Skip to content

docs(rfc): record legacy-loop PR reads, kept agent stops, declared waits - #22165

Merged
iamwhatever merged 2 commits into
mainfrom
docs/rfc-legacy-loop-reads-stops-waits
Nov 20, 2026
Merged

iamwhatever merged 2 commits into
mainfrom
docs/rfc-legacy-loop-reads-stops-waits

Conversation

@kyleseaman

@kyleseaman kyleseaman commented Oct 19, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Record, as an RFC on main, Kyle's decisions for how legacy monitoring loops read their pull request while held or ungated, keep the agent's own stop, and wait for a person, so the implementing stack is built on a recorded decision.

The stack #21377 → #21621 → #21622 changes what a first-class loop does by default, and each of those PRs rewrote the implemented RFC it contradicted. The First Principles lane correctly reads that as a proposal, not a decision, and blocks all three. Kyle asked for these behaviours and asked that they be recorded in an RFC rather than by an override.

Why it matters

Without a decision on the base, the three PRs cannot pass review, and the next reader of the four implemented RFCs would find them contradicted by shipped code with no record of who decided otherwise.

Not a goal

  • Any code change. This PR is docs only; the behaviour lands in the three PRs above.
  • Editing the four implemented RFCs. This document amends them in its own text, as rfc-wake-on-stop-signal and rfc-fold-recorded-edit-cards do.

What changed (motivation → approach → change)

  • docs/request-for-change/rfc-legacy-loop-reads-stops-waits.md (new, partial): four decisions, each naming the base text it supersedes or amends. Re-audited 2026-11-09 at ad553518b0: § 2.1 for a loop held for an approval and § 2.2 shipped in fix(autonudge): read a legacy loop's pull request between cycles and while held #21377 (merged 2026-11-07); § 2.1 for a declared wait, § 2.3 and § 2.4 are open in fix(autonudge): keep a legacy loop's row when the agent stops it #21621 and feat(autonudge): let a legacy loop declare it is waiting on a person #21622.
    • § 2.1: a loop held for a person that names one pull request reads it every 5 minutes, settles when it merges or closes, and is rescued by the reconciler. Supersedes rfc-goal-loop-approval-hold § 3 While held ("A held tick fires nothing and arms no timer. The reconciler skips a held loop…") for that loop, and narrows its § 4 "A hold nobody ends".
    • § 2.2: an ungated loop naming one pull request reads it between cycles and wakes early only on a new merge conflict, never on BEHIND.
    • § 2.3: autonudge_stop / monitor_stop keep a legacy row as agent_stop with the agent's reason, resumable and displaced by the next monitor_start. Supersedes rfc-token-efficient-monitors's "keep current semantics" line for this case, the out-of-scope bullet in rfc-goal-popover-pause-play-controls, and the code pins that record the removal.
    • § 2.4: a legacy loop's own agent may declare it waits on a person, only after asking a question it cannot proceed without, refused where no reply can release it, and expiring at the earlier of 24 hours and the loop's remaining runtime budget, with the expired wait charged to the budget and the release reason recorded. Amends the non-goal bullet of rfc-work-ledger-person-wait-hold.
  • docs/request-for-change/README.md: the index row and the audit-log sentence.

Rebased 2026-11-16 onto main 5818627f3a: the README index row and audit-log sentence are unioned with main's (main's text kept, this RFC's row in alphabetical order); the 2026-11-09 re-audit commit is kept as it was, its RFC-file change byte-identical. No RFC sentence changed: § 2.3's "Research Lab autonudge_stop tombstone" is still true, since main routes that tombstone through the stopped_loop_tombstone seam that Research Lab provides.

Backwards compatibility

Compatible: documentation only.

Tests

N/A — documentation only. scripts/docs_lint.py passes.

Manual verification

Every "today's code" claim was checked at 4fe2494b7d (main): autonudge_service/subject_reads.py does not exist, the approval-hold check in _timer returns without arming, the stop applier's docstring in session_directive_apply_monitor.py records the removal, and no person_wait_declared field exists.

Related Issues

no linked issue: Kyle asked for no tracking issue; the motivation above is the record.

