Skip to content

fix: backport 0.12.1 late batch 4 (15 fixes merged 11-08 12:05-13:24Z) - #33207

Merged
buluoray merged 16 commits into
release/0.12.0from
crew/slack/0.12.1-late-4
Nov 8, 2026
Merged

buluoray merged 16 commits into
release/0.12.0from
crew/slack/0.12.1-late-4

Conversation

@buluoray

@buluoray buluoray commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Bring 16 fixes merged on main (13 on 2026-11-08 between 12:05 and 13:24 UTC, plus #30086, #30874 and #33221) onto release/0.12.0 for 0.12.1, one commit each, in a PR of their own.

Why it matters

Each fix changes behaviour a 0.12.0 user can hit today. On KAS: agent spec hooks get kiro-cli's stdin field names, the telemetry opt-out reaches KAS, a dashboard MCP tool switch stays off, the agent role comes back after a timed-out compaction, and KAS status reads during a gateway restart show offline. A claude PreToolUse hook now meets claude's built-in tools. The rest fix lost keyboard focus, Chinese chip separators, the Worlds scene fallback, the wake judge retry, page embed reset and the Bot webhooks token list.

Not a goal

  • No fix that is not already merged on main; nothing is changed only here.
  • No version bump, no tag, no CHANGELOG.md change.
  • No feature, CI, test-only, docs-only, refactor, perf or internal dev-tooling change.
  • No row that needs a prerequisite feature; the one hand port of production code and the rows left out are listed under What changed.

What changed (motivation → approach → change)

Each main squash commit was cherry-picked onto release/0.12.0 @ 80d6211963, in merge order on main, one commit each, with the (cherry picked from commit …) trailer. The repository's leak guard requires the public identity, so every commit is authored as Ray Xu and names its original author on an Original author: line.

# PR Original author main release
1 #33111 join the design tweak request chip parts with the locale's list Rohan Khanderia d86392c545 28307e7991
2 #33105 fall back to office for an unknown saved worlds scene Rohan Khanderia 99ebd1ba0e eed6f5e542
3 #33092 retry the wake judge once before a provider error fires a turn Joe Guo 94a6b06192 fc7e84708c
4 #32465 reset a page embed's conversation when its app is uninstalled Bolin Chen 1cd288151f a4c46b4a75
5 #30086 map claude built-in tool names onto kiro-cli tool ids Bolin Chen 28cb6801de 3bddd5a762
6 #30937 give agent spec hooks kiro-cli's stdin field names Joe Guo 2ee2df5237 5308db5b8e
7 #33059 leave KAS status reads that failed during a gateway restart to the offline state Zezhen Xu df553b0643 8b7db8a04f
8 #32597 list the tokens that run as a mate in its webhooks pane Bolin Chen de25ac3b9c b9ca9ee1f2
9 #33108 keep focus on the dismiss and undo buttons while they save Rohan Khanderia 9b1933a651 2a32d08751
10 #33128 keep focus on the auto improvement clone button while it runs Rohan Khanderia 48cac3a9f3 9b398db11b
11 #33149 restore the agent role after a timed-out kas compaction Bolin Chen 44877d2df9 cbf5125225
12 #33131 keep focus on the ops board poll and claim button while it runs Rohan Khanderia ce879f309d 8ebbeaa0e1
13 #33160 keep a separator between the design tweak chip counts in Chinese Ray Xu 02d4cbe1c4 2f9a41ed80
14 #33026 send kiro-cli's telemetry opt-out to KAS Joe Guo 4a75e4cfad 67425d10d9
15 #30874 keep a switched-off MCP tool off on the default backend Bolin Chen 34ba4ffd3c 7c210b0f6e
16 #33221 import the settings reader through the skill projection facade Ray Xu 0826d055ae b6ac0e2092

#33221 is the main fix for #33026's kiro_home import (kas_cli_settings.py bound its own kiro_home, so the skill projection facade tests saw two objects). It ships with #33026 so the two stay together on 0.12.

