Skip to content

fix(crew): keep the built-in conductor in the Mate list - #23685

Merged
buluoray merged 1 commit into
mainfrom
fix/list-builtin-conductor-in-mate-roster
Oct 24, 2026
Merged

buluoray merged 1 commit into
mainfrom
fix/list-builtin-conductor-in-mate-roster

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Oct 24, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Users who already chat with the built-in kirocrew-conductor see it in the Mate list again, on its shared default memory, while the new mate experience from #23010 stays as it is.

Since #23010, the Mate list and the crewmate pickers no longer show kirocrew-conductor. A user with weeks of conductor history opens the Mate list and their conductor is gone. The thread is still on disk, but the roster no longer reaches it.

Why it matters

The conductor is a top-level agent people pick and chat with directly, so every existing install that used it loses it from the roster after upgrading. The only workaround, giving the binding a member_id, does not help: the Mate page then reads its shared default memory as a half-moved mate.

Not a goal

What changed (motivation → approach → change)

Before After
kirocrew-conductor in the Mate list and crewmate pickers hidden listed, on default memory
Other built-ins with no member_id hidden hidden
Mates from #23010 listed listed

Symptom: the conductor vanished from GET /api/members and GET /api/agents. Cause: is_legacy_binding in src/kiro_crew/mate_worker.py hides every source: builtin binding with no member_id. It was written for an old install's assistant, but the conductor has the same shape.

Change: a named set, USER_FACING_BUILTIN_BINDINGS, holds kirocrew-conductor, and is_legacy_binding never calls a name in it legacy. The binding is untouched, so it keeps its default memory and its old thread. The startup mate migration skips it because it has no member_id, and the member thread pins a private store only for v2 memory, so the conductor opens on shared memory as it did before #23010.

Backwards compatibility

Compatible: this only lists one more row; every row listed today is still listed, and no record is changed.

Removes nothing: the diff narrows a filter, so nothing that works today is hidden or rejected.

Tests

test/test_legacy_binding_roster.py: kirocrew-conductor with no member_id is not legacy and GET /api/agents lists it; kirocrew-worker with the same shape stays hidden.

Proof: PROVEN test/test_legacy_binding_roster.py::test_the_builtin_conductor_stays_listed_without_an_id, test/test_legacy_binding_roster.py::test_the_agents_roster_leaves_the_legacy_binding_out (head 9260e07)

Manual verification

On an install whose config has kirocrew-conductor as source: builtin with no member_id and memory_store: default, is_legacy_binding answers False for it and True for kirocrew-worker.

Related Issues

Fixes #23684

Sibling sweep

Swept: git grep -n "is_legacy_binding" -- src website
Sibling: src/kiro_crew/dashboard/handlers/agents.py -- not affected -- it calls the shared is_legacy_binding, so the fix reaches it
Sibling: src/kiro_crew/dashboard/handlers/members_roster.py -- not affected -- it calls the shared is_legacy_binding, so the fix reaches it

Pattern harvest

Not generalizable: the filter matched on record shape alone, and one user-facing agent shared that shape; the fix names that agent, and no other filter keys on this shape.

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 24, 2026 07:35
@iamwhatever
iamwhatever requested a review from CrysisDeu October 24, 2026 07:35
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Oct 24, 2026
@github-actions

github-actions Bot commented Oct 24, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 9260e0765f4837727a0b326da1e06263b3d8e95a 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 24, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 9260e0765f4837727a0b326da1e06263b3d8e95a — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: a narrow, named exemption that brings back pre-#23010 listing for the one built-in users chat with directly, and leaves the binding and its memory untouched.

[DESIGN-REVIEWED] 9260e07

Description read

[DESCRIPTION-READ] 8474fc96e2314742af53f46e1431c4250fe023fed077c2915b961246ef0eb345

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 24, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 9260e0765f4837727a0b326da1e06263b3d8e95a — 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 does not.

First-Principles-Verdict: PASS

Nothing blocks. The change narrows one filter so a pre-#23010 behaviour comes back, and the change is aimed at the cause: the shape-only signature in is_legacy_binding.