Pattern harvest

Not generalizable: the README already describes amending an accepted document in a new one.

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

@kyleseaman
kyleseaman requested review from a team and KiroCrewCaptain as code owners October 19, 2026 13:17
@kyleseaman
kyleseaman requested a review from bolichen97 October 19, 2026 13:17
@github-actions

github-actions Bot commented Oct 19, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 98c4350fe8127a156417987f5f3bd5e5379ea832 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 Oct 19, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ⏭️ skipped

Revision 98c4350fe8127a156417987f5f3bd5e5379ea832 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 added the readiness: checking Automated validation is still running label Oct 19, 2026
@github-actions

github-actions Bot commented Oct 19, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 98c4350fe8127a156417987f5f3bd5e5379ea832 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: the PR is docs only, it records the owner's decisions in a new RFC that amends the four implemented RFCs without editing them, and its partial-status claims match the base tree.

Notes

  • The front matter says status: partial, but the first body line says "Status: accepted". Make the two agree so the First Principles lane reads one status.

[DESIGN-REVIEWED] 98c4350

Description read

[DESCRIPTION-READ] 116f47dabfdfe6c396556c5951cb223d44fcc15d01ecc334ca0e5d8f887b2108

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 19, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 98c4350fe8127a156417987f5f3bd5e5379ea832 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 98c4350

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 98c4350fe8127a156417987f5f3bd5e5379ea832 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Oct 19, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 98c4350fe8127a156417987f5f3bd5e5379ea832 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 98c4350

Verdict parsed from the review's SHA-scoped output markers for commit 98c4350fe8127a156417987f5f3bd5e5379ea832.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 98c4350fe8127a156417987f5f3bd5e5379ea832 false-positive: <reason, 20 to 500 characters>

@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.

Needs a maintainer design sign-off. This is a docs-only RFC that records four decisions as accepted, so I am leaving a comment, not an approval.

Head reviewed: e64a20b. Bots read: Design CONCERNS, First Principles skipped (docs only), UX skipped, Opus no findings, GPT no findings. Readiness was still checking when I read it.

What I checked against origin/main:

  • Every quoted base sentence exists as cited: the rfc-goal-loop-approval-hold § 3 "While held" lines, the rfc-token-efficient-monitors "keep current semantics" line, the rfc-goal-popover-pause-play-controls non-goal, the rfc-work-ledger-person-wait-hold § 2 non-goal, the session_directive_apply_monitor.py docstring, the test/test_autonudge_stop_auth.py docstring, the learn-cron-dashboard.md sentence and the firing.py comment.
  • All four amended RFCs are implemented on main. This document amends them in its own text and edits none of them, which follows the README convention.
  • No SUBJECT_READ_SECS, PERSON_WAIT_MAX_SECS or gh_pr.fetch_state exists on main yet. That matches the "not yet the code" index row.
  • Diff matches the description: one new RFC and one index row plus its audit-log sentence. No code, no CHANGELOG.

Open point for the design sign-off (not blocking from me):

  • The Design Review CONCERNS on this head is not answered yet. §§ 2.1 and 2.2 add a per-loop gh pr view read every 300 s on the legacy path. The RFC does not say how that read relates to the consolidated monitor plan, which wants one shared, batched GitHub observation layer. One sentence in § 3 or § 5 would clear it: either these reads are retired with the legacy path, or they move onto the shared provider when it lands.

Maintainer check that remains: an RFC is never approved by an automated reviewer. A maintainer should confirm the accepted status and the decisions in § 2, then approve and merge.

@github-actions github-actions Bot added the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Oct 19, 2026
@kyleseaman
kyleseaman force-pushed the docs/rfc-legacy-loop-reads-stops-waits branch from e64a20b to f329bca Compare October 19, 2026 14:21
@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention and removed merge conflict Branch has merge conflicts with its base — author must resolve before merge readiness: checking Automated validation is still running labels Oct 19, 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.

Still needs a maintainer design sign-off, so this is a comment, not an approval.

Head reviewed: f329bca. The push is a rebase onto current main. The RFC file is byte-identical to the previous head, and the README index row is the same row re-applied on top of the rows main gained. No new findings from me.