Hand-resolved hunks:

Left out of this batch:

PR Why
#33054 Conflicts in acp/batch_guard.py; needs #31274's creator-token rework (_shell_creates). Too long a chain.
#32602 Needs #32195 (mounted MCP wait budget) and #32600 (kerberos/ssh-agent relay, 20 files). Too long a chain.
#32972 Needs #26951 (KAS sessions on the Usage page) and #32583.
#32931 Needs the chunk_watch feature (#29356).

Backwards compatibility

None: each fix keeps its main PR's compatibility notes; nothing here changes stored data or config beyond what those PRs already shipped on main.

Tests

Proof: not provable -- other: a backport of main commits whose proofs ran on their own PRs

  • CI does not run the backend suite on PRs into release/*, so the related set ran here, one pytest process at a time with no xdist, with TMPDIR outside ~/.kiro/crew: the 15 Python test files the batch changes, 866 passed; 22 related compaction, KAS agent/env/settings, hook and decisions files, 1,052 passed.
  • Frontend: vitest on the 11 changed test files, 233 passed.
  • flake8 passes on the changed Python files.
  • After the fix(kas): import the settings reader through the skill projection facade #33221 pick: test_kas_cli_settings.py plus the skill projection family (13 files: test_acp_runtime_skill_projection_opt_out.py, test_native_skill_projection*.py, test_skill_projection_facade.py, test_skill_projection_sandbox_seal.py), 415 passed.

Manual verification

N/A - each fix was verified on its own main PR. The 0.12.1 RC soak is the end-to-end check.

Screenshots / video

Why no screenshot: the frontend picks carry the same rendered change as their main PRs, which show it.

Related Issues

Backport to the 0.12 line for 0.12.1 of #33111, #33105, #33092, #32465, #30086, #30937, #33059, #32597, #33108, #33128, #33149, #33131, #33160, #33026, #30874, #33221.

Sibling sweep

Siblings: none -- each source PR carried its own sibling sweep; this PR only carries those fixes.

Pattern harvest

Not generalizable: this PR only carries fixes already on main. The source PRs have their own harvest.

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.

… list (#33111)

Original author: Rohan Khanderia
(cherry picked from commit d86392c)
…#33105)

Agent Worlds restored the last scene by casting whatever string
localStorage held to a SceneKey. A key another build saved (a scene
added later, then a downgrade) named no scene, so every scene wrapper
stayed hidden, the canvas was blank and no scene chip was checked.

The saved key is now looked up in SCENES and falls back to office, the
same default as no saved key.

Original author: Rohan Khanderia
(cherry picked from commit 99ebd1b)
…es a turn (#33092)

Original author: Joe Guo
(cherry picked from commit 94a6b06)
…32465)

Original author: Bolin Chen
(cherry picked from commit 1cd2881)
A Hooks-page PreToolUse hook whose matcher names a kiro-cli tool
(execute_bash, fs_write, web_fetch, ...) never ran on a claude call:
claude's permission request carried no harness_tool_id, because claude
had no HARNESS_TOOL_TABLES row, and its title is the command or a prose
label, not the tool name.

Add CLAUDE_TOOL_IDS_BY_KIRO_TOOL and register it under
ACP_BACKEND_CLAUDE. The existing dispatch branch then names each claude
permission event from the _meta.claudeCode.toolName its tool_call frame
stamped (claude#Bash), so the hook matcher meets Bash, Write, Edit,
WebFetch and the rest. The name is read by hook matching alone, where a
hook can only refuse a call. harness_builtin_tool, the READ_ONLY proof
and the deny-target name, stays Side-Chat-only, so auto_deny_tools and
governance verdicts on claude are unchanged, and claude stays out of
ACP_BACKENDS_CREW_FIRES_SPEC_HOOKS.

A new claude-agent-acp 0.94.0 capture holds a Bash, Edit and WebFetch
