Skip to content

feat(crew): a Crew bot's harness follows Settings -> Agent Harness when unset - #29509

Merged
bolichen97 merged 2 commits into
mainfrom
feat/crewmate-harness-inherit
Nov 8, 2026
Merged

bolichen97 merged 2 commits into
mainfrom
feat/crewmate-harness-inherit

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Nov 4, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: A Crew bot with no harness of its own runs on the harness picked in Settings -> Agent Harness, and the person can see which harness Crew bots run on and why.

Today a Crew bot with no pin runs on agent.member_acp_backend, whose default is kas. Picking Claude Code or Codex in Settings -> Agent Harness moves every chat except Crew bots, and nothing on the page says Crew bots stayed behind.

Why it matters

Someone who picks a harness expects their Crew bots to use it. Today they silently keep running on KAS, so model lists, costs and tool behaviour differ between a Crew bot's chat and every other chat, with no hint why.

Not a goal

  • No new harness becomes able to run Crew bots: membership is the two existing sets in agent_sdk/backends_members.py, unchanged.
  • A Crew bot pin that cannot start still refuses (H17); it never falls back.
  • The enterprise KAS floor (RFC D6) and governance harness locks are unchanged and still win.
  • The picker's graduation out of Feature Preview already landed in feat(crew): pick a crewmate's agent harness from the runnable list #29498; this PR does not touch it.

What changed (motivation → approach → change)

Design: docs/request-for-change/rfc-crewmate-harness-follows-settings.md (#29442).

Resolution for a Crew bot's own chat and the workers it opens: Crew bot pin agents.<name>.acp_backend > an explicitly stored agent.member_acp_backend (legacy) > agent.acp_backend. Kiro CLI reads as KAS, as a stored member_acp_backend: "kiro" already does.

  • One resolver, in the loader. _read_backend_choice (config/loader_builders.py) now resolves an unset member_acp_backend from the already resolved agent.acp_backend through crewmate_inherited_backend (agent_sdk/backends_members.py). The loaded field stays the one answer, so its 20+ readers follow Settings with no edit and cannot disagree. The selection gate keeps its shape (H13).
  • Fallback, logged and shown. A Settings harness outside ACP_BACKENDS_MEMBER_CAPABILITIES ∩ ACP_BACKENDS_MEMBER_DISPATCH ∩ ACP_BACKENDS_MATE_WORKER_KIT runs Crew bots on KAS. Today that is Claude Code, Codex and KAS. The fallback is one warning per harness per process (_note_member_fallback, H3) plus one bell note (src/kiro_crew/crewmate_harness_notice.py), sent at start (src/kiro_crew/slack/gateway_runtime/service_boot.py) and on config change (config_watch.py).
  • Per Crew bot: worker spec. Only KAS carries a Crew bot's worker tool limits (ACP_BACKENDS_MATE_WORKER_TOOL_LIMITS) and its hooks / permissions / toolsSettings (applies_spec_policy), and the chat tool limits of its saved Capabilities spec (ACP_BACKENDS_MEMBER_TOOL_LIMITS). Such a Crew bot runs on KAS, chat and workers, with a log line, a bell note opening its page and readout source worker_spec (worker_spec_forces_kas in src/kiro_crew/crewmate_harness.py, fields from kas_only_worker_fields in src/kiro_crew/mate_worker.py). The answer is held in memory, read off the loop at start and on config change; the event loop only reads it and refreshes stale entries in a thread. watch_document in src/kiro_crew/config/live.py sees a stored-to-inherited change. Log text in src/kiro_crew/members_parts/member_sessions.py.
  • Pin to a harness Bots cannot run on. A pin to goose, opencode and the like runs the Bot on KAS with an error log and an error bell note (CrewBackendPin.checked); a pin that cannot start still refuses (H17). The Bot's model follows the harness it lands on, through the gate's backend.
  • Picker in line with RFC O6. This brings main's picker (feat(crew): pick a crewmate's agent harness from the runnable list #29498) in line with RFC O6: CREWMATE_CAPABLE_BACKENDS in src/kiro_crew/crewmate_harness.py now also needs ACP_BACKENDS_MATE_WORKER_KIT, so crewmate_harnesses() offers only harnesses a Bot can fully run (KAS, Claude Code, Codex). pi and deepseek leave the picker and a save rejects them. A hand-edited pin to them still runs on KAS with an error, as above. The picker and the pin fallback now read one rule, so no offered pick lands on KAS.
  • Moved-user notice (RFC section 6). The first Bot start after an unpinned Bot left KAS for the Settings harness rings one bell note, once per install (crewmate_harness_notice.deliver_moved, from refresh_session_verdict), claimed with an O_EXCL marker under the data home like kiro_on_kas_notice. Every bell note now names the route: Agent harness in the Bot's Profile → Settings on the Bots page.
  • Fresh read before a cold start. src/kiro_crew/session_allocation_parts/get_or_create.py awaits refresh_session_verdict off the loop before the factory; a template apply (src/kiro_crew/mate_worker_kit.py) is judged on the spec being written.
  • Model spelling on the effective harness. kiro_spelling_applies(backend) judges on the harness the pin runs on, inherited included; _pin_entitlement_backend judges an unpinned Bot on its own route, never the install's (src/kiro_crew/dashboard/handlers/agents.py, src/kiro_crew/dashboard/agent_admin/crew_update.py, src/kiro_crew/cli_commands_agent.py).
  • Where it comes from. inherited_harness_source in src/kiro_crew/crewmate_harness.py labels the answer legacy / settings / fallback, and crewmate_inherited_source adds worker_spec per Crew bot (member_acp_backend_declared() tells a stored value from none). GET /api/acp-backends returns it as crewmate_harness; the crew readout (crew_records.py) adds inherited_source and settings_harness.
  • Settings shows it. The copy says "Bot", untranslated, per docs/decisions/2026-10-30-the-standing-agent-is-called-a-bot.md. The Agent Harness panel gets one line under the picker naming the harness Crew bots run on and the setting that decided it; a fallback is a warning-coloured role="alert". A Crew bot's Inherited option names the same source. Types in website/src/api/client.ts, website/src/api/client/agents.ts, website/src/api/client/config.ts; copy in website/src/i18n/locales/ (bn.json ... zh-CN.json).
  • A comment in src/kiro_crew/connections/status.py no longer says Crew bots always run on KAS. Field help, config-baseline.json and the config / crew-mode specs describe the new default.

