metadata)
|
||||
self.enqueue(
|
||||
f"dispatch:{work_unit}:{state_version}:{decision.active_executor}",
|
||||
"gateway",
|
||||
{"event_type": "TASK_DISPATCHED", "work_unit": work_unit, **metadata},
|
||||
)
|
||||
return status
|
||||
|
||||
def start_task(self, work_unit: str, executor: str, state_version: int, lease_ttl_seconds: int) -> bool:
|
||||
if not self.claim_lease(work_unit, executor, lease_ttl_seconds):
|
||||
return False
|
||||
self.append_lifecycle(work_unit, "TASK_STARTED", executor, state_version, {"status": "RUNNING"})
|
||||
self.enqueue(
|
||||
f"started:{work_unit}:{state_version}:{executor}",
|
||||
"gateway",
|
||||
{"event_type": "TASK_STARTED", "work_unit": work_unit, "executor": executor, "state_version": state_version},
|
||||
)
|
||||
return True
|
||||
|
||||
def end_task(
|
||||
self,
|
||||
work_unit: str,
|
||||
executor: str,
|
||||
state_version: int,
|
||||
result: str,
|
||||
summary: Mapping[str, Any],
|
||||
*,
|
||||
project_completed: bool = False,
|
||||
) -> None:
|
||||
validate_metadata_only(summary)
|
||||
self.db.execute("BEGIN IMMEDIATE")
|
||||
try:
|
||||
task = self.db.execute("SELECT active_executor,state_version FROM tasks WHERE work_unit=?", (work_unit,)).fetchone()
|
||||
if not task or task["active_executor"] != executor:
|
||||
raise ControllerError("only the active executor may end a task")
|
||||
if task["state_version"] != state_version:
|
||||
raise StaleStateVersion(f"stale state version for {work_unit}")
|
||||
self.db.execute(
|
||||
"UPDATE tasks SET status='COMPLETED', lease_owner=NULL, lease_until=NULL, updated_at=? WHERE work_unit=?",
|
||||
(time.time(), work_unit),
|
||||
)
|
||||
self.append_lifecycle(work_unit, "TASK_ENDED", executor, state_version, {"result": result})
|
||||
self.append_lifecycle(work_unit, "DECISION_APPLIED", executor, state_version, {"result": result})
|
||||
self.append_lifecycle(work_unit, "PROJECT_SUMMARY", executor, state_version, summary)
|
||||
if project_completed:
|
||||
self.append_lifecycle(work_unit, "PROJECT_COMPLETED", executor, state_version, {"result": result})
|
||||
self.persist_summary(work_unit, summary)
|
||||
outbound = (
|
||||
("TASK_ENDED", {"result": result}),
|
||||
("DECISION_APPLIED", {"result": result}),
|
||||
("PROJECT_SUMMARY", dict(summary)),
|
||||
)
|
||||
for event_type, metadata in outbound:
|
||||
self.enqueue(
|
||||
f"{event_type.lower()}:{work_unit}:{state_version}:{executor}",
|
||||
"gateway",
|
||||
{
|
||||
"event_type": event_type,
|
||||
"work_unit": work_unit,
|
||||
"executor": executor,
|
||||
"state_version": state_version,
|
||||
**metadata,
|
||||
},
|
||||
)
|
||||
if project_completed:
|
||||
self.enqueue(
|
||||
f"project_completed:{work_unit}:{state_version}:{executor}",
|
||||
"gateway",
|
||||
{
|
||||
"event_type": "PROJECT_COMPLETED",
|
||||
"work_unit": work_unit,
|
||||
"executor": executor,
|
||||
"state_version": state_version,
|
||||
"result": result,
|
||||
},
|
||||
)
|
||||
self.db.execute("COMMIT")
|
||||
except Exception:
|
||||
if self.db.in_transaction:
|
||||
self.db.execute("ROLLBACK")
|
||||
raise
|
||||
|
||||
def record_effect(self, effect_id: str, work_unit: str, payload: Mapping[str, Any]) -> bool:
|
||||
validate_metadata_only(payload)
|
||||
digest = digest_json(payload)
|
||||
existing = self.db.execute("SELECT payload_digest FROM effects WHERE effect_id=?", (effect_id,)).fetchone()
|
||||
if existing:
|
||||
if existing["payload_digest"] != digest:
|
||||
raise EventConflict(f"effect id payload conflict: {effect_id}")
|
||||
return False
|
||||
self.db.execute(
|
||||
"INSERT INTO effects VALUES(?,?,?,?,?)",
|
||||
(effect_id, work_unit, digest, "COMPLETED", time.time()),
|
||||
)
|
||||
return True
|
||||
|
||||
def append_lifecycle(
|
||||
self,
|
||||
work_unit: str,
|
||||
event_type: str,
|
||||
executor: str | None,
|
||||
state_version: int,
|
||||
metadata: Mapping[str, Any],
|
||||
) -> None:
|
||||
if event_type not in ALLOWED_LIFECYCLE_EVENTS:
|
||||
raise ControllerError(f"unsupported lifecycle event: {event_type}")
|
||||
validate_metadata_only(metadata)
|
||||
self.db.execute(
|
||||
"INSERT OR IGNORE INTO lifecycle(work_unit,event_type,executor,state_version,metadata_json,created_at) VALUES(?,?,?,?,?,?)",
|
||||
(work_unit, event_type, executor, state_version, canonical_json(metadata), time.time()),
|
||||
)
|
||||
|
||||
def persist_summary(self, work_unit: str, summary: Mapping[str, Any]) -> None:
|
||||
validate_metadata_only(summary)
|
||||
encoded = canonical_json(summary)
|
||||
digest = hashlib.sha256(encoded.encode("utf-8")).hexdigest()
|
||||
self.db.execute(
|
||||
"INSERT OR REPLACE INTO summaries VALUES(?,?,?,?)",
|
||||
(work_unit, digest, encoded, time.time()),
|
||||
)
|
||||
|
||||
def enqueue(self, outbox_id: str, destination: str, payload: Mapping[str, Any]) -> bool:
|
||||
validate_metadata_only(payload)
|
||||
encoded = canonical_json(payload)
|
||||
digest = hashlib.sha256(encoded.encode("utf-8")).hexdigest()
|
||||
existing = self.db.execute("SELECT payload_digest FROM outbox WHERE outbox_id=?", (outbox_id,)).fetchone()
|
||||
if existing:
|
||||
if existing["payload_digest"] != digest:
|
||||
raise EventConflict(f"outbox id payload conflict: {outbox_id}")
|
||||
return False
|
||||
self.db.execute(
|
||||
"INSERT INTO outbox VALUES(?,?,?,?,?,?,?,?)",
|
||||
(outbox_id, destination, digest, encoded, "PENDING", 0, time.time(), time.time()),
|
||||
)
|
||||
return True
|
||||
|
||||
def record_blocker(self, blocker_key: str, threshold: int) -> str:
|
||||
now = time.time()
|
||||
row = self.db.execute("SELECT occurrences FROM blockers WHERE blocker_key=?", (blocker_key,)).fetchone()
|
||||
occurrences = (row["occurrences"] if row else 0) + 1
|
||||
status = "DEAD_LETTER" if occurrences > threshold else "RETRY"
|
||||
self.db.execute(
|
||||
"INSERT INTO blockers VALUES(?,?,?,?) ON CONFLICT(blocker_key) DO UPDATE SET occurrences=excluded.occurrences,status=excluded.status,updated_at=excluded.updated_at",
|
||||
(blocker_key, occurrences, status, now),
|
||||
)
|
||||
return status
|
||||
|
||||
def deliver_outbox(self, sender: Callable[[Mapping[str, Any]], None], max_attempts: int, now: float | None = None) -> tuple[int, int]:
|
||||
now = time.time() if now is None else now
|
||||
sent = 0
|
||||
failed = 0
|
||||
rows = self.db.execute(
|
||||
"SELECT * FROM outbox WHERE status='PENDING' AND next_attempt<=? ORDER BY created_at,outbox_id LIMIT 100",
|
||||
(now,),
|
||||
).fetchall()
|
||||
for row in rows:
|
||||
payload = json.loads(row["payload_json"])
|
||||
validate_metadata_only(payload)
|
||||
try:
|
||||
sender(payload)
|
||||
except Exception:
|
||||
attempts = row["attempts"] + 1
|
||||
status = "DEAD_LETTER" if attempts >= max_attempts else "PENDING"
|
||||
delay = min(300, 2 ** min(attempts, 8))
|
||||
self.db.execute(
|
||||
"UPDATE outbox SET attempts=?,status=?,next_attempt=? WHERE outbox_id=?",
|
||||
(attempts, status, now + delay, row["outbox_id"]),
|
||||
)
|
||||
failed += 1
|
||||
else:
|
||||
self.db.execute(
|
||||
"UPDATE outbox SET attempts=attempts+1,status='SENT',next_attempt=? WHERE outbox_id=?",
|
||||
(now, row["outbox_id"]),
|
||||
)
|
||||
sent += 1
|
||||
return sent, failed
|
||||
|
||||
def observe_ref(self, ref_name: str, oid: str) -> bool:
|
||||
row = self.db.execute("SELECT oid FROM observed_refs WHERE ref_name=?", (ref_name,)).fetchone()
|
||||
changed = row is not None and row["oid"] != oid
|
||||
self.db.execute(
|
||||
"INSERT INTO observed_refs VALUES(?,?,?) ON CONFLICT(ref_name) DO UPDATE SET oid=excluded.oid,updated_at=excluded.updated_at",
|
||||
(ref_name, oid, time.time()),
|
||||
)
|
||||
return changed
|
||||
|
||||
|
||||
def spool_after_http_failure(
|
||||
sender: Callable[[Mapping[str, Any]], None],
|
||||
payload: Mapping[str, Any],
|
||||
spool_dir: Path,
|
||||
event_id: str,
|
||||
) -> bool:
|
||||
validate_metadata_only(payload)
|
||||
try:
|
||||
sender(payload)
|
||||
return True
|
||||
except Exception:
|
||||
atomic_json_write(spool_dir / f"{event_id}.json", {"event_id": event_id, "payload": dict(payload)})
|
||||
return False
|
||||
|
||||
|
||||
def poll_file_inbox(store: QuorumStore, inbox_dir: Path) -> int:
|
||||
if not inbox_dir.exists():
|
||||
return 0
|
||||
validate_secure_directory(inbox_dir, expected_uid=os.geteuid() if os.name == "posix" else None)
|
||||
count = 0
|
||||
for path in sorted(inbox_dir.glob("*.json")):
|
||||
if path.is_symlink():
|
||||
raise ControllerError(f"symlink inbox entry rejected: {path}")
|
||||
item = read_secure_json(path, expected_uid=os.geteuid() if os.name == "posix" else None)
|
||||
event_id = item.get("event_id")
|
||||
payload = item.get("payload")
|
||||
if not isinstance(event_id, str) or not isinstance(payload, dict):
|
||||
raise ControllerError(f"invalid inbox envelope: {path}")
|
||||
if store.ingest_event(event_id, payload, "file-inbox"):
|
||||
count += 1
|
||||
path.unlink()
|
||||
return count
|
||||
|
||||
|
||||
def resolve_git_ref(repo: Path, ref_name: str) -> str:
|
||||
if not repo.is_absolute():
|
||||
raise ControllerError("Git repository path must be absolute")
|
||||
info = repo.lstat()
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISDIR(info.st_mode):
|
||||
raise ControllerError("Git repository must be a non-symlink directory")
|
||||
if os.name == "posix" and repo.resolve(strict=True) != Path(os.path.abspath(repo)):
|
||||
raise ControllerError("Git repository has a symlinked path component")
|
||||
if os.name == "posix" and info.st_mode & 0o002:
|
||||
raise ControllerError("world-writable Git repository rejected")
|
||||
try:
|
||||
completed = subprocess.run(
|
||||
[
|
||||
"git",
|
||||
"-c",
|
||||
f"safe.directory={repo}",
|
||||
"-C",
|
||||
str(repo),
|
||||
"rev-parse",
|
||||
"--verify",
|
||||
ref_name,
|
||||
],
|
||||
check=True,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.DEVNULL,
|
||||
text=True,
|
||||
timeout=10,
|
||||
)
|
||||
except (OSError, subprocess.CalledProcessError, subprocess.TimeoutExpired) as exc:
|
||||
raise ControllerError("Git ref unavailable") from exc
|
||||
oid = completed.stdout.strip()
|
||||
if len(oid) != 40 or any(character not in "0123456789abcdef" for character in oid.lower()):
|
||||
raise ControllerError("invalid Git object id")
|
||||
return oid
|
||||
|
||||
|
||||
def poll_git_refs(
|
||||
store: QuorumStore,
|
||||
repo: Path,
|
||||
refs: Iterable[str],
|
||||
resolver: Callable[[Path, str], str] = resolve_git_ref,
|
||||
) -> int:
|
||||
changed = 0
|
||||
for ref_name in refs:
|
||||
if not ref_name.startswith("refs/") or ".." in ref_name or ref_name.endswith("/"):
|
||||
raise ControllerError(f"invalid Git ref: {ref_name}")
|
||||
oid = resolver(repo, ref_name)
|
||||
if store.observe_ref(ref_name, oid):
|
||||
event_id = f"gitref:{ref_name}:{oid}"
|
||||
if store.ingest_event(event_id, {"ref": ref_name, "oid": oid}, "git-ref-poll"):
|
||||
changed += 1
|
||||
return changed
|
||||
|
||||
|
||||
def responses_fallback_allowed(
|
||||
workspace_agent_ok: bool,
