Skip to content

feat(conductor): kirocrew-conductor becomes the ledger conductor - #10265

Merged
bolichen97 merged 2 commits into
mainfrom
feat/conductor-becomes-ledger-conductor
Sep 12, 2026
Merged

bolichen97 merged 2 commits into
mainfrom
feat/conductor-becomes-ledger-conductor

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Sep 12, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

The work-ledger conducting flow ships on a spec nobody reaches by default. kirocrew-conductor — the agent a user actually gets when they hand over a long-horizon goal — still learns each worker's state by reading its transcript against a stored cursor, and still squeezes item state into session_ledger artifacts values under a 2000-character-per-entry cap. The ledger flow, with one record per item and an evaluator verdict instead of a transcript read, lives on kirocrew-ledger-conductor, which a user has to know to name.

That split was deliberate (#9277, Phase 2.5): mounting the tools on the shipped conductor would have moved every existing conductor user onto a different procedure without asking. The RFC set two merge criteria for closing it, and this PR is that close.

Why it matters

Every conductor goal that runs on the default spec pays the old costs — a per-item transcript read per patrol cycle, item state in a capped string field, and a done that is settled by the conductor's own reading rather than by accept_eval.py. Leaving the flow behind a name means the improvement exists and nobody gets it, and it means goal-conductor/SKILL.md stays frozen against every later ledger phase.

What changed (motivation → approach → change)

Goal: make the ledger flow the default without breaking the old name.

Approach: one spec body, two filenames. Two installers that each hand-build the same list are exactly where a grant lands on one spec and not the other, and an alias that emits a different spec silently changes what an in-flight session can do — which is the one failure the alias exists to prevent. So _conductor_spec(name=, description=, filename=, source=) is the single body; filename and source are the only per-installer values and neither reaches the emitted JSON (filename is the KAS agent_id in the derive's log line, source names the installer in the withheld-grant audit event).

What that produced:

  • kirocrew-conductor mounts kirocrew-work, auto-approves work_ledger_read / work_ledger_record / work_brief and not work_report, and carries the ledger prompt. Every property the old installer's docstring argued for is unchanged: no file-writing tool at all (not fs_write, not code), @kirocrew-core / @kirocrew-dashboard / @kirocrew-work mounted whole but auto-approved verb by verb, execute_bash mounted and never auto-approved, permissions derived from the FILTERED grant list.
  • kirocrew-ledger-conductor emits that same spec under its old name for one release, with description prefixed Deprecated alias of kirocrew-conductor (removed next release). The name is a public string — what a running session records as its agent, what a seed prompt names for a second-level conductor, what an operator typed into a cron — so deleting it in the same release as the swap would break those in place.
  • Prompt. The ledger prompt is now _CONDUCTOR_SYSTEM_PROMPT; its opening no longer says "you differ from kirocrew-conductor in ONE thing" but states the ledger flow directly, and the dispatch table's decomposable row names kirocrew-conductor. _LEDGER_CONDUCTOR_SYSTEM_PROMPT is gone rather than duplicated.
  • Skills. goal-conductor/SKILL.md is the ledger procedure (the content of goal-ledger-conductor/SKILL.md, references renamed); goal-ledger-conductor/SKILL.md is a one-paragraph deprecation pointer to it. Both keep a byte-identical scripts/accept_eval.py, so a session that already loaded the old skill name keeps a working evaluator. The builtin-skill scope gate passes on the moved content.
  • Not swapped: kirocrew-pipeline-conductor and kirocrew-security-conductor still mount nothing. Their children report through their own skills' scripts, so the mount would grant a flow whose procedure neither runs.
  • Deliberately left: goal-conductor/scripts/ledger_entry.py is still shipped, now unreferenced by the SKILL.md. Deleting it and test_conductor_ledger_entry.py is Phase 4's scope in the RFC, and the rollout note says so rather than leaving the reader to notice.

Docs updated to match: src/kiro_crew/docs/agents.md, docs/feature-map/README.md, docs/system-specs/modules/pipeline-conductor.md, docs/request-for-change/README.md, and the RFC — which gains a 2.6 — the swap phase row and a Rollout note — swap done section recording the decision against its own criteria, marks Phase 2.5's superseded exit criteria as superseded, and re-frames §Motivation as the historical cost it now is.