Backwards compatibility

Behaviour change for existing installs. An install with no stored agent.member_acp_backend whose Settings harness is Claude Code or Codex moves its unpinned Bots off KAS on upgrade, onto that harness (unless a Bot's worker spec needs KAS). Their model, tool gate and native conversation move with them; the next turn starts a new native session, and Crew's own transcript and memory carry over. Such a person gets one bell note, once per install, at the first Bot start, saying so and how to set a Bot back to KAS (Profile → Settings → Agent harness).

Behaviour change for existing pins. A Bot pinned to pi, deepseek, goose, opencode, strands or copilot used to run on that harness. It now runs on Kiro Agent, with an error bell note that names the pin and the route to change it (CrewBackendPin.checked). A new save rejects pi and deepseek, which the #29498 picker offered and saved (harness_pin_rejected, via CREWMATE_CAPABLE_BACKENDS adding the worker-kit term; RFC O6/O7). A pin that cannot start here still refuses (H17).

Unchanged: a stored agent.member_acp_backend (including kiro) resolves exactly as before. A pin to Kiro Agent, Claude Code or Codex still wins. On every other Settings harness, unpinned Bots run on KAS as before, now with a warning when that harness is not Kiro CLI or KAS. No key, field or route is removed, and the API responses only gain fields.

Readers of what tightened:

  • Save check: PUT /api/agents/{name} (dashboard/agent_admin/crew_update.py → crewmate_harness.harness_pin_rejected) now refuses pi and deepseek. Covered by test_crewmate_harness.py::TestCrewmateHarnesses::test_a_harness_without_the_worker_kit_is_not_offered_nor_saved.
  • Pin fallback: every session start reads the pin through crewmate_backend_pin → CrewBackendPin.checked, which lands a pin to a harness Bots cannot run on at Kiro Agent. Covered by test_crewmate_harness_inherit.py::TestUnrunnablePin.

Release note

  • Bots with no harness of their own now follow Settings → Agent Harness. If you picked Claude Code or Codex there, your Bots move off Kiro Agent to that harness, and their next turn starts a new conversation. To keep a Bot on Kiro Agent, set it in the Bot's Profile → Settings → Agent harness. The Bot picker now offers only Kiro Agent, Claude Code and Codex.
  • A Bot pinned to pi, deepseek, goose, opencode, strands or copilot now runs on Kiro Agent and shows an error saying so. To use another harness, pick Kiro Agent, Claude Code or Codex in the Bot's Profile → Settings → Agent harness.