|
||||
receipt: Mapping[str, Any],
|
||||
*,
|
||||
now: float | None = None,
|
||||
) -> bool:
|
||||
validate_metadata_only(receipt)
|
||||
if workspace_agent_ok:
|
||||
return False
|
||||
responses = receipt.get("responses_api")
|
||||
return (
|
||||
validate_health_receipt(receipt, "central_gpt", now=now) is Health.HEALTHY
|
||||
and isinstance(responses, Mapping)
|
||||
and responses.get("validated_live") is True
|
||||
)
|
||||
|
||||
|
||||
def _validate_gateway_url(url: str) -> None:
|
||||
parsed = urllib.parse.urlparse(url)
|
||||
if (
|
||||
parsed.scheme != "http"
|
||||
or parsed.hostname != "127.0.0.1"
|
||||
or parsed.port != 18920
|
||||
or parsed.path != "/v1/orchestrator/events"
|
||||
or parsed.params
|
||||
or parsed.query
|
||||
or parsed.fragment
|
||||
):
|
||||
raise ControllerError("gateway endpoint must be the fixed loopback endpoint")
|
||||
|
||||
|
||||
def get_gateway_state(url: str, project_key: str, token: str, timeout: float = 5.0) -> int:
|
||||
_validate_gateway_url(url)
|
||||
state_url = url.removesuffix("/events") + "/state/" + urllib.parse.quote(project_key, safe="")
|
||||
request = urllib.request.Request(
|
||||
state_url,
|
||||
headers={"Authorization": f"Bearer {token}"},
|
||||
method="GET",
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=timeout) as response:
|
||||
payload = json.loads(response.read(262_145))
|
||||
except urllib.error.HTTPError as exc:
|
||||
if exc.code == 404:
|
||||
return 0
|
||||
raise ControllerError(f"gateway state rejected HTTP {exc.code}") from exc
|
||||
except (urllib.error.URLError, TimeoutError, json.JSONDecodeError) as exc:
|
||||
raise ControllerError("gateway state unavailable") from exc
|
||||
version = payload.get("state_version") if isinstance(payload, Mapping) else None
|
||||
if not isinstance(version, int) or version < 0:
|
||||
raise ControllerError("gateway state version invalid")
|
||||
return version
|
||||
|
||||
|
||||
def post_json(url: str, payload: Mapping[str, Any], token: str, timeout: float = 5.0) -> None:
|
||||
validate_metadata_only(payload)
|
||||
_validate_gateway_url(url)
|
||||
request = urllib.request.Request(
|
||||
url,
|
||||
data=canonical_json(payload).encode("utf-8"),
|
||||
headers={"Content-Type": "application/json", "Authorization": f"Bearer {token}"},
|
||||
method="POST",
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=timeout) as response:
|
||||
if response.status < 200 or response.status >= 300:
|
||||
raise ControllerError(f"gateway rejected HTTP {response.status}")
|
||||
except urllib.error.HTTPError as exc:
|
||||
raise ControllerError(f"gateway rejected HTTP {exc.code}") from exc
|
||||
except (urllib.error.URLError, TimeoutError) as exc:
|
||||
raise ControllerError("gateway unavailable") from exc
|
||||
|
||||
|
||||
def run_once(config_path: Path) -> int:
|
||||
config = read_secure_json(config_path, expected_uid=0 if os.name == "posix" else None)
|
||||
gateway_url = config["gateway_event_url"]
|
||||
token = read_gateway_token(Path(config["gateway_token_file"]))
|
||||
state_version = get_gateway_state(gateway_url, config["project_key"], token)
|
||||
store = QuorumStore(Path(config["database_path"]))
|
||||
try:
|
||||
receipts: dict[str, Health] = {}
|
||||
for subject in ("central_gpt", "openclaw", "codex"):
|
||||
receipt_path = Path(config["health_receipts"][subject])
|
||||
try:
|
||||
receipt = read_secure_json(receipt_path, expected_uid=0 if os.name == "posix" else None)
|
||||
receipts[subject] = validate_health_receipt(
|
||||
receipt,
|
||||
subject,
|
||||
max_age_seconds=int(config.get("max_health_age_seconds", 60)),
|
||||
)
|
||||
except (FileNotFoundError, ControllerError, json.JSONDecodeError):
|
||||
receipts[subject] = Health.UNKNOWN
|
||||
decision = evaluate_quorum(
|
||||
receipts["central_gpt"], receipts["openclaw"], receipts["codex"], config.get("default_workload", "large_repetitive_infrastructure_monitoring")
|
||||
)
|
||||
quorum_event_id = f"quorum-{time.time_ns()}"
|
||||
store.enqueue(
|
||||
quorum_event_id,
|
||||
"gateway",
|
||||
{
|
||||
"schema_version": 1,
|
||||
"project_key": config["project_key"],
|
||||
"contract_commit": config["contract_commit"],
|
||||
"event_id": quorum_event_id,
|
||||
"source_agent": "system",
|
||||
"event_type": "executor_quorum_evaluated",
|
||||
"work_unit_id": "A0-AUTOMATION-QUORUM",
|
||||
"status": "READY" if decision.allowed else "BLOCKED",
|
||||
"state_version": state_version,
|
||||
"implementation_commit": None,
|
||||
"result_commit": None,
|
||||
"blocker": None if decision.allowed else decision.status,
|
||||
"evidence_refs": [],
|
||||
"payload": {
|
||||
"allowed": decision.allowed,
|
||||
"priority": decision.priority,
|
||||
"quorum_status": decision.status,
|
||||
"active_executor": decision.active_executor,
|
||||
"standby_executor": decision.standby_executor,
|
||||
},
|
||||
},
|
||||
)
|
||||
poll_file_inbox(store, Path(config["file_inbox_path"]))
|
||||
git_polling = config.get("git_ref_polling")
|
||||
if isinstance(git_polling, Mapping):
|
||||
poll_git_refs(store, Path(git_polling["repository"]), git_polling["refs"])
|
||||
store.deliver_outbox(
|
||||
lambda payload: post_json(gateway_url, payload, token),
|
||||
max_attempts=int(config["blocker_retry_threshold"]),
|
||||
)
|
||||
return 0 if decision.allowed else 2
|
||||
finally:
|
||||
store.close()
|
||||
|
||||
|
||||
def build_parser() -> argparse.ArgumentParser:
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("--config", type=Path, required=True)