After the change, grep -rn kirocrew-ledger-conductor src test docs website/src scripts hits only the alias installer, the alias filename constant, deprecation text, and the RFC's history.

Tests

  • test_ledger_conductor_agent.py is now the alias's identity proof. test_the_alias_spec_is_identical_apart_from_name_and_description installs both specs under one stub and compares the emitted JSON field by field — {k for k, v in live.items() if alias.get(k) != v} == {"name", "description"} — rather than asserting both call the same helper, because a helper is what a later edit routes around. It also pins that the deprecation prefix is present and that the charter sentence survives it. test_the_governance_ceiling_reaches_the_alias_the_same_way pins that a ceiling strips the same ref from both, on allowedTools and on the derived KAS block.
  • The mount, on all four surfaces. test_the_work_mount_lands_on_all_four_surfaces asserts tools, mcpServers, allowedTools and permissions.rules[].match. The last is the one that silently survives an incomplete edit: a spec can look correctly mounted on kiro-cli while the KAS projection grants nothing, and every patrol cycle then stalls on an approval nobody is there to give. work_report and kirocrew-work/* are asserted absent on both grant surfaces.
  • Flipped, not deleted. test_prompt_carries_no_work_ledger_procedure → test_prompt_carries_the_work_ledger_procedure (and it pins dispatch ORDER, not just presence); test_mcp_surface_is_narrowed_to_core_plus_dashboard → ..._plus_work as an exact set; the two exact-allowedTools lists and the KAS match expectations gain the three work resources. test_worker_agent.py's "a shipped conductor does not mount the server" keeps kirocrew-pipeline-conductor and parametrizes the positive case over the live spec and the alias.
  • Procedure ratchets follow the procedure. The batch-filter, nested-conductor-reports-upward, watch: "work-ledger", skill-body and quoted-heredoc pins moved to test_conductor_agent.py against goal-conductor/SKILL.md. The codec doc-ratchet is replaced by one asserting the skill routes item state to the store and names no codec. test_builtin_skill_index_line.py's parametrize list moves to goal-conductor, and a new test pins that the deprecated skill's rendered index line says "Deprecated" and names goal-conductor — that one line is all an agent reads before deciding whether to load a skill.
  • test_the_evaluator_is_byte_identical_to_the_shipped_one is unchanged and green.

Run locally with the repo venv: 918 passed across test_conductor_agent.py, test_ledger_conductor_agent.py, test_worker_agent.py, test_pipeline_conductor_agent.py, test_security_conductor_agent.py, test_builtin_skill_index_line.py, test_work_ledger.py, test_work_ledger_tools.py, test_conductor_ledger_entry.py, test_agent.py, test_agents_roster_contract.py, test_agent_discovery.py, test_skill_listing_cost.py, test_agent_template_skills.py; a further 317 across the installer/permission/roster consumers (test_derived_agent_permissions_consumers.py, test_kas_agents.py, test_acp_set_mode_all_agents.py, test_agents_janitor.py, test_migrate_agent_specs.py, test_agent_sdk_boundary.py, test_spawn_agent_roster.py, test_agent_roster_shared.py, test_pipeline_conductor_skill_contract.py, test_agent_import_hoist.py, test_agent_lifecycle_cycle.py).

Gates run with their own base-ref exports: black --target-version py310 --check, isort --check-only, flake8, mypy src/kiro_crew/agent.py, check_brand_name.py, check_comment_history.py, check_focus_cue.py, check_changelog_history.py, check_harness_parity.py, check_feature_map.py, check_builtin_skill_scope.py, docs_lint.py — all clean.

Manual verification

N/A — the whole change is the content of two generated JSON specs and two markdown files, and the installer tests read back the JSON that was actually written.

Related Issues

Implements the merge criteria in docs/request-for-change/rfc-conductor-work-ledger.md §Rollout note (v2.1), following #9277.

