Skip to content

docs(rfc): conductor drops its chat context at a round close - #18097

Merged
iamwhatever merged 1 commit into
mainfrom
docs/rfc-conductor-round-reset
Oct 8, 2026
Merged

iamwhatever merged 1 commit into
mainfrom
docs/rfc-conductor-round-reset

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Oct 8, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Record the decision that a goal conductor may drop its own chat context at a round close, from its own patrol wake, so the implementation can land.

The implementation PR changes who may call reset_conversation. Its First Principles lane reads the decision off the base branch, so the RFC lands first.

Why it matters

A conductor that patrols for days re-sends its whole chat on every wake, even when nothing changed. Its state already lives in the work ledger and its session ledger, so the chat is cost with no use.

Not a goal

  • Any code change. That is the implementation PR.
  • Letting a wake run set_project or chat_tag.

What changed (motivation → approach → change)

Adds docs/request-for-change/rfc-conductor-round-reset.md (status in-progress): grant reset_conversation to the conductor agent only, admit it from a wake only when the wake is the slot's own live self-armed loop and nothing is pending, log it at WARNING, and reset only after the ledger write at a round close. Adds its row to docs/request-for-change/README.md. Implementation: #18113.

Backwards compatibility

Compatible: documentation only.

Removes nothing: adds one document and one index row.

Tests

N/A — docs only; scripts/docs-lint.sh and test/test_docs_lint_fact_checks.py pass.

Manual verification

N/A — docs only.

Related Issues

Part of #18093

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title
  • 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 8, 2026 08:45
@iamwhatever
iamwhatever requested a review from buluoray October 8, 2026 08:45
@github-actions github-actions Bot added the readiness: action required A blocking check or review needs attention label Oct 8, 2026
@iamwhatever
iamwhatever force-pushed the docs/rfc-conductor-round-reset branch from 16c717e to fc2c571 Compare October 8, 2026 09:48
@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: action required A blocking check or review needs attention labels Oct 8, 2026
@github-actions

github-actions Bot commented Oct 8, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 106433b5cb043702e2fdc853a689627eda937af0 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

github-actions Bot commented Oct 8, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 106433b5cb043702e2fdc853a689627eda937af0 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Design-Verdict: PASS

Before merging, check that writing self-arm records for ordinary dashboard slots (§3 "The trust record") leaves every existing is_recorded_self_arm reader unchanged.

[DESIGN-REVIEWED] 106433b

Description read

[DESCRIPTION-READ] 85ba1784fd1fe2933abe9576a6c76cde90b9d1fe6419f9aaeca1b29794bc0e2c

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 Oct 8, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ⏭️ skipped

Revision 106433b5cb043702e2fdc853a689627eda937af0 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 commented Oct 8, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 106433b5cb043702e2fdc853a689627eda937af0 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 106433b

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 106433b5cb043702e2fdc853a689627eda937af0: <one-sentence reason>

@github-actions

github-actions Bot commented Oct 8, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 106433b5cb043702e2fdc853a689627eda937af0 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 106433b

Verdict parsed from the review's SHA-scoped output markers for commit 106433b5cb043702e2fdc853a689627eda937af0.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 106433b5cb043702e2fdc853a689627eda937af0: <one-sentence reason>

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention and removed readiness: checking Automated validation is still running labels Oct 8, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Security rests on unforgeability span=97bca7b37e75 — fixed in the next push

Verified: trust is in _CREW_SANDBOX_VISIBLE_LEAVES (src/kiro_crew/sandbox.py), so a sandboxed shell could write the record.
Section 5 now says so and rests the case on bounded harm: conductor agent only, own slot only, memory only; transcript and ledgers untouched.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Security rests on unforgeability span=f4ec36b1828c — fixed in the next push

Verified: trust is in _CREW_SANDBOX_VISIBLE_LEAVES (src/kiro_crew/sandbox.py), so a sandboxed shell could write the record.
Section 5 now says so and rests the case on bounded harm: conductor agent only, own slot only, memory only; transcript and ledgers untouched.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Security rests on unforgeability span=04f3091a2a7e — fixed in the next push

Verified: trust is in _CREW_SANDBOX_VISIBLE_LEAVES (src/kiro_crew/sandbox.py), so a sandboxed shell could write the record.
Section 5 now says so and rests the case on bounded harm: conductor agent only, own slot only, memory only; transcript and ledgers untouched.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Security rests on unforgeability span=204e7c5d2e4a — fixed in the next push

Verified: trust is in _CREW_SANDBOX_VISIBLE_LEAVES (src/kiro_crew/sandbox.py), so a sandboxed shell could write the record.
Section 5 now says so and rests the case on bounded harm: conductor agent only, own slot only, memory only; transcript and ledgers untouched.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Security rests on unforgeability span=6ff629be7f75 — fixed in the next push

Verified: trust is in _CREW_SANDBOX_VISIBLE_LEAVES (src/kiro_crew/sandbox.py), so a sandboxed shell could write the record.
Section 5 now says so and rests the case on bounded harm: conductor agent only, own slot only, memory only; transcript and ledgers untouched.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Security rests on unforgeability span=eac1b136813c — fixed in the next push

Verified: trust is in _CREW_SANDBOX_VISIBLE_LEAVES (src/kiro_crew/sandbox.py), so a sandboxed shell could write the record.
Section 5 now says so and rests the case on bounded harm: conductor agent only, own slot only, memory only; transcript and ledgers untouched.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Session-title changes exceed the conductor RFC's declared scope span=2f6082500a24 — rebutted

Not in this PR: docs/feature-map/README.md comes from #18016, already on main; this PR's own diff is the RFC and its index row only, as the adjudicator notes.
The branch is rebased onto current main in the next push, so the stale merge range is gone.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • Grant and unforgeability claims overstated span=d34d4444727d — fixed in the next push

The grant only auto-approves; section 3 now says the gate checks the slot's agent (implemented in #18113).
Section 5 no longer claims the record is unforgeable; it names the sandbox-visible trust leaf and rests on bounded harm.

@iamwhatever
iamwhatever force-pushed the docs/rfc-conductor-round-reset branch from fc2c571 to 106433b Compare October 8, 2026 10:26
@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: action required A blocking check or review needs attention labels Oct 8, 2026
@iamwhatever
iamwhatever enabled auto-merge (squash) October 8, 2026 11:09
@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 8, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Self-review (crew-pr-reviewer, read-only): HOLD for a maintainer / security owner

This RFC records the decision to let kirocrew-conductor call reset_conversation from its own self-armed patrol wake at a round close, so a days-long patrol stops re-sending a chat whose state already lives in the work and session ledgers. As a decision document it is sound: the five admission checks (conductor agent, named loop id, current active loop, self-arm trust record, nothing pending) are well bounded, and section 5 now honestly says the trust record is forgeable from an in-sandbox shell (trust is a visible sandbox leaf) and rests the case on bounded harm instead. The earlier Design/GPT/Opus findings on fc2c571 are each answered and fixed in the current head 106433b, and every lane on that head is PASS or skipped, with base main and all checks green. I tried to break the Design lane's open question: on origin/main the only reader of is_recorded_self_arm is GatewayOrchestrator._dashboard_mode_admits in src/kiro_crew/slack/gateway.py, which returns early for any mode other than crew/member, so writing records for ordinary dashboard slots does not change any existing reader. The one leftover gap is a slot whose mode changes later under the same slot_key, which the implementation PR (#18113) should pin. HOLD only because this is an RFC that narrows a human-only gate (reset_conversation admitted from an unattended wake, plus new trust-record writes). A person needs to sign off on that permission change. Otherwise the document is ready. — crew-pr-reviewer

@buluoray buluoray 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.

Approve at 106433b5cb043702e2fdc853a689627eda937af0 (docs-only RFC).

I checked the RFC's claims about current code against source: the directive apply path (src/kiro_crew/dashboard/session_directive_apply.py:74,299), the self-arm authorization gate (src/kiro_crew/autonudge_authz.py:1063-1075,1256-1259), the loop mutation path (src/kiro_crew/autonudge_service/mutations.py:1245-1276) and the sandbox reference (src/kiro_crew/sandbox.py:745-755) match what the RFC describes. scripts/docs-lint.sh passes.

Non-blocking follow-up for the implementation PR: the RFC says test/test_autonudge_member_self_arm.py already pins that a wake cannot call reset_conversation. That file only exercises set_project; reset_conversation appears once, in a docstring (:1430). Please add the actual test when this is implemented, and soften the sentence here so a reader does not assume it is already covered.

CI: 85 success, 13 skipped, 0 failing. No tests run (docs-only).

@iamwhatever
iamwhatever merged commit a8f6c5f into main Oct 8, 2026
102 checks passed
@iamwhatever
iamwhatever deleted the docs/rfc-conductor-round-reset branch October 8, 2026 16:20
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 8, 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.

2 participants