|
||||
parser.add_argument("--once", action="store_true", required=True)
|
||||
return parser
|
||||
|
||||
|
||||
def main(argv: Iterable[str] | None = None) -> int:
|
||||
args = build_parser().parse_args(argv)
|
||||
try:
|
||||
return run_once(args.config)
|
||||
except (ControllerError, KeyError, OSError, sqlite3.Error, json.JSONDecodeError) as error:
|
||||
print(f"automation-quorum-controller: fail-closed: {type(error).__name__}", file=os.sys.stderr)
|
||||
return 3
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -1,146 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Strict metadata-only helpers shared by root health probes."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import stat
|
||||
import tempfile
|
||||
from typing import Any
|
||||
import urllib.error
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
|
||||
|
||||
class ProbeError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def secure_regular(path: Path, *, max_mode: int, owners: set[int]) -> os.stat_result:
|
||||
if not path.is_absolute():
|
||||
raise ProbeError("path_not_absolute")
|
||||
info = path.lstat()
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISREG(info.st_mode):
|
||||
raise ProbeError("unsafe_file_type")
|
||||
if stat.S_IMODE(info.st_mode) & ~max_mode:
|
||||
raise ProbeError("unsafe_file_mode")
|
||||
if os.name == "posix" and info.st_uid not in owners:
|
||||
raise ProbeError("unsafe_file_owner")
|
||||
if os.name == "posix" and path.resolve(strict=True) != Path(os.path.abspath(path)):
|
||||
raise ProbeError("symlinked_path_component")
|
||||
return info
|
||||
|
||||
|
||||
def load_config(path: Path) -> dict[str, Any]:
|
||||
secure_regular(path, max_mode=0o600, owners={0})
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
if not isinstance(value, dict):
|
||||
raise ProbeError("config_not_object")
|
||||
return value
|
||||
|
||||
|
||||
def read_token(path: Path) -> str:
|
||||
info = secure_regular(path, max_mode=0o640, owners={0, os.geteuid()})
|
||||
if info.st_size <= 0 or info.st_size > 16_384:
|
||||
raise ProbeError("invalid_token_size")
|
||||
fd = os.open(path, os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0))
|
||||
try:
|
||||
opened = os.fstat(fd)
|
||||
if not stat.S_ISREG(opened.st_mode) or opened.st_ino != info.st_ino or opened.st_dev != info.st_dev:
|
||||
raise ProbeError("token_changed_during_validation")
|
||||
data = os.read(fd, 16_385)
|
||||
if os.read(fd, 1):
|
||||
raise ProbeError("invalid_token_size")
|
||||
finally:
|
||||
os.close(fd)
|
||||
if b"\n" in data or b"\r" in data:
|
||||
raise ProbeError("invalid_token_format")
|
||||
try:
|
||||
return data.decode("utf-8")
|
||||
except UnicodeDecodeError as exc:
|
||||
raise ProbeError("invalid_token_encoding") from exc
|
||||
|
||||
|
||||
def gateway_base(endpoint: str) -> str:
|
||||
parsed = urllib.parse.urlparse(endpoint)
|
||||
if (
|
||||
parsed.scheme != "http"
|
||||
or parsed.hostname != "127.0.0.1"
|
||||
or parsed.port != 18920
|
||||
or parsed.path != "/v1/orchestrator/events"
|
||||
or parsed.query
|
||||
or parsed.fragment
|
||||
):
|
||||
raise ProbeError("invalid_gateway_endpoint")
|
||||
return endpoint.removesuffix("/events")
|
||||
|
||||
|
||||
def request_json(
|
||||
url: str,
|
||||
token: str,
|
||||
*,
|
||||
method: str = "GET",
|
||||
payload: dict[str, Any] | None = None,
|
||||
timeout: float = 10.0,
|
||||
) -> tuple[int, dict[str, Any]]:
|
||||
data = None if payload is None else json.dumps(payload, sort_keys=True, separators=(",", ":")).encode()
|
||||
headers = {"Authorization": f"Bearer {token}"}
|
||||
if data is not None:
|
||||
headers["Content-Type"] = "application/json"
|
||||
request = urllib.request.Request(url, data=data, headers=headers, method=method)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=timeout) as response:
|
||||
body = json.loads(response.read(262_145))
|
||||
if not isinstance(body, dict):
|
||||
raise ProbeError("gateway_response_not_object")
|
||||
return response.status, body
|
||||
except urllib.error.HTTPError as exc:
|
||||
if exc.code in {401, 403, 409, 422}:
|
||||
raise ProbeError(f"gateway_fail_closed_{exc.code}") from exc
|
||||
raise ProbeError(f"gateway_http_{exc.code}") from exc
|
||||
except (urllib.error.URLError, TimeoutError, json.JSONDecodeError) as exc:
|
||||
raise ProbeError("gateway_unavailable") from exc
|
||||
|
||||
|
||||
def state_version(endpoint: str, project_key: str, token: str) -> int:
|
||||
url = gateway_base(endpoint) + "/state/" + urllib.parse.quote(project_key, safe="")
|
||||
try:
|
||||
_, value = request_json(url, token)
|
||||
except ProbeError as exc:
|
||||
if str(exc) == "gateway_http_404":
|
||||
return 0
|
||||
raise
|
||||
version = value.get("state_version")
|
||||
if not isinstance(version, int) or version < 0:
|
||||
raise ProbeError("invalid_state_version")
|
||||
return version
|
||||
|
||||
|
||||
def atomic_receipt(path: Path, value: dict[str, Any]) -> None:
|
||||
if not path.is_absolute() or path.parent != Path("/run/aios-health"):
|
||||
raise ProbeError("invalid_receipt_path")
|
||||
parent = path.parent
|
||||
info = parent.lstat()
|
||||
if stat.S_ISLNK(info.st_mode) or not stat.S_ISDIR(info.st_mode):
|
||||
raise ProbeError("unsafe_receipt_directory")
|
||||
if os.name == "posix" and (info.st_uid != 0 or stat.S_IMODE(info.st_mode) != 0o750):
|
||||
raise ProbeError("unsafe_receipt_directory_metadata")
|
||||
fd, temporary = tempfile.mkstemp(prefix=f".{path.name}.", dir=parent)
|
||||
try:
|
||||
# Receipts contain availability metadata only. Give the dedicated
|
||||
# aios-quorum group read access so its unprivileged controller can
|
||||
# consume them, while retaining root ownership and no public access.
|
||||
if os.name == "posix":
|
||||
os.fchown(fd, 0, info.st_gid)
|
||||
os.fchmod(fd, 0o640)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as handle:
|
||||
json.dump(value, handle, sort_keys=True, separators=(",", ":"))
|
||||
handle.write("\n")
|
||||
handle.flush()
|
||||
os.fsync(handle.fileno())
|
||||
os.replace(temporary, path)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
+24
-12
@@ -1,13 +1,25 @@
|
||||
{
|
||||
"current_baseline": "V1R4C6",
|
||||
"previous_baseline": "V1R4C5",
|
||||
"promoted_at": "2026-07-11T21:00:00+08:00",
|
||||
"git": "e204a90398bf646d46245b3088226749fa056edd",
|
||||
"promoted_by": "openclaw/admin",
|
||||
"promotion_reason": "V1R4C6 admin search agent integration, search gateway, agent platform, VERSION bump, merge tests deploy pipeline — not yet deployed to production",
|
||||
"constraints": {
|
||||
"memory_search_enabled": false,
|
||||
"force_push_allowed": false,
|
||||
"gitea_db_mutation_requires_owner_approval": true
|
||||
}
|
||||
}
|
||||
"current_baseline": "V2R1C2",
|
||||
"previous_baseline": "V2R1C1",
|
||||
"promoted_at": "2026-07-22T01:40:51Z",
|
||||
"git": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
|
||||
"promoted_by": "codex/owner-approved-gitops",
|
||||
"promotion_reason": "Owner-authorized V2R1C2 Unified Portal production release after exact tag binding, complete evidence verification, and production acceptance PASS.",
|
||||
"version": "V2R1C2",
|
||||
"release_oid": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
|
||||
"tag_oid": "a3bd84ebec9c705f7c9c5c03f7f4ec55f8854e36",
|
||||
"target_oid": "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24",
|
||||
"release_run_id": "AIOS-V2R1C2-PRODUCTION-20260722T011836Z",
|
||||
"status": "PRODUCTION_DEPLOYED",
|
||||
"production_service": "aios-v2r1c2-production.service",
|
||||
"production_port": 18920,
|
||||
"rollback_version": "V2R1C1",
|
||||
"constraints": {
|
||||
"product_code_changed": true,
|
||||
"production_redeployed": true,
|
||||
"production_traffic_changed": true,
|
||||
"tag_rewritten": false,
|
||||
"force_push_allowed": false,
|
||||
"rollback_assets_preserved": true
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,24 +0,0 @@
|
||||
{
|
||||
"$schema": "../schemas/automation-quorum-controller.schema.json",
|
||||
"project_key": "v2r1-personal-weixin-production",
|
||||
"contract_commit": "cbe33ecab8e9794ba5f318bea43aeaf447a56fbc",
|
||||
"database_path": "/var/lib/aios-automation-quorum/controller.sqlite3",
|
||||
"file_inbox_path": "/var/lib/aios-automation-quorum/inbox",
|
||||
"default_workload": "large_repetitive_infrastructure_monitoring",
|
||||
"health_receipts": {
|
||||
"central_gpt": "/run/aios-health/central-gpt.json",
|
||||
"openclaw": "/run/aios-health/openclaw.json",
|
||||
"codex": "/run/aios-health/codex.json"
|
||||
},
|
||||
"git_ref_polling": {
|
||||
"repository": "/data/aios-gitops/repo.git",
|
||||
"refs": [
|
||||
"refs/heads/task/governance/v2r1-personal-weixin-production-contract-20260717"
|
||||
]
|
||||
},
|
||||
"blocker_retry_threshold": 3,
|
||||
"max_health_age_seconds": 60,
|
||||
"lease_ttl_seconds": 120,
|
||||
"gateway_event_url": "http://127.0.0.1:18920/v1/orchestrator/events",
|
||||
"gateway_token_file": "/etc/aios-orchestrator-gateway/inbound.token"
|
||||
}
|
||||
@@ -1,17 +0,0 @@
|
||||
{
|
||||
"active_dir": "/data/aios-gitops/workspace/agents/commands/active",
|
||||
"completed_dir": "/data/aios-gitops/workspace/agents/commands/completed",
|
||||
"dead_letter_dir": "/data/aios-gitops/workspace/agents/commands/dead-letter",
|
||||
"database_path": "/var/lib/aios-codex-watcher/state.sqlite3",
|
||||
"audit_log_path": "/var/log/aios-codex-watcher/audit.jsonl",
|
||||
"gateway_endpoint": "http://127.0.0.1:18920/v1/orchestrator/events",
|
||||
"gateway_token_file": "/etc/aios-orchestrator-gateway/inbound.token",
|
||||
"contract_commit": "cbe33ecab8e9794ba5f318bea43aeaf447a56fbc",
|
||||
"lease_seconds": 60,
|
||||
"retry_seconds": 10,
|
||||
"max_attempts": 5,
|
||||
"poll_seconds": 5,
|
||||
"executor_path": null,
|
||||
"executor_args": [],
|
||||
"executor_timeout_seconds": 1800
|
||||
}
|
||||
@@ -1,17 +0,0 @@
|
||||
{
|
||||
"project_key": "v2r1-personal-weixin-production",
|
||||
"contract_commit": "cbe33ecab8e9794ba5f318bea43aeaf447a56fbc",
|
||||
"gateway_event_url": "http://127.0.0.1:18920/v1/orchestrator/events",
|
||||
"gateway_token_file": "/etc/aios-orchestrator-gateway/inbound.token",
|
||||
"gateway_database_path": "/var/lib/aios-orchestrator-gateway/state.sqlite3",
|
||||
"probe_clean_base_commit": "c3984ca2b4388875d2875b4fdfdf95a2984f6ab3",
|
||||
"central_receipt_path": "/run/aios-health/central-gpt.json",
|
||||
"codex_receipt_path": "/run/aios-health/codex.json",
|
||||
"codex_command_queue": "/data/aios-gitops/workspace/agents/commands/active",
|
||||
"codex_database_path": "/var/lib/aios-codex-watcher/state.sqlite3",
|
||||
"codex_audit_log": "/var/log/aios-codex-watcher/audit.jsonl",
|
||||
"central_timeout_seconds": 90,
|
||||
"codex_timeout_seconds": 90,
|
||||
"cycle_timeout_seconds": 180,
|
||||
"poll_interval_seconds": 1
|
||||
}
|
||||
@@ -1,49 +0,0 @@
|
||||
{
|
||||
"host": "127.0.0.1",
|
||||
"port": 18920,
|
||||
"database_path": "/var/lib/aios-orchestrator-gateway/state.sqlite3",
|
||||
"event_inbox_dir": "/var/lib/aios-orchestrator-gateway/inbox/events",
|
||||
"decision_inbox_dir": "/var/lib/aios-orchestrator-gateway/inbox/decisions",
|
||||
"dispatch_outbox_dir": "/var/lib/aios-orchestrator-gateway/outbox",
|
||||
"openclaw_sync_dir": "/var/lib/aios-orchestrator-gateway/openclaw-sync",
|
||||
"command_queue_dir": "/var/lib/aios-orchestrator-gateway/commands",
|
||||
"inbound_token_file": "/etc/aios-orchestrator-gateway/inbound.token",
|
||||
"callback_token_file": "/etc/aios-orchestrator-gateway/callback.token",
|
||||
"contract_commit": "cbe33ecab8e9794ba5f318bea43aeaf447a56fbc",
|
||||
"workspace_agent": {
|
||||
"trigger_id": "agtch_REPLACE_ME",
|
||||
"access_token_file": "/etc/aios-orchestrator-gateway/workspace-agent.token"
|
||||
},
|
||||
"responses_fallback": {
|
||||
"api_key_file": "/etc/aios-orchestrator-gateway/openai-api.key",
|
||||
"model": "REPLACE_WITH_APPROVED_MODEL"
|
||||
},
|
||||
"polling": {
|
||||
"interval_seconds": 10,
|
||||
"summary_interval_seconds": 300
|
||||
},
|
||||
"loop_controls": {
|
||||
"callback_timeout_seconds": 900,
|
||||
"lease_seconds": 60,
|
||||
"retry_base_seconds": 10,
|
||||
"max_retries": 5,
|
||||
"max_same_blocker_retries": 3,
|
||||
"max_hops_per_gate": 20
|
||||
},
|
||||
"openclaw_sync": {
|
||||
"endpoint": null,
|
||||
"token_file": null
|
||||
},
|
||||
"project_key": "v2r1-personal-weixin-production",
|
||||
"git_poll": {
|
||||
"enabled": true,
|
||||
"bare_repo": "/data/aios-gitops/repo.git",
|
||||
"ref_prefixes": [
|
||||
"refs/heads/main",
|
||||
"refs/heads/task/governance/",
|
||||
"refs/heads/patch/",
|
||||
"refs/heads/result/"
|
||||
],
|
||||
"interval_seconds": 30
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,103 @@
|
||||
{
|
||||
"schema_version": 4,
|
||||
"automatic": [
|
||||
"build",
|
||||
"test",
|
||||
"artifact",
|
||||
"canary",
|
||||
"evidence"
|
||||
],
|
||||
"owner": [
|
||||
"signed_release_plan"
|
||||
],
|
||||
"forbidden": [
|
||||
"force_push",
|
||||
"tag_rewrite",
|
||||
"direct_main_push",
|
||||
"baseline_mutation",
|
||||
"registry_mutation"
|
||||
],
|
||||
"runtime_deployment": {
|
||||
"approval_action": "signed_release_plan",
|
||||
"required_capability": "runtime_switch",
|
||||
"tag_operations_allowed": false,
|
||||
"baseline_mutation_allowed": false,
|
||||
"registry_mutation_allowed": false,
|
||||
"writer_default": false,
|
||||
"rollback_required": true
|
||||
},
|
||||
"tag_release": {
|
||||
"approval_action": "signed_release_plan",
|
||||
"required_capability": "tag_publish",
|
||||
"separate_controller": true,
|
||||
"duplicate_conflict": "fail_closed",
|
||||
"rewrite_allowed": false,
|
||||
"force_push_allowed": false
|
||||
},
|
||||
"baseline_registry_finalize": {
|
||||
"approval_action": "signed_release_plan",
|
||||
"required_capability": "baseline_registry_finalize",
|
||||
"separate_controller": true,
|
||||
"remote_tag_verification_required": true,
|
||||
"gitea_api_verification_required": true,
|
||||
"registry_baseline_consistency_required": true
|
||||
},
|
||||
"approval": {
|
||||
"algorithm": "Ed25519",
|
||||
"trust_domain": "aios.production",
|
||||
"maximum_lifetime_seconds": 3600,
|
||||
"release_plan_sha256_required": true,
|
||||
"not_before_required": true,
|
||||
"replay_protection": true,
|
||||
"revocation_fail_closed": true,
|
||||
"key_rotation_supported": true,
|
||||
"capabilities": [
|
||||
"runtime_switch",
|
||||
"tag_publish",
|
||||
"baseline_registry_finalize"
|
||||
]
|
||||
},
|
||||
"execution": {
|
||||
"environment_variable": "AIOS_SILENT_RELEASE_EXECUTION_ENABLED",
|
||||
"default_enabled": false,
|
||||
"shadow_side_effects_allowed": false,
|
||||
"durable_saga_required": true,
|
||||
"pre_switch_revalidation_required": true,
|
||||
"trusted_candidate_builder_required": true,
|
||||
"actual_plan_regeneration_required": true,
|
||||
"startup_fail_closed_on_missing_component": true,
|
||||
"recovery_worker_shadow_default": true,
|
||||
"production_approval_backend_required": true,
|
||||
"production_builder_signer": "kms-hsm-secret-manager-only",
|
||||
"production_execution_without_backend": "unavailable"
|
||||
},
|
||||
"durability": {
|
||||
"journal": "sha256-hash-chain",
|
||||
"probe_journal": "sha256-hash-chain",
|
||||
"exclusive_capability_claims": true,
|
||||
"side_effect_probe_before_lease_takeover": true,
|
||||
"side_effect_probe_before_failed_recoverable_retry": true,
|
||||
"probe_results": [
|
||||
"NOT_APPLIED",
|
||||
"APPLIED_VERIFIED",
|
||||
"INDETERMINATE",
|
||||
"CONFLICT"
|
||||
],
|
||||
"probe_operation_digest_required": true,
|
||||
"probe_freshness_required": true,
|
||||
"tamper_result": "MANUAL_OWNER_REVIEW_REQUIRED"
|
||||
},
|
||||
"tag_pending": {
|
||||
"required_observations": [
|
||||
"remote_git_ref",
|
||||
"annotated_tag_object",
|
||||
"peeled_target",
|
||||
"gitea_api",
|
||||
"gitea_listing",
|
||||
"repository_identity"
|
||||
],
|
||||
"indeterminate_result": "RECONCILIATION_REQUIRED",
|
||||
"conflict_result": "MANUAL_OWNER_REVIEW_REQUIRED",
|
||||
"automatic_reconciliation": false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,59 @@
|
||||
version: 1
|
||||
policy_id: gitops-isolated-worktree-governance-20260714T232948UTC8
|
||||
|
||||
runtime_identity:
|
||||
user: aiman
|
||||
group: gitops
|
||||
umask: "0002"
|
||||
prohibit_root_workspace_writes: true
|
||||
|
||||
repository:
|
||||
source_worktree: /data/aios-gitops/workspace
|
||||
bare_repo: /data/aios-gitops/repo.git
|
||||
worktree_root: /data/aios-gitops/worktrees
|
||||
remote: origin
|
||||
|
||||
worktrees:
|
||||
controller: /data/aios-gitops/worktrees/controller
|
||||
task_pattern: /data/aios-gitops/worktrees/{agent}/{task_id}
|
||||
allowed_agents:
|
||||
- openclaw
|
||||
- chatgpt
|
||||
- controller
|
||||
require_clean_start: true
|
||||
remove_after_successful_push: true
|
||||
retain_on_failure: true
|
||||
|
||||
permissions:
|
||||
owner: aiman
|
||||
group: gitops
|
||||
directory_mode: "2775"
|
||||
file_mode: "0664"
|
||||
default_acl:
|
||||
user:aiman: rwx
|
||||
group:gitops: rwx
|
||||
apply_to:
|
||||
- /data/aios-gitops
|
||||
- /data/aios-gitops/worktrees
|
||||
|
||||
preflight:
|
||||
required_user: aiman
|
||||
required_group: gitops
|
||||
required_umask: "0002"
|
||||
require_writable_git_dir: true
|
||||
require_writable_task_dir: true
|
||||
require_writable_result_dir: true
|
||||
reject_shared_source_worktree: true
|
||||
reject_existing_git_lock: true
|
||||
|
||||
notifications:
|
||||
owner_on_received: required
|
||||
owner_on_terminal: required
|
||||
preferred_channel: weixin
|
||||
redact_secrets: true
|
||||
|
||||
rollback:
|
||||
preserve_source_worktree: true
|
||||
remove_created_worktrees: true
|
||||
restore_service_dropins: true
|
||||
restore_service_state: true
|
||||
@@ -0,0 +1,14 @@
|
||||
# Install as a systemd drop-in for GitOps/OpenClaw writer services.
|
||||
# Example: /etc/systemd/system/<service>.service.d/10-runtime-identity.conf
|
||||
|
||||
[Service]