Deprecation plan

release kirocrew-conductor kirocrew-ledger-conductor goal-conductor goal-ledger-conductor
this one the ledger conductor alias, same spec, description says deprecated the ledger procedure one-paragraph pointer + byte-identical accept_eval.py
next one unchanged removed, gated on #10268 unchanged removed, gated on #10268

Nothing new should name either deprecated item. A session, cron or crew binding that already names the old agent keeps resolving through this release and gets the merged spec, not a Mode not found failure. Phase 4 removes both names and deletes goal-conductor/scripts/ledger_entry.py with its tests.

Review round 2 — what the advisory lanes changed

Design Review and First Principles both returned 🟡 CONCERNS on the same real defect, and both are addressed in commit 2:

  • Criterion 2 was waived, not met, and the RFC said "met". The rollout note opened "the merge criteria above are met" two paragraphs above its own record that the watch: "work-ledger" gate is unmerged. It now says criterion 1 met / criterion 2 waived, with the re-judgement stated: the objection criterion 2 encoded was "not yet cheaper than the agent it would replace", and the agent actually being replaced pays a per-item transcript read per cycle, which is not cheaper than one work_ledger_read.
  • Criterion 1's evidence is now bounded by what it actually is. The note states the 7-items-over-3-rounds lifecycle as the grounds the decision was taken on, and names the two sub-clauses (a blocked/question, a second-level conductor) that have no linkable record rather than claiming them.
  • The kirocrew doctor notice the retirement spec requires does not ship here, and that gap is real: the deprecated description is read by an operator looking at the roster, not by a cron job or a crew binding, so without a notice the one-release window warns nobody. Recorded as a precondition for deleting the alias (not for the swap — an unmigrated config keeps working while the alias exists) and tracked as kirocrew doctor should flag a config naming a deprecated agent spec #10268.
  • Mid-goal upgrade behaviour is now stated, per the Design lane's suggestion: a session mid-goal under the old procedure wakes into the ledger prompt with item state still in session_ledger artifacts; every old tool is still mounted so it can finish its round, and what it must not do is keep both records.
  • ledger_entry.py's deletion moves out of Phase 4 and rides with the alias's removal next release, per the FP lane's subtraction: its only remaining consumers are those mid-goal sessions, which expire on the same schedule as the alias. Phase 4 keeps the Crew page surfaces.
  • Dropped the one-entry @pytest.mark.parametrize in test_worker_agent.py for the inline filename.

Round 3

Design Review's one actionable suggestion applied: the RFC's rollout note said "Both are removed next release" unconditionally while the same note makes #10268's doctor notice a precondition for that deletion. The note now gates the removal on it explicitly, so the removal PR inherits the gate from the document it will be read against.

Both lanes' remaining Watch items are maintainer decisions rather than changes to make here, and both name that in their own Clears when: lines:

  • Criterion 1's run has no linkable record. The end-to-end goal ran in agent sessions, not against a public artifact, so there is nothing to link. The rollout note states the lifecycle evidence it rests on and explicitly does not claim the two sub-clauses (a blocked/question item, a second-level conductor). Clearing this is "a maintainer explicitly accepts the note's evidence."
  • Criterion 2 is waived by the PR it gated, and the cost comparison is reasoned rather than measured. That is accurate: the note argues a per-item transcript read per cycle is not cheaper than one work_ledger_read, and does not present a measurement. Clearing this is Phase 3's wake gate merging, or a maintainer ratifying the waiver.

Both are advisory; neither lane blocks readiness, and the First Principles inventory is 9 items / 9 justified after round 2.

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 a review from a team September 12, 2026 01:09
@iamwhatever iamwhatever added the no-screenshots PR has no visual delta; screenshot gate exempt label Sep 12, 2026
@iamwhatever iamwhatever added the no-screenshots PR has no visual delta; screenshot gate exempt label Sep 12, 2026
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Sep 12, 2026
@github-actions

github-actions Bot commented Sep 12, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Fable 5) — 🟡 CONCERNS

Design-level review of a6a64d734c77925230d794e699add9519a953351 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Design-Verdict: CONCERNS

Sound consolidation with an enforced identity alias — but the PR ratifies its own merge gate: criterion 2 waived, criterion 1 partly unevidenced.

