Skip to content

fix(chat): show a plain name for the Conductor where a chat's agent is labelled - #22944

Merged
bolichen97 merged 1 commit into
mainfrom
fix/21531-conductor-display-name
Oct 22, 2026
Merged

bolichen97 merged 1 commit into
mainfrom
fix/21531-conductor-display-name

Conversation

@iamwhatever

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: A chat that runs on the built-in Conductor shows "Conductor" as its agent label, not the code name kirocrew-conductor.

In a chat on the kirocrew-conductor template (Crew Mode), the session row and the composer chip show kirocrew-conductor. A user who just turned Crew Mode on cannot tell whether that is another assistant. Deferred from the UX review of #21526.

Why it matters

Every Crew Mode chat shows the code name on its row and under its message box. It reads as jargon and makes "same chat, one switch" look like a different assistant.

Not a goal

  • Display names for other built-in agents. Only the Conductor has a code name a user meets.
  • Changing the agent picker list, search, routing or any stored agent id.
  • Guessing a session's kind from its name when the session recorded none.

What changed (motivation → approach → change)

agentOrDefaultLabel is the one label every surface uses for a chat's agent, and it only knew the name. It now also takes the kind the session recorded (agent_kind). A template pick of kirocrew-conductor reads "Conductor"; an agent-less chat whose default template is the Conductor reads "Conductor · default". A crewmate with the same name, a kind-less pin, and every other agent keep the raw name.

The session row (SessionRow.tsx), composer chip (ComposerDockView.tsx), chat pane (ChatPane.tsx), agent sync hook (useAgentSync.ts) and crew window (crewWindowAgentMode.tsx) now pass the slot's kind. History rows and schedule jobs record no kind, so their pins stay raw. The raw id still drives tint, routing and search. "Conductor" is a new components.agentLabel.builtin_conductor key in every catalog under website/src/i18n/locales/ (en-XA regenerated by i18n:pseudo), reusing each locale's existing word for conductor.

Backwards compatibility

Compatible: the new kind argument is optional, and every label without the Conductor template reads exactly as before.

Removes nothing: only a display string changes; no id, key, field or path is taken away.

Tests

  • website/src/utils/agentLabel.test.ts (new): the template conductor reads "Conductor"; a same-named crewmate and a kind-less pin keep kirocrew-conductor; an unknown agent stays raw; the inherited default reads "Conductor · default"; French reads "Conducteur". On origin/main 4 of 6 fail (the crewmate and kind-less cases already pass there and guard against a name-only mapping).
  • website/src/test/ChatSidebar.defaultAgentMarker.test.tsx: a rendered session row shows "Conductor" for the template slot and the name for the crewmate slot. Fails when SessionRow stops passing s.agent_kind.
  • Determinism: both files run 5 times with --sequence.shuffle seeds 1-5, 17/17 each run.
  • Related frontend set (run_scoped_tests.py --surface frontend): 82 files, 1323 tests pass. src/i18n/ 50 files pass; tsc -p tsconfig.app.json, eslint and lint:i18n clean.

Manual verification

Ran the built SPA with stubbed slots (website/scripts/capture-21531-conductor-label.mjs): the template conductor's row and composer chip read "Conductor", the same-named crewmate row reads kirocrew-conductor, a kirocrew row is unchanged.

Screenshots / video

Session list and composer: template conductor reads Conductor, crewmate keeps kirocrew-conductor

Related Issues

Closes #21531

Pattern harvest

Not generalizable: one label helper gained a display name for one built-in template; there is no repeated defect shape to rule out.

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 21, 2026 23:14
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Oct 21, 2026
@github-actions

github-actions Bot commented Oct 21, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 0e1c9af193e323a44b06c472d5e43bec77a55937 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: a display-only label change in one shared helper, keyed on the kind each session recorded, with rendered evidence of this revision.

Notes

  • When a chat has no agent, the default path maps kirocrew-conductor by name alone, with no kind check. That holds only while the default is always a template (fix(session): a plain session is the default template, never the default crewmate #18342). If a crewmate can ever become the default, that crewmate would be mislabelled "Conductor · default".
  • The chip now reads "Conductor" while the agent picker still lists kirocrew-conductor. The PR scopes the picker out as "Not a goal", but a user who opens the picker from the chip sees two different names for the same agent.

[DESIGN-REVIEWED] 0e1c9af

Description read

[DESCRIPTION-READ] 7a1590d35a133cff3c2c08a76fa89cd1543615a12daf75857eef87da52c4737c

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 21, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 0e1c9af193e323a44b06c472d5e43bec77a55937 — 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. Issue #21531 is the source of the relabel, and the new tests fail on base. The one leftover is a lookup built to hold more names than the one it carries.

Notes

  • Item 7 — one consumer, generalized: export function builtinAgentDisplayName is a switch with one case. Outside agentLabel.ts it has 0 callers (grep builtinAgentDisplayName: the defining site plus the test). The description itself says "Only the Conductor has a code name a user meets." Subtraction: drop the export, and replace the switch with one ternary on 'kirocrew-conductor' inside agentOrDefaultLabel.

What this change ships

Inventory (8 items) — 7 justified

Intent: someone using Crew Mode sees "Conductor" instead of the code name kirocrew-conductor as the chat's agent. This is a FIX.