Bots on this head: Design CONCERNS, First Principles skipped (docs only), UX skipped, Opus no findings, GPT no findings.

Open for the design sign-off (not blocking from me):

  • My earlier question is still open, since the text did not change: §§ 2.1 and 2.2 add a per-loop gh pr view read every 300 s on the legacy path, and the RFC does not say how that relates to the planned consolidation onto one shared GitHub observation layer. One sentence in § 3 would clear it: these reads retire with the legacy path, or they move onto the shared provider when it lands.
  • The Design Review now raises a sharper point on the same section: § 2.1 settles a held loop when "the" pull request its free-text message names merges, but never says how that pull request is chosen. A message like "fix the regression #123 introduced" would be settled with subject_outcome: success when #123 merges. That sits against the existing monitor-architecture position against acting on prose in a monitor_start message. Naming the subject explicitly at arming time, or stating the parse rule and its false-positive bound, would answer it.

CI: Fast Gate is red on the Harness Parity x-capture check (ACP_BACKENDS_MEMBER_CAPABILITIES [claude]: allowlisted but now proven; delete the entry). That allowlist is not in this diff, which touches only two files under docs/request-for-change/, so it looks like a main-side gate state rather than something this PR has to fix. Readiness stays action required until that clears.

Maintainer check that remains: an automated reviewer never approves an RFC. A maintainer should confirm the accepted status and the decisions in § 2, then approve and merge.

@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.

Still needs a maintainer design sign-off, so this is a comment, not an approval.

Head reviewed: 0631d7e. This push is another rebase onto current main. The RFC file is byte-identical to f329bca, and the README patch is the same index row and audit-log sentence. No new findings from me.

Bots on this head: Design PASS, First Principles skipped (docs only), UX skipped. The Opus and GPT checks show as failed on this head and their sticky comments still name f329bca, so they have not produced a verdict for this head yet. Readiness is still checking.

The two questions from my last review are still open, since the text did not change. The Design lane moved to PASS, but neither is answered in the RFC:

  • Relation to monitor consolidation. §§ 2.1 and 2.2 add a per-loop gh pr view read every 300 s on the legacy path. One sentence in § 3 would settle it: these reads retire with the legacy path, or they move onto the shared GitHub observation provider when it lands.
  • How § 2.1 picks the pull request. A held loop settles when "the" pull request its free-text message names merges, but the RFC does not say how that pull request is chosen. A message like "fix the regression #123 introduced" would settle with subject_outcome: success when #123 merges. Naming the subject explicitly at arming time, or stating the parse rule and its false-positive bound, would answer it.

Maintainer check that remains: an automated reviewer never approves an RFC. The Design lane also asks a maintainer to confirm that the author of these decisions approved this exact text, since the accepted status rests on that. After that, a maintainer can approve and merge.

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention labels Oct 19, 2026
@kyleseaman

Copy link
Copy Markdown
Contributor Author

Design punchline (who approved the accepted text): the behaviours here are the ones @kyleseaman asked for on the legacy-loop stack (#21377, #21621, #21622); his instruction was to record them in an RFC rather than override First Principles. The RFC states that in its Motivation. This PR is not merged by its author: the merge is his, and that merge is the confirmation the reviewer asks for.

@github-actions github-actions Bot added the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Oct 20, 2026
@kyleseaman
kyleseaman force-pushed the docs/rfc-legacy-loop-reads-stops-waits branch from 0631d7e to a634621 Compare October 20, 2026 02:05
@github-actions github-actions Bot removed the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Oct 21, 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.

Still a design sign-off for a maintainer, so this is a comment, not an approval.

Head reviewed: 5c961bf. Compared with 2c406e7, the only content change is the section 2.1 bullet on a held loop that names no pull request. The README row is unchanged apart from the rebase.

The new text matches main. On main a loop held for approval has no live timer, fires no cycle and spends neither its cycle cap nor its runtime budget (autonudge_service/timers.py, notify_approval_stalled), the reconciler skips it while approval_stalled is set (the check near line 968), and release_approval_hold re-arms it once someone answers an approval, sends a message or fires it in that session. That resolves the Opus finding on 2c406e7, which said the old wording claimed an arm toward the deadline that main does not make. The AI lanes have not re-run on this head yet.

