Skip to content

fix(website): drop "whole" from the crewmate saved-agent card line - #21863

Merged
buluoray merged 1 commit into
mainfrom
fix/member-saved-agent-copy-19066
Oct 18, 2026
Merged

buluoray merged 1 commit into
mainfrom
fix/member-saved-agent-copy-19066

Conversation

@buluoray

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: The Agent Harness card stops telling users that crewmates load their "whole" saved agent on backends that only confirm part of it.

Since #16847, Claude Code, codex and deepseek confirm an enrolled crewmate's saved spec by projection. Those backends report some saved fields as projection gaps instead of applying them (hooks, toolsSettings, excludedTools, native tool limits, per-tool mounts, auto-approval; see docs/system-specs/modules/harness-parity.md, H6 paragraph). The card's detail line still read "Crewmates load their whole saved agent" on every backend that has the capability, so on those three it promised more than ships.

Why it matters

A user picking a harness for crewmates reads "whole saved agent" as "everything in my spec applies here". On Claude Code, codex and deepseek it does not, so hooks and auto-approval rules a user relies on are silently not applied.

Not a goal

  • No new card line id or per-backend wording. The label stays keyed per capability, as AgentBackendTab.tsx does for every line.
  • No change to crewCapabilities.newRuntime. feat(members): confirm saved member specs on Claude, Codex and DeepSeek #16847 already made it backend-neutral on main ("Saving leaves active sessions unchanged. A new runtime loads the saved version.").
  • No change to which backends are members of ACP_BACKENDS_MEMBER_CAPABILITIES or to how gaps are computed.

What changed (motivation → approach → change)

  • Symptom: the member_saved_agent detail line says "whole" on Claude Code, codex and deepseek, which report projection gaps.
  • Cause: the label predates feat(members): confirm saved member specs on Claude, Codex and DeepSeek #16847, when only the kiro family had the capability. It is one string per capability id (CAPABILITY_LABEL in website/src/pages/developer/AgentBackendTab.tsx), so it cannot say "whole" for kiro-cli alone without a second line id from agent_sdk/backend_cards.py.
  • Change: one neutral label for every backend, "Crewmates load their saved agent". The card already lists, per backend, "These settings in your agent config file will not take effect on {{name}}", so the fields a projecting backend does not apply are named right under the line (see screenshots). All 12 authored catalogs drop their "whole" word (zh-CN 完整, hi/bn पूरा/পুরো, es/pt todo, fr/it tout/tutto, de ganzen, ru весь, ja そのまま, ko 전부); en-XA.json is regenerated with npm run i18n:pseudo.
  • The comment on the LINE_MEMBER_SAVED_AGENT entry in src/kiro_crew/agent_sdk/backend_cards.py and the ACP_BACKENDS_MEMBER_CAPABILITIES row in docs/system-specs/modules/harness-onboarding.md still said "only kiro-cli" / "full saved agent spec"; both now match agent_sdk/backends_members.py: kiro-cli and KAS load the saved spec, Claude Code, codex and deepseek confirm the projection they consumed.

Backwards compatibility

Compatible: copy and a comment only; no key renamed, no API or data shape touched.

Removes nothing: the line, its key and its id are unchanged; only the label text changes.

Tests

  • website/src/test/AgentBackendTab.test.tsx ("folds the detail lines behind a disclosure and keeps them out of the count") now looks up the new label. Reverting en.json to the old label turns that test red (1 failed, run with -t "detail"); with the change the file passes 117/117.
  • npm run i18n:check passes (key parity, placeholders, pseudolocale).
  • scripts/check_comment_history.py with COMMENT_HISTORY_BASE_REF=origin/main passes.

Manual verification

Booted a pod from this worktree, opened Settings → Agent Harness, opened the Claude Code, codex, deepseek and Kiro CLI rows and expanded "Other differences (not counted)". Each shows "Crewmates load their saved agent"; the old string is absent. Claude Code, codex and deepseek also show the "will not take effect" list; Kiro CLI shows none. Translations were reviewed by reading only, not by a native speaker.

Screenshots / video

Claude Code (projecting backend): the new line, with the fields it does not apply listed under it.