  1. Sidebar session row for a chat on the Conductor template reads "Conductor" — justified
  2. Composer and chat-pane agent chip read "Conductor" — justified
  3. Crew-window peer chip reads "Conductor" — justified
  4. Slot switcher list label reads "Conductor" — justified
  5. Agent-less chat whose default template is the Conductor reads "Conductor · default" — justified
  6. New components.agentLabel.builtin_conductor string in every locale catalog — justified
  7. Exported single-case builtinAgentDisplayName lookup — one consumer, generalized
  8. New screenshot harness capture-21531-conductor-label.mjs — justified

[FIRST-PRINCIPLES-REVIEWED] 0e1c9af

Description read

[DESCRIPTION-READ] 9f35224ed5e0cda51690a25f99f7d8ebdbeb8733aae5b6baefe381715a525496

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 21, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ✅ PASS

UX-level review of 0e1c9af193e323a44b06c472d5e43bec77a55937 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

UX-Verdict: PASS

Nothing blocks. The screenshot shows the new "Conductor" label on the session row and on the composer chip, and the blind reader read it correctly as "the name of the helper or assistant that ran this chat".

Notes

  • No screenshot shows the inherited-default label, "Conductor · default" (when a chat has no agent and the default template is the Conductor). It uses the existing <default> · default pattern, so it is not a blocker. Attaching a shot of it would complete the evidence.
  • The reader saw "Conductor" and "kirocrew-conductor" side by side and couldn't tell whether they were the same helper. That only happens when a crewmate shares the Conductor's name, which is rare. If it does happen, a crewmate marker on that row would separate the two; the raw name alone doesn't.

[UX-REVIEWED] 0e1c9af

Description read

[DESCRIPTION-READ] 9d7f1e0bc1c1e77584cb3ca2f3514212e166f10652a0c2ed0a493785993f93f5

That sha256 names everything this verdict read: the PR description, plus the 4 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 21, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 0e1c9af193e323a44b06c472d5e43bec77a55937 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 0e1c9af

Verdict parsed from the review's SHA-scoped output markers for commit 0e1c9af193e323a44b06c472d5e43bec77a55937.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 0e1c9af193e323a44b06c472d5e43bec77a55937: <one-sentence reason>

@github-actions

github-actions Bot commented Oct 21, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 0e1c9af193e323a44b06c472d5e43bec77a55937 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 0e1c9af

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 0e1c9af193e323a44b06c472d5e43bec77a55937: <one-sentence reason>

@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 head 0cfe1b2. The change looks good to ship. I found no blocking or should-fix issues.

What I checked:

  • agentOrDefaultLabel maps the name only when the slot recorded agent_kind === 'template'. A same-named crewmate and a kind-less pin keep the raw id. The old 'default' special case still behaves the same, because builtinAgentDisplayName('default') returns 'default'.
  • Every chip and row that labels a live slot now passes the slot's kind. History rows and schedule jobs keep the raw name, as the description says. The raw id still drives tint, routing and search; only the display string changes.
  • The new key exists in all 13 checked-in catalogs, and en.manual.json carries the English source.
  • No file is on a security-sensitive path. All five AI review lanes pass on this head.

Remaining maintainer checks before approval: the readiness label is still checking, PR Readiness is pending, and Backend Tests (Windows) shard 7 is red on this head. This PR changes frontend files only, so that shard is probably unrelated, but it must be green or rerun first. I will look again when readiness settles.

@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 22, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Status: the only red check on head 0cfe1b2 is Backend Tests (Windows) (7), failing test/test_backend_cards_advertised.py::test_no_new_runtime_site_gates_a_field_backed_line_on_a_set on acp/client_mcp_array.py. This is a main-wide red: the same test fails on a clean origin/main checkout (6e9766f). The fix is open in #22951, which also clears the Real Adapter lane red tracked in #22958. This PR needs no change. After #22951 merges, I will re-run the failed job once.

🤖 AI-assisted comment 🤖

@iamwhatever
iamwhatever force-pushed the fix/21531-conductor-display-name branch from 0cfe1b2 to 0e1c9af Compare October 22, 2026 01:58
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Rebased onto the #22951 fix (0cfe1b2 -> 0e1c9af, base 398772f). The diff is unchanged. Locally the scoped frontend tests, tsc and i18n lint pass, and the set-gate test that was red now passes. CI is re-running.

🤖 AI-assisted comment 🤖

@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: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Oct 22, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Review-ready on head 0e1c9af. pr_status.py --reviewers gpt,opus exits 0 with 105 checks passing and the label readiness: passed. Design, First Principles and UX all pass; GPT and Opus are fresh with no findings. green_age.py reports FRESH (main moved in nothing this PR touches). It is mergeable with no conflicts. The only step left is a maintainer's review.

🤖 AI-assisted comment 🤖

@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.

Approving head 0e1c9af.

Gates checked on this head:

  • Readiness label is passed and PR Readiness is green.
  • Required checks are green, including Coverage Gate.
  • All AI review lanes name this head, including UX. None of them blocks.
  • No open change request. The linked issue is tier T2. No security path is touched.

This head is a rebase only. The range diff matches the commit I reviewed before, so my earlier review stands. The Conductor now shows a plain name wherever a chat's agent is labelled.

@bolichen97
bolichen97 enabled auto-merge (squash) October 22, 2026 04:11
@bolichen97
bolichen97 merged commit a1d3703 into main Oct 22, 2026
106 checks passed
@bolichen97
bolichen97 deleted the fix/21531-conductor-display-name branch October 22, 2026 04:36
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 22, 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.

Show a plain name for the Conductor where a chat's agent is labelled

2 participants