The AI workforce engine's driver. One tick moves every ready task one step:
a turn, a gate, or a platform merge. The AI never runs git.
- scheduler.py: tick() over TURN_STAGES/MERGE_STAGES; selection caps
(per-org 3, global 8); optimistic advance so two workers cannot both win;
worktree created for code pipelines, released on completion/cancel/failure
(kept during error_review); budget pause before any turn is spent; merge
conflict back-off; transient-failure retries then the manager's error turn.
- gates.py: diff guard (empty/.git/CI/symlink/oversize), no-progress hash,
tests in the sandbox, green gate that only trusts a green tests row or an
explicit waiver. Every verdict is a gate_results row + a task.gate event.
Fixed forbidden_paths: lstrip("./") stripped all leading dots, hiding
.git and .github from the guard.
- container_engine.build_scheduler + worker drives the engine tick.
- ManagerOutcome.error_kind; TaskSpendRepository.spend_for_task.
- New settings engine_max_concurrent_turns, engine_max_turns_per_org,
engine_tests_timeout_seconds, engine_max_merge_conflicts,
engine_max_task_credits (+ .env.example).
- tests: test_engine_gates.py (13), test_engine_flow.py (11).
Checks: pytest 746 passed/1 skipped, ruff clean, mypy clean (160 files).
A push to `dev` now becomes a live demo, and a failed build never takes the
demo down.
- Four tables (pipeline_runs, pipeline_steps, releases, app_runtimes) and their
migration; alembic upgrade/downgrade/check all clean.
- DeliveryService implements DeliveryHooks: on_app_created provisions the demo
port + host + first build (idempotently); on_branch_pushed queues a run for
`dev` and supersedes older *queued* runs, leaving a running one alone.
- The 8-step pipeline. Blue/green is real: the replacement starts on a staging
port, is healthchecked, and only then does the route move — then the previous
container is stopped. A failure removes the replacement, releases its port and
leaves the old container serving.
- The demo port ledger is the DATABASE, not the router adapters' in-memory maps:
the API and the delivery worker are separate processes.
- Runs are claimed with a conditional UPDATE, so two workers never build the
same run.
- Live logs are batched (1 event / 500 ms, 200 lines) and redacted as a whole
tail — per-chunk redaction misses a secret split across pipe reads, and the
*stored* tail leaked until this was fixed.
- delivery worker: drain the queue, then poll remotes for pushes made outside
the engine.
- 7 routes; reads need membership, actions need projects.manage and are audited.
Tests: 415 API (+21, 1 docker-marked skipped); ruff, mypy, alembic check clean.
Report: docs/plan/reports/agent-3-phase-3.md
The execution boundary for v2. Adds the local docker/podman sandbox adapter
and the hardened host subprocess runner every other delivery adapter will use.
- adapters/process.py: the one place the platform shells out. argv-only (no
shell), start_new_session + killpg on timeout, concurrent stdout/stderr
drains with a byte cap, explicit minimal env (never os.environ), and a
missing binary reported as spawn_failed rather than an exception.
- adapters/docker_sandbox.py: DockerSandboxAdapter over SandboxProviderPort.
--user 1000:1000, --cap-drop ALL, no-new-privileges, pids/cpu/memory limits,
--read-only with tmpfs scratch, one bind mount (the work tree, never the git
dir), labels, no published ports. Path-safe file access; secrets refused in
`docker exec -e`. Extras for later phases: start_demo_container (loopback
publish only), list_managed_containers, remove_container.
- registry: SANDBOX_PROVIDER=docker, cached singleton so the workspace registry
survives create_workspace -> start_session.
- sandbox_gateway worker: reap_orphans() removes labelled containers no live
session points at, audited as sandbox.reap; run_pass() does both passes.
- sandbox router: every mutating route now requires the platform owner
(PLAN-v2 §7.7); read-only status routes stay open to org members.
- sandbox-panel: canManageInfra prop (fails closed) hides the create form,
the session panel and the action buttons from non-owners.
Tests: 346 API (+37), 67 web (+3); ruff, mypy, tsc and lint clean.
Three existing tests now drive the sandbox as the platform owner, since that
is who may touch it.
Report: docs/plan/reports/agent-3-phase-1.md
مخزن اختصاصی برنامهٔ وب؛ محتوای پوشهٔ web در ریشهٔ مخزن قرار گرفت.
تاریخچهٔ پروژهٔ ربات (agy-bot) در این مخزن وجود ندارد و هیچ وابستگی runtime به آن نیست.