Tests

  • test/test_crewmate_harness_inherit.py: TestColdStartRefresh::test_a_plain_bot_cold_start_sends_one_moved_note (a Bot cold start through refresh_session_verdict rings exactly one moved note; fails when deliver_moved is a no-op); test_moved_notice_shown_once_when_inherited_differs_from_kas; no moved note for a KAS Settings harness, a fallback, a pin or the legacy setting; test_no_bell_when_crewmates_follow_the_settings_harness still rings no fallback bell, and now asserts the moved note is owed.
  • test/test_crewmate_harness.py: pi and deepseek are neither offered nor saved; no offered harness is in kas_pin_harnesses().
  • test/test_crewmate_harness_inherit.py: each tier (settings, explicit legacy incl. a legacy value outside the inheritable set, "" as unset), Kiro CLI -> KAS (also on the bundle route), fallback for goose/opencode/strands/copilot and for pi/deepseek (worker kit), with one warning line; an inherited harness never refuses a Crew bot's worker; policy-denied Settings harness and denied KAS landing on the floor, pin wins / unstartable pin still raises CrewmateHarnessUnavailable, worker backend agrees with the readout, bell note once per harness / not for settings or legacy / again after moving away / still owed after a failed delivery, never raises, panel readout.
  • test/test_crewmate_harness_inherit.py (per Crew bot): tool limits, hooks, permissions or toolsSettings each run the Crew bot on KAS through the gate, pinned_backend and the worker route; a plain Crew bot follows Settings; legacy setting and pin never moved; inherited KAS reads no file; no fallback when KAS is not selectable; logged once, never for a pinned readout; the event loop never reads the file and a background refresh fills memory; the startup refresh reads each Crew bot once; chat tool limits; the watch sees an inheritance change; readout worker_spec; model judged on KAS; kas_only_worker_fields names each field; spelling follows the effective backend; loader mark never written back; per-mate bell note.
  • website/src/test/AgentBackendTab.crewmateHarness.test.tsx: the three lines and the alert role; nothing on an older gateway.
  • website/src/pages/members/CrewProfileSettings.test.tsx: the Inherited hint names each source.

Manual verification

Rendered both surfaces in a real browser with /api/ answered from fixtures: Settings -> Agent Harness on a Vite dev build, and Bot Profile -> Settings -> Agent harness on the built SPA. Each shot below is from this head.

Screenshots / video

Bots follow the Settings harness (Claude Code):

Bots follow Claude Code

Fallback: goose picked, Bots run on Kiro Agent, shown as a warning:

Fallback, light

Fallback, dark

Legacy agent.member_acp_backend decides:

Legacy setting

Bot Profile -> Settings -> Agent harness, open, with the Inherited hint for each source:

settings, Inherited is the Settings harness:

Inherited hint, settings

legacy, Inherited is the stored agent.member_acp_backend:

Inherited hint, legacy

fallback, the Settings harness is one Bots can't run on:

Inherited hint, fallback

worker_spec, this Bot's worker settings need KAS:

Inherited hint, worker spec

Owner decision: inherited pi or deepseek runs on KAS

RFC 5.8 leaves an inherited pi or deepseek to the owner. The owner decided that a harness Bots cannot run on falls back to KAS with an alarm: owner decision, recorded as O2 and O7 in RFC #29442 and amendment #30116. pi and deepseek have no worker kit, so an inherited one takes that fallback (crewmate_inherited_backend in src/kiro_crew/agent_sdk/backends_members.py), with the same warning as goose.

Merge order

  1. This PR (feat(crew): a Crew bot's harness follows Settings -> Agent Harness when unset #29509) first.
  2. feat(settings): fold Agent Harness details behind a summary so the picker comes first #32849 (simpler Agent Harness page) rebases on it after it lands.
  3. feat: run the kiro cli harness on v2 and kas on v3 #31801 (Kiro CLI runs V2, KAS runs V3) does not depend on this PR. Whichever of the two lands second rebases.

#31801 decides how a kiro pin behaves under O7: it makes a Bot kiro pin start kiro-cli and leaves "should it run on KAS" to the maintainer. This PR does not change a kiro pin (bots_cannot_run_on skips Kiro CLI, and CrewBackendPin.resolve keeps its launch rule). It only maps an inherited Kiro CLI Settings harness to KAS (RFC 5.1).