Claude Code card

codex, deepseek, Kiro CLI

codex card

deepseek card

Kiro CLI card

Related Issues

Closes #19066
Refs #16847, #12451

Pattern harvest

Not generalizable: a single label written before a capability set grew; the card already sources per-backend gaps from data, which is what this relies on.

Decision for the owner

The decision is whether the projecting backends get their own card wording (a second line id) or one neutral label covers every backend. This draft picks the neutral label without "whole" and relies on the card's existing "will not take effect" list to name the gaps, because a per-backend label would need a new line id in backend_cards.py and a new key in every locale for the same information.

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

Contribution License Agreement

Contributions are accepted under the project's Apache-2.0 license; see the Licensing section of CONTRIBUTING.md.

Claude, Codex and DeepSeek now confirm a crewmate's saved spec by
projection and report hooks, toolsSettings, excludedTools, native tool
limits, per-tool mounts and auto-approval as gaps, so "Crewmates load
their whole saved agent" overclaims on those cards. The label is keyed
per capability, so it now reads "Crewmates load their saved agent" on
every backend, and the card's existing "will not take effect" list names
the fields a backend does not apply. Every locale drops its "whole"
equivalent; en-XA is regenerated.

Closes #19066
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Oct 18, 2026
@github-actions

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec — 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.

First-Principles-Verdict: PASS

Nothing to check.

What this change ships

Inventory (4 items) — 4 justified

Intent: stop the Agent Harness card from telling users crewmates load their "whole" saved agent on backends that only project it. FIX.

  1. The "Other differences" detail line now reads "Crewmates load their saved agent" on every backend, in all 13 catalogs — justified
  2. The LINE_MEMBER_SAVED_AGENT comment in backend_cards.py no longer says only kiro-cli has the capability — justified
  3. The ACP_BACKENDS_MEMBER_CAPABILITIES row in harness-onboarding spec no longer says "full saved agent spec" — justified
  4. The folded-detail test looks up the new label — justified

[FIRST-PRINCIPLES-REVIEWED] 446d100

Description read

[DESCRIPTION-READ] d48101a579b183d8fc2d66ac67bfaa23af4d83e4c1f36bce0e03f641a145d798

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

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Design-Verdict: PASS

Nothing to check.

[DESIGN-REVIEWED] 446d100

Description read

[DESCRIPTION-READ] 3e68dc0cb21e9310b08acbe3359add69762075a0f718510da845227361b9c0b4

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

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ✅ PASS

UX-level review of 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

UX-Verdict: PASS

Check that the green tick on "Crewmates load their saved agent" still reads as "everything applies". The "will not take effect" list, which says otherwise, sits two rows lower.

[UX-REVIEWED] 446d100

Description read

[DESCRIPTION-READ] fc442b4acdf1285310570c9e599a22006fc766a731e77845baa10c0d9da941e4

That sha256 names everything this verdict read: the PR description, plus the 7 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

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 446d100

Verdict parsed from the review's SHA-scoped output markers for commit 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec: <one-sentence reason>

@github-actions

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 446d100

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 446d1009b1aef8e409ae2d1a70b8b05a2ff479ec: <one-sentence reason>

@buluoray
buluoray marked this pull request as ready for review October 18, 2026 11:35
@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners October 18, 2026 11:35
@buluoray
buluoray requested a review from iamwhatever October 18, 2026 11:35
@buluoray
buluoray enabled auto-merge (squash) October 18, 2026 11:35
@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Oct 18, 2026

@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.

Tier 1 auto-approve: fix (16 files). Criteria: no conflict, no requested changes, security path denylist clean, design-doc gate clean, security checklist all-NO, no reviewer-lane findings, readiness signal fresh for this head SHA, declared category matches the diff. Category: the crewmate saved-agent card line drops "whole" in every locale, with the matching backend comment, spec line and test string.

@buluoray
buluoray merged commit 39439b2 into main Oct 18, 2026
106 checks passed
@buluoray
buluoray deleted the fix/member-saved-agent-copy-19066 branch October 18, 2026 13:07
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 18, 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.

Member copy: name the backends that confirm a saved spec, drop "whole" off kiro-cli

2 participants