|
||||
User=aiman
|
||||
Group=gitops
|
||||
SupplementaryGroups=gitops
|
||||
UMask=0002
|
||||
Environment=AIOS_GITOPS_ROOT=/data/aios-gitops
|
||||
Environment=AIOS_BARE_REPO=/data/aios-gitops/repo.git
|
||||
Environment=AIOS_WORKTREE_ROOT=/data/aios-gitops/worktrees
|
||||
Environment=AIOS_RUNTIME_USER=aiman
|
||||
Environment=AIOS_RUNTIME_GROUP=gitops
|
||||
Environment=AIOS_RUNTIME_UMASK=0002
|
||||
@@ -0,0 +1,27 @@
|
||||
# AIOS V2R1C2 Unified Portal production metadata.
|
||||
# No secret values belong in this file; runtime integrations use references.
|
||||
|
||||
AIOS_V2_HOST=127.0.0.1
|
||||
AIOS_V2_PORT=18920
|
||||
AIOS_V2_STATE_DIR=/var/lib/aios-v2r1c2-production
|
||||
AIOS_PROVENANCE_STORE_FILE=/var/lib/aios-v2r1c2-production/run-provenance.sqlite3
|
||||
AIOS_EXTERNAL_TASK_STORE_FILE=/var/lib/aios-v2r1c2-production/external-task-truth.sqlite3
|
||||
AIOS_EXECUTOR_CATALOG_FILE=/var/lib/aios-v2r1c2-production/executor-catalog.json
|
||||
AIOS_EXECUTION_PLAN_FILES=/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-RELEASE.json:/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-TAKEOVER.json
|
||||
AIOS_EXECUTION_PLAN_FILE=/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-TAKEOVER.json
|
||||
|
||||
AIOS_RELEASE_VERSION=V2R1C2
|
||||
AIOS_TARGET_VERSION=V2R1C2
|
||||
AIOS_BASELINE_VERSION=V2R1C1
|
||||
AIOS_PREVIOUS_VERSION=V2R1C1
|
||||
AIOS_RELEASE_STATUS=PRODUCTION
|
||||
AIOS_RELEASE_SOURCE_OID=3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24
|
||||
AIOS_RELEASE_OID=3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24
|
||||
AIOS_RELEASE_TAG=V2R1C2
|
||||
AIOS_RELEASE_EVIDENCE_SHA256=2e27bb73b8e6297bd3077238f73a96d697fc3c3611c601c4dc9357e5fdcd8eee
|
||||
|
||||
AIOS_OPENCLAW_CONTRACT_VERSION=aios.openclaw.command.v2
|
||||
AIOS_OPENCLAW_SIGNATURE_ALGORITHM=Ed25519
|
||||
AIOS_OPENCLAW_PLUGIN_VERSION=2.1.0-rc.4
|
||||
AIOS_OPENCLAW_SIGNING_KEY_ID=openclaw-v2r1-candidate-ed25519
|
||||
AIOS_OWNER_WECHAT_TARGET_REF=AIOS_OWNER_WECHAT_TARGET_REF
|
||||
@@ -0,0 +1,44 @@
|
||||
[Unit]
|
||||
Description=AIOS V2R1C2 Unified Portal Production
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
Conflicts=aios-orchestrator-gateway.service
|
||||
ConditionPathExists=/opt/aios-v2r1c2/active-runtime/app/aios_web/release_application.py
|
||||
ConditionPathExists=/opt/aios-v2r1c2/plans/AIOS-V2R1C2-UNIFIED-PORTAL-TAKEOVER.json
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios
|
||||
Group=aios
|
||||
WorkingDirectory=/opt/aios-v2r1c2/active-runtime/app
|
||||
EnvironmentFile=/etc/aios-v2/aios-v2r1c2-production.env
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
Environment=PYTHONDONTWRITEBYTECODE=1
|
||||
ExecStartPre=/usr/bin/test "$AIOS_V2_PORT" = "18920"
|
||||
ExecStartPre=/usr/bin/test "$AIOS_RELEASE_SOURCE_OID" = "3dd622b5a515f1fa4ef72b9f8ae9ce48ac703f24"
|
||||
ExecStartPre=/usr/bin/test "$AIOS_RELEASE_TAG" = "V2R1C2"
|
||||
ExecStart=/usr/bin/python3 -m aios_web.release_application
|
||||
Restart=on-failure
|
||||
RestartSec=3
|
||||
TimeoutStartSec=60
|
||||
TimeoutStopSec=30
|
||||
KillSignal=SIGTERM
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
LockPersonality=true
|
||||
MemoryDenyWriteExecute=true
|
||||
ReadWritePaths=/var/lib/aios-v2r1c2-production
|
||||
StateDirectory=aios-v2r1c2-production
|
||||
StateDirectoryMode=0750
|
||||
UMask=0027
|
||||
LimitNOFILE=65536
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,4 @@
|
||||
AIOS_V2_VERSION=V2R1C6
|
||||
AIOS_V2R1C6_PORT=18926
|
||||
AIOS_GITOPS_WRITES_ENABLED=false
|
||||
AIOS_V2R1C6_PRODUCTION_DEPLOYED=false
|
||||
@@ -0,0 +1,30 @@
|
||||
[Unit]
|
||||
Description=AIOS V2R1C6 candidate privacy service (not production-enabled)
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-v2r1c6
|
||||
Group=aios-v2r1c6
|
||||
WorkingDirectory=/opt/aios/v2r1c6
|
||||
EnvironmentFile=-/etc/aios/aios-v2r1c6.env
|
||||
Environment=AIOS_GITOPS_WRITES_ENABLED=false
|
||||
Environment=AIOS_V2R1C6_PRODUCTION_DEPLOYED=false
|
||||
ExecStart=/usr/bin/python3 /opt/aios/v2r1c6/active-runtime/app/v2r1c6_privacy_tools.py --serve --host 127.0.0.1 --port 18926
|
||||
Restart=on-failure
|
||||
RestartSec=5
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectHome=true
|
||||
ProtectSystem=strict
|
||||
ProtectKernelLogs=true
|
||||
ProtectKernelModules=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectControlGroups=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
|
||||
IPAddressDeny=any
|
||||
IPAddressAllow=localhost
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"schema": "aios.v2r1c6.candidate-rollback.v1",
|
||||
"candidate_version": "V2R1C6",
|
||||
"rollback_version": "V2R1C5",
|
||||
"previous_tag": "V2R1C5",
|
||||
"previous_tag_oid": "9e65bd59baea392294c0f253046d3ab116f63145",
|
||||
"previous_target_oid": "aa60e891547abd7e215af7cf2bf3f21fd23541da",
|
||||
"baseline_unchanged": true,
|
||||
"tag_rewrite": false,
|
||||
"force_push": false,
|
||||
"production_deploy_authorized": false,
|
||||
"rollback_steps": [
|
||||
"stop aios-v2r1c6-production.service if a separately approved deployment exists",
|
||||
"restore the V2R1C5 production artifact and service configuration",
|
||||
"verify V2R1C5 tag and Baseline before any restart"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,24 @@
|
||||
[Unit]
|
||||
Description=AIOS manifest-driven release controller (validation only)
|
||||
ConditionPathExists=/var/lib/aios-release/release-source-manifest.json
|
||||
ConditionPathExists=/var/lib/aios-release/release-request.json
|
||||
After=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
User=aios-release
|
||||
Group=aios-release
|
||||
Environment=PYTHONPATH=/opt/aios/release-controller
|
||||
Environment=AIOS_GITOPS_WRITES_ENABLED=false
|
||||
Environment=AIOS_PRODUCTION_DEPLOYMENT_AUTHORIZED=false
|
||||
ExecStart=/usr/bin/python3 -m aios_release_controller.cli validate-release /var/lib/aios-release/release-source-manifest.json /var/lib/aios-release/release-request.json
|
||||
NoNewPrivileges=yes
|
||||
PrivateTmp=yes
|
||||
ProtectSystem=strict
|
||||
ProtectHome=yes
|
||||
ReadWritePaths=/var/lib/aios-release
|
||||
CapabilityBoundingSet=
|
||||
RestrictAddressFamilies=AF_UNIX
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user