One optional wording point: "it ends only when a person releases the hold" reads as if the loop ends. On main the hold ends and the loop resumes, and a person can still stop the loop outright. Something like "it stays paused until a person comes back to the session, or stops the loop" would be exact.

The two questions from earlier reviews are still open, for whoever merges to settle or accept as written:

  • Relation to monitor consolidation: do the per-loop gh pr view reads in 2.1 and 2.2 retire with the legacy path, or move onto the shared GitHub observation provider?
  • How 2.1 picks the pull request when the message names a precondition PR rather than the loop's subject.

@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 21, 2026
@iamwhatever
iamwhatever enabled auto-merge (squash) October 21, 2026 21:15
@github-actions github-actions Bot added the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Oct 21, 2026
@kyleseaman
kyleseaman force-pushed the docs/rfc-legacy-loop-reads-stops-waits branch from 5c961bf to ee30ca5 Compare October 22, 2026 01:01
@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention and removed readiness: passed Eligible automated validation passed for the current revision merge conflict Branch has merge conflicts with its base — author must resolve before merge readiness: checking Automated validation is still running labels Oct 22, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor

Hold at bace4e4.

  • The PR now conflicts with main (mergeable: CONFLICTING). It is likely the README index row. A rebase clears it.
  • Two design points that bolichen97 raised on earlier heads are still unanswered in the text, and as an accepted RFC they need a maintainer ruling before merge:
    • Section 2.1 settles a held loop when the one PR its message names merges, but it never says how that PR is chosen. A loop that names a precondition PR would end as a success just when its work should start. To fix it, take the subject from a typed monitor_start/monitor_update argument, or list this case under Risks with how the agent re-arms.
    • The Non-goals and Risks don't say whether the per-loop 300 s gh pr view reads retire with the legacy path or move onto a shared GitHub observation provider. One sentence would settle it.
  • Optional wording: "it ends only when a person releases the hold" (L77) reads as if the loop ends. On main the hold ends and the loop resumes.

The cited base sentences match, all AI lanes pass, and CI is green on this head.

— crew-pr-reviewer (r119)

@kyleseaman

Copy link
Copy Markdown
Contributor Author

@bolichen97 both design questions from your reviews on 461807f and 5c961bf are answered in the RFC text at d101b1c (docs only):

  • Where the per-loop PR reads end up: § 3 Non-goals, last bullet. The one gh pr view per loop in § 2.1 and § 2.2 moves onto the shared GitHub observation provider when it lands, or retires with the legacy loop path, whichever comes first.
  • A held loop naming a precondition/dependency PR: § 4 Risks, "A held loop that names the wrong pull request". It settles when that PR merges or closes; accepted because the settlement sends the usual expiry notice and the agent re-arms with monitor_start (or monitor_update from a turn a person sent) naming the subject PR.
  • § 2.1 wording: a held loop that names no PR now "stays paused until a person comes back to the session, or stops the loop".

Previous head backed up as backup/rfc-legacy-loop-reads-stops-waits-210ee9812e.

@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.

Still a design sign-off for a maintainer, so this is a comment, not an approval.

Head reviewed: d101b1c. Compared with 210ee98 (same base), the README patch is unchanged and the RFC has three edits:

  1. Section 2.1, held loop that names no pull request: it now "stays paused until a person comes back to the session, or stops the loop". That matches the release signs of the approval hold RFC on main (an answer, a typed dashboard message, or Play) and adds the manual stop. Reads correctly.
  2. Non goals: the per loop gh pr view in sections 2.1 and 2.2 is marked temporary, moving onto the shared GitHub observation provider when it lands or retiring with the legacy loop path. This answers the earlier consolidation question.
  3. Risks: a held loop that names a precondition PR rather than its subject settles when that PR merges or closes. It is accepted, with the expiry notice as the signal and a re-arm naming the subject PR. This answers the earlier section 2.1 PR selection question.

