- run-team.py: add the 'dispatch <thread_id>' operator command (P3 option-b).
The read-only box parks at DISPATCH; this completes it with a just-in-time
WRITE token: reads candidate_diff + scope from the checkpoint (or --diff/--scope
files), pushes the head branch + fires workflow_dispatch via dispatch_apply_verify,
prints the located run_id, and (--write-back) writes it into the task checkpoint
so VERIFY binds. +2 tests.
- OPERATOR-RUNBOOK: fix the misleading 'systemctl show -p Environment' check (it
does NOT show EnvironmentFile= vars) -> use /proc/<MainPID>/environ +
_p3_env_is_configured(); document the operator-initiated dispatch flow + the
fine-grained-token write-probe caveat.
Suite green, ruff clean. Branch only; not merged.
Two gaps surfaced by a live /new-task (task 9bce78ad): the plan was produced
and approved, but the "plan ready" notice posted top-level (not in the task
thread) and contained no plan to review.
1. THREADING — `run-team.py` `_build_notifiers` exposed `notify(message)` with
no `thread_ts`. The coordinator's `_emit` calls `notify(message,
thread_ts=root)`; that raised TypeError, and `_emit`'s fallback re-posted
TOP-LEVEL. So every lifecycle milestone (plan-ready / parked / failed) landed
unthreaded, despite the coordinator computing the root ts. (The clarifier
QUESTION threaded fine — different path.) Fix: the sink now accepts and
forwards `thread_ts` into the chat.postMessage payload (build_slack_poster
already forwards the key).
2. PRESENTATION — the plan-ready milestone was a bare one-liner. It now posts a
CONDENSED plan (summary + numbered phase names; step detail stays on the
status dashboard) via new `Coordinator._summarize_plan`, so the plan is
actually reviewable in-thread.
Tests: notify sink forwards thread_ts (and omits it for top-level); condensed
plan renders summary + phase names (not steps); malformed plan falls back;
plan-ready milestone threads under the task root AND carries the plan. 1193 pass.
WS Slack-UX Feature 1. A /new-task task now maps to ONE Slack thread instead of
several top-level messages.
- /new-task posts an immediate root "📥 Task received: …" ack and captures its
ts (root_ts); this is the instant acknowledgement.
- root_ts is plumbed into start: new PipelineState/TaskRecord channel
slack_thread_ts, seeded by graph.start_task and threaded through
Coordinator.start_task. The NewTaskCallback is now (task_text, via, root_ts).
- All clarifier questions for the task post as THREADED REPLIES under root_ts
(chat.postMessage thread_ts=root_ts), and each question's ledger channel_ref
is set to root_ts (NOT the reply's own ts). Because answer-mapping resolves a
reply via find_open_question_by_channel_ref(thread_ts), a reply in the root
thread (thread_ts==root_ts) maps to the task's currently-open question with NO
change to the mapping logic or the first-answer-wins CAS. The open-only
partial-unique index still holds (one open question per task at a time).
- Lifecycle milestones (parked / plan-ready / needs-input) and follow-up
questions thread under root_ts too; the notify sink gained an optional
thread_ts kwarg (degrades to top-level on a sink that doesn't accept it).
notify failures still never break tick.
- SlackTransport.post_question + the live poster accept/forward thread_ts.
- No root_ts (non-/new-task origin) ⇒ top-level posts exactly as before.
AUTHZ-01 (owner-allowlist-first, fail-closed) and the atomic open→answered
compare-and-set are unchanged.
Adds plumbing for the inbound-ack reactor seam used by Feature 2 (dormant until
a reactor is injected). Tests cover thread_ts forwarding, channel_ref=root_ts,
graph seeding, and coordinator threading.
The bot only ever posted clarifier questions; parks/completions were silent and
multi-turn follow-up questions were never posted during normal operation (only
the startup recover sweep posted them). So an answered task was a black box.
- Coordinator gains a 'notify' sink + _emit() (guarded, never breaks the loop).
- tick() now runs _post_resume_followups(results) after the drain: for each
resumed thread it (a) POSTS a newly-pending clarifier question (fixes silent
multi-turn — the drain path left it unposted) and emits 'needs more input';
else emits 'parked — needs attention' or 'plan ready for review' from the
settled state.
- run-team serve wires notify -> Slack channel (build_slack_poster) and an
alarm_hook that logs the deadline-park WARNING AND posts a parked notice.
Live-Slack only; dry-run/non-Slack/no-channel = silent (None), no token needed.
Tests: +4 (needs-input/parked/plan-ready emits + notify-failure swallow);
_FakeCoordinator gains notify/alarm_hook. 1147 passed, ruff clean.
Gap-audit findings:
- G1 (blocks-feature): make_cross_reviewer_invoker / make_fast_coder_invoker did
'from models import' without putting the orchestrator root on sys.path. The
run-team serve daemon only bootstraps agent-team/, so on the live box every
GPT-4.1 plan review hit ModuleNotFoundError -> review_plan's blanket except
silently fail-closed to REQUEST_CHANGES (GPT-4.1 never actually ran). Both
in-process invokers now call invoker_multi._ensure_orchestrator_on_path()
before the deferred import. WS1 introduced this when it swapped the review
default from the subprocess invoker to in-process.
- G4 (degrades): the handbook context_provider was wired into the planner only;
default_clarify_node_factory now accepts + forwards it, and run-team wires it
into build_clarify_node too, so clarifying questions are handbook-aware.
Tests: +2 regression tests (path-bootstrap, clarifier threading); _FakeCoordinator
gains build_clarify_node. 1142 passed, ruff clean.
Integration branch combining WS0-WS5 (PRs #43-#46) + the activation wiring that
flips the safe seams ON in the run-team serve path:
- WS5 (D10): inject the Sea Haven handbook conventions into the planner prompt
via context_provider (zero-arg handbook loader; fail-safe to '' when absent).
- WS2: an allowlisted Slack /new-task starts a task on this coordinator
(set_new_task_callback adapter -> start_task; AUTHZ-01 gates it upstream).
- WS1 bind_multi_invoker() is already wired in _cmd_serve.
Coordinator gains a new_task_callback param + set_new_task_callback() (resolves
the constructor chicken-and-egg of referencing the coordinator's own start_task);
default_slack_listener_factory forwards it to the SlackListener.
NOT wired (deliberately): the P3 dispatch_node / build_verify path. Activating
it correctly needs a per-task expected_run_id bound into gated_build_verify_wiring
(plumbing that does not exist yet) AND the CI trust-boundary security re-review.
It stays inert pending that work.
Tests: +5 activation-wiring tests; _FakeCoordinator stub gains
set_new_task_callback. Full agent-team suite: 1140 passed, ruff clean.
- invoker_multi.py: multi_invoke(prompt, *, model) dispatches to GPT-4.1
(cross_reviewer), DeepSeek (fast_coder), or Gemini (scanner) in-process;
bind_multi_invoker() wires the review seam; lazy models import
- review_loop_llm: swap default_plan_reviewer from make_run_py_invoker()
to make_cross_reviewer_invoker() (in-process GPT-4.1); subprocess path
retained as make_run_py_invoker() for opt-in use
- builders_llm: add make_fast_coder_invoker() in-process DeepSeek path;
rename subprocess path to subprocess_build (opt-in fallback); default_build
now delegates to make_fast_coder_invoker()
- api.py: FastAPI app with bearer-token auth (AGENT_TEAM_API_TOKEN env),
POST /tasks, GET /tasks/{id}, POST /orchestrator/invoke; binds 127.0.0.1;
code only — not started here
- run-team.py: bind_multi_invoker() called in serve() alongside
bind_subscription_invoker()
- tests: 21 new WS1 tests + updated builders_llm tests (1065 total, all passing)
* feat(agent-team): durable GitHub-issue intake de-dup (schema v2)
The intake poller de-duped ingested issues in an in-memory set that does
not survive a process restart. A scheduled/cron intake (each run a fresh
process) would therefore re-ingest every still-open labeled issue on every
run and spawn duplicate pipeline tasks. Since the box is read-only (no write
token to remove the intake label), durable de-dup is the only correct guard.
- schema v2: new ingested_issues(source, issue_id, ingested_at) table +
issue_already_ingested / record_issue_ingested helpers; migrate() adds the
table to a legacy v1 DB and restamps; init_db creates it.
- github_intake: pluggable IngestStore seam (in-memory default preserved for
tests/one-off; durable build_ledger_ingest_store for production). Record is
after start_task succeeds, so a failed intake stays retryable.
- run-team.py intake-github wires the ledger store keyed by github:owner/repo,
making a scheduled timer idempotent across runs.
978 tests pass (ruff clean).
* fix(agent-team): harden github intake per /sh-security-review (CWE-918, idempotency)
Fixes from the high-recall detector fan-out on the durable-dedup change:
- INTAKE-LOGIC-01 (idempotency): switch the IngestStore seam from
check-then-record (seen/mark) to claim-then-do (claim/release). The id is
now reserved BEFORE the non-idempotent start_task side effect, so a crash in
that window cannot re-spawn a duplicate task on the next run; a raising
start_task releases the claim so transient failures stay retryable. Adds
delete_issue_ingested to the schema layer for the release path.
- INTAKE-SSRF-001 / INTAKE-PATHSPLICE-002 (CWE-918) in build_default_issue_client:
drop the caller-overridable api_root (hardcode GITHUB_API_ROOT) and validate
owner/repo against an anchored charset before splicing them into the
token-bearing API URL — mirrors the sibling ci_fetcher BLOCK-3/FIX-3 fixes.
Tests cover cross-process duplicate prevention, release-on-failure retry, and
the owner/repo + api_root rejection. 982 tests pass, ruff clean.
Follow-up (pre-existing, not introduced here): the label-only intake has no
author allowlist (cf. AGENT_TEAM_SLACK_OWNER_IDS on the Slack listener); the
Slack answer gate bounds the blast radius. Track as separate hardening.
* fix(agent-team): handle real slack_bolt event envelope + map thread replies to open questions
The Socket Mode inbound listener was unit-tested against a SYNTHETIC payload
shape that does not match what slack_bolt actually delivers, so the suite was
green while a real Slack thread reply was silently dropped (the clarifier
question stayed `open`). Real slack_bolt delivers an Events API message /
app_mention as `{"type":"event_callback","event":{"type":"message",...}}` and
a free-text thread reply carries NO callback_id/question_id/metadata.
Three breaks fixed (all on the free-text reply path):
1. Type gate — handle_event gated on the OUTER `type`, which is
"event_callback" for a real message/app_mention, so the event fell outside
_ANSWER_BEARING_TYPES and was dropped. Now collapsed to the discriminating
INNER `event.type` via _discriminating_type / _inner_event.
2. question_id recovery — a real reply has no callback_id/question_id/metadata
(the bot's metadata is on the QUESTION message, not the reply). When explicit
id recovery fails, the listener now resolves the question by the inner
event's `thread_ts` against the OPEN ledger row whose `channel_ref` equals it
(new schema helper find_open_question_by_channel_ref, constrained to
status='open' as anti-replay). Explicit id recovery still takes precedence.
3. answer extraction — a real message event carries its text at `event.text`,
not a top-level `answer`/`text`. The thread-reply path now takes the inner
`event.text` (stripped) as the answer value.
AUTHZ-01 is unchanged and still runs FIRST: authorization gates on the sender's
Slack user id (`event.user` for the Events API shape) and fails closed on an
empty/unknown allowlist or unrecoverable sender. The new mapping only resolves
WHICH question is answered, never WHO may answer. Answers stay opaque DATA
(parameterized SQL + json.dumps; never eval/exec/interpolate).
Tests: replaced the synthetic events-API fixtures with REAL Bolt envelopes and
added regression coverage — real thread reply maps via channel_ref and is
accepted, text is stripped, non-owner reply rejected (row stays open), thread_ts
matching no open row is a no-op, reply to an already-answered row is a no-op
(anti-replay), and app_mention is normalized identically. block_actions /
slash_command paths retained.
* fix(agent-team): bind subscription invoker in the start CLI
`run-team.py start` runs the clarifier graph to the first human gate IN the CLI
process, and the clarifier calls Claude (assess_confidence). The invoker is a
process-local binding that only `serve` set, so `start` failed with
"claude_invoke has no invoker bound". Bind the real subscription invoker here,
mirroring Coordinator.serve(). Found during the live R720 P1 bring-up.
* feat(agent-team): Plane-1 Tier-3 fixer — dependency-cve finding -> patch + CI dispatch (opt-in/inert)
The fixer (design §4 fixer row, §7 Phase 5, §3.3.2) takes a CONFIRMED,
low-risk dependency-cve finding (the narrowest fix class) and produces:
* a fix SPEC (Claude, via the §3.1 billing seam), and
* a minimal bump PATCH (DeepSeek fast_coder, via the orchestrator run.py
path that builders_llm uses),
records the candidate diff + its content-hash, and emits the org-CI
workflow_dispatch inputs (task_id / diff_artifact_name / expected_diff_hash /
declared_scope) for the gate-passed P3-live apply/verify surface.
INERT / opt-in / fail-safe, mirroring build_verify_wiring:
* plan_fix dispatches NOTHING; dispatch_fix has NO default dispatcher
(the box holds no write token, D2) so an un-wired call can never fire a
workflow.
* no git/patch/subprocess/fs-write in executable code — the patch is emitted
as diff TEXT only; CI applies it and opens a DRAFT PR, the box never
applies/pushes/merges.
* untrusted-patch hygiene: the generated diff is confined box-side to the
single dependency manifest (declared_scope) and rejected via
ci_gate.denylist_violations if it escapes scope or touches the
trust-control surface — defense-in-depth with the CI guard.
* bad/ambiguous findings (wrong check/status/category, missing
package/fixed_version, ambiguous fixed_version, unparseable/empty diff)
yield a FAILED no-op plan, never a fabricated fix.
29 new pytest tests under agent-team/tests/test_fixer.py.
* feat(agent-team): run-team.py 'fix --dry-run' subcommand for the Plane-1 fixer
Adds the fixer front door to the operator CLI: load one confirmed
dependency-cve finding from a dependency-cve.json report (--report
--finding-id), plan the fix, and in --dry-run print the spec + patch + the
org-CI workflow_dispatch inputs WITHOUT dispatching anything.
Opt-in/inert: the command binds NO workflow dispatcher and holds no write
token, so even an ok plan only prints; live dispatch is provisioning-gated
(refuses to run without --dry-run). A non-fixable finding prints the
fail-safe reason and exits 1.
4 new pytest tests under agent-team/tests/test_run_team.py.
* feat(agent-team): P5 checker-finding intake module + tests
Add agent_team.transport.checker_intake: turn a confirmed, at/above-threshold
Plane-1 checker FINDING into one Plane-2 pipeline remediation task via the
committed coordinator intake entry (start_task), mirroring github_intake.
- select_findings: status==confirmed AND severity>=threshold (default high);
unverified/suppressed/below-threshold dropped; unknown threshold rejected.
- finding_identity: stable de-dup key (finding id, else content-hash). In-memory
set, best-effort, NOT durable across restart (ledger table is the follow-up).
- finding_task_text/_sanitize: every repo-controlled field (title, proof, repo)
is newline/control-char neutralised and length-bounded before it reaches the
task text or operator log (log-injection hygiene).
- load_report_findings/ingest_reports: read the exact checker report JSON shape
(top-level object with findings[]; bare array and dir-of-*.json also accepted).
28 hermetic unit tests (stub coordinator, in-memory findings / temp reports).
* feat(agent-team): wire opt-in intake-checker run-team subcommand
Expose the P5 cross-plane loop only as a manual run-team subcommand
(intake-checker --report PATH [--threshold] [--transport] [--dry-run]),
mirroring how intake-github is exposed. NOT wired into the always-on serve
path: the loop stays opt-in/inert by default.
* fix(agent-team): read SLACK_CHANNEL_ID, aligning code with deploy doc + systemd
run-team.py read os.environ['SLACK_CHANNEL'] while DEPLOY-R720.md and the
coordinator systemd unit both document SLACK_CHANNEL_ID; the mismatch would
silently default the live Slack transport channel to empty. Standardize on
SLACK_CHANNEL_ID (decision locked 2026-06-18).
* feat(secrev): dependency-cve Plane-1 Tier-1 checker (OSV, ALARM-only)
Read-only checker on the Phase-0 substrate: scans $MIRROR_DIR mirrors for
pinned deps (requirements/poetry/Pipfile/package-lock/yarn/csproj across
PyPI/npm/NuGet), cross-refs OSV querybatch (live) or an offline advisory
fixture (canary). Mode-600 reports, ALARM-only, --canary asserts 2 planted
vulns (jinja2 2.11.2, lodash 4.17.15). Complements Dependabot. Not provisioned.
* feat(secrev): Plane-1 checker coordinator (shared budget, rotation, dedup)
Coordinator (design §5/§6.7) orchestrating Tier-1 checkers under one shared
budget ledger + versioned rotation/coverage state (atomic write + schema/hash/
logical-consistency integrity, park-on-corrupt). Canary-suite-first
(COMPLACENCY skip), fan-out under the shared cap with defer-not-drop, COVERAGE
alarm past MAX_CYCLE_NIGHTS, cross-checker dedup/prioritize, ALARM-only routing.
--squeeze-dry-run proves deferral-not-drop + COVERAGE alarm. Not provisioned.
* fix(secrev): hide dependency-cve canary manifests from dependency-review
The canary fixtures intentionally pin known-vulnerable deps (jinja2 2.11.2,
lodash 4.17.15) so the checker has something to detect. GitHub's dependency
graph parsed those fixture manifests as real project deps, failing the
dependency-review PR gate (fail-on-severity: high). Store the manifests with a
.fixture suffix so the dependency graph ignores them; the --canary materializer
strips the suffix in its temp work area before scanning, so detection is
unchanged (still 2/2). No advisory allowlist, no change to the shared org
reusable workflow — the real gate stays strict for actual deps.
Live github (issue-comment poster) and claude_code (file-drop) transports, plus GithubIntake (labeled issue -> coordinator.start_task, de-duped). run-team _build_transport now wires github/claude_code live (was SystemExit) + adds the intake-github subcommand. claude_code drop-path also neutralizes backslash (defense-in-depth).
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).
Addresses the confirmed findings from /sh-security-review + the GPT-4.1
cross-review of the Plane-2 scaffold. Full suite: 589 passed; ruff clean.
FIXED (proven-exploitable):
- CI-guard denylist bypass (HIGH): Python fnmatch '**/' is non-recursive, so
root-level template.yaml/*.tf/cdk.json/*.pem/*.key/*-stack.* evaded the
trust-control surface. Replaced fnmatch with a recursive, case-insensitive
glob->regex matcher. (verified: fnmatch('template.yaml','**/template.yaml')==False)
- CI-guard scope bypass (HIGH): a '**' declared_scope made every path in-scope.
Scope is now concrete-prefix confinement (reduces a glob to its leading
metacharacter-free segments; '**' -> empty -> dropped -> unscoped reject).
- Box-side vs CI denylist divergence (MED): builders.py _DENY_PATTERNS now covers
Terraform, *.pem/*.key, CDK stack files, .github/actions, *iam*, bare policy*.json
(case-insensitive), matching the CI surface.
- force-resume was backwards (MED): it superseded the answered row recovery
resumes from, making a stuck task permanently un-resumable while printing
success. Now re-opens an EXPIRED (parked) question via a new reopen_question
CAS helper; never supersedes an answered row; honest exit codes.
- operator attribution (MED): run-team.py --operator defaulted to "" -> now the
OS login, so destructive actions are always attributable.
- audit-log append race (MED): replaced read-modify-rewrite (lost records under
concurrent operators) with an O_APPEND single-line write, mode 600 enforced.
- lstrip("ab/") path-mangling in the symlink error path -> regex prefix strip.
Regression tests added across test_ci_gate_workflow / test_builders / test_run_team
/ test_schema. Design-level findings (resume-worker durability, egress breadth,
answered_at ordering, DB-swap TOCTOU, diff-hash threat-model) are pre-deployment
/ P1-build-proper and recorded with written justification in
agent-team/.security-review/suppressions.json; CI README diff-hash wording made
honest.
Resolves three execution-proven verifier findings from the scaffold review.
Full suite: 548 passed, 1 skipped (stable across repeated runs); ruff clean.
builders denylist (§3.3.2 #2): scan was +++-only and missed header-only
sections. Now section-driven off `diff --git a/<src> b/<dest>`, catching the 4
proven bypasses — delete of a denied path, mode-change-only, `copy to` a denied
path, out-of-scope delete (regression tests for each).
§3.3.1 compare-and-set concurrency: BEGIN IMMEDIATE moved inside guarded retry;
each CAS now runs on its own connection (shared sqlite3.Connection cannot hold
two transactions, and is unsafe for concurrent use even for reads). connect()
stashes the db path on a Connection subclass so the path is derived by a
thread-safe attribute read, not a PRAGMA on the shared conn; busy_timeout set
before the WAL pragma. Added shared-connection concurrent regression tests
(distinct + same question) — previously raised "transaction within a
transaction".
operator CLI (run-team.py): added the design-named re-deliver and force-resume
verbs (were missing); audit now records the attempt BEFORE the mutation and the
outcome after, so a ledger mutation can never land without a trail; main()
catches OSError instead of leaving an uncaught traceback on audit-write failure.