Related Issues

Part of #21910

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 November 4, 2026 08:48
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 4, 2026
@github-actions

github-actions Bot commented Nov 4, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ✅ PASS

UX-level review of 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

UX-Verdict: PASS

Nothing blocks: screenshots 01–08 cover all eight new lines, the blind reader read each one correctly, and no element is swapped out.

Notes

  • crewmate_harness_legacy and profile_harness_source_legacy show the raw key "agent.member_acp_backend in config.json". The blind reader "wouldn't know how to find or change it". Say what to do instead, e.g. "Bots run on {{harness}}, set in your config file. Remove that setting to follow the harness picked here."
  • profile_harness_source_worker_spec ("This bot's workers use settings {{settings}} can't carry") drew "no idea… I couldn't fix whatever it's complaining about". Name the settings involved (tool limits, hooks or permissions) and where to change them.
  • In shot-04, the legacy line under "Agent Harness" sits next to a Claude Code row marked "In use". The reader said "'In use' doesn't mean what I'd think". The line should scope "In use" to new chats, e.g. "New chats use Claude Code; bots run on Kiro Agent…".

[UX-REVIEWED] 83cab22

Description read

[DESCRIPTION-READ] 77e42d96a4179b33864c2041a5e1e0f451d801a4220a565cc9648ea19103d9b2

That sha256 names everything this verdict read: the PR description, plus the 11 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 4, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: unset Bot harnesses now resolve once in the loader, every existing reader picks that up, and the fallback and pin behaviour match H17 and the RFC.

Notes

  • Pins to goose, opencode, pi or deepseek used to run on that harness and now run on KAS. That take-away sits in the truncated ## Backwards compatibility section, so its full reader list could not be checked here.

[DESIGN-REVIEWED] 83cab22

Description read

[DESCRIPTION-READ] c00444effe8709d4f80c85a9c890eac3c67baebb8c7f76d2e0bac05323e01860

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 4, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ human override accepted

@iamwhatever overrode this lane for 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c via /ai-review override (this commit only).

@github-actions

github-actions Bot commented Nov 4, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 83cab22

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 4, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 83cab22

Verdict parsed from the review's SHA-scoped output markers for commit 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c false-positive: <reason, 20 to 500 characters>

@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 4, 2026
@iamwhatever
iamwhatever force-pushed the feat/crewmate-harness-inherit branch from 8c5e79d to 711be6d Compare November 4, 2026 09:11
@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention merge conflict Branch has merge conflicts with its base — author must resolve before merge and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Nov 4, 2026
@iamwhatever
iamwhatever force-pushed the feat/crewmate-harness-inherit branch from 711be6d to 5cb0906 Compare November 5, 2026 06:16
@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: action required A blocking check or review needs attention merge conflict Branch has merge conflicts with its base — author must resolve before merge labels Nov 5, 2026
@iamwhatever
iamwhatever force-pushed the feat/crewmate-harness-inherit branch from 5cb0906 to 485e542 Compare November 5, 2026 06:39
@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 5, 2026
@iamwhatever
iamwhatever force-pushed the feat/crewmate-harness-inherit branch from 485e542 to c57901c Compare November 5, 2026 07:57
@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: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Nov 5, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author

@buluoray rebase only: the head is now 562ae7c59062 (still one commit), rebased onto main 0795ebc479. It changes nothing for review 5803783347.

  • src/kiro_crew/slack/gateway_runtime/service_boot.py: main added the set-aside-skills bell block to _init_dashboard. I kept it, after this PR's crewmate_harness_notice.schedule call, which stays inside the not self._test_mode block.
  • test/test_dashboard_server_composition_contract.py: the lazy-import count is 135. That is main's 134 plus this PR's one name.

No other code changed. Local GPT and Opus found nothing blocking, and the related tests pass (1519).

Could you re-review?

@iamwhatever

Copy link
Copy Markdown
Contributor Author

@buluoray this push is a rebase only. The head is now c8e564601d38 (still one commit), on main b2b05f6d14. Nothing changes for review 5803783347.

  • docs/system-specs/modules/config.md: main added the "Sandbox-loosening content provenance" paragraph. I kept it, and this PR's harness-choice paragraph follows it unchanged.
  • test/test_dashboard_server_composition_contract.py: the lazy-import count is 136, which is main's 135 plus this PR's one name.

