Skip to content

fix(goal-conductor): park findings that no Done when condition needs - #37648

Merged
buluoray merged 1 commit into
mainfrom
crew/slack/park-out-of-scope-findings
Nov 15, 2026
Merged

buluoray merged 1 commit into
mainfrom
crew/slack/park-out-of-scope-findings

Conversation

@buluoray

@buluoray buluoray commented Nov 15, 2026 •

Copy link
Copy Markdown
Contributor

Part of #37361

Problem / Motivation

Goal: A goal-conductor Bot parks a finding that its goal's "Done when" does not need, instead of turning it into a new work item, so the work can end.

In #37361 a Bot with one goal ran for six days and never finished. A review found something, the finding became a work item, the item became a merge request, and that merge request got a review that found more. Open issues went from 46 to 108 while the goal still read "beta fixed".

Why it matters

Every owner who gives a Bot a goal can hit this loop: the plan reviewer runs every round, and the skill told the conductor that each fix the reviewer finds "becomes a new item if you take it". Nothing in the skill said when not to take it, so the work grows faster than it closes.

Not a goal

What changed (motivation → approach → change)

The goal-conductor skill now tells the conductor to park any finding (from the plan reviewer, a worker's report or its own patrol) that no "Done when" condition of the goal needs. A parked finding goes on a new Parked: line of the goal text, with where it came from, and does not become an item, a seed or a decide. Each round report lists the findings parked that round. Only the owner moves a parked finding in: the conductor then adds a "Done when" condition for it and creates its item.

The goal text keeps Changed as its last part, because the Board's Latest change line reads Changed to the end of the goal text. The conductor's charter (_LEDGER_CONDUCTOR_RULES["goal_plan"] in src/kiro_crew/agent_parts/spec_prompts.py, which the skill points to for the goal text) and the team-lead skill now list the same five parts, so the prompt and the skill agree. The plan-review RFC's "What stays" line now says the same rule.

Backwards compatibility

Compatible: this changes skill and prompt instructions only; goal texts without a Parked: line still read the same on the Board.

Removes nothing: the conductor still creates items for findings a "Done when" condition needs; the change only adds a rule for the others.

Tests

test/test_goal_conductor_parks_findings.py pins the wording in three sections of the skill: the goal text has a Parked part before Changed (Round 0), the park rule and the reviewer line (Patrol), and the parked list in the round report (Close the round). A fourth test pins that the charter lists Parked before Changed and that the team-lead skill names the same five parts. Reverting any one changed hunk of the two skills or the charter on its own turns one test red.

The conductor prompt text changed, so test/fixtures/crewmate_prompts/ledger.golden.txt, the _CONDUCTOR_SYSTEM_PROMPT shape in test/test_agent_refactor_contracts.py and the kirocrew-conductor.json / kirocrew-ledger-conductor.json digests in test/test_agent_refactor_spec_bytes.py are re-pinned. Only those two spec files' digests moved; every other spec, the audit events and the state sidecar match as before.

Proof: PROVEN test/test_agent_refactor_contracts.py::test_every_pre_split_name_resolves_with_its_pre_split_shape, test/test_agent_refactor_spec_bytes.py::test_every_written_spec_matches_the_pre_split_bytes[clean_over_customized], test/test_agent_refactor_spec_bytes.py::test_every_written_spec_matches_the_pre_split_bytes[customized], test/test_agent_refactor_spec_bytes.py::test_every_written_spec_matches_the_pre_split_bytes[forks], test/test_agent_refactor_spec_bytes.py::test_every_written_spec_matches_the_pre_split_bytes[fresh] (head 38a9cbc)

Determinism: the file passed 3 repeated runs and a run in reversed test order. It reads one shipped file and has no shared state.

Manual verification

N/A — the change is skill and prompt text; the tests pin the wording, and the 2767 tests that read the conductor skills and prompts pass with it.

Related Issues

Part of #37361

Sibling sweep

Swept: git grep -n -i "becomes a new item|new item if|finding.*new item" -- src/kiro_crew docs
Sibling: docs/request-for-change/rfc-conductor-plan-review-hourly-check.md:137 -- changed here
Sibling: src/kiro_crew/builtin_skills/goal-conductor/SKILL.md:678 -- changed here
Swept: git grep -n -i -E "four parts|Changed: a time and why|Done when, Plan, Changed" -- src test
Sibling: src/kiro_crew/agent_parts/spec_prompts.py:140 -- changed here
Sibling: src/kiro_crew/builtin_skills/team-lead/SKILL.md:43 -- changed here
Sibling: test/fixtures/crewmate_prompts/ledger.golden.txt:127 -- changed here

Pattern harvest

Not generalizable: the defect is one missing rule in one skill's prose about when a finding becomes work, not a code pattern a rule can catch.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners November 15, 2026 17:17
@buluoray
buluoray enabled auto-merge (squash) November 15, 2026 17:18
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 15, 2026
@github-actions

github-actions Bot commented Nov 15, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3 touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Does not block merge.

@github-actions

github-actions Bot commented Nov 15, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3 — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

First-Principles-Verdict: PASS

Nothing blocks. The fix adds one missing rule, in the prose that let every finding become an item, which is where the loop came from. Its siblings in the charter, the team-lead skill and the RFC all change in step.

Notes

What this change ships

Inventory (6 items) — 5 justified

Intent: stop a goal Bot from turning every finding into a new work item, so its goal can finish. This is a FIX.

  1. The conductor no longer makes an item for a finding that no "Done when" condition needs. — justified
  2. Parked findings go on a new Parked: line of the goal text, kept before Changed. — inherited
  3. Each round report lists that round's parked findings, or "none parked". — justified
  4. Only the owner moves a parked finding in, and a "Done when" condition is added first. — justified
  5. The charter prompt and the team-lead skill list five goal parts instead of four. — justified
  6. The accepted plan-review RFC's "What stays" line repeats the same rule. — justified

[FIRST-PRINCIPLES-REVIEWED] 38a9cbc

Description read

[DESCRIPTION-READ] 1c33b79d364b42edf43d956e8c264f63735ba70eeccccc3a4fd6da816f916d5e

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

github-actions Bot commented Nov 15, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: this is prompt text only, the new part sits between Plan and Changed, and both Board parsers (goalDoneWhen stops at Plan:, latestChange reads Changed: to the end) still read the goal correctly.

Notes

[DESIGN-REVIEWED] 38a9cbc

Description read

[DESCRIPTION-READ] fe44ea87538d9c5fc32f874c80bed5c12cb906489a610d1e7a245437406f2ffc

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

github-actions Bot commented Nov 15, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 38a9cbc

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 15, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 38a9cbc

Verdict parsed from the review's SHA-scoped output markers for commit 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 38a9cbc8df965fc54d89c6f3a2a03a536f5268f3 false-positive: <reason, 20 to 500 characters>

@buluoray
buluoray force-pushed the crew/slack/park-out-of-scope-findings branch from c1eb7d2 to 38a9cbc Compare November 15, 2026 17:45
@buluoray

Copy link
Copy Markdown
Contributor Author

span=1c12c52038a7

fixed in 38a9cbc: the charter rule _LEDGER_CONDUCTOR_RULES["goal_plan"] in src/kiro_crew/agent_parts/spec_prompts.py now lists five parts (Parked before Changed), and team-lead/SKILL.md names the same five parts, so the prompt and the skill agree.
test/test_goal_conductor_parks_findings.py::test_charter_and_team_lead_list_the_same_five_parts pins both; reverting either file turns it red. The prompt goldens are re-pinned.
self-added: no

@KiroCrewCaptain

Copy link
Copy Markdown
Collaborator

Code change approver recommendation: Approve

Why: the decider estimates a 10% chance that this change introduces a defect, within the 12% limit for approving on its own, and every check passes.

Prompt- and skill-only change. It adds a rule that sends findings no "Done when" condition needs to a Parked: part of the goal text, placed before Changed. The charter, the team-lead skill, the RFC, the golden prompt fixture and the spec digests all change to match. The Board parsers still read the goal correctly: latestChange reads Changed to the end, and Changed stays last. Workers never see the goal text, because work_brief returns only the worker's own item, so no worker text reaches a worker's instructions. The parity test's anchor phrases are still in the skill. The new test pins the wording, which is how this repo tests prompt changes.

An automated recommendation, not a review: a maintainer still decides. It approves on its own only when the estimated chance of a defect is at most 12% and the change has at most 400 changed lines. Decider v3c (217fe607) · commit 38a9cbc8df · 141 changed lines. If this recommendation is wrong, reply here: replies are how the approver is evaluated.

@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Nov 15, 2026
@KiroCrewCaptain

Copy link
Copy Markdown
Collaborator

This adds a new concept, so it needs a design sign-off from a maintainer before it can merge. A maintainer will post the decision here.

The review found nothing that blocks this head. Only prompt and skill text changes: the goal-conductor and team-lead skills, the goal_plan charter string, and one line of the RFC. The new tests in test/test_goal_conductor_parks_findings.py fail at the merge base and pass at this head. Reverting any single changed hunk of the skills or the charter turns its own test red. One strength: Changed stays the last part of the goal text, and a test pins that order, so the Board's latestChange parser still reads it.

Optional:

  • website/src/pages/chat/command-center/ConductorModeCrewPanel.tsx:242: the goalDoneWhen lookahead stops at plan: and changed: only. Adding parked would keep Parked entries out of the Done when line when a goal has no Plan part.
  • src/kiro_crew/builtin_skills/goal-conductor/SKILL.md:850: the "Goal changes mid-flight" rewrite still names only the Plan and Changed lines. An owner moves a parked finding in through that step, so naming Parked there too keeps the other parked entries from dropping out.
  • src/kiro_crew/agent_parts/spec_prompts.py:146: the Parked line has no size rule inside the 2000-character goal text. A short clause on what to do when it grows would help long runs.

This PR and #37652 re-pin the same conductor prompt and spec digests. Whichever merges second needs a rebase and a fresh re-pin.

@bolichen97 bolichen97 left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approving 38a9cbc8df.

  • The rule is consistent across all four places: spec_prompts.py (goal text now five parts, Changed last), the goal-conductor Patrol and plan-reviewer steps, the team-lead skill, and the RFC. A finding becomes an item only when a Done when condition needs it; everything else goes on Parked: until the owner moves it in.
  • Keeping Changed last matters because the Board reads it to the end of the text; the prompt and the skill both say so.
  • Small note, not blocking: Parked shares the 2000-character goal budget, so a long Parked line could crowd out Plan. One short entry each, as written, should keep that in check.
  • Ran test_goal_conductor_parks_findings.py, test_agent_refactor_contracts.py and test_agent_refactor_spec_bytes.py locally: 80 passed. CI is green on this head.

AI-assisted, sent by Bolin Review bot

@buluoray
buluoray merged commit 56f3e84 into main Nov 15, 2026
101 of 106 checks passed
@buluoray
buluoray deleted the crew/slack/park-out-of-scope-findings branch November 15, 2026 19:12
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Nov 15, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants