Compare commits

..
Author SHA1 Message Date
Codex da776bad52 docs: record personal weixin foundation retry9 owner gate failure 2026-07-16 01:29:02 +08:00
chatgpt-gitops-bot d5b51e1342 chore(gitops): bootstrap owner-approved B6/B7 implementation branch 2026-07-15 11:53:10 +08:00
OpenClaw Design d74229927b docs(v2r1): define personal Weixin golden contract 2026-07-15 07:27:10 +08:00
openclaw 68d2787910 feat(v2r1): package canonical authenticated ingress 2026-07-15 04:59:10 +08:00
openclaw 57103c11d2 test(openclaw): make tenant-boundary hook compatibility executable 2026-07-15 04:25:04 +08:00
openclaw a9a0b4ae39 docs(v2r1): expand B2 executable runtime matrix 2026-07-15 04:21:19 +08:00
openclaw 60ae6db60c fix(notify): terminate descendants and reject encoded traversal 2026-07-14 06:48:54 +08:00
openclaw e2d0c6aaf3 fix(notify): fail closed on ambiguous delivery 2026-07-14 06:37:17 +08:00
openclaw c21a326e81 fix(notify): restore hardened WeChat send backend 2026-07-14 06:17:54 +08:00
openclaw 14b03fc893 docs(v2r1): isolate gateway receipt journals 2026-07-14 04:45:31 +08:00
openclaw 04100a1aae docs(v2r1): finalize executable release contracts 2026-07-14 04:36:13 +08:00
openclaw e13f601cff docs(v2r1): make blocker gates executable 2026-07-14 04:18:06 +08:00
openclaw 1e7d1969cd docs(v2r1): close runtime bridge review gaps 2026-07-14 04:02:35 +08:00
openclaw d2a3814a2f docs(v2r1): define authenticated runtime release design 2026-07-14 03:16:08 +08:00
openclaw c444622279 integrate(v2r1): replay verified runtime tree 2026-07-14 03:02:17 +08:00
151 changed files with 8430 additions and 6152 deletions
@@ -1,32 +0,0 @@
{
"contract_commit": "cbe33ecab8e9794ba5f318bea43aeaf447a56fbc",
"created_at": "2026-07-17T14:13:38+00:00",
"schema_version": 1,
"state_writer": "openclaw",
"work_units": [
{
"fallback": "codex",
"gate": "R0_RUNNER_LIVE_RECOVERY",
"id": "R0-DISCOVER-SECRET-PROVIDER",
"primary": "openclaw",
"status": "READY",
"track": "R_RUNNER"
},
{
"fallback": "codex",
"gate": "P2_REAL_B3_EVIDENCE",
"id": "P2-INVENTORY-REAL-EVIDENCE",
"primary": "openclaw",
"status": "READY",
"track": "P_PERSONAL_WEIXIN"
},
{
"fallback": "openclaw",
"gate": "P1_REPAIR3_CODE",
"id": "P1-POST-CONTRACT-REACK",
"primary": "codex",
"status": "READY",
"track": "P_PERSONAL_WEIXIN"
}
]
}
@@ -1,157 +0,0 @@
{
"adaptive_dispatch": {
"codex_first": [
"complex_code",
"security_boundary",
"architecture",
"high_risk_review",
"strong_model_materially_better"
],
"default_orchestrator": "openclaw",
"dual_required": [
"release_gate",
"crypto_or_identity_change",
"production_migration_or_rollback"
],
"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,
"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"
}
},
"contract_id": "V2R1-PERSONAL-WEIXIN-PRODUCTION-EXECUTION-CONTRACT",
"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": "2026-07-17T14:13:38+00:00",
"handoff": {
"ack": "CONTRACT_ACK=<full_contract_commit_oid>",
"advance": "independent_verification_required",
"all_agents_match": true
},
"join_gate": {
"requires": [
"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": [
"MAIN_MERGE",
"STAGING_AND_CANARY",
"PRODUCTION"
],
"schema_version": 3,
"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"
],
"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"
]
}
}
}
@@ -1,55 +0,0 @@
---
contract: cbe33ecab8e9794ba5f318bea43aeaf447a56fbc
work_unit: A0-CODEX-AUTOMATION-CLOSURE
status: PASS
base_oid: 9195470ceb78fd57ffface3dcc38f40b75efa9d8
baseline_remediation_commit: 378cc4d56ab58dde7da8814846ffd64a979b23f6
orchestrator_implementation_oid: 95fc4d37f0b9502945e5ba97a1f8e5a146768f6b
integration_merge_commit: 1b3b74fd626028ae5d5f11ae6933953fecf57df5
implementation_commit: c3984ca2b4388875d2875b4fdfdf95a2984f6ab3
full_unittest: PASS_78
full_pytest: PASS_154_PLUS_34_SUBTESTS
python_compile: PASS
bash_syntax: PASS
json_schema_openapi: PASS
systemd_verify: PASS
gitleaks_final_tree: PASS
gitleaks_head_history: PASS_297_COMMITS
gitleaks_implementation_range: PASS
codex_auto_claim: PASS
worktree_oid: c3984ca2b4388875d2875b4fdfdf95a2984f6ab3
bare_oid: c3984ca2b4388875d2875b4fdfdf95a2984f6ab3
gitea_oid: c3984ca2b4388875d2875b4fdfdf95a2984f6ab3
all_equal: true
---
# A0 Codex automation closure result
## A0-C1 baseline remediation
Lineage showed that `tests/test_wechat_send_backend.py` entered the authoritative ancestry without its source, while no source-deletion commit existed. The approved hardened source/test blobs were restored through their direct lineage. Relevant unittest and pytest each passed 26 tests; the remediation commit was pushed with equal worktree, bare, and Gitea OIDs.
## A0-C2 Gateway integration
The remediation commit and Gateway implementation were combined by a normal two-parent merge. Gateway tests passed, as did the repository suites and the compile, Bash, JSON/schema, OpenAPI, systemd, diff, rollback, and Gitleaks gates.
## A0-C3 persistent Codex watcher
The watcher is installed as a five-second systemd timer under `aios-orchestrator`. It uses a SQLite unique `work_unit_id`, optimistic atomic leases, stale-lease recovery, phase persistence, bounded retries, dead-letter handling, exact contract rejection, durable idempotent lifecycle events, sanitized executor environment, secure no-follow file reads, and a loopback-only Gateway endpoint. External execution is at-most-once: an ambiguous post-launch crash is not replayed.
The first installer run failed closed because systemd-tmpfiles rejected an ownership transition into the Gateway command tree. No task ran. The append-only repair limited tmpfiles to watcher-owned `/var` paths and validated the existing command-tree owner and modes before creating only the absent dead-letter directory.
The harmless live command was created in the production queue and claimed by the timer without manually starting the service. Watcher SQLite recorded `COMPLETED`, `DONE`, `attempts=1`; Gateway SQLite contained exact matching `work_unit_started` and `work_unit_ended` event JSON. The audit chain was:
```text
COMMAND_CREATED
-> CODEX_AUTO_CLAIM
-> TASK_STARTED
-> TASK_EXECUTED
-> TASK_ENDED
-> EVENT_POSTED
```
The acceptance result retained only an input SHA-256 and exit code. A second live command with a wrong contract OID was moved to dead-letter, created no watcher command row, and posted no Gateway event. Journal scanning found no bearer token, API key, or secret pattern. The superseded broken watcher was disabled; the new timer is enabled and active.
The full all-ref Gitleaks diagnostic found four pre-existing findings only on unrelated refs (three governance/result documents, outside this ancestry). They were not treated as evidence for this work unit. The final tree, the complete `HEAD` ancestry, and the implementation range contained zero findings.
@@ -0,0 +1,102 @@
status: FAIL
previous_result_commit: 4f2aa830027ab71cc292fc338dd0184212565005
owner_bundle_source: C:/Users/ImRuY/Downloads/pwx_retry9_owner_bundle.tar.gz
owner_bundle_sha256: 1864104c61d3078f53ca0f6d5712f06984086ab0105a73f1e5da11283fe8ad16
owner_materializer_sha256: NOT_RUN
owner_context_script_sha256: NOT_RUN
archive_transfer: PASS
archive_sha256_gate: PASS
archive_member_safety: NOT_RUN
archive_member_diff_exit: 1
archive_member_diff: |
Literal owner commands require `tar -tzf ... | sort > actual`, while the supplied
expected heredoc places `SHA256SUMS.pwx_retry9` first. The sorted actual list places
it last. `diff -u /tmp/pwx-retry9-expected-members.txt /tmp/pwx-retry9-actual-members.txt`
exited 1 before extraction:
--- expected
+++ actual
@@ -1,4 +1,3 @@
-SHA256SUMS.pwx_retry9
portal/Dockerfile
portal/requirements.txt
pwx_retry5_finalize_image_contract.py
@@ -6,3 +5,4 @@
pwx_retry8_apply_offline_contract.sh
pwx_retry9_materialize_offline_wheelhouse.py
pwx_retry9_prepare_image_context.sh
+SHA256SUMS.pwx_retry9
literal_expected_members:
- SHA256SUMS.pwx_retry9
- portal/Dockerfile
- portal/requirements.txt
- pwx_retry5_finalize_image_contract.py
- pwx_retry5_local_image_build.sh
- pwx_retry8_apply_offline_contract.sh
- pwx_retry9_materialize_offline_wheelhouse.py
- pwx_retry9_prepare_image_context.sh
sorted_actual_members:
- portal/Dockerfile
- portal/requirements.txt
- pwx_retry5_finalize_image_contract.py
- pwx_retry5_local_image_build.sh
- pwx_retry8_apply_offline_contract.sh
- pwx_retry9_materialize_offline_wheelhouse.py
- pwx_retry9_prepare_image_context.sh
- SHA256SUMS.pwx_retry9
owner_files_extracted: false
owner_syntax_gate: NOT_RUN
record_path_policy_self_test: NOT_RUN
record_path_policy_manifest_gate: NOT_RUN
ignored_external_script_entries: NOT_RUN
ignored_external_bytecode_entries: NOT_RUN
unexpected_ignored_entries: NOT_RUN
trusted_portal_python: /tmp/pwx-foundation-retry3.91ecvh/venv/bin/python
trusted_django_version: 5.2.15
trusted_asgiref_version: 3.12.1
trusted_sqlparse_version: 0.5.5
trusted_dependency_version_gate: PASS
offline_wheelhouse: NOT_RUN
offline_wheelhouse_manifest_sha256: null
offline_wheel_files: []
offline_wheel_sha256: {}
dependency_network_used: false
implementation_branch: patch/v2r1-personal-weixin-foundation-codex-retry9-20260715T183951UTC8
implementation_commit: null
implementation_parent: d5b51e1342541bf51887782f530c3d2971155996
implementation_commits: 0
merge_commits: 0
runtime_wheel: NOT_RUN
fresh_venv_install: NOT_RUN
external_import: NOT_RUN
package_identity_tests: NOT_RUN
portal_check: NOT_RUN
migration_dry_run: NOT_RUN
temporary_migration_apply: NOT_RUN
model_security: NOT_RUN
repository_single_consume: NOT_RUN
repository_idempotency: NOT_RUN
repository_conflict_fail_closed: NOT_RUN
repository_concurrency_contract: NOT_RUN
local_base_digest_equivalence: NOT_RUN
build_engine: none
build_network: none
remote_resolution_attempted: false
image_build: NOT_RUN
container_offline_dependency_gate: NOT_RUN
container_non_root: NOT_RUN
runtime_uid: null
image_id: null
image_digest: null
image_digest_kind: null
image_contract: NOT_RUN
gitleaks: NOT_RUN
changed_paths_exact_18: NOT_RUN
worktree_artifact_pollution: NOT_RUN
worktree_clean: true
production_changed: false
baseline_after: V1R4C6
release_status: paused
b6_b7_started: false
canary_started: false
owner_action_required: Correct the Retry 9 archive expected-member contract so it compares against a sorted expected list, or remove sort from the literal actual-member command; do not normalize this contradiction autonomously.
next_gate: Re-run Retry 9 from bundle transfer after owner supplies a coherent literal archive member comparison contract.
@@ -1,15 +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,
"production_release": "NOT_STARTED",
"release": "paused",
"repair3": "PASS_CANDIDATE_PREPARED",
"runner": "BLOCKED_GATEWAY_SECRET_REF_UNAVAILABLE",
"schema_version": 1,
"single_state_writer": "openclaw",
"updated_at": "2026-07-17T14:13:38+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.
@@ -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.
@@ -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.
+4
View File
@@ -11,3 +11,7 @@ runtime/tmp/
runtime/cache/
logs/
config/test_write_perms
/data/webops.sqlite3
/data/webops.sqlite3-wal
/data/webops.sqlite3-shm
/data/webops.sqlite3-journal
-11
View File
@@ -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.
-107
View File
@@ -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`.
+3
View File
@@ -0,0 +1,3 @@
"""Canonical AIOS V2R1 runtime package."""
__version__ = "2.1.0-rc.1"
+119
View File
@@ -0,0 +1,119 @@
"""Append-only, tamper-evident audit chain for AIOS V2R1."""
from __future__ import annotations
from collections.abc import Callable
from contextlib import closing
import hashlib
import json
import os
from pathlib import Path
import sqlite3
from typing import Any, TypeVar
from .tenant_context import ConflictError, canonical_json, isoformat, require_ident
T = TypeVar("T")
class AuditLog:
def __init__(self, database: str | Path) -> None:
self.database = Path(database)
self.database.parent.mkdir(parents=True, exist_ok=True)
self._initialize()
os.chmod(self.database, 0o600)
def _connect(self) -> sqlite3.Connection:
db = sqlite3.connect(str(self.database), timeout=30)
db.execute("PRAGMA journal_mode=WAL")
db.execute("PRAGMA synchronous=FULL")
db.execute("PRAGMA busy_timeout=30000")
return db
def _storage(self, operation: Callable[[], T]) -> T:
failure: ConflictError | None = None
try:
return operation()
except sqlite3.Error:
failure = ConflictError("audit storage unavailable")
raise failure
def _initialize(self) -> None:
def initialize() -> None:
with closing(self._connect()) as connection, connection as db:
db.execute(
"""
CREATE TABLE IF NOT EXISTS audit_events (
seq INTEGER PRIMARY KEY AUTOINCREMENT,
tenant_id TEXT NOT NULL,
trace_id TEXT NOT NULL,
event_type TEXT NOT NULL,
payload TEXT NOT NULL,
previous_hash TEXT NOT NULL,
event_hash TEXT NOT NULL UNIQUE,
created_at TEXT NOT NULL
)
"""
)
self._storage(initialize)
def append(
self, *, tenant_id: str, trace_id: str, event_type: str,
payload: dict[str, Any],
) -> str:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
trace_id = require_ident("trace_id", trace_id)
event_type = require_ident("event_type", event_type)
def write() -> str:
with closing(self._connect()) as connection, connection as db:
db.execute("BEGIN IMMEDIATE")
previous = db.execute(
"SELECT event_hash FROM audit_events ORDER BY seq DESC LIMIT 1"
).fetchone()
previous_hash = previous[0] if previous else "GENESIS"
body = {
"tenant_id": tenant_id, "trace_id": trace_id,
"event_type": event_type, "payload": payload,
"previous_hash": previous_hash, "created_at": isoformat(),
}
digest = hashlib.sha256(canonical_json(body)).hexdigest()
db.execute(
"INSERT INTO audit_events VALUES(NULL,?,?,?,?,?,?,?)",
(
tenant_id, trace_id, event_type,
json.dumps(payload, ensure_ascii=False),
previous_hash, digest, body["created_at"],
),
)
db.commit()
return digest
return self._storage(write)
def verify(self) -> bool:
def check() -> bool:
previous = "GENESIS"
with closing(self._connect()) as connection, connection as db:
rows = db.execute(
"SELECT tenant_id,trace_id,event_type,payload,previous_hash,"
"event_hash,created_at FROM audit_events ORDER BY seq"
)
for row in rows:
try:
payload = json.loads(row[3])
except (json.JSONDecodeError, TypeError):
return False
body = {
"tenant_id": row[0], "trace_id": row[1],
"event_type": row[2], "payload": payload,
"previous_hash": row[4], "created_at": row[6],
}
if row[4] != previous:
return False
digest = hashlib.sha256(canonical_json(body)).hexdigest()
if digest != row[5]:
return False
previous = digest
return True
return self._storage(check)
@@ -0,0 +1,162 @@
"""AIOS V2R1 Tenant Cell lifecycle and atomic registry primitives."""
from __future__ import annotations
from contextlib import contextmanager
from dataclasses import dataclass
from datetime import datetime, timezone
import fcntl
import json
import os
from pathlib import Path
import tempfile
import threading
from typing import Iterator
from .tenant_context import ValidationError, require_ident
_THREAD_LOCKS_GUARD = threading.Lock()
_THREAD_LOCKS: dict[str, threading.RLock] = {}
_STATES = {"created", "starting", "healthy", "upgrading", "rollback", "failed"}
_TRANSITIONS = {
"created": {"starting", "failed"},
"starting": {"healthy", "failed"},
"healthy": {"upgrading", "failed"},
"upgrading": {"healthy", "rollback", "failed"},
"rollback": {"healthy", "failed"},
"failed": {"starting"},
}
def _lock_for(path: Path) -> threading.RLock:
key = str(path.resolve())
with _THREAD_LOCKS_GUARD:
return _THREAD_LOCKS.setdefault(key, threading.RLock())
@dataclass(frozen=True)
class CellRecord:
tenant_id: str
cell_id: str
version: str
state: str
config_digest: str
created_at: str
class CellManager:
def __init__(self, registry: str | Path) -> None:
self.registry = Path(registry)
self.registry.parent.mkdir(parents=True, exist_ok=True)
self._lock_file = self.registry.with_name(self.registry.name + ".lock")
self._thread_lock = _lock_for(self.registry)
with self._exclusive():
if not self.registry.exists():
self._save({"cells": {}})
else:
self._load()
@contextmanager
def _exclusive(self) -> Iterator[None]:
with self._thread_lock:
with self._lock_file.open("a+", encoding="utf-8") as lock:
os.chmod(self._lock_file, 0o600)
fcntl.flock(lock.fileno(), fcntl.LOCK_EX)
try:
yield
finally:
fcntl.flock(lock.fileno(), fcntl.LOCK_UN)
def _load(self) -> dict[str, dict[str, dict[str, str]]]:
failure: ValidationError | None = None
try:
value = json.loads(self.registry.read_text(encoding="utf-8"))
except (OSError, UnicodeError, json.JSONDecodeError):
failure = ValidationError("cell registry unavailable")
if failure is not None:
raise failure
if not isinstance(value, dict) or set(value) != {"cells"}:
raise ValidationError("cell registry unavailable")
cells = value["cells"]
if not isinstance(cells, dict):
raise ValidationError("cell registry unavailable")
expected = {
"tenant_id", "cell_id", "version", "state",
"config_digest", "created_at",
}
for tenant_id, item in cells.items():
if (
not isinstance(item, dict) or set(item) != expected
or item.get("tenant_id") != tenant_id
or item.get("state") not in _STATES
or any(not isinstance(item.get(name), str) for name in expected)
):
raise ValidationError("cell registry unavailable")
return value
def _save(self, value: dict[str, object]) -> None:
descriptor, temporary_name = tempfile.mkstemp(
prefix=f".{self.registry.name}.", dir=self.registry.parent, text=True
)
temporary = Path(temporary_name)
try:
with os.fdopen(descriptor, "w", encoding="utf-8") as output:
json.dump(value, output, ensure_ascii=False, indent=2)
output.write("\n")
output.flush()
os.fsync(output.fileno())
os.chmod(temporary, 0o600)
os.replace(temporary, self.registry)
directory = os.open(self.registry.parent, os.O_RDONLY | os.O_DIRECTORY)
try:
os.fsync(directory)
finally:
os.close(directory)
finally:
if temporary.exists():
temporary.unlink()
def create(
self, tenant_id: str, cell_id: str, version: str, digest: str,
) -> CellRecord:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
cell_id = require_ident("cell_id", cell_id)
version = require_ident("version", version)
digest = require_ident("digest", digest)
with self._exclusive():
data = self._load()
if tenant_id in data["cells"]:
raise ValidationError("tenant already has a cell")
record = CellRecord(
tenant_id, cell_id, version, "created", digest,
datetime.now(timezone.utc).isoformat(),
)
data["cells"][tenant_id] = record.__dict__
self._save(data)
return record
def status(self, tenant_id: str) -> CellRecord:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
with self._exclusive():
data = self._load()
item = data["cells"].get(tenant_id)
if not item:
raise ValidationError("unknown tenant")
return CellRecord(**item)
def transition(self, tenant_id: str, state: str) -> CellRecord:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
if state not in _STATES:
raise ValidationError("invalid cell state")
with self._exclusive():
data = self._load()
item = data["cells"].get(tenant_id)
if not item:
raise ValidationError("unknown tenant")
current = item["state"]
if state == current:
return CellRecord(**item)
if state not in _TRANSITIONS[current]:
raise ValidationError(f"invalid cell transition: {current}->{state}")
item["state"] = state
self._save(data)
return CellRecord(**item)
@@ -0,0 +1,64 @@
"""The only V2R1 ingress adapter: verified context to routed ledger record."""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime
from threading import RLock
from typing import Callable, Mapping, Any
from .message_ledger import LedgerRecord, MessageLedger
from .router import Route, TenantRouter
from .session_pool import SessionLease, SessionPool
from .tenant_context import CanonicalMessage, TenantContext, utc_now
@dataclass(frozen=True)
class IngressResult:
record: LedgerRecord
route: Route
session: SessionLease
class ChannelAdapter:
"""Fail-closed runtime ingress composition.
The adapter intentionally accepts no tenant or Cell authority outside the
signed context and TenantRouter. A process lock keeps rollback handling
deterministic for a single runtime while SQLite protects cross-process
ledger writes.
"""
def __init__(
self,
*,
router: TenantRouter,
ledger: MessageLedger,
session_pool: SessionPool,
signing_key: bytes,
clock: Callable[[], datetime] = utc_now,
) -> None:
self._router = router
self._ledger = ledger
self._session_pool = session_pool
self._signing_key = signing_key
self._clock = clock
self._lock = RLock()
def ingest(self, *, token: str, message: Mapping[str, Any]) -> IngressResult:
with self._lock:
context = TenantContext.verify(token, self._signing_key, now=self._clock())
canonical = CanonicalMessage.from_mapping(message)
canonical.assert_context(context)
route = self._router.assert_context_route(context)
self._router.assert_message_route(canonical)
self._session_pool.assert_available(context, route)
existed = self._ledger.matches(canonical)
record = self._ledger.append(canonical)
try:
lease = self._session_pool.acquire(context, route)
except Exception:
if not existed:
self._ledger.remove(record)
raise
return IngressResult(record=record, route=route, session=lease)
+81
View File
@@ -0,0 +1,81 @@
"""aios-cell command implementation for V2R1 Cell lifecycle."""
from __future__ import annotations
import argparse
import json
import sys
from .cell_manager import CellManager
from .ingress_service import serve
from .tenant_context import V2R1Error, ValidationError
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(prog="aios-cell")
parser.add_argument("registry")
sub = parser.add_subparsers(dest="command", required=True)
create = sub.add_parser("create")
create.add_argument("tenant_id")
create.add_argument("cell_id")
create.add_argument("version")
create.add_argument("digest")
status = sub.add_parser("status")
status.add_argument("tenant_id")
transition = sub.add_parser("transition")
transition.add_argument("tenant_id")
transition.add_argument("state")
return parser
def build_serve_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(prog="aios-cell serve")
parser.add_argument("--host", default="127.0.0.1")
parser.add_argument("--port", type=int, default=18792)
return parser
def _domain_failure(error: V2R1Error) -> int:
code = "VALIDATION_ERROR" if isinstance(error, ValidationError) else "RUNTIME_ERROR"
print(
json.dumps({"code": code, "error": str(error)}, ensure_ascii=False, sort_keys=True),
file=sys.stderr,
)
return 3
def main(argv: list[str] | None = None) -> int:
values = list(sys.argv[1:] if argv is None else argv)
service_mode = (
bool(values) and values[0] == "serve"
and (len(values) == 1 or values[1].startswith("-"))
)
if service_mode:
serve_args = build_serve_parser().parse_args(values[1:])
serve(serve_args.host, serve_args.port)
return 0
args = build_parser().parse_args(values)
try:
manager = CellManager(args.registry)
if args.command == "create":
result = manager.create(
args.tenant_id, args.cell_id, args.version, args.digest
)
elif args.command == "status":
result = manager.status(args.tenant_id)
elif args.command == "transition":
result = manager.transition(args.tenant_id, args.state)
else:
return 2
except V2R1Error as error:
return _domain_failure(error)
print(json.dumps(result.__dict__, ensure_ascii=False, sort_keys=True))
return 0
if __name__ == "__main__":
sys.exit(main())
+106
View File
@@ -0,0 +1,106 @@
"""OpenClaw Cell lifecycle adapter for AIOS V2R1."""
from __future__ import annotations
from dataclasses import asdict, dataclass, field
import json
from pathlib import Path
import subprocess
from typing import Any, Mapping
from .tenant_context import ValidationError, V2R1Error, require_ident
@dataclass(frozen=True)
class CellSpec:
tenant_id: str
image: str
runtime: str = "docker"
port: int | None = None
memory: str = "2g"
cpus: str = "2"
pids_limit: int = 512
network: str = "bridge"
env: tuple[str, ...] = field(default_factory=tuple)
def __post_init__(self) -> None:
require_ident("tenant_id", self.tenant_id, tenant=True)
if self.runtime not in {"docker", "podman"}:
raise ValidationError("unsupported runtime")
if not self.image:
raise ValidationError("image required")
class OpenClawFleet:
def __init__(self, binary: str = "openclaw") -> None:
self.binary = binary
def _run(self, args: list[str]) -> dict[str, Any]:
proc = subprocess.run(
[self.binary, *args],
check=False,
text=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
if proc.returncode:
raise V2R1Error(proc.stderr.strip() or "openclaw command failed")
data = json.loads(proc.stdout or "{}")
if isinstance(data, dict):
return data
return {"result": data}
def create(self, spec: CellSpec) -> dict[str, Any]:
return self._run([
"fleet", "create", spec.tenant_id,
"--image", spec.image,
"--runtime", spec.runtime,
"--json",
])
def status(self, tenant_id: str) -> dict[str, Any]:
require_ident("tenant_id", tenant_id, tenant=True)
return self._run(["fleet", "status", tenant_id, "--json"])
def doctor(self, tenant_id: str | None = None) -> dict[str, Any]:
args = ["fleet", "doctor"]
if tenant_id:
require_ident("tenant_id", tenant_id, tenant=True)
args.append(tenant_id)
args.append("--json")
return self._run(args)
def backup(self, tenant_id: str, output: str | Path) -> dict[str, Any]:
return self._run(["fleet", "backup", tenant_id, "--out", str(output), "--json"])
def restore(self, tenant_id: str, archive: str | Path) -> dict[str, Any]:
return self._run(["fleet", "restore", tenant_id, "--from", str(archive), "--json"])
def upgrade(self, tenant_id: str, image: str) -> dict[str, Any]:
return self._run(["fleet", "upgrade", tenant_id, "--image", image, "--json"])
def load_inventory(path: str | Path) -> list[CellSpec]:
raw = json.loads(Path(path).read_text(encoding="utf-8"))
if raw.get("schema_version") != "aios.cells.v1":
raise ValidationError("invalid inventory schema")
result: list[CellSpec] = []
seen: set[str] = set()
for item in raw.get("cells", []):
spec = CellSpec(
tenant_id=item["tenant_id"],
image=item["image"],
runtime=item.get("runtime", "docker"),
port=item.get("port"),
env=tuple(item.get("env", [])),
)
if spec.tenant_id in seen:
raise ValidationError("duplicate tenant")
seen.add(spec.tenant_id)
result.append(spec)
if not result:
raise ValidationError("no cells")
return result
def inventory_as_dict(items: list[CellSpec]) -> dict[str, Any]:
return {"schema_version": "aios.cells.v1", "cells": [asdict(x) for x in items]}
@@ -0,0 +1,164 @@
"""Tenant-partitioned Hermes shared agent fabric primitives."""
from __future__ import annotations
from collections.abc import Callable
from contextlib import closing
from dataclasses import dataclass
from datetime import datetime, timezone
import os
from pathlib import Path
import sqlite3
from typing import Any, TypeVar
from .tenant_context import (
CanonicalMessage, ConflictError, ScopeError, ValidationError,
isoformat, require_ident,
)
T = TypeVar("T")
@dataclass(frozen=True)
class FabricJob:
job_id: str
tenant_id: str
cell_id: str
profile_id: str
session_id: str
event_id: str
status: str = "queued"
def __post_init__(self) -> None:
for name in ("job_id", "cell_id", "profile_id", "session_id", "event_id"):
require_ident(name, getattr(self, name))
require_ident("tenant_id", self.tenant_id, tenant=True)
if self.status not in {"queued", "running", "completed", "failed", "cancelled"}:
raise ValidationError("invalid job status")
class HermesFabric:
"""Shared scheduler storage with mandatory tenant partition keys."""
def __init__(self, database: str | Path) -> None:
self.database = str(database)
Path(self.database).parent.mkdir(parents=True, exist_ok=True)
self._initialize()
os.chmod(self.database, 0o600)
def _connect(self) -> sqlite3.Connection:
db = sqlite3.connect(self.database, timeout=30)
db.execute("PRAGMA journal_mode=WAL")
db.execute("PRAGMA synchronous=FULL")
db.execute("PRAGMA busy_timeout=30000")
return db
def _storage(self, operation: Callable[[], T]) -> T:
failure: ConflictError | None = None
try:
return operation()
except sqlite3.Error:
failure = ConflictError("fabric storage unavailable")
raise failure
def _initialize(self) -> None:
def initialize() -> None:
with closing(self._connect()) as connection, connection as db:
db.execute(
"""
CREATE TABLE IF NOT EXISTS fabric_jobs (
job_id TEXT PRIMARY KEY,
tenant_id TEXT NOT NULL,
cell_id TEXT NOT NULL,
profile_id TEXT NOT NULL,
session_id TEXT NOT NULL,
event_id TEXT NOT NULL UNIQUE,
status TEXT NOT NULL,
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL
)
"""
)
db.execute(
"CREATE INDEX IF NOT EXISTS idx_fabric_tenant_queue "
"ON fabric_jobs(tenant_id, cell_id, status)"
)
self._storage(initialize)
def enqueue(
self, *, message: CanonicalMessage, profile_id: str,
) -> FabricJob:
profile_id = require_ident("profile_id", profile_id)
if not message.command_capable:
raise ScopeError("non-command events cannot create execution jobs")
if not message.is_authenticated_human_command:
raise ScopeError("only authenticated human commands can create jobs")
job = FabricJob(
job_id=f"job-{message.event_id}", tenant_id=message.tenant_id,
cell_id=message.cell_id, profile_id=profile_id,
session_id=message.session_id, event_id=message.event_id,
)
now = isoformat()
failure: ConflictError | None = None
try:
with closing(self._connect()) as connection, connection as db:
db.execute(
"INSERT INTO fabric_jobs VALUES(?,?,?,?,?,?,?,?,?)",
(
job.job_id, job.tenant_id, job.cell_id, job.profile_id,
job.session_id, job.event_id, job.status, now, now,
),
)
except sqlite3.IntegrityError:
failure = ConflictError(
"fabric event already exists or violates queue uniqueness"
)
except sqlite3.Error:
failure = ConflictError("fabric storage unavailable")
if failure is not None:
raise failure
return job
def claim(
self, tenant_id: str, cell_id: str, profile_id: str,
) -> FabricJob | None:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
cell_id = require_ident("cell_id", cell_id)
profile_id = require_ident("profile_id", profile_id)
def claim_one() -> FabricJob | None:
with closing(self._connect()) as connection, connection as db:
db.execute("BEGIN IMMEDIATE")
row = db.execute(
"SELECT * FROM fabric_jobs WHERE tenant_id=? AND cell_id=? "
"AND profile_id=? AND status='queued' ORDER BY created_at LIMIT 1",
(tenant_id, cell_id, profile_id),
).fetchone()
if not row:
db.commit()
return None
updated = db.execute(
"UPDATE fabric_jobs SET status='running', updated_at=? "
"WHERE job_id=? AND status='queued'",
(isoformat(), row[0]),
)
if updated.rowcount != 1:
db.rollback()
return None
db.commit()
return FabricJob(
job_id=row[0], tenant_id=row[1], cell_id=row[2],
profile_id=row[3], session_id=row[4], event_id=row[5],
status="running",
)
return self._storage(claim_one)
def health(self) -> dict[str, Any]:
def query() -> int:
with closing(self._connect()) as connection, connection as db:
return int(db.execute("SELECT count(*) FROM fabric_jobs").fetchone()[0])
return {
"component": "hermes_fabric", "jobs": self._storage(query),
"checked_at": datetime.now(timezone.utc).isoformat(),
}
@@ -0,0 +1,67 @@
"""Hermes shared-fabric profile isolation primitives."""
from __future__ import annotations
from dataclasses import dataclass
import os
from pathlib import Path
from .tenant_context import ValidationError, require_ident
@dataclass(frozen=True)
class HermesProfile:
tenant_id: str
cell_id: str
profile_id: str
hermes_home: Path
workspace: Path
def __post_init__(self) -> None:
require_ident("tenant_id", self.tenant_id, tenant=True)
for name in ("cell_id", "profile_id"):
require_ident(name, getattr(self, name))
if (
not isinstance(self.hermes_home, Path)
or not isinstance(self.workspace, Path)
or not self.hermes_home.is_absolute()
or not self.workspace.is_absolute()
):
raise ValidationError("profile paths must be absolute")
@property
def environment(self) -> dict[str, str]:
return {
"HERMES_HOME": str(self.hermes_home),
"HOME": str(self.hermes_home),
"AIOS_TENANT_ID": self.tenant_id,
"AIOS_CELL_ID": self.cell_id,
"AIOS_PROFILE_ID": self.profile_id,
}
@staticmethod
def _reject_symlink_components(root: Path) -> None:
current = Path(root.anchor)
for part in root.parts[1:]:
current = current / part
if current.is_symlink():
raise ValidationError("profile root contains symlink")
def _validate_roots(self) -> None:
for root in (self.hermes_home, self.workspace):
self._reject_symlink_components(root)
def prepare(self) -> None:
self._validate_roots()
for root in (self.hermes_home, self.workspace):
root.mkdir(parents=True, exist_ok=True)
self._validate_roots()
for root in (self.hermes_home, self.workspace):
os.chmod(root, 0o700)
def assert_path_allowed(self, path: str | Path) -> None:
self._validate_roots()
target = Path(path).resolve()
for root in (self.hermes_home.resolve(), self.workspace.resolve()):
if target == root or root in target.parents:
return
raise ValidationError("path escapes profile isolation boundary")
+158
View File
@@ -0,0 +1,158 @@
"""Fail-closed identity binding for authenticated external ingress.
External payload claims are not authority. An HMAC-authenticated envelope is
the sole factory for :class:`AuthenticatedPrincipal`; the resolver then checks
every claim against the authoritative ``TenantRouter`` before the runtime signs
an internal ``TenantContext``.
"""
from __future__ import annotations
from dataclasses import dataclass
import hashlib
import hmac
import re
from typing import Any, Mapping
from .router import Route, TenantRouter
from .tenant_context import ScopeError, ValidationError, canonical_json, require_ident
_PROVENANCE = object()
_SIGNATURE_RE = re.compile(r"^[0-9a-f]{64}$")
_SCOPE_FIELDS = (
"principal_id", "tenant_id", "cell_id", "channel",
"channel_account_id", "session_id", "message",
)
class AuthenticationError(ValidationError):
"""Authentication or identity resolution failed without disclosing scope."""
@dataclass(frozen=True, init=False)
class AuthenticatedPrincipal:
"""A principal which only the verified envelope factory can create."""
principal_id: str
def __init__(self, principal_id: str, *, _provenance: object) -> None:
if _provenance is not _PROVENANCE:
raise TypeError("AuthenticatedPrincipal is created by authenticated ingress only")
object.__setattr__(self, "principal_id", require_ident("principal_id", principal_id))
@classmethod
def _verified(cls, principal_id: str) -> "AuthenticatedPrincipal":
return cls(principal_id, _provenance=_PROVENANCE)
@dataclass(frozen=True)
class IdentityClaims:
tenant_id: str
cell_id: str
channel: str
channel_account_id: str
session_id: str
def __post_init__(self) -> None:
require_ident("tenant_id", self.tenant_id, tenant=True)
for field in ("cell_id", "channel", "channel_account_id", "session_id"):
require_ident(field, getattr(self, field))
@dataclass(frozen=True)
class AuthenticatedIngress:
principal: AuthenticatedPrincipal
claims: IdentityClaims
message: Mapping[str, Any]
@dataclass(frozen=True)
class RuntimeIdentity:
tenant_id: str
cell_id: str
principal_id: str
channel: str
channel_account_id: str
session_id: str
class IngressAuthenticator:
"""Verify a canonical HMAC envelope before any identity lookup occurs."""
def __init__(self, hmac_key: bytes) -> None:
if not isinstance(hmac_key, bytes) or len(hmac_key) < 32:
raise ValidationError("ingress HMAC key must be at least 32 bytes")
self._hmac_key = hmac_key
@staticmethod
def _signed_payload(request: Mapping[str, Any]) -> dict[str, Any]:
if not isinstance(request, Mapping):
raise ValidationError("ingress request must be an object")
if set(request) != {*_SCOPE_FIELDS, "signature"}:
raise ValidationError("ingress request fields are invalid")
values = {field: request[field] for field in _SCOPE_FIELDS}
if not isinstance(values["message"], Mapping):
raise ValidationError("ingress message must be an object")
return values
def authenticate(self, request: Mapping[str, Any]) -> AuthenticatedIngress:
values = self._signed_payload(request)
signature = request["signature"]
if not isinstance(signature, str) or not _SIGNATURE_RE.fullmatch(signature):
raise AuthenticationError("invalid ingress signature")
expected = hmac.new(
self._hmac_key, canonical_json(values), hashlib.sha256
).hexdigest()
if not hmac.compare_digest(expected, signature):
raise AuthenticationError("invalid ingress signature")
return AuthenticatedIngress(
principal=AuthenticatedPrincipal._verified(values["principal_id"]),
claims=IdentityClaims(
tenant_id=values["tenant_id"],
cell_id=values["cell_id"],
channel=values["channel"],
channel_account_id=values["channel_account_id"],
session_id=values["session_id"],
),
message=dict(values["message"]),
)
class RuntimeIdentityResolver:
"""Resolve authenticated ingress identity through ``TenantRouter`` only."""
def __init__(self, router: TenantRouter) -> None:
self._router = router
def resolve(
self, principal: AuthenticatedPrincipal, claims: IdentityClaims
) -> RuntimeIdentity:
if not isinstance(principal, AuthenticatedPrincipal):
raise AuthenticationError("untrusted principal type")
try:
route: Route = self._router.resolve(
channel=claims.channel,
channel_account_id=claims.channel_account_id,
principal_id=principal.principal_id,
session_id=claims.session_id,
)
except (ScopeError, ValidationError) as exc:
raise AuthenticationError("identity is not registered") from None
expected = (
claims.tenant_id, claims.cell_id, claims.channel,
claims.channel_account_id, principal.principal_id, claims.session_id,
)
actual = (
route.tenant_id, route.cell_id, route.channel,
route.channel_account_id, route.principal_id, route.session_id,
)
if actual != expected:
raise AuthenticationError("identity claims do not match authoritative route")
return RuntimeIdentity(
tenant_id=route.tenant_id,
cell_id=route.cell_id,
principal_id=route.principal_id,
channel=route.channel,
channel_account_id=route.channel_account_id,
session_id=route.session_id or "",
)
@@ -0,0 +1,512 @@
"""Fail-closed loopback HTTP shell for V2R1 ingress processors."""
from __future__ import annotations
import ipaddress
import json
import socket
import threading
import time
from collections.abc import Callable, Mapping
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from typing import Any
from urllib.parse import urlsplit
MAX_REQUEST_BYTES = 1024 * 1024
MAX_RESPONSE_BYTES = 4096
REQUEST_IO_TIMEOUT_SECONDS = 0.5
REQUEST_NETWORK_DEADLINE_SECONDS = 1.0
HEX_DIGITS = frozenset("0123456789abcdefABCDEF")
HEADER_NAME_BYTES = frozenset(
b"!#$%&'*+-.^_`|~0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
)
INTERNAL_ERROR_BODY = b'{"status":"INTERNAL_ERROR"}'
MUTATION_ROUTES = frozenset(
{"/v1/ingress", "/v1/receipts/status", "/v1/outbound-receipts"}
)
Processor = Callable[[str, bytes], tuple[int, Mapping[str, Any]]]
class RequestRejected(Exception):
def __init__(self, status: int, payload_status: str) -> None:
super().__init__(payload_status)
self.status = status
self.payload_status = payload_status
class IngressHTTPServer(ThreadingHTTPServer):
"""Threaded loopback server with an optional externally supplied processor."""
daemon_threads = False
block_on_close = True
def __init__(
self,
address: tuple[str, int],
handler: type[BaseHTTPRequestHandler],
processor: Processor | None,
) -> None:
self._closing = threading.Event()
self._lifecycle_lock = threading.RLock()
self._connections_lock = threading.Lock()
self._connections: set[socket.socket] = set()
self._server_close_lock = threading.Lock()
self.processor = processor
super().__init__(address, handler)
@property
def is_closing(self) -> bool:
return self._closing.is_set()
def get_request(self) -> tuple[socket.socket, tuple[str, int]]:
"""Register each accepted socket before handler scheduling can begin."""
connection, client_address = super().get_request()
with self._lifecycle_lock:
if self._closing.is_set():
reject = True
else:
with self._connections_lock:
self._connections.add(connection)
reject = False
if reject:
self._shutdown_and_close_connection(connection)
raise OSError("server is closing")
return connection, client_address
def unregister_connection(self, connection: socket.socket) -> None:
with self._connections_lock:
self._connections.discard(connection)
def _shutdown_and_close_connection(self, connection: socket.socket) -> None:
try:
connection.shutdown(socket.SHUT_RDWR)
except OSError:
pass
try:
connection.close()
except OSError:
pass
finally:
self.unregister_connection(connection)
def _close_accepted_connections(self) -> None:
with self._connections_lock:
connections = tuple(self._connections)
for connection in connections:
self._shutdown_and_close_connection(connection)
def process_request(
self,
request: socket.socket,
client_address: tuple[str, int],
) -> None:
"""Linearize request admission with the transition to closing."""
with self._lifecycle_lock:
if self._closing.is_set():
reject = True
else:
reject = False
try:
super().process_request(request, client_address)
except Exception:
self._shutdown_and_close_connection(request)
raise
if reject:
self._shutdown_and_close_connection(request)
def shutdown_request(self, request: socket.socket) -> None:
try:
request.shutdown(socket.SHUT_RDWR)
except OSError:
pass
try:
super().shutdown_request(request)
finally:
self.unregister_connection(request)
def call_processor(self, path: str, body: bytes) -> tuple[bool, Any]:
"""Start processing atomically with respect to server shutdown."""
with self._lifecycle_lock:
if self._closing.is_set() or self.processor is None:
return False, None
return True, self.processor(path, body)
def _begin_closing(self) -> None:
with self._lifecycle_lock:
self._closing.set()
def shutdown(self) -> None:
self._begin_closing()
self._close_accepted_connections()
super().shutdown()
def server_close(self) -> None:
"""Interrupt accepted sockets before the base class joins handlers."""
with self._server_close_lock:
self._begin_closing()
self._close_accepted_connections()
super().server_close()
def handle_error(
self,
request: socket.socket,
client_address: tuple[str, int],
) -> None:
"""Close unexpected handler failures without printing request data."""
try:
request.shutdown(socket.SHUT_RDWR)
except OSError:
pass
class _ValidatingHeaderReader:
"""Validate raw header lines before the standard library normalizes them."""
def __init__(self, handler: "IngressRequestHandler", reader: Any) -> None:
self._handler = handler
self._reader = reader
def readline(self, limit: int = -1) -> bytes:
try:
line = self._reader.readline(limit)
except TimeoutError as exc:
raise RequestRejected(408, "REQUEST_TIMEOUT") from exc
self._handler._ensure_network_read_active()
self._validate(line)
return line
@staticmethod
def _validate(line: bytes) -> None:
if line == b"\r\n":
return
if not line or not line.endswith(b"\r\n"):
raise RequestRejected(400, "BAD_REQUEST")
raw = line[:-2]
if not raw or raw[:1] in {b" ", b"\t"}:
raise RequestRejected(400, "BAD_REQUEST")
separator = raw.find(b":")
if separator <= 0:
raise RequestRejected(400, "BAD_REQUEST")
name = raw[:separator]
value = raw[separator + 1 :]
if any(byte not in HEADER_NAME_BYTES for byte in name):
raise RequestRejected(400, "BAD_REQUEST")
if any((byte < 0x20 and byte != 0x09) or byte == 0x7F for byte in value):
raise RequestRejected(400, "BAD_REQUEST")
if name.lower() == b"content-length":
numeric = value[1:] if value.startswith(b" ") else value
if not numeric or any(byte < 0x30 or byte > 0x39 for byte in numeric):
raise RequestRejected(400, "BAD_REQUEST")
class IngressRequestHandler(BaseHTTPRequestHandler):
"""Bounded JSON transport; application processing is injected later."""
server: IngressHTTPServer
def setup(self) -> None:
super().setup()
self.connection.settimeout(REQUEST_IO_TIMEOUT_SECONDS)
self._network_read_lock = threading.Lock()
self._network_read_expired = threading.Event()
self._network_read_deadline: float | None = None
self._network_read_timer: threading.Timer | None = None
self._network_read_active = False
def finish(self) -> None:
self._complete_network_read()
try:
super().finish()
except OSError:
pass
def _start_network_read(self) -> None:
self._complete_network_read()
timer = threading.Timer(
REQUEST_NETWORK_DEADLINE_SECONDS,
self._expire_network_read,
)
timer.name = f"aios-ingress-read-deadline-{id(self)}"
timer.daemon = True
with self._network_read_lock:
self._network_read_expired.clear()
self._network_read_deadline = (
time.monotonic() + REQUEST_NETWORK_DEADLINE_SECONDS
)
self._network_read_active = True
self._network_read_timer = timer
timer.start()
def _expire_network_read(self) -> None:
with self._network_read_lock:
if not self._network_read_active:
return
self._network_read_expired.set()
self.close_connection = True
try:
self.connection.shutdown(socket.SHUT_RD)
except OSError:
pass
def _complete_network_read(self) -> None:
timer: threading.Timer | None
with getattr(self, "_network_read_lock", threading.Lock()):
self._network_read_active = False
self._network_read_deadline = None
timer = self._network_read_timer
self._network_read_timer = None
if timer is not None:
timer.cancel()
if timer is not threading.current_thread():
timer.join(timeout=REQUEST_IO_TIMEOUT_SECONDS)
def _ensure_network_read_active(self) -> None:
if self.server.is_closing:
raise RequestRejected(503, "SERVICE_UNAVAILABLE")
deadline = self._network_read_deadline
if self._network_read_expired.is_set() or (
deadline is not None and time.monotonic() >= deadline
):
self._network_read_expired.set()
raise RequestRejected(408, "REQUEST_TIMEOUT")
def parse_request(self) -> bool:
original_reader = self.rfile
self.rfile = _ValidatingHeaderReader(self, original_reader) # type: ignore[assignment]
try:
return super().parse_request()
finally:
self.rfile = original_reader
def handle_one_request(self) -> None:
self._start_network_read()
try:
super().handle_one_request()
except RequestRejected as rejection:
self.close_connection = True
self._send_safely(rejection.status, {"status": rejection.payload_status})
except TimeoutError:
self.close_connection = True
self._send_safely(408, {"status": "REQUEST_TIMEOUT"})
except (BrokenPipeError, ConnectionResetError, OSError):
self.close_connection = True
except Exception:
self.close_connection = True
self._send_safely(500, {"status": "INTERNAL_ERROR"})
finally:
self._complete_network_read()
def send_error(
self,
code: int,
message: str | None = None,
explain: str | None = None,
) -> None:
"""Replace BaseHTTPRequestHandler HTML errors with bounded JSON."""
self.close_connection = True
if code == 501:
self._method_not_allowed()
return
self._send(int(code), {"status": "HTTP_ERROR"})
def log_message(self, format: str, *args: object) -> None:
return
def _send_safely(self, status: int, payload: Mapping[str, Any]) -> None:
try:
self._send(status, payload)
except OSError:
self.close_connection = True
def _path(self) -> str:
target = self.path
if not target or any(
ord(character) < 0x20 or ord(character) == 0x7F for character in target
):
raise RequestRejected(400, "BAD_REQUEST")
for index, character in enumerate(target):
if character == "%" and (
index + 2 >= len(target)
or any(value not in HEX_DIGITS for value in target[index + 1 : index + 3])
):
raise RequestRejected(400, "BAD_REQUEST")
try:
parts = urlsplit(target)
except ValueError as exc:
raise RequestRejected(400, "BAD_REQUEST") from exc
if parts.fragment:
raise RequestRejected(400, "BAD_REQUEST")
if target.startswith("/"):
if parts.scheme or parts.netloc:
raise RequestRejected(400, "BAD_REQUEST")
elif parts.scheme in {"http", "https"} and parts.netloc:
if parts.hostname is None:
raise RequestRejected(400, "BAD_REQUEST")
try:
_ = parts.port
except ValueError as exc:
raise RequestRejected(400, "BAD_REQUEST") from exc
else:
raise RequestRejected(400, "BAD_REQUEST")
return parts.path or "/"
@staticmethod
def _encoded_response(
status: object,
payload: object,
) -> tuple[int, bytes]:
if (
type(status) is not int
or not 200 <= status <= 599
or status in {204, 205, 304}
or not isinstance(payload, Mapping)
):
return 500, INTERNAL_ERROR_BODY
try:
body = json.dumps(
dict(payload),
ensure_ascii=False,
separators=(",", ":"),
sort_keys=True,
allow_nan=False,
).encode("utf-8")
except Exception:
return 500, INTERNAL_ERROR_BODY
if len(body) > MAX_RESPONSE_BYTES:
return 500, INTERNAL_ERROR_BODY
return status, body
def _send(self, status: int, payload: Mapping[str, Any]) -> None:
self._complete_network_read()
status, body = self._encoded_response(status, payload)
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.send_header("Cache-Control", "no-store")
self.end_headers()
if getattr(self, "command", None) != "HEAD":
self.wfile.write(body)
def _method_not_allowed(self) -> None:
self._send(405, {"status": "METHOD_NOT_ALLOWED"})
def _reject(self, status: int, payload_status: str) -> None:
self.close_connection = True
self._send(status, {"status": payload_status})
def _content_length(self) -> int:
if self.headers.get_all("Transfer-Encoding", []):
raise RequestRejected(400, "BAD_REQUEST")
values = self.headers.get_all("Content-Length", [])
if len(values) > 1:
raise RequestRejected(400, "BAD_REQUEST")
if not values:
return 0
raw_length = values[0]
if (
not raw_length
or not raw_length.isascii()
or not raw_length.isdigit()
):
raise RequestRejected(400, "BAD_REQUEST")
try:
length = int(raw_length)
except ValueError as exc:
raise RequestRejected(400, "BAD_REQUEST") from exc
if length > MAX_REQUEST_BYTES:
raise RequestRejected(413, "REQUEST_TOO_LARGE")
return length
def _read_exact_body(self, length: int) -> bytes:
try:
body = self.rfile.read(length)
except TimeoutError as exc:
raise RequestRejected(408, "REQUEST_TIMEOUT") from exc
self._ensure_network_read_active()
if len(body) != length:
raise RequestRejected(400, "BAD_REQUEST")
return body
def do_GET(self) -> None:
path = self._path()
if path == "/health/live":
self._send(200, {"status": "LIVE"})
elif path == "/health/ready":
if self.server.processor is None:
self._send(503, {"status": "SERVICE_NOT_CONFIGURED"})
else:
self._send(200, {"status": "READY"})
elif path in MUTATION_ROUTES:
self._method_not_allowed()
else:
self._send(404, {"status": "NOT_FOUND"})
def do_POST(self) -> None:
path = self._path()
if path not in MUTATION_ROUTES:
if path in {"/health/live", "/health/ready"}:
self._method_not_allowed()
else:
self._send(404, {"status": "NOT_FOUND"})
return
try:
length = self._content_length()
except RequestRejected as rejection:
self._reject(rejection.status, rejection.payload_status)
return
processor = self.server.processor
if processor is None:
self._send(503, {"status": "SERVICE_NOT_CONFIGURED"})
return
if self.server.is_closing:
self._reject(503, "SERVICE_UNAVAILABLE")
return
try:
body = self._read_exact_body(length)
except RequestRejected as rejection:
self._reject(rejection.status, rejection.payload_status)
return
self._complete_network_read()
try:
started, result = self.server.call_processor(path, body)
if not started:
self._reject(503, "SERVICE_UNAVAILABLE")
return
status, payload = result
except Exception:
self._send(500, {"status": "INTERNAL_ERROR"})
return
self._send(status, payload)
do_DELETE = _method_not_allowed
do_HEAD = _method_not_allowed
do_OPTIONS = _method_not_allowed
do_PATCH = _method_not_allowed
do_PUT = _method_not_allowed
def build_server(
host: str = "127.0.0.1",
port: int = 18792,
*,
processor: Processor | None = None,
) -> IngressHTTPServer:
"""Build a loopback-only HTTP server without starting it."""
try:
address = ipaddress.ip_address(host)
except ValueError as exc:
raise ValueError("host must be a loopback IP address") from exc
if address.version != 4 or not address.is_loopback:
raise ValueError("host must be an IPv4 loopback address")
return IngressHTTPServer((host, port), IngressRequestHandler, processor)
def serve(host: str = "127.0.0.1", port: int = 18792) -> None:
"""Run the unconfigured loopback shell until interrupted."""
server = build_server(host, port)
try:
server.serve_forever()
except KeyboardInterrupt:
return
finally:
server.server_close()
@@ -0,0 +1,63 @@
"""Tenant-scoped memory namespace and access policy for AIOS V2R1."""
from __future__ import annotations
from dataclasses import dataclass
from pathlib import PurePosixPath
from typing import Literal
from .tenant_context import ScopeError, ValidationError, require_ident
MemoryKind = Literal["session", "profile", "cell", "tenant", "shared_artifact"]
@dataclass(frozen=True)
class MemoryScope:
tenant_id: str
cell_id: str
profile_id: str
session_id: str | None
kind: MemoryKind
def __post_init__(self) -> None:
require_ident("tenant_id", self.tenant_id, tenant=True)
for name in ("cell_id", "profile_id"):
require_ident(name, getattr(self, name))
if self.session_id is not None:
require_ident("session_id", self.session_id)
if self.kind not in {"session", "profile", "cell", "tenant", "shared_artifact"}:
raise ValidationError("invalid memory kind")
if self.kind == "session" and self.session_id is None:
raise ValidationError("session memory requires session_id")
@property
def namespace(self) -> str:
parts = ["tenant", self.tenant_id, "cell", self.cell_id]
if self.kind in {"profile", "session"}:
parts.extend(["profile", self.profile_id])
if self.kind == "session":
parts.extend(["session", str(self.session_id)])
parts.extend(["memory", self.kind])
return str(PurePosixPath(*parts))
def assert_access(self, requested: "MemoryScope", *, write: bool = False) -> None:
if self.tenant_id != requested.tenant_id:
raise ScopeError("cross-tenant memory access denied")
if self.cell_id != requested.cell_id:
raise ScopeError("cross-cell memory access denied")
if requested.kind == "shared_artifact":
if write:
raise ScopeError("shared artifacts are immutable")
return
if self.kind != requested.kind:
raise ScopeError("cross-kind memory access denied")
if self.profile_id != requested.profile_id and requested.kind in {"profile", "session"}:
raise ScopeError("cross-profile memory access denied")
if requested.kind == "session" and self.session_id != requested.session_id:
raise ScopeError("cross-session memory access denied")
def qualify_memory_key(scope: MemoryScope, key: str) -> str:
normalized = require_ident("memory_key", key)
if normalized != key:
raise ValidationError("memory_key must be canonical")
return f"{scope.namespace}/{normalized}"
@@ -0,0 +1,227 @@
"""Tenant-scoped append-only message ledger and exact quote resolver."""
from __future__ import annotations
from collections.abc import Callable
from contextlib import closing
from dataclasses import dataclass
from datetime import timedelta
import os
from pathlib import Path
import sqlite3
from typing import TypeVar
from .tenant_context import (
CanonicalMessage, ConflictError, ScopeError, ValidationError,
isoformat, normalize_message_id, utc_now,
)
T = TypeVar("T")
@dataclass(frozen=True)
class LedgerRecord:
tenant_id: str
cell_id: str
channel: str
channel_account_id: str
peer_id: str
direction: str
message_id: str
event_id: str
body: str
occurred_at: str
expires_at: str
class MessageLedger:
"""Exact-ID ledger with no fuzzy, prefix, or time-nearest fallback."""
def __init__(self, database: str | Path, *, ttl_days: int = 7) -> None:
if not 1 <= ttl_days <= 365:
raise ValidationError("ttl_days must be between 1 and 365")
self.database = Path(database)
self.ttl_days = ttl_days
self.database.parent.mkdir(parents=True, exist_ok=True)
self._initialize()
try:
os.chmod(self.database, 0o600)
except OSError:
pass
def _connect(self) -> sqlite3.Connection:
db = sqlite3.connect(str(self.database), timeout=30)
db.row_factory = sqlite3.Row
db.execute("PRAGMA journal_mode=WAL")
db.execute("PRAGMA synchronous=FULL")
db.execute("PRAGMA busy_timeout=30000")
return db
def _storage(self, operation: Callable[[], T]) -> T:
failure: ConflictError | None = None
try:
return operation()
except sqlite3.Error:
failure = ConflictError("ledger storage unavailable")
# Raise after the driver exception handler, keeping SQLite details out of
# both the public exception and its implicit context.
raise failure
def _initialize(self) -> None:
def initialize() -> None:
with closing(self._connect()) as connection, connection as db:
db.executescript(
"""
CREATE TABLE IF NOT EXISTS message_ledger (
tenant_id TEXT NOT NULL,
cell_id TEXT NOT NULL,
channel TEXT NOT NULL,
channel_account_id TEXT NOT NULL,
peer_id TEXT NOT NULL,
direction TEXT NOT NULL CHECK(direction IN ('inbound','outbound','internal')),
message_id TEXT NOT NULL,
event_id TEXT NOT NULL,
body TEXT NOT NULL,
occurred_at TEXT NOT NULL,
expires_at TEXT NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(
tenant_id, cell_id, channel, channel_account_id,
peer_id, direction, message_id
),
UNIQUE(tenant_id, cell_id, event_id)
);
CREATE INDEX IF NOT EXISTS idx_message_reply_lookup ON message_ledger(
tenant_id, cell_id, channel, channel_account_id,
peer_id, message_id, expires_at
);
"""
)
self._storage(initialize)
def append(self, message: CanonicalMessage) -> LedgerRecord:
message_id = normalize_message_id(message.message_id)
now = utc_now()
expires = isoformat(now + timedelta(days=self.ttl_days))
key = (
message.tenant_id, message.cell_id, message.channel,
message.channel_account_id, message.peer_id, message.direction, message_id,
)
def write() -> LedgerRecord:
with closing(self._connect()) as connection, connection as db:
db.execute("BEGIN IMMEDIATE")
existing = db.execute(
"SELECT event_id, body, occurred_at, expires_at FROM message_ledger "
"WHERE tenant_id=? AND cell_id=? AND channel=? AND channel_account_id=? "
"AND peer_id=? AND direction=? AND message_id=?", key,
).fetchone()
if existing:
if existing["body"] != message.body:
db.rollback()
raise ConflictError("message ID collision with different content")
db.commit()
return LedgerRecord(
*key, existing["event_id"], existing["body"],
existing["occurred_at"], existing["expires_at"],
)
db.execute(
"INSERT INTO message_ledger VALUES(?,?,?,?,?,?,?,?,?,?,?,?)",
(*key, message.event_id, message.body, message.occurred_at,
expires, isoformat(now)),
)
db.commit()
return LedgerRecord(
*key, message.event_id, message.body, message.occurred_at, expires
)
return self._storage(write)
def remember(self, message: CanonicalMessage) -> LedgerRecord:
"""Backward-compatible API wrapper outside the runtime write path."""
return self.append(message)
def matches(self, message: CanonicalMessage) -> bool:
message_id = normalize_message_id(message.message_id)
def query() -> bool:
with closing(self._connect()) as connection, connection as db:
row = db.execute(
"SELECT event_id, body FROM message_ledger WHERE tenant_id=? AND "
"cell_id=? AND channel=? AND channel_account_id=? AND peer_id=? "
"AND direction=? AND message_id=?",
(
message.tenant_id, message.cell_id, message.channel,
message.channel_account_id, message.peer_id, message.direction,
message_id,
),
).fetchone()
return bool(
row and row["event_id"] == message.event_id
and row["body"] == message.body
)
return self._storage(query)
def remove(self, record: LedgerRecord) -> None:
def delete() -> None:
with closing(self._connect()) as connection, connection as db:
db.execute(
"DELETE FROM message_ledger WHERE tenant_id=? AND cell_id=? AND "
"channel=? AND channel_account_id=? AND peer_id=? AND direction=? "
"AND message_id=? AND event_id=?",
(
record.tenant_id, record.cell_id, record.channel,
record.channel_account_id, record.peer_id, record.direction,
record.message_id, record.event_id,
),
)
self._storage(delete)
def resolve_quote(self, message: CanonicalMessage) -> str:
if message.quoted_body is not None:
return message.quoted_body
if message.reply_to_message_id is None:
raise ScopeError("quoted_text_unavailable")
reply_id = normalize_message_id(
message.reply_to_message_id, field_name="reply_to_message_id"
)
def query() -> list[sqlite3.Row]:
with closing(self._connect()) as connection, connection as db:
return db.execute(
"SELECT direction, body, event_id FROM message_ledger "
"WHERE tenant_id=? AND cell_id=? AND channel=? AND channel_account_id=? "
"AND peer_id=? AND message_id=? AND expires_at>?",
(
message.tenant_id, message.cell_id, message.channel,
message.channel_account_id, message.peer_id, reply_id, isoformat(),
),
).fetchall()
rows = self._storage(query)
if len(rows) == 1:
return str(rows[0]["body"])
if len(rows) > 1:
raise ConflictError("ambiguous reply ID across message directions")
raise ScopeError("quoted_text_unavailable")
def purge_expired(self) -> int:
def purge() -> int:
with closing(self._connect()) as connection, connection as db:
cursor = db.execute(
"DELETE FROM message_ledger WHERE expires_at<=?", (isoformat(),)
)
return cursor.rowcount
return self._storage(purge)
def integrity_check(self) -> str:
def check() -> str:
with closing(self._connect()) as connection, connection as db:
return str(db.execute("PRAGMA integrity_check").fetchone()[0])
return self._storage(check)
def count(self) -> int:
def query() -> int:
with closing(self._connect()) as connection, connection as db:
return int(db.execute("SELECT count(*) FROM message_ledger").fetchone()[0])
return self._storage(query)
+336
View File
@@ -0,0 +1,336 @@
"""Authoritative tenant registry and fail-closed message router."""
from __future__ import annotations
from contextlib import contextmanager
from contextlib import closing
from dataclasses import dataclass
from datetime import datetime, timedelta
import sqlite3
from pathlib import Path
from typing import Callable, Iterator
from .tenant_context import (
CanonicalMessage,
ConflictError,
ScopeError,
TenantContext,
ValidationError,
isoformat,
parse_time,
require_ident,
utc_now,
)
@dataclass(frozen=True)
class Route:
tenant_id: str
cell_id: str
channel: str
channel_account_id: str
principal_id: str
session_id: str | None
class TenantRouter:
"""SQLite-backed routing registry.
Channel accounts are authoritative tenant ownership boundaries. Principal and
session bindings may narrow a route, but can never move traffic to another
tenant or Cell.
"""
def __init__(
self, database: str | Path, *, clock: Callable[[], datetime] = utc_now
) -> None:
self.database = str(database)
self._clock = clock
self._initialize()
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(self.database, timeout=30, isolation_level=None)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA foreign_keys=ON")
connection.execute("PRAGMA journal_mode=WAL")
connection.execute("PRAGMA synchronous=FULL")
connection.execute("PRAGMA busy_timeout=30000")
return connection
@contextmanager
def _transaction(self) -> Iterator[sqlite3.Connection]:
connection = self._connect()
try:
connection.execute("BEGIN IMMEDIATE")
yield connection
connection.execute("COMMIT")
except Exception:
connection.execute("ROLLBACK")
raise
finally:
connection.close()
def _initialize(self) -> None:
with closing(self._connect()) as connection, connection as db:
db.executescript(
"""
CREATE TABLE IF NOT EXISTS tenants (
tenant_id TEXT PRIMARY KEY,
cell_id TEXT NOT NULL UNIQUE,
status TEXT NOT NULL CHECK(status IN ('active','suspended','retired')),
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS channel_routes (
channel TEXT NOT NULL,
channel_account_id TEXT NOT NULL,
tenant_id TEXT NOT NULL,
cell_id TEXT NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(channel, channel_account_id),
FOREIGN KEY(tenant_id) REFERENCES tenants(tenant_id)
);
CREATE TABLE IF NOT EXISTS principal_routes (
channel TEXT NOT NULL,
channel_account_id TEXT NOT NULL,
principal_id TEXT NOT NULL,
tenant_id TEXT NOT NULL,
cell_id TEXT NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(channel, channel_account_id, principal_id),
FOREIGN KEY(channel, channel_account_id)
REFERENCES channel_routes(channel, channel_account_id)
);
CREATE TABLE IF NOT EXISTS session_bindings (
tenant_id TEXT NOT NULL,
session_id TEXT NOT NULL,
cell_id TEXT NOT NULL,
principal_id TEXT NOT NULL,
expires_at TEXT NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(tenant_id, session_id),
FOREIGN KEY(tenant_id) REFERENCES tenants(tenant_id)
);
CREATE INDEX IF NOT EXISTS idx_session_expiry
ON session_bindings(expires_at);
"""
)
def register_tenant(self, tenant_id: str, cell_id: str) -> None:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
cell_id = require_ident("cell_id", cell_id)
now = isoformat(self._clock())
with self._transaction() as db:
row = db.execute(
"SELECT cell_id, status FROM tenants WHERE tenant_id=?", (tenant_id,)
).fetchone()
if row:
if row["cell_id"] != cell_id:
raise ConflictError("tenant already bound to another cell")
db.execute(
"UPDATE tenants SET status='active', updated_at=? WHERE tenant_id=?",
(now, tenant_id),
)
return
conflict = db.execute(
"SELECT tenant_id FROM tenants WHERE cell_id=?", (cell_id,)
).fetchone()
if conflict:
raise ConflictError("cell already belongs to another tenant")
db.execute(
"INSERT INTO tenants VALUES(?,?,?,?,?)",
(tenant_id, cell_id, "active", now, now),
)
def set_tenant_status(self, tenant_id: str, status: str) -> None:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
if status not in {"active", "suspended", "retired"}:
raise ValidationError("invalid tenant status")
with self._transaction() as db:
cursor = db.execute(
"UPDATE tenants SET status=?, updated_at=? WHERE tenant_id=?",
(status, isoformat(self._clock()), tenant_id),
)
if cursor.rowcount != 1:
raise ValidationError("unknown tenant")
def bind_channel(
self,
*,
tenant_id: str,
channel: str,
channel_account_id: str,
) -> None:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
channel = require_ident("channel", channel)
channel_account_id = require_ident("channel_account_id", channel_account_id)
with self._transaction() as db:
tenant = db.execute(
"SELECT cell_id, status FROM tenants WHERE tenant_id=?", (tenant_id,)
).fetchone()
if not tenant or tenant["status"] != "active":
raise ValidationError("tenant is not active")
existing = db.execute(
"SELECT tenant_id, cell_id FROM channel_routes "
"WHERE channel=? AND channel_account_id=?",
(channel, channel_account_id),
).fetchone()
if existing:
if existing["tenant_id"] != tenant_id or existing["cell_id"] != tenant["cell_id"]:
raise ConflictError("channel account already belongs to another tenant")
return
db.execute(
"INSERT INTO channel_routes VALUES(?,?,?,?,?)",
(channel, channel_account_id, tenant_id, tenant["cell_id"], isoformat(self._clock())),
)
def bind_principal(
self,
*,
tenant_id: str,
channel: str,
channel_account_id: str,
principal_id: str,
) -> None:
principal_id = require_ident("principal_id", principal_id)
route = self.resolve_channel(channel, channel_account_id)
if route.tenant_id != tenant_id:
raise ScopeError("principal cannot cross tenant boundary")
with self._transaction() as db:
existing = db.execute(
"SELECT tenant_id, cell_id FROM principal_routes WHERE "
"channel=? AND channel_account_id=? AND principal_id=?",
(channel, channel_account_id, principal_id),
).fetchone()
if existing:
if existing["tenant_id"] != tenant_id or existing["cell_id"] != route.cell_id:
raise ConflictError("principal route conflict")
return
db.execute(
"INSERT INTO principal_routes VALUES(?,?,?,?,?,?)",
(
channel,
channel_account_id,
principal_id,
tenant_id,
route.cell_id,
isoformat(self._clock()),
),
)
def bind_session(
self,
*,
tenant_id: str,
session_id: str,
cell_id: str,
principal_id: str,
ttl_seconds: int = 86400,
) -> None:
tenant_id = require_ident("tenant_id", tenant_id, tenant=True)
session_id = require_ident("session_id", session_id)
cell_id = require_ident("cell_id", cell_id)
principal_id = require_ident("principal_id", principal_id)
if not 60 <= ttl_seconds <= 31 * 86400:
raise ValidationError("invalid session TTL")
now = self._clock()
expires = isoformat(now + timedelta(seconds=ttl_seconds))
with self._transaction() as db:
tenant = db.execute(
"SELECT cell_id, status FROM tenants WHERE tenant_id=?", (tenant_id,)
).fetchone()
if not tenant or tenant["status"] != "active" or tenant["cell_id"] != cell_id:
raise ScopeError("session cell does not match tenant")
existing = db.execute(
"SELECT cell_id, principal_id FROM session_bindings "
"WHERE tenant_id=? AND session_id=?",
(tenant_id, session_id),
).fetchone()
if existing and (
existing["cell_id"] != cell_id or existing["principal_id"] != principal_id
):
raise ConflictError("session is already bound to another principal or cell")
db.execute(
"INSERT INTO session_bindings VALUES(?,?,?,?,?,?) "
"ON CONFLICT(tenant_id,session_id) DO UPDATE SET expires_at=excluded.expires_at",
(tenant_id, session_id, cell_id, principal_id, expires, isoformat(now)),
)
def resolve_channel(self, channel: str, channel_account_id: str) -> Route:
channel = require_ident("channel", channel)
channel_account_id = require_ident("channel_account_id", channel_account_id)
with closing(self._connect()) as connection, connection as db:
row = db.execute(
"SELECT r.tenant_id, r.cell_id, t.status FROM channel_routes r "
"JOIN tenants t ON t.tenant_id=r.tenant_id "
"WHERE r.channel=? AND r.channel_account_id=?",
(channel, channel_account_id),
).fetchone()
if not row:
raise ScopeError("unknown channel account")
if row["status"] != "active":
raise ScopeError("tenant is not active")
return Route(row["tenant_id"], row["cell_id"], channel, channel_account_id, "", None)
def resolve(
self,
*,
channel: str,
channel_account_id: str,
principal_id: str,
session_id: str | None = None,
) -> Route:
principal_id = require_ident("principal_id", principal_id)
base = self.resolve_channel(channel, channel_account_id)
with closing(self._connect()) as connection, connection as db:
principal = db.execute(
"SELECT tenant_id, cell_id FROM principal_routes WHERE "
"channel=? AND channel_account_id=? AND principal_id=?",
(channel, channel_account_id, principal_id),
).fetchone()
if principal and (
principal["tenant_id"] != base.tenant_id or principal["cell_id"] != base.cell_id
):
raise ScopeError("principal route violates channel ownership")
if session_id is not None:
session_id = require_ident("session_id", session_id)
session = db.execute(
"SELECT cell_id, principal_id, expires_at FROM session_bindings "
"WHERE tenant_id=? AND session_id=?",
(base.tenant_id, session_id),
).fetchone()
if not session:
raise ScopeError("unknown session")
if parse_time(session["expires_at"]) <= self._clock():
raise ScopeError("session expired")
if session["cell_id"] != base.cell_id or session["principal_id"] != principal_id:
raise ScopeError("session scope mismatch")
return Route(
base.tenant_id,
base.cell_id,
channel,
channel_account_id,
principal_id,
session_id,
)
def assert_message_route(self, message: CanonicalMessage) -> Route:
route = self.resolve(
channel=message.channel,
channel_account_id=message.channel_account_id,
principal_id=message.principal_id,
session_id=message.session_id,
)
if message.tenant_id != route.tenant_id or message.cell_id != route.cell_id:
raise ScopeError("message claims do not match authoritative route")
return route
def assert_context_route(self, context: TenantContext) -> Route:
route = self.resolve(
channel=context.channel,
channel_account_id=context.channel_account_id,
principal_id=context.principal_id,
session_id=context.session_id,
)
if context.tenant_id != route.tenant_id or context.cell_id != route.cell_id:
raise ScopeError("context claims do not match authoritative route")
return route
+136
View File
@@ -0,0 +1,136 @@
"""V2R1 runtime composition root for authenticated channel ingress."""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime
from pathlib import Path
from typing import Any, Callable, Mapping
from .channel_adapter import ChannelAdapter, IngressResult
from .identity import (
AuthenticationError,
IngressAuthenticator,
RuntimeIdentity,
RuntimeIdentityResolver,
)
from .message_ledger import MessageLedger
from .router import TenantRouter
from .session_pool import SessionPool
from .tenant_context import ConflictError, ScopeError, TenantContext, ValidationError, utc_now
@dataclass(frozen=True)
class RuntimeIngressResponse:
"""Sanitised boundary response; no exception text crosses external ingress."""
status: str
result: IngressResult | None = None
class RuntimeWiring:
"""Own the only external-to-runtime identity binding and message path.
The request accepted by :meth:`ingest` is an HMAC-authenticated envelope;
tenant, cell, channel, account, session, principal, and message claims are
signed together. The envelope is then resolved against ``TenantRouter``.
Only that resolved identity can mint the short-lived internal context passed
to ``ChannelAdapter``.
"""
def __init__(
self,
*,
router: TenantRouter,
ledger: MessageLedger,
session_pool: SessionPool,
channel_adapter: ChannelAdapter,
identity_resolver: RuntimeIdentityResolver,
ingress_authenticator: IngressAuthenticator,
internal_signing_key: bytes,
clock: Callable[[], datetime],
) -> None:
self.router = router
self.ledger = ledger
self.session_pool = session_pool
self.channel_adapter = channel_adapter
self.identity_resolver = identity_resolver
self._ingress_authenticator = ingress_authenticator
self._internal_signing_key = internal_signing_key
self._clock = clock
@classmethod
def create(
cls,
root: str | Path,
*,
signing_key: bytes,
ingress_hmac_key: bytes | None = None,
clock: Callable[[], datetime] = utc_now,
) -> "RuntimeWiring":
if not isinstance(signing_key, bytes) or len(signing_key) < 32:
raise ValidationError("internal signing key must be at least 32 bytes")
# Kept optional for one controlled migration release; the external
# request path still cannot supply a TenantContext token.
hmac_key = ingress_hmac_key if ingress_hmac_key is not None else signing_key
root_path = Path(root)
root_path.mkdir(parents=True, exist_ok=True)
router = TenantRouter(root_path / "router.sqlite3", clock=clock)
ledger = MessageLedger(root_path / "message_ledger.sqlite3")
session_pool = SessionPool(router)
adapter = ChannelAdapter(
router=router,
ledger=ledger,
session_pool=session_pool,
signing_key=signing_key,
clock=clock,
)
return cls(
router=router,
ledger=ledger,
session_pool=session_pool,
channel_adapter=adapter,
identity_resolver=RuntimeIdentityResolver(router),
ingress_authenticator=IngressAuthenticator(hmac_key),
internal_signing_key=signing_key,
clock=clock,
)
def _issue_internal_context(self, identity: RuntimeIdentity) -> TenantContext:
"""Mint internal scope only after all claims matched the router route."""
return TenantContext.issue(
lifetime_seconds=300,
now=self._clock(),
tenant_id=identity.tenant_id,
cell_id=identity.cell_id,
principal_id=identity.principal_id,
principal_type="authenticated_user",
session_id=identity.session_id,
task_id=None,
channel=identity.channel,
channel_account_id=identity.channel_account_id,
)
def ingest(self, *, request: Mapping[str, Any]) -> RuntimeIngressResponse:
"""Authenticate, resolve, issue internal context, then append and lease.
The only successful route is ``IngressAuthenticator`` ->
``RuntimeIdentityResolver`` -> ``ChannelAdapter`` ->
``MessageLedger.append`` + ``SessionPool``. The legacy caller-supplied
TenantContext token interface is intentionally not accepted.
"""
try:
ingress = self._ingress_authenticator.authenticate(request)
identity = self.identity_resolver.resolve(ingress.principal, ingress.claims)
context = self._issue_internal_context(identity)
result = self.channel_adapter.ingest(
token=context.sign(self._internal_signing_key), message=ingress.message
)
return RuntimeIngressResponse(status="ACCEPTED", result=result)
except (AuthenticationError, ScopeError):
return RuntimeIngressResponse(status="AUTH_FAILED")
except ValidationError:
return RuntimeIngressResponse(status="VALIDATION_FAILED")
except ConflictError:
return RuntimeIngressResponse(status="CONFLICT")
except Exception:
return RuntimeIngressResponse(status="INTERNAL_ERROR")
@@ -0,0 +1,61 @@
"""Tenant and Cell scoped, value-free secret reference model."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Any, Literal
from .tenant_context import ScopeError, ValidationError, require_ident
@dataclass(frozen=True)
class SecretRef:
secret_id: str
tenant_id: str
cell_id: str
kind: Literal["channel", "model", "tool", "runtime"]
version: str
broker_path: str
def __post_init__(self) -> None:
for name in ("secret_id", "cell_id", "version"):
value = getattr(self, name)
if require_ident(name, value) != value:
raise ValidationError(f"{name} must be canonical")
if require_ident("tenant_id", self.tenant_id, tenant=True) != self.tenant_id:
raise ValidationError("tenant_id must be canonical")
if self.kind not in {"channel", "model", "tool", "runtime"}:
raise ValidationError("invalid secret kind")
self._validate_broker_path()
def _validate_broker_path(self) -> None:
if not isinstance(self.broker_path, str) or not self.broker_path.startswith("secret://"):
raise ValidationError("secret broker path required")
suffix = self.broker_path[len("secret://"):]
if (
not suffix or "?" in suffix or "#" in suffix or chr(92) in suffix
or any(part in {"", ".", ".."} for part in suffix.split("/"))
):
raise ValidationError("invalid secret broker path")
for part in suffix.split("/"):
if require_ident("secret broker path segment", part) != part:
raise ValidationError("invalid secret broker path")
def can_be_used_by(self, *, tenant_id: str, cell_id: str) -> bool:
return self.tenant_id == tenant_id and self.cell_id == cell_id
def resolve(self, broker: Any) -> str:
"""Resolve through one explicit broker boundary without leaking provider errors."""
failure: ScopeError | None = None
value: object = None
try:
reader = getattr(broker, "read_secret")
if not callable(reader):
raise TypeError("invalid broker")
value = reader(self)
if not isinstance(value, str) or not value:
raise ValueError("invalid broker result")
except Exception:
failure = ScopeError("secret broker unavailable")
if failure is not None:
raise failure
return value
@@ -0,0 +1,59 @@
"""Process-local session lease pool backed by TenantRouter authority."""
from __future__ import annotations
from dataclasses import dataclass
from threading import RLock
from .router import Route, TenantRouter
from .tenant_context import ScopeError, TenantContext
@dataclass(frozen=True)
class SessionLease:
tenant_id: str
cell_id: str
principal_id: str
session_id: str
class SessionPool:
"""Tracks active leases without creating a second session authority store."""
def __init__(self, router: TenantRouter) -> None:
self._router = router
self._leases: dict[tuple[str, str], SessionLease] = {}
self._lock = RLock()
@staticmethod
def _assert_route(context: TenantContext, route: Route) -> None:
if (
route.tenant_id != context.tenant_id
or route.cell_id != context.cell_id
or route.principal_id != context.principal_id
or route.session_id != context.session_id
):
raise ScopeError("session lease does not match authoritative route")
def assert_available(self, context: TenantContext, route: Route) -> None:
"""Re-resolve the context from the router before a ledger mutation."""
self._assert_route(context, route)
self._assert_route(context, self._router.assert_context_route(context))
def acquire(self, context: TenantContext, route: Route) -> SessionLease:
self._assert_route(context, route)
lease = SessionLease(
tenant_id=context.tenant_id,
cell_id=context.cell_id,
principal_id=context.principal_id,
session_id=context.session_id,
)
with self._lock:
return self._leases.setdefault((lease.tenant_id, lease.session_id), lease)
def release(self, lease: SessionLease) -> None:
with self._lock:
self._leases.pop((lease.tenant_id, lease.session_id), None)
def active_count(self) -> int:
with self._lock:
return len(self._leases)
@@ -0,0 +1,316 @@
"""Signed tenant context and canonical message contract for AIOS V2R1."""
from __future__ import annotations
import base64
from dataclasses import asdict, dataclass
from datetime import datetime, timedelta, timezone
import hashlib
import hmac
import json
import re
import secrets
from typing import Any, Mapping
VERSION = "V2R1C0"
MAX_SAFE_INTEGER = 9_007_199_254_740_991
TENANT_RE = re.compile(r"^[a-z0-9](?:[a-z0-9-]{0,38}[a-z0-9])?$")
IDENT_RE = re.compile(r"^[A-Za-z0-9](?:[A-Za-z0-9._:@-]{0,126}[A-Za-z0-9])?$")
class V2R1Error(RuntimeError):
pass
class ValidationError(V2R1Error):
pass
class ScopeError(V2R1Error):
pass
class ConflictError(V2R1Error):
pass
def utc_now() -> datetime:
return datetime.now(timezone.utc)
def isoformat(value: datetime | None = None) -> str:
return (value or utc_now()).astimezone(timezone.utc).isoformat()
def parse_time(value: str) -> datetime:
if not isinstance(value, str) or not value.strip():
raise ValidationError("timestamp must be a non-empty string")
text = value.strip()
if text.endswith("Z"):
text = text[:-1] + "+00:00"
try:
parsed = datetime.fromisoformat(text)
except ValueError as exc:
raise ValidationError(f"invalid timestamp: {value!r}") from exc
if parsed.tzinfo is None:
raise ValidationError("timestamp must include timezone")
return parsed.astimezone(timezone.utc)
def require_ident(name: str, value: Any, *, tenant: bool = False) -> str:
if not isinstance(value, str):
raise ValidationError(f"{name} must be a string")
value = value.strip()
pattern = TENANT_RE if tenant else IDENT_RE
if not pattern.fullmatch(value):
raise ValidationError(f"invalid {name}: {value!r}")
return value
def normalize_message_id(value: Any, *, field_name: str = "message_id") -> str:
if isinstance(value, bool):
raise ValidationError(f"{field_name} cannot be boolean")
if isinstance(value, str):
value = value.strip()
if not value or len(value) > 256 or any(ord(ch) < 32 for ch in value):
raise ValidationError(f"invalid {field_name}")
return value
if isinstance(value, int):
if abs(value) > MAX_SAFE_INTEGER:
raise ValidationError(f"{field_name} is an unsafe numeric ID")
return str(value)
raise ValidationError(f"{field_name} must be a lossless string or safe integer")
def canonical_json(value: Any) -> bytes:
return json.dumps(
value, ensure_ascii=False, separators=(",", ":"), sort_keys=True
).encode("utf-8")
def _b64(data: bytes) -> str:
return base64.urlsafe_b64encode(data).rstrip(b"=").decode("ascii")
def _unb64(value: str) -> bytes:
return base64.urlsafe_b64decode(value + "=" * (-len(value) % 4))
@dataclass(frozen=True)
class TenantContext:
tenant_id: str
cell_id: str
principal_id: str
principal_type: str
session_id: str
task_id: str | None
channel: str
channel_account_id: str
issued_at: str
expires_at: str
nonce: str
def __post_init__(self) -> None:
require_ident("tenant_id", self.tenant_id, tenant=True)
for name in (
"cell_id", "principal_id", "principal_type", "session_id",
"channel", "channel_account_id", "nonce",
):
require_ident(name, getattr(self, name))
if self.task_id is not None:
require_ident("task_id", self.task_id)
issued = parse_time(self.issued_at)
expires = parse_time(self.expires_at)
if expires <= issued or expires - issued > timedelta(hours=1):
raise ValidationError("invalid tenant context lifetime")
@classmethod
def issue(cls, *, lifetime_seconds: int = 300, now: datetime | None = None, **scope: Any) -> "TenantContext":
if not 1 <= lifetime_seconds <= 3600:
raise ValidationError("lifetime_seconds must be between 1 and 3600")
current = (now or utc_now()).astimezone(timezone.utc)
return cls(
**scope,
issued_at=isoformat(current),
expires_at=isoformat(current + timedelta(seconds=lifetime_seconds)),
nonce=secrets.token_hex(16),
)
def sign(self, key: bytes) -> str:
if len(key) < 32:
raise ValidationError("signing key must be at least 32 bytes")
payload = _b64(canonical_json(asdict(self)))
signature = _b64(hmac.new(key, payload.encode("ascii"), hashlib.sha256).digest())
return f"{payload}.{signature}"
@classmethod
def verify(
cls,
token: str,
key: bytes,
*,
now: datetime | None = None,
expected_tenant_id: str | None = None,
expected_cell_id: str | None = None,
) -> "TenantContext":
if len(key) < 32:
raise ValidationError("signing key must be at least 32 bytes")
try:
payload, encoded_signature = token.split(".", 1)
actual = _unb64(encoded_signature)
if encoded_signature != _b64(actual):
raise ValidationError("non-canonical tenant context signature")
data = json.loads(_unb64(payload))
except Exception as exc:
raise ValidationError("malformed tenant context token") from exc
expected = hmac.new(key, payload.encode("ascii"), hashlib.sha256).digest()
if not hmac.compare_digest(actual, expected):
raise ValidationError("tenant context signature mismatch")
context = cls(**data)
current = (now or utc_now()).astimezone(timezone.utc)
if current < parse_time(context.issued_at) - timedelta(seconds=60):
raise ValidationError("tenant context issued in future")
if current >= parse_time(context.expires_at):
raise ValidationError("tenant context expired")
if expected_tenant_id and context.tenant_id != expected_tenant_id:
raise ScopeError("tenant mismatch")
if expected_cell_id and context.cell_id != expected_cell_id:
raise ScopeError("cell mismatch")
return context
@dataclass(frozen=True)
class CanonicalMessage:
tenant_id: str
cell_id: str
principal_id: str
principal_type: str
origin_type: str
channel: str
channel_account_id: str
peer_id: str
conversation_id: str
session_id: str
task_id: str | None
event_id: str
message_id: str
reply_to_message_id: str | None
direction: str
command_capable: bool
occurred_at: str
received_at: str
body: str
quoted_body: str | None
adapter_name: str
adapter_version: str
schema_version: str = "aios.message.v1"
def __post_init__(self) -> None:
if self.schema_version != "aios.message.v1":
raise ValidationError("unsupported message schema version")
require_ident("tenant_id", self.tenant_id, tenant=True)
for name in (
"cell_id", "principal_id", "principal_type", "origin_type", "channel",
"channel_account_id", "peer_id", "conversation_id", "session_id",
"event_id", "adapter_name", "adapter_version",
):
require_ident(name, getattr(self, name))
if self.task_id is not None:
require_ident("task_id", self.task_id)
normalize_message_id(self.message_id)
if self.reply_to_message_id is not None:
normalize_message_id(self.reply_to_message_id, field_name="reply_to_message_id")
if self.direction not in {"inbound", "outbound", "internal"}:
raise ValidationError("invalid direction")
if not isinstance(self.command_capable, bool):
raise ValidationError("command_capable must be boolean")
parse_time(self.occurred_at)
parse_time(self.received_at)
if not isinstance(self.body, str):
raise ValidationError("body must be a string")
if self.quoted_body is not None and not isinstance(self.quoted_body, str):
raise ValidationError("quoted_body must be a string or null")
@classmethod
def from_mapping(cls, data: Mapping[str, Any]) -> "CanonicalMessage":
content = data.get("content") or {}
adapter = data.get("adapter") or {}
if not isinstance(content, Mapping) or not isinstance(adapter, Mapping):
raise ValidationError("content and adapter must be objects")
values = dict(data)
return cls(
schema_version=values.get("schema_version", "aios.message.v1"),
tenant_id=values["tenant_id"],
cell_id=values["cell_id"],
principal_id=values["principal_id"],
principal_type=values["principal_type"],
origin_type=values["origin_type"],
channel=values["channel"],
channel_account_id=values["channel_account_id"],
peer_id=values["peer_id"],
conversation_id=values["conversation_id"],
session_id=values["session_id"],
task_id=values.get("task_id"),
event_id=values["event_id"],
message_id=normalize_message_id(values["message_id"]),
reply_to_message_id=(
normalize_message_id(values["reply_to_message_id"], field_name="reply_to_message_id")
if values.get("reply_to_message_id") is not None else None
),
direction=values["direction"],
command_capable=values["command_capable"],
occurred_at=values["occurred_at"],
received_at=values["received_at"],
body=content.get("body", ""),
quoted_body=content.get("quoted_body"),
adapter_name=adapter["name"],
adapter_version=adapter["version"],
)
def assert_context(self, context: TenantContext) -> None:
fields = (
"tenant_id", "cell_id", "principal_id", "session_id", "task_id",
"channel", "channel_account_id",
)
mismatches = [name for name in fields if getattr(self, name) != getattr(context, name)]
if mismatches:
raise ScopeError("message/context mismatch: " + ", ".join(mismatches))
@property
def is_authenticated_human_command(self) -> bool:
return (
self.direction == "inbound"
and self.command_capable
and self.principal_type == "authenticated_user"
and self.origin_type == "channel_user"
)
@dataclass(frozen=True)
class PolicyDecision:
allowed: bool
approval_required: bool
code: str
reason: str
READ_ONLY_TOOLS = frozenset({
"read", "grep", "glob", "find", "ls", "web_search", "web_fetch",
"memory_search", "sessions_list", "sessions_history", "session_status",
})
def evaluate_tool_call(tool_name: str, message: CanonicalMessage) -> PolicyDecision:
normalized = tool_name.strip().lower() if isinstance(tool_name, str) else ""
if not normalized:
return PolicyDecision(False, False, "invalid_tool", "tool name missing")
if normalized in READ_ONLY_TOOLS:
return PolicyDecision(True, False, "read_only", "read-only operation")
if not message.is_authenticated_human_command:
return PolicyDecision(
False, False, "origin_denied",
"side effects require an authenticated current human command",
)
return PolicyDecision(
True, True, "approval_required",
"authenticated human side effect requires explicit approval",
)
+17
View File
@@ -0,0 +1,17 @@
[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"
[project]
name = "aios-v2r1-runtime"
version = "2.1.0rc1"
description = "AIOS V2R1 canonical runtime package"
requires-python = ">=3.11"
dependencies = []
[project.scripts]
aios-cell = "aios_v2r1.cli:main"
[tool.setuptools]
package-dir = {"" = "app"}
packages = ["aios_v2r1"]
+18 -29
View File
@@ -1,8 +1,7 @@
<<<<<<< HEAD
# AIOS Agent Command Plane Registry
# Git is the single source of truth for all agent commands.
version: 1.0.0
created_at: 2026-07-08T15:20:00+08:00
created_at: "2026-07-08T15:20:00+08:00"
baseline: V1R3C1
commands:
@@ -12,6 +11,22 @@ commands:
completed_path: "agents/commands/completed/"
failed_path: "agents/commands/failed/"
directories:
commands/active: "New commands pending execution — Git is the only entry point"
commands/running: "Commands currently being executed by an agent"
commands/completed: "Commands that finished successfully — moved here on success"
commands/failed: "Commands that finished with errors — moved here on failure"
lifecycle:
new: active/
running: running/
success: completed/
failure: failed/
# Command lifecycle state machine:
# active/ → locked & moved to running/ → execute → success → completed/
# → failure → failed/
policies:
path: "agents/policies/"
source: "git"
@@ -38,30 +53,4 @@ audit:
agent_runs: "audit/agent-runs/"
version_history: "audit/version-history/"
command_history: "audit/command-history/"
=======
# AIOS Agent Command Registry
# Git is the single source of truth for all agent commands.
registry_version: 1.0.0
created_at: "2026-07-08T15:44:00+08:00"
baseline: V1R3C1
directories:
commands/active: "New commands pending execution — Git is the only entry point"
commands/running: "Commands currently being executed by an agent"
commands/completed: "Commands that finished successfully — moved here on success"
commands/failed: "Commands that finished with errors — moved here on failure"
state: agents/state/
policies: agents/policies/
lifecycle:
new: active/
running: running/
success: completed/
failure: failed/
# Command lifecycle state machine:
# active/ → locked & moved to running/ → execute → success → completed/
# → failure → failed/
>>>>>>> 4d18ee0 (feat(cmd): enable Agent Command Plane, audit plane, and Web UI dashboard)
interaction_history: "audit/interaction-history/"
-17
View File
@@ -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
}
@@ -1,49 +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
}
}
+39
View File
@@ -0,0 +1,39 @@
# Personal Weixin v1 security contract
Status: normative design contract for R10 B6/B7. It authorizes no runtime or production change.
## Trust boundaries and ownership
The browser is untrusted. The Portal authenticates the human user and resolves tenant identity from the server session. The Portal adapter is least-privileged: it may request account-scoped operations but must not store provider credentials, tokens, raw iLink state, or OpenClaw protocol state. OpenClaw owns provider credentials and protocol state. The Gateway transport authenticator, not an event-body boolean or identity field, establishes whether an inbound event is authentic.
Every operation is keyed by server-resolved `(tenantId, accountId)`. Entitlements are allow-only, server-owned records. A default account is display preference, never authorization. The browser-visible `accountId` is an untrusted reference to a server-preallocated account slot: the server MUST resolve it through the authenticated user's tenant and current entitlement on list, readiness, login start, login wait, status, inbound challenge, canary, and rollback checks. Start and every wait poll re-run that resolution. Missing, arbitrary, stale, cross-tenant, or no-longer-entitled values fail closed before account existence or state is disclosed; there is no default/first/configured-account fallback.
## Login state and secret handling
`sessionKey` is a required, nonempty opaque value returned by OpenClaw. The adapter MUST forward its exact bytes unchanged. It MUST NOT trim, normalize, case-fold, derive, regenerate, alias, or substitute the value. A missing or empty `sessionKey` fails closed and MUST NOT fall back to `accountId` or any identifier. Durable state stores only a one-way session-key digest where correlation is required; raw `sessionKey` is not persisted.
`verifyCode` is accepted only as an authenticated, CSRF-protected wait POST test/input field, matches 4-8 decimal digits, is forwarded once, and is discarded. `challengeCode` is accepted only as an authenticated Gateway event test/input field, is compared through a one-way digest, and is discarded. Neither secret may be persisted in raw form or appear in URLs, responses, logs, traces, metrics labels, analytics, audit payloads, exceptions, or background-job arguments. Golden fixtures containing these values are synthetic test vectors only and MUST NOT be copied into production telemetry or responses.
QR data URLs are transient no-store response data with a 1 MiB bound and MUST NOT be logged or persisted. Canonical login outcomes are `qr_pending`, `need_verifycode`, `invalid_verifycode`, `expired`, `failed`, `already_connected`, and `confirmed`. Any unknown upstream status maps fail-closed to canonical `failed` with `errorCode=unknown_upstream_status`; raw unknown status is bounded evidence only. Upstream `binded_redirect` maps only to `already_connected` with `connected=false`, `alreadyConnected=true`, and `terminal=true`, never to `confirmed`.
## Canonical readiness
Readiness is one live, authenticated snapshot from the Gateway/OpenClaw boundary with one unified response shape for `ready`, `not_ready`, and `error`. It MUST include Gateway reachability/error, exact plugin id/version/digest, selected account identity, configured/enabled/running/last-error state, current tenant/account entitlement, reasons, observation time, and freshness deadline. `ready=true` is legal only when every required field is present, the snapshot is still fresh, expected plugin version/digest match, the selected account is entitled/configured/enabled/running with null error, and the Gateway is reachable. Missing fields, an old snapshot, digest mismatch, no entitlement, not-running state, unauthenticated evidence, or any contradiction returns `ready=false` with `code=not_ready` or `code=error` and at least one stable reason. Cached, synthetic, file-only, default-account, or service-up-only evidence cannot produce ready.
## Authenticated inbound-event challenge
The event body contains exactly `eventId`, `accountId`, `senderId`, `chatId`, `challengeCode`, and `observedAt`. It does not and cannot assert authentication, tenant id, Portal user id, or session key. Those values are absent by contract. Transport authentication MUST cover HTTP method, path, timestamp header, nonce header, and raw body digest; enforce a bounded clock window; durably reserve nonce/event replay keys for at least that window; compare signatures in constant time; and complete before body values reach logs or mutable business state.
After transport authentication, the server hashes the ephemeral `challengeCode` and resolves the pending durable challenge. That server-created record already owns tenant id, Portal user id, entitled account id, session-key digest, issued/expiry/consumed times, and state (`issued`, `consumed`, or `expired`). The body `accountId` must exactly match the record and current entitlement; it never supplies tenant/user/session authority. The first valid authenticated event atomically binds its provider `senderId` and `chatId`.
Issuance and consumption MUST run in a database transaction with row locking or an equivalent compare-and-swap primitive. `issued -> consumed` is single-use and atomic. An exact replay of the same authenticated event is idempotent. A changed event payload, sender, chat, account, durable tenant/user/account/session binding, expired or already-consumed record, duplicate event with different payload, missing entitlement, or unauthenticated transport fails closed with zero mutation. Raw challenge codes and raw session keys are never stored.
## Unsupported unbind
End-to-end unbind is unsupported in R10. Every public or internal unbind entry point MUST return the exact schema response with HTTP 501, `ok=false`, `supported=false`, `code=unbind_not_supported`, and `mutationCount=0`. The 501 decision occurs before token deletion, account update, session or challenge mutation, Gateway/OpenClaw call, business-state audit mutation, or background-job enqueue.
## Web, canary, and rollback controls
Only exact B6/B7 allowlisted paths in the R10 amendment may change. Portal endpoints require authenticated Django sessions, CSRF protection for mutations, server-scoped object lookup, IDOR tests, rate limits, request-size limits, `Cache-Control: no-store`, and structured redaction of session keys, verification codes, challenge codes, QR data, tokens, and provider payloads. Stable public errors never expose upstream bodies or cross-tenant existence.
The canary uses one explicitly entitled tenant/account pair and proves restart, concurrent waits, atomic challenge consumption, exact replay, altered replay denial, cross-tenant denial, all canonical statuses/readiness shapes, and zero-mutation 501 behavior. Promotion requires byte-identical artifacts and digests from the verified canary. Rollback restores the immediately preceding byte-identical artifacts/configuration and re-runs canonical readiness; database rollback is forbidden unless an explicitly approved manifest proves backward incompatibility and supplies a separate recovery plan.
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"tenant.account.entitlement","tenantId":"tenant-canary","accountId":"account-canary","effect":"allow","policyVersion":"policy-v1","issuedAtMs":1784068000000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"personal.weixin.readiness","tenantId":"tenant-canary","selectedAccountId":"account-canary","gateway":{"reachable":true,"errorCode":null},"plugin":{"id":"openclaw-weixin","loaded":true,"version":"2.4.6","digestSha256":"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"},"accounts":[{"accountId":"account-canary","name":"Canary Personal Weixin","configured":true,"enabled":true,"running":true,"lastError":null,"isDefault":false,"entitled":true}],"ready":true,"code":"ready","reasons":[],"observedAtMs":1784068060000,"freshUntilMs":1784068120000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"personal.weixin.readiness","tenantId":"tenant-canary","selectedAccountId":"account-canary","gateway":{"reachable":true,"errorCode":null},"plugin":{"id":"openclaw-weixin","loaded":true,"version":"2.4.6","digestSha256":null},"accounts":[{"accountId":"account-canary","name":"Canary Personal Weixin","configured":true,"enabled":true,"running":true,"lastError":null,"isDefault":false,"entitled":true}],"ready":false,"code":"not_ready","reasons":[{"code":"field_missing","field":"plugin.digestSha256"}],"observedAtMs":1784068060000,"freshUntilMs":1784068120000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"personal.weixin.readiness","tenantId":"tenant-canary","selectedAccountId":"account-canary","gateway":{"reachable":true,"errorCode":null},"plugin":{"id":"openclaw-weixin","loaded":true,"version":"2.4.6","digestSha256":"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"},"accounts":[{"accountId":"account-canary","name":"Canary Personal Weixin","configured":true,"enabled":true,"running":true,"lastError":null,"isDefault":false,"entitled":true}],"ready":false,"code":"not_ready","reasons":[{"code":"snapshot_stale","field":"freshUntilMs"}],"observedAtMs":1784060000000,"freshUntilMs":1784060060000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"personal.weixin.readiness","tenantId":"tenant-canary","selectedAccountId":"account-canary","gateway":{"reachable":true,"errorCode":null},"plugin":{"id":"openclaw-weixin","loaded":true,"version":"2.4.6","digestSha256":"bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"},"accounts":[{"accountId":"account-canary","name":"Canary Personal Weixin","configured":true,"enabled":true,"running":true,"lastError":null,"isDefault":false,"entitled":true}],"ready":false,"code":"not_ready","reasons":[{"code":"plugin_digest_mismatch","field":"plugin.digestSha256"}],"observedAtMs":1784068060000,"freshUntilMs":1784068120000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"personal.weixin.readiness","tenantId":"tenant-canary","selectedAccountId":"account-canary","gateway":{"reachable":true,"errorCode":null},"plugin":{"id":"openclaw-weixin","loaded":true,"version":"2.4.6","digestSha256":"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"},"accounts":[{"accountId":"account-canary","name":"Canary Personal Weixin","configured":true,"enabled":true,"running":true,"lastError":null,"isDefault":false,"entitled":false}],"ready":false,"code":"not_ready","reasons":[{"code":"account_not_entitled","field":"accounts[0].entitled"}],"observedAtMs":1784068060000,"freshUntilMs":1784068120000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"personal.weixin.readiness","tenantId":"tenant-canary","selectedAccountId":"account-canary","gateway":{"reachable":true,"errorCode":null},"plugin":{"id":"openclaw-weixin","loaded":true,"version":"2.4.6","digestSha256":"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"},"accounts":[{"accountId":"account-canary","name":"Canary Personal Weixin","configured":true,"enabled":true,"running":false,"lastError":"plugin_not_running","isDefault":false,"entitled":true}],"ready":false,"code":"not_ready","reasons":[{"code":"account_not_running","field":"accounts[0].running"}],"observedAtMs":1784068060000,"freshUntilMs":1784068120000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"personal.weixin.readiness","tenantId":"tenant-canary","selectedAccountId":"account-canary","gateway":{"reachable":false,"errorCode":"gateway_unreachable"},"plugin":{"id":"openclaw-weixin","loaded":false,"version":null,"digestSha256":null},"accounts":[{"accountId":"account-canary","name":"Canary Personal Weixin","configured":true,"enabled":true,"running":false,"lastError":"gateway_unreachable","isDefault":false,"entitled":true}],"ready":false,"code":"error","reasons":[{"code":"gateway_error","field":"gateway.reachable"}],"observedAtMs":1784068060000,"freshUntilMs":1784068060000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.start.request","accountId":"account-canary","force":false,"timeoutMs":30000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.wait.request","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","verifyCode":"4321","currentQrDataUrl":"data:image/png;base64,iVBORw0KGgo=","timeoutMs":30000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"qr_pending","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":false,"alreadyConnected":false,"terminal":false,"needsVerifyCode":false,"qrDataUrl":"data:image/png;base64,iVBORw0KGgo="}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"need_verifycode","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":false,"alreadyConnected":false,"terminal":false,"needsVerifyCode":true}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"invalid_verifycode","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":false,"alreadyConnected":false,"terminal":false,"needsVerifyCode":true,"errorCode":"invalid_verifycode"}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"expired","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":false,"alreadyConnected":false,"terminal":true,"needsVerifyCode":false,"errorCode":"login_expired"}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"failed","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":false,"alreadyConnected":false,"terminal":true,"needsVerifyCode":false,"errorCode":"upstream_failed"}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"already_connected","upstreamStatus":"binded_redirect","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":false,"alreadyConnected":true,"terminal":true,"needsVerifyCode":false}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"confirmed","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":true,"alreadyConnected":false,"terminal":true,"needsVerifyCode":false,"userId":"sender-canary"}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.login.result","status":"failed","upstreamStatus":"future_unknown_state","accountId":"account-canary","sessionKey":"weixin-session-20260715-A1","connected":false,"alreadyConnected":false,"terminal":true,"needsVerifyCode":false,"errorCode":"unknown_upstream_status"}
@@ -0,0 +1 @@
{"eventId":"event-20260715-A1","accountId":"account-canary","senderId":"sender-canary","chatId":"chat-canary","challengeCode":"A1B2C3D4","observedAt":1784068120000}
@@ -0,0 +1 @@
{"schemaVersion":"aios.personal-weixin.golden.v1","kind":"web.unbind.result","httpStatus":501,"ok":false,"supported":false,"code":"unbind_not_supported","mutationCount":0}
@@ -0,0 +1,986 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://aios.imruyi.top/contracts/personal-weixin/v1/golden-contract.schema.json",
"title": "AIOS Personal Weixin Golden Contract v1",
"oneOf": [
{
"$ref": "#/$defs/entitlement"
},
{
"$ref": "#/$defs/readiness"
},
{
"$ref": "#/$defs/startRequest"
},
{
"$ref": "#/$defs/waitRequest"
},
{
"$ref": "#/$defs/loginResult"
},
{
"$ref": "#/$defs/inboundEvent"
},
{
"$ref": "#/$defs/unbindResult"
}
],
"$defs": {
"identifier": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"pattern": "^[A-Za-z0-9._~:@-]+$"
},
"sessionKey": {
"type": "string",
"minLength": 1,
"maxLength": 256,
"pattern": "^[A-Za-z0-9._~:-]+$"
},
"schemaVersion": {
"const": "aios.personal-weixin.golden.v1"
},
"entitlement": {
"type": "object",
"additionalProperties": false,
"required": [
"schemaVersion",
"kind",
"tenantId",
"accountId",
"effect",
"policyVersion",
"issuedAtMs"
],
"properties": {
"schemaVersion": {
"$ref": "#/$defs/schemaVersion"
},
"kind": {
"const": "tenant.account.entitlement"
},
"tenantId": {
"$ref": "#/$defs/identifier"
},
"accountId": {
"$ref": "#/$defs/identifier"
},
"effect": {
"const": "allow"
},
"policyVersion": {
"$ref": "#/$defs/identifier"
},
"issuedAtMs": {
"type": "integer",
"minimum": 0
}
}
},
"readinessReason": {
"type": "object",
"additionalProperties": false,
"required": [
"code",
"field"
],
"properties": {
"code": {
"enum": [
"field_missing",
"snapshot_stale",
"plugin_digest_mismatch",
"account_not_entitled",
"account_not_running",
"gateway_error"
]
},
"field": {
"type": "string",
"minLength": 1,
"maxLength": 128
}
}
},
"readiness": {
"type": "object",
"additionalProperties": false,
"required": [
"schemaVersion",
"kind",
"tenantId",
"selectedAccountId",
"gateway",
"plugin",
"accounts",
"ready",
"code",
"reasons",
"observedAtMs",
"freshUntilMs"
],
"properties": {
"schemaVersion": {
"$ref": "#/$defs/schemaVersion"
},
"kind": {
"const": "personal.weixin.readiness"
},
"tenantId": {
"$ref": "#/$defs/identifier"
},
"selectedAccountId": {
"$ref": "#/$defs/identifier"
},
"gateway": {
"type": "object",
"additionalProperties": false,
"required": [
"reachable",
"errorCode"
],
"properties": {
"reachable": {
"type": "boolean"
},
"errorCode": {
"type": [
"string",
"null"
],
"minLength": 1,
"maxLength": 128
}
}
},
"plugin": {
"type": "object",
"additionalProperties": false,
"required": [
"id",
"loaded",
"version",
"digestSha256"
],
"properties": {
"id": {
"const": "openclaw-weixin"
},
"loaded": {
"type": "boolean"
},
"version": {
"type": [
"string",
"null"
],
"minLength": 1,
"maxLength": 64
},
"digestSha256": {
"anyOf": [
{
"type": "string",
"pattern": "^[a-f0-9]{64}$"
},
{
"type": "null"
}
]
}
}
},
"accounts": {
"type": "array",
"minItems": 1,
"maxItems": 100,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"accountId",
"name",
"configured",
"enabled",
"running",
"lastError",
"isDefault",
"entitled"
],
"properties": {
"accountId": {
"$ref": "#/$defs/identifier"
},
"name": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"configured": {
"type": "boolean"
},
"enabled": {
"type": "boolean"
},
"running": {
"type": "boolean"
},
"lastError": {
"type": [
"string",
"null"
],
"minLength": 1,
"maxLength": 256
},
"isDefault": {
"type": "boolean"
},
"entitled": {
"type": "boolean"
}
}
}
},
"ready": {
"type": "boolean"
},
"code": {
"enum": [
"ready",
"not_ready",
"error"
]
},
"reasons": {
"type": "array",
"maxItems": 32,
"items": {
"$ref": "#/$defs/readinessReason"
}
},
"observedAtMs": {
"type": "integer",
"minimum": 0
},
"freshUntilMs": {
"type": "integer",
"minimum": 0
}
},
"allOf": [
{
"if": {
"properties": {
"ready": {
"const": true
}
},
"required": [
"ready"
]
},
"then": {
"properties": {
"code": {
"const": "ready"
},
"reasons": {
"maxItems": 0
},
"gateway": {
"properties": {
"reachable": {
"const": true
},
"errorCode": {
"const": null
}
}
},
"plugin": {
"properties": {
"loaded": {
"const": true
},
"version": {
"type": "string"
},
"digestSha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
}
},
"accounts": {
"items": {
"properties": {
"configured": {
"const": true
},
"enabled": {
"const": true
},
"running": {
"const": true
},
"lastError": {
"const": null
},
"entitled": {
"const": true
}
}
}
}
}
},
"else": {
"properties": {
"code": {
"enum": [
"not_ready",
"error"
]
},
"reasons": {
"minItems": 1
}
}
}
}
]
},
"startRequest": {
"type": "object",
"additionalProperties": false,
"required": [
"schemaVersion",
"kind",
"accountId",
"force",
"timeoutMs"
],
"properties": {
"schemaVersion": {
"$ref": "#/$defs/schemaVersion"
},
"kind": {
"const": "web.login.start.request"
},
"accountId": {
"$ref": "#/$defs/identifier"
},
"force": {
"const": false
},
"timeoutMs": {
"type": "integer",
"minimum": 1000,
"maximum": 120000
}
}
},
"waitRequest": {
"type": "object",
"additionalProperties": false,
"required": [
"schemaVersion",
"kind",
"accountId",
"sessionKey",
"timeoutMs"
],
"properties": {
"schemaVersion": {
"$ref": "#/$defs/schemaVersion"
},
"kind": {
"const": "web.login.wait.request"
},
"accountId": {
"$ref": "#/$defs/identifier"
},
"sessionKey": {
"$ref": "#/$defs/sessionKey"
},
"verifyCode": {
"type": "string",
"pattern": "^[0-9]{4,8}$"
},
"currentQrDataUrl": {
"type": "string",
"minLength": 1,
"maxLength": 1048576,
"pattern": "^data:image/png;base64,"
},
"timeoutMs": {
"type": "integer",
"minimum": 1000,
"maximum": 120000
}
}
},
"loginResult": {
"type": "object",
"additionalProperties": false,
"required": [
"schemaVersion",
"kind",
"status",
"accountId",
"sessionKey",
"connected",
"alreadyConnected",
"terminal",
"needsVerifyCode"
],
"properties": {
"schemaVersion": {
"$ref": "#/$defs/schemaVersion"
},
"kind": {
"const": "web.login.result"
},
"status": {
"enum": [
"qr_pending",
"need_verifycode",
"invalid_verifycode",
"expired",
"failed",
"already_connected",
"confirmed"
]
},
"accountId": {
"$ref": "#/$defs/identifier"
},
"sessionKey": {
"$ref": "#/$defs/sessionKey"
},
"connected": {
"type": "boolean"
},
"alreadyConnected": {
"type": "boolean"
},
"terminal": {
"type": "boolean"
},
"needsVerifyCode": {
"type": "boolean"
},
"qrDataUrl": {
"type": "string",
"minLength": 1,
"maxLength": 1048576,
"pattern": "^data:image/png;base64,"
},
"userId": {
"$ref": "#/$defs/identifier"
},
"errorCode": {
"enum": [
"invalid_verifycode",
"login_expired",
"upstream_failed",
"unknown_upstream_status"
]
},
"upstreamStatus": {
"type": "string",
"minLength": 1,
"maxLength": 128
}
},
"allOf": [
{
"if": {
"properties": {
"status": {
"const": "qr_pending"
}
}
},
"then": {
"required": [
"qrDataUrl"
],
"properties": {
"connected": {
"const": false
},
"alreadyConnected": {
"const": false
},
"terminal": {
"const": false
},
"needsVerifyCode": {
"const": false
}
},
"not": {
"anyOf": [
{
"required": [
"userId"
]
},
{
"required": [
"errorCode"
]
},
{
"required": [
"upstreamStatus"
]
}
]
}
}
},
{
"if": {
"properties": {
"status": {
"const": "need_verifycode"
}
}
},
"then": {
"properties": {
"connected": {
"const": false
},
"alreadyConnected": {
"const": false
},
"terminal": {
"const": false
},
"needsVerifyCode": {
"const": true
}
},
"not": {
"anyOf": [
{
"required": [
"qrDataUrl"
]
},
{
"required": [
"userId"
]
},
{
"required": [
"errorCode"
]
},
{
"required": [
"upstreamStatus"
]
}
]
}
}
},
{
"if": {
"properties": {
"status": {
"const": "invalid_verifycode"
}
}
},
"then": {
"required": [
"errorCode"
],
"properties": {
"errorCode": {
"const": "invalid_verifycode"
},
"connected": {
"const": false
},
"alreadyConnected": {
"const": false
},
"terminal": {
"const": false
},
"needsVerifyCode": {
"const": true
}
},
"not": {
"anyOf": [
{
"required": [
"qrDataUrl"
]
},
{
"required": [
"userId"
]
},
{
"required": [
"upstreamStatus"
]
}
]
}
}
},
{
"if": {
"properties": {
"status": {
"const": "expired"
}
}
},
"then": {
"required": [
"errorCode"
],
"properties": {
"errorCode": {
"const": "login_expired"
},
"connected": {
"const": false
},
"alreadyConnected": {
"const": false
},
"terminal": {
"const": true
},
"needsVerifyCode": {
"const": false
}
},
"not": {
"anyOf": [
{
"required": [
"qrDataUrl"
]
},
{
"required": [
"userId"
]
},
{
"required": [
"upstreamStatus"
]
}
]
}
}
},
{
"if": {
"properties": {
"status": {
"const": "failed"
}
}
},
"then": {
"required": [
"errorCode"
],
"properties": {
"connected": {
"const": false
},
"alreadyConnected": {
"const": false
},
"terminal": {
"const": true
},
"needsVerifyCode": {
"const": false
}
},
"not": {
"anyOf": [
{
"required": [
"qrDataUrl"
]
},
{
"required": [
"userId"
]
}
]
}
}
},
{
"if": {
"required": [
"upstreamStatus"
],
"properties": {
"status": {
"const": "failed"
}
}
},
"then": {
"properties": {
"errorCode": {
"const": "unknown_upstream_status"
}
},
"not": {
"anyOf": [
{
"required": [
"qrDataUrl"
]
},
{
"required": [
"userId"
]
}
]
}
}
},
{
"if": {
"required": [
"status",
"errorCode"
],
"properties": {
"status": {
"const": "failed"
},
"errorCode": {
"const": "unknown_upstream_status"
}
}
},
"then": {
"required": [
"upstreamStatus"
]
}
},
{
"if": {
"required": [
"status",
"errorCode"
],
"properties": {
"status": {
"const": "failed"
},
"errorCode": {
"const": "upstream_failed"
}
}
},
"then": {
"not": {
"required": [
"upstreamStatus"
]
}
}
},
{
"if": {
"properties": {
"status": {
"const": "already_connected"
}
}
},
"then": {
"required": [
"upstreamStatus"
],
"properties": {
"upstreamStatus": {
"const": "binded_redirect"
},
"connected": {
"const": false
},
"alreadyConnected": {
"const": true
},
"terminal": {
"const": true
},
"needsVerifyCode": {
"const": false
}
},
"not": {
"anyOf": [
{
"required": [
"qrDataUrl"
]
},
{
"required": [
"userId"
]
},
{
"required": [
"errorCode"
]
}
]
}
}
},
{
"if": {
"properties": {
"status": {
"const": "confirmed"
}
}
},
"then": {
"required": [
"userId"
],
"properties": {
"connected": {
"const": true
},
"alreadyConnected": {
"const": false
},
"terminal": {
"const": true
},
"needsVerifyCode": {
"const": false
}
},
"not": {
"anyOf": [
{
"required": [
"qrDataUrl"
]
},
{
"required": [
"errorCode"
]
},
{
"required": [
"upstreamStatus"
]
}
]
}
}
}
]
},
"inboundEvent": {
"type": "object",
"additionalProperties": false,
"required": [
"eventId",
"accountId",
"senderId",
"chatId",
"challengeCode",
"observedAt"
],
"properties": {
"eventId": {
"$ref": "#/$defs/identifier"
},
"accountId": {
"$ref": "#/$defs/identifier"
},
"senderId": {
"$ref": "#/$defs/identifier"
},
"chatId": {
"$ref": "#/$defs/identifier"
},
"challengeCode": {
"type": "string",
"minLength": 6,
"maxLength": 64,
"pattern": "^[A-Z0-9]+$"
},
"observedAt": {
"type": "integer",
"minimum": 0
}
}
},
"unbindResult": {
"type": "object",
"additionalProperties": false,
"required": [
"schemaVersion",
"kind",
"httpStatus",
"ok",
"supported",
"code",
"mutationCount"
],
"properties": {
"schemaVersion": {
"$ref": "#/$defs/schemaVersion"
},
"kind": {
"const": "web.unbind.result"
},
"httpStatus": {
"const": 501
},
"ok": {
"const": false
},
"supported": {
"const": false
},
"code": {
"const": "unbind_not_supported"
},
"mutationCount": {
"const": 0
}
}
}
}
}
Binary file not shown.
+20
View File
@@ -0,0 +1,20 @@
#!/usr/bin/env bash
set -euo pipefail
printf 'AIOS V2R1C0 RC1 health check\n'
python3 - <<'PY'
from pathlib import Path
required = [
'active-runtime/app/aios_v2r1/tenant_context.py',
'active-runtime/app/aios_v2r1/router.py',
'active-runtime/app/aios_v2r1/hermes_fabric.py',
'openclaw/plugins/aios-tenant-boundary/openclaw.plugin.json',
]
missing=[p for p in required if not Path(p).exists()]
if missing:
raise SystemExit('missing: '+','.join(missing))
print('artifact presence PASS')
PY
echo 'runtime health requires OpenClaw environment probe'
+29
View File
@@ -0,0 +1,29 @@
#!/usr/bin/env bash
set -euo pipefail
ROOT=$(cd "$(dirname "$0")/../.." && pwd)
EXPECTED_BRANCH="release/v2r1c0-tenant-cell-fabric-20260712"
if [[ "$(git -C "$ROOT" branch --show-current)" != "$EXPECTED_BRANCH" ]]; then
echo "wrong release branch"
exit 1
fi
COMMIT=$(git -C "$ROOT" rev-parse HEAD)
echo "Installing AIOS V2R1C0 RC1 commit=$COMMIT"
python3 - <<'PY'
import compileall
if not compileall.compile_dir('active-runtime/app/aios_v2r1', quiet=1):
raise SystemExit(1)
print('python compile PASS')
PY
if [[ -f openclaw/plugins/aios-tenant-boundary/package.json ]]; then
echo "plugin package PASS"
else
echo "plugin package missing"
exit 1
fi
echo "Installation preflight PASS"
+27
View File
@@ -0,0 +1,27 @@
#!/usr/bin/env bash
set -euo pipefail
MODE=${1:---check}
case "$MODE" in
--check)
echo "V2R1C0 RC1 validation mode"
;;
--install)
echo "Install requires approved OpenClaw Cell target"
;;
--rollback)
echo "Rollback requires recorded Cell backup"
;;
*)
echo "Usage: $0 [--check|--install|--rollback]"
exit 2
;;
esac
python3 - <<'PY'
import compileall
raise SystemExit(0 if compileall.compile_dir('active-runtime/app/aios_v2r1', quiet=1) else 1)
PY
echo "python runtime syntax: PASS"
+41 -52
View File
@@ -1,4 +1,3 @@
<<<<<<< HEAD
# AIOS Agent Audit Plane Architecture
## Overview
@@ -25,9 +24,10 @@ Agent Command Plane (agents/commands/)
+---> Audit
| |
| v
| audit/agent-runs/ (per-agent log)
| audit/command-history/ (per-command log)
| audit/version-history/ (per-baseline log)
| audit/agent-runs/ (per-agent log)
| audit/command-history/ (per-command log)
| audit/version-history/ (per-baseline log)
| audit/interaction-history/ (agent conversation traces)
|
+---> Git Commit
|
@@ -45,8 +45,39 @@ Agent Command Plane (agents/commands/)
5. Git commit locks the audit record
6. Web UI displays timeline from git history
## Directory Structure
```
audit/
├── agent-runs/ # Per-execution records (JSON)
├── command-history/ # Command lifecycle history
├── version-history/ # Version/baseline change log
└── interaction-history/ # Agent conversation traces
```
## Audit Record Schema
Current agent-run records use the following fields:
| Field | Description |
|-------|-------------|
| agent_run_id | Unique execution ID |
| command | Command file name |
| agent | Executing agent name |
| version | Baseline version at execution time |
| objective | Human-readable goal |
| start_time | ISO-8601 start timestamp |
| end_time | ISO-8601 completion timestamp |
| interaction_count | Agent-owner interaction turns |
| tool_call_count | Tool invocations during execution |
| changed_files | Files modified in this run |
| commit_sha | Git commit hash |
| test_result | Test verification outcome |
| final_result | SUCCESS / FAILED / PARTIAL |
| evidence_path | Link to evidence directory |
Legacy records remain valid and may use the following compatibility shape:
```json
{
"id": "",
@@ -72,51 +103,6 @@ Agent Command Plane (agents/commands/)
- Every code change must be traceable to who/what agent created it
- No agent-created changes without audit trail
## Related
- [Agent Command Plane](../agents/README.md)
- [Baseline System](baseline-system.md)
=======
# AIOS Agent Audit Plane
## Purpose
Every agent action is recorded. All code changes are traceable to:
- Who made the change
- Why the change was made
- When it was made
- Which version introduced it
- What test results showed
## Directory Structure
```
audit/
├── agent-runs/ # Per-execution records (JSON)
├── command-history/ # Command lifecycle history
├── version-history/ # Version/baseline change log
└── interaction-history/ # Agent conversation traces
```
## Agent Run Record
| Field | Description |
|-------|-------------|
| agent_run_id | Unique execution ID |
| command | Command file name |
| agent | Executing agent name |
| version | Baseline version at execution time |
| objective | Human-readable goal |
| start_time | ISO-8601 start timestamp |
| end_time | ISO-8601 completion timestamp |
| interaction_count | Agent-owner interaction turns |
| tool_call_count | Tool invocations during execution |
| changed_files | Files modified in this run |
| commit_sha | Git commit hash |
| test_result | Test verification outcome |
| final_result | SUCCESS / FAILED / PARTIAL |
| evidence_path | Link to evidence directory |
## Version History
Records baseline promotions, rollbacks, and version changes.
@@ -127,6 +113,9 @@ Conversation logs between agent and owner for each command execution.
## Audit Trail Requirement
All changes tracked via Git with signed commits where possible.
Every commit message references the originating Command ID.
>>>>>>> 4d18ee0 (feat(cmd): enable Agent Command Plane, audit plane, and Web UI dashboard)
All changes are tracked via Git with signed commits where possible. Every commit references the originating Command ID.
## Related
- [Agent Command Plane](../agents/README.md)
- [Baseline System](baseline-system.md)
@@ -0,0 +1,26 @@
# AIOS V1R5 to V2R1 Migration Plan
## Goal
Move from shared Gateway assumptions to Tenant Cell isolation.
## Order
1. Establish Tenant Registry and signed Tenant Context.
2. Implement Tenant Router.
3. Implement OpenClaw Cell lifecycle management.
4. Introduce canonical message envelope.
5. Add provenance and execution policy enforcement.
6. Migrate Hermes into shared fabric with isolated profiles.
7. Migrate memory, secrets and audit storage.
## Do Not
- Do not modify Hermes first.
- Do not share production credentials across tenants.
- Do not treat workspace separation as a sandbox.
- Do not allow unknown message origins to execute tools.
## Acceptance
Each migration stage requires automated tests and runtime evidence before promotion.
@@ -0,0 +1,49 @@
# AIOS V2R1 OpenClaw Tenant Cell + Hermes Shared Agent Fabric Architecture
## Status
Release train: V2R1C0
Purpose: replace shared runtime trust assumptions with tenant-isolated Cell architecture.
## Principles
1. OpenClaw Gateway is a trust boundary.
2. Each production tenant receives an isolated Cell.
3. Hermes provides shared scheduling/fabric capability but not shared tenant state.
4. Tenant identity, origin, session and task scope are mandatory in every event.
5. Unknown provenance fails closed.
## Target Components
- Tenant Router
- OpenClaw Cell Manager
- Canonical Message Envelope
- Tenant Inbox/Outbox Ledger
- Secret Scope Manager
- Memory Namespace Manager
- Hermes Profile Worker Fabric
- Sandbox Execution Layer
- Audit Event Pipeline
## Migration Order
Phase 1: Tenant Router + Cell Manager
Phase 2: Canonical Message and Policy Layer
Phase 3: Hermes Shared Agent Fabric
Phase 4: Memory, Secret and Audit isolation
Phase 5: Production tenant migration
## Release Gate
A V2R1 production release requires:
- tenant isolation tests passed
- message provenance tests passed
- runtime commit matches release commit
- OpenClaw plugin runtime inspection passed
- rollback verified
@@ -0,0 +1,635 @@
# V2R1 Authenticated Runtime Release Implementation Plan
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
**Goal:** Close exactly five reviewed blockers between the replayed V2R1 tree and an evidence-backed, authenticated, digest-bound release candidate.
**Architecture:** Use one canonical `aios_v2r1` Python package; authenticate a Node-to-Python loopback envelope before server-side Weixin projection and authority resolution; make `ACCEPTED` terminal; dispatch through a durable outbox and the verified Hermes HTTP router; stage an isolated OpenClaw candidate with three services; promote only byte-identical artifacts after live reconciliation evidence.
**Tech Stack:** Python 3.11 and pytest, SQLite, Node.js, OpenClaw 2026.6.11, loopback HTTP, systemd credentials and units, SHA-256 manifests.
## Global gates and dynamic blocker ledger
- B1 and B2 may proceed only after review accepts the corrected design and plan.
- B3, B4, and B5 are evidence-gated. Unresolved evidence stops that task before implementation, commit, or ledger append.
- Current outbound evidence is `EVIDENCE_REQUIRED`; B4 and B5 remain stopped until a verified provider echo exactly binds `client_id -> message_id`.
- Keep exactly five blocker commits, one each for B1 through B5. The docs-correction commit is the reviewed starting point, not a blocker.
- Do not create a tag, edit `VERSION` or `baseline/current.json`, push `main`, deploy/restart a live service, modify active OpenClaw configuration, or invoke Fleet.
- All OpenClaw loader work uses an isolated temporary or candidate config/state directory.
- `ACCEPTED` is terminal. Legacy handling is reachable only when bridge mode is explicitly `disabled`.
- Never claim exactly-once Hermes delivery or use time/approximation as message authority.
- D0 is a non-blocker documentation correction. Its reviewed commit is the R9 `START`; it does not consume a blocker label or relax any B3/B4/B5 evidence gate.
- B2 is both the canonical-package blocker and the executable completeness gate for Ledger, Memory, Secret, Audit, Hermes Profile, Cell Manager/CLI, and Fabric. Existing correct behavior is recorded as characterization; a production edit requires an observed contract RED first.
After docs review, initialize the stable per-worktree ledger from the then-current tip rather than a hardcoded SHA:
```bash
test -z "$(git status --porcelain)"
test "$(git branch --show-current)" = "integration/v2r1-runtime-20260715-r9"
start_sha="$(git rev-parse HEAD)"
start_parent="$(git rev-parse HEAD^)"
start_tree="$(git rev-parse HEAD^{tree})"
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
umask 077
test ! -e "$ledger"
printf 'START\t%s\t%s\t%s\n' "$start_sha" "$start_parent" "$start_tree" >"$ledger"
```
Expected: the clean reviewed docs-correction tip is `START`. At the beginning of every blocker, rehydrate and verify the latest ledger row before work:
```bash
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
test -s "$ledger"
IFS=$'\t' read -r last_label last_sha last_parent last_tree < <(tail -n 1 "$ledger")
test "$(git rev-parse HEAD)" = "$last_sha"
test "$(git rev-parse HEAD^)" = "$last_parent"
test "$(git rev-parse HEAD^{tree})" = "$last_tree"
```
Each blocker appends `label, SHA, parent, tree` only after its review passes. The ledger stays in the worktree Git directory and is never staged.
---
## Task B1: Prove the real OpenClaw plugin loader and permission contract
**Files:**
- Modify: `openclaw/plugins/aios-tenant-boundary/package.json`
- Modify: `openclaw/plugins/aios-tenant-boundary/openclaw.plugin.json`
- Modify only on demonstrated hook failure: `openclaw/plugins/aios-tenant-boundary/dist/index.js`
- Modify only on demonstrated policy failure: `openclaw/plugins/aios-tenant-boundary/dist/policy.js`
- Create: `openclaw/plugins/aios-tenant-boundary/test/compat.test.js`
- Create: `openclaw/plugins/aios-tenant-boundary/test/policy.test.js`
- Create: `openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs`
**Exact contract:** package/manifest versions `2.1.0-rc.1`; `blockUnknownAgentRuns` boolean default `false`; `approvalTimeoutMs` integer min `1000`, max `300000`, default `60000`; every runtime-read property declared. Default permission proves only `before_tool_call` is usable. `before_agent_run` and `agent_end` require `plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`. Fake API tests are supplemental; real runtime inspection is mandatory.
- [ ] Add Node tests for missing/blocked/allowlisted senders, automation, read-only tools, absent provenance, approval, exact timeout bounds, cleanup, age pruning, versions, and schema.
- [ ] Add `loader.test.mjs` to parse real inspect JSON and assert linked path, version, diagnostics, hooks, and permission state.
- [ ] Run initial RED:
```bash
cd openclaw/plugins/aios-tenant-boundary
npm test
```
Expected RED: current package has no tracked tests; version and missing-schema assertions fail.
- [ ] Normalize versions/schema; change runtime only when an executable test proves incompatibility. Capture TAP and prove at least one test executed:
```bash
tmp="$(mktemp -d)"
set -o pipefail
npm test -- --test-reporter=tap | tee "$tmp/plugin.tap"
test "$(grep -c '^ok [0-9]' "$tmp/plugin.tap")" -gt 0
test -z "$(grep '^not ok ' "$tmp/plugin.tap" || true)"
```
Expected GREEN: npm exits 0, TAP contains one or more `ok` test records, and contains no `not ok` record.
- [ ] Run the real loader twice in isolated state:
```bash
repo="$(git rev-parse --show-toplevel)"
tmp="$(mktemp -d)"
export OPENCLAW_STATE_DIR="$tmp/state"
export OPENCLAW_CONFIG_PATH="$tmp/state/openclaw.json"
mkdir -p "$OPENCLAW_STATE_DIR"
openclaw plugins install --link "$repo/openclaw/plugins/aios-tenant-boundary"
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/default-inspect.json"
node "$repo/openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs" default "$tmp/default-inspect.json"
openclaw config set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess true --strict-json
openclaw config validate
set +e
openclaw doctor --lint --json >"$tmp/doctor-lint.json"
doctor_rc=$?
set -e
test "$doctor_rc" = 0 || test "$doctor_rc" = 1
python3 - "$tmp/doctor-lint.json" <<'PY'
import json, sys
data = json.load(open(sys.argv[1]))
def walk(value):
if isinstance(value, dict):
yield value
for child in value.values(): yield from walk(child)
elif isinstance(value, list):
for child in value: yield from walk(child)
bad = [item for item in walk(data) if str(item.get("severity", "")).lower() in {"error", "fatal"} and "plugin" in json.dumps(item).lower()]
assert not bad, bad
PY
openclaw doctor --post-upgrade --json >"$tmp/doctor-plugin.json"
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/opt-in-inspect.json"
node "$repo/openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs" opt-in "$tmp/opt-in-inspect.json"
```
Expected GREEN: config validation and post-upgrade doctor exit 0; lint doctor may exit 0 or 1, warnings are allowed, parsed JSON contains zero error/fatal plugin findings; default inspection proves only `before_tool_call`; opt-in proves `before_agent_run`, `before_tool_call`, `agent_end`.
- [ ] Run carried-forward tests:
```bash
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH=active-runtime/app python3 -m pytest tests/v2r1 tests/integration -q
```
Expected GREEN: `32 passed`.
- [ ] Commit and append ledger:
```bash
git add openclaw/plugins/aios-tenant-boundary/package.json openclaw/plugins/aios-tenant-boundary/openclaw.plugin.json \
openclaw/plugins/aios-tenant-boundary/dist/index.js openclaw/plugins/aios-tenant-boundary/dist/policy.js \
openclaw/plugins/aios-tenant-boundary/test/compat.test.js openclaw/plugins/aios-tenant-boundary/test/policy.test.js \
openclaw/plugins/aios-tenant-boundary/test/loader.test.mjs
git commit -m "fix(v2r1): prove OpenClaw plugin compatibility"
```
### Review B1
- [ ] `git diff --check HEAD^ HEAD` has no output; commit contains only named B1 paths and unchanged optional `dist` files do not appear.
- [ ] Re-run Node tests, both real loader permission modes, validation/doctor, and 32 Python tests.
- [ ] Prove B1 parent equals ledger `START` and, before the final append step, the ledger still contains only `START`.
- [ ] Stop if real inspection does not prove default-only `before_tool_call` and explicit conversation-access hooks.
- [ ] After every prior B1 review check passes, append B1 and verify the recorded commit identity:
```bash
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
printf 'B1\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
test "$label" = B1
test "$sha" = "$(git rev-parse HEAD)"
test "$parent" = "$(git rev-parse HEAD^)"
test "$tree" = "$(git rev-parse HEAD^{tree})"
```
---
## Task B2: Package only `aios_v2r1` and repair the exact legacy import set
**Files:**
- Create: `active-runtime/pyproject.toml`
- Create: `active-runtime/app/aios_v2r1/__init__.py`
- Create: `active-runtime/app/aios_v2r1/ingress_service.py`
- Modify: `active-runtime/app/aios_v2r1/cli.py`
- Create: `tests/v2r1/test_ingress_service.py`
- Create: `tests/test_v2r1_package_identity.py`
- Modify: the exact 23 Appendix A test files, and no unlisted legacy import file
- Modify only after an observed matrix RED: `active-runtime/app/aios_v2r1/message_ledger.py`
- Modify only after an observed matrix RED: `active-runtime/app/aios_v2r1/memory_scope.py`
- Modify only after an observed matrix RED: `active-runtime/app/aios_v2r1/secret_scope.py`
- Modify only after an observed matrix RED: `active-runtime/app/aios_v2r1/audit.py`
- Modify only after an observed matrix RED: `active-runtime/app/aios_v2r1/hermes_profile.py`
- Modify only after an observed matrix RED: `active-runtime/app/aios_v2r1/cell_manager.py`
- Modify only after an observed matrix RED: `active-runtime/app/aios_v2r1/hermes_fabric.py`
- Expand: `tests/v2r1/test_message_ledger_append.py`
- Create: `tests/v2r1/test_memory_scope.py`
- Create: `tests/v2r1/test_secret_scope.py`
- Create: `tests/v2r1/test_audit.py`
- Create: `tests/v2r1/test_hermes_profile.py`
- Create: `tests/v2r1/test_cell_manager.py`
- Expand: `tests/v2r1/test_hermes_fabric.py`
**Exact contract:** V2R1 imports only as `aios_v2r1`; no `active_runtime` shim/alias/namespace extension/copied tree. Wheel includes `aios_v2r1`, excludes `active_runtime` and legacy `app`. Legacy repository tests change `active_runtime.app.*` to `app.*` and run with `PYTHONPATH='active-runtime:active-runtime/app'`. Mutation routes return bounded `SERVICE_NOT_CONFIGURED` until B3/B4 processors exist. Existing cell CLI stays compatible and `serve` is separate. B2 changes exactly 43 paths: the original 29 package/import paths plus the seven named runtime modules and seven named matrix-test paths above.
**Executable completeness matrix:** Message Ledger proves exact-ID query with no fallback, idempotency, collision conflict, tenant/cell/direction isolation, expiry/purge, restart, concurrency, and sanitized SQLite failures. Memory proves every namespace, cross-scope denial, shared-artifact read-only access, qualified keys, traversal rejection, and disabled search. Secret proves reference/path/scope/kind/version/identifier validation, no value leakage, and fail-closed broker boundaries. Audit proves genesis, tamper/delete/reorder detection, Unicode canonicalization, concurrency, restart, validation, tenant isolation, and sanitized SQLite failures. Hermes Profile proves exact environment, absolute roots, `0700` modes, traversal/symlink denial, scope, idempotent prepare, and no inherited environment. Cell Manager/CLI proves one cell per tenant, an explicit state graph, atomic/concurrent persistence, corrupt-registry fail-closed behavior, stable CLI exit codes/JSON, and restart. Fabric proves claimed jobs return `running` consistently with durable state, tenant/cell/profile isolation, one concurrent claimant, rejection of non-claimable states, restart, and sanitized SQLite failures.
- [ ] Rehydrate the stable blocker ledger using the global snippet and require its latest label is `B1`.
- [ ] Rehydrate the exact explorer manifest path and compare sorted actual/expected lists between exact marker lines. The marker names are assembled from split literals so this command cannot match itself:
```bash
actual="$(git rev-parse --git-path v2r1-active-runtime-imports.actual)"
expected="$(git rev-parse --git-path v2r1-active-runtime-imports.expected)"
plan=docs/superpowers/plans/2026-07-14-v2r1-runtime-release-plan.md
begin="$(printf '%s' 'APPENDIX_A_''BEGIN')"
end="$(printf '%s' 'APPENDIX_A_''END')"
tick="$(printf '\140')"
git grep -l -E '^(from|import) active_runtime\.app' -- tests | sort >"$actual"
awk -v begin="${tick}${begin}${tick}" -v end="${tick}${end}${tick}" '
$0 == begin {inside=1; next}
$0 == end {inside=0; next}
inside && /^- tests\// {sub(/^- /, ""); print}
' "$plan" | sort >"$expected"
test "$(wc -l < "$actual" | tr -d ' ')" = 23
test "$(wc -l < "$expected" | tr -d ' ')" = 23
cmp -s "$actual" "$expected"
```
Expected: exact match to 23 paths. Drift requires another docs review.
- [ ] Add package/service/CLI tests and the seven-component matrix before any production repair. Run each focused case and record the exact command plus its expected contract failure. If current behavior already satisfies the contract, record it as characterization and do not manufacture a failure or edit that production module.
- [ ] Run the aggregate initial RED/characterization command:
```bash
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' \
python3 -m pytest tests/v2r1/test_ingress_service.py tests/test_v2r1_package_identity.py \
tests/v2r1/test_message_ledger_append.py tests/v2r1/test_memory_scope.py \
tests/v2r1/test_secret_scope.py tests/v2r1/test_audit.py \
tests/v2r1/test_hermes_profile.py tests/v2r1/test_cell_manager.py \
tests/v2r1/test_hermes_fabric.py -q
```
Expected: package metadata, ingress service, and identity tests begin RED because their implementation is absent. Each matrix case is either a recorded contract RED or a recorded characterization; no production repair precedes its corresponding RED.
- [ ] Implement package/disabled processor boundary and replace imports in exactly Appendix A. Apply only the minimum runtime repairs demonstrated by matrix REDs; do not delete or weaken a matrix test. Prove no shim/old import:
```bash
test ! -e active_runtime
test -z "$(git grep -l -E '^(from|import) active_runtime\.app' -- tests || true)"
```
- [ ] Run full collect and full suite:
```bash
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' \
python3 -m pytest tests/v2r1 tests/integration tests/test_v2r1_package_identity.py -q
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest --collect-only -q
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest -q
PYTHONDONTWRITEBYTECODE=1 python3 -m compileall -q active-runtime/app/aios_v2r1
(cd openclaw/plugins/aios-tenant-boundary && npm test)
```
Expected GREEN: the focused carried suite reports at least `160 passed`, including every matrix bullet; full collection has zero import errors; the complete pytest suite, 15 Node tests, and Python compileall pass. Re-run B1's real isolated default/opt-in loader sequence and require the same hook evidence. Pre-existing failures still block B2.
- [ ] Build and inspect isolated wheel:
```bash
tmp="$(mktemp -d)"
python3 -m pip wheel --no-deps --no-build-isolation active-runtime -w "$tmp/wheels"
wheel="$(find "$tmp/wheels" -name '*.whl' -print -quit)"
python3 -m venv "$tmp/venv"
"$tmp/venv/bin/python" -m pip install --no-deps "$wheel"
"$tmp/venv/bin/python" - "$wheel" <<'PY'
import sys, zipfile
names = zipfile.ZipFile(sys.argv[1]).namelist()
assert any(n.endswith("aios_v2r1/ingress_service.py") for n in names)
assert not any(n.startswith("active_runtime/") or n.startswith("app/") for n in names)
import aios_v2r1
assert aios_v2r1.__name__ == "aios_v2r1"
PY
```
Expected GREEN: one wheel, one V2R1 namespace, installed identity `aios_v2r1`.
- [ ] Stage the exact 43 paths (six package paths, Appendix A's 23 import paths, seven matrix runtime modules, and seven matrix-test paths), commit, append ledger:
```bash
actual="$(git rev-parse --git-path v2r1-active-runtime-imports.actual)"
git add active-runtime/pyproject.toml active-runtime/app/aios_v2r1/__init__.py \
active-runtime/app/aios_v2r1/ingress_service.py active-runtime/app/aios_v2r1/cli.py \
tests/v2r1/test_ingress_service.py tests/test_v2r1_package_identity.py \
active-runtime/app/aios_v2r1/message_ledger.py active-runtime/app/aios_v2r1/memory_scope.py \
active-runtime/app/aios_v2r1/secret_scope.py active-runtime/app/aios_v2r1/audit.py \
active-runtime/app/aios_v2r1/hermes_profile.py active-runtime/app/aios_v2r1/cell_manager.py \
active-runtime/app/aios_v2r1/hermes_fabric.py tests/v2r1/test_message_ledger_append.py \
tests/v2r1/test_memory_scope.py tests/v2r1/test_secret_scope.py tests/v2r1/test_audit.py \
tests/v2r1/test_hermes_profile.py tests/v2r1/test_cell_manager.py tests/v2r1/test_hermes_fabric.py
while IFS= read -r path; do git add -- "$path"; done <"$actual"
git commit -m "feat(v2r1): package canonical authenticated ingress"
```
### Review B2
- [ ] Require `git diff --check`, exactly 43 paths (the original 29 plus the exact 14 matrix paths), exact-list/no-shim checks, focused matrix/carried tests, full collect/full pytest, Node 15, real loader default/opt-in, compileall, and wheel identity.
- [ ] Require B2 parent equals B1 in ledger.
- [ ] Prove mutation routes remain fail-closed until authenticated processors are installed.
- [ ] Prove every production matrix edit has a recorded pre-edit RED and every already-correct case is recorded as characterization. The partial R9 ledger must contain exactly `START,B1,B2`; B3/B4/B5 remain absent.
- [ ] After all prior B2 review checks pass, append B2 and verify the recorded commit identity:
```bash
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
printf 'B2\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
test "$label" = B2
test "$sha" = "$(git rev-parse HEAD)"
test "$parent" = "$(git rev-parse HEAD^)"
test "$tree" = "$(git rev-parse HEAD^{tree})"
```
---
## Task B3: Implement authenticated Node transport and server-side Weixin authority
**Evidence gate before code:** create `release/v2r1c0-rc1/weixin-bridge-evidence.json` only after recording installed TS/JS paths and SHA-256, exact inbound bigint/raw fields, authenticated account/sender/conversation sources, authority-map owner/mode/schema, candidate credential contract, and `disabled|enforced` mode owner. Stop if any source is inferred, Node would need the authority map, or patch targets are not byte-idempotent.
**Files after evidence acceptance:**
- Modify: `active-runtime/app/aios_v2r1/identity.py`
- Modify: `active-runtime/app/aios_v2r1/tenant_context.py`
- Modify: `active-runtime/app/aios_v2r1/ingress_service.py`
- Create: `active-runtime/app/aios_v2r1/bridge_auth.py`
- Create: `active-runtime/app/aios_v2r1/weixin_projection.py`
- Create: `fixes/patch_openclaw_weixin_v2r1_ingress.py`
- Create: `tests/v2r1/test_bridge_auth.py`
- Create: `tests/v2r1/test_weixin_projection.py`
- Create: `tests/integration/test_v2r1_bridge_transport.py`
- Create: `tests/test_weixin_v2r1_ingress_bridge.py`
- Create: four `tests/fixtures/weixin_v2r1/*.json` files named in the commit command
- Create: `release/v2r1c0-rc1/weixin-bridge-evidence.json`
**Exact contract:** Every authenticated POST has wire shape `{"unsigned_body":{"schema_version":"aios.signed-request.v1","key_id":"bridge-current","issued_at_ms":1784000000000,"nonce":"base64url-16-byte-value","route_payload":{}},"signature":"lowercase-64-hex"}`. `unsigned_body` has exactly those five fields; `route_payload` holds only route-specific content. The signing object is exactly `{"method":"POST","path":"<exact route>","body":unsigned_body}`. Canonical JSON is UTF-8 with recursive Unicode-codepoint-sorted object keys, no whitespace, no ASCII escaping, no floats, and string IDs; the outer `signature` is the lowercase 64-hex HMAC-SHA256 of those bytes. There is no authorization header, nested signature, or alternate route form. Python verifies before projection. Skew 30 seconds; replay five minutes; active+previous rotation; fresh nonce retry. Node reads bridge-ingress and the separate receipt-read keyring through distinct `$CREDENTIALS_DIRECTORY` files. Python owns projection/authority/internal signing. `POST /v1/receipts/status` accepts `account_id` plus exactly one of `event_id|receipt_id`, resolves only same-account/event scope, and uses receipt-read. Response max 4096 bytes. `REPLAY_REJECTED` is transport/service-only, never `RuntimeIngressResponse`. Accepted is terminal; legacy disabled-only. `Date.now()` and every local `_ms` timestamp are telemetry only.
- [ ] Rehydrate the stable ledger with the global snippet and require latest label `B2` before evidence collection.
- [ ] Add RED tests for the one exact wire/signing contract on `/v1/ingress` and `/v1/receipts/status`, including rejection of extra/missing fields, signature-inside-body, authorization-header variants, nonce lengths, skew boundaries, replay, key rotation, fresh retry, roles, bounded routes, terminal accepted, disabled legacy, bigint, and exact quote/attachment.
- [ ] Run initial RED:
```bash
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' \
python3 -m pytest tests/v2r1/test_bridge_auth.py tests/v2r1/test_weixin_projection.py \
tests/integration/test_v2r1_bridge_transport.py tests/test_weixin_v2r1_ingress_bridge.py -q
```
Expected RED: authenticator, server projection, processor, patcher absent.
- [ ] Implement authenticated transport/server projection and byte-idempotent TS/JS patch. Never embed authority or internal key in Node.
- [ ] Run focused, existing Weixin, full collect, and full pytest. Expected GREEN: all pass.
- [ ] Commit exactly 15 paths and append ledger:
```bash
git add active-runtime/app/aios_v2r1/identity.py active-runtime/app/aios_v2r1/tenant_context.py \
active-runtime/app/aios_v2r1/ingress_service.py active-runtime/app/aios_v2r1/bridge_auth.py \
active-runtime/app/aios_v2r1/weixin_projection.py fixes/patch_openclaw_weixin_v2r1_ingress.py \
tests/v2r1/test_bridge_auth.py tests/v2r1/test_weixin_projection.py \
tests/integration/test_v2r1_bridge_transport.py tests/test_weixin_v2r1_ingress_bridge.py \
tests/fixtures/weixin_v2r1/text.json tests/fixtures/weixin_v2r1/quoted-text.json \
tests/fixtures/weixin_v2r1/image-with-text.json tests/fixtures/weixin_v2r1/unresolved-reference.json \
release/v2r1c0-rc1/weixin-bridge-evidence.json
git commit -m "feat(v2r1): bridge authenticated Weixin authority"
```
### Review B3
- [ ] Require exactly 15 named paths, `git diff --check`, focused/full tests, and a second patcher pass with empty diff.
- [ ] Prove Node transports evidence only; Python owns projection/authority; RuntimeWiring re-resolves.
- [ ] Prove fresh nonce on retry, terminal accepted, and legacy unreachable in `enforced`.
- [ ] Require B3 parent equals B2. Stop without commit/ledger append when evidence is unresolved.
- [ ] After all prior B3 review checks pass, append B3 and verify the recorded commit identity:
```bash
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
printf 'B3\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
test "$label" = B3
test "$sha" = "$(git rev-parse HEAD)"
test "$parent" = "$(git rev-parse HEAD^)"
test "$tree" = "$(git rev-parse HEAD^{tree})"
```
---
## Task B4: Connect the durable outbox to the verified Hermes HTTP router
**Evidence gate before code:** create `release/v2r1c0-rc1/hermes-http-contract-evidence.json` from live listener/unit/source/schema inspection and `release/v2r1c0-rc1/weixin-outbound-binding-evidence.json` from raw protocol evidence. Hermes evidence resolves schemas, `aios-hermes-router.service`, source digest, exact 140-second timeout, tenant/user ownership, and repeated-`route_id` behavior as idempotent/non-idempotent. Outbound evidence must prove exact provider echo `client_id -> message_id`. Current ACK `ret/errmsg` plus reference `ref_msg.message_item.msg_id/ref_msg.message_item.create_time_ms` is `EVIDENCE_REQUIRED` and hard-stops B4; timestamp cannot unlock it.
**Files only after both gates pass:**
- Create: `active-runtime/app/aios_v2r1/outbox.py`
- Create: `active-runtime/app/aios_v2r1/hermes_http.py`
- Create: `active-runtime/app/aios_v2r1/hermes_worker.py`
- Create: `active-runtime/app/aios_v2r1/outbound_receipt.py`
- Modify: `active-runtime/app/aios_v2r1/ingress_service.py`
- Modify: `active-runtime/app/aios_v2r1/message_ledger.py`
- Create: `tests/v2r1/test_outbox.py`
- Create: `tests/v2r1/test_hermes_http.py`
- Create: `tests/v2r1/test_outbound_receipt.py`
- Create: `tests/integration/test_v2r1_delivery_flow.py`
- Modify: `fixes/patch_openclaw_weixin_outbound_quotes.py`
- Create: `fixes/patch_openclaw_weixin_outbound_receipts.py`
- Create: `openclaw/plugins/aios-tenant-boundary/dist/receipt-client.js`
- Create: `openclaw/plugins/aios-tenant-boundary/dist/outbound-receipt-journal.js`
- Create: `openclaw/plugins/aios-tenant-boundary/test/receipt-client.test.js`
- Modify: `tests/test_weixin_outbound_quote_timestamp.py`
- Create: `tests/test_weixin_outbound_receipt_boundary.py`
- Create: both evidence JSON files named above
**Exact contract:** readiness `GET http://127.0.0.1:18791/health/ready`; dispatch `POST http://127.0.0.1:18791/internal/hermes/route`; downstream 140 seconds; worker deadline 150 seconds; 120-second direct timeout forbidden. States `pending|leased|delivered|delivery_unknown|dead`. No exactly-once. Unknown idempotency stops; known false prevents ambiguous retry; known true retries same `route_id`/digest. After B4 evidence, the actual Node Weixin sender receives a separate `outbound-receipt-write` `LoadCredential=` and uses the same one POST signing contract for `/v1/outbound-receipts`: exact five-field `unsigned_body`, exact `{method,path,body}` signing object, canonical JSON, and outer lowercase 64-hex HMAC-SHA256 signature.
Node alone owns its callback journal at `$STATE_DIRECTORY/outbound-receipts`. The gateway unit supplies a gateway-specific `StateDirectory=` with `StateDirectoryMode=0700`; the directory and its mode-`0600` files are owned and readable only by that gateway's service user. The send-boundary patch persists one sanitized per-client-ID JSON entry using a safe fixed-width digest filename: same-directory temporary file, file `fsync`, atomic rename to `.pending`, then directory `fsync`. Records contain only bounded IDs, send-success, attempt count, and next-attempt metadata—no bodies, quotes, attachments, signatures, credentials, key material, or provider payloads. Startup recovery and a background worker perform bounded authenticated callback retries without invoking Weixin send again. A pending record is deleted and the directory `fsync`ed only after an authenticated application ACK. Python owns receipt/outbox/worker storage and has no second send journal. Missing exact binding records `EVIDENCE_REQUIRED`, null provider ID, hard stop; `Date.now()` and local `_ms` fields remain telemetry only.
- [ ] Rehydrate the stable ledger and require latest label `B3` before evidence collection.
- [ ] Execute evidence collectors first. Current expected result is `EVIDENCE_REQUIRED`; stop with no runtime edit, B4 commit, or ledger append.
- [ ] After future exact binding acceptance, add RED tests for replay/collision/lease/unknown/dead, HTTP schema, 140/150 budgets, idempotency branches, the exact receipt signing role, exact provider mapping, ledger quote, `$STATE_DIRECTORY/outbound-receipts` resolution, directory/file ownership and `0700`/`0600` modes, file/directory `fsync`, atomic `.pending` rename, startup/background bounded retry, no-body/no-secret persistence, no content resend, and authenticated-ACK-only delete plus directory `fsync`.
- [ ] Run initial RED:
```bash
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' \
python3 -m pytest tests/v2r1/test_outbox.py tests/v2r1/test_hermes_http.py \
tests/v2r1/test_outbound_receipt.py tests/integration/test_v2r1_delivery_flow.py \
tests/test_weixin_outbound_quote_timestamp.py tests/test_weixin_outbound_receipt_boundary.py -q
node --test openclaw/plugins/aios-tenant-boundary/test/receipt-client.test.js
```
Expected RED after evidence acceptance: modules absent.
- [ ] Implement outbox, bounded HTTP adapter/worker, authenticated callback client, Node-owned durable callback journal, actual Weixin send-boundary patch, role-authenticated receipt route, exact Python receipt store, and outbound ledger append only after exact binding. Run Python, Node, both patchers twice for byte-idempotence, actual send-boundary, full, and loader tests; expected GREEN, with callback failure journaled without resend, timeout ambiguity `delivery_unknown`, and no exactly-once assertion.
- [ ] Commit exactly 19 paths:
```bash
git add active-runtime/app/aios_v2r1/outbox.py active-runtime/app/aios_v2r1/hermes_http.py \
active-runtime/app/aios_v2r1/hermes_worker.py active-runtime/app/aios_v2r1/outbound_receipt.py \
active-runtime/app/aios_v2r1/ingress_service.py active-runtime/app/aios_v2r1/message_ledger.py \
tests/v2r1/test_outbox.py tests/v2r1/test_hermes_http.py tests/v2r1/test_outbound_receipt.py \
tests/integration/test_v2r1_delivery_flow.py fixes/patch_openclaw_weixin_outbound_quotes.py \
fixes/patch_openclaw_weixin_outbound_receipts.py openclaw/plugins/aios-tenant-boundary/dist/receipt-client.js \
openclaw/plugins/aios-tenant-boundary/dist/outbound-receipt-journal.js \
openclaw/plugins/aios-tenant-boundary/test/receipt-client.test.js tests/test_weixin_outbound_quote_timestamp.py \
tests/test_weixin_outbound_receipt_boundary.py release/v2r1c0-rc1/hermes-http-contract-evidence.json \
release/v2r1c0-rc1/weixin-outbound-binding-evidence.json
git commit -m "feat(v2r1): dispatch through evidenced Hermes outbox"
```
### Review B4
- [ ] Require exactly 19 paths, accepted evidence digests, `git diff --check`, Python/Node/patcher/send-boundary/full/loader tests.
- [ ] Prove 150 exceeds exact 140 and no 120-second production deadline remains.
- [ ] Search changed files for exactly-once claims and timestamp/approximate binding; require none.
- [ ] Require B4 parent equals B3. If either evidence remains unresolved, correct result is STOP with no commit.
- [ ] After all prior B4 review checks pass, append B4 and verify the recorded commit identity:
```bash
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
printf 'B4\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
test "$label" = B4
test "$sha" = "$(git rev-parse HEAD)"
test "$parent" = "$(git rev-parse HEAD^)"
test "$tree" = "$(git rev-parse HEAD^{tree})"
```
---
## Task B5: Build digest-bound isolated candidate staging and rollback
**Evidence gate before code:** accepted B3/B4 ledger entries. `capture_live_preflight.py` creates one evidence file containing a reconciled Gitea branch-consistency sentinel (`status=healthy`, `drift_count=0`, refs matching candidate) and the V1R4C6 live snapshot (host identity, capture time, Git SHA, units, commands, listeners, OpenClaw version, config/plugin digests, credential metadata, state/database paths, mounts, active artifact, rollback target). `release_ctl.py --preflight-file` validates the schema, exact current host, sentinel, all required fields, and freshness no older than 300 seconds. Stop if either record is missing, stale, host-mismatched, malformed, or inconsistent before staging or promotion.
**Files:**
- Create: `deploy/v2r1/release_ctl.py`
- Create: `deploy/v2r1/capture_live_preflight.py`
- Modify: `deploy/v2r1/install.sh`, `deploy/v2r1/validate.sh`, `deploy/v2r1/healthcheck.sh`
- Create: `deploy/v2r1/rollback.sh`
- Create: `deploy/v2r1/aios-v2r1-candidate-gateway.service`
- Create: `deploy/v2r1/aios-v2r1-production-gateway.service`
- Create: `deploy/v2r1/aios-v2r1-ingress.service`
- Create: `deploy/v2r1/aios-v2r1-hermes-worker.service`
- Create: `deploy/v2r1/openclaw-candidate.json5`
- Create: `release/v2r1c0-rc1/FLEET_UNSUPPORTED`
- Create: `tests/deploy/test_v2r1_release_contract.py`
- Modify: `release/v2r1c0-rc1/RELEASE.md`
**Exact contract:** `python3 deploy/v2r1/release_ctl.py` exposes only `build`, `stage`, `verify-stage`, `promote`, `status`, and `rollback`. Forward states are exactly `BUILT -> STAGED -> STAGE_VERIFIED -> PRODUCTION`; rollback states are `ROLLBACK_STARTED -> ROLLED_BACK|ROLLBACK_FAILED`. Forward commands accept `--preflight-file`; callers supply no artifact, reconciled-sentinel, or runtime-snapshot digest strings. The controller validates the evidence and computes/persists all three digests internally. `verify-stage` and `promote` each recapture live evidence with the collector, revalidate it, recompute the triplet, and reject any drift from the recorded candidate state. Deterministic same bytes stage/prod; isolated users/state/config/ports/credentials; `LoadCredential=` least-role delivery; linked candidate plugin with runtime inspect, `allowConversationAccess=true`, config validate, doctor, inspect; `NOOP_DIGEST_MATCH` zero mutation/controller calls. Candidate and production gateway units use distinct dedicated users and distinct `StateDirectory=` values (`aios-v2r1-candidate-gateway` versus `aios-v2r1-production-gateway`), both set `StateDirectoryMode=0700`, and resolve journals only below their own `$STATE_DIRECTORY/outbound-receipts`; sharing, symlinking, or bind-mounting journal state is forbidden. The current root-run production gateway remains root-owned only until its audited migration; candidate staging never reads it, and migrated mode-`0600` records become readable only by the production gateway user. STOP blocks forward actions but permits only `rollback --rollback-only --to-previous-recorded --reason-file "$reason_file"`; exact prior digest/snapshot, no forward migration, cannot remove STOP, audited.
- [ ] Rehydrate the stable ledger and require latest label `B4` before live evidence capture.
- [ ] Add RED release tests for deterministic builds, dirty/secret rejection, rejection of caller digest arguments, preflight schema/required fields/exact-host/sentinel/freshness-at-300-seconds, tamper and recapture drift, isolated config, loader sequence, unit credentials, candidate/production service-user ownership, exact distinct `StateDirectory=` names and paths, `StateDirectoryMode=0700`, journal file mode `0600`, no shared/symlink/bind-mounted journal state, root-production transition only during audited migration, no-op, STOP forward block, constrained rollback, readiness timeout, and prior integrity.
- [ ] Run initial RED:
```bash
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' python3 -m pytest tests/deploy/test_v2r1_release_contract.py -q
```
Expected RED: driver, collector, units/config, rollback wrapper, lifecycle absent.
- [ ] Implement deterministic artifact and the executable state machine; wrappers never switch branches/create tags/edit baseline/version/suppress errors. Exercise exact commands:
```bash
preflight_file="$(mktemp)"
python3 deploy/v2r1/capture_live_preflight.py --output "$preflight_file"
python3 deploy/v2r1/release_ctl.py build --source "$source_sha" --output "$build_dir" --preflight-file "$preflight_file"
python3 deploy/v2r1/release_ctl.py stage --artifact "$artifact" --preflight-file "$preflight_file" --root "$release_root"
python3 deploy/v2r1/release_ctl.py verify-stage --preflight-file "$preflight_file" --root "$release_root"
python3 deploy/v2r1/release_ctl.py promote --preflight-file "$preflight_file" --root "$release_root"
python3 deploy/v2r1/release_ctl.py status --root "$release_root"
python3 deploy/v2r1/release_ctl.py rollback --root "$release_root" --rollback-only --to-previous-recorded --reason-file "$reason_file"
```
Expected GREEN: the collector creates the evidence file; the controller accepts no caller digest strings, validates it, and computes the artifact/sentinel/runtime triplet internally. State records advance only through `BUILT,STAGED,STAGE_VERIFIED,PRODUCTION`; `verify-stage` and `promote` recapture current live state and require the same triplet; rollback records `ROLLBACK_STARTED` then `ROLLED_BACK` or `ROLLBACK_FAILED`.
- [ ] Execute candidate loader in isolated environment:
```bash
tmp="$(mktemp -d)"
candidate_release="$tmp/release/current"
export OPENCLAW_STATE_DIR="$tmp/openclaw-state"
export OPENCLAW_CONFIG_PATH="$tmp/openclaw-state/openclaw.json"
mkdir -p "$OPENCLAW_STATE_DIR"
openclaw plugins install --link "$candidate_release/openclaw/plugins/aios-tenant-boundary"
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/plugin-before.json"
openclaw config set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess true --strict-json
openclaw config validate
set +e
openclaw doctor --lint --json >"$tmp/doctor-lint.json"
doctor_rc=$?
set -e
test "$doctor_rc" = 0 || test "$doctor_rc" = 1
python3 - "$tmp/doctor-lint.json" <<'PY'
import json, sys
data = json.load(open(sys.argv[1]))
def walk(value):
if isinstance(value, dict):
yield value
for child in value.values(): yield from walk(child)
elif isinstance(value, list):
for child in value: yield from walk(child)
bad = [item for item in walk(data) if str(item.get("severity", "")).lower() in {"error", "fatal"} and "plugin" in json.dumps(item).lower()]
assert not bad, bad
PY
openclaw doctor --post-upgrade --json >"$tmp/doctor-plugin.json"
openclaw plugins inspect aios-tenant-boundary --runtime --json >"$tmp/plugin-after.json"
```
Expected GREEN: plugin path inside candidate; config validation and post-upgrade doctor exit 0; lint doctor exits 0 or 1, warnings are allowed, and parsed JSON has zero error/fatal plugin findings; final inspect proves three hooks/permission; active V1R4C6 paths are absent.
- [ ] Run release/full Python/Node/loader tests, two byte-identical builds, and refreshed sentinel/snapshot comparisons. Expected GREEN: all pass.
- [ ] Commit exactly 14 paths and append ledger:
```bash
git add deploy/v2r1/release_ctl.py deploy/v2r1/capture_live_preflight.py deploy/v2r1/install.sh \
deploy/v2r1/validate.sh deploy/v2r1/healthcheck.sh deploy/v2r1/rollback.sh \
deploy/v2r1/aios-v2r1-candidate-gateway.service deploy/v2r1/aios-v2r1-production-gateway.service \
deploy/v2r1/aios-v2r1-ingress.service \
deploy/v2r1/aios-v2r1-hermes-worker.service deploy/v2r1/openclaw-candidate.json5 \
release/v2r1c0-rc1/FLEET_UNSUPPORTED tests/deploy/test_v2r1_release_contract.py release/v2r1c0-rc1/RELEASE.md
git commit -m "deploy(v2r1): bind candidate release to live evidence"
```
### Review B5
- [ ] Require exactly 14 paths, no live secret/snapshot payload in Git, `git diff --check`, complete tests, two identical builds.
- [ ] Inspect both gateway units and acceptance-test distinct service users, distinct `StateDirectory=` names/absolute paths, `StateDirectoryMode=0700`, mode-`0600` journal files, and no shared, symlinked, or bind-mounted receipt journal.
- [ ] Prove candidate paths never resolve active V1R4C6; STOP blocks forward while rollback selects only recorded previous state and cannot remove STOP.
- [ ] Prove staging validates the collector-created file and `verify-stage`/`promote` each recapture current live sentinel/runtime state, compute digests internally, and compare the same triplet; prove no caller-supplied digest option exists.
- [ ] Require B5 parent equals B4.
- [ ] After all prior B5 review checks pass, append B5 and verify the recorded commit identity:
```bash
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
printf 'B5\t%s\t%s\t%s\n' "$(git rev-parse HEAD)" "$(git rev-parse HEAD^)" "$(git rev-parse HEAD^{tree})" >>"$ledger"
IFS=$'\t' read -r label sha parent tree < <(tail -n 1 "$ledger")
test "$label" = B5
test "$sha" = "$(git rev-parse HEAD)"
test "$parent" = "$(git rev-parse HEAD^)"
test "$tree" = "$(git rev-parse HEAD^{tree})"
```
## Final five-commit verification
Run only after all evidence/task reviews pass:
```bash
ledger="$(git rev-parse --git-path v2r1-blocker-ledger.tsv)"
python3 - "$ledger" <<'PY'
from pathlib import Path
import subprocess, sys
rows = [line.split("\t") for line in Path(sys.argv[1]).read_text().splitlines()]
assert [row[0] for row in rows] == ["START", "B1", "B2", "B3", "B4", "B5"]
for i in range(1, len(rows)):
label, sha, recorded_parent, recorded_tree = rows[i]
parent = subprocess.check_output(["git", "rev-parse", sha + "^"], text=True).strip()
tree = subprocess.check_output(["git", "rev-parse", sha + "^{tree}"], text=True).strip()
assert parent == rows[i - 1][1]
assert parent == recorded_parent and tree == recorded_tree, label
start, head = rows[0][1], rows[-1][1]
assert subprocess.check_output(["git", "rev-parse", "HEAD"], text=True).strip() == head
assert subprocess.check_output(["git", "rev-list", "--count", f"{start}..{head}"], text=True).strip() == "5"
assert not subprocess.check_output(["git", "rev-list", "--merges", f"{start}..{head}"], text=True).strip()
PY
test -z "$(git status --porcelain)"
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest --collect-only -q
PYTHONDONTWRITEBYTECODE=1 PYTEST_ADDOPTS='-p no:cacheprovider' PYTHONPATH='active-runtime:active-runtime/app' python3 -m pytest -q
(cd openclaw/plugins/aios-tenant-boundary && npm test)
```
Expected: labels exactly `START,B1,B2,B3,B4,B5`; current HEAD/parent/tree match recorded values; `START..HEAD` has exactly five commits and no merge; clean tree; full collect/full Python/Node/loader/release tests pass.
Review authority roles, status spelling, timeout units, routes, response bounds, terminal semantics, evidence states, types, and sentinel behavior. Scan unresolved markers with split literals:
```bash
marker_pattern="$(printf '%s' 'TO''DO|T''BD|FIX''ME|CHANGE''_ME|INSERT''_')"
git grep -nE "$marker_pattern" -- active-runtime deploy/v2r1 openclaw/plugins/aios-tenant-boundary release/v2r1c0-rc1 tests
```
Expected: no matches. Any contradiction, type mismatch, unresolved evidence, extra blocker commit, or missing review stops release preparation.
## Appendix A: Exact legacy `active_runtime.app` import files
`APPENDIX_A_BEGIN`
- tests/test_agent_event_bus.py
- tests/test_agent_observability_loop.py
- tests/test_architect_governance.py
- tests/test_architect_research_timeline.py
- tests/test_architecture_change_classifier.py
- tests/test_architecture_owner_gate.py
- tests/test_architect_weekly_research.py
- tests/test_change_governance.py
- tests/test_governance_event_bridge.py
- tests/test_governance_timeline.py
- tests/test_search_agent_adapter.py
- tests/test_search_architect_integration.py
- tests/test_search_gateway_dashboard.py
- tests/test_search_gateway_general_capability.py
- tests/test_search_gateway_orchestrator.py
- tests/test_search_gateway.py
- tests/test_search_provider_registry.py
- tests/test_task_center.py
- tests/test_task_dashboard_view.py
- tests/test_task_event_and_statistics.py
- tests/test_task_lifecycle.py
- tests/test_task_orchestrator.py
- tests/test_v1r4c1_risk_fixes.py
`APPENDIX_A_END`
@@ -0,0 +1,188 @@
# V2R1 R10 personal Weixin release-plan amendment
Status: reviewed design-only amendment. It adds D1, B6, and B7 to the R9 linear release plan. It does not authorize runtime, candidate, production, baseline, tag, or Fleet mutation.
Authority remains `docs/superpowers/plans/2026-07-14-v2r1-runtime-release-plan.md` at B2 tip `68d27879103990aac692207a8512b3725c6d0d41`. R9 `START` is `a9a0b4ae396e33c9bfc35a5f5694e5e354c3a47c`; accepted B1 is `57103c11d21192a50febe846d30cee6fc5da4ac1`; accepted B2 is `68d27879103990aac692207a8512b3725c6d0d41`. Their trees and path sets are immutable. This amendment does not relabel, squash, reorder, or absorb any of the original five blockers.
## Exact linear ledger
The only valid ancestry is:
```text
START -> B1 -> B2 -> D1 -> B3 -> B4 -> B5 -> B6 -> B7
```
`D1` is a non-blocker design dependency whose parent is exactly B2. `B3` parent is D1; every later blocker parent is the immediately preceding row. `START..B7` contains exactly eight non-merge commits: B1, B2, D1, B3, B4, B5, B6, B7. B1-B5 remain five distinct original blocker commits; B6 and B7 are distinct new blocker commits. No cherry-pick collapse, squash, fixup, merge commit, history rewrite, or force push is allowed.
B3/B4 retain every R9 evidence gate. In particular, unresolved `EVIDENCE_REQUIRED` for the exact provider `client_id -> message_id` binding stops B4 with no implementation, commit, or ledger append. B5 can land only after accepted B4. Even after B5 lands, every forward `stage`, `verify-stage`, or `promote` operation remains blocked until accepted B6 and B7 commits exist and all gates below pass.
## D1 design-only commit
D1 changes exactly these 23 paths and no others:
```text
docs/superpowers/plans/2026-07-15-v2r1-personal-weixin-r10-release-plan-amendment.md
contracts/personal-weixin/v1/SECURITY.md
contracts/personal-weixin/v1/golden-contract.schema.json
contracts/personal-weixin/v1/fixtures/01-tenant-account-entitlement.json
contracts/personal-weixin/v1/fixtures/02-readiness-ready.json
contracts/personal-weixin/v1/fixtures/03-readiness-field-missing.json
contracts/personal-weixin/v1/fixtures/04-readiness-stale.json
contracts/personal-weixin/v1/fixtures/05-readiness-plugin-digest-mismatch.json
contracts/personal-weixin/v1/fixtures/06-readiness-account-not-entitled.json
contracts/personal-weixin/v1/fixtures/07-readiness-account-not-running.json
contracts/personal-weixin/v1/fixtures/08-readiness-error.json
contracts/personal-weixin/v1/fixtures/09-web-login-start-request.json
contracts/personal-weixin/v1/fixtures/10-web-login-wait-request.json
contracts/personal-weixin/v1/fixtures/11-qr-pending.json
contracts/personal-weixin/v1/fixtures/12-need-verify-code.json
contracts/personal-weixin/v1/fixtures/13-invalid-verify-code.json
contracts/personal-weixin/v1/fixtures/14-expired.json
contracts/personal-weixin/v1/fixtures/15-failed.json
contracts/personal-weixin/v1/fixtures/16-already-connected.json
contracts/personal-weixin/v1/fixtures/17-confirmed.json
contracts/personal-weixin/v1/fixtures/18-unknown-upstream-fail-closed.json
contracts/personal-weixin/v1/fixtures/19-authenticated-inbound-event.json
contracts/personal-weixin/v1/fixtures/20-unbind-unsupported.json
```
D1 validation requires JSON parse, Draft 2020-12 schema validation of every fixture, negative mutation tests, exact 23-path comparison, `git diff --check`, placeholder/secret scan, and confirmation that no runtime/deploy/release-active path changed.
## Preserved R9 blocker allowlists
B1 and B2 are already accepted at the immutable SHAs above. Their actual commit path sets, parent SHAs, and trees are the allowlists; compare with `git diff-tree --no-commit-id --name-only -r <sha>` and reject any mismatch. B1 has six actual paths under `openclaw/plugins/aios-tenant-boundary/`; B2 has exactly 43 actual package/import/matrix paths. No later blocker may amend them.
B3 changes exactly these 15 R9 paths:
```text
active-runtime/app/aios_v2r1/identity.py
active-runtime/app/aios_v2r1/tenant_context.py
active-runtime/app/aios_v2r1/ingress_service.py
active-runtime/app/aios_v2r1/bridge_auth.py
active-runtime/app/aios_v2r1/weixin_projection.py
fixes/patch_openclaw_weixin_v2r1_ingress.py
tests/v2r1/test_bridge_auth.py
tests/v2r1/test_weixin_projection.py
tests/integration/test_v2r1_bridge_transport.py
tests/test_weixin_v2r1_ingress_bridge.py
tests/fixtures/weixin_v2r1/text.json
tests/fixtures/weixin_v2r1/quoted-text.json
tests/fixtures/weixin_v2r1/image-with-text.json
tests/fixtures/weixin_v2r1/unresolved-reference.json
release/v2r1c0-rc1/weixin-bridge-evidence.json
```
B4 changes exactly these 19 R9 paths and remains evidence-stopped until both R9 evidence files are accepted:
```text
active-runtime/app/aios_v2r1/outbox.py
active-runtime/app/aios_v2r1/hermes_http.py
active-runtime/app/aios_v2r1/hermes_worker.py
active-runtime/app/aios_v2r1/outbound_receipt.py
active-runtime/app/aios_v2r1/ingress_service.py
active-runtime/app/aios_v2r1/message_ledger.py
tests/v2r1/test_outbox.py
tests/v2r1/test_hermes_http.py
tests/v2r1/test_outbound_receipt.py
tests/integration/test_v2r1_delivery_flow.py
fixes/patch_openclaw_weixin_outbound_quotes.py
fixes/patch_openclaw_weixin_outbound_receipts.py
openclaw/plugins/aios-tenant-boundary/dist/receipt-client.js
openclaw/plugins/aios-tenant-boundary/dist/outbound-receipt-journal.js
openclaw/plugins/aios-tenant-boundary/test/receipt-client.test.js
tests/test_weixin_outbound_quote_timestamp.py
tests/test_weixin_outbound_receipt_boundary.py
release/v2r1c0-rc1/hermes-http-contract-evidence.json
release/v2r1c0-rc1/weixin-outbound-binding-evidence.json
```
B5 changes exactly these 14 R9 paths:
```text
deploy/v2r1/release_ctl.py
deploy/v2r1/capture_live_preflight.py
deploy/v2r1/install.sh
deploy/v2r1/validate.sh
deploy/v2r1/healthcheck.sh
deploy/v2r1/rollback.sh
deploy/v2r1/aios-v2r1-candidate-gateway.service
deploy/v2r1/aios-v2r1-production-gateway.service
deploy/v2r1/aios-v2r1-ingress.service
deploy/v2r1/aios-v2r1-hermes-worker.service
deploy/v2r1/openclaw-candidate.json5
release/v2r1c0-rc1/FLEET_UNSUPPORTED
tests/deploy/test_v2r1_release_contract.py
release/v2r1c0-rc1/RELEASE.md
```
## B6: evidence-bound OpenClaw personal-Weixin candidate
B6 changes exactly these 13 paths:
```text
openclaw/candidates/personal-weixin-r10/README.md
openclaw/candidates/personal-weixin-r10/manifest.json
openclaw/candidates/personal-weixin-r10/src/golden-contract.js
openclaw/candidates/personal-weixin-r10/src/gateway-inbound-auth.js
openclaw/candidates/personal-weixin-r10/plugin/openclaw.plugin.json
openclaw/candidates/personal-weixin-r10/plugin/index.js
fixes/patch_openclaw_personal_weixin_login.py
fixes/patch_openclaw_personal_weixin_gateway_auth.py
openclaw/candidates/personal-weixin-r10/test/golden-contract.test.js
openclaw/candidates/personal-weixin-r10/test/gateway-auth.test.js
tests/personal_weixin/test_golden_fixtures.py
tests/integration/test_personal_weixin_gateway_contract.py
release/v2r1c0-rc1/personal-weixin-b6-evidence.json
```
Before B6 code, evidence records exact installed upstream source commit, every patch target path/digest, plugin loader version/digest, Gateway auth owner, credential files, and candidate-only state/config. Stop on inference or drift. Tests are RED before implementation and prove: required nonempty opaque `sessionKey`; no account fallback; exact canonical statuses and readiness shapes; unknown status fail-closed; 4-8 digit one-shot `verifyCode` with no persistence/log/response; exact event body with no authentication/tenant/user/session assertions; transport signature/skew/nonce/replay checks; exact 501 zero mutation; byte-idempotent patches; build/runtime inspect in isolated candidate state. The B6 evidence JSON is produced only after these gates pass.
## B7: tenant-scoped Portal adapter and durable challenge
B7 changes exactly these 13 paths:
```text
active-runtime/app/aios_v2r1/personal_weixin/official_login.py
active-runtime/app/aios_v2r1/personal_weixin/adapter.py
portal/personal_weixin/views.py
portal/personal_weixin/urls.py
portal/personal_weixin/services.py
portal/personal_weixin/templates/personal_weixin/bind.html
tests/personal_weixin/test_adapter.py
tests/personal_weixin/test_portal_views.py
tests/integration/test_personal_weixin_golden_flow.py
release/v2r1c0-rc1/personal-weixin-source-baseline.json
release/v2r1c0-rc1/personal-weixin-source-baseline.sha256
release/v2r1c0-rc1/personal-weixin-canary-contract.json
release/v2r1c0-rc1/personal-weixin-rollback-contract.json
```
Tests are RED before B7 implementation and prove: Django authentication/CSRF; server-session tenant resolution; browser `accountId` treated only as a preallocated-slot reference and current entitlement rechecked on every list/readiness/start/wait/status; exact `sessionKey` forwarding without fallback; live canonical readiness; authenticated Gateway transport context separate from the six-field event body; durable challenge record owning tenant/user/account/session digest; hash-only secret storage; transactional/CAS single consumption; exact replay idempotence; altered replay/concurrency/expiry/cross-tenant denial with zero mutation; no provider token/raw iLink/verify code/challenge code persistence or leakage; size/rate/no-store controls; restart; and unbind 501 before all mutations/calls/jobs.
## Canonical contract gates
`sessionKey` is nonempty and exact. Canonical results are:
```text
qr_pending connected=false alreadyConnected=false terminal=false needsVerifyCode=false
need_verifycode connected=false alreadyConnected=false terminal=false needsVerifyCode=true
invalid_verifycode connected=false alreadyConnected=false terminal=false needsVerifyCode=true
expired connected=false alreadyConnected=false terminal=true needsVerifyCode=false
failed connected=false alreadyConnected=false terminal=true needsVerifyCode=false
already_connected connected=false alreadyConnected=true terminal=true needsVerifyCode=false
confirmed connected=true alreadyConnected=false terminal=true needsVerifyCode=false
```
`binded_redirect` maps to `already_connected`. An unknown upstream status maps to canonical `failed/errorCode=unknown_upstream_status`. Readiness always uses the same complete shape: missing fields, stale evidence, plugin digest mismatch, absent entitlement, not-running account, and Gateway error all produce `ready=false`; only a live authenticated all-green snapshot produces `ready=true/code=ready`.
The inbound event body is exactly `eventId/accountId/senderId/chatId/challengeCode/observedAt`; transport authentication and server-resolved tenant/user/session context are not body fields. Fixture secrets are test inputs only. Raw `verifyCode` and `challengeCode` never enter persistence, logs, responses, URLs, analytics, traces, metrics labels, or job arguments. Raw `sessionKey` appears only where the golden login request/result contract requires it; it is never persisted or logged and is forwarded byte-exact without fallback.
## Merge, canary, promotion, and rollback gates
For each D1/B3-B7 row: require the exact parent row SHA, one non-merge commit, exact sorted path allowlist, clean `diff --check`, focused and carried tests, reviewer acceptance, then append `label/SHA/parent/tree` to the worktree-local ledger. No row may start from an unaccepted predecessor.
After B7, rebuild once from the accepted B7 tree. Stage one isolated candidate using B5 controls and no active configuration. Canary exactly one explicitly entitled `(tenant-canary, account-canary)` pair. Before traffic, require live Gateway/plugin/account readiness with expected digests and freshness. Exercise all golden outcomes, invalid and unknown fail-closed paths, restart, concurrent waits, atomic challenge consumption, exact replay, altered replay, expiry, unauthenticated event, tenant/account mismatch, cross-tenant IDOR, secret redaction, and exact end-to-end unbind 501 with zero durable/runtime/upstream/job mutation. Any missing evidence, extra account, digest drift, stale snapshot, noncanonical status, secret observation, or mutation fails the canary and blocks promotion.
Promotion accepts only the exact artifact/config/plugin/source digests verified by canary; it never rebuilds, repatches, switches branches, edits `VERSION`/`baseline/current.json`, creates a tag, invokes Fleet, or changes unrelated services. Candidate and production artifacts must be byte-identical. B5 live preflight is recaptured and reconciled immediately before `verify-stage` and `promote`.
Rollback is armed before canary with the immediately preceding production artifact/config/plugin digests, units, credentials metadata, and health contract. On any gate failure, STOP blocks forward actions; invoke only B5's recorded rollback-only path. Restore byte-identical prior artifacts/config, never the candidate rebuild; do not delete STOP automatically; do not roll back the database absent a separately approved incompatibility plan. Verify previous digests, listeners, units, secret paths/modes, canonical readiness, and tenant/account isolation. If verification fails, record `ROLLBACK_FAILED`, keep STOP, and escalate without forward mutation.
@@ -0,0 +1,294 @@
# V2R1 Authenticated Runtime Bridge Design
**Date:** 2026-07-14
**Status:** Preflight design — B3/B4/B5 evidence-gated
**Release target:** V2R1C0 RC1
**Scope:** Executable OpenClaw policy compatibility, canonical Python packaging, authenticated Weixin loopback ingress, exact message authority, real Hermes HTTP dispatch, and digest-bound release operations.
## Decision and execution gates
Three alternatives were evaluated:
- **Alternative A — preserve the verified replay and stop at documentation.** Lowest immediate risk, but every runtime release blocker remains open.
- **Alternative B — patch only the Weixin path.** Demonstrates a message path but cannot prove plugin loading, transport authority, durable dispatch, artifact identity, or rollback.
- **Alternative C — close five independently reviewed blockers.** Prove the plugin, package one Python namespace, build the authenticated bridge, connect a durable outbox to the real Hermes HTTP router, then rehearse a digest-bound release.
Alternative C remains the selected architecture because active full-execution authorization covers implementation preparation. That authorization does not waive the following gates:
- B1 and B2 may start only after this corrected design and plan are reviewed.
- B3 stops unless the installed Weixin payload shape, patch target hashes, authority-map ownership, and transport signing boundary are evidenced.
- B4 stops unless Hermes request/response schema, router ownership, downstream timeout, idempotency behavior, and exact outbound message binding are evidenced.
- B5 stops unless B3 and B4 are accepted and the reconciled sentinel plus the V1R4C6 live-runtime snapshot are current for the candidate digest.
- The R9 D0 documentation correction becomes ledger `START` without consuming a blocker. It expands B2 executable coverage only; all authenticated transport, evidence, terminal, isolation, and release gates remain unchanged.
The present outbound evidence is insufficient, so B4 and B5 are currently stopped. This document defines the fail-closed path; it does not claim the missing evidence exists.
## Verified preflight observations
Read-only inspection on 2026-07-14 established these facts:
- OpenClaw is `2026.6.11` and exposes `plugins install --link`, `plugins inspect --runtime --json`, `config set`, `config validate`, and `doctor`.
- The OpenClaw schema requires a non-bundled plugin to opt into conversation-bearing hooks with `plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`.
- Without that opt-in, the tenant-boundary plugin's currently usable policy hook is `before_tool_call`; `before_agent_run` and `agent_end` cannot be treated as delivered authority.
- `aios-hermes-router.service` owns `/opt/aios-v23/shared/hermes_route_memory/hermes_router_service.py` and listens on `127.0.0.1:18791`.
- `GET http://127.0.0.1:18791/health/ready` returns router readiness and identifies the executor health URL.
- `POST http://127.0.0.1:18791/internal/hermes/route` is the router submission endpoint.
- The router forwards to the executor with an exact 140-second timeout. The existing direct Weixin helper uses 120 seconds, so it is incompatible and cannot be reused as the worker deadline.
- Router ownership and schema are inspectable, but replay/idempotency behavior for repeated `route_id` is not proved.
- A Weixin reference event exposes `ref_msg.message_item.msg_id` and `ref_msg.message_item.create_time_ms`, but not the original outbound `client_id`. The send acknowledgement exposes only `ret` and `errmsg`. No exact `client_id -> message_id` binding currently exists.
## Execution modes and terminal semantics
The gateway has exactly two modes:
- `disabled`: the V2R1 bridge performs no submission and the legacy message path may run.
- `enforced`: every eligible Weixin event is handled by the V2R1 bridge. The legacy path is prohibited.
There is no shadow, dual-send, or fall-through mode. In `enforced` mode:
- `ACCEPTED` is terminal. The Node caller must not invoke the legacy handler, Hermes directly, or a second transport path.
- A duplicate with the same canonical event and payload returns the same accepted receipt and is also terminal.
- `AUTH_FAILED`, `VALIDATION_FAILED`, `CONFLICT`, and `INTERNAL_ERROR` are terminal runtime results for that attempt. They never authorize legacy fallback. `REPLAY_REJECTED` belongs only to the authenticated HTTP transport/service boundary and is never a `RuntimeIngressResponse.status`.
- A transport timeout requires a receipt-status query. A retry is allowed only when the status is absent and must use a fresh nonce while retaining the same exact event identity.
Legacy handling is therefore reachable only when configuration explicitly says `disabled`, never as error recovery.
## Architecture and data flow
```text
Authenticated Weixin event in isolated OpenClaw candidate gateway
-> Node bridge client reads bridge credential from CREDENTIALS_DIRECTORY
-> Node signs the exact method/path/unsigned_body object and POSTs the outer wrapper to 127.0.0.1
-> Python ingress service authenticates freshness, nonce, key role, and replay
-> server-side WeixinProjection parses exact protocol evidence
-> server-side root-owned authority map supplies tenant/cell/principal/session
-> Python signs an internal RuntimeWiring request with a separate key role
-> RuntimeWiring.ingest -> TenantRouter -> MessageLedger -> SessionPool
-> ingress receipt reaches terminal ACCEPTED
-> HermesOutbox -> dedicated Hermes worker
-> HermesHttpAdapter -> 127.0.0.1:18791/internal/hermes/route
-> Weixin send boundary -> outbound receipt evidence
```
Node never constructs `CanonicalMessage`, never opens the authority map, and never supplies tenant or cell authority. Python never trusts route claims from the raw Weixin object. The root-owned authority map is keyed by authenticated account, sender, and conversation evidence; its result is still re-resolved through `TenantRouter` before mutation.
## One POST signing contract
Every authenticated POST route uses exactly one wire shape; there is no `auth`, authorization header, nested signature, or route-specific signing variant:
```json
{"unsigned_body":{"schema_version":"aios.signed-request.v1","key_id":"bridge-current","issued_at_ms":1784000000000,"nonce":"base64url-16-byte-value","route_payload":{}},"signature":"lowercase-64-hex"}
```
`unsigned_body` contains exactly `schema_version`, `key_id`, `issued_at_ms`, `nonce`, and `route_payload`. `route_payload` is the route-specific content: ingress account/sender/conversation/raw event, receipt-status account plus one identifier, or outbound receipt. The signer constructs exactly:
```json
{"method":"POST","path":"<exact route>","body":{"schema_version":"aios.signed-request.v1","key_id":"bridge-current","issued_at_ms":1784000000000,"nonce":"base64url-16-byte-value","route_payload":{}}}
```
The signing input is canonical JSON encoded as UTF-8, with object keys recursively sorted by Unicode code point, `,` and `:` separators, no insignificant whitespace, no ASCII escaping of Unicode, no floats, and protocol IDs represented as strings. `signature` is lowercase 64-hex HMAC-SHA256 of those bytes. It is outside `unsigned_body` and outside the signing input. Verification reconstructs the same object using literal method `POST` and the exact request path; no normalized, decoded, prefix-matched, or caller-declared path is accepted.
Transport authentication is fail-closed:
- accepted clock skew is at most 30 seconds in either direction;
- `(key_id, nonce)` is retained in a durable replay cache for five minutes;
- a nonce decoding to any length other than 16 bytes is rejected;
- a repeated nonce is `REPLAY_REJECTED`, even when payload and signature are identical;
- every retry creates a cryptographically fresh nonce and `issued_at_ms` while preserving the exact event/message identity used for idempotency;
- the keyring contains one active key and at most one previous key; `key_id` selects the key and unknown IDs fail;
- rotation first installs the new verifier key, then switches the Node signer, then removes the old key only after the five-minute replay window and maximum request lifetime have elapsed.
The Node candidate gateway receives the bridge-ingress and receipt-read keyrings through separate systemd `LoadCredential=` entries below `$CREDENTIALS_DIRECTORY`. It never receives the Python internal signing key or authority map. Only after B4 evidence is accepted, the Node Weixin sender receives a third, separate `outbound-receipt-write` credential for authenticated callbacks.
## Service routes and bounded responses
The Python service binds loopback only and exposes exactly:
- `GET /health/live`
- `GET /health/ready`
- `POST /v1/ingress`
- `POST /v1/receipts/status`
- `POST /v1/outbound-receipts`
`POST /v1/ingress` requires the `bridge-ingress` HMAC role. `POST /v1/receipts/status` requires `receipt-read`; its `route_payload` contains `account_id` plus exactly one of `event_id` or `receipt_id`. Both or neither is `VALIDATION_FAILED`. Resolution is restricted to the same account and event scope, and unknown/cross-account identifiers return the same bounded result. `POST /v1/outbound-receipts` requires `outbound-receipt-write`; no receipt role can submit ingress. Every route uses the one POST signing contract above and the same nonce, skew, replay, rotation, and fresh-retry rules.
Request bodies are at most 1 MiB. Any JSON response is at most 4096 bytes and contains only stable codes and bounded identifiers. The ingress response fields are `status`, `event_id`, `message_id`, and `receipt_id`. The receipt-status response fields are `status`, `receipt_id`, `event_id`, `updated_at`, `outbox_status`, `outbound_status`, and `evidence_state`. No response contains message bodies, quote text, attachments, route objects, paths, signatures, keys, provider payloads, or exception text.
Runtime-to-HTTP status mapping is exact:
| Stable status | HTTP | Retry rule |
|---|---:|---|
| `ACCEPTED` | 202 | Terminal; query receipt after transport uncertainty |
| `AUTH_FAILED` | 401 | No retry until credential or authority changes |
| `REPLAY_REJECTED` | 409 | Transport/service only; retry same event with a fresh nonce |
| `VALIDATION_FAILED` | 400 | No retry |
| `CONFLICT` | 409 | Operator review |
| `INTERNAL_ERROR` | 503 | Query receipt first; identical event may retry with fresh nonce |
## Canonical Python package
The release package has one V2R1 import identity: `aios_v2r1`. There is no `active_runtime` compatibility shim, alias package, `sys.modules` alias, or copied source tree.
`active-runtime/pyproject.toml` packages `aios_v2r1` from `active-runtime/app`. Repository tests use `PYTHONPATH='active-runtime:active-runtime/app'`: legacy modules import as `app.*`, while V2R1 imports as `aios_v2r1.*`. The implementation plan enumerates all 23 known `active_runtime.app` test imports and replaces them explicitly. Full collection, full pytest, and wheel inspection must prove the wheel contains one V2R1 namespace and that source and installed imports resolve to `aios_v2r1` only.
Packaging acceptance is also the executable completeness gate for seven preserved runtime components. Message Ledger must prove exact-ID/no-fallback semantics, idempotency/conflict, tenant/cell/direction isolation, expiry/purge/restart/concurrency, and sanitized SQLite errors. Memory must prove every namespace, cross-scope denial, shared-artifact read-only behavior, qualified-key traversal rejection, and disabled search. Secret must prove reference, broker path, scope, kind, version, identifier, no-value-leakage, and fail-closed broker behavior. Audit must prove genesis and tamper/delete/reorder detection, Unicode canonicalization, concurrency, restart, validation, tenant isolation, and sanitized SQLite errors. Hermes Profile must prove exact environment, absolute `0700` roots, traversal/symlink denial, scope, idempotence, and no environment inheritance. Cell Manager/CLI must prove one cell per tenant, an explicit state graph, atomic concurrent persistence, corrupt-registry fail-closed behavior, stable JSON/exit codes, and restart. Fabric must prove that claims return `running` consistently with durable state, isolation, one concurrent claimant, non-claimable states, restart, and sanitized SQLite errors.
The original 29 B2 paths are extended by exactly fourteen reviewed paths: seven production modules (`message_ledger.py`, `memory_scope.py`, `secret_scope.py`, `audit.py`, `hermes_profile.py`, `cell_manager.py`, and `hermes_fabric.py`) and seven matrix tests (`test_message_ledger_append.py`, `test_memory_scope.py`, `test_secret_scope.py`, `test_audit.py`, `test_hermes_profile.py`, `test_cell_manager.py`, and `test_hermes_fabric.py`). `cli.py` remains one of the original package paths. A production module changes only after its focused test has been observed failing for the intended contract; already-correct behavior is a characterization and must not be weakened merely to manufacture a RED.
The B2 review requires exactly 43 changed paths, at least 160 passing carried V2R1/integration/package tests with every matrix bullet represented, zero full-collection errors, a passing complete pytest suite, the 15 Node tests, the real isolated loader in default and opt-in modes, compileall, wheel identity, and a clean tree. These coverage additions do not authorize B3 bridge, B4 Hermes HTTP/outbound, B5 deployment, active service, main, tag, `VERSION`, or baseline mutation.
## Exact projection, quote, and attachment authority
`WeixinProjection` runs in Python after transport authentication. It preserves numeric Weixin IDs from the JSON token as decimal strings and rejects a value that has already passed through unsafe JavaScript-number conversion.
- `event_id` is deterministic from authenticated account, sender, conversation, direction, and exact protocol event ID.
- `message_id` is an exact provider/server message ID when supplied.
- `reply_to_message_id` comes only from an explicit reference ID.
- `quoted_body` comes only from explicit referenced text or from `MessageLedger.resolve_quote()` using the fully scoped exact message ID.
- Timestamp, nearest-message order, recent-message cache, numeric approximation, prefix, similarity, and local client ID are never quote authority.
`CanonicalAttachment` contains `attachment_id`, `kind`, `media_type`, `sha256`, and `size_bytes`. Attachment bytes are accepted only when exact protocol identity and digest/size verification both pass. A reference without exact media evidence cannot fall back to the latest image.
`Date.now()` is local send telemetry only. It may populate a local observation timestamp but cannot populate a provider timestamp, resolve a quote, correlate a client ID, or select a message.
## Outbound evidence and hard stop
The current Weixin protocol evidence cannot bind an outbound client ID to a later reference:
- send acknowledgement: `ret` and `errmsg` only;
- later reference: `ref_msg.message_item.msg_id` and `ref_msg.message_item.create_time_ms`;
- absent evidence: the original outbound `client_id` echoed beside the provider `message_id`.
Therefore outbound quote authority is unavailable. A successful send may be recorded as transport success, but `OutboundReceipt.evidence_state` must be `EVIDENCE_REQUIRED`, and the release gate must hard STOP. `sent` does not mean `confirmed`, and neither timestamp equality nor proximity may upgrade it.
The only acceptable future unlock is verified provider/reference evidence that echoes or otherwise exactly binds `client_id -> message_id`. That evidence must include the raw protocol fields, parser test, collision test, and a durable mapping scoped by tenant, cell, account, peer, direction, and exact IDs. Until then no outbound record becomes quote authority.
`OutboundReceipt` has stable fields:
```text
receipt_id, outbox_id, tenant_id, cell_id, channel, channel_account_id,
peer_id, client_message_id, provider_message_id, payload_sha256,
status = sent | confirmed | failed,
evidence_state = EXACT | EVIDENCE_REQUIRED
```
`provider_message_id` is null while evidence is unavailable. `POST /v1/outbound-receipts` rejects any attempt to synthesize it from `Date.now()`, `ref_msg.message_item.create_time_ms`, message order, or approximate matching. Every local timestamp field is explicitly suffixed `_ms` and remains telemetry.
After B4 evidence is accepted, the actual Node Weixin sender owns its outbound callback retry journal at `$STATE_DIRECTORY/outbound-receipts`. Its systemd unit declares a gateway-specific `StateDirectory=` and `StateDirectoryMode=0700`; systemd owns that directory to the unit's `User=`/`Group=`, and no other gateway service user may read it. The sender receives its separate `outbound-receipt-write` `LoadCredential=` entry only at that gate. Each journal entry is one sanitized JSON record per client ID, named by a safe fixed-width digest of that ID. It contains only bounded identifiers, send-success state, callback-attempt count, and next-attempt metadata—never message bodies, quote text, attachments, signatures, key material, credentials, or provider payloads.
Persistence is exact: create a same-directory temporary file with mode `0600`, owned and readable only by that gateway's service user, write the sanitized record, `fsync` the file, atomically rename it to its final `.pending` name, then `fsync` the directory. Startup recovery and a background worker retry authenticated callbacks with bounded attempts and backoff; they never call the Weixin send operation again. A pending record is deleted, followed by directory `fsync`, only after the Python callback returns an authenticated application ACK. Transport uncertainty, non-ACK responses, and callback authentication failures retain the record for bounded retry.
Ownership is deliberately split. Node owns this send-success/callback-retry journal. Python owns the authenticated receipt endpoint, receipt store, outbox, and Hermes worker state. Python does not create or own a second send journal, so there is only one durable resend boundary.
## Real Hermes HTTP adapter and outbox semantics
The runtime does not claim that the local `HermesFabric` SQLite primitive is the production Hermes transport. Production dispatch uses:
- readiness: `GET http://127.0.0.1:18791/health/ready`;
- submission: `POST http://127.0.0.1:18791/internal/hermes/route`;
- owner: `aios-hermes-router.service`;
- downstream executor budget: exactly 140 seconds;
- worker HTTP deadline: 150 seconds, so the known 120-second direct-bridge mismatch is removed.
`HermesHttpAdapter` validates bounded request and response schemas before accepting a result. `HermesOutbox` provides durable intent and leases, but the system makes no exactly-once claim. Exact local states are `pending`, `leased`, `delivered`, `delivery_unknown`, and `dead`.
Repeated delivery behavior depends on evidence:
- if the verified router contract proves the same `route_id` and payload digest are idempotent, an expired/failed attempt may retry with that exact pair;
- if idempotency is false, the worker never automatically retries an ambiguous submission;
- if idempotency is unresolved, B4 stops before implementation and commit;
- a client timeout or connection loss after send becomes `delivery_unknown`, never a fabricated failure or success.
B4 evidence must record the live listener, owning unit, executable/source digest, readiness response schema, route request fields, route response fields, exact 140-second downstream timeout, router tenant/user ownership rules, and repeated-`route_id` behavior. The dedicated `aios-v2r1-hermes-worker.service` is installed only in B5 after this evidence is accepted.
## OpenClaw plugin compatibility and permissions
The plugin configuration contract is exact:
- `blockUnknownAgentRuns`: boolean, default `false`;
- `approvalTimeoutMs`: integer, minimum `1000`, maximum `300000`, default `60000`;
- package and manifest versions are identical;
- every property read by runtime code appears in `configSchema`.
Unit tests with a fake API remain useful, but they are insufficient. B1 must run the real OpenClaw loader in an isolated state/config directory. It must prove two permission states:
1. Default hook permissions: runtime inspection shows only `before_tool_call` is usable for this plugin; no test treats `before_agent_run` provenance as present.
2. Explicit conversation access: set `plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`, validate config, reload/inspect runtime, and prove `before_agent_run`, `before_tool_call`, and `agent_end` are installed.
The default remains fail-closed for side effects because absent run provenance cannot authorize them. Candidate production never relies on the default-only state; the isolated staging config explicitly opts in and is validated.
## Isolated candidate staging and plugin loader sequence
B5 defines separate staging and production gateway units plus the isolated ingress and worker units. Staging starts the candidate trio; production gateway activation occurs only through the evidence-gated promotion/migration:
- `aios-v2r1-candidate-gateway.service`
- `aios-v2r1-production-gateway.service`
- `aios-v2r1-ingress.service`
- `aios-v2r1-hermes-worker.service`
The candidate gateway uses its dedicated service user with `StateDirectory=aios-v2r1-candidate-gateway`; the migrated production gateway uses a different dedicated service user with `StateDirectory=aios-v2r1-production-gateway`. Both units set `StateDirectoryMode=0700`, and both resolve their journal only as `$STATE_DIRECTORY/outbound-receipts`. The names, absolute paths, owners, and journal contents are distinct; staging and production never share, bind-mount, or symlink journal state. The current root-run production gateway retains its own root-owned state only until an explicit audited migration. Candidate staging never reads that state. Migration verifies pending records contain no bodies or secrets, installs them only into the production-specific directory with its service user ownership and mode `0600`, and leaves no root-owned production journal in active use.
The candidate gateway has its own OpenClaw state directory, config file, port, credentials, and plugin link. It does not edit or restart the active V1R4C6 gateway. The loader sequence against the candidate state is fixed:
```bash
openclaw plugins install --link "$candidate_release/openclaw/plugins/aios-tenant-boundary"
openclaw plugins inspect aios-tenant-boundary --runtime --json
openclaw config set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess true --strict-json
openclaw config validate
openclaw doctor --lint --json
openclaw doctor --post-upgrade --json
openclaw plugins inspect aios-tenant-boundary --runtime --json
```
The environment supplies the isolated config/state paths. Any command that resolves to the active V1R4C6 config is a hard stop. Inspection output must prove the linked candidate path, version, hooks, and permission state.
## Artifact, preflight evidence, promotion, and rollback
One deterministic archive and manifest are built from a clean reviewed commit. Staging and production consume byte-identical artifact digests. `NOOP_DIGEST_MATCH` returns exit 0 and performs no extraction, migration, symlink change, restart, or deployment audit increment.
The executable controller is `python3 deploy/v2r1/release_ctl.py` with commands `build`, `stage`, `verify-stage`, `promote`, `status`, and `rollback`. Forward state transitions are exactly `BUILT -> STAGED -> STAGE_VERIFIED -> PRODUCTION`; skipping or reversing a forward edge is rejected. `capture_live_preflight.py` creates the evidence file and every mutating controller command accepts it as `--preflight-file`; callers never supply digest strings. The controller validates the evidence schema, exact host identity, reconciled sentinel health and candidate refs, required runtime fields, and capture freshness of at most 300 seconds. It then computes the artifact, reconciled-sentinel, and runtime-snapshot SHA-256 digests internally and persists that triplet in the state record.
`verify-stage` and `promote` each invoke the live collector again, validate the fresh result by the same rules, recompute the triplet internally, and compare the recaptured live state with the recorded candidate state. Any host, sentinel, candidate-ref, runtime-field, artifact, or digest drift rejects the transition. `status` is read-only. Rollback transitions are `PRODUCTION -> ROLLBACK_STARTED -> ROLLED_BACK`; a failed recovery records `ROLLBACK_FAILED` without claiming the prior state is active. `NOOP_DIGEST_MATCH` leaves the current state and all three digests unchanged.
Before staging and again before promotion, both pieces of live evidence are mandatory:
- reconciled Gitea branch-consistency sentinel: `status=healthy`, `drift_count=0`, and recorded refs matching the candidate manifest;
- V1R4C6 live-runtime snapshot: active Git SHA, service units, process commands, listener ports, OpenClaw version, config/plugin digests, credential metadata without secrets, state/database paths, mounts, current artifact identity, and rollback target.
The snapshot is immutable, SHA-256-addressed, and timestamped. Promotion rejects a snapshot older than 300 seconds or any live drift from it. `capture_live_preflight.py` creates these evidence inputs from live inspection; `release_ctl.py` may validate and recapture them but may not invent missing fields or accept caller-asserted digests.
The host sentinel `/var/lib/aios-v2r1/STOP` blocks forward mutation: install, migration, staging activation, promotion, candidate/production restart, and new artifact selection. It does not block one constrained recovery command:
```text
rollback --rollback-only --to-previous-recorded --reason-file "$reason_file"
```
That escape may only select the exact previous digest and its recorded compatible database snapshot; it cannot install new bytes, run forward migrations, choose an arbitrary digest, remove the sentinel, or start a new candidate. It writes an audit record before and after the attempt. If previous-state evidence is missing or fails digest/integrity checks, rollback also stops.
The tracked `release/v2r1c0-rc1/FLEET_UNSUPPORTED` capability sentinel remains authoritative. `OpenClawFleet` and `openclaw fleet` are outside this release.
## Stop conditions
Preparation or release stops when any of these is true:
- corrected design/plan review is not accepted;
- a B3/B4/B5 evidence gate remains unresolved;
- authoritative Git refs differ from reviewed values or the worktree is dirty;
- the real plugin loader does not prove the required hook permissions;
- transport key role, `key_id`, timestamp, exact nonce length, skew, replay cache, rotation, or fresh-retry behavior fails;
- Node attempts projection/authority resolution or Python trusts route claims from the raw event;
- `ACCEPTED` can fall through to legacy processing, or legacy runs while bridge mode is `enforced`;
- quote or attachment resolution uses timestamp, approximation, recent order, or a local client ID;
- outbound evidence remains `EVIDENCE_REQUIRED`;
- Hermes schema, ownership, 140-second downstream budget, router identity rules, or repeated-route behavior is unresolved;
- any code or document claims exactly-once Hermes delivery;
- the candidate gateway is not isolated from V1R4C6;
- reconciled sentinel or V1R4C6 live-runtime snapshot is absent, stale, inconsistent, or digest-invalid;
- artifact, migration, staging, or production digest differs;
- the STOP sentinel blocks a forward action;
- constrained rollback cannot prove the exact previous artifact and compatible snapshot;
- any main, tag, `VERSION`, baseline, live service, or deployment mutation occurs without the separate release authorization.
## Acceptance
The design is review-complete when the plan contains exactly five blocker commits, dynamically anchors their parent chain at B1 start, enumerates all legacy import edits, and has executable RED/GREEN/review gates. R9 preparation additionally requires D0 as `START`, B1 as its child, B2 as one 43-path child commit, the full seven-component executable matrix, and a partial ledger containing exactly `START,B1,B2`. Runtime release acceptance additionally requires all B3/B4/B5 evidence gates, the full Python collection and suite, the real Node/OpenClaw loader harness, exact receipt semantics, isolated candidate staging, deterministic artifacts, current live evidence, and rehearsed constrained rollback.
+111
View File
@@ -0,0 +1,111 @@
import {
classifyRun,
decideToolCall,
resolveSenderId,
runKey,
} from "./policy.js";
const MAX_RUN_AGE_MS = 60 * 60 * 1000;
function prune(activeRuns, now = Date.now()) {
for (const [key, value] of activeRuns.entries()) {
if (now - value.recordedAt > MAX_RUN_AGE_MS) activeRuns.delete(key);
}
}
function approvalTimeout(config) {
const value = config.approvalTimeoutMs;
return Number.isInteger(value) && value >= 1000 && value <= 300000
? value
: 60000;
}
export default {
id: "aios-tenant-boundary",
name: "AIOS Tenant Boundary",
description: "Fail-closed user-origin and side-effect policy for Tenant Cells.",
register(api) {
const activeRuns = new Map();
api.on(
"before_agent_run",
async (event, ctx) => {
prune(activeRuns);
const config = event.context?.pluginConfig ?? api.pluginConfig ?? {};
const trust = classifyRun(ctx, config);
const key = runKey(event, ctx);
const existing = key ? activeRuns.get(key) : undefined;
if (existing && existing.senderId !== trust.senderId) {
return {
outcome: "block",
reason: "run_scope_sender_conflict",
message: "This run scope is already bound to a different authenticated sender.",
};
}
if (key) {
activeRuns.set(key, { ...trust, recordedAt: Date.now() });
}
if (
config.blockUnknownAgentRuns === true &&
trust.trusted !== true &&
trust.reason !== "job_id_present"
) {
return {
outcome: "block",
reason: trust.reason,
message: "This message cannot be verified as coming from the active authenticated user.",
};
}
return { outcome: "pass" };
},
{ priority: 100 },
);
api.on(
"before_tool_call",
async (event, ctx) => {
prune(activeRuns);
const config = event.context?.pluginConfig ?? api.pluginConfig ?? {};
const key = runKey(event, ctx);
let trust = key ? activeRuns.get(key) : undefined;
const senderId = resolveSenderId(ctx);
if (trust && senderId && trust.senderId !== senderId) {
trust = { trusted: false, reason: "run_scope_sender_conflict" };
}
const decision = decideToolCall(event.toolName, trust, config);
if (decision.action === "block") {
return {
block: true,
blockReason: `AIOS V2R1 origin policy denied tool call: ${decision.code}`,
};
}
if (decision.action === "approval") {
return {
requireApproval: {
title: `Approve ${String(event.toolName)}`,
description: "Authenticated user requested a side-effecting tool call in this Tenant Cell.",
severity: "warning",
timeoutMs: approvalTimeout(config),
allowedDecisions: ["allow-once", "deny"],
pluginId: "aios-tenant-boundary",
},
};
}
return undefined;
},
{ priority: 100 },
);
api.on(
"agent_end",
async (event, ctx) => {
const key = runKey(event, ctx);
if (key) activeRuns.delete(key);
},
{ priority: 100 },
);
},
};
+91
View File
@@ -0,0 +1,91 @@
const DEFAULT_READ_ONLY_TOOLS = Object.freeze([
"read", "grep", "glob", "find", "ls", "web_search", "web_fetch",
"memory_search", "sessions_list", "sessions_history", "session_status",
]);
function strings(value) {
return Array.isArray(value)
? value.filter((item) => typeof item === "string" && item.trim())
.map((item) => item.trim())
: [];
}
export function resolveSenderId(ctx = {}) {
const direct = typeof ctx.senderId === "string" ? ctx.senderId.trim() : "";
const nested = typeof ctx.channelContext?.sender?.id === "string"
? ctx.channelContext.sender.id.trim()
: "";
return direct || nested || undefined;
}
export function classifyRun(ctx = {}, config = {}) {
const senderId = resolveSenderId(ctx);
const trusted = new Set(strings(config.trustedSenderIds));
const blocked = new Set(strings(config.blockedSenderIds));
if (typeof ctx.jobId === "string" && ctx.jobId) {
return { trusted: false, origin: "automation", reason: "job_id_present" };
}
if (!senderId) {
return { trusted: false, origin: "system_or_unknown", reason: "sender_id_missing" };
}
if (blocked.has(senderId)) {
return { trusted: false, origin: "blocked_sender", reason: "sender_blocked", senderId };
}
if (config.requireExplicitTrustedSenders !== false && !trusted.has(senderId)) {
return { trusted: false, origin: "untrusted_sender", reason: "sender_not_allowlisted", senderId };
}
return {
trusted: true,
origin: "authenticated_channel_user",
reason: "sender_verified",
senderId,
};
}
export function decideToolCall(toolName, runTrust, config = {}) {
const name = typeof toolName === "string" ? toolName.trim().toLowerCase() : "";
const configured = strings(config.readOnlyTools).map((item) => item.toLowerCase());
const readOnly = new Set(configured.length ? configured : DEFAULT_READ_ONLY_TOOLS);
if (!name) {
return { action: "block", code: "tool_name_missing" };
}
if (readOnly.has(name)) {
return { action: "allow", code: "read_only" };
}
if (!runTrust || runTrust.trusted !== true) {
return {
action: "block",
code: runTrust?.reason || "run_provenance_missing",
};
}
if (config.requireApprovalForHumanSideEffects === false) {
return { action: "allow", code: "trusted_side_effect" };
}
return { action: "approval", code: "human_side_effect" };
}
export function runKey(event = {}, ctx = {}) {
const normalize = (value) => typeof value === "string" && value.trim()
? value.trim()
: undefined;
const sameField = (eventValue, contextValue) => {
const fromEvent = normalize(eventValue);
const fromContext = normalize(contextValue);
return {
valid: !(fromEvent && fromContext && fromEvent !== fromContext),
value: fromEvent || fromContext,
};
};
const runId = sameField(event.runId, ctx.runId);
const agentId = sameField(event.agentId, ctx.agentId);
const sessionId = sameField(event.sessionId, ctx.sessionId);
const sessionKey = sameField(event.sessionKey, ctx.sessionKey);
if (!runId.valid || !agentId.valid || !sessionId.valid || !sessionKey.valid) {
return undefined;
}
const selectedSession = sessionId.value || sessionKey.value;
return runId.value && agentId.value && selectedSession
? JSON.stringify([runId.value, agentId.value, selectedSession])
: undefined;
}
@@ -0,0 +1,25 @@
{
"id": "aios-tenant-boundary",
"name": "AIOS Tenant Boundary",
"description": "Enforces AIOS V2R1 tenant provenance and tool policy boundaries.",
"version": "2.1.0-rc.1",
"entry": "dist/index.js",
"configSchema": {
"type": "object",
"additionalProperties": false,
"properties": {
"requireExplicitTrustedSenders": { "type": "boolean", "default": true },
"trustedSenderIds": { "type": "array", "items": { "type": "string" }, "default": [] },
"blockedSenderIds": { "type": "array", "items": { "type": "string" }, "default": [] },
"readOnlyTools": { "type": "array", "items": { "type": "string" } },
"requireApprovalForHumanSideEffects": { "type": "boolean", "default": true },
"blockUnknownAgentRuns": { "type": "boolean", "default": false },
"approvalTimeoutMs": {
"type": "integer",
"minimum": 1000,
"maximum": 300000,
"default": 60000
}
}
}
}
@@ -0,0 +1,18 @@
{
"name": "@aios/openclaw-tenant-boundary",
"version": "2.1.0-rc.1",
"type": "module",
"description": "AIOS V2R1 Tenant Cell provenance and side-effect policy boundary for OpenClaw.",
"files": [
"dist",
"openclaw.plugin.json"
],
"scripts": {
"test": "node --test test/*.test.js"
},
"openclaw": {
"extensions": [
"./dist/index.js"
]
}
}
@@ -0,0 +1,64 @@
import assert from "node:assert/strict";
import { readFile } from "node:fs/promises";
import test from "node:test";
import plugin from "../dist/index.js";
const packageJson = JSON.parse(
await readFile(new URL("../package.json", import.meta.url), "utf8"),
);
const manifest = JSON.parse(
await readFile(new URL("../openclaw.plugin.json", import.meta.url), "utf8"),
);
function registrations(config = {}) {
const seen = [];
plugin.register({
pluginConfig: config,
on(name, handler, options) {
seen.push({ name, handler, options });
},
});
return seen;
}
test("package, manifest, and executable test command are release compatible", () => {
assert.equal(packageJson.version, "2.1.0-rc.1");
assert.equal(manifest.version, "2.1.0-rc.1");
assert.equal(packageJson.scripts.test, "node --test test/*.test.js");
});
test("schema declares every runtime-read property and exact B1 bounds", () => {
const properties = manifest.configSchema.properties;
const runtimeKeys = [
"approvalTimeoutMs",
"blockUnknownAgentRuns",
"blockedSenderIds",
"readOnlyTools",
"requireApprovalForHumanSideEffects",
"requireExplicitTrustedSenders",
"trustedSenderIds",
];
assert.deepEqual(Object.keys(properties).sort(), runtimeKeys);
assert.deepEqual(properties.blockUnknownAgentRuns, {
type: "boolean",
default: false,
});
assert.deepEqual(properties.approvalTimeoutMs, {
type: "integer",
minimum: 1000,
maximum: 300000,
default: 60000,
});
});
test("all three hooks register exactly once at priority 100", () => {
const seen = registrations();
assert.deepEqual(
seen.map(({ name }) => name).sort(),
["agent_end", "before_agent_run", "before_tool_call"],
);
for (const registration of seen) {
assert.deepEqual(registration.options, { priority: 100 });
}
});
@@ -0,0 +1,50 @@
import assert from "node:assert/strict";
import { readFile } from "node:fs/promises";
import { realpath } from "node:fs/promises";
const [mode, inspectPath] = process.argv.slice(2);
assert.ok(["default", "opt-in"].includes(mode), `unsupported mode: ${mode}`);
assert.ok(inspectPath, "inspect JSON path is required");
const data = JSON.parse(await readFile(inspectPath, "utf8"));
const plugin = data.plugin;
assert.equal(plugin.id, "aios-tenant-boundary");
assert.equal(plugin.version, "2.1.0-rc.1");
assert.equal(plugin.status, "loaded");
assert.equal(plugin.activated, true);
assert.equal(await realpath(plugin.rootDir), await realpath(new URL("..", import.meta.url)));
assert.equal(await realpath(plugin.source), await realpath(new URL("../dist/index.js", import.meta.url)));
assert.equal(data.install.source, "path");
assert.equal(await realpath(data.install.installPath), await realpath(plugin.rootDir));
const hooks = data.typedHooks
.map(({ name, priority }) => ({ name, priority }))
.sort((a, b) => a.name.localeCompare(b.name));
const expectedNames = mode === "default"
? ["before_tool_call"]
: ["agent_end", "before_agent_run", "before_tool_call"];
assert.deepEqual(hooks.map(({ name }) => name), expectedNames);
assert.ok(hooks.every(({ priority }) => priority === 100));
const diagnostics = data.diagnostics ?? [];
assert.equal(
diagnostics.filter(({ level, severity }) =>
["error", "fatal"].includes(String(level ?? severity).toLowerCase())).length,
0,
);
if (mode === "default") {
assert.deepEqual(
diagnostics.map(({ level, message }) => ({ level, message })).sort((a, b) => a.message.localeCompare(b.message)),
["agent_end", "before_agent_run"].map((hook) => ({
level: "warn",
message: `typed hook "${hook}" blocked because non-bundled plugins must set plugins.entries.aios-tenant-boundary.hooks.allowConversationAccess=true`,
})).sort((a, b) => a.message.localeCompare(b.message)),
);
} else {
assert.deepEqual(diagnostics, []);
}
const properties = plugin.configJsonSchema?.properties ?? {};
for (const key of ["approvalTimeoutMs", "blockUnknownAgentRuns"]) {
assert.ok(Object.hasOwn(properties, key), `missing runtime schema property: ${key}`);
}
@@ -0,0 +1,349 @@
import assert from "node:assert/strict";
import test from "node:test";
import plugin from "../dist/index.js";
import {
classifyRun,
decideToolCall,
resolveSenderId,
runKey,
} from "../dist/policy.js";
function registration(config = {}) {
const handlers = new Map();
plugin.register({
pluginConfig: config,
on(name, handler) {
handlers.set(name, handler);
},
});
return {
beforeAgentRun: handlers.get("before_agent_run"),
beforeToolCall: handlers.get("before_tool_call"),
agentEnd: handlers.get("agent_end"),
};
}
function agentContext(id, senderId) {
return {
runId: `run-${id}`,
agentId: "agent-main",
sessionId: "session-uuid-123",
sessionKey: "agent:main:weixin:direct:user",
...(senderId ? { senderId } : {}),
};
}
function toolContext(id, extra = {}) {
return {
runId: `run-${id}`,
agentId: "agent-main",
sessionId: "session-uuid-123",
sessionKey: "agent:main:weixin:direct:user",
...extra,
};
}
test("sender classification covers missing, blocked, allowlisted, and automation", () => {
assert.equal(resolveSenderId({ channelContext: { sender: { id: " nested " } } }), "nested");
assert.deepEqual(classifyRun({}, {}), {
trusted: false,
origin: "system_or_unknown",
reason: "sender_id_missing",
});
assert.equal(
classifyRun({ senderId: "blocked" }, { blockedSenderIds: ["blocked"] }).reason,
"sender_blocked",
);
assert.equal(
classifyRun(
{ senderId: "alice" },
{ requireExplicitTrustedSenders: true, trustedSenderIds: ["alice"] },
).trusted,
true,
);
assert.deepEqual(classifyRun({ jobId: "job-1" }, {}), {
trusted: false,
origin: "automation",
reason: "job_id_present",
});
});
test("unknown agent runs default to pass but fail closed when explicitly enabled", async () => {
const defaultHandlers = registration();
assert.deepEqual(
await defaultHandlers.beforeAgentRun({}, agentContext("default")),
{ outcome: "pass" },
);
const enforced = registration({ blockUnknownAgentRuns: true });
const denied = await enforced.beforeAgentRun({}, agentContext("denied"));
assert.equal(denied.outcome, "block");
assert.equal(denied.reason, "sender_id_missing");
assert.doesNotMatch(denied.reason + denied.message, /undefined|\r|\n/);
assert.deepEqual(
await enforced.beforeAgentRun({}, { ...agentContext("job"), jobId: "job-1" }),
{ outcome: "pass" },
);
});
test("read-only tools pass without provenance and side effects fail with a stable reason", async () => {
assert.deepEqual(decideToolCall("read", undefined, {}), {
action: "allow",
code: "read_only",
});
assert.deepEqual(decideToolCall("shell", undefined, {}), {
action: "block",
code: "run_provenance_missing",
});
const handlers = registration();
assert.equal(await handlers.beforeToolCall({ toolName: "read" }, {}), undefined);
const blocked = await handlers.beforeToolCall({ toolName: "shell" }, {});
assert.equal(blocked.block, true);
assert.equal(
blocked.blockReason,
"AIOS V2R1 origin policy denied tool call: run_provenance_missing",
);
});
test("trusted human side effects request approval with exact timeout validation", async () => {
for (const [configured, expected] of [
[undefined, 60000],
[1000, 1000],
[300000, 300000],
[999, 60000],
[300001, 60000],
[60000.5, 60000],
["1000", 60000],
[null, 60000],
]) {
const config = {
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice"],
};
if (configured !== undefined) config.approvalTimeoutMs = configured;
const handlers = registration(config);
const id = `approval-${String(configured)}`;
await handlers.beforeAgentRun({}, agentContext(id, "alice"));
const result = await handlers.beforeToolCall({ toolName: "shell" }, toolContext(id));
assert.equal(result.requireApproval.timeoutMs, expected, String(configured));
assert.deepEqual(result.requireApproval.allowedDecisions, ["allow-once", "deny"]);
}
});
test("active run provenance is isolated by registration, run, and sender", async () => {
const config = {
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice", "bob"],
};
const first = registration(config);
const second = registration(config);
await first.beforeAgentRun({}, agentContext("shared", "alice"));
const otherSender = await first.beforeToolCall(
{ toolName: "shell" },
toolContext("shared", { senderId: "bob" }),
);
assert.equal(otherSender.block, true);
assert.match(otherSender.blockReason, /run_scope_sender_conflict$/);
const otherRegistration = await second.beforeToolCall(
{ toolName: "shell" },
toolContext("shared"),
);
assert.equal(otherRegistration.block, true);
assert.match(otherRegistration.blockReason, /run_provenance_missing$/);
});
test("agent_end cleanup removes only the matching shared scope", async () => {
const handlers = registration({
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice", "bob"],
});
await handlers.beforeAgentRun({}, agentContext("alice-scope", "alice"));
await handlers.beforeAgentRun({}, agentContext("bob-scope", "bob"));
await handlers.agentEnd({}, toolContext("alice-scope"));
const alice = await handlers.beforeToolCall(
{ toolName: "shell" },
toolContext("alice-scope"),
);
assert.equal(alice.block, true);
const bob = await handlers.beforeToolCall(
{ toolName: "shell" },
toolContext("bob-scope"),
);
assert.ok(bob.requireApproval);
});
test("run provenance expires after the bounded age", async (t) => {
const originalNow = Date.now;
t.after(() => { Date.now = originalNow; });
let now = 1_000_000;
Date.now = () => now;
const handlers = registration({
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice"],
});
await handlers.beforeAgentRun({}, agentContext("expiring", "alice"));
now += 60 * 60 * 1000 + 1;
const result = await handlers.beforeToolCall(
{ toolName: "shell" },
toolContext("expiring"),
);
assert.equal(result.block, true);
assert.match(result.blockReason, /run_provenance_missing$/);
});
test("host-shaped lifecycle keeps distinct sessionId and sessionKey across all hooks", async () => {
const handlers = registration({
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice"],
});
const before = agentContext("host-shape", "alice");
const tool = toolContext("host-shape");
const end = toolContext("host-shape");
for (const ctx of [before, tool, end]) {
assert.equal(ctx.sessionId, "session-uuid-123");
assert.equal(ctx.sessionKey, "agent:main:weixin:direct:user");
assert.equal(ctx.runId, "run-host-shape");
assert.equal(ctx.agentId, "agent-main");
}
await handlers.beforeAgentRun({}, before);
const result = await handlers.beforeToolCall(
{ toolName: "shell" },
tool,
);
assert.ok(result.requireApproval);
assert.equal(result.block, undefined);
await handlers.agentEnd({}, end);
const cleaned = await handlers.beforeToolCall({ toolName: "shell" }, tool);
assert.equal(cleaned.block, true);
assert.match(cleaned.blockReason, /run_provenance_missing$/);
});
test("shared scope collision fails closed without overwriting original sender", async () => {
const handlers = registration({
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice", "bob"],
});
assert.deepEqual(
await handlers.beforeAgentRun({}, agentContext("collision", "alice")),
{ outcome: "pass" },
);
const collision = await handlers.beforeAgentRun(
{},
agentContext("collision", "bob"),
);
assert.equal(collision.outcome, "block");
assert.equal(collision.reason, "run_scope_sender_conflict");
assert.doesNotMatch(collision.message, /alice|bob/);
const original = await handlers.beforeToolCall(
{ toolName: "shell" },
toolContext("collision"),
);
assert.ok(original.requireApproval);
});
test("shared scope normalization is exact and incomplete scope fails closed", async () => {
const bothAliases = runKey({}, {
runId: " run-1 ",
agentId: " agent-1 ",
sessionId: " session-uuid-123 ",
sessionKey: " agent:main:weixin:direct:user ",
});
assert.equal(
bothAliases,
JSON.stringify(["run-1", "agent-1", "session-uuid-123"]),
);
const fallback = runKey(
{ sessionKey: " agent:main:weixin:direct:user " },
{
runId: "run-1",
agentId: "agent-1",
sessionKey: "agent:main:weixin:direct:user",
},
);
assert.equal(
fallback,
JSON.stringify(["run-1", "agent-1", "agent:main:weixin:direct:user"]),
);
assert.equal(runKey(
{ sessionId: "event-session" },
{
runId: "run-1",
agentId: "agent-1",
sessionId: "context-session",
sessionKey: "agent:main:weixin:direct:user",
},
), undefined);
assert.equal(runKey({}, {
runId: "run-1",
agentId: "agent-1",
sessionKey: "agent:main:weixin:direct:user",
sessionId: "session-uuid-123",
}), bothAliases);
assert.equal(runKey({}, {
runId: "run-1",
agentId: "agent-1",
sessionKey: "agent:main:weixin:direct:user",
}), fallback);
assert.equal(runKey({}, {
agentId: "agent-1", sessionId: "session-uuid-123",
}), undefined);
const handlers = registration();
const missing = await handlers.beforeToolCall(
{ toolName: "shell" },
{ agentId: "agent-1", sessionId: "session-uuid-123" },
);
assert.equal(missing.block, true);
assert.match(missing.blockReason, /run_provenance_missing$/);
});
test("sessionKey fallback requires sessionId absent from both hook contexts", async () => {
const handlers = registration({
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice"],
});
const before = {
runId: "run-fallback",
agentId: "agent-main",
sessionKey: "agent:main:weixin:direct:user",
senderId: "alice",
};
const tool = {
runId: "run-fallback",
agentId: "agent-main",
sessionKey: "agent:main:weixin:direct:user",
};
await handlers.beforeAgentRun({}, before);
assert.ok((await handlers.beforeToolCall({ toolName: "shell" }, tool)).requireApproval);
const mismatchedSelection = await handlers.beforeToolCall(
{ toolName: "shell" },
{ ...tool, sessionId: "session-uuid-123" },
);
assert.equal(mismatchedSelection.block, true);
assert.match(mismatchedSelection.blockReason, /run_provenance_missing$/);
});
test("same-named event and context sessionId mismatch fails closed", async () => {
const handlers = registration({
requireExplicitTrustedSenders: true,
trustedSenderIds: ["alice"],
});
await handlers.beforeAgentRun({}, agentContext("event-mismatch", "alice"));
const result = await handlers.beforeToolCall(
{ toolName: "shell", sessionId: "different-session" },
toolContext("event-mismatch"),
);
assert.equal(result.block, true);
assert.match(result.blockReason, /run_provenance_missing$/);
});
@@ -0,0 +1,16 @@
{
"task_id": "TASK-CODEX-V2R1-PERSONAL-WEIXIN-B6B7-BOOTSTRAP-AND-CANARY-20260715T120000UTC8",
"phase": "A",
"type": "branch",
"branch": "patch/v2r1-personal-weixin-b6b7-impl-20260715T115309UTC8",
"base_ref": "design/v2r1-personal-weixin-golden-contract-20260715",
"base_commit": "d74229927b2dadca7719455984aea10d010c5123",
"created_by": "aiman",
"created_at": "2026-07-15T03:53:09Z",
"direct_main_push": false,
"owner_approval_required": false,
"owner_approved": true,
"owner_approval_scope": "Phase A bootstrap for owner-approved B6/B7 personal-Weixin implementation; no production, runtime, database, secret, tag, baseline, or controller/ChatGPT worktree changes.",
"production_change": false,
"user_action_required": false
}
+36
View File
@@ -0,0 +1,36 @@
# AIOS V2R1C0 RC1
## Architecture
OpenClaw Tenant Cell + Hermes Shared Agent Fabric.
## Included
- Signed Tenant Context
- Canonical Message Envelope
- Tenant Router
- OpenClaw Cell lifecycle adapter
- Exact Message Ledger
- Hermes tenant partitioned scheduler
- Memory Namespace policy
- Secret Scope references
- Append-only Audit Chain
- Hermes Profile isolation
- OpenClaw tenant boundary plugin
## Release Gates
Before production:
- automated isolation tests pass
- OpenClaw plugin runtime inspect passes
- Cell health probes pass
- running commit matches release commit
- rollback test passes
## Security Rules
Unknown provenance fails closed.
Quoted text is data, not command input.
Cross-tenant access is denied.
Shared Fabric does not share tenant state.
-25
View File
@@ -1,25 +0,0 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://aios.local/schemas/codex-command.schema.json",
"title": "AIOS Codex command",
"type": "object",
"additionalProperties": false,
"required": ["schema_version", "command_id", "project_key", "work_unit_id", "contract_commit", "state_version", "execution"],
"properties": {
"schema_version": {"const": 1},
"command_id": {"type": "string", "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$"},
"project_key": {"type": "string", "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$"},
"work_unit_id": {"type": "string", "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$"},
"contract_commit": {"type": "string", "pattern": "^[0-9a-f]{40}$"},
"state_version": {"type": "integer", "minimum": 0},
"execution": {
"type": "object",
"additionalProperties": false,
"required": ["kind", "input"],
"properties": {
"kind": {"enum": ["acceptance_probe", "codex"]},
"input": {"type": "string", "maxLength": 65536}
}
}
}
}
-145
View File
@@ -1,145 +0,0 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "AIOS Orchestrator Decision",
"type": "object",
"additionalProperties": false,
"required": [
"schema_version",
"project_key",
"contract_commit",
"event_id",
"expected_state_version",
"verdict",
"state_updates",
"next_work_units",
"requires_human_input",
"stop_reason"
],
"properties": {
"schema_version": {
"type": "integer",
"const": 1
},
"project_key": {
"type": "string"
},
"contract_commit": {
"type": "string",
"pattern": "^[0-9a-f]{40}$"
},
"event_id": {
"type": "string"
},
"expected_state_version": {
"type": "integer",
"minimum": 0
},
"verdict": {
"type": "string",
"enum": [
"BLOCKED",
"COMPLETE",
"DISPATCH",
"NOOP"
]
},
"state_updates": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"key",
"value"
],
"properties": {
"key": {
"type": "string"
},
"value": {
"type": "string"
}
}
}
},
"next_work_units": {
"type": "array",
"maxItems": 32,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"id",
"track_id",
"gate_id",
"primary_agent",
"fallback_agent",
"clean_base_commit",
"allowed_paths",
"required_checks",
"forbidden_operations",
"instruction"
],
"properties": {
"id": {
"type": "string"
},
"track_id": {
"type": "string"
},
"gate_id": {
"type": "string"
},
"primary_agent": {
"type": "string",
"enum": [
"openclaw",
"codex"
]
},
"fallback_agent": {
"type": "string",
"enum": [
"openclaw",
"codex"
]
},
"clean_base_commit": {
"type": "string",
"pattern": "^[0-9a-f]{40}$"
},
"allowed_paths": {
"type": "array",
"items": {
"type": "string"
}
},
"required_checks": {
"type": "array",
"items": {
"type": "string"
}
},
"forbidden_operations": {
"type": "array",
"items": {
"type": "string"
}
},
"instruction": {
"type": "string"
}
}
}
},
"requires_human_input": {
"type": "boolean"
},
"stop_reason": {
"type": [
"string",
"null"
]
}
}
}
-102
View File
@@ -1,102 +0,0 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "AIOS Orchestrator Event",
"type": "object",
"additionalProperties": false,
"required": [
"schema_version",
"project_key",
"contract_commit",
"event_id",
"source_agent",
"event_type",
"work_unit_id",
"status",
"state_version",
"implementation_commit",
"result_commit",
"blocker",
"evidence_refs",
"payload"
],
"properties": {
"schema_version": {
"const": 1
},
"project_key": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"contract_commit": {
"type": "string",
"pattern": "^[0-9a-f]{40}$"
},
"event_id": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"source_agent": {
"enum": [
"openclaw",
"codex",
"gitea",
"system",
"workspace-agent"
]
},
"event_type": {
"type": "string"
},
"work_unit_id": {
"type": "string"
},
"status": {
"enum": [
"READY",
"RUNNING",
"PASS",
"BLOCKED",
"FAIL",
"TIMEOUT",
"NOT_EXECUTED"
]
},
"state_version": {
"type": "integer",
"minimum": 0
},
"implementation_commit": {
"type": [
"string",
"null"
],
"pattern": "^[0-9a-f]{40}$"
},
"result_commit": {
"type": [
"string",
"null"
],
"pattern": "^[0-9a-f]{40}$"
},
"blocker": {
"type": [
"string",
"null"
],
"maxLength": 512
},
"evidence_refs": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 64
},
"payload": {
"type": "object"
}
}
}
-63
View File
@@ -1,63 +0,0 @@
#!/usr/bin/env python3
"""Seed exactly one orchestration event when the project has no durable state."""
from __future__ import annotations
import argparse
from pathlib import Path
import sys
REPO_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(REPO_ROOT))
from services.aios_orchestrator_gateway.config import Config
from services.aios_orchestrator_gateway.models import Event
from services.aios_orchestrator_gateway.securefs import atomic_write_bytes_shared
from services.aios_orchestrator_gateway.store import Store
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--config", type=Path, required=True)
args = parser.parse_args()
config = Config.from_file(args.config)
store = Store(config.database_path)
if store.project_state(config.project_key) is not None:
print("ORCHESTRATION_BOOTSTRAP=NOOP reason=STATE_EXISTS")
return 0
event = Event.from_dict(
{
"schema_version": 1,
"project_key": config.project_key,
"contract_commit": config.contract_commit,
"event_id": "bootstrap-" + config.contract_commit[:24],
"source_agent": "system",
"event_type": "orchestration_bootstrap",
"work_unit_id": "ORCHESTRATION-BOOTSTRAP",
"status": "READY",
"state_version": 0,
"implementation_commit": None,
"result_commit": None,
"blocker": None,
"evidence_refs": [],
"payload": {
"reason": "initial_gateway_install",
"polling_enabled": True,
"openclaw_sync_required": True,
},
}
)
path = config.event_inbox_dir / "pending" / f"{event.event_id}.json"
atomic_write_bytes_shared(
path,
(event.canonical_json() + "\n").encode(),
mode=0o640,
group_writable_directory=True,
)
print(f"ORCHESTRATION_BOOTSTRAP=PASS event_id={event.event_id}")
return 0
if __name__ == "__main__":
raise SystemExit(main())
-64
View File
@@ -1,64 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
[[ ${EUID} -eq 0 ]] || { echo "root required" >&2; exit 1; }
ROOT=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd -P)
CONFIG=${1:-/etc/aios-codex-watcher/config.json}
[[ "$CONFIG" = /* ]] || { echo "config path must be absolute" >&2; exit 1; }
[[ -f "$CONFIG" && ! -L "$CONFIG" ]] || { echo "pre-provisioned regular config required" >&2; exit 1; }
for path in \
services/aios_codex_watcher/__init__.py \
services/aios_codex_watcher/__main__.py \
services/aios_codex_watcher/watcher.py \
systemd/aios-codex-watcher.service \
systemd/aios-codex-watcher.timer \
systemd/aios-codex-watcher.sysusers \
systemd/aios-codex-watcher.tmpfiles; do
[[ -f "$ROOT/$path" && ! -L "$ROOT/$path" ]] || { echo "missing or unsafe: $path" >&2; exit 1; }
done
digest=$(sha256sum \
"$ROOT/services/aios_codex_watcher/__init__.py" \
"$ROOT/services/aios_codex_watcher/__main__.py" \
"$ROOT/services/aios_codex_watcher/watcher.py" | sha256sum | awk '{print $1}')
release="/opt/aios-codex-watcher/releases/$digest"
install -d -o root -g root -m 0755 "$release/services/aios_codex_watcher" "$release/bin"
install -o root -g root -m 0644 "$ROOT/services/aios_codex_watcher/"*.py "$release/services/aios_codex_watcher/"
launcher="$release/bin/aios-codex-watcher"
printf '%s\n' '#!/usr/bin/env bash' 'set -euo pipefail' \
"export PYTHONPATH='$release'" \
"exec /usr/bin/python3 -m services.aios_codex_watcher \"\$@\"" >"$launcher"
chown root:root "$launcher"
chmod 0755 "$launcher"
install -d -o root -g root -m 0755 /opt/aios-codex-watcher /etc/aios-codex-watcher
ln -sfn "releases/$digest" /opt/aios-codex-watcher/current.new
mv -Tf /opt/aios-codex-watcher/current.new /opt/aios-codex-watcher/current
install -o root -g root -m 0644 "$ROOT/systemd/aios-codex-watcher.service" /etc/systemd/system/
install -o root -g root -m 0644 "$ROOT/systemd/aios-codex-watcher.timer" /etc/systemd/system/
install -o root -g root -m 0644 "$ROOT/systemd/aios-codex-watcher.sysusers" /usr/lib/sysusers.d/
install -o root -g root -m 0644 "$ROOT/systemd/aios-codex-watcher.tmpfiles" /usr/lib/tmpfiles.d/
systemd-sysusers /usr/lib/sysusers.d/aios-codex-watcher.sysusers
systemd-tmpfiles --create /usr/lib/tmpfiles.d/aios-codex-watcher.tmpfiles
commands=/data/aios-gitops/workspace/agents/commands
for directory in "$commands/active" "$commands/completed"; do
[[ -d "$directory" && ! -L "$directory" ]] || { echo "missing or unsafe command directory: $directory" >&2; exit 1; }
[[ $(stat -c '%U:%G' "$directory") == aios-orchestrator:aios-orchestrator ]] || { echo "unexpected command directory owner: $directory" >&2; exit 1; }
mode=$(stat -c '%a' "$directory")
(( (8#$mode & 2) == 0 )) || { echo "world-writable command directory: $directory" >&2; exit 1; }
done
if [[ -e "$commands/dead-letter" || -L "$commands/dead-letter" ]]; then
[[ -d "$commands/dead-letter" && ! -L "$commands/dead-letter" ]] || { echo "unsafe dead-letter directory" >&2; exit 1; }
else
install -d -o aios-orchestrator -g aios-orchestrator -m 0750 "$commands/dead-letter"
fi
[[ $(stat -c '%U:%G' "$commands/dead-letter") == aios-orchestrator:aios-orchestrator ]] || { echo "unexpected dead-letter owner" >&2; exit 1; }
mode=$(stat -c '%a' "$commands/dead-letter")
(( (8#$mode & 2) == 0 )) || { echo "world-writable dead-letter directory" >&2; exit 1; }
printf '{"release_sha256":"%s","installed_at":"%s"}\n' "$digest" "$(date -u +%FT%TZ)" >"$release/receipt.json"
chmod 0644 "$release/receipt.json"
systemctl daemon-reload
systemctl enable --now aios-codex-watcher.timer
printf 'installed_sha256=%s\n' "$digest"
@@ -1,239 +0,0 @@
#!/usr/bin/env bash
set -Eeuo pipefail
umask 0077
SOURCE_ROOT="${SOURCE_ROOT:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)}"
INSTALL_ROOT="${INSTALL_ROOT:-/opt/aios-orchestrator-gateway}"
CONFIG_ROOT="${CONFIG_ROOT:-/etc/aios-orchestrator-gateway}"
STATE_ROOT="${STATE_ROOT:-/var/lib/aios-orchestrator-gateway}"
UNIT_ROOT="${UNIT_ROOT:-/etc/systemd/system}"
SYSUSERS_ROOT="${SYSUSERS_ROOT:-/etc/sysusers.d}"
TMPFILES_ROOT="${TMPFILES_ROOT:-/etc/tmpfiles.d}"
DRY_RUN=0
if [[ "${1:-}" == "--dry-run" ]]; then
DRY_RUN=1
fi
fail() {
printf 'AIOS_ORCHESTRATOR_INSTALL=BLOCKED reason=%s\n' "$1" >&2
exit 2
}
[[ "$(id -u)" -eq 0 ]] || fail OWNER_INSTALL_REQUIRED
for cmd in git python3 systemd-analyze systemctl systemd-sysusers systemd-tmpfiles sha256sum find sort xargs; do
command -v "$cmd" >/dev/null 2>&1 || fail "MISSING_COMMAND_${cmd}"
done
if [[ -f "$SOURCE_ROOT/SHA256SUMS" ]]; then
(cd "$SOURCE_ROOT" && sha256sum --check SHA256SUMS)
fi
for path in \
"$SOURCE_ROOT/services/aios_orchestrator_gateway" \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway.service" \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway-poll.service" \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway-poll.timer" \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway.sysusers" \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway.tmpfiles" \
"$SOURCE_ROOT/config/aios-orchestrator-gateway.example.json"; do
[[ -e "$path" ]] || fail "MISSING_SOURCE_${path}"
done
PYCACHE="/tmp/aios-orchestrator-install-pycache-$$"
rm -rf "$PYCACHE"
PYTHONPYCACHEPREFIX="$PYCACHE" python3 -m compileall -q "$SOURCE_ROOT/services" "$SOURCE_ROOT/scripts"
PYTHONDONTWRITEBYTECODE=1 PYTHONPATH="$SOURCE_ROOT" \
python3 -m unittest -v tests.test_aios_orchestrator_gateway
rm -rf "$PYCACHE"
for script in "$SOURCE_ROOT"/scripts/*.sh; do bash -n "$script"; done
python3 -m json.tool "$SOURCE_ROOT/config/aios-orchestrator-gateway.example.json" >/dev/null
systemd-analyze verify \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway.service" \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway-poll.service" \
"$SOURCE_ROOT/systemd/aios-orchestrator-gateway-poll.timer"
SOURCE_FILES=(
README-AIOS-ORCHESTRATOR-GATEWAY.md
config/aios-orchestrator-gateway.example.json
schemas/decision.schema.json
schemas/event.schema.json
scripts/bootstrap_orchestration_loop.py
scripts/install_aios_orchestrator_gateway.sh
scripts/report_orchestrator_event.py
scripts/rollback_aios_orchestrator_gateway.sh
scripts/verify_aios_orchestrator_gateway.sh
systemd/aios-orchestrator-gateway-poll.service
systemd/aios-orchestrator-gateway-poll.timer
systemd/aios-orchestrator-gateway.service
systemd/aios-orchestrator-gateway.sysusers
systemd/aios-orchestrator-gateway.tmpfiles
tests/test_aios_orchestrator_gateway.py
tests/test_aios_orchestrator_gateway_rollback.sh
workspace-agent/CENTRAL_AGENT_INSTRUCTIONS.md
workspace-agent/orchestrator-decision-action.openapi.yaml
)
while IFS= read -r path; do SOURCE_FILES+=("$path"); done < <(
cd "$SOURCE_ROOT"
find services/aios_orchestrator_gateway -type f ! -path '*/__pycache__/*' ! -name '*.pyc' -print | sort
)
for path in "${SOURCE_FILES[@]}"; do
[[ -f "$SOURCE_ROOT/$path" && ! -L "$SOURCE_ROOT/$path" ]] || fail "INVALID_SOURCE_FILE_${path}"
done
SOURCE_DIGEST="$(
cd "$SOURCE_ROOT"
printf '%s\0' "${SOURCE_FILES[@]}" | sort -z | xargs -0 sha256sum \
| sha256sum \
| awk '{print $1}'
)"
[[ "$SOURCE_DIGEST" =~ ^[0-9a-f]{64}$ ]] || fail SOURCE_DIGEST_INVALID
RELEASE_DIR="$INSTALL_ROOT/releases/$SOURCE_DIGEST"
if [[ "$DRY_RUN" -eq 1 ]]; then
printf 'AIOS_ORCHESTRATOR_INSTALL_DRY_RUN=PASS digest=%s release=%s\n' \
"$SOURCE_DIGEST" "$RELEASE_DIR"
exit 0
fi
install -d -m 0755 "$INSTALL_ROOT/releases"
install -d -m 0700 "$CONFIG_ROOT"
install -d -m 0700 "$STATE_ROOT"
systemd-sysusers "$SOURCE_ROOT/systemd/aios-orchestrator-gateway.sysusers"
systemd-tmpfiles --create "$SOURCE_ROOT/systemd/aios-orchestrator-gateway.tmpfiles"
if [[ ! -d "$RELEASE_DIR" ]]; then
TMP_RELEASE="$INSTALL_ROOT/releases/.tmp-$SOURCE_DIGEST-$$"
install -d -m 0755 "$TMP_RELEASE"
for path in "${SOURCE_FILES[@]}"; do
install -d -m 0755 "$TMP_RELEASE/$(dirname "$path")"
cp -a "$SOURCE_ROOT/$path" "$TMP_RELEASE/$path"
done
printf '%s\n' "$SOURCE_DIGEST" > "$TMP_RELEASE/SOURCE_DIGEST"
chmod -R go-w "$TMP_RELEASE"
mv "$TMP_RELEASE" "$RELEASE_DIR"
fi
PREVIOUS_TARGET=""
if [[ -L "$INSTALL_ROOT/current" ]]; then
PREVIOUS_TARGET="$(readlink -f "$INSTALL_ROOT/current")"
fi
ln -s "$RELEASE_DIR" "$INSTALL_ROOT/.current-new-$$"
mv -Tf "$INSTALL_ROOT/.current-new-$$" "$INSTALL_ROOT/current"
install -m 0644 "$SOURCE_ROOT/systemd/aios-orchestrator-gateway.service" \
"$UNIT_ROOT/aios-orchestrator-gateway.service"
install -m 0644 "$SOURCE_ROOT/systemd/aios-orchestrator-gateway-poll.service" \
"$UNIT_ROOT/aios-orchestrator-gateway-poll.service"
install -m 0644 "$SOURCE_ROOT/systemd/aios-orchestrator-gateway-poll.timer" \
"$UNIT_ROOT/aios-orchestrator-gateway-poll.timer"
install -m 0644 "$SOURCE_ROOT/systemd/aios-orchestrator-gateway.sysusers" \
"$SYSUSERS_ROOT/aios-orchestrator-gateway.conf"
install -m 0644 "$SOURCE_ROOT/systemd/aios-orchestrator-gateway.tmpfiles" \
"$TMPFILES_ROOT/aios-orchestrator-gateway.conf"
if [[ ! -f "$CONFIG_ROOT/inbound.token" ]]; then
python3 - <<'PY' > "$CONFIG_ROOT/inbound.token"
import secrets
print(secrets.token_urlsafe(48))
PY
fi
[[ ! -L "$CONFIG_ROOT/inbound.token" ]] || fail INBOUND_TOKEN_SYMLINK
chown root:aios-orchestrator "$CONFIG_ROOT/inbound.token"
chmod 0640 "$CONFIG_ROOT/inbound.token"
if [[ ! -f "$CONFIG_ROOT/callback.token" ]]; then
python3 - <<'PY' > "$CONFIG_ROOT/callback.token"
import secrets
print(secrets.token_urlsafe(48))
PY
fi
[[ ! -L "$CONFIG_ROOT/callback.token" ]] || fail CALLBACK_TOKEN_SYMLINK
chown root:aios-orchestrator "$CONFIG_ROOT/callback.token"
chmod 0640 "$CONFIG_ROOT/callback.token"
if [[ ! -f "$CONFIG_ROOT/config.json" ]]; then
install -m 0600 \
"$SOURCE_ROOT/config/aios-orchestrator-gateway.example.json" \
"$CONFIG_ROOT/config.json.example"
printf 'AIOS_ORCHESTRATOR_INSTALL=BLOCKED reason=CONFIGURATION_REQUIRED digest=%s\n' \
"$SOURCE_DIGEST"
exit 2
fi
chown root:aios-orchestrator "$CONFIG_ROOT/config.json"
chmod 0640 "$CONFIG_ROOT/config.json"
python3 -m json.tool "$CONFIG_ROOT/config.json" >/dev/null
AIOS_ORCHESTRATOR_CONFIG_OWNER_UID=0 \
AIOS_ORCHESTRATOR_SECRET_OWNER_UID=0 \
PYTHONPATH="$INSTALL_ROOT/current" \
python3 - "$CONFIG_ROOT/config.json" <<'PY'
import sys
from pathlib import Path
from services.aios_orchestrator_gateway.config import Config
cfg = Config.from_file(Path(sys.argv[1]))
cfg.inbound_token()
cfg.callback_token()
if cfg.workspace_trigger_id:
cfg.workspace_token()
if cfg.responses_api_key_file:
cfg.responses_api_key()
if cfg.openclaw_sync_endpoint:
cfg.openclaw_sync_token()
print("CONFIG_VALIDATE=PASS")
PY
python3 - "$STATE_ROOT/install-receipt.json" "$SOURCE_DIGEST" "$RELEASE_DIR" "$PREVIOUS_TARGET" <<'PY'
import json, os, sys, tempfile
from pathlib import Path
path = Path(sys.argv[1])
data = {
"schema_version": 1,
"source_digest": sys.argv[2],
"current_release": sys.argv[3],
"previous_release": sys.argv[4] or None,
"last_rollback": None,
}
path.parent.mkdir(parents=True, exist_ok=True)
fd, temp = tempfile.mkstemp(prefix=".install-receipt-", dir=path.parent)
try:
with os.fdopen(fd, "w") as handle:
json.dump(data, handle, indent=2, sort_keys=True)
handle.write("\n")
handle.flush()
os.fsync(handle.fileno())
os.chmod(temp, 0o600)
os.replace(temp, path)
directory = os.open(path.parent, os.O_RDONLY | os.O_DIRECTORY)
try:
os.fsync(directory)
finally:
os.close(directory)
finally:
try:
os.unlink(temp)
except FileNotFoundError:
pass
PY
chown aios-orchestrator:aios-orchestrator "$STATE_ROOT/install-receipt.json"
chmod 0600 "$STATE_ROOT/install-receipt.json"
systemctl daemon-reload
systemctl enable --now aios-orchestrator-gateway.service
systemctl enable --now aios-orchestrator-gateway-poll.timer
systemctl is-active --quiet aios-orchestrator-gateway.service
systemctl is-active --quiet aios-orchestrator-gateway-poll.timer
AIOS_ORCHESTRATOR_CONFIG_OWNER_UID=0 \
AIOS_ORCHESTRATOR_SECRET_OWNER_UID=0 \
PYTHONPATH="$INSTALL_ROOT/current" \
python3 "$INSTALL_ROOT/current/scripts/bootstrap_orchestration_loop.py" \
--config "$CONFIG_ROOT/config.json"
systemctl start aios-orchestrator-gateway-poll.service
printf 'AIOS_ORCHESTRATOR_INSTALL=PASS digest=%s previous=%s\n' \
"$SOURCE_DIGEST" "${PREVIOUS_TARGET:-NONE}"
-130
View File
@@ -1,130 +0,0 @@
#!/usr/bin/env python3
"""Submit an OpenClaw/Codex task lifecycle event over HTTP or a polled inbox."""
from __future__ import annotations
import argparse
import json
import os
from pathlib import Path
import sys
import urllib.error
import urllib.request
REPO_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(REPO_ROOT))
from services.aios_orchestrator_gateway.models import Event
from services.aios_orchestrator_gateway.securefs import atomic_write_bytes_shared, read_secure_json, read_secure_text
def parser() -> argparse.ArgumentParser:
p = argparse.ArgumentParser()
p.add_argument("--project-key", required=True)
p.add_argument("--contract-commit", required=True)
p.add_argument("--event-id", required=True)
p.add_argument("--source-agent", required=True, choices=["openclaw", "codex", "gitea", "system"])
p.add_argument("--event-type", required=True)
p.add_argument("--work-unit-id", required=True)
p.add_argument(
"--status",
required=True,
choices=["READY", "RUNNING", "PASS", "BLOCKED", "FAIL", "TIMEOUT", "NOT_EXECUTED"],
)
p.add_argument("--state-version", type=int, required=True)
p.add_argument("--implementation-commit")
p.add_argument("--result-commit")
p.add_argument("--blocker")
p.add_argument("--evidence-ref", action="append", default=[])
p.add_argument("--payload-file", type=Path)
p.add_argument("--endpoint")
p.add_argument("--token-file", type=Path)
p.add_argument("--inbox-dir", type=Path)
p.add_argument("--timeout-seconds", type=int, default=15)
return p
def main() -> int:
args = parser().parse_args()
if not args.endpoint and not args.inbox_dir:
raise SystemExit("either --endpoint or --inbox-dir is required")
if args.endpoint and not args.token_file:
raise SystemExit("--token-file is required with --endpoint")
payload = {}
if args.payload_file:
if not args.payload_file.is_absolute():
raise SystemExit("--payload-file must be absolute")
payload = read_secure_json(
args.payload_file, expected_uid=os.getuid(), max_bytes=262_144
)
if not isinstance(payload, dict):
raise SystemExit("payload root must be an object")
event = Event.from_dict(
{
"schema_version": 1,
"project_key": args.project_key,
"contract_commit": args.contract_commit,
"event_id": args.event_id,
"source_agent": args.source_agent,
"event_type": args.event_type,
"work_unit_id": args.work_unit_id,
"status": args.status,
"state_version": args.state_version,
"implementation_commit": args.implementation_commit,
"result_commit": args.result_commit,
"blocker": args.blocker,
"evidence_refs": args.evidence_ref,
"payload": payload,
}
)
encoded = event.canonical_json().encode()
http_error: Exception | None = None
if args.endpoint:
token = read_secure_text(
args.token_file,
expected_uid=None,
max_bytes=64_000,
)
request = urllib.request.Request(
args.endpoint.rstrip("/") + "/v1/orchestrator/events",
data=encoded,
method="POST",
headers={
"Authorization": f"Bearer {token}",
"Content-Type": "application/json",
"Idempotency-Key": event.event_id,
"User-Agent": "aios-agent-event-reporter/0.2",
},
)
try:
with urllib.request.urlopen(request, timeout=args.timeout_seconds) as response:
response.read(65_536)
if response.status not in {200, 202}:
raise RuntimeError(f"unexpected HTTP {response.status}")
print(f"EVENT_SUBMIT=PASS event_id={event.event_id} channel=http")
return 0
except (urllib.error.URLError, urllib.error.HTTPError, TimeoutError, OSError) as exc:
http_error = exc
if args.inbox_dir:
pending = args.inbox_dir / "pending"
path = pending / f"{event.event_id}.json"
atomic_write_bytes_shared(
path,
(json.dumps(event.to_dict(), indent=2, sort_keys=True) + "\n").encode(),
mode=0o640,
group_writable_directory=True,
)
print(f"EVENT_SUBMIT=PASS event_id={event.event_id} channel=file_inbox")
return 0
print(
f"EVENT_SUBMIT=FAIL event_id={event.event_id} reason={type(http_error).__name__}",
file=sys.stderr,
)
return 2
if __name__ == "__main__":
raise SystemExit(main())
@@ -1,102 +0,0 @@
#!/usr/bin/env bash
set -Eeuo pipefail
umask 0077
INSTALL_ROOT="${INSTALL_ROOT:-/opt/aios-orchestrator-gateway}"
STATE_ROOT="${STATE_ROOT:-/var/lib/aios-orchestrator-gateway}"
RECEIPT="$STATE_ROOT/install-receipt.json"
fail() {
printf 'AIOS_ORCHESTRATOR_ROLLBACK=BLOCKED reason=%s\n' "$1" >&2
exit 2
}
[[ "$(id -u)" -eq 0 ]] || fail OWNER_REQUIRED
[[ -f "$RECEIPT" ]] || fail RECEIPT_MISSING
[[ ! -L "$RECEIPT" ]] || fail RECEIPT_SYMLINK
[[ "$(stat -c '%u:%a' "$RECEIPT")" == "0:600" ]] || fail RECEIPT_PERMISSION
readarray -t VALUES < <(
python3 - "$RECEIPT" "$INSTALL_ROOT/releases" "$INSTALL_ROOT/current" <<'PY'
import json, os, stat, sys
from pathlib import Path
receipt = Path(sys.argv[1])
releases = Path(sys.argv[2]).resolve()
current_link = Path(sys.argv[3])
data = json.loads(receipt.read_text())
previous = data.get("previous_release")
current = data.get("current_release")
if not previous or not current:
raise SystemExit(2)
previous_path = Path(previous).resolve()
current_path = Path(current).resolve()
if previous_path.parent != releases or current_path.parent != releases:
raise SystemExit(2)
if not stat.S_ISDIR(os.lstat(previous_path).st_mode) or not stat.S_ISDIR(os.lstat(current_path).st_mode):
raise SystemExit(2)
for release in (previous_path, current_path):
if len(release.name) != 64 or any(ch not in "0123456789abcdef" for ch in release.name):
raise SystemExit(2)
digest_file = release / "SOURCE_DIGEST"
if digest_file.is_symlink() or not digest_file.is_file():
raise SystemExit(2)
if digest_file.read_text(encoding="utf-8").strip() != release.name:
raise SystemExit(2)
last = data.get("last_rollback")
if isinstance(last, dict) and last.get("to") == current and current_link.is_symlink():
if current_link.resolve() == current_path:
print("ALREADY_ROLLED_BACK")
raise SystemExit(0)
print(previous_path)
print(current_path)
PY
) || fail RECEIPT_INVALID
if [[ "${VALUES[0]:-}" == "ALREADY_ROLLED_BACK" ]]; then
echo "AIOS_ORCHESTRATOR_ROLLBACK=PASS result=NOOP_ALREADY_ROLLED_BACK"
exit 0
fi
[[ "${#VALUES[@]}" -eq 2 ]] || fail RECEIPT_INVALID
PREVIOUS="${VALUES[0]}"
CURRENT="${VALUES[1]}"
systemctl stop aios-orchestrator-gateway-poll.timer || true
systemctl stop aios-orchestrator-gateway-poll.service || true
systemctl stop aios-orchestrator-gateway.service || true
ln -s "$PREVIOUS" "$INSTALL_ROOT/.current-rollback-$$"
mv -Tf "$INSTALL_ROOT/.current-rollback-$$" "$INSTALL_ROOT/current"
systemctl start aios-orchestrator-gateway.service
systemctl is-active --quiet aios-orchestrator-gateway.service
systemctl start aios-orchestrator-gateway-poll.timer
systemctl is-active --quiet aios-orchestrator-gateway-poll.timer
python3 - "$RECEIPT" "$PREVIOUS" "$CURRENT" <<'PY'
import json, os, sys, tempfile
from pathlib import Path
path = Path(sys.argv[1])
data = json.loads(path.read_text())
data["current_release"] = sys.argv[2]
data["previous_release"] = sys.argv[3]
data["last_rollback"] = {"from": sys.argv[3], "to": sys.argv[2]}
fd, temp = tempfile.mkstemp(prefix=".rollback-receipt-", dir=path.parent)
try:
with os.fdopen(fd, "w") as handle:
json.dump(data, handle, indent=2, sort_keys=True)
handle.write("\n")
handle.flush()
os.fsync(handle.fileno())
os.chmod(temp, 0o600)
os.chown(temp, 0, 0)
os.replace(temp, path)
directory = os.open(path.parent, os.O_RDONLY | os.O_DIRECTORY)
try:
os.fsync(directory)
finally:
os.close(directory)
finally:
try:
os.unlink(temp)
except FileNotFoundError:
pass
PY
printf 'AIOS_ORCHESTRATOR_ROLLBACK=PASS current=%s previous=%s\n' "$PREVIOUS" "$CURRENT"
@@ -1,32 +0,0 @@
#!/usr/bin/env bash
set -Eeuo pipefail
CONFIG="${1:-/etc/aios-orchestrator-gateway/config.json}"
PORT="${PORT:-18920}"
python3 -m json.tool "$CONFIG" >/dev/null
systemd-analyze verify \
/etc/systemd/system/aios-orchestrator-gateway.service \
/etc/systemd/system/aios-orchestrator-gateway-poll.service \
/etc/systemd/system/aios-orchestrator-gateway-poll.timer
systemctl is-active --quiet aios-orchestrator-gateway.service
systemctl is-active --quiet aios-orchestrator-gateway-poll.timer
health="$(curl --fail --silent --show-error "http://127.0.0.1:${PORT}/healthz")"
python3 -c '
import json, sys
v=json.load(sys.stdin)
assert v["service"]=="aios-orchestrator-gateway"
assert v["status"]=="active"
assert v["polling"] is True
assert len(v["contract_commit"])==40
' <<<"$health"
systemctl start aios-orchestrator-gateway-poll.service
if journalctl -u aios-orchestrator-gateway.service -n 200 --no-pager \
| grep -Eqi 'Bearer |token=|api[_-]?key|secret='; then
echo "AIOS_ORCHESTRATOR_VERIFY=BLOCKED reason=SECRET_PATTERN_IN_LOG" >&2
exit 2
fi
echo "AIOS_ORCHESTRATOR_VERIFY=PASS"
-1
View File
@@ -1 +0,0 @@
"""AIOS services namespace."""
-5
View File
@@ -1,5 +0,0 @@
"""Reliable, fail-closed Codex command watcher."""
from .watcher import CommandWatcher, Config, load_config
__all__ = ["CommandWatcher", "Config", "load_config"]
-19
View File
@@ -1,19 +0,0 @@
from __future__ import annotations
import argparse
import sys
from .watcher import CommandWatcher, load_config
def main() -> int:
parser = argparse.ArgumentParser(description="Claim and execute Codex work units")
parser.add_argument("--config", required=True)
parser.add_argument("--once", action="store_true", help="process one scan and exit")
args = parser.parse_args()
watcher = CommandWatcher(load_config(args.config))
return watcher.run_once() if args.once else watcher.run_forever()
if __name__ == "__main__":
sys.exit(main())
-480
View File
@@ -1,480 +0,0 @@
from __future__ import annotations
from dataclasses import dataclass
import hashlib
import json
import os
from pathlib import Path
import re
import sqlite3
import stat
import subprocess
import time
from typing import Any, Callable
import urllib.error
import urllib.parse
import urllib.request
import uuid
OID_RE = re.compile(r"^[0-9a-f]{40}$")
ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$")
TERMINAL = {"COMPLETED", "DEAD_LETTER", "REJECTED"}
class WatcherError(RuntimeError):
pass
@dataclass(frozen=True)
class Config:
active_dir: Path
completed_dir: Path
dead_letter_dir: Path
database_path: Path
audit_log_path: Path
gateway_endpoint: str
gateway_token_file: Path
contract_commit: str
lease_seconds: int
retry_seconds: int
max_attempts: int
poll_seconds: float
executor_path: Path | None
executor_args: tuple[str, ...]
executor_timeout_seconds: int
def _absolute(value: Any, key: str) -> Path:
if not isinstance(value, str) or not value or not Path(value).is_absolute():
raise WatcherError(f"invalid_{key}")
return Path(value)
def _secure_regular(path: Path, *, writable_mask: int = 0o022) -> os.stat_result:
info = os.lstat(path)
if stat.S_ISLNK(info.st_mode) or not stat.S_ISREG(info.st_mode):
raise WatcherError(f"unsafe_file:{path}")
if stat.S_IMODE(info.st_mode) & writable_mask:
raise WatcherError(f"unsafe_mode:{path}")
return info
def _read_secure_text(
path: Path,
*,
writable_mask: int = 0o022,
max_bytes: int,
allowed_owners: set[int] | None = None,
) -> str:
flags = os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0)
fd = os.open(path, flags)
try:
info = os.fstat(fd)
if not stat.S_ISREG(info.st_mode) or stat.S_IMODE(info.st_mode) & writable_mask:
raise WatcherError(f"unsafe_file:{path}")
if allowed_owners is not None and info.st_uid not in allowed_owners:
raise WatcherError(f"owner_mismatch:{path}")
if info.st_size > max_bytes:
raise WatcherError(f"file_too_large:{path}")
chunks: list[bytes] = []
total = 0
while True:
chunk = os.read(fd, min(65_536, max_bytes + 1 - total))
if not chunk:
break
chunks.append(chunk)
total += len(chunk)
if total > max_bytes:
raise WatcherError(f"file_too_large:{path}")
return b"".join(chunks).decode("utf-8")
finally:
os.close(fd)
def load_config(path_value: str) -> Config:
path = _absolute(path_value, "config_path")
raw = json.loads(_read_secure_text(path, max_bytes=131_072, allowed_owners={0, os.geteuid()}))
expected = {
"active_dir", "completed_dir", "dead_letter_dir", "database_path",
"audit_log_path", "gateway_endpoint", "gateway_token_file",
"contract_commit", "lease_seconds", "retry_seconds", "max_attempts",
"poll_seconds", "executor_path", "executor_args",
"executor_timeout_seconds",
}
if not isinstance(raw, dict) or set(raw) != expected:
raise WatcherError("invalid_config_fields")
contract = raw["contract_commit"]
if not isinstance(contract, str) or not OID_RE.fullmatch(contract):
raise WatcherError("invalid_contract_commit")
endpoint = raw["gateway_endpoint"]
if not isinstance(endpoint, str) or not endpoint.startswith("http://127.0.0.1:") or not endpoint.endswith("/v1/orchestrator/events"):
raise WatcherError("gateway_endpoint_must_be_loopback")
executor_raw = raw["executor_path"]
executor = None if executor_raw is None else _absolute(executor_raw, "executor_path")
executor_args = raw["executor_args"]
if not isinstance(executor_args, list) or any(not isinstance(x, str) or not x for x in executor_args):
raise WatcherError("invalid_executor_args")
ints = ("lease_seconds", "retry_seconds", "max_attempts", "executor_timeout_seconds")
if any(not isinstance(raw[x], int) or raw[x] <= 0 for x in ints):
raise WatcherError("invalid_positive_integer")
if not isinstance(raw["poll_seconds"], (int, float)) or raw["poll_seconds"] <= 0:
raise WatcherError("invalid_poll_seconds")
return Config(
active_dir=_absolute(raw["active_dir"], "active_dir"),
completed_dir=_absolute(raw["completed_dir"], "completed_dir"),
dead_letter_dir=_absolute(raw["dead_letter_dir"], "dead_letter_dir"),
database_path=_absolute(raw["database_path"], "database_path"),
audit_log_path=_absolute(raw["audit_log_path"], "audit_log_path"),
gateway_endpoint=endpoint,
gateway_token_file=_absolute(raw["gateway_token_file"], "gateway_token_file"),
contract_commit=contract,
lease_seconds=raw["lease_seconds"], retry_seconds=raw["retry_seconds"],
max_attempts=raw["max_attempts"], poll_seconds=float(raw["poll_seconds"]),
executor_path=executor, executor_args=tuple(executor_args),
executor_timeout_seconds=raw["executor_timeout_seconds"],
)
def canonical_digest(value: dict[str, Any]) -> str:
return hashlib.sha256(json.dumps(value, sort_keys=True, separators=(",", ":")).encode()).hexdigest()
def validate_command(value: Any, expected_contract: str) -> dict[str, Any]:
expected = {
"schema_version", "command_id", "project_key", "work_unit_id",
"contract_commit", "state_version", "execution",
}
if not isinstance(value, dict) or set(value) != expected or value.get("schema_version") != 1:
raise WatcherError("invalid_command_fields")
for key in ("command_id", "project_key", "work_unit_id"):
if not isinstance(value[key], str) or not ID_RE.fullmatch(value[key]):
raise WatcherError(f"invalid_{key}")
if value["contract_commit"] != expected_contract:
raise WatcherError("contract_commit_mismatch")
if not isinstance(value["state_version"], int) or value["state_version"] < 0:
raise WatcherError("invalid_state_version")
execution = value["execution"]
if not isinstance(execution, dict) or set(execution) != {"kind", "input"}:
raise WatcherError("invalid_execution")
if execution["kind"] not in {"acceptance_probe", "codex"}:
raise WatcherError("invalid_execution_kind")
if not isinstance(execution["input"], str) or len(execution["input"].encode()) > 65_536:
raise WatcherError("invalid_execution_input")
return value
class CommandWatcher:
def __init__(
self,
config: Config,
*,
clock: Callable[[], float] = time.time,
event_poster: Callable[[dict[str, Any]], None] | None = None,
executor: Callable[[dict[str, Any]], dict[str, Any]] | None = None,
worker_id: str | None = None,
) -> None:
self.config = config
self.clock = clock
self.worker_id = worker_id or f"{os.uname().nodename}:{os.getpid()}:{uuid.uuid4().hex[:8]}"
self._uses_gateway = event_poster is None
self.event_poster = event_poster or self._post_event
self.executor = executor or self._execute
self._prepare()
def _prepare(self) -> None:
for directory in (self.config.active_dir, self.config.completed_dir, self.config.dead_letter_dir):
info = os.lstat(directory)
if stat.S_ISLNK(info.st_mode) or not stat.S_ISDIR(info.st_mode) or stat.S_IMODE(info.st_mode) & 0o002:
raise WatcherError(f"unsafe_directory:{directory}")
self.config.database_path.parent.mkdir(parents=True, exist_ok=True, mode=0o700)
self.config.audit_log_path.parent.mkdir(parents=True, exist_ok=True, mode=0o700)
with self._db() as db:
db.execute("PRAGMA journal_mode=WAL")
db.execute("""
CREATE TABLE IF NOT EXISTS commands (
command_id TEXT PRIMARY KEY, work_unit_id TEXT NOT NULL UNIQUE,
payload_sha256 TEXT NOT NULL,
source_path TEXT NOT NULL, status TEXT NOT NULL,
phase TEXT NOT NULL, attempts INTEGER NOT NULL DEFAULT 0,
lease_owner TEXT, lease_until REAL, next_attempt REAL NOT NULL DEFAULT 0,
result_json TEXT, start_event_json TEXT, end_event_json TEXT,
last_error TEXT, updated_at REAL NOT NULL
)
""")
def _db(self) -> sqlite3.Connection:
db = sqlite3.connect(self.config.database_path, timeout=5, isolation_level=None)
db.row_factory = sqlite3.Row
return db
def _audit(self, marker: str, command_id: str, **fields: Any) -> None:
safe = {k: v for k, v in fields.items() if k not in {"input", "token", "secret"}}
record = {"time": int(self.clock()), "marker": marker, "command_id": command_id, **safe}
fd = os.open(self.config.audit_log_path, os.O_APPEND | os.O_CREAT | os.O_WRONLY | os.O_NOFOLLOW, 0o600)
try:
os.write(fd, (json.dumps(record, sort_keys=True, separators=(",", ":")) + "\n").encode())
finally:
os.close(fd)
def _read_command(self, path: Path) -> tuple[dict[str, Any], str]:
raw = _read_secure_text(path, max_bytes=131_072, allowed_owners={0, os.geteuid()})
value = validate_command(json.loads(raw), self.config.contract_commit)
return value, canonical_digest(value)
def _register(self, command: dict[str, Any], digest: str, path: Path) -> str:
now = self.clock()
with self._db() as db:
db.execute("BEGIN IMMEDIATE")
row = db.execute("SELECT payload_sha256,status FROM commands WHERE command_id=?", (command["command_id"],)).fetchone()
if row:
db.execute("COMMIT")
if row["payload_sha256"] != digest:
raise WatcherError("duplicate_command_payload_conflict")
return "duplicate_terminal" if row["status"] in TERMINAL else "existing"
prior_work_unit = db.execute(
"SELECT command_id FROM commands WHERE work_unit_id=?",
(command["work_unit_id"],),
).fetchone()
if prior_work_unit:
db.execute("COMMIT")
raise WatcherError("duplicate_work_unit")
db.execute(
"INSERT INTO commands(command_id,work_unit_id,payload_sha256,source_path,status,phase,updated_at) VALUES(?,?,?,?,?,?,?)",
(command["command_id"], command["work_unit_id"], digest, str(path), "PENDING", "START", now),
)
db.execute("COMMIT")
return "new"
def _claim(self, command_id: str) -> sqlite3.Row | None:
now = self.clock()
with self._db() as db:
db.execute("BEGIN IMMEDIATE")
row = db.execute("SELECT * FROM commands WHERE command_id=?", (command_id,)).fetchone()
if not row or row["status"] in TERMINAL or row["next_attempt"] > now:
db.execute("COMMIT")
return None
if row["lease_until"] is not None and row["lease_until"] > now and row["lease_owner"] != self.worker_id:
db.execute("COMMIT")
return None
attempts = row["attempts"] + 1
db.execute(
"UPDATE commands SET status='CLAIMED',attempts=?,lease_owner=?,lease_until=?,updated_at=? WHERE command_id=?",
(attempts, self.worker_id, now + self.config.lease_seconds, now, command_id),
)
row = db.execute("SELECT * FROM commands WHERE command_id=?", (command_id,)).fetchone()
db.execute("COMMIT")
assert row is not None
self._audit("CODEX_AUTO_CLAIM", command_id, attempt=row["attempts"], worker=self.worker_id)
return row
def _update(self, command_id: str, *, status: str, phase: str, result: dict[str, Any] | None = None, error: str | None = None) -> None:
with self._db() as db:
release = status in TERMINAL
db.execute(
"UPDATE commands SET status=?,phase=?,result_json=COALESCE(?,result_json),last_error=?,lease_owner=CASE WHEN ? THEN NULL ELSE lease_owner END,lease_until=CASE WHEN ? THEN NULL ELSE lease_until END,updated_at=? WHERE command_id=?",
(status, phase, json.dumps(result, sort_keys=True) if result is not None else None, error, release, release, self.clock(), command_id),
)
def _retry_or_dead(self, command_id: str, path: Path, error: Exception) -> None:
message = f"{type(error).__name__}:{str(error)[:240]}"
with self._db() as db:
row = db.execute("SELECT attempts,phase FROM commands WHERE command_id=?", (command_id,)).fetchone()
attempts = row["attempts"] if row else self.config.max_attempts
if str(error) == "gateway_stale_state_version" and row:
column = "start_event_json" if row["phase"] == "START" else "end_event_json"
db.execute(f"UPDATE commands SET {column}=NULL WHERE command_id=?", (command_id,))
if attempts >= self.config.max_attempts:
db.execute("UPDATE commands SET status='DEAD_LETTER',last_error=?,lease_owner=NULL,lease_until=NULL,updated_at=? WHERE command_id=?", (message, self.clock(), command_id))
self._move(path, self.config.dead_letter_dir)
self._audit("DEAD_LETTER", command_id, error=message)
else:
db.execute("UPDATE commands SET status='RETRY',last_error=?,next_attempt=?,lease_owner=NULL,lease_until=NULL,updated_at=? WHERE command_id=?", (message, self.clock() + self.config.retry_seconds, self.clock(), command_id))
self._audit("RETRY_SCHEDULED", command_id, attempt=attempts, error=message)
def _event(self, command: dict[str, Any], event_type: str, status: str, suffix: str, result: dict[str, Any] | None = None) -> dict[str, Any]:
return {
"schema_version": 1, "project_key": command["project_key"],
"contract_commit": command["contract_commit"],
"event_id": f"{command['command_id']}:{suffix}", "source_agent": "codex",
"event_type": event_type, "work_unit_id": command["work_unit_id"],
"status": status, "state_version": command["state_version"],
"implementation_commit": None, "result_commit": None, "blocker": None,
"evidence_refs": [], "payload": {"command_id": command["command_id"], "result": result or {}},
}
def _gateway_token(self) -> str:
token = _read_secure_text(
self.config.gateway_token_file,
writable_mask=0o027,
max_bytes=16_384,
allowed_owners={0, os.geteuid()},
).strip()
if not token or "\n" in token or "\r" in token:
raise WatcherError("invalid_gateway_token")
return token
def _gateway_state_version(self, project_key: str, fallback: int) -> int:
state_url = self.config.gateway_endpoint.removesuffix("/events") + "/state/" + urllib.parse.quote(project_key, safe="")
request = urllib.request.Request(
state_url,
headers={"Authorization": f"Bearer {self._gateway_token()}"},
method="GET",
)
try:
with urllib.request.urlopen(request, timeout=15) as response:
payload = json.loads(response.read(262_145))
version = payload.get("state_version")
if not isinstance(version, int) or version < 0:
raise WatcherError("invalid_gateway_state")
return version
except urllib.error.HTTPError as exc:
if exc.code == 404:
return fallback
raise WatcherError(f"gateway_state_http_{exc.code}") from exc
except urllib.error.URLError as exc:
raise WatcherError("gateway_state_unavailable") from exc
def _durable_event(self, command: dict[str, Any], column: str, event: dict[str, Any]) -> dict[str, Any]:
with self._db() as db:
row = db.execute(f"SELECT {column} FROM commands WHERE command_id=?", (command["command_id"],)).fetchone()
if row and row[column]:
return json.loads(row[column])
if self._uses_gateway:
event["state_version"] = self._gateway_state_version(command["project_key"], command["state_version"])
encoded = json.dumps(event, sort_keys=True, separators=(",", ":"))
with self._db() as db:
db.execute(f"UPDATE commands SET {column}=? WHERE command_id=? AND {column} IS NULL", (encoded, command["command_id"]))
saved = db.execute(f"SELECT {column} FROM commands WHERE command_id=?", (command["command_id"],)).fetchone()
if not saved or not saved[column]:
raise WatcherError("event_persistence_failed")
return json.loads(saved[column])
def _post_event(self, event: dict[str, Any]) -> None:
request = urllib.request.Request(
self.config.gateway_endpoint,
data=json.dumps(event, separators=(",", ":")).encode(),
headers={"Authorization": f"Bearer {self._gateway_token()}", "Content-Type": "application/json"},
method="POST",
)
try:
with urllib.request.urlopen(request, timeout=15) as response:
if response.status not in {200, 201, 202}:
raise WatcherError(f"gateway_http_{response.status}")
except urllib.error.HTTPError as exc:
body = exc.read(16_384)
try:
reason = json.loads(body).get("error")
except (json.JSONDecodeError, UnicodeDecodeError, AttributeError):
reason = None
if exc.code == 409 and reason == "stale_state_version":
raise WatcherError("gateway_stale_state_version") from exc
raise WatcherError(f"gateway_http_{exc.code}") from exc
except urllib.error.URLError as exc:
raise WatcherError("gateway_unavailable") from exc
def _execute(self, command: dict[str, Any]) -> dict[str, Any]:
execution = command["execution"]
if execution["kind"] == "acceptance_probe":
return {"kind": "acceptance_probe", "input_sha256": hashlib.sha256(execution["input"].encode()).hexdigest(), "exit_code": 0}
assert self.config.executor_path is not None
proc = subprocess.run(
[str(self.config.executor_path), *self.config.executor_args],
input=execution["input"], text=True, stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL, timeout=self.config.executor_timeout_seconds,
check=False, env={"PATH": "/usr/bin:/bin", "LANG": "C.UTF-8"},
)
if proc.returncode != 0:
raise WatcherError(f"codex_executor_failed:{proc.returncode}")
return {"kind": "codex", "exit_code": 0}
def _preflight_execution(self, command: dict[str, Any]) -> None:
if command["execution"]["kind"] == "acceptance_probe":
return
if self.config.executor_path is None:
raise WatcherError("codex_executor_unavailable")
info = _secure_regular(self.config.executor_path)
if not info.st_mode & stat.S_IXUSR:
raise WatcherError("codex_executor_not_executable")
def _move(self, source: Path, target_dir: Path) -> None:
if not source.exists() and not source.is_symlink():
return
target = target_dir / source.name
if target.exists() or target.is_symlink():
target = target_dir / f"{source.stem}-{uuid.uuid4().hex[:8]}{source.suffix}"
os.replace(source, target)
def _reject_unregistered(self, path: Path, error: Exception) -> None:
command_id = path.stem[:128] if ID_RE.fullmatch(path.stem[:128]) else f"invalid-{uuid.uuid4().hex[:12]}"
self._audit("COMMAND_REJECTED", command_id, error=f"{type(error).__name__}:{str(error)[:240]}")
self._move(path, self.config.dead_letter_dir)
def process_path(self, path: Path) -> bool:
try:
command, digest = self._read_command(path)
registration = self._register(command, digest, path)
if registration == "duplicate_terminal":
self._move(path, self.config.completed_dir)
return False
row = self._claim(command["command_id"])
if row is None:
return False
phase = row["phase"]
result = json.loads(row["result_json"]) if row["result_json"] else None
if phase == "START":
start_event = self._durable_event(
command,
"start_event_json",
self._event(command, "work_unit_started", "RUNNING", "started"),
)
self.event_poster(start_event)
self._audit("TASK_STARTED", command["command_id"])
self._update(command["command_id"], status="PENDING", phase="EXECUTE")
phase = "EXECUTE"
if phase == "EXECUTE":
self._preflight_execution(command)
self._update(command["command_id"], status="CLAIMED", phase="EXECUTING")
phase = "EXECUTING"
result = self.executor(command)
self._audit("TASK_EXECUTED", command["command_id"], result=result)
self._update(command["command_id"], status="PENDING", phase="END", result=result)
phase = "END"
elif phase == "EXECUTING":
raise WatcherError("ambiguous_execution_not_repeated")
if phase == "END":
assert result is not None
end_event = self._durable_event(
command,
"end_event_json",
self._event(command, "work_unit_ended", "PASS", "ended", result),
)
self.event_poster(end_event)
self._audit("TASK_ENDED", command["command_id"])
self._audit("EVENT_POSTED", command["command_id"], event="work_unit_ended")
self._update(command["command_id"], status="COMPLETED", phase="DONE", result=result)
self._move(path, self.config.completed_dir)
return True
except Exception as exc:
try:
if isinstance(exc, WatcherError) and str(exc) in {"duplicate_command_payload_conflict", "duplicate_work_unit"}:
self._reject_unregistered(path, exc)
elif "command" in locals():
self._retry_or_dead(command["command_id"], path, exc)
else:
self._reject_unregistered(path, exc)
except Exception:
pass
return False
def run_once(self) -> int:
failures = 0
for path in sorted(self.config.active_dir.glob("*.json")):
if not self.process_path(path):
failures += 1
return 1 if failures else 0
def run_forever(self) -> int:
while True:
self.run_once()
time.sleep(self.config.poll_seconds)
@@ -1,3 +0,0 @@
"""Reliable central orchestration gateway for AIOS."""
__version__ = "0.2.0"
@@ -1,34 +0,0 @@
from __future__ import annotations
import argparse
import logging
from pathlib import Path
from .config import Config
from .service import Runtime, serve
def main() -> int:
parser = argparse.ArgumentParser(description="AIOS Orchestrator Gateway")
parser.add_argument("--config", type=Path, required=True)
parser.add_argument("--log-level", default="INFO")
parser.add_argument(
"--poll-once",
action="store_true",
help="Run one inbox/model/outbox/OpenClaw synchronization polling cycle.",
)
args = parser.parse_args()
logging.basicConfig(
level=getattr(logging, args.log_level.upper(), logging.INFO),
format="%(asctime)s %(levelname)s %(name)s %(message)s",
)
if args.poll_once:
runtime = Runtime(Config.from_file(args.config))
runtime.poll_once()
return 0
serve(args.config)
return 0
if __name__ == "__main__":
raise SystemExit(main())
@@ -1,178 +0,0 @@
from __future__ import annotations
import json
import urllib.error
import urllib.request
from typing import Any
from .errors import TriggerError
from .models import DECISION_SCHEMA, Decision, Event
class WorkspaceAgentClient:
"""Asynchronous Workspace Agent trigger.
The official endpoint returns only 202 and no run ID or retrievable output.
Completion therefore arrives through the gateway callback endpoint.
"""
def __init__(self, trigger_id: str, token: str, timeout_seconds: int = 30):
self.trigger_id = trigger_id
self.token = token
self.timeout_seconds = timeout_seconds
def trigger(self, event: Event) -> None:
url = f"https://api.chatgpt.com/v1/workspace_agents/{self.trigger_id}/trigger"
prompt = (
"Process this AIOS orchestration event under the committed contract. "
"When complete, call submit_orchestration_decision with strict JSON. "
"Do not fabricate tests, Git state, secrets, evidence, or deployment facts.\n\n"
+ event.canonical_json()
)
body = json.dumps(
{
"conversation_key": event.project_key,
"input": prompt,
}
).encode()
request = urllib.request.Request(
url,
data=body,
method="POST",
headers={
"Authorization": f"Bearer {self.token}",
"Content-Type": "application/json",
"Idempotency-Key": event.event_id,
"User-Agent": "aios-orchestrator-gateway/0.2",
},
)
try:
with urllib.request.urlopen(request, timeout=self.timeout_seconds) as response:
response.read(1024)
if response.status != 202:
raise TriggerError(f"workspace_agent_http_{response.status}")
except urllib.error.HTTPError as exc:
raise TriggerError(f"workspace_agent_http_{exc.code}") from exc
except (urllib.error.URLError, TimeoutError, OSError) as exc:
raise TriggerError("workspace_agent_trigger_failed") from exc
class ResponsesClient:
"""Background Responses API client with polling and strict output validation."""
def __init__(self, api_key: str, model: str, timeout_seconds: int = 60):
self.api_key = api_key
self.model = model
self.timeout_seconds = timeout_seconds
def start(self, event: Event) -> str:
body = {
"model": self.model,
"background": True,
"instructions": (
"You are the AIOS central orchestration brain. Apply the exact "
"contract_commit in the event. Return only a strict decision. "
"Never fabricate evidence, secrets, Git facts, tests, approvals, "
"or deployment state. Keep external blockers fail-closed."
),
"input": event.canonical_json(),
"text": {
"format": {
"type": "json_schema",
"name": "aios_orchestrator_decision",
"strict": True,
"schema": DECISION_SCHEMA,
}
},
"metadata": {
"event_id": event.event_id,
"project_key": event.project_key,
"contract_commit": event.contract_commit,
},
}
payload = self._request(
"POST",
"https://api.openai.com/v1/responses",
body,
idempotency_key=event.event_id,
)
response_id = payload.get("id")
if not isinstance(response_id, str) or not response_id.startswith("resp_"):
raise TriggerError("responses_missing_id")
return response_id
def poll(self, response_id: str) -> tuple[str, Decision | None]:
payload = self._request(
"GET",
f"https://api.openai.com/v1/responses/{response_id}",
None,
)
status = payload.get("status")
if status in {"queued", "in_progress"}:
return str(status), None
if status == "completed":
text = _extract_output_text(payload)
try:
return "completed", Decision.from_dict(json.loads(text))
except json.JSONDecodeError as exc:
raise TriggerError("responses_invalid_json") from exc
if status in {"failed", "cancelled", "incomplete"}:
raise TriggerError(f"responses_{status}")
raise TriggerError("responses_unknown_status")
def _request(
self,
method: str,
url: str,
body: dict[str, Any] | None,
*,
idempotency_key: str | None = None,
) -> dict[str, Any]:
encoded = json.dumps(body).encode() if body is not None else None
headers = {
"Authorization": f"Bearer {self.api_key}",
"Content-Type": "application/json",
"User-Agent": "aios-orchestrator-gateway/0.2",
}
if idempotency_key:
headers["Idempotency-Key"] = idempotency_key
request = urllib.request.Request(
url,
data=encoded,
method=method,
headers=headers,
)
try:
with urllib.request.urlopen(request, timeout=self.timeout_seconds) as response:
raw = response.read(4_194_304)
if response.status not in {200, 201}:
raise TriggerError(f"responses_http_{response.status}")
except urllib.error.HTTPError as exc:
raise TriggerError(f"responses_http_{exc.code}") from exc
except (urllib.error.URLError, TimeoutError, OSError) as exc:
raise TriggerError("responses_request_failed") from exc
try:
payload = json.loads(raw)
except json.JSONDecodeError as exc:
raise TriggerError("responses_invalid_payload") from exc
if not isinstance(payload, dict):
raise TriggerError("responses_payload_not_object")
return payload
def _extract_output_text(payload: dict[str, Any]) -> str:
output = payload.get("output")
if not isinstance(output, list):
raise TriggerError("responses_missing_output")
for item in output:
if not isinstance(item, dict):
continue
content = item.get("content")
if not isinstance(content, list):
continue
for part in content:
if isinstance(part, dict) and part.get("type") == "output_text":
text = part.get("text")
if isinstance(text, str):
return text
raise TriggerError("responses_missing_output_text")
@@ -1,203 +0,0 @@
from __future__ import annotations
from dataclasses import dataclass
import os
from pathlib import Path
from typing import Any
from .errors import ConfigurationError
from .securefs import read_secure_json, read_secure_text
@dataclass(frozen=True)
class Config:
host: str
port: int
project_key: str
database_path: Path
event_inbox_dir: Path
decision_inbox_dir: Path
dispatch_outbox_dir: Path
openclaw_sync_dir: Path
command_queue_dir: Path
inbound_token_file: Path
callback_token_file: Path
contract_commit: str
workspace_trigger_id: str | None
workspace_token_file: Path | None
responses_api_key_file: Path | None
responses_model: str | None
poll_interval_seconds: int
summary_interval_seconds: int
callback_timeout_seconds: int
lease_seconds: int
retry_base_seconds: int
max_retries: int
max_same_blocker_retries: int
max_hops_per_gate: int
openclaw_sync_endpoint: str | None
openclaw_sync_token_file: Path | None
git_poll_enabled: bool
git_poll_bare_repo: Path | None
git_poll_ref_prefixes: tuple[str, ...]
git_poll_interval_seconds: int
@classmethod
def from_file(cls, path: Path) -> "Config":
owner_uid = int(os.environ.get("AIOS_ORCHESTRATOR_CONFIG_OWNER_UID", "0"))
raw = read_secure_json(path, expected_uid=owner_uid)
expected = {
"host", "port", "project_key", "database_path", "event_inbox_dir",
"decision_inbox_dir", "dispatch_outbox_dir", "openclaw_sync_dir",
"command_queue_dir", "inbound_token_file", "callback_token_file",
"contract_commit", "workspace_agent", "responses_fallback",
"polling", "loop_controls", "openclaw_sync", "git_poll",
}
if set(raw) != expected:
raise ConfigurationError("invalid_config_fields")
def path_value(key: str) -> Path:
value = raw.get(key)
if not isinstance(value, str):
raise ConfigurationError(f"invalid_{key}")
result = Path(value)
if not result.is_absolute():
raise ConfigurationError(f"path_not_absolute:{key}")
return result
def integer(container: dict[str, Any], key: str, lo: int, hi: int) -> int:
value = container.get(key)
if not isinstance(value, int) or not lo <= value <= hi:
raise ConfigurationError(f"invalid_{key}")
return value
host = raw.get("host")
port = raw.get("port")
project_key = raw.get("project_key")
contract = raw.get("contract_commit")
if not isinstance(host, str) or not host:
raise ConfigurationError("invalid_host")
if not isinstance(project_key, str) or not project_key:
raise ConfigurationError("invalid_project_key")
if not isinstance(port, int) or not 1 <= port <= 65535:
raise ConfigurationError("invalid_port")
if not isinstance(contract, str) or len(contract) != 40:
raise ConfigurationError("invalid_contract_commit")
workspace = raw.get("workspace_agent")
responses = raw.get("responses_fallback")
polling = raw.get("polling")
loop = raw.get("loop_controls")
sync = raw.get("openclaw_sync")
git_poll = raw.get("git_poll")
if not all(isinstance(x, dict) for x in (workspace, responses, polling, loop, sync, git_poll)):
raise ConfigurationError("invalid_nested_config")
trigger_id = workspace.get("trigger_id")
workspace_token = workspace.get("access_token_file")
if trigger_id is not None:
if not isinstance(trigger_id, str) or not trigger_id.startswith("agtch_"):
raise ConfigurationError("invalid_workspace_trigger_id")
if not isinstance(workspace_token, str) or not Path(workspace_token).is_absolute():
raise ConfigurationError("invalid_workspace_token_file")
workspace_token_file = Path(workspace_token)
else:
workspace_token_file = None
responses_key = responses.get("api_key_file")
responses_model = responses.get("model")
if responses_key is not None:
if not isinstance(responses_key, str) or not Path(responses_key).is_absolute():
raise ConfigurationError("invalid_responses_key_file")
if not isinstance(responses_model, str) or not responses_model:
raise ConfigurationError("invalid_responses_model")
responses_key_file = Path(responses_key)
else:
responses_key_file = None
responses_model = None
if trigger_id is None and responses_key_file is None:
raise ConfigurationError("no_central_model_channel")
endpoint = sync.get("endpoint")
token_file = sync.get("token_file")
if endpoint is not None and (not isinstance(endpoint, str) or not endpoint.startswith(("http://", "https://"))):
raise ConfigurationError("invalid_openclaw_sync_endpoint")
if endpoint is not None:
if not isinstance(token_file, str) or not Path(token_file).is_absolute():
raise ConfigurationError("invalid_openclaw_sync_token_file")
sync_token_file = Path(token_file)
else:
sync_token_file = None
git_enabled = git_poll.get("enabled")
if not isinstance(git_enabled, bool):
raise ConfigurationError("invalid_git_poll_enabled")
git_bare_repo_raw = git_poll.get("bare_repo")
git_prefixes_raw = git_poll.get("ref_prefixes")
if git_enabled:
if not isinstance(git_bare_repo_raw, str) or not Path(git_bare_repo_raw).is_absolute():
raise ConfigurationError("invalid_git_poll_bare_repo")
if (
not isinstance(git_prefixes_raw, list)
or not git_prefixes_raw
or any(not isinstance(item, str) or not item.startswith("refs/") for item in git_prefixes_raw)
):
raise ConfigurationError("invalid_git_poll_ref_prefixes")
git_bare_repo = Path(git_bare_repo_raw)
git_prefixes = tuple(git_prefixes_raw)
else:
git_bare_repo = None
git_prefixes = ()
return cls(
host=host,
port=port,
project_key=project_key,
database_path=path_value("database_path"),
event_inbox_dir=path_value("event_inbox_dir"),
decision_inbox_dir=path_value("decision_inbox_dir"),
dispatch_outbox_dir=path_value("dispatch_outbox_dir"),
openclaw_sync_dir=path_value("openclaw_sync_dir"),
command_queue_dir=path_value("command_queue_dir"),
inbound_token_file=path_value("inbound_token_file"),
callback_token_file=path_value("callback_token_file"),
contract_commit=contract,
workspace_trigger_id=trigger_id,
workspace_token_file=workspace_token_file,
responses_api_key_file=responses_key_file,
responses_model=responses_model,
poll_interval_seconds=integer(polling, "interval_seconds", 1, 300),
summary_interval_seconds=integer(polling, "summary_interval_seconds", 10, 86400),
callback_timeout_seconds=integer(loop, "callback_timeout_seconds", 30, 86400),
lease_seconds=integer(loop, "lease_seconds", 10, 3600),
retry_base_seconds=integer(loop, "retry_base_seconds", 1, 3600),
max_retries=integer(loop, "max_retries", 0, 20),
max_same_blocker_retries=integer(loop, "max_same_blocker_retries", 0, 20),
max_hops_per_gate=integer(loop, "max_hops_per_gate", 1, 100),
openclaw_sync_endpoint=endpoint,
openclaw_sync_token_file=sync_token_file,
git_poll_enabled=git_enabled,
git_poll_bare_repo=git_bare_repo,
git_poll_ref_prefixes=git_prefixes,
git_poll_interval_seconds=integer(git_poll, "interval_seconds", 5, 3600),
)
def _secret(self, path: Path) -> str:
owner_uid = int(os.environ.get("AIOS_ORCHESTRATOR_SECRET_OWNER_UID", "0"))
return read_secure_text(path, expected_uid=owner_uid, max_bytes=64_000)
def inbound_token(self) -> str:
return self._secret(self.inbound_token_file)
def callback_token(self) -> str:
return self._secret(self.callback_token_file)
def workspace_token(self) -> str | None:
return self._secret(self.workspace_token_file) if self.workspace_token_file else None
def responses_api_key(self) -> str | None:
return self._secret(self.responses_api_key_file) if self.responses_api_key_file else None
def openclaw_sync_token(self) -> str | None:
return self._secret(self.openclaw_sync_token_file) if self.openclaw_sync_token_file else None
@@ -1,89 +0,0 @@
from __future__ import annotations
import json
from pathlib import Path
import re
import os
import stat
from typing import Any
from .errors import DispatchError
from .securefs import (
atomic_write_bytes,
atomic_write_bytes_shared,
ensure_secure_directory,
ensure_shared_directory,
read_secure_bytes,
)
SAFE_ID = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$")
class DispatchSink:
"""Reliable file-based dispatch adapter for existing OpenClaw/Codex watchers."""
def __init__(self, outbox_dir: Path, command_queue_dir: Path, contract_commit: str):
self.outbox_dir = Path(outbox_dir)
self.command_queue_dir = Path(command_queue_dir)
self.contract_commit = contract_commit
ensure_secure_directory(self.outbox_dir)
ensure_shared_directory(self.command_queue_dir)
def dispatch(self, record: dict[str, Any]) -> tuple[Path, Path]:
work_unit_id = record.get("work_unit_id")
event_id = record.get("event_id")
agent = record.get("assigned_agent")
payload_json = record.get("payload_json")
if (
not isinstance(work_unit_id, str)
or not SAFE_ID.fullmatch(work_unit_id)
or not isinstance(event_id, str)
or not SAFE_ID.fullmatch(event_id)
or agent not in {"openclaw", "codex"}
or not isinstance(payload_json, str)
):
raise DispatchError("invalid_dispatch_record")
try:
work_unit = json.loads(payload_json)
except json.JSONDecodeError as exc:
raise DispatchError("invalid_dispatch_payload") from exc
envelope = {
"schema_version": 1,
"contract_commit": self.contract_commit,
"event_id": event_id,
"assigned_agent": agent,
"work_unit": work_unit,
"callback": {
"event_endpoint": "/v1/orchestrator/events",
"start_event_type": "work_unit_started",
"end_event_type": "work_unit_completed",
},
}
outbox_path = self.outbox_dir / "dispatched" / f"{work_unit_id}.json"
queue_path = self.command_queue_dir / agent / "pending" / f"{work_unit_id}.json"
ensure_secure_directory(outbox_path.parent)
ensure_shared_directory(queue_path.parent)
# Idempotent immutable payload: existing identical file is accepted.
self._write_idempotent_json(outbox_path, envelope, shared=False)
self._write_idempotent_json(queue_path, envelope, shared=True)
return outbox_path, queue_path
@staticmethod
def _write_idempotent_json(path: Path, value: dict[str, Any], *, shared: bool) -> None:
payload = (json.dumps(value, indent=2, sort_keys=True) + "\n").encode()
try:
st = os.lstat(path)
except FileNotFoundError:
if shared:
atomic_write_bytes_shared(path, payload, mode=0o640)
else:
atomic_write_bytes(path, payload, mode=0o600)
return
if not stat.S_ISREG(st.st_mode):
raise DispatchError(f"dispatch_target_not_regular:{path.name}")
existing = read_secure_bytes(path, expected_uid=None, max_bytes=1_048_576)
if existing != payload:
raise DispatchError(f"dispatch_idempotency_conflict:{path.name}")
@@ -1,26 +0,0 @@
class OrchestratorError(Exception):
"""Base orchestration error."""
class ConfigurationError(OrchestratorError):
"""Unsafe or invalid configuration."""
class ValidationError(OrchestratorError):
"""Invalid event or decision."""
class AuthenticationError(OrchestratorError):
"""Authentication failed."""
class ConflictError(OrchestratorError):
"""Idempotency, lease, or optimistic concurrency conflict."""
class TriggerError(OrchestratorError):
"""Central model trigger failed."""
class DispatchError(OrchestratorError):
"""Dispatch or synchronization output failed."""
@@ -1,346 +0,0 @@
from __future__ import annotations
from dataclasses import dataclass, field
import hashlib
import json
import re
from typing import Any
from .errors import ValidationError
OID_RE = re.compile(r"^[0-9a-f]{40}$")
ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$")
AGENTS = {"openclaw", "codex", "gitea", "system", "workspace-agent"}
EVENT_STATUSES = {"READY", "RUNNING", "PASS", "BLOCKED", "FAIL", "TIMEOUT", "NOT_EXECUTED"}
VERDICTS = {"DISPATCH", "BLOCKED", "COMPLETE", "NOOP"}
EXECUTORS = {"openclaw", "codex"}
def req_str(value: dict[str, Any], key: str, pattern: re.Pattern[str] | None = None) -> str:
item = value.get(key)
if not isinstance(item, str) or not item:
raise ValidationError(f"invalid_{key}")
if pattern is not None and not pattern.fullmatch(item):
raise ValidationError(f"invalid_{key}")
return item
def opt_oid(item: Any, key: str) -> str | None:
if item is None:
return None
if not isinstance(item, str) or not OID_RE.fullmatch(item):
raise ValidationError(f"invalid_{key}")
return item
def string_list(value: dict[str, Any], key: str, limit: int) -> tuple[str, ...]:
raw = value.get(key)
if not isinstance(raw, list) or len(raw) > limit:
raise ValidationError(f"invalid_{key}")
result: list[str] = []
for item in raw:
if not isinstance(item, str) or not item or len(item) > 1024:
raise ValidationError(f"invalid_{key}")
result.append(item)
return tuple(result)
@dataclass(frozen=True)
class Event:
schema_version: int
project_key: str
contract_commit: str
event_id: str
source_agent: str
event_type: str
work_unit_id: str
status: str
state_version: int
implementation_commit: str | None = None
result_commit: str | None = None
blocker: str | None = None
evidence_refs: tuple[str, ...] = ()
payload: dict[str, Any] = field(default_factory=dict)
@classmethod
def from_dict(cls, value: dict[str, Any]) -> "Event":
allowed = {
"schema_version", "project_key", "contract_commit", "event_id",
"source_agent", "event_type", "work_unit_id", "status",
"state_version", "implementation_commit", "result_commit",
"blocker", "evidence_refs", "payload",
}
if not isinstance(value, dict) or set(value) - allowed:
raise ValidationError("invalid_event_fields")
if value.get("schema_version") != 1:
raise ValidationError("unsupported_event_schema")
source = req_str(value, "source_agent")
status = req_str(value, "status")
if source not in AGENTS:
raise ValidationError("invalid_source_agent")
if status not in EVENT_STATUSES:
raise ValidationError("invalid_event_status")
version = value.get("state_version")
if not isinstance(version, int) or version < 0:
raise ValidationError("invalid_state_version")
blocker = value.get("blocker")
if blocker is not None and (not isinstance(blocker, str) or len(blocker) > 512):
raise ValidationError("invalid_blocker")
payload = value.get("payload", {})
if not isinstance(payload, dict):
raise ValidationError("invalid_payload")
if len(json.dumps(payload, sort_keys=True).encode()) > 262_144:
raise ValidationError("payload_too_large")
return cls(
schema_version=1,
project_key=req_str(value, "project_key", ID_RE),
contract_commit=req_str(value, "contract_commit", OID_RE),
event_id=req_str(value, "event_id", ID_RE),
source_agent=source,
event_type=req_str(value, "event_type", ID_RE),
work_unit_id=req_str(value, "work_unit_id", ID_RE),
status=status,
state_version=version,
implementation_commit=opt_oid(value.get("implementation_commit"), "implementation_commit"),
result_commit=opt_oid(value.get("result_commit"), "result_commit"),
blocker=blocker,
evidence_refs=string_list(value, "evidence_refs", 64),
payload=payload,
)
def to_dict(self) -> dict[str, Any]:
return {
"schema_version": 1,
"project_key": self.project_key,
"contract_commit": self.contract_commit,
"event_id": self.event_id,
"source_agent": self.source_agent,
"event_type": self.event_type,
"work_unit_id": self.work_unit_id,
"status": self.status,
"state_version": self.state_version,
"implementation_commit": self.implementation_commit,
"result_commit": self.result_commit,
"blocker": self.blocker,
"evidence_refs": list(self.evidence_refs),
"payload": self.payload,
}
def canonical_json(self) -> str:
return json.dumps(self.to_dict(), separators=(",", ":"), sort_keys=True)
def digest(self) -> str:
return hashlib.sha256(self.canonical_json().encode()).hexdigest()
@dataclass(frozen=True)
class WorkUnit:
id: str
track_id: str
gate_id: str
primary_agent: str
fallback_agent: str
clean_base_commit: str
allowed_paths: tuple[str, ...]
required_checks: tuple[str, ...]
forbidden_operations: tuple[str, ...]
instruction: str
@classmethod
def from_dict(cls, value: dict[str, Any]) -> "WorkUnit":
expected = {
"id", "track_id", "gate_id", "primary_agent", "fallback_agent",
"clean_base_commit", "allowed_paths", "required_checks",
"forbidden_operations", "instruction",
}
if not isinstance(value, dict) or set(value) != expected:
raise ValidationError("invalid_work_unit_fields")
primary = req_str(value, "primary_agent")
fallback = req_str(value, "fallback_agent")
if primary not in EXECUTORS or fallback not in EXECUTORS or primary == fallback:
raise ValidationError("invalid_agent_assignment")
instruction = req_str(value, "instruction")
if len(instruction.encode()) > 65_536:
raise ValidationError("instruction_too_large")
return cls(
id=req_str(value, "id", ID_RE),
track_id=req_str(value, "track_id", ID_RE),
gate_id=req_str(value, "gate_id", ID_RE),
primary_agent=primary,
fallback_agent=fallback,
clean_base_commit=req_str(value, "clean_base_commit", OID_RE),
allowed_paths=string_list(value, "allowed_paths", 128),
required_checks=string_list(value, "required_checks", 128),
forbidden_operations=string_list(value, "forbidden_operations", 64),
instruction=instruction,
)
def to_dict(self) -> dict[str, Any]:
return {
"id": self.id,
"track_id": self.track_id,
"gate_id": self.gate_id,
"primary_agent": self.primary_agent,
"fallback_agent": self.fallback_agent,
"clean_base_commit": self.clean_base_commit,
"allowed_paths": list(self.allowed_paths),
"required_checks": list(self.required_checks),
"forbidden_operations": list(self.forbidden_operations),
"instruction": self.instruction,
}
@dataclass(frozen=True)
class Decision:
schema_version: int
project_key: str
contract_commit: str
event_id: str
expected_state_version: int
verdict: str
state_updates: dict[str, str]
next_work_units: tuple[WorkUnit, ...]
requires_human_input: bool
stop_reason: str | None
@classmethod
def from_dict(cls, value: dict[str, Any]) -> "Decision":
expected = {
"schema_version", "project_key", "contract_commit", "event_id",
"expected_state_version", "verdict", "state_updates",
"next_work_units", "requires_human_input", "stop_reason",
}
if not isinstance(value, dict) or set(value) != expected:
raise ValidationError("invalid_decision_fields")
if value.get("schema_version") != 1:
raise ValidationError("unsupported_decision_schema")
version = value.get("expected_state_version")
if not isinstance(version, int) or version < 0:
raise ValidationError("invalid_expected_state_version")
verdict = req_str(value, "verdict")
if verdict not in VERDICTS:
raise ValidationError("invalid_verdict")
updates = value.get("state_updates")
normalized: dict[str, str] = {}
if isinstance(updates, dict):
update_items = [{"key": key, "value": item} for key, item in updates.items()]
elif isinstance(updates, list):
update_items = updates
else:
raise ValidationError("invalid_state_updates")
if len(update_items) > 128:
raise ValidationError("invalid_state_updates")
for update in update_items:
if not isinstance(update, dict) or set(update) != {"key", "value"}:
raise ValidationError("invalid_state_update")
key = update.get("key")
item = update.get("value")
if not isinstance(key, str) or not ID_RE.fullmatch(key):
raise ValidationError("invalid_state_update_key")
if not isinstance(item, str) or not item or len(item) > 256:
raise ValidationError("invalid_state_update_value")
if key in normalized:
raise ValidationError("duplicate_state_update_key")
normalized[key] = item
raw_units = value.get("next_work_units")
if not isinstance(raw_units, list) or len(raw_units) > 32:
raise ValidationError("invalid_next_work_units")
units = tuple(WorkUnit.from_dict(item) for item in raw_units)
human = value.get("requires_human_input")
if not isinstance(human, bool):
raise ValidationError("invalid_requires_human_input")
stop = value.get("stop_reason")
if stop is not None and (not isinstance(stop, str) or len(stop) > 512):
raise ValidationError("invalid_stop_reason")
if verdict == "DISPATCH" and not units:
raise ValidationError("dispatch_without_work_units")
if verdict != "DISPATCH" and units:
raise ValidationError("work_units_without_dispatch")
return cls(
schema_version=1,
project_key=req_str(value, "project_key", ID_RE),
contract_commit=req_str(value, "contract_commit", OID_RE),
event_id=req_str(value, "event_id", ID_RE),
expected_state_version=version,
verdict=verdict,
state_updates=normalized,
next_work_units=units,
requires_human_input=human,
stop_reason=stop,
)
def to_dict(self) -> dict[str, Any]:
return {
"schema_version": 1,
"project_key": self.project_key,
"contract_commit": self.contract_commit,
"event_id": self.event_id,
"expected_state_version": self.expected_state_version,
"verdict": self.verdict,
"state_updates": [
{"key": key, "value": value}
for key, value in sorted(self.state_updates.items())
],
"next_work_units": [u.to_dict() for u in self.next_work_units],
"requires_human_input": self.requires_human_input,
"stop_reason": self.stop_reason,
}
DECISION_SCHEMA: dict[str, Any] = {
"type": "object",
"additionalProperties": False,
"required": [
"schema_version", "project_key", "contract_commit", "event_id",
"expected_state_version", "verdict", "state_updates",
"next_work_units", "requires_human_input", "stop_reason",
],
"properties": {
"schema_version": {"type": "integer", "const": 1},
"project_key": {"type": "string"},
"contract_commit": {"type": "string", "pattern": "^[0-9a-f]{40}$"},
"event_id": {"type": "string"},
"expected_state_version": {"type": "integer", "minimum": 0},
"verdict": {"type": "string", "enum": sorted(VERDICTS)},
"state_updates": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": False,
"required": ["key", "value"],
"properties": {
"key": {"type": "string"},
"value": {"type": "string"}
}
}
},
"next_work_units": {
"type": "array",
"maxItems": 32,
"items": {
"type": "object",
"additionalProperties": False,
"required": [
"id", "track_id", "gate_id", "primary_agent",
"fallback_agent", "clean_base_commit", "allowed_paths",
"required_checks", "forbidden_operations", "instruction",
],
"properties": {
"id": {"type": "string"},
"track_id": {"type": "string"},
"gate_id": {"type": "string"},
"primary_agent": {"type": "string", "enum": ["openclaw", "codex"]},
"fallback_agent": {"type": "string", "enum": ["openclaw", "codex"]},
"clean_base_commit": {"type": "string", "pattern": "^[0-9a-f]{40}$"},
"allowed_paths": {"type": "array", "items": {"type": "string"}},
"required_checks": {"type": "array", "items": {"type": "string"}},
"forbidden_operations": {"type": "array", "items": {"type": "string"}},
"instruction": {"type": "string"},
},
},
},
"requires_human_input": {"type": "boolean"},
"stop_reason": {"type": ["string", "null"]},
},
}
@@ -1,229 +0,0 @@
from __future__ import annotations
import json
import os
from pathlib import Path
import stat
from typing import Any
from .errors import ConfigurationError
_NOFOLLOW = getattr(os, "O_NOFOLLOW", 0)
def reject_symlink_chain(path: Path) -> None:
"""Reject symlinks in every existing component of an absolute path."""
path = Path(path)
if not path.is_absolute():
raise ConfigurationError(f"path_not_absolute:{path}")
current = Path(path.anchor)
for part in path.parts[1:]:
current = current / part
try:
st = os.lstat(current)
except FileNotFoundError:
continue
if stat.S_ISLNK(st.st_mode):
raise ConfigurationError(f"symlink_rejected:{current}")
def verify_secure_file(
path: Path,
*,
expected_uid: int | None,
allowed_write_bits: int = stat.S_IWUSR,
require_executable: bool = False,
) -> os.stat_result:
path = Path(path)
reject_symlink_chain(path)
before = os.lstat(path)
if not stat.S_ISREG(before.st_mode):
raise ConfigurationError(f"not_regular_file:{path}")
if expected_uid is not None and before.st_uid != expected_uid:
raise ConfigurationError(f"unexpected_owner:{path}")
write_bits = before.st_mode & (stat.S_IWUSR | stat.S_IWGRP | stat.S_IWOTH)
if write_bits & ~allowed_write_bits:
raise ConfigurationError(f"permissive_mode:{path}")
if require_executable and not (before.st_mode & stat.S_IXUSR):
raise ConfigurationError(f"not_executable:{path}")
fd = os.open(path, os.O_RDONLY | _NOFOLLOW)
try:
after = os.fstat(fd)
if (before.st_dev, before.st_ino) != (after.st_dev, after.st_ino):
raise ConfigurationError(f"inode_changed:{path}")
finally:
os.close(fd)
return before
def read_secure_bytes(
path: Path,
*,
expected_uid: int | None,
max_bytes: int = 1_048_576,
) -> bytes:
path = Path(path)
before = verify_secure_file(path, expected_uid=expected_uid)
if before.st_size > max_bytes:
raise ConfigurationError(f"file_too_large:{path}")
fd = os.open(path, os.O_RDONLY | _NOFOLLOW)
try:
data = bytearray()
while True:
chunk = os.read(fd, min(65536, max_bytes + 1 - len(data)))
if not chunk:
break
data.extend(chunk)
if len(data) > max_bytes:
raise ConfigurationError(f"file_too_large:{path}")
return bytes(data)
finally:
os.close(fd)
def read_secure_text(path: Path, *, expected_uid: int | None, max_bytes: int = 1_048_576) -> str:
try:
return read_secure_bytes(path, expected_uid=expected_uid, max_bytes=max_bytes).decode("utf-8").strip()
except UnicodeDecodeError as exc:
raise ConfigurationError(f"not_utf8:{path}") from exc
def read_secure_json(path: Path, *, expected_uid: int | None, max_bytes: int = 1_048_576) -> dict[str, Any]:
try:
value = json.loads(read_secure_text(path, expected_uid=expected_uid, max_bytes=max_bytes))
except json.JSONDecodeError as exc:
raise ConfigurationError(f"invalid_json:{path}") from exc
if not isinstance(value, dict):
raise ConfigurationError(f"json_root_not_object:{path}")
return value
def ensure_secure_directory(path: Path, *, mode: int = 0o700) -> None:
path = Path(path)
if not path.is_absolute():
raise ConfigurationError(f"path_not_absolute:{path}")
reject_symlink_chain(path.parent)
path.mkdir(parents=True, exist_ok=True, mode=mode)
reject_symlink_chain(path)
st = os.lstat(path)
if not stat.S_ISDIR(st.st_mode):
raise ConfigurationError(f"not_directory:{path}")
if st.st_mode & (stat.S_IWGRP | stat.S_IWOTH):
raise ConfigurationError(f"permissive_directory:{path}")
def atomic_write_bytes(path: Path, payload: bytes, *, mode: int = 0o600) -> None:
"""Write through a verified directory fd and atomically replace the target."""
path = Path(path)
ensure_secure_directory(path.parent)
parent_before = os.lstat(path.parent)
parent_fd = os.open(path.parent, os.O_RDONLY | os.O_DIRECTORY | _NOFOLLOW)
temp_name = f".{path.name}.tmp-{os.getpid()}-{os.urandom(6).hex()}"
try:
parent_after = os.fstat(parent_fd)
if (parent_before.st_dev, parent_before.st_ino) != (
parent_after.st_dev,
parent_after.st_ino,
):
raise ConfigurationError(f"directory_changed:{path.parent}")
fd = os.open(
temp_name,
os.O_WRONLY | os.O_CREAT | os.O_EXCL | _NOFOLLOW,
mode,
dir_fd=parent_fd,
)
try:
view = memoryview(payload)
while view:
written = os.write(fd, view)
view = view[written:]
os.fsync(fd)
finally:
os.close(fd)
os.replace(
temp_name,
path.name,
src_dir_fd=parent_fd,
dst_dir_fd=parent_fd,
)
os.fsync(parent_fd)
finally:
try:
os.unlink(temp_name, dir_fd=parent_fd)
except FileNotFoundError:
pass
os.close(parent_fd)
def atomic_write_json(path: Path, value: Any, *, mode: int = 0o600) -> None:
payload = (json.dumps(value, indent=2, sort_keys=True) + "\n").encode("utf-8")
atomic_write_bytes(path, payload, mode=mode)
def ensure_shared_directory(path: Path, *, group_writable: bool = False) -> None:
"""Verify/create a setgid queue directory shared with a consumer group."""
path = Path(path)
if not path.is_absolute():
raise ConfigurationError(f"path_not_absolute:{path}")
reject_symlink_chain(path.parent)
mode = 0o2770 if group_writable else 0o2750
try:
path.mkdir(parents=True, mode=mode)
except FileExistsError:
pass
else:
os.chmod(path, mode)
reject_symlink_chain(path)
st = os.lstat(path)
if not stat.S_ISDIR(st.st_mode):
raise ConfigurationError(f"not_directory:{path}")
observed = stat.S_IMODE(st.st_mode)
required = stat.S_ISGID | stat.S_IRGRP | stat.S_IXGRP
if group_writable:
required |= stat.S_IWGRP
if observed & 0o007 or observed & required != required:
raise ConfigurationError(f"invalid_shared_directory_mode:{path}")
def atomic_write_bytes_shared(
path: Path,
payload: bytes,
*,
mode: int = 0o640,
group_writable_directory: bool = False,
) -> None:
"""Atomic write into a setgid/group-readable shared queue directory."""
path = Path(path)
ensure_shared_directory(path.parent, group_writable=group_writable_directory)
parent_before = os.lstat(path.parent)
parent_fd = os.open(path.parent, os.O_RDONLY | os.O_DIRECTORY | _NOFOLLOW)
temp_name = f".{path.name}.tmp-{os.getpid()}-{os.urandom(6).hex()}"
try:
parent_after = os.fstat(parent_fd)
if (parent_before.st_dev, parent_before.st_ino) != (
parent_after.st_dev,
parent_after.st_ino,
):
raise ConfigurationError(f"directory_changed:{path.parent}")
fd = os.open(
temp_name,
os.O_WRONLY | os.O_CREAT | os.O_EXCL | _NOFOLLOW,
mode,
dir_fd=parent_fd,
)
os.fchmod(fd, mode)
try:
view = memoryview(payload)
while view:
written = os.write(fd, view)
view = view[written:]
os.fsync(fd)
finally:
os.close(fd)
os.replace(temp_name, path.name, src_dir_fd=parent_fd, dst_dir_fd=parent_fd)
os.fsync(parent_fd)
finally:
try:
os.unlink(temp_name, dir_fd=parent_fd)
except FileNotFoundError:
pass
os.close(parent_fd)
@@ -1,642 +0,0 @@
from __future__ import annotations
import hashlib
import hmac
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
import json
import logging
import os
from pathlib import Path
import socket
import subprocess
import threading
import time
from typing import Any
from urllib.parse import urlparse
from .clients import ResponsesClient, WorkspaceAgentClient
from .config import Config
from .dispatch import DispatchSink
from .errors import (
AuthenticationError,
ConflictError,
DispatchError,
OrchestratorError,
TriggerError,
ValidationError,
)
from .models import Decision, Event
from .securefs import ensure_secure_directory, ensure_shared_directory, read_secure_json
from .store import Store
from .sync import OpenClawSynchronizer, lifecycle_record
LOG = logging.getLogger("aios-orchestrator-gateway")
class Runtime:
def __init__(self, config: Config):
self.config = config
self.store = Store(config.database_path)
self.dispatch = DispatchSink(
config.dispatch_outbox_dir,
config.command_queue_dir,
config.contract_commit,
)
self.workspace = None
workspace_token = config.workspace_token()
if config.workspace_trigger_id and workspace_token:
self.workspace = WorkspaceAgentClient(
config.workspace_trigger_id,
workspace_token,
)
self.responses = None
responses_key = config.responses_api_key()
if responses_key and config.responses_model:
self.responses = ResponsesClient(
responses_key,
config.responses_model,
)
self.synchronizer = OpenClawSynchronizer(
config.openclaw_sync_dir,
endpoint=config.openclaw_sync_endpoint,
bearer_token=config.openclaw_sync_token(),
)
self.worker_id = f"{socket.gethostname()}-{os.getpid()}-{threading.get_native_id()}"
self.stop_event = threading.Event()
self.worker = threading.Thread(target=self._loop, daemon=True)
self._next_git_poll = 0.0
for directory in (
config.event_inbox_dir,
config.decision_inbox_dir,
config.dispatch_outbox_dir,
config.openclaw_sync_dir,
):
ensure_secure_directory(directory)
ensure_shared_directory(config.command_queue_dir)
def start(self) -> None:
self.worker.start()
def stop(self) -> None:
self.stop_event.set()
if self.worker.is_alive():
self.worker.join(timeout=15)
self.store.close()
def submit_event(self, payload: dict[str, Any]) -> tuple[bool, dict[str, Any]]:
event = Event.from_dict(payload)
if event.contract_commit != self.config.contract_commit:
raise ConflictError("contract_version_mismatch")
created, stored = self.store.register_event(event)
if created:
self._enqueue_event_lifecycle(event)
return created, stored
def submit_decision(self, payload: dict[str, Any]) -> int:
decision = Decision.from_dict(payload)
if decision.contract_commit != self.config.contract_commit:
raise ConflictError("contract_version_mismatch")
version = self.store.apply_decision(
decision,
max_hops_per_gate=self.config.max_hops_per_gate,
max_same_blocker_retries=self.config.max_same_blocker_retries,
)
self._enqueue_decision_lifecycle(decision, version)
return version
def _loop(self) -> None:
next_summary = 0.0
while not self.stop_event.wait(self.config.poll_interval_seconds):
try:
self.poll_once()
if time.monotonic() >= next_summary:
self.enqueue_periodic_summaries()
next_summary = time.monotonic() + self.config.summary_interval_seconds
except Exception:
LOG.exception("poll_cycle_failed")
def poll_once(self) -> None:
"""One deterministic reliability cycle.
This is deliberately callable from a systemd timer or health supervisor
in addition to the internal loop.
"""
self.ingest_file_inboxes()
self.poll_git_refs()
self.process_new_events()
self.process_workspace_timeouts()
self.poll_background_responses()
self.dispatch_work_units()
self.synchronize_openclaw()
def ingest_file_inboxes(self) -> None:
self._ingest_directory(self.config.event_inbox_dir, kind="event")
self._ingest_directory(self.config.decision_inbox_dir, kind="decision")
def _ingest_directory(self, directory: Path, *, kind: str) -> None:
pending = directory / "pending"
processed = directory / "processed"
rejected = directory / "rejected"
ensure_shared_directory(pending, group_writable=True)
ensure_secure_directory(processed)
ensure_secure_directory(rejected)
for path in sorted(pending.glob("*.json"))[:128]:
try:
payload = read_secure_json(path, expected_uid=None)
if kind == "event":
self.submit_event(payload)
else:
self.submit_decision(payload)
target = processed / path.name
except Exception as exc:
LOG.warning("file_inbox_rejected path=%s error=%s", path, type(exc).__name__)
target = rejected / path.name
if target.exists():
# Same file name is an idempotency replay. Keep original audit copy.
path.unlink()
else:
path.replace(target)
def poll_git_refs(self) -> None:
"""Poll authoritative local bare refs so missed webhooks cannot stall the loop."""
if not self.config.git_poll_enabled or self.config.git_poll_bare_repo is None:
return
now = time.monotonic()
if now < self._next_git_poll:
return
self._next_git_poll = now + self.config.git_poll_interval_seconds
command = [
"git",
f"--git-dir={self.config.git_poll_bare_repo}",
"for-each-ref",
"--format=%(refname) %(objectname)",
*self.config.git_poll_ref_prefixes,
]
try:
result = subprocess.run(
command,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
check=False,
timeout=30,
env={"PATH": "/usr/bin:/bin", "LANG": "C", "LC_ALL": "C"},
)
except (OSError, subprocess.SubprocessError):
LOG.exception("git_ref_poll_failed")
return
if result.returncode != 0:
LOG.warning("git_ref_poll_rc=%s", result.returncode)
return
refs: dict[str, str] = {}
for line in result.stdout.splitlines():
refname, sep, oid = line.partition(" ")
if not sep or not refname.startswith("refs/") or len(oid) != 40:
continue
if any(ch not in "0123456789abcdef" for ch in oid):
continue
refs[refname] = oid
initialized, changes = self.store.observe_refs(refs)
if not initialized or not changes:
return
payload_changes = [
{"ref": refname, "old_oid": old_oid, "new_oid": new_oid}
for refname, old_oid, new_oid in sorted(changes)
]
canonical = json.dumps(payload_changes, separators=(",", ":"), sort_keys=True)
event_id = "gitpoll-" + hashlib.sha256(canonical.encode()).hexdigest()[:40]
state = self.store.project_state(self.config.project_key)
state_version = 0 if state is None else int(state["state_version"])
event = Event.from_dict(
{
"schema_version": 1,
"project_key": self.config.project_key,
"contract_commit": self.config.contract_commit,
"event_id": event_id,
"source_agent": "gitea",
"event_type": "git_refs_changed",
"work_unit_id": "GIT-REF-POLL",
"status": "READY",
"state_version": state_version,
"implementation_commit": None,
"result_commit": None,
"blocker": None,
"evidence_refs": [],
"payload": {"changes": payload_changes},
}
)
try:
self.submit_event(event.to_dict())
except ConflictError:
LOG.info("git_ref_event_already_registered event_id=%s", event_id)
def process_new_events(self) -> None:
rows = self.store.claim_events(
owner=self.worker_id,
statuses=("RECEIVED", "TRIGGER_FAILED"),
limit=32,
lease_seconds=self.config.lease_seconds,
)
for row in rows:
event = Event.from_dict(json.loads(row["event_json"]))
attempts = int(row["attempts"])
try:
if self.workspace is not None:
self.workspace.trigger(event)
self.store.update_event_trigger(
event.event_id,
status="AWAITING_DECISION",
channel="workspace_agent",
remote_id=None,
)
elif self.responses is not None:
response_id = self.responses.start(event)
self.store.update_event_trigger(
event.event_id,
status="POLLING_RESPONSE",
channel="responses_api",
remote_id=response_id,
retry_after=self.config.poll_interval_seconds,
)
else:
raise TriggerError("no_model_channel")
except TriggerError as exc:
self._retry_or_dead_letter(event, attempts, str(exc))
def process_workspace_timeouts(self) -> None:
cutoff = int(time.time()) - self.config.callback_timeout_seconds
for row in self.store.claim_workspace_timeouts(
owner=self.worker_id,
older_than=cutoff,
limit=32,
lease_seconds=self.config.lease_seconds,
):
event = Event.from_dict(json.loads(row["event_json"]))
if self.responses is None:
self._retry_or_dead_letter(
event,
int(row["attempts"]),
"workspace_callback_timeout",
)
continue
try:
response_id = self.responses.start(event)
self.store.update_event_trigger(
event.event_id,
status="POLLING_RESPONSE",
channel="responses_api",
remote_id=response_id,
retry_after=self.config.poll_interval_seconds,
increment_attempt=True,
)
except TriggerError as exc:
self._retry_or_dead_letter(event, int(row["attempts"]), str(exc))
def poll_background_responses(self) -> None:
if self.responses is None:
return
for row in self.store.claim_response_polls(
owner=self.worker_id,
limit=32,
lease_seconds=self.config.lease_seconds,
):
event = Event.from_dict(json.loads(row["event_json"]))
response_id = row.get("remote_id")
if not isinstance(response_id, str):
self._retry_or_dead_letter(event, int(row["attempts"]), "missing_response_id")
continue
try:
status, decision = self.responses.poll(response_id)
if status in {"queued", "in_progress"}:
attempts = int(row["attempts"])
if attempts + 1 > self.config.max_retries:
self._retry_or_dead_letter(
event, attempts, f"response_{status}_retry_limit"
)
continue
self.store.update_event_trigger(
event.event_id,
status="POLLING_RESPONSE",
channel="responses_api",
remote_id=response_id,
retry_after=self.config.poll_interval_seconds,
increment_attempt=True,
)
continue
if decision is None:
raise TriggerError("completed_without_decision")
self.submit_decision(decision.to_dict())
except OrchestratorError as exc:
self._retry_or_dead_letter(event, int(row["attempts"]), str(exc))
def dispatch_work_units(self) -> None:
rows = self.store.claim_outbox(
owner=self.worker_id,
limit=64,
lease_seconds=self.config.lease_seconds,
)
for row in rows:
try:
outbox_path, queue_path = self.dispatch.dispatch(row)
self.store.mark_outbox(row["work_unit_id"], status="DISPATCHED")
payload = {
"assigned_agent": row["assigned_agent"],
"event_id": row["event_id"],
"dispatch_outbox": str(outbox_path),
"command_queue": str(queue_path),
}
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=self._project_for_event(row["event_id"]),
kind="TASK_DISPATCHED",
work_unit_id=row["work_unit_id"],
payload=payload,
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=record["project_key"],
work_unit_id=row["work_unit_id"],
kind=record["kind"],
payload=record,
)
except Exception:
attempts = int(row["attempts"])
status = "DEAD_LETTER" if attempts >= self.config.max_retries else "RETRY"
self.store.mark_outbox(
row["work_unit_id"],
status=status,
retry_after=self._backoff(attempts),
increment_attempt=True,
)
LOG.exception("dispatch_failed work_unit=%s", row["work_unit_id"])
def synchronize_openclaw(self) -> None:
rows = self.store.claim_lifecycle(
owner=self.worker_id,
limit=64,
lease_seconds=self.config.lease_seconds,
)
for row in rows:
try:
payload = json.loads(row["payload_json"])
self.synchronizer.emit(payload)
self.store.mark_lifecycle(row["sync_id"], status="SENT")
except Exception:
attempts = int(row["attempts"])
status = "DEAD_LETTER" if attempts >= self.config.max_retries else "RETRY"
self.store.mark_lifecycle(
row["sync_id"],
status=status,
retry_after=self._backoff(attempts),
increment_attempt=True,
)
LOG.exception("openclaw_sync_failed sync_id=%s", row["sync_id"])
def enqueue_periodic_summaries(self) -> None:
for state in self.store.all_project_states():
project_key = state["project_key"]
if not self.store.summary_due(project_key, self.config.summary_interval_seconds):
continue
summary = self.store.project_summary(project_key)
if summary is None:
continue
digest = hashlib.sha256(
json.dumps(summary, separators=(",", ":"), sort_keys=True).encode()
).hexdigest()
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=project_key,
kind="PROJECT_SUMMARY",
work_unit_id=None,
payload=summary,
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=project_key,
work_unit_id=None,
kind=record["kind"],
payload=record,
)
self.store.mark_summary(project_key, digest)
def _enqueue_event_lifecycle(self, event: Event) -> None:
if event.event_type == "work_unit_started":
kind = "TASK_STARTED"
elif event.event_type in {"work_unit_completed", "work_unit_failed", "work_unit_blocked"}:
kind = "TASK_ENDED"
else:
kind = "EVENT_RECEIVED"
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=event.project_key,
kind=kind,
work_unit_id=event.work_unit_id,
payload=event.to_dict(),
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=event.project_key,
work_unit_id=event.work_unit_id,
kind=kind,
payload=record,
)
def _enqueue_decision_lifecycle(self, decision: Decision, version: int) -> None:
kind = "PROJECT_COMPLETED" if decision.verdict == "COMPLETE" else "DECISION_APPLIED"
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=decision.project_key,
kind=kind,
work_unit_id=None,
payload={"decision": decision.to_dict(), "state_version": version},
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=decision.project_key,
work_unit_id=None,
kind=kind,
payload=record,
)
summary = self.store.project_summary(decision.project_key)
if summary:
summary_record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=decision.project_key,
kind="PROJECT_SUMMARY",
work_unit_id=None,
payload=summary,
)
self.store.enqueue_lifecycle(
sync_id=summary_record["sync_id"],
project_key=decision.project_key,
work_unit_id=None,
kind=summary_record["kind"],
payload=summary_record,
)
def _project_for_event(self, event_id: str) -> str:
rows = self.store._conn().execute(
"SELECT project_key FROM events WHERE event_id=?",
(event_id,),
).fetchone()
if rows is None:
raise ConflictError("event_not_found")
return str(rows["project_key"])
def _retry_or_dead_letter(self, event: Event, attempts: int, reason: str) -> None:
next_attempt = attempts + 1
if next_attempt > self.config.max_retries:
self.store.update_event_trigger(
event.event_id,
status="DEAD_LETTER",
channel=None,
remote_id=None,
increment_attempt=True,
)
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=event.project_key,
kind="TASK_ENDED",
work_unit_id=event.work_unit_id,
payload={
"status": "FAIL",
"reason": reason,
"event_id": event.event_id,
"attempts": next_attempt,
},
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=event.project_key,
work_unit_id=event.work_unit_id,
kind=record["kind"],
payload=record,
)
return
self.store.update_event_trigger(
event.event_id,
status="TRIGGER_FAILED",
channel=None,
remote_id=None,
retry_after=self._backoff(attempts),
increment_attempt=True,
)
def _backoff(self, attempts: int) -> int:
return min(3600, self.config.retry_base_seconds * (2 ** min(attempts, 10)))
class Handler(BaseHTTPRequestHandler):
runtime: Runtime
def log_message(self, fmt: str, *args: object) -> None:
LOG.info("%s %s", self.client_address[0], fmt % args)
def _reply(self, status: int, payload: dict[str, Any]) -> None:
body = json.dumps(payload, separators=(",", ":"), sort_keys=True).encode()
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.send_header("Cache-Control", "no-store")
self.end_headers()
self.wfile.write(body)
def _body(self) -> 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 or length > 1_048_576:
raise ValidationError("invalid_body_size")
try:
value = json.loads(self.rfile.read(length))
except json.JSONDecodeError as exc:
raise ValidationError("invalid_json") from exc
if not isinstance(value, dict):
raise ValidationError("json_root_not_object")
return value
def _authenticate(self, expected: str) -> None:
header = self.headers.get("Authorization", "")
if not header.startswith("Bearer "):
raise AuthenticationError("missing_bearer")
if not hmac.compare_digest(header[7:], expected):
raise AuthenticationError("invalid_bearer")
def do_GET(self) -> None:
path = urlparse(self.path).path.rstrip("/") or "/"
try:
if path == "/healthz":
self._reply(
200,
{
"service": "aios-orchestrator-gateway",
"status": "active",
"contract_commit": self.runtime.config.contract_commit,
"polling": True,
},
)
return
if path.startswith("/v1/orchestrator/state/"):
self._authenticate(self.runtime.config.inbound_token())
key = path.rsplit("/", 1)[-1]
state = self.runtime.store.project_summary(key)
self._reply(200 if state else 404, state or {"error": "project_not_found"})
return
self._reply(404, {"error": "not_found"})
except AuthenticationError as exc:
self._reply(401, {"error": str(exc)})
except OrchestratorError as exc:
self._reply(400, {"error": str(exc)})
def do_POST(self) -> None:
path = urlparse(self.path).path.rstrip("/")
try:
if path == "/v1/orchestrator/events":
self._authenticate(self.runtime.config.inbound_token())
created, event = self.runtime.submit_event(self._body())
self._reply(202 if created else 200, {"created": created, "event": event})
return
if path == "/v1/orchestrator/decisions":
self._authenticate(self.runtime.config.callback_token())
version = self.runtime.submit_decision(self._body())
self._reply(202, {"accepted": True, "state_version": version})
return
if path == "/v1/orchestrator/poll":
self._authenticate(self.runtime.config.inbound_token())
self.runtime.poll_once()
self._reply(200, {"polled": True})
return
self._reply(404, {"error": "not_found"})
except AuthenticationError as exc:
self._reply(401, {"error": str(exc)})
except ConflictError as exc:
self._reply(409, {"error": str(exc)})
except ValidationError as exc:
self._reply(422, {"error": str(exc)})
except OrchestratorError as exc:
self._reply(400, {"error": str(exc)})
except Exception:
LOG.exception("request_failed path=%s", path)
self._reply(500, {"error": "internal_error"})
def serve(config_path: Path) -> None:
config = Config.from_file(config_path)
runtime = Runtime(config)
Handler.runtime = runtime
server = ThreadingHTTPServer((config.host, config.port), Handler)
runtime.start()
LOG.info(
"gateway_started host=%s port=%s contract=%s polling=%ss",
config.host,
config.port,
config.contract_commit,
config.poll_interval_seconds,
)
try:
server.serve_forever(poll_interval=0.5)
finally:
server.server_close()
runtime.stop()
-826
View File
@@ -1,826 +0,0 @@
from __future__ import annotations
import json
from pathlib import Path
import sqlite3
import threading
import time
from typing import Any
from .errors import ConflictError
from .models import Decision, Event
from .securefs import ensure_secure_directory
class Store:
"""Durable state machine with idempotency, optimistic versioning, and leases."""
def __init__(self, path: Path):
self.path = Path(path)
ensure_secure_directory(self.path.parent)
self._local = threading.local()
self._initialize()
def _connect(self) -> sqlite3.Connection:
conn = sqlite3.connect(self.path, timeout=30, isolation_level=None)
conn.row_factory = sqlite3.Row
conn.execute("PRAGMA journal_mode=WAL")
conn.execute("PRAGMA synchronous=FULL")
conn.execute("PRAGMA foreign_keys=ON")
conn.execute("PRAGMA busy_timeout=30000")
return conn
def _conn(self) -> sqlite3.Connection:
conn = getattr(self._local, "conn", None)
if conn is None:
conn = self._connect()
self._local.conn = conn
return conn
def _initialize(self) -> None:
conn = self._connect()
try:
conn.executescript(
"""
CREATE TABLE IF NOT EXISTS project_state (
project_key TEXT PRIMARY KEY,
contract_commit TEXT NOT NULL,
state_version INTEGER NOT NULL,
state_json TEXT NOT NULL,
hops INTEGER NOT NULL DEFAULT 0,
updated_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS gate_hops (
project_key TEXT NOT NULL,
gate_id TEXT NOT NULL,
hops INTEGER NOT NULL DEFAULT 0,
updated_at INTEGER NOT NULL,
PRIMARY KEY(project_key, gate_id)
);
CREATE TABLE IF NOT EXISTS events (
event_id TEXT PRIMARY KEY,
project_key TEXT NOT NULL,
digest TEXT NOT NULL,
event_json TEXT NOT NULL,
status TEXT NOT NULL,
channel TEXT,
remote_id TEXT,
attempts INTEGER NOT NULL DEFAULT 0,
next_attempt_at INTEGER NOT NULL DEFAULT 0,
lease_owner TEXT,
lease_until INTEGER,
created_at INTEGER NOT NULL,
updated_at INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_events_poll
ON events(status, next_attempt_at, lease_until, created_at);
CREATE TABLE IF NOT EXISTS decisions (
event_id TEXT PRIMARY KEY REFERENCES events(event_id),
project_key TEXT NOT NULL,
decision_json TEXT NOT NULL,
state_version_after INTEGER NOT NULL,
created_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS outbox (
work_unit_id TEXT PRIMARY KEY,
event_id TEXT NOT NULL REFERENCES events(event_id),
assigned_agent TEXT NOT NULL,
payload_json TEXT NOT NULL,
status TEXT NOT NULL,
attempts INTEGER NOT NULL DEFAULT 0,
next_attempt_at INTEGER NOT NULL DEFAULT 0,
lease_owner TEXT,
lease_until INTEGER,
created_at INTEGER NOT NULL,
updated_at INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_outbox_poll
ON outbox(status, next_attempt_at, lease_until, created_at);
CREATE TABLE IF NOT EXISTS lifecycle (
sync_id TEXT PRIMARY KEY,
project_key TEXT NOT NULL,
work_unit_id TEXT,
kind TEXT NOT NULL,
payload_json TEXT NOT NULL,
status TEXT NOT NULL,
attempts INTEGER NOT NULL DEFAULT 0,
next_attempt_at INTEGER NOT NULL DEFAULT 0,
lease_owner TEXT,
lease_until INTEGER,
created_at INTEGER NOT NULL,
updated_at INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_lifecycle_poll
ON lifecycle(status, next_attempt_at, lease_until, created_at);
CREATE TABLE IF NOT EXISTS blocker_history (
project_key TEXT NOT NULL,
gate_id TEXT NOT NULL,
blocker TEXT NOT NULL,
repetitions INTEGER NOT NULL,
updated_at INTEGER NOT NULL,
PRIMARY KEY(project_key, gate_id, blocker)
);
CREATE TABLE IF NOT EXISTS summaries (
project_key TEXT PRIMARY KEY,
last_emitted_at INTEGER NOT NULL DEFAULT 0,
last_digest TEXT
);
CREATE TABLE IF NOT EXISTS observed_refs (
refname TEXT PRIMARY KEY,
object_id TEXT NOT NULL,
observed_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS metadata (
key TEXT PRIMARY KEY,
value TEXT NOT NULL
);
"""
)
finally:
conn.close()
def register_event(self, event: Event) -> tuple[bool, dict[str, Any]]:
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
existing = conn.execute(
"SELECT digest, event_json FROM events WHERE event_id=?",
(event.event_id,),
).fetchone()
if existing:
if existing["digest"] != event.digest():
raise ConflictError("event_id_payload_conflict")
conn.execute("COMMIT")
return False, json.loads(existing["event_json"])
state = conn.execute(
"SELECT contract_commit, state_version FROM project_state WHERE project_key=?",
(event.project_key,),
).fetchone()
if state is None:
conn.execute(
"""
INSERT INTO project_state(
project_key, contract_commit, state_version, state_json,
hops, updated_at
) VALUES (?, ?, ?, '{}', 0, ?)
""",
(event.project_key, event.contract_commit, event.state_version, now),
)
else:
if state["contract_commit"] != event.contract_commit:
raise ConflictError("contract_version_mismatch")
if state["state_version"] != event.state_version:
raise ConflictError("stale_state_version")
conn.execute(
"""
INSERT INTO events(
event_id, project_key, digest, event_json, status,
next_attempt_at, created_at, updated_at
) VALUES (?, ?, ?, ?, 'RECEIVED', ?, ?, ?)
""",
(
event.event_id,
event.project_key,
event.digest(),
event.canonical_json(),
now,
now,
now,
),
)
conn.execute("COMMIT")
return True, event.to_dict()
except Exception:
conn.execute("ROLLBACK")
raise
def claim_events(
self,
*,
owner: str,
statuses: tuple[str, ...],
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
if not statuses:
return []
now = int(time.time())
placeholders = ",".join("?" for _ in statuses)
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
rows = conn.execute(
f"""
SELECT event_id FROM events
WHERE status IN ({placeholders})
AND next_attempt_at <= ?
AND (lease_until IS NULL OR lease_until < ?)
ORDER BY created_at
LIMIT ?
""",
(*statuses, now, now, limit),
).fetchall()
ids = [row["event_id"] for row in rows]
for event_id in ids:
conn.execute(
"""
UPDATE events SET lease_owner=?, lease_until=?, updated_at=?
WHERE event_id=?
""",
(owner, now + lease_seconds, now, event_id),
)
conn.execute("COMMIT")
except Exception:
conn.execute("ROLLBACK")
raise
if not ids:
return []
placeholders = ",".join("?" for _ in ids)
return [
dict(row)
for row in conn.execute(
f"SELECT * FROM events WHERE event_id IN ({placeholders})",
ids,
).fetchall()
]
def update_event_trigger(
self,
event_id: str,
*,
status: str,
channel: str | None,
remote_id: str | None,
retry_after: int = 0,
increment_attempt: bool = False,
) -> None:
now = int(time.time())
self._conn().execute(
"""
UPDATE events
SET status=?, channel=?, remote_id=?,
attempts=attempts + ?,
next_attempt_at=?,
lease_owner=NULL, lease_until=NULL, updated_at=?
WHERE event_id=?
""",
(
status,
channel,
remote_id,
1 if increment_attempt else 0,
now + max(0, retry_after),
now,
event_id,
),
)
def claim_workspace_timeouts(
self,
*,
owner: str,
older_than: int,
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
return self._claim_event_subset(
owner=owner,
where_sql="status='AWAITING_DECISION' AND channel='workspace_agent' AND updated_at <= ?",
where_params=(older_than,),
limit=limit,
lease_seconds=lease_seconds,
)
def claim_response_polls(
self,
*,
owner: str,
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
now = int(time.time())
return self._claim_event_subset(
owner=owner,
where_sql="status='POLLING_RESPONSE' AND next_attempt_at <= ?",
where_params=(now,),
limit=limit,
lease_seconds=lease_seconds,
)
def _claim_event_subset(
self,
*,
owner: str,
where_sql: str,
where_params: tuple[Any, ...],
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
allowed = {
"status='AWAITING_DECISION' AND channel='workspace_agent' AND updated_at <= ?",
"status='POLLING_RESPONSE' AND next_attempt_at <= ?",
}
if where_sql not in allowed:
raise ValueError("invalid_event_claim_query")
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
rows = conn.execute(
f"""
SELECT event_id FROM events
WHERE {where_sql}
AND (lease_until IS NULL OR lease_until < ?)
ORDER BY updated_at
LIMIT ?
""",
(*where_params, now, limit),
).fetchall()
ids = [str(row["event_id"]) for row in rows]
for event_id in ids:
conn.execute(
"""
UPDATE events SET lease_owner=?, lease_until=?
WHERE event_id=?
""",
(owner, now + lease_seconds, event_id),
)
conn.execute("COMMIT")
except Exception:
conn.execute("ROLLBACK")
raise
if not ids:
return []
placeholders = ",".join("?" for _ in ids)
return [
dict(row)
for row in conn.execute(
f"SELECT * FROM events WHERE event_id IN ({placeholders})",
ids,
).fetchall()
]
def apply_decision(
self,
decision: Decision,
*,
max_hops_per_gate: int,
max_same_blocker_retries: int,
) -> int:
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
event = conn.execute(
"SELECT project_key FROM events WHERE event_id=?",
(decision.event_id,),
).fetchone()
if event is None:
raise ConflictError("event_not_found")
if event["project_key"] != decision.project_key:
raise ConflictError("event_project_mismatch")
existing = conn.execute(
"SELECT decision_json, state_version_after FROM decisions WHERE event_id=?",
(decision.event_id,),
).fetchone()
if existing:
if json.loads(existing["decision_json"]) != decision.to_dict():
raise ConflictError("decision_idempotency_conflict")
conn.execute("COMMIT")
return int(existing["state_version_after"])
state = conn.execute(
"SELECT * FROM project_state WHERE project_key=?",
(decision.project_key,),
).fetchone()
if state is None:
raise ConflictError("project_state_not_found")
if state["contract_commit"] != decision.contract_commit:
raise ConflictError("contract_version_mismatch")
if state["state_version"] != decision.expected_state_version:
raise ConflictError("stale_decision_state_version")
state_json = json.loads(state["state_json"])
gate = str(
decision.state_updates.get(
"current_gate", state_json.get("current_gate", "unknown")
)
)
gate_hops = conn.execute(
"SELECT hops FROM gate_hops WHERE project_key=? AND gate_id=?",
(decision.project_key, gate),
).fetchone()
if gate_hops is not None and int(gate_hops["hops"]) >= max_hops_per_gate:
raise ConflictError("max_hops_exceeded")
state_json.update(decision.state_updates)
next_version = int(state["state_version"]) + 1
if decision.stop_reason:
row = conn.execute(
"""
SELECT repetitions FROM blocker_history
WHERE project_key=? AND gate_id=? AND blocker=?
""",
(decision.project_key, gate, decision.stop_reason),
).fetchone()
repetitions = (int(row["repetitions"]) if row else 0) + 1
conn.execute(
"""
INSERT INTO blocker_history(
project_key, gate_id, blocker, repetitions, updated_at
) VALUES (?, ?, ?, ?, ?)
ON CONFLICT(project_key, gate_id, blocker)
DO UPDATE SET repetitions=excluded.repetitions,
updated_at=excluded.updated_at
""",
(decision.project_key, gate, decision.stop_reason, repetitions, now),
)
if repetitions > max_same_blocker_retries:
raise ConflictError("same_blocker_retry_limit_exceeded")
conn.execute(
"""
INSERT INTO gate_hops(project_key, gate_id, hops, updated_at)
VALUES (?, ?, 1, ?)
ON CONFLICT(project_key, gate_id)
DO UPDATE SET hops=gate_hops.hops + 1, updated_at=excluded.updated_at
""",
(decision.project_key, gate, now),
)
conn.execute(
"""
UPDATE project_state
SET state_version=?, state_json=?, hops=hops+1, updated_at=?
WHERE project_key=?
""",
(
next_version,
json.dumps(state_json, separators=(",", ":"), sort_keys=True),
now,
decision.project_key,
),
)
conn.execute(
"""
INSERT INTO decisions(
event_id, project_key, decision_json,
state_version_after, created_at
) VALUES (?, ?, ?, ?, ?)
""",
(
decision.event_id,
decision.project_key,
json.dumps(decision.to_dict(), separators=(",", ":"), sort_keys=True),
next_version,
now,
),
)
for unit in decision.next_work_units:
conn.execute(
"""
INSERT INTO outbox(
work_unit_id, event_id, assigned_agent, payload_json,
status, next_attempt_at, created_at, updated_at
) VALUES (?, ?, ?, ?, 'PENDING', ?, ?, ?)
""",
(
unit.id,
decision.event_id,
unit.primary_agent,
json.dumps(unit.to_dict(), separators=(",", ":"), sort_keys=True),
now,
now,
now,
),
)
conn.execute(
"""
UPDATE events SET status='DECIDED', lease_owner=NULL,
lease_until=NULL, updated_at=?
WHERE event_id=?
""",
(now, decision.event_id),
)
conn.execute("COMMIT")
return next_version
except Exception:
conn.execute("ROLLBACK")
raise
def claim_outbox(self, *, owner: str, limit: int, lease_seconds: int) -> list[dict[str, Any]]:
return self._claim_table(
table="outbox",
key="work_unit_id",
owner=owner,
statuses=("PENDING", "RETRY"),
limit=limit,
lease_seconds=lease_seconds,
)
def mark_outbox(
self,
work_unit_id: str,
*,
status: str,
retry_after: int = 0,
increment_attempt: bool = False,
) -> None:
self._mark_table(
table="outbox",
key="work_unit_id",
value=work_unit_id,
status=status,
retry_after=retry_after,
increment_attempt=increment_attempt,
)
def enqueue_lifecycle(
self,
*,
sync_id: str,
project_key: str,
work_unit_id: str | None,
kind: str,
payload: dict[str, Any],
) -> None:
now = int(time.time())
encoded = json.dumps(payload, separators=(",", ":"), sort_keys=True)
self._conn().execute(
"""
INSERT OR IGNORE INTO lifecycle(
sync_id, project_key, work_unit_id, kind, payload_json,
status, next_attempt_at, created_at, updated_at
) VALUES (?, ?, ?, ?, ?, 'PENDING', ?, ?, ?)
""",
(sync_id, project_key, work_unit_id, kind, encoded, now, now, now),
)
def claim_lifecycle(self, *, owner: str, limit: int, lease_seconds: int) -> list[dict[str, Any]]:
return self._claim_table(
table="lifecycle",
key="sync_id",
owner=owner,
statuses=("PENDING", "RETRY"),
limit=limit,
lease_seconds=lease_seconds,
)
def mark_lifecycle(
self,
sync_id: str,
*,
status: str,
retry_after: int = 0,
increment_attempt: bool = False,
) -> None:
self._mark_table(
table="lifecycle",
key="sync_id",
value=sync_id,
status=status,
retry_after=retry_after,
increment_attempt=increment_attempt,
)
def _claim_table(
self,
*,
table: str,
key: str,
owner: str,
statuses: tuple[str, ...],
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
if table not in {"outbox", "lifecycle"} or key not in {"work_unit_id", "sync_id"}:
raise ValueError("invalid_claim_table")
now = int(time.time())
placeholders = ",".join("?" for _ in statuses)
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
rows = conn.execute(
f"""
SELECT {key} FROM {table}
WHERE status IN ({placeholders})
AND next_attempt_at <= ?
AND (lease_until IS NULL OR lease_until < ?)
ORDER BY created_at
LIMIT ?
""",
(*statuses, now, now, limit),
).fetchall()
values = [row[key] for row in rows]
for item in values:
conn.execute(
f"""
UPDATE {table} SET lease_owner=?, lease_until=?, updated_at=?
WHERE {key}=?
""",
(owner, now + lease_seconds, now, item),
)
conn.execute("COMMIT")
except Exception:
conn.execute("ROLLBACK")
raise
if not values:
return []
placeholders = ",".join("?" for _ in values)
return [
dict(row)
for row in conn.execute(
f"SELECT * FROM {table} WHERE {key} IN ({placeholders})",
values,
).fetchall()
]
def _mark_table(
self,
*,
table: str,
key: str,
value: str,
status: str,
retry_after: int,
increment_attempt: bool,
) -> None:
if table not in {"outbox", "lifecycle"} or key not in {"work_unit_id", "sync_id"}:
raise ValueError("invalid_mark_table")
now = int(time.time())
self._conn().execute(
f"""
UPDATE {table}
SET status=?, attempts=attempts + ?, next_attempt_at=?,
lease_owner=NULL, lease_until=NULL, updated_at=?
WHERE {key}=?
""",
(
status,
1 if increment_attempt else 0,
now + max(0, retry_after),
now,
value,
),
)
def project_state(self, project_key: str) -> dict[str, Any] | None:
row = self._conn().execute(
"SELECT * FROM project_state WHERE project_key=?",
(project_key,),
).fetchone()
if row is None:
return None
result = dict(row)
result["state"] = json.loads(result.pop("state_json"))
return result
def all_project_states(self) -> list[dict[str, Any]]:
result = []
for row in self._conn().execute("SELECT * FROM project_state ORDER BY project_key").fetchall():
item = dict(row)
item["state"] = json.loads(item.pop("state_json"))
result.append(item)
return result
def summary_due(self, project_key: str, interval: int) -> bool:
now = int(time.time())
row = self._conn().execute(
"SELECT last_emitted_at FROM summaries WHERE project_key=?",
(project_key,),
).fetchone()
return row is None or now - int(row["last_emitted_at"]) >= interval
def mark_summary(self, project_key: str, digest: str) -> None:
now = int(time.time())
self._conn().execute(
"""
INSERT INTO summaries(project_key, last_emitted_at, last_digest)
VALUES (?, ?, ?)
ON CONFLICT(project_key)
DO UPDATE SET last_emitted_at=excluded.last_emitted_at,
last_digest=excluded.last_digest
""",
(project_key, now, digest),
)
def project_summary(self, project_key: str) -> dict[str, Any] | None:
state = self.project_state(project_key)
if state is None:
return None
conn = self._conn()
event_counts = {
row["status"]: int(row["count"])
for row in conn.execute(
"""
SELECT status, COUNT(*) AS count FROM events
WHERE project_key=? GROUP BY status
""",
(project_key,),
).fetchall()
}
outbox_counts = {
row["status"]: int(row["count"])
for row in conn.execute(
"""
SELECT o.status, COUNT(*) AS count
FROM outbox o JOIN events e ON e.event_id=o.event_id
WHERE e.project_key=? GROUP BY o.status
""",
(project_key,),
).fetchall()
}
return {
"project_key": project_key,
"contract_commit": state["contract_commit"],
"state_version": state["state_version"],
"state": state["state"],
"event_counts": event_counts,
"work_unit_counts": outbox_counts,
"updated_at": state["updated_at"],
}
def metadata_get(self, key: str) -> str | None:
row = self._conn().execute(
"SELECT value FROM metadata WHERE key=?",
(key,),
).fetchone()
return None if row is None else str(row["value"])
def metadata_set(self, key: str, value: str) -> None:
self._conn().execute(
"""
INSERT INTO metadata(key, value) VALUES (?, ?)
ON CONFLICT(key) DO UPDATE SET value=excluded.value
""",
(key, value),
)
def observe_refs(self, refs: dict[str, str]) -> tuple[bool, list[tuple[str, str | None, str]]]:
"""Persist a Git snapshot and return changes after the initial baseline."""
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
initialized = conn.execute(
"SELECT value FROM metadata WHERE key='git_poll_initialized'"
).fetchone()
previous = {
row["refname"]: row["object_id"]
for row in conn.execute("SELECT refname, object_id FROM observed_refs").fetchall()
}
changes: list[tuple[str, str | None, str]] = []
if initialized is not None:
for refname, oid in refs.items():
old = previous.get(refname)
if old != oid:
changes.append((refname, old, oid))
for refname, old in previous.items():
if refname not in refs:
changes.append((refname, old, "0" * 40))
conn.execute("DELETE FROM observed_refs")
for refname, oid in refs.items():
conn.execute(
"""
INSERT INTO observed_refs(refname, object_id, observed_at)
VALUES (?, ?, ?)
""",
(refname, oid, now),
)
conn.execute(
"""
INSERT INTO metadata(key, value)
VALUES ('git_poll_initialized', '1')
ON CONFLICT(key) DO UPDATE SET value='1'
"""
)
conn.execute("COMMIT")
return initialized is not None, changes
except Exception:
conn.execute("ROLLBACK")
raise
def close(self) -> None:
conn = getattr(self._local, "conn", None)
if conn is not None:
conn.close()
self._local.conn = None
-108
View File
@@ -1,108 +0,0 @@
from __future__ import annotations
import hashlib
import json
import os
import stat
from pathlib import Path
import urllib.error
import urllib.request
from typing import Any
from .errors import DispatchError
from .securefs import atomic_write_bytes_shared, ensure_shared_directory, read_secure_bytes
class OpenClawSynchronizer:
"""Synchronize task starts, ends, dispatches, and project summaries.
A durable file is always emitted. An optional HTTP endpoint is best-effort;
failure leaves the lifecycle record pending for retry.
"""
def __init__(
self,
queue_dir: Path,
*,
endpoint: str | None = None,
bearer_token: str | None = None,
timeout_seconds: int = 10,
):
self.queue_dir = Path(queue_dir)
self.endpoint = endpoint
self.bearer_token = bearer_token
self.timeout_seconds = timeout_seconds
ensure_shared_directory(self.queue_dir)
def emit(self, record: dict[str, Any]) -> Path:
sync_id = record.get("sync_id")
if not isinstance(sync_id, str) or not sync_id:
raise DispatchError("invalid_sync_id")
payload = (json.dumps(record, indent=2, sort_keys=True) + "\n").encode()
path = self.queue_dir / "pending" / f"{sync_id}.json"
ensure_shared_directory(path.parent)
try:
st = os.lstat(path)
except FileNotFoundError:
atomic_write_bytes_shared(path, payload, mode=0o640)
else:
if not stat.S_ISREG(st.st_mode):
raise DispatchError("sync_target_not_regular")
if read_secure_bytes(path, expected_uid=None, max_bytes=1_048_576) != payload:
raise DispatchError("sync_idempotency_conflict")
if self.endpoint:
headers = {
"Content-Type": "application/json",
"Idempotency-Key": sync_id,
"User-Agent": "aios-orchestrator-gateway/0.2",
}
if self.bearer_token:
headers["Authorization"] = f"Bearer {self.bearer_token}"
request = urllib.request.Request(
self.endpoint,
data=payload,
method="POST",
headers=headers,
)
try:
with urllib.request.urlopen(request, timeout=self.timeout_seconds) as response:
response.read(65_536)
if response.status not in {200, 201, 202, 204}:
raise DispatchError(f"openclaw_sync_http_{response.status}")
except urllib.error.HTTPError as exc:
raise DispatchError(f"openclaw_sync_http_{exc.code}") from exc
except (urllib.error.URLError, TimeoutError, OSError) as exc:
raise DispatchError("openclaw_sync_failed") from exc
return path
def lifecycle_record(
*,
contract_commit: str,
project_key: str,
kind: str,
work_unit_id: str | None,
payload: dict[str, Any],
) -> dict[str, Any]:
canonical = json.dumps(
{
"contract_commit": contract_commit,
"project_key": project_key,
"kind": kind,
"work_unit_id": work_unit_id,
"payload": payload,
},
separators=(",", ":"),
sort_keys=True,
)
sync_id = hashlib.sha256(canonical.encode()).hexdigest()
return {
"schema_version": 1,
"sync_id": sync_id,
"contract_commit": contract_commit,
"project_key": project_key,
"kind": kind,
"work_unit_id": work_unit_id,
"payload": payload,
}
-35
View File
@@ -1,35 +0,0 @@
[Unit]
Description=AIOS Codex automatic command watcher
After=network-online.target aios-orchestrator-gateway.service
Wants=network-online.target
[Service]
Type=oneshot
User=aios-orchestrator
Group=aios-orchestrator
UMask=0077
Environment=PYTHONPATH=/opt/aios-codex-watcher/current
ExecStart=/usr/bin/python3 -m services.aios_codex_watcher --config /etc/aios-codex-watcher/config.json --once
NoNewPrivileges=yes
PrivateDevices=yes
PrivateTmp=yes
ProtectClock=yes
ProtectControlGroups=yes
ProtectHome=yes
ProtectHostname=yes
ProtectKernelLogs=yes
ProtectKernelModules=yes
ProtectKernelTunables=yes
ProtectSystem=strict
ReadOnlyPaths=/etc/aios-orchestrator-gateway/inbound.token
ReadWritePaths=/data/aios-gitops/workspace/agents/commands /var/lib/aios-codex-watcher /var/log/aios-codex-watcher
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
RestrictNamespaces=yes
RestrictRealtime=yes
RestrictSUIDSGID=yes
SystemCallArchitectures=native
LockPersonality=yes
MemoryDenyWriteExecute=yes
[Install]
WantedBy=multi-user.target
-1
View File
@@ -1 +0,0 @@
u aios-orchestrator - "AIOS Orchestrator" /var/lib/aios-orchestrator-gateway

Some files were not shown because too many files have changed in this diff Show More