No other code changed. The security package line-budget test now passes on this head, because #32252 is on main. Local GPT and Opus found nothing blocking, and the related tests pass (1610).

Could you re-review?

@iamwhatever

Copy link
Copy Markdown
Contributor Author

/ai-review override first-principles c8e5646 owner-decision: same owner decision as #29509 (comment) (RFC #29442 and its revision #30116 are merged; only the RFC status line still reads draft).

@github-actions

github-actions Bot commented Nov 7, 2026

Copy link
Copy Markdown
Contributor

Human judgment recorded

@iamwhatever recorded a owner-decision release (class owner-decision) for the first-principles AI finding on c8e564601d38da483a67ce106a770047cfee70b6.

same owner decision as #29509 (comment) (RFC #29442 and its revision #30116 are merged; only the RFC status line still reads draft).

This decision applies only to this commit. A new push requires a new judgment.

buluoray
buluoray previously approved these changes Nov 7, 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.

🤖 Kiro Crew Auto-Pipeline [operator: buluoray]:

APPROVE on c8e5646. Every item from the change request on 07285d9 is fixed at this head, and I found no new defect.

What it does for users: a Bot with no harness of its own now follows Settings → Agent Harness. A Claude Code or Codex user's Bots run there instead of staying on Kiro Agent. The Settings page says which harness Bots run on and why. The person whose Bots moved gets one bell note at the first Bot start. A Bot pinned to a harness Bots cannot fully run on now runs on Kiro Agent and shows an error saying so.

Earlier change request, item by item (checked at this head, not taken from the author's summary):

  • Pins misdescribed: fixed. Backwards compatibility now has a "Behaviour change for existing pins" entry. It says pins to pi, deepseek, goose, opencode, strands or copilot now run on Kiro Agent with an error bell, that a new save rejects pi and deepseek, and that an unstartable pin still refuses. Source agrees. CrewBackendPin.checked (crewmate_harness.py:166) sends a pin that bots_cannot_run_on matches to KAS through the gate and sets harness_fallback. resolve still raises CrewmateHarnessUnavailable for a pin that cannot start (H17). CREWMATE_CAPABLE_BACKENDS (:697) adds ACP_BACKENDS_MATE_WORKER_KIT, so harness_pin_rejected (:771) refuses pi and deepseek. "Removes nothing" and "a pin still wins" are gone. The PUT route only judges acp_backend when the body carries it (crew_update.py:361), and the profile page sends one key per save. So a Bot with an old pi pin can still save its other settings.
  • Reader lines: added, under "Readers of what tightened". They cover the save check (crew update route → harness_pin_rejected, test_a_harness_without_the_worker_kit_is_not_offered_nor_saved) and the pin fallback (crewmate_backend_pin → CrewBackendPin.checked, TestUnrunnablePin). I found no other writer of a Bot's acp_backend pin in src: the crew update route is the only save path.
  • Release note: fixed. The second line now covers the pinned-Bot move and the route back.
  • Coverage gap: closed. TestColdStartRefresh::test_a_plain_bot_cold_start_sends_one_moved_note drives refresh_session_verdict twice and asserts one note.

Since the earlier head: the push is a rebase onto main, plus that one new test and the lazy-import count in test_dashboard_server_composition_contract.py (now 136). I compared the PR's own patch at both heads with range-diff, and nothing else changed. One question I checked: does an inherited member_acp_backend reach disk on a whole-config save and freeze the inheritance? It does not. save() restores the harness fields from the stored document (_restore_stored_harness_fields, loader_config.py), and the PATCH writers write deltas.

Evidence:

  • Mutation 1: replacing the deliver_moved call in refresh_session_verdict (crewmate_harness.py:636) with a no-op reddens TestColdStartRefresh::test_a_plain_bot_cold_start_sends_one_moved_note (assert 0 == 1). The other 111 tests in the file pass. Restored, tree clean.
  • Mutation 2: dropping the worker-kit term from CREWMATE_CAPABLE_BACKENDS reddens test_a_harness_without_the_worker_kit_is_not_offered_nor_saved[pi] and [deepseek]. Restored, tree clean.
  • Tests on the clean head: test_crewmate_harness_inherit.py, test_crewmate_harness.py, test_kas_cli_floor.py, test_mate_spec_policy.py, test_dashboard_server_composition_contract.py and test_config_live_server_appliers.py ran 470 passed, 0 failed. I did not run the full suite or the frontend tests this round.
  • CI on this head: 85 success, 11 skipped, none failed. PR Readiness is success. The merge with main is clean (merge-tree exit 0). take_away_check.py passes locally against the current body: no take-away shape in the diff.
  • Lanes: Opus and GPT found nothing blocking. Design and UX gave PASS. First Principles was released by the author as an owner decision. That release points to RFC #29442 and amendment #30116, which maintainers merged.
  • Source-only: the Settings panel copy and the bell note text. I read them but did not render them.

Non-blocking follow-ups:

  • The reader list is prose bullets. take-away-changes.md asks for Reader: <path>:<symbol> -- <entry> -- <test> lines. Each bullet already has the path, the symbol and the test. Rewriting them in that form, with the entry named (crew page for the save check, chat and the spawn entry for the pin fallback), would match the rule.
  • The release note says the picker offers "only Kiro Agent, Claude Code and Codex". Where the host's kiro-cli is confirmed to serve v3, a Kiro CLI pin resolves to KAS, so crewmate_harnesses() also lists Kiro CLI. That was already true on main, and the pin runs on Kiro Agent, so the note is close enough. A parenthetical would make it exact.
  • The UX lane's evidence gaps still stand. No screenshot shows the Bot profile's Inherited hint. The Agent Harness screenshots show the older "Mates" wording, not the "Bots" copy this commit ships.
  • The Design lane notes that a pin to goose and similar harnesses now runs on Kiro Agent instead of refusing. That gives a second "pin not honoured" path next to H17. RFC amendment #30116 records this as the chosen behaviour, so I treat it as decided.

@bolichen97

Copy link
Copy Markdown
Contributor

requesting name change and simplify harness selection setting UI. too wordy

@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.

requesting name change and simplify harness selection setting UI. too wordy

@iamwhatever

Copy link
Copy Markdown
Contributor Author

@bolichen97 thanks for the review.

  • Name: done in c8d0d5f (head c8d0d5f0c64b8f715ed70581ca0d2a6b3c6eaeab, rebased onto latest main). Every human-readable line this PR adds now says "Crew bot", not "crewmate": log and warning messages, docstrings, comments and the spec prose in docs/system-specs/modules/crew-mode.md and config.md. Code identifiers, module names, config keys and RFC slugs (crewmate_harness.py, agent.member_acp_backend, ...) keep their names because main already uses them. UI copy that already says "Bot" stays as it is, per docs/decisions/2026-10-30-the-standing-agent-is-called-a-bot.md.
  • Simpler harness setting UI: this goes to a separate follow-up PR so feat(crew): a Crew bot's harness follows Settings -> Agent Harness when unset #29509 does not restructure the page. That PR is in progress; I will link it here once it is open.

Re-requesting review from you and @buluoray.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

/ai-review override first-principles 78feaa1 owner-decision: same owner decision as #29509 (comment) (RFC #29442 and its revision #30116 are merged; only the RFC status line still reads draft).

@github-actions

github-actions Bot commented Nov 8, 2026

Copy link
Copy Markdown
Contributor

Human judgment recorded

@iamwhatever recorded a owner-decision release (class owner-decision) for the first-principles AI finding on 78feaa1518a27e1f690fe350e1be33646ba559c3.

same owner decision as #29509 (comment) (RFC #29442 and its revision #30116 are merged; only the RFC status line still reads draft).

This decision applies only to this commit. A new push requires a new judgment.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

@bolichen97 the simpler Agent Harness setting UI is in #32849 (#32849). This PR now only does the rename to Crew bot.

@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.

This head needs fresh UI evidence before review can finish.

  1. website/src/pages/members/CrewProfileSettings.tsx:62 and website/src/i18n/locales/en.json:8388. The UX lane on 78feaa1 could not evaluate this head, and a verdict blocked by missing evidence counts as a BLOCK. Two gaps:

    • Shots 01, 02 and 04 show the old copy ("Mates run on Claude Code ... A mate can pin its own in its settings."). This head ships "Bots run on {{harness}}, the harness picked here. A Bot can pin its own in its settings."
    • The new Inherited hint in Bot Profile > Settings > Agent harness has no screenshot. That is inheritedHarnessHint, with the four source strings at en.json:9304-9307. A unit test does not show how it renders.

    Smallest fix: retake shots 01, 02 and 04 on the current head. Then add one shot of the Bot Profile harness picker, open, with the Inherited hint for each source (settings, legacy, fallback, worker_spec). After that, re-run the UX lane. No code change is needed.

Optional:

  • src/kiro_crew/dashboard/handlers/agents.py:1751: the _pin_entitlement_backend docstring still describes the namespace comparison this PR removed. The body now always resolves the Bot's own member route.
  • src/kiro_crew/agent_sdk/backends_members.py:526: an inherited pi or deepseek now falls back to KAS. RFC 5.3 lists that option as "Not chosen", and amendment 5.8 leaves it to the owner. A link to that decision in the body would help.
  • Please name the merge order with #31801 and #32849, and say which PR decides how a kiro pin behaves under O7.

Joe Guo added 2 commits November 8, 2026 06:13
Owner decision on bolichen97's review: log and warning messages, docstrings,
comments and spec prose that #29509 adds say 'Crew bot', not 'crewmate'.
Code identifiers, module names, config keys and RFC slugs keep their names
(main already uses them).

English copy this PR adds writes 'bot' in lowercase after another word, per
docs/decisions/2026-11-08-bot-is-lowercase-after-another-word.md (en.json,
en-XA.json, bell notes, field help, log lines).

The _pin_entitlement_backend docstring now describes what the body does:
with no pin it always returns the Bot's own member route.
@iamwhatever

Copy link
Copy Markdown
Contributor Author

@KiroCrewCaptain thanks. Review 5816581816 is addressed on 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c (rebased on main 1dde2fb14f):

This head also follows docs/decisions/2026-11-08-bot-is-lowercase-after-another-word.md: English copy this PR adds writes "bot" in lowercase after another word.

Re-requesting review from @KiroCrewCaptain, @bolichen97 and @buluoray.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

/ai-review override first-principles 83cab22 owner-decision: same owner decision as #29509 (comment) (RFC #29442 and its revision #30116 are merged; only the RFC status line still reads draft).

@github-actions

github-actions Bot commented Nov 8, 2026

Copy link
Copy Markdown
Contributor

Human judgment recorded

@iamwhatever recorded a owner-decision release (class owner-decision) for the first-principles AI finding on 83cab225f9c7e7a3d7aa8de2280a87bb29dd549c.

same owner decision as #29509 (comment) (RFC #29442 and its revision #30116 are merged; only the RFC status line still reads draft).

This decision applies only to this commit. A new push requires a new judgment.

@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.

Review result on 83cab22: no blocking defect found. Upgrade behaviour changes for unpinned Bots and for existing pins. The RFC this PR implements is still marked draft on main, and a change request asking for simpler, shorter harness settings copy is still open.

Earlier change request from this account, item by item:

Optional:

  • platform/bootstrap.py:529: bots_may_run_on_kas returns True on any inherited install. On a host where Settings picks Claude Code or Codex and the Kiro CLI lacks the v3 engine, the floor now logs "Kiro Crew is using kiro-cli instead" even though no Bot moved. Word the notice from what actually moved, and add a test for that case in test_kas_cli_floor.py.
  • agent_sdk/backends_members.py:526: the worker-kit term sends an inherited pi or deepseek to KAS. RFC 5.3 and 5.4 say otherwise, and 5.8 leaves the question to the owner. A one-line RFC amendment would make the code and the design agree.
  • test/test_mate_spec_policy.py:317: the template-apply test monkeypatches _crewmate_backend with a copy of its new body. If you revert mate_worker_kit.py:494, every test still passes. Let the real function run against the patched KiroCrewConfig.load.

@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 83cab22, and recording the maintainer design sign-off this PR was waiting on.

  • Name: done. The text this PR adds says "Crew bot", and the UI copy keeps "Bot" per the recorded decision.
  • Simpler harness setting UI: I accept the split. That work lands in #32849, which rebases on this PR as the Merge order section says, so this PR is not held for it.
  • Design: I accept both upgrade changes the description lists. On an install with no stored agent.member_acp_backend whose Settings harness is Claude Code or Codex, unpinned Bots move off KAS onto that harness, with the one-time moved note. A Bot pinned to pi, deepseek, goose, opencode, strands or copilot now runs on Kiro Agent with an error bell note naming the pin, and a new save rejects pi and deepseek. A stored agent.member_acp_backend and pins to Kiro Agent, Claude Code or Codex resolve as before.

Captain's optional notes (the bots_may_run_on_kas notice wording, the RFC 5.3/5.4 amendment for pi/deepseek, and the _crewmate_backend test that copies its body) are fine as follow-ups.

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