This repository has been archived on 2026-08-04.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/docs/provisioning/P3-LIVE-FLIP-PLAN.md
Adam Moussa 8afe876fa2
docs(agent-team): formal phased plan for the P3-live flip (build->verify->draft-PR) (#28)
Phased plan to take Plane-2 from clarify+plan to producing reviewable draft PRs:
locked decisions (GitHub App pull-requests:write, zero-AWS, read-only box), the
mandatory gates (/sh-plan-review + /sh-security-review + GPT-4.1 cross-review on
the CI surface), the B4 CI trust boundary (split CI, denylist, diff-hash, pure-code
green gate), phases 0-6 with owners + exercised rollbacks, what changes vs what
does not, risks, and definition of done. Input to /sh-plan-review before any build.
2026-06-22 16:05:54 -04:00

8.9 KiB

P3-LIVE-FLIP PLAN — agent-team build → verify → draft-PR

Formal phased plan to take the agent-team Plane-2 pipeline from clarify+plan only to producing reviewable draft PRs, while keeping the always-on R720 box read-only and the apply path zero-AWS. Status as of 2026-06-22: NOT STARTED (P3 is built but inert). This plan is the input to /sh-plan-review before any build.

Prerequisite reading: docs/r720-agent-team-design.md §3.3.2 (CI-as-verifier trust boundary, "B4"), PROVISIONING-RUNBOOK.md (the P3-live-flip section), and memory project_r720_agent_team (locked decisions).


1. Objective & current state

Today (inert): the pipeline runs INTAKE → CLARIFIER → PLANNER → REVIEW, but serve passes build_verify_wiring=None, the Tier-3 fixer is --dry-run only, and agent-team/ci/agent-team-apply-verify.yml has its privileged steps disabled with if: ${{ false }} and pull-requests:write / environment: commented out. So it clarifies + plans but writes no code and opens no PR.

After P3: the pipeline can emit a diff, have org CI build/test/security-review it in an untrusted sandbox, a pure-code gate confirm green from authenticated Checks-API results, and a scoped GitHub App open a draft PR for human review. The box never gains a write token.

2. Locked decisions (carried in — do not relitigate here)

  • D-OIDC: apply path uses a GitHub App pull-requests:write token, ZERO AWS, no OIDC.
  • D2: box stays read-only / no standing write token; org CI does the applying.
  • B4: the LLM-proposed diff is untrusted code; the CI trust boundary (below) is mandatory.
  • Output is draft PRs only — nothing auto-merges; human approval is the merge gate.
  • (Separate, not part of this plan: aws-posture resident access via step-ca + IAM Roles Anywhere — that IAM is already cross-review-approved and is its own sub-task.)

3. Hard gates (must clear before the flip — these block everything)

Gate Why Owner
/sh-plan-review on THIS plan adversarial plan audit before build me → GPT-4.1
/sh-security-review on the apply/verify CI surface auth + untrusted-input + CI trust boundary me
GPT-4.1 cross-family review on the apply/verify CI + any permission change mandatory for the trust-boundary / permissions surface orchestrator
GH_TOKEN→GITHUB_TOKEN resolved the GitHub transport reads GITHUB_TOKEN; box has GH_TOKEN me (folded in here)

The flip does NOT proceed until /sh-security-review AND the GPT-4.1 cross-review on the CI surface both pass.

4. The CI trust boundary (design B4 — what the workflow must enforce)

  1. Split CI. An untrusted build/test job: contents: read only, no secrets / no OIDC / no write token, egress-restricted. A separate privileged job that never checks out the patch code (no pull_request_target + head checkout) opens the draft PR.
  2. Denylist. A diff touching .github/workflows/**, IAM/permission IaC, branch-protection / CODEOWNERS / Dependabot config, or out-of-scope files is rejected / escalated to a human — never auto-built.
  3. Diff-hash integrity. The box records the diff hash in its ledger; CI verifies the hash before apply. The diff reaches CI as a signed artifact / short-lived branch-only token (the box has no write token).
  4. Pure-code green gate. Pass/fail is owned by a pure-code gate reading authenticated Checks-API results (run id + diff hash). The LLM verifier may propose fixes but can never declare a build green.
  5. Merge gate. Draft PR + required checks + /sh-security-review + Claude Code App review + human approval.

5. Phases

Phase 0 — Plan review & pre-reqs 🤖/🧑

  • Run /sh-plan-review on this doc; fold BLOCK/FIX items in.
  • Confirm a clean revert point (git tag main; Hyper-V snapshot of sh-secrev).
  • Resolve GH_TOKEN→GITHUB_TOKEN (transport accepts both / box env updated).
  • Rollback: none (no state changed).

Phase 1 — Author the split-CI apply/verify workflow 🤖 (review-gated)

  • Write agent-team/ci/agent-team-apply-verify.yml per §4: split jobs, denylist, diff-hash verification, pure-code gate reading Checks-API. SHA-pin all actions.
  • Implement/confirm agent_team/ci_fetcher.py (read-only Checks-API result fetcher; fails closed: missing token / 404 / auth fail → None → gate BLOCKs, task parks) and agent_team/ci_gate.py (pure-code green decision).
  • /sh-security-review + GPT-4.1 cross-review on this surface. Hard stop until both pass.
  • Rollback: workflow file stays inert (if: ${{ false }} not yet flipped); delete the file.

Phase 2 — Provision the GitHub App + environment 🧑 OPERATOR (browser/admin)

  • Create a dedicated GitHub App with pull-requests:write (+ minimal contents to open a branch/PR); install on the org. Token lives in CI, never on the box.
  • Create the agent-apply GitHub Actions Environment with a required reviewer (Adam) + branch-protection so the privileged job cannot run unreviewed.
  • Store the App credentials as repo/org Actions secrets (not on the box).
  • Rollback: uninstall the App; delete the environment + secrets.

Phase 3 — Bind the live wiring (still gated by the environment) 🤖

  • In the workflow: uncomment permissions: pull-requests: write and environment: agent-apply; flip the two if: ${{ false }} → enabled.
  • Bind agent_team.coordinator.gated_build_verify_wiring(...) (real diff builder + read-only CI-result fetcher) so a leaf calls it only after the gate clears.
  • Set the box-side apply env vars the live path reads (read-only CI-result token + dispatch target). Confirm no write token lands on the box.
  • Rollback: re-set if: ${{ false }}, re-comment environment:, set build_verify_wiring=None; restart the coordinator. (Exercise this rollback once.)

Phase 4 — Smoke test to a first draft PR 🧑/🤖

  • Drive one trivial, in-scope task end-to-end → confirm: untrusted job builds/tests with no secrets, denylist rejects an out-of-scope diff, pure-code gate gates on real Checks results, privileged job opens a draft PR with required checks attached, nothing merged.
  • Flip the Tier-3 fixer off --dry-run only after the smoke test passes; verify a dependency-CVE bump produces a draft PR.
  • Rollback: close the draft PR; Phase-3 rollback.

Phase 5 — Enable the cross-plane loop 🤖

  • Allow confirmed Plane-1 checker findings (intake-checker) to flow into pipeline tasks that end in draft-PR fixes (start conservative: highest-severity, one at a time).
  • Rollback: revert intake-checker wiring to report-only.

Phase 6 — Docs & memory 🤖

  • Update OPERATOR-RUNBOOK.md, the Confluence host page, and memory: P3 is LIVE, what the apply path can/can't do, the denylist, the merge gate, the rollback.

6. What changes (and what does NOT)

Changes:

  • The pipeline produces draft PRs for well-scoped work (dep bumps, small fixes, docs, checker-surfaced issues). Your role shifts from author → reviewer/approver for that class.
  • Tier-3 fixer goes live (dep-CVE bumps → draft PRs).
  • Plane-1 findings can become draft-PR fixes (cross-plane loop).

Does NOT change:

  • Box stays read-only; CI applies, not the box. No AWS / no OIDC in the apply path.
  • Denylisted, high-blast-radius changes (workflows, IAM, branch protection, CODEOWNERS, Dependabot) are never auto-built — always escalated.
  • Human gates stay: the clarifier question-set AND the PR approval are both yours.
  • Drafts, not merges — you remain the merge authority.

7. Risks & mitigations

Risk Mitigation
Untrusted diff exfiltrates secrets / escalates in CI split CI: build job has no secrets/OIDC/write, egress-restricted; privileged job never checks out patch code
Malicious diff edits CI/IAM/branch-protection to self-escalate denylist → reject/escalate, never auto-build
LLM "declares" a broken build green pure-code gate reads authenticated Checks-API only; LLM can't set status
Diff tampered between box and CI diff-hash recorded in ledger, verified before apply
Standing write capability on the always-on box there is none — App token lives in CI; box holds only a read-only CI-result token
Runaway PR volume start with Tier-3 only + one finding at a time; required-reviewer environment gates each

8. Definition of done

  • /sh-plan-review, /sh-security-review, and GPT-4.1 cross-review on the CI surface all passed.
  • Phase-4 smoke test produced a draft PR; nothing auto-merged; rollback exercised once.
  • No write token on the box (verified); apply path is zero-AWS.
  • Docs + Confluence + memory updated.
  • Snapshot retained until P3 runs clean for one cycle, then pruned.