Notes

  • Item 3 — one consumer, generalized: USER_FACING_BUILTIN_BINDINGS = frozenset({"kirocrew-conductor"}) is a public set with one entry. I grepped USER_FACING_BUILTIN_BINDINGS and found one reader, is_legacy_binding. Subtraction: delete the set and its docstring cross-reference, and write name in ("default", "kirocrew-conductor") inside is_legacy_binding.

What this change ships

Inventory (3 items) — 2 justified

Intent: Users who already chat with the built-in conductor find it in the Mate list and pickers again. This is a FIX (#23684).

  1. kirocrew-conductor shows again in the Mate list (/api/members) and crewmate pickers (/api/agents), on its shared memory — justified
  2. Other builtin bindings with no id (kirocrew-worker etc.) stay hidden — justified
  3. A new exported name mate_worker.USER_FACING_BUILTIN_BINDINGS — one consumer, generalized: single-entry set, single reader

[FIRST-PRINCIPLES-REVIEWED] 9260e07

Description read

[DESCRIPTION-READ] d156f2f5750bc8dac83311b5188ddb8e630b78b4093a8b568a35f67f07b935b2

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

github-actions Bot commented Oct 24, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — 🔴 changes requested (blocking)

Reviewed 9260e0765f4837727a0b326da1e06263b3d8e95a — this comment is updated in place on each push.

BLOCKING: the owning spec still says every built-in binding without a member_id is left out of GET /api/agents and GET /api/members, but this change lists kirocrew-conductor there anyway. The spec was not updated in the same commit.

BLOCKING — docs/system-specs/modules/crew-mode.md:3804
`member_id` is not a crewmate (an old `assistant`): skipped silently, and left
out of `GET /api/agents` and `GET /api/members` (`mate_worker.is_legacy_binding`).
Trigger: a config where agents["kirocrew-conductor"] has source: "builtin" and no member_id. GET /api/agents goes through agents.py:1652, and GET /api/members through members_roster.py:276. Both call is_legacy_binding, which now returns False for that name at mate_worker.py:120.
Outcome: both endpoints now list the conductor, but the spec still says they leave it out. A contributor who trusts the spec will "fix" the code back and hide every existing user's conductor thread again.
Anchor: defect
Fix: add the USER_FACING_BUILTIN_BINDINGS exception to that crew-mode.md sentence: kirocrew-conductor stays listed without a member id.

[BLOCK-MERGE] 9260e07
[OPUS-REVIEWED] 9260e07

Verdict parsed from the review's SHA-scoped output markers for commit 9260e0765f4837727a0b326da1e06263b3d8e95a.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 9260e0765f4837727a0b326da1e06263b3d8e95a false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Oct 24, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 9260e0765f4837727a0b326da1e06263b3d8e95a and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 9260e07

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 9260e0765f4837727a0b326da1e06263b3d8e95a false-positive: <reason, 20 to 500 characters>

#23010 hid every builtin binding with no member id from the roster, which also hid kirocrew-conductor: users chat with it directly, so existing conductor threads vanished from the Mate list and the crewmate pickers. Exempt it by name; internal built-ins stay hidden.
@iamwhatever
iamwhatever force-pushed the fix/list-builtin-conductor-in-mate-roster branch from 712bc44 to 9260e07 Compare October 24, 2026 07:52
@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 24, 2026

@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.

Change makes sense: kirocrew-conductor runs on its own template (not the mate conductor), so listing it does not route it into the mate worker hand-off, and it keeps its shared default memory and thread. Other id-less built-ins stay hidden, covered by the new test. One small follow-up, also what Opus flagged: docs/system-specs/modules/crew-mode.md (~line 3804) still says every built-in binding without a member_id is left out of GET /api/agents and GET /api/members; please add the USER_FACING_BUILTIN_BINDINGS exception there so the spec matches.

@buluoray
buluoray merged commit 4d5d86a into main Oct 24, 2026
105 of 107 checks passed
@buluoray
buluoray deleted the fix/list-builtin-conductor-in-mate-roster branch October 24, 2026 12:34
@github-actions github-actions Bot removed the readiness: action required A blocking check or review needs attention label Oct 24, 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.

Mate list and crewmate pickers hide the built-in kirocrew-conductor after #23010

2 participants