Skip to content

docs(rfc): conductor reads each open worker's new transcript lines on patrol and steers drift - #36360

Merged
KiroCrewCaptain merged 1 commit into
mainfrom
rfc-conductor-drift-check
Nov 13, 2026
Merged

KiroCrewCaptain merged 1 commit into
mainfrom
rfc-conductor-drift-check

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Nov 13, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Record the owner's decision that the goal conductor checks each open worker for drift on every patrol turn, so the skill change in #36302 traces to an accepted RFC.

#36302 changes the goal conductor's default patrol: on every patrol turn it reads each open worker's new transcript lines from a stored cursor and steers drift. First Principles blocked it (span 717730afd96c) because that is a product-shape change and rfc-conductor-work-ledger.md replaced the transcript-reading patrol. This document records the decision on the base branch.

Why it matters

Without it the conductor only sees each worker's own claims, so a worker building the wrong thing is caught at acceptance, after the whole item's run is spent. The owner asked for the check.

Not a goal

What changed (motivation → approach → change)

Product-shape change needs a record on the base → a short RFC, docs only → docs/request-for-change/rfc-conductor-drift-check.md (status accepted, takes effect on merge) and its row in docs/request-for-change/README.md.

The RFC states three things:

  1. The drift read is neither a liveness check nor a verdict; it only decides whether to send a steer. It is the "conversation" rfc-conductor-work-ledger.md kept (line 722).
  2. Cost is bounded: since cursor (an unmoved transcript returns no rows), limit: 10, at most two reads (20 rows) per open item per patrol turn, on turns the patrol already takes. Remote-dispatched items are skipped on a patrol wake, since their reads and sends need an owner turn.
  3. Why a monitor judge cannot replace it: it screens QUIET ticks only (_monitor_tick_is_quiet in autonudge_service/gate.py), sees no item title or acceptance (two 500-char criteria, 8 targets), cannot steer, and its targets change on every dispatch.

It amends rfc-conductor-work-ledger.md. Every code reference was read at 27e9359419.

Backwards compatibility

Compatible: docs only.

Removes nothing: adds one RFC and one index row.

Tests

Proof: not provable -- docs or config only

Manual verification

N/A — docs only; every cited constant and line was re-read at 27e9359419.

Related Issues

Part of #36299

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

@github-actions

github-actions Bot commented Nov 13, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ⏭️ skipped

Revision b792440dcd7da3f4ca11c6f49f22e2ad3da88463 ships no reviewable capability (docs, tests or generated files only), so there is nothing to inventory. Does not block merge.

@github-actions

github-actions Bot commented Nov 13, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision b792440dcd7da3f4ca11c6f49f22e2ad3da88463 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 13, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of b792440dcd7da3f4ca11c6f49f22e2ad3da88463 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: the RFC is docs-only and records an owner-requested patrol change with a bounded cost. The code references cited in it check out.

Notes

  • §6 says session_read_message is "auto-approved for the conductor", but rfc-conductor-work-ledger.md line 722 says that path "keeps its human approval prompt". Pick one and state it. If the prompt is still there, a read on every patrol turn means up to 12 approval prompts per turn.
  • §6 says "Sessions with no stored cursor read without since once". §2.2 counts its reads assuming a cursor already exists. Say whether the first read counts toward the at-most-two-reads limit.

[DESIGN-REVIEWED] b792440

Description read

[DESCRIPTION-READ] 26255c94045ffe17b942b4d94fef5942e7fd3642fe78a1e9803accf1f970fb44

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 13, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of b792440dcd7da3f4ca11c6f49f22e2ad3da88463 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] b792440

False positive or not applicable? A repository writer can comment:
/ai-review override gpt b792440dcd7da3f4ca11c6f49f22e2ad3da88463 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 13, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed b792440dcd7da3f4ca11c6f49f22e2ad3da88463 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] b792440

Verdict parsed from the review's SHA-scoped output markers for commit b792440dcd7da3f4ca11c6f49f22e2ad3da88463.

False positive or not applicable? A repository writer can comment:
/ai-review override fable b792440dcd7da3f4ca11c6f49f22e2ad3da88463 false-positive: <reason, 20 to 500 characters>

@KiroCrewCaptain

KiroCrewCaptain commented Nov 13, 2026 •

Copy link
Copy Markdown
Collaborator

Code change approver recommendation: Approve

Why: the decider estimates a 7% chance that this change introduces a defect, within the 12% limit for approving on its own, and every check passes.

This PR only changes docs: one new accepted RFC plus its index row. The RFC records the owner's decision that the goal conductor reads each open local worker's new transcript lines on every patrol turn, bounded by a since cursor, limit: 10 and at most two reads per item, and steers when a worker drifts. I checked every code reference it cites and each one is accurate: _MAX_QUIET_STREAK = 10 and the QUIET branch of _monitor_tick_is_quiet in gate.py, MAX_JUDGE_TARGETS = 8 and MAX_JUDGE_CRITERION_CHARS = 500, MAX_READ_CONTENT_CHARS = 4000, cursor_unavailable and next_since in session_status.py, the skill's step 5 wording, and the shared read_message_detail rule. It has no trust problem. session_read_message is in the conductor's dashboard grants (spec_grants.py _CONDUCTOR_DASHBOARD_GRANTS), so the RFC is right to call it auto-approved. The steer's session_send into the conductor's own child runs without a prompt under agent.conductor_own_child_verbs. Remote items are skipped on patrol wakes, which matches the existing remote-dispatch rule. Liveness and acceptance are left unchanged, as the PR's non-goals say. Acceptance on the owner's request, taking effect

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 b792440dcd · 155 changed lines. If this recommendation is wrong, reply here: replies are how the approver is evaluated.

@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 Nov 13, 2026
@iamwhatever
iamwhatever force-pushed the rfc-conductor-drift-check branch from 740ece9 to b792440 Compare November 13, 2026 05:16
@github-actions github-actions Bot removed the readiness: action required A blocking check or review needs attention label Nov 13, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • fixed span=bc2eb9533565 in b792440

The cost bound now matches the procedure: at most two reads (the since read, plus the newest-10 read only on overflow), so 20 rows per item and 12 calls / 120 rows per turn at the default cap of 6.
The second point in the summary is also fixed: remote-dispatched items are skipped on a patrol wake, because session_read_message and session_send with crew= need an owner turn (goal-conductor remote-dispatch section); their drift is checked in the next owner turn.
Source Gates line citations (file:line) replaced with symbol names; scripts/docs-lint.sh passes locally.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Nov 13, 2026

@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.

Reviewed the whole diff at b792440. It adds one RFC document and its README row, and changes no code. This is a design brief, not an approval.

What it decides: on every patrol turn of the goal conductor, floor turn included, the conductor reads each open local worker's new transcript lines (session_read_message, since the stored cursor, limit 10), compares them with the item's title, acceptance and goal, and sends a steer correction through session_send if the worker has drifted. It records the correction with work_ledger_record and keeps the cursor in its session ledger's next. A remote-dispatched item is skipped on a patrol wake and checked on the next owner turn.

Pros:

  • It closes a real gap: today the conductor sees only each worker's own work_report claims, so a worker that widens scope looks on track until its done fails acceptance, after the item's run is spent.
  • It adds no turns, tools, fields or stored formats. It rides on wakes that already happen and on reads the conductor is already granted.
  • The cost is bounded and written down: at most two reads per item per turn, 20 rows per item, and at the default cap of 6 open items 12 calls and 120 rows, each row capped at 4,000 characters.
  • It keeps the earlier decisions intact: liveness stays with the stale and orphaned flags, acceptance stays with accept_eval, and a transcript never passes or fails an item.
  • The read goes through the existing session read path, which authorizes the target and redacts each row, so the conductor reads only what it could read by hand and nothing leaves its own turn.
  • The monitor judge is considered and rejected for sound reasons (it screens quiet ticks only, its criteria are capped at 500 characters, it cannot steer, and its targets move with every dispatch).

Cons and risks:

  • Drift is a model judgement. A false steer sends a worker a correction it did not need, and a missed drift still waits for acceptance. The document says on-track means silence, which keeps the false-steer cost low, but it has no measure of either error rate.
  • Remote-dispatched items get no drift check on a patrol wake, so the gap stays open for them until an owner turn.
  • Each patrol turn now carries up to 120 more rows of context for a full crew. That is bounded, but it is context spent on every wake, including the quiet floor turn.

Long-term debt: low. It is a skill and prompt change with no new schema. The one thing to watch is the per-item cursor kept in the session ledger's next, which is free-form text the skill must keep writing in the same shape, so a later change to that field should name it.

My stance: the direction is right and small, and I have no objection to it. The sign-off on this RFC stays with the maintainers. The implementing change is a separate pull request, and I would want its parity test and agent-spec goldens to move as this document says.

@KiroCrewCaptain
KiroCrewCaptain enabled auto-merge (squash) November 13, 2026 07:27

@KiroCrewCaptain KiroCrewCaptain left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Approving. The author is the repository owner, and this RFC records the owner's own decision, so the standing sign-off for design docs from team members applies.

Review result on this head: nothing blocks. The PR adds docs only: one new RFC and one index row. The cited code checks out at the PR head and at 27e9359419:

  • MAX_READ_CONTENT_CHARS, MAX_JUDGE_TARGETS and MAX_JUDGE_CRITERION_CHARS have the values the RFC states.
  • DEFAULT_GOAL_CONCURRENCY_CAP matches, and so do the cursor_unavailable and next_since behaviour of the read and the QUIET-only branch of _monitor_tick_is_quiet.

Done well: §3 rejects the monitor judge with reasons you can check in the code, and the cost bound (12 calls and 120 rows per turn at the default cap) is spelled out.

For the security review:

  • No boundary moves in this PR. Every read still goes through authorize_target, and each row goes through redact_and_truncate.
  • session_read_message is already in _CONDUCTOR_DASHBOARD_GRANTS.
  • The drift steer is a session_send. It skips the prompt only for the conductor's own child sessions, and only while agent.conductor_own_child_verbs is on (the default). Otherwise it prompts.

Optional:

  • §1 and §2.2 say a floor patrol comes after _MAX_QUIET_STREAK (10) quiet ticks. When no worker has reported since the last delivered turn, which is the silent-drift case this RFC targets, _quiet_floor returns _IDLE_LEDGER_QUIET_FLOOR (40 ticks). Consider stating the real cadence.
  • §2.1 quotes rfc-conductor-work-ledger.md line 722 with an ellipsis that drops "that path keeps its human approval prompt", and §6 says the opposite. One sentence saying this RFC amends that clause would help. §6 could also say the step adds steers as well as reads, and name the approval path above.
  • #36302 at its current head does not yet carry the remote-item skip or the at-most-two-reads wording that §5 lists as exit criteria.

@KiroCrewCaptain
KiroCrewCaptain merged commit 72b62cf into main Nov 13, 2026
100 of 101 checks passed
@KiroCrewCaptain
KiroCrewCaptain deleted the rfc-conductor-drift-check branch November 13, 2026 07:28
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Nov 13, 2026

@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.

Reviewed the whole diff at b792440. It adds one RFC document and its README row, and changes no code. The direction matches the repository owner's ask, and it is small and low in long-term debt: on every patrol turn the conductor reads each open local worker's new transcript lines with a stored cursor, a limit of 10 and at most two reads per item, and steers only when the worker has drifted. Liveness and acceptance stay where they are.

The one thing to watch in the implementation pull request is the per-item cursor kept in the session ledger's free-text next. The skill must keep writing it in the same shape, so the change should name that field and its format.

The earlier failure of the Sensitive Change Review helper on this head was followed by a passing run of the same check, and everything else is green. Auto-merge is already set by someone else, so I leave it as it is.

Direction signed by maintainer (bolichen97).

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