One small wording point in that new risk: once the loop has settled it is terminal, so monitor_update has nothing left to revise. If the parenthesis means retargeting before settlement, saying so would help; otherwise monitor_start alone is the re-arm path.

No other open questions from my side. The design call stays with the maintainers.

@kyleseaman

Copy link
Copy Markdown
Contributor Author

@bolichen97 thanks -- fixed in bc6dd1d80e (docs only). § 4, "A held loop that names the wrong pull request", now reads: "A settled loop is terminal, so the agent re-arms with monitor_start naming the subject pull request; monitor_update can only retarget the message before it settles." The earlier "(or monitor_update from a turn a person sent)" re-arm path is gone.

@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.

Still a design sign-off for a maintainer, so this is a comment, not an approval.

Head reviewed: bc6dd1d. Compared with d101b1c (same base), the README patch is unchanged and the only RFC edit is the re-arm sentence in the wrong pull request risk. It now says a settled loop is terminal, the agent re-arms with monitor_start naming the subject pull request, and monitor_update can only retarget the message before it settles. That resolves my earlier wording point.

No open questions from my side. The design call stays with the maintainers.

@iamwhatever

Copy link
Copy Markdown
Contributor

HOLD at 96aa385.

  • The PR still conflicts with main (mergeable: CONFLICTING), most likely in the docs/request-for-change/README.md index row. A rebase clears it, and the new head needs another look.
  • This records four decisions as an accepted RFC, so a maintainer still has to confirm the decisions and merge it. An automated reviewer does not approve an RFC.

The two design points from r119 are answered in the text. The Non-goals and Risks now say the per-loop gh pr view moves to the shared observation provider or retires with the legacy path, and they accept the precondition-PR case with monitor_start as the re-arm. The section 2.1 wording is fixed. Design passes, Opus and GPT have no findings, and CI is green on this head.

— crew-pr-reviewer (r122)

@bolichen97

Copy link
Copy Markdown
Contributor

This RFC records four default behaviors for legacy monitoring loops, retained stop reasons, and agent-declared waits. Those choices change how long automation reads pull requests, when it stops, and which waits are accepted. They require explicit maintainer acceptance.

design-doc-gate: Rule D — this changes a design document, so it needs a human to agree to the design. Not approved and not rejected by this review.

@iamwhatever

Copy link
Copy Markdown
Contributor

HOLD at 4b60ac0.

  • This RFC records four decisions as accepted, so a maintainer has to confirm the decisions and merge it. An automated reviewer does not approve an RFC, and the design-doc gate comment from @bolichen97 asks for the same explicit maintainer acceptance.

The conflict from r122 is gone: this head is a rebase, the RFC text is identical to 96aa385, and only the README index row moved onto the new base. Design passes, Opus and GPT have no findings, and CI is green on this head.

— crew-pr-reviewer (r123)

@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.

Still a design sign-off for a maintainer, so this is a comment, not an approval.

Head reviewed: efad3a3. Compared with 4b60ac0 (same base), the README patch is unchanged. The RFC edit narrows section 2.1 to gated loops: a held loop now reads its pull request and settles on merge or close only when it was armed with gate=true. A held gate=false loop reads nothing and keeps main's behaviour, so a merged or closed pull request never ends an ungated loop or blocks its resume. The section 2.4 Held bullet and the two section 4 risks are reworded to match.

I checked this against the implementation in #21377 at e6e01f0: the held tick admits only a gated loop and records the outcome on its monitor, and the sleep read is skipped for gated loops. The RFC text and that code agree.

No open questions from my side. The design call stays with the maintainers.

@iamwhatever

Copy link
Copy Markdown
Contributor

HOLD at 51785e7.

  • This records four decisions as an accepted RFC, so a maintainer has to accept the decisions and merge it. The design-doc gate comment asks for the same. An automated reviewer does not approve an RFC.

This head is a rebase. The RFC is byte-identical to efad3a3, which narrowed section 2.1 to gated loops. One small optional fix: the README index row still says a held loop that names one pull request reads it, without the gate=true condition that section 2.1 now has. Design passes, Opus and GPT have no findings, and CI is green.

— crew-pr-reviewer (r124)

@bolichen97

Copy link
Copy Markdown
Contributor

@kyleseaman, this branch now conflicts with main after recent merges there, in docs/request-for-change/README.md (the RFC index). Could you rebase it onto current main (not a merge commit, since PR Hygiene allows only one or two commits)? I will take another look once the new head is up.

@iamwhatever

Copy link
Copy Markdown
Contributor

Hold at 37af4e7.

This records four product decisions as an accepted RFC, so a maintainer has to accept them and merge it. The design-doc gate comment asks for the same thing. An automated reviewer does not approve an RFC.

One accuracy point for whoever accepts it: #21377 merged on 2026-11-07, after this head was built. The README row still says the decisions are "not yet the code" and that subject_reads.py does not exist. On main that file now exists. A refresh of that row (and perhaps the RFC's audited-at) before merge would keep the index true. The row also still omits the gate=true condition that section 2.1 carries.

The RFC text is byte-identical to 51785e7, which r124 reviewed. The conflict is gone.

AI findings judged non-blocking:

All checks are green (76 success, 18 skipped).

— crew-pr-reviewer (r149)

@KiroCrewCaptain

Copy link
Copy Markdown
Collaborator

This changes behaviour users already rely on, so it needs a design sign-off from a maintainer before it can merge. A maintainer will post the decision here. To propose a design, follow the request-for-change process in CONTRIBUTING.md (docs/request-for-change/).

Review result on this head: no blocking findings. The PR changes two markdown files and no code. We checked the RFC's claims about current behaviour against main, and they match:

  • The superseded sentences quoted from the four amended RFCs, the stop applier docstring, the stop test pin and the spec all exist at the cited places.
  • Sections 2.1 (approval hold) and 2.2 match the shipped subject_reads.py, including the 300 second read and settling on merge or close.
  • Sections 2.3 and 2.4 are still open on main, as the re-audit says.

Done well: the RFC amends the implemented RFCs in its own text and quotes each reversed sentence exactly, so a later reader can trace every change.

Optional:

  • docs/request-for-change/README.md:64 and the PR body's section 2.1 bullet leave out the gate=true condition. A held ungated loop reads nothing. Consider "a gated legacy loop held for a person ...".
  • rfc-legacy-loop-reads-stops-waits.md:17 says "Status: accepted." while the front matter says partial. Consider "Status: partial (accepted 2026-10-19)".

@KiroCrewCaptain

KiroCrewCaptain commented Nov 12, 2026 •

Copy link
Copy Markdown
Collaborator

Code change approver recommendation: A person should decide

Why: the decider estimates a 7% chance that this change introduces a defect, within the 12% limit for approving on its own, but it is held at tier 2: design-doc-gate: D.

This PR changes docs only: a new RFC that records the product owner's four decisions about legacy monitoring loops, plus its row in the RFC index README. I checked its claims about the code at the PR's head commit and they hold. autonudge_service/subject_reads.py has hold_tick and sleep_until_cycle, and firing.py and timers.py call them. The ungated read wakes only on a new conflict, once per head, and never ends or suppresses the loop. The held read settles only a gated loop, records success or blocked on its monitor and credits the held time back to the runtime budget. These match § 2.1 and § 2.2, and the partial status is right for them. The parts the RFC calls not yet built really are missing: no person_wait_declared field exists, and the stop applier docstring, the test docstring, the spec sentence and the model.py pin it supersedes are all still there, word for word. Every sentence it quotes from the documents it supersedes or amends exists as quoted, and it amends them in its own text instead of editing them, as the README's convention allows. On the trust check: the agent-declared wait in § 2.4 lets an agent quiet its own loop. The agent can already stop tha

Tier: 2, held for a person: design-doc-gate: D.

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 98c4350fe8 · 237 changed lines. If this recommendation is wrong, reply here: replies are how the approver is evaluated.

kyleseaman and others added 2 commits November 19, 2026 23:19
the ungated conflict wake (2.2). The RFC and its index row still said accepted,
not yet the code. Mark it partial, re-audited at ad55351, and name what is
still open in #21621 and #21622.
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.

4 participants