Renn F 366800299b [F008] evidence_builder: surface persisted pr_review verdict+issues in the PM task_handoff ...

The pr_fail a2a steer to the owning PM is fire-and-forget; a PM respawned
into needs_revision later read none of it (build_task_handoff never looked
at notes_structured), saw a generic 'needs revision' with zero concrete
change-requests, and re-submitted the same PR (the 2026-06-27 infinite
pr_fail loop on 9980d0a0 / PR #138). The signal-gap was only partially
closed by the a2a.

build_task_handoff now extracts notes_structured.pr_review
(verdict/summary/issues/head_sha — the slot pr_fail authors on every fail)
into a pr_review field on the handoff, so every PM briefing for the task
carries the concrete change-requests. A prior pr_fail alone now counts as
prior-work-worth-resuming. Type-guarded + capped; absent => no key (no
misleading empty slot).

TDD red->green; ruff + mypy clean; evidence_builder suite green (14 passed).

2026-06-28 10:25:53 +02:00

..

__init__.py

Gateway/full (#9)

2026-05-02 03:11:49 +02:00

test_acceptance_criteria_status_writer.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_audit_on_rejection.py

feat(gateway): C8 PM-decision gate windowed satisfaction

2026-05-12 06:27:33 +02:00

test_auditor_idle_note_guard.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_auditor_silent_guard.py

Feature: lifecycle canonical spec (#14)

2026-05-11 02:15:47 +02:00

test_auto_pause_checkpoint.py

fix: read the real commit key (hash) and audit the restore-unblock path

2026-06-08 02:45:03 +02:00

test_behind_base_gate.py

[feature] i_am_done behind-base submit gate (Phase B2)

2026-06-28 04:46:09 +02:00

test_briefing_memory.py

Feat/v0.13.0 (#270)

2026-06-26 01:43:08 +02:00

test_choreographer_auditor.py

feat(gateway): C8 PM-decision gate windowed satisfaction

2026-05-12 06:27:33 +02:00

test_choreographer_board.py

feat(content): anti-soup guard on the flow verbs' free-text

2026-06-21 05:11:20 +02:00

test_choreographer_claim_guards.py

Feature/observability gateway health (#247)

2026-06-23 07:26:41 +02:00

test_choreographer_completion_guards.py

[F002] retype board-routed MegaTask root-subtasks code->planning on activation

2026-06-28 09:57:08 +02:00

test_choreographer_delegate_guards.py

Bunch of runtime fixes for MegaTask and other issues

2026-06-27 06:52:59 +02:00

test_choreographer_dev.py

fix(run-hardening): break PM decision-gate, stale-agent, and empty-diff loops (#255)

2026-06-25 01:07:05 +02:00

test_choreographer_doc.py

fix(docs): push the documenter's doc commit so it lands in the PR

2026-06-23 00:39:08 +02:00

test_choreographer_idle_guards.py

fix(gateway): let a dev idle past lane-held code-queue siblings

2026-06-16 05:13:00 +02:00

test_choreographer_impl_branches.py

fix(run-hardening): break PM decision-gate, stale-agent, and empty-diff loops (#255)

2026-06-25 01:07:05 +02:00

test_choreographer_pm_extras.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_choreographer_pm.py

Fix different project same PR number collision problem

2026-06-27 07:19:35 +02:00

test_choreographer_qa.py

fix(gateway): evidence/QA/doc paths populate files_changed from git

2026-05-15 06:31:38 +02:00

test_choreographer_reassignment.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_choreographer_submit_qa_gates.py

fix(run-hardening): break PM decision-gate, stale-agent, and empty-diff loops (#255)

2026-06-25 01:07:05 +02:00

test_claim_arg_order.py

feat(gateway): developers author the full rich plan, at parity with PMs

2026-05-24 06:59:25 +02:00

test_claim_doc_task_checkout.py

fix: panel logo (#160), diff base fallback (#161), doc branch checkout (#162)

2026-05-16 00:13:14 +02:00

test_claimant_lock.py

Gateway/full (#9)

2026-05-02 03:11:49 +02:00

test_commit_prefix.py

fix(gateway): heartbeat on content-write success, single-claimant gate, progress soft-warn

2026-06-03 18:44:33 +02:00

test_commit_validator.py

[beb8cae1] Type-gate tests/ under mypy — fix all errors and flip quality gate (#156) (#157)

2026-06-14 13:43:46 +02:00

test_content_actions_ownership.py

fix(gateway): let a dependent agent read its dependency via evidence

2026-06-04 02:12:45 +02:00

test_content_actions_pitch.py

fix(content): anti-soup guard on pitch slug + restore pitch test intent

2026-06-21 08:08:28 +02:00

test_content_actions_runkiller.py

fix(gateway): heartbeat on content-write success, single-claimant gate, progress soft-warn

2026-06-03 18:44:33 +02:00

test_content_actions.py

feat(content): extend anti-soup guard to pitch title, open_session topic, pr_update, note narratives

2026-06-21 04:46:28 +02:00

test_content_soup_guard.py

feat(content): universal anti-soup guard on every agent free-text field

2026-06-21 04:20:07 +02:00

test_conventions_gate_i_am_done.py

Feature/architectural conventions standard (#243)

2026-06-22 12:37:46 +02:00

test_conventions_gate_pr_pass.py

Feature/architectural conventions standard (#243)

2026-06-22 12:37:46 +02:00

test_conventions_in_qa_evidence.py

Feature/architectural conventions standard (#243)

2026-06-22 12:37:46 +02:00

test_delegate_assignee_task_type.py

Chore: v1 removal gateway canonical (#46)

2026-06-03 06:35:03 +02:00

test_delegate_incomplete_input.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_delegate_project_routing.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_delegate_propagates_sessions.py

feat(gateway): propagate sessions to subtasks + auto-emit milestone progress

2026-05-15 06:54:35 +02:00

test_delegate_rejects_documentation_subtask.py

fix(gateway): reject PM-created documentation subtasks (#163)

2026-05-16 00:47:59 +02:00

test_delegate_sizing.py

feat(gateway): enable 2-devs-per-cell parallelism + split-before-claim sizing

2026-06-14 04:34:02 +02:00

test_dev_steps_gate.py

feat(gateway): developers author the full rich plan, at parity with PMs

2026-05-24 06:59:25 +02:00

test_dm_a2a_denied.py

[beb8cae1] Type-gate tests/ under mypy — fix all errors and flip quality gate (#156) (#157)

2026-06-14 13:43:46 +02:00

test_doc_reflect_autowrite.py

fix(gateway): i_documented auto-records journal:reflect from submission

2026-05-28 00:24:42 +02:00

test_envelope_from_decision.py

[beb8cae1] Type-gate tests/ under mypy — fix all errors and flip quality gate (#156) (#157)

2026-06-14 13:43:46 +02:00

test_envelope_incomplete_input.py

Feature: lifecycle canonical spec (#14)

2026-05-11 02:15:47 +02:00

test_envelope_introspection.py

Feature: lifecycle canonical spec (#14)

2026-05-11 02:15:47 +02:00

test_envelope.py

fix(gateway): rejection envelopes always carry a human-readable message

2026-06-04 06:01:06 +02:00

test_evidence_builder.py

[F008] evidence_builder: surface persisted pr_review verdict+issues in the PM task_handoff

2026-06-28 10:25:53 +02:00

test_evidence_populates_files_changed.py

fix(gateway): evidence/QA/doc paths populate files_changed from git

2026-05-15 06:31:38 +02:00

test_evidence_repo.py

feat: company-in-a-box — goal-aware company layer (0.4.0) (#171)

2026-06-15 20:47:41 +02:00

test_flow_soup_guard.py

feat(content): anti-soup guard on the flow verbs' free-text

2026-06-21 05:11:20 +02:00

test_gateway_rejection_attempt_id.py

Chore: reduce analytics complexity (#100)

2026-06-11 04:36:17 +02:00

test_give_me_work_pre_assigned.py

feat(gateway): C8 PM-decision gate windowed satisfaction

2026-05-12 06:27:33 +02:00

test_heartbeat_on_rejection.py

feat(gateway): C8 PM-decision gate windowed satisfaction

2026-05-12 06:27:33 +02:00

test_heartbeat_wired.py

feat(gateway): C8 PM-decision gate windowed satisfaction

2026-05-12 06:27:33 +02:00

test_i_am_blocked_no_escalation_target.py

[F016,F017] choreographer: surface invalid_state instead of None.status 500 on submit_root / i_am_blocked

2026-06-28 10:20:39 +02:00

test_i_am_blocked_rate_limited.py

Fix: rate limit real probe (#110)

2026-06-11 18:16:20 +02:00

test_i_will_plan_persists_rich_plan.py

feat(gateway): substantive-plan gate — approach >=150 + real sub_task descriptions (#171)

2026-05-16 10:14:45 +02:00

test_i_will_plan_sub_tasks_gate.py

feat(gateway): substantive-plan gate — approach >=150 + real sub_task descriptions (#171)

2026-05-16 10:14:45 +02:00

test_merge_chain.py

Chore: v1 removal gateway canonical (#46)

2026-06-03 06:35:03 +02:00

test_merge_conflict_resolver.py

Fix different project same PR number collision problem

2026-06-27 07:19:35 +02:00

test_milestone_progress.py

feat(gateway): propagate sessions to subtasks + auto-emit milestone progress

2026-05-15 06:54:35 +02:00

test_needs_revision_recovery.py

fix(lifecycle): let a PM recover its rejected coordination task from needs_revision

2026-06-21 06:09:59 +02:00

test_note_handoff.py

Bunch of runtime fixes for MegaTask and other issues

2026-06-27 06:52:59 +02:00

test_notify.py

Fix: dependency spawn gate and cell ownership (#73)