Watch

  • The RFC's merge criteria are settled by the PR they gated: criterion 2 ("not yet cheaper") is waived on a reasoned, unmeasured cost comparison ("re-judged against the agent actually being replaced… the objection does not hold"), and criterion 1's two sub-clauses (a blocked/question item, a second-level conductor) are explicitly unevidenced. The design is right and the record is honest, but the decision basis is self-certified — a defect in the ledger flow now lands on every default conductor user instead of on opt-ins, which is exactly the containment Phase 2.5 bought and this PR spends.
    Clears when: a maintainer explicitly ratifies the waiver and the criterion-1 evidence in review (or Phase 3's watch: "work-ledger" gate merges, retiring the waived criterion).

Suggestions

The shape itself is the right one: _conductor_spec as a single body with the alias pinned field-by-field ({k for k, v in live.items() if alias.get(k) != v} == {"name", "description"}) closes the drift channel two hand-built installers had; the flipped Phase 2.5 pins are treated as a superseded decision with the re-judgement recorded in the RFC, not as a gap; in-flight sessions, crons and seed prompts keep resolving through the window; and the mid-goal soft-migration story (old tools still mounted, ledger_entry.py retained on the alias's schedule) is stated rather than left to be discovered.

[DESIGN-REVIEWED] a6a64d7

@github-actions

github-actions Bot commented Sep 12, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Fable 5) — 🟡 CONCERNS

Premise-level review of a6a64d734c77925230d794e699add9519a953351 — 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/CONCERNS are advisory.

All evidence gathered. Composing the review.

First-Principles-Verdict: CONCERNS

The swap passes its own recorded two-part merge gate by waiving criterion 2 and asserting criterion 1 on evidence with no linkable record.

Not justified as shipped

  • Item 7 (the merge-criteria rewrite) — inherited premise: the RFC pinned the fold-back on "when BOTH hold"; this commit amends that gate in the same change that passes through it. Criterion 2's waiver rests on an asserted, unmeasured cost comparison, and criterion 1's run ("7 items across 3 rounds") is cited nowhere linkable — the note itself concedes two sub-clauses are unevidenced.

What this change ships

Inventory (9 items) — 8 justified

Intent: make the work-ledger flow what the default conductor runs, keeping the old name resolving for one release — an ADDITION (a changed default), and the description matches the diff.

  1. The default kirocrew-conductor now tracks goals in the work ledger (mount, bind-before-seed, evaluator-settled acceptance) — every existing conductor user changes procedure — justified
  2. kirocrew-ledger-conductor becomes a deprecated alias emitting the identical spec, removed next release — justified
  3. goal-conductor skill body is now the ledger procedure; the transcript-reading procedure is gone — justified
  4. goal-ledger-conductor skill collapses to a one-paragraph pointer, keeping a byte-identical evaluator — justified
  5. A mid-goal conductor session wakes into the new procedure with its items still in session_ledger artifacts — justified (declared, tools still mounted)
  6. ledger_entry.py still ships, referenced by nothing an agent reads; deletion rides with the alias's removal — justified (named consumer: in-flight sessions)
  7. The RFC's merge criteria are re-recorded as "criterion 1 met, criterion 2 waived", superseding Phase 2.5's exit pins — inherited: the gate is amended by the change it gates, on asserted evidence
  8. The kirocrew doctor notice for configs naming the old agent is deferred to kirocrew doctor should flag a config naming a deprecated agent spec #10268, gated as precondition for alias deletion — justified (linked issue)
  9. Two hand-built installers collapse into one _conductor_spec body (2 consumers counted: agent.py:6285, agent.py:6316), with a field-by-field identity test replacing the deleted Phase-2.5 negative pins — justified

Watch

  • Criterion 1's evidence is only asserted: "7 items across 3 rounds… settled by accept_eval.py" appears in the description and a docstring, with no linked run, issue, or session record, and the rollout note itself says the blocked/question and second-level sub-clauses are "unevidenced". The deleted pins (test_the_shipped_conductor_skill_is_untouched_by_this_flow, the conductor no-mount assertions) recorded the decision this reverses. Clears when: the criterion-1 run is backed by a linkable record (issue, session log, or PR link).
  • Criterion 2 is waived on the unmeasured claim that "the old procedure's per-item transcript read per cycle is not cheaper than one work_ledger_read", so every default conductor now pays a turn per quiet tick by decision rather than by evidence. Clears when: a human owner confirms accepting the per-quiet-tick cost, or Phase 3's watch: "work-ledger" gate lands.

[FIRST-PRINCIPLES-REVIEWED] a6a64d7

@github-actions

github-actions Bot commented Sep 12, 2026 •

Copy link
Copy Markdown
Contributor

Opus 4.8 Review — ✅ no blocking findings

Reviewed a6a64d734c77925230d794e699add9519a953351 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] a6a64d7

Verdict parsed from the review's SHA-scoped output markers for commit a6a64d734c77925230d794e699add9519a953351.

False positive or not applicable? A repository writer can comment:
/ai-review override fable a6a64d734c77925230d794e699add9519a953351: <one-sentence reason>

@github-actions

github-actions Bot commented Sep 12, 2026 •

Copy link
Copy Markdown
Contributor

GPT 5.6 Review — ✅ no blocking findings

GPT 5.6 completed its review of a6a64d734c77925230d794e699add9519a953351 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] a6a64d7

False positive or not applicable? A repository writer can comment:
/ai-review override gpt a6a64d734c77925230d794e699add9519a953351: <one-sentence reason>

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running and removed readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention labels Sep 12, 2026
@github-actions

Copy link
Copy Markdown
Contributor

GPT 5.6 Review — ✅ no blocking findings

GPT 5.6 completed its review of 777ab3b6918934ae4f872521772a18604e5bb328 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 777ab3b

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 777ab3b6918934ae4f872521772a18604e5bb328: <one-sentence reason>

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention 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 readiness: action required A blocking check or review needs attention readiness: passed Eligible automated validation passed for the current revision labels Sep 12, 2026
Joe Guo added 2 commits September 12, 2026 02:27
The work-ledger flow shipped on a separate `kirocrew-ledger-conductor` spec so
that migrating every existing conductor user was a decision rather than a side
effect. The decision is taken: the flow ran a multi-item goal end to end (7
items across 3 rounds, each acceptance settled by `accept_eval.py` rather than
by a transcript read), so `kirocrew-conductor` is what emits it.

`_conductor_spec` is the one body both installers call, so the live spec and the
alias cannot drift: `kirocrew-conductor` mounts `kirocrew-work`, grants
`work_ledger_read` / `work_ledger_record` / `work_brief` and not `work_report`,
and carries the ledger prompt. `kirocrew-ledger-conductor` emits that same spec
under its old name for one release, with a description that says it is
deprecated — the name is a public string a running session, a cron and a crew
binding all resolve, so deleting it in the same release as the swap would break
them in place.

`goal-conductor/SKILL.md` is the ledger procedure and
`goal-ledger-conductor/SKILL.md` is a one-paragraph pointer to it, with a
byte-identical `accept_eval.py` beside each. `kirocrew-pipeline-conductor` and
`kirocrew-security-conductor` still mount nothing: their children report
through their own skills' scripts.

`goal-conductor/scripts/ledger_entry.py` stays shipped and undocumented —
deleting it and its tests is Phase 4's scope, recorded in the RFC's rollout
note.
The rollout note opened "the merge criteria above are met" two paragraphs above
its own record that the `watch: "work-ledger"` gate is unmerged and the timer's
cost was accepted. A waiver is a legitimate decision; calling it met makes the
document contradict itself and leaves a later reader unable to tell whether the
wake gate is still owed. Criterion 1 now states the evidence it rests on and
names the two sub-clauses that have no linkable record, rather than claiming
them.

The retirement spec requires a `kirocrew doctor` notice for any config still
naming the alias, and none ships here: the deprecated `description` is read by
an operator looking at the roster, not by a cron job or a crew binding, so
without the notice the one-release window warns nobody. Recorded as a
precondition for DELETING the alias and tracked as #10268.

Also recorded: what a mid-goal conductor session sees when it wakes into the
ledger prompt, and that `ledger_entry.py`'s deletion rides with the alias's
removal rather than waiting for Phase 4 — its only remaining consumers are
those sessions, which expire on the same schedule.

Drops a one-entry parametrize in test_worker_agent.py for the inline filename.
@iamwhatever
iamwhatever force-pushed the feat/conductor-becomes-ledger-conductor branch from 777ab3b to a6a64d7 Compare September 12, 2026 02:27
@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: passed Eligible automated validation passed for the current revision labels Sep 12, 2026
@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 Sep 12, 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.

Maintainer review (agent-assisted), pinned to a6a64d7. Approving the owner-delegated default-conductor migration. Dedicated review verified the shared alias spec, bind-before-seed protocol and strict caller-derived ledger identity. I additionally read the previously omitted conductor test diff, pipeline-conductor spec diff and permission derivation. Tests pin the exact three-server set, verb-limited work grants, no server autoApprove, no work_report/wildcard automatic grant, and filtered KAS permissions. Pipeline/security conductor mounts remain unchanged. Alias and evaluator compatibility are retained.

Accepted nonblocking documentation issue: the promoted skill says TBD acceptance bars are not server-filtered, but the store and prompt correctly omit them; correct that carried-over paragraph. Advisory rollout evidence/waiver is accepted as disclosed, not reclassified as measured proof; alias deletion remains separately gated by #10268. Source/test review and current-head CI; no local suites rerun.

@bolichen97
bolichen97 merged commit cb7fe76 into main Sep 12, 2026
98 of 106 checks passed
@bolichen97
bolichen97 deleted the feat/conductor-becomes-ledger-conductor branch September 12, 2026 04:35
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Sep 12, 2026
amadsalmon pushed a commit to amadsalmon/KiroCrew that referenced this pull request Sep 22, 2026
…odotdev#10265)

* feat(conductor): kirocrew-conductor becomes the ledger conductor

The work-ledger flow shipped on a separate `kirocrew-ledger-conductor` spec so
that migrating every existing conductor user was a decision rather than a side
effect. The decision is taken: the flow ran a multi-item goal end to end (7
items across 3 rounds, each acceptance settled by `accept_eval.py` rather than
by a transcript read), so `kirocrew-conductor` is what emits it.

`_conductor_spec` is the one body both installers call, so the live spec and the
alias cannot drift: `kirocrew-conductor` mounts `kirocrew-work`, grants
`work_ledger_read` / `work_ledger_record` / `work_brief` and not `work_report`,
and carries the ledger prompt. `kirocrew-ledger-conductor` emits that same spec
under its old name for one release, with a description that says it is
deprecated — the name is a public string a running session, a cron and a crew
binding all resolve, so deleting it in the same release as the swap would break
them in place.

`goal-conductor/SKILL.md` is the ledger procedure and
`goal-ledger-conductor/SKILL.md` is a one-paragraph pointer to it, with a
byte-identical `accept_eval.py` beside each. `kirocrew-pipeline-conductor` and
`kirocrew-security-conductor` still mount nothing: their children report
through their own skills' scripts.

`goal-conductor/scripts/ledger_entry.py` stays shipped and undocumented —
deleting it and its tests is Phase 4's scope, recorded in the RFC's rollout
note.

* docs(rfc): criterion 2 is waived, not met, and the doctor notice is owed

The rollout note opened "the merge criteria above are met" two paragraphs above
its own record that the `watch: "work-ledger"` gate is unmerged and the timer's
cost was accepted. A waiver is a legitimate decision; calling it met makes the
document contradict itself and leaves a later reader unable to tell whether the
wake gate is still owed. Criterion 1 now states the evidence it rests on and
names the two sub-clauses that have no linkable record, rather than claiming
them.

The retirement spec requires a `kirocrew doctor` notice for any config still
naming the alias, and none ships here: the deprecated `description` is read by
an operator looking at the roster, not by a cron job or a crew binding, so
without the notice the one-release window warns nobody. Recorded as a
precondition for DELETING the alias and tracked as kirodotdev#10268.

Also recorded: what a mid-goal conductor session sees when it wakes into the
ledger prompt, and that `ledger_entry.py`'s deletion rides with the alias's
removal rather than waiting for Phase 4 — its only remaining consumers are
those sessions, which expire on the same schedule.

Drops a one-entry parametrize in test_worker_agent.py for the inline filename.

---------

Co-authored-by: Joe Guo <zejiangg@amazon.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

no-screenshots PR has no visual delta; screenshot gate exempt

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants