This repository has been archived on 2026-08-04. You can view files and clone it, but cannot push or open issues or pull requests.
orchestrator/agent-team/README.md
Adam Moussa cb84629c2b feat(agent-team): P3 Phases A/B/E — safety tooling, wiring, docs
Phase A (safety):
- scripts/p3_rollback.sh (+test): restore all privileged P3 surfaces from a
  recorded baseline; --dry-run default, --apply gated. Correct App-uninstall
  (App JWT) model; per-task env-reviewer restore by numeric id; real
  protection post-restore assert (normalize reads argv, fails loud, divergent
  state exits non-zero — regression-tested). KNOWN-LIMITATIONS header flags the
  branch-protection GET->PUT transform + live-validation for the C1 gate.
- scripts/assert_no_write_token.py (+test): box/CI audit that no write token
  (incl. ghu_/ghr_ prefixes + App PEM) lives on the box.
- draft_pr_monitor.py (+test): runaway (>3/15min) + stale (7d) draft-PR sweep,
  wired into tick() and bound a read-only provider in serve.

Phase B (wiring): systemd EnvironmentFile P3 vars + verification; new-draft-PR
lifecycle notice.

Phase E (docs): P3-LIVE-FLIP-PLAN/README/ci-README reflect CI-live-since-6/22 +
box-integration; runbook consolidated (rollback Incident 7 + box-env wiring);
removed a stray duplicate runbook.

Suite: 1360 passed, ruff clean. Branch only; not merged/deployed.
REMAINING HUMAN GATES: C1 /sh-security-review + GPT-4.1 cross-review on the
enabled workflow + rollback script; D box deploy + smoke + merge.
2026-06-23 19:52:04 -04:00

180 lines
12 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# agent-team — R720 Plane-2 SDLC pipeline
The durable, human-gated agentic SDLC pipeline for the R720 (`sh-secrev` VM),
design: `../docs/r720-agent-team-design.md`. A task flows INTAKE → CLARIFY (the
human gate) → PLAN → REVIEW, and (P3) → BUILD → DISPATCH → VERIFY → draft
PR. Every stage is durable and resumable (LangGraph + a SQLite checkpointer);
the human gate suspends on `interrupt()` and resumes on a real answer.
```
INTAKE → CLARIFY (Claude, human gate) → PLAN (Claude) → REVIEW (GPT-4.1)
▲ │
└── loop-back ───┤
approve/escalate → END
(P3 box path — gated behind the C1 re-review):
approve → BUILD (DeepSeek) → DISPATCH (push branch, trigger CI,
capture run_id, suspend) → [CI-watcher resumes on terminal
conclusion] → VERIFY (ci_gate) → draft PR
```
> **Status (2026-06-23).** P1 (human gate) + P2 (planner + adversarial review
> loop) + the live runtime (coordinator, Slack/GitHub/Claude-Code transports,
> intake) + P3 (build/dispatch/verify subgraph) + P4 (more transports +
> GitHub-issue intake) are **built, reviewed, and merged to main**.
> **The CI apply/verify workflow is LIVE + provisioned** (the `agent-apply`
> environment, the `AGENT_APPLY_APP_*` secrets, and dispatched runs all exist as
> of 2026-06-22). **The box-side integration that drives it** (run_id capture,
> the BUILD → DISPATCH → VERIFY reorder, async CI-watch, and the fail-safe bound
> `serve` default) is built on this branch but **gated behind the C1 re-review**
> — the `/sh-security-review` + mandatory GPT-4.1 cross-review of the new
> CI-trigger boundary — before it ships to the box. See the project memory
> `project_r720_agent_team` and §7 of the design (and `docs/P3-PHASE0-DESIGN.md`)
> for the phased rollout.
## Layout
```
agent-team/
run-team.py # operator CLI: init-db, list/show/answer/expire/
# force-resume (ledger), start (intake), serve (daemon),
# intake-github
agent_team/ # importable package (snake_case)
coordinator.py # the live runtime keystone: invoker→graph→ResumeWorker;
# start_task / submit_answer / drain / tick / recover / serve
graph.py # LangGraph wiring: P1 (intake→clarify→plan) + opt-in P2
# review loop + opt-in P3 build/verify subgraph
invoker.py # §3.1 real Claude path (subscription-OAuth / API / Bedrock)
invoker_multi.py # WS1 in-process non-Claude invokers (GPT-4.1 / DeepSeek /
# Gemini via the orchestrator's models.py); bind_multi_invoker()
api.py # WS1 FastAPI HTTP API (bearer auth, 127.0.0.1:8765) — SEPARATE
# opt-in process (api.serve()), NOT started by the coordinator
dashboard.py # read-only LAN status dashboard (FastAPI, 0.0.0.0:8770):
# /api/state /api/topology /api/task/{id} + serves web/dist SPA
topology.py # pipeline map derived from the compiled LangGraph
# (get_graph() + NODE_META sidecar) — new agents appear auto
status_page.py # read-only DATA LAYER for /api/state (build_snapshot /
# snapshot_to_dict); HTML rendering retired in the makeover
billing.py # §3.1 claude_invoke billing-mode seam
ci_gate.py # §3.3.2 pure-code authenticated-Checks PASS/FAIL gate
task_model.py / state_store.py
db/{schema.py,schema.sql} # SQLite ledger DDL + BEGIN IMMEDIATE compare-and-set
db/transitions.py # task_transitions recorder (per-task pipeline history,
# idempotent + fail-soft; written by instrumented graph nodes)
ledger.py / responder.py / resume_worker.py / deadline_timer.py / recovery.py
operator_cli.py
nodes/ # pipeline stages + their model bindings
clarifier.py + clarifier_llm.py # human gate (Claude)
planner.py # plan (Claude)
review_loop.py + review_loop_llm.py # adversarial review (GPT-4.1 via orchestrator)
builders.py + builders_llm.py # candidate diff (DeepSeek) — INERT, proposes only
verifier.py + verifier_llm.py # ci_gate sole PASS authority; LLM = fix-proposer;
# binds expected_run_id per-task from state["run_id"]
build_verify_subgraph.py # P3 BUILD→DISPATCH→VERIFY topology + the tick()-driven
# CI-watcher that resumes a suspended task on the
# dispatched run's terminal conclusion (or parks on timeout)
handbook.py # WS5 load_handbook_conventions (handbook seam,
# fail-safe → "" if dir missing); planner context
dispatch_invoker.py # P3 DISPATCH node — pushes the per-dispatch head branch,
# triggers CI (gh workflow run), and captures run_id +
# dispatched_at into state via a correlation-tagged poll
# of gh run list (fails closed on an unfound run)
transport/ # one adapter contract + a live impl per channel
base.py # Transport ABC + QuestionSet / NormalizedAnswer
slack_adapter.py + slack_live.py + slack_listener.py # Block Kit + Socket Mode + /new-task
github_adapter.py + github_live.py + github_intake.py # issue-comment + issue intake
claude_code_adapter.py + claude_code_live.py # file-drop responder
web/ # React/Vite/TypeScript status-dashboard SPA (React Flow map,
# task list, click-through task history); built to web/dist
scripts/ # deploy-r720-ws-rollout.sh — attended WS0–WS5 UPDATE of the box
ci/ # §3.3.2 split-job CI apply/verify workflow (LIVE since 2026-06-22)
systemd/ # agent-team-coordinator.service + agent-team-status.service
DEPLOY-R720.md # provisioning runbook (snapshot-first, rsync, tokens, demo)
tests/ # pytest, one module per source module + sim harness
```
The Claude Code plugin lives in a sibling top-level dir, `../sea-haven-claude-plugin/`
(CLAUDE.md, settings.template.json, `hooks/user_prompt_submit.py`): a
`UserPromptSubmit` hook that forwards `/delegate <task>` prompts from Claude Code
to the HTTP API's `POST /tasks` (env `AGENT_TEAM_API_URL` / `AGENT_TEAM_API_TOKEN`).
The top directory is kebab-case (`agent-team/`); the importable package is
snake_case (`agent_team/`), per the engineering handbook.
## Key design points
- **Durable human gate (§3.3.1).** The `pending_questions` ledger is the single
source of truth for the question lifecycle. Every race (duplicate answers,
transport redelivery, answer-vs-timeout) resolves via one atomic
compare-and-set against `status`, inside a `BEGIN IMMEDIATE` transaction —
first-answer-wins (`rowcount == 1`), late/duplicate ignored. The LangGraph
`SqliteSaver` checkpointer shares the same DB file.
- **Fail-safe model seams.** Every node treats model output as untrusted and
fails SAFE: garbage never clears the 98% clarifier gate, never auto-approves a
plan, never fabricates a build success, and the verifier's `ci_gate` is the
**sole** PASS authority (the LLM is structurally a fix-proposer only).
- **Inbound auth (§3.3.1).** The Slack Socket Mode listener authorizes the
**sender** against an owner allowlist (`AGENT_TEAM_SLACK_OWNER_IDS`,
fail-closed) on top of the open-status CAS anti-replay.
- **Billing seam (§3.1).** Claude runs under subscription OAuth on the box;
GPT-4.1 (review) and DeepSeek (builders) route through the local orchestrator
`run.py`. Switching Claude billing is a config flip.
## Status dashboard (WebUI)
A read-only LAN dashboard (FastAPI, `0.0.0.0:8770`, no auth, `mode=ro` ledger
opens) for watching the pipeline. Served by `agent_team.dashboard` (systemd unit
`agent-team-status.service`):
- **Live pipeline map** — a React Flow graph **auto-laid-out from the real
LangGraph** (`topology.py` introspects `compiled.get_graph()` + a `NODE_META`
display sidecar). Adding an agent node in `graph.py` makes it appear on the map
with no manual coordinates; nodes group into **trees** (processes) branching off
`intake`. Node color = live state; loop-back edges (review→plan, verify→build)
render dashed.
- **Click-through task history** — selecting a task opens a timeline of its journey
through each node (entry/exit timestamps, per-node duration, per-stage cost, Q&A,
verdicts, plan), backed by the `task_transitions` ledger (schema v3) written by
the coordinator's instrumented graph nodes (`db/transitions.py`, fail-soft).
Endpoints: `GET /api/state` (live overview + per-node state), `GET /api/topology`
(map nodes/edges/trees), `GET /api/task/{thread_id}` (one task's history;
`thread_id` is validated `^[A-Za-z0-9_-]{1,64}$`). The legacy stdlib HTML page was
retired; `status_page.py` remains as the `/api/state` data layer.
**Build (on the Mac — the box Node is too old for Vite 5+):**
```
cd agent-team/web
npm ci && npm run build # -> web/dist (gitignored), rsynced to the VM
npm test # Vitest + React Testing Library
```
In dev, `npm run dev` proxies `/api` to a locally running dashboard
(`AGENT_TEAM_DASH`, default `http://127.0.0.1:8770`).
## WS0–WS5 rollout glossary
The "WS-rollout" (workstreams 0–5) layered HTTP/integration surfaces onto the
P1–P4 pipeline. What is **live** vs **inert** after the rollout:
| WS | What it adds | Live? |
|---|---|---|
| WS1 | `invoker_multi.py` (in-process GPT-4.1 / DeepSeek / Gemini via the orchestrator's `models.py`) + `api.py` (FastAPI HTTP API, bearer auth via `AGENT_TEAM_API_TOKEN`, binds `127.0.0.1:8765`, `/docs`+`/openapi` disabled, concurrency-capped) | `bind_multi_invoker()` wired in `run-team.py` `_cmd_serve` (LIVE); the **HTTP API is a separate opt-in process** (`api.serve()`), NOT started by the coordinator |
| WS5 | `nodes/handbook.py` `load_handbook_conventions` (reads `SEA_HAVEN_HANDBOOK_DIR` or `~/.sea-haven/engineering-handbook`, fail-safe → `""`); `retriever.py` `save_memory` writes to a `_box-drafts/` review queue | LIVE — the planner prompt receives the handbook via the `context_provider` seam in `run-team.py` `_build_coordinator` |
| WS2/WS0/WS4 | Slack `/new-task` slash command (AUTHZ-01 owner-allowlist gated) → `Coordinator.set_new_task_callback`; the `sea-haven-claude-plugin/` (CLAUDE.md, settings, `/delegate` `UserPromptSubmit` hook) | LIVE (`/new-task` wired in `serve`); the plugin/HTTP-API path is opt-in |
| WS3 / P3 | `nodes/dispatch_invoker.py` (DISPATCH LangGraph node) + the BUILD → DISPATCH → VERIFY reorder, the `tick()`-driven CI-watcher, per-task `run_id` plumbing, and the bound `serve` default | **Built on `feat/agent-team-p3-box-integration`, gated behind the C1 re-review** before it ships to the box. The `agent-apply` GitHub Environment human-approval gate is KEPT; dispatch is **operator-initiated** (the box holds no standing write token — the branch push + `gh workflow run` use operator-host credentials). The bound P3 wiring is the new fail-safe `serve` default: a missing `AGENT_TEAM_REPO_OWNER`/`_NAME` or CI-read token degrades to the INERT P3 path (task parks + a `#agent-team` notice), never a serve-start crash |
The HTTP API endpoints: `POST /tasks` (start a task), `GET /tasks/{thread_id}`
(status), `POST /orchestrator/invoke` (one-shot model invoke). See
`DEPLOY-R720.md` for the WS-rollout deploy (`scripts/deploy-r720-ws-rollout.sh`).
## Running the tests
```
cd agent-team
python3 -m pytest -q # conftest puts the package on sys.path; no install needed
```
## Deploy
Deploy-gated. See `DEPLOY-R720.md` for the provisioning runbook (VM snapshot
first, rsync, venv deps, `~/secrev.env` tokens, `init-db`, systemd, and the live
P1 exit-criteria demo). Secrets are never committed.