2026-06-06 22:10:48 +02:00

test_open_pr.py

fix(run-hardening): break PM decision-gate, stale-agent, and empty-diff loops (#255)

2026-06-25 01:07:05 +02:00

test_open_session_schema.py

fix(gateway): open_session passes model schema, not API schema

2026-05-14 03:28:38 +02:00

test_playbook_verbs.py

Feat/v0.13.0 (#270)

2026-06-26 01:43:08 +02:00

test_pm_decision_autorecord.py

fix(run-hardening): break PM decision-gate, stale-agent, and empty-diff loops (#255)

2026-06-25 01:07:05 +02:00

test_pm_decision_window.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_pm_own_review_hint.py

fix(gateway): rejected PM is told the exact complete() call (#170, partial)

2026-05-16 06:37:49 +02:00

test_pr_gate_notifies_pm.py

[chore] mypy tests/: clear all 15 pre-existing type errors so make quality can go green

2026-06-28 02:19:48 +02:00

test_pr_gate_posts_review.py

feat: in-path PR-review gate — per-cell + main reviewers (#229)

2026-06-20 09:27:29 +02:00

test_pr_gate_records_verdict.py

[chore] mypy tests/: clear all 15 pre-existing type errors so make quality can go green

2026-06-28 02:19:48 +02:00

test_pr_review_hand_format_guard.py

[chore] mypy tests/: clear all 15 pre-existing type errors so make quality can go green

2026-06-28 02:19:48 +02:00

test_pr_review_structured.py

feat(content): structured PR-review findings + generated GitHub comment

2026-06-21 03:47:17 +02:00

test_pr_review_verdict_consistency.py

fix(pr-review): reject a verdict that contradicts the review's findings

2026-06-26 02:13:41 +02:00

test_pr_reviewer_notes_obligation.py

feat(content): obligate role note sections like journals

2026-06-21 20:31:42 +02:00

test_pr_update.py

feat(content): anti-soup guard on the flow verbs' free-text

2026-06-21 05:11:20 +02:00

test_project_slug_for.py

fix(pr-gate): land gate verdict on product-scoped PRs + persist it to notes

2026-06-25 10:54:31 +02:00

test_qa_ac_coverage.py

feat(qa): require a per-acceptance-criterion verdict before pass_review

2026-06-14 04:44:21 +02:00

test_quality_gate.py

[beb8cae1] Type-gate tests/ under mypy — fix all errors and flip quality gate (#156) (#157)

2026-06-14 13:43:46 +02:00

test_reassign_verb.py

Fix: dependency spawn gate and cell ownership (#73)

2026-06-06 22:10:48 +02:00

test_remediation.py

Chore: v1 removal gateway canonical (#46)

2026-06-03 06:35:03 +02:00

test_resume.py

feat(gateway): C8 PM-decision gate windowed satisfaction

2026-05-12 06:27:33 +02:00

test_role_config.py

Chore: v1 removal gateway canonical (#46)

2026-06-03 06:35:03 +02:00

test_say_channel_rbac.py

feat(gateway): notify(target, text, scope?) for PMs and Board

2026-05-03 09:19:08 +02:00

test_say_status.py

fix(gateway): journal task_id auto-injection works from blocked/paused

2026-05-14 04:21:07 +02:00

test_spine_cap_cross_team.py

feat(dispatch): per-dev sequenced queues for code subtasks (guardrails spec 3)

2026-06-16 04:10:05 +02:00

test_spine_cap_remediate.py

feat(gateway): enable 2-devs-per-cell parallelism + split-before-claim sizing

2026-06-14 04:34:02 +02:00

test_submit_root_unchanged_pr_guard.py

[F016,F017] choreographer: surface invalid_state instead of None.status 500 on submit_root / i_am_blocked

2026-06-28 10:20:39 +02:00

test_submit_up_unchanged_pr_guard.py

[F007] choreographer: cell-level unchanged-PR re-submit loop-stopper for submit_up

2026-06-28 10:23:54 +02:00

test_sync_branch.py

[feature] sync_branch dev verb — gate-level branch rebase (Phase B1)

2026-06-28 04:40:06 +02:00

test_toolchain_guard.py

fix(gateway): surface an 'unknown' toolchain status at the gate instead of passing silently

2026-06-22 13:06:55 +02:00

test_tracing_gap_hints.py

fix(gateway): cross-team planning fanout + complete tracing-gap hints

2026-05-15 08:21:08 +02:00

test_trigger_filter.py

[aaac85d2] Rate limit guardrails for Anthropic and Ollama providers (#104)

2026-06-11 09:21:26 +02:00

test_unclaim.py

feat(gateway): C8 PM-decision gate windowed satisfaction

2026-05-12 06:27:33 +02:00

test_verb_runner.py

fix(run-hardening): stop three blocked-task respawn loops (#253)

2026-06-24 15:43:30 +02:00

test_work_session_auto_create.py

[beb8cae1] Type-gate tests/ under mypy — fix all errors and flip quality gate (#156) (#157)

2026-06-14 13:43:46 +02:00