Skip to content

docs(rfc): a conductor drops its chat after a turn that closes an item or fills a free seat - #22088

Merged
chenmingwei23 merged 1 commit into
mainfrom
docs/rfc-conductor-rolling-reset
Oct 19, 2026
Merged

chenmingwei23 merged 1 commit into
mainfrom
docs/rfc-conductor-rolling-reset

Conversation

@iamwhatever

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Put the proposed conductor reset rule on main as a draft RFC, so its owner can accept it before the prompt and skill change that follows.

A goal conductor drops its chat only at a round close. Its own skill refills a seat as soon as an item lands, so under a full queue a round never closes and the reset never comes. On one operator's conductor DM, 10 patrol turns closed an item or filled a free seat in the 23 hours to 2026-10-19 05:00 UTC, and none of them reset.

Why it matters

Every patrol wake re-sends the whole chat. In that DM a request carried 450K to 550K tokens. Measured on the same host, a request after a reset was about 2 to 5 s faster and cost about 75% fewer credits. The wakes come 900 s apart, longer than the prompt cache lives, so each one pays for the whole chat.

The fix changes what the kirocrew-conductor agent and the goal-conductor skill do by default. The First Principles lane reads that decision from an RFC on the base branch, so the RFC lands first.

Not a goal

  • Changing the prompt, the skill or any code. The implementation PR does that after the RFC is accepted.
  • Accepting the RFC. It stays draft until its owner decides.
  • Editing rfc-conductor-round-reset.md. An implemented RFC is amended in its own document.
  • Any change to KAS compaction or session.autocompact_pct (KAS compaction: decide Crew's threshold and drop the dead refusal arm #18931 keeps the engine's thresholds).

What changed (motivation → approach → change)

The goal conductor (kirocrew-conductor) resets its chat only when "every item in the round has landed", and the goal-conductor skill's concurrency cap makes sure that never happens. The new RFC moves the reset point from the round to the turn.

File What it adds
docs/request-for-change/rfc-conductor-rolling-reset.md A draft RFC. A patrol turn that closed an item, or dispatched one into a free seat, ends with session_ledger_record and then reset_conversation, once every item it touched is at rest and no question is unanswered.
docs/request-for-change/README.md Its index row and audit note.

"Mid-round" then means partway through the turn's own steps, not "other items are open". The RFC keeps the old non-goals: no timer, no reset forced by the gateway, and no change to _refuse_unvouched_wake_reset. Its section 4 lists what survives of rfc-conductor-round-reset.md.

Backwards compatibility

Compatible: documentation only; nothing reads an RFC at runtime.

Removes nothing: the diff adds one document and one index row.

Tests

N/A — documentation only. python3 scripts/docs_lint.py passes on this branch.

Manual verification

N/A — documentation only. The figures in the RFC were read from the conductor DM's transcript and the round-1 latency research on the same host, as section 1 says.

Related Issues

Part of #22082

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

@iamwhatever
iamwhatever requested review from a team and KiroCrewCaptain as code owners October 19, 2026 05:49
@github-actions

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 7dc4308efaeddeee1a3590d4912440dfb601943e touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Advisory — does not block merge.

@github-actions

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ⏭️ skipped

Revision 7dc4308efaeddeee1a3590d4912440dfb601943e ships no reviewable capability (docs, tests or generated files only), so there is nothing to inventory. Advisory — does not block merge.

@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Oct 19, 2026
@github-actions

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 7dc4308efaeddeee1a3590d4912440dfb601943e — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Design-Verdict: PASS

Before merge, check that the RFC's reset trigger ("closed an item or filled a free seat") can't fire on a turn that only re-patrolled. If it can, quiet cycles start resetting too.

[DESIGN-REVIEWED] 7dc4308

Description read

[DESCRIPTION-READ] b451bba2560e4630bc3b644228346e4869ffa68fb1f225ec8652d4b73b37f246

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

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 7dc4308efaeddeee1a3590d4912440dfb601943e — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 7dc4308

Verdict parsed from the review's SHA-scoped output markers for commit 7dc4308efaeddeee1a3590d4912440dfb601943e.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 7dc4308efaeddeee1a3590d4912440dfb601943e: <one-sentence reason>

@github-actions

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 7dc4308efaeddeee1a3590d4912440dfb601943e and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 7dc4308

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 7dc4308efaeddeee1a3590d4912440dfb601943e: <one-sentence reason>

@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.

Looks good as a draft RFC. This needs a design sign-off from a maintainer, so I am leaving a comment and not an approval.

Head reviewed: 7dc4308. Bots read: Design PASS, First Principles skipped (docs only), UX skipped, Opus no blocking findings, GPT no blocking findings. Readiness was still checking when I read it.

What I verified against current main:

  • The three skill quotes in section 1 are verbatim in the goal-conductor SKILL.md: "dispatch the next item when one lands" (Concurrency cap), "When every item in the round has landed" (Close the round), and "the round is still running" (Never reset when).
  • _CONDUCTOR_SYSTEM_PROMPT in agent.py still says to reset once the next round is dispatched and never mid-round, so the contradiction the RFC describes is real on main.
  • _refuse_unvouched_wake_reset exists in session_directive_apply.py, test_conductor_agent.py exists for the text pin, and work_ledger_record action=decide after session_send is already the skill's documented answer path.
  • rfc-conductor-round-reset.md is implemented on main and is not edited here. The amendment lives in its own document, which matches how other amendments in the index are recorded.
  • The README change adds one index row and appends one audit sentence to the long audit paragraph. Nothing else in that paragraph changed.

On the Design lane's note: the trigger in section 3.1 requires the turn to close an item or dispatch one into a free seat, so a quiet re-patrol cannot fire it. I see no gap there.

One question for whoever accepts this: the Status line names the author as the owner of the decision. The linked issue is tiered as a change to existing behaviour, so please record the acceptance from a maintainer in section 8 or the Status line before the implementation PR opens, and say whose decision it is.

Other open RFC PRs (#21646, #21613, #19437) also edit the RFC index. They do not overlap in content. Whichever merges later needs a rebase of that one paragraph.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • The reset trigger cannot fire on a turn that only re-patrolled — rebutted, no change

Section 3.1 makes the trigger a patrol turn that closed an item or dispatched one into a free seat. A quiet cycle reads the ledger and does neither, so it never resets.
Section 7 rejects "reset after every patrol turn" for exactly this reason: it would also reset on quiet cycles.
The implementation PR pins that trigger phrase on both the prompt and the skill in test/test_conductor_agent.py, so a later edit cannot widen it to quiet cycles without a red test.

@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 Oct 19, 2026
@chenmingwei23
chenmingwei23 merged commit 7ab7df6 into main Oct 19, 2026
103 of 104 checks passed
@chenmingwei23
chenmingwei23 deleted the docs/rfc-conductor-rolling-reset branch October 19, 2026 14:09
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 19, 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