Commit graph

6 commits

Author SHA1 Message Date
Claude
72076b7874
feat(ws3): add dispatch node + remove agent-apply env gate
- Add agent_team/nodes/dispatch_invoker.py: make_dispatch_node() wraps
  dispatcher.dispatch_apply_verify() as a LangGraph node; fail-safe
  (parks task on any error); INERT unless wired by coordinator.
- graph.py: add DISPATCH_NODE constant; add dispatch_node param to
  build_graph; when provided, repoint APPROVED_ROUTE → DISPATCH_NODE →
  END (P3+). Validates dispatch_node requires build_verify.
- coordinator.py: add DispatchNodeFactory type; thread dispatch_node_wiring
  through __init__ and setup(); default None = inert (no auto-dispatch).
- agent-team-apply-verify.yml: remove agent-apply environment gate from
  gate-and-pr; add Slack-notify + audit-log compensating control steps.
- test_apply_verify_workflow_hardening.py: flip env assertion → assert env
  REMOVED and compensating steps present.

All 1044 tests passing. ruff clean.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QYp761G9HojkmLqLZrASVi
2026-06-23 01:31:29 +00:00
Adam Moussa
c671e6bdbb
fix(agent-team): register QuestionSet with the langgraph checkpoint serializer (silence/avoid msgpack block) (#30) 2026-06-22 16:14:27 -04:00
e1208ee563 feat(agent-team): P3-inert build/verify subgraph topology (opt-in, no live CI)
build_verify_subgraph: BUILD->VERIFY nodes + route_after_verify. build_graph gains an opt-in build_verify param that repoints the review 'build' route at the subgraph (BUILD->VERIFY->{approved->END | loop->PLAN | parked->END}); default unchanged (P2). Coordinator build_verify_wiring composes it INERT (no ci_result -> ci_gate BLOCK -> PARKED; LLM is fix-proposer only, never declares green). NOT enabled in production: the live CI apply/verify + OIDC stays held for its /sh-security-review + GPT-4.1 cross-review gate. Also escapes untrusted intake text in logs (log-injection hygiene).
2026-06-18 13:23:03 -04:00
22edd4143a feat(agent-team): P1/P2 graph wiring + coordinator daemon + run-team start/serve
build_graph gains injected live_plan_node/review_node/route_review: P1 = plan->END, P2 = clarify->plan->review->{build|loop-back|parked}. Coordinator composes clarifier->graph->ResumeWorker, wraps planner fail-safe, binds the GPT-4.1 review loop; run-team start/serve opt production into P2. Re-delivery uses a guarded CAS so a concurrently-answered row is never clobbered (closes RACE-REDELIVER).
2026-06-18 12:56:42 -04:00
0eae5dbfc3 Prove P1 exit criteria against the real LangGraph graph; fix question_id stability
Reworks the P1 sim so the four §7.1 exit criteria are demonstrated against the
ACTUAL mechanic, not a model (resolves the verifier's "sim models the ledger,
not the LangGraph integration" finding).

- New tests/sim/test_p1_graph_integration.py drives the real agent_team.graph
  StateGraph (interrupt/Command(resume)) + the real langgraph SqliteSaver
  checkpointer + the committed pending_questions compare-and-set, proving:
  (a) suspend survives a simulated restart (drop saver/conn, rebuild over the
  same checkpoint DB) and resumes; (b) duplicate answer loses the CAS and the
  graph never double-advances; (c) a post-deadline answer loses to expire and
  the task is not resumed; (d) two concurrent tasks resume to the correct
  thread, with a turn-guarded no-double-apply check.
- graph.py: derive a STABLE question_id from uuid5(thread_id, turn). The
  clarifier node replays on resume, so the prior fresh-uuid id changed between
  the delivered/ledgered question and the qa_history entry — breaking the
  §3.3.1 identity contract. Now the delivered id == ledger key == history entry
  (unit-tested in test_graph.py).
- harness._connect() now uses the committed schema.connect() (WAL + busy_timeout)
  instead of a raw sqlite3.connect, so concurrent responders genuinely serialize;
  the criterion-(d) concurrency test no longer swallows OperationalError (it
  asserts zero errors + exactly one CAS winner).
- requirements.txt: pin langgraph-checkpoint-sqlite==3.1.0 (design D9 durable
  checkpointer), now exercised by the integration test.

Full suite: 564 passed; ruff + format clean.
2026-06-17 15:16:12 -04:00
15a416d31a Add Plane-2 leaf scaffold (pipeline graph, nodes, HITL, transports, CI)
Consolidates the 18 leaf modules from the r720-plane2-scaffold workflow onto
the foundation commit. Full suite: 535 passed, 1 skipped; ruff + format clean.

Built (pre-deployment scaffold only — nothing provisioned/enabled):
- LangGraph pipeline graph.py (INTAKE->CLARIFY->PLAN, interrupt()/resume, checkpointer-injectable)
- nodes: clarifier (98% gate), planner, review_loop (GPT-4.1), builders->candidate diff, verifier
- §3.3.1 HITL: ledger ops, resume_worker, deadline_timer, recovery sweep, responder
- transports: slack / github / claude_code adapters
- ci_gate (pure-code pass/fail), operator_cli, run-team.py entry, P1 sim harness
- ci/agent-team-apply-verify.yml (split untrusted/privileged jobs) — authored, disabled

KNOWN OPEN FINDINGS (verifier/cross-review, not yet fixed — see follow-up):
- builders denylist: 4 execution-proven bypasses (delete, mode-change, copy-to, out-of-scope delete)
- §3.3.1 CAS: BEGIN IMMEDIATE outside try/except; shared-connection txn nesting unsafe under concurrency
- operator_cli: missing re-deliver/force-resume; audit-after-mutate ordering gap
- ci yaml: GPT-4.1 cross-review PASS w/ 4 FIX items (symlink path escape, etc.)
- P1 sim harness models the ledger layer, not real LangGraph interrupt/resume; P1 exit criteria not yet truly proven

Deploy-gated (NOT done): IAM/step-ca/Roles Anywhere/confluence-bot provisioning,
/sh-security-review sign-off, live Slack/CI, rsync, live dry-runs, Adam approval.
2026-06-17 15:16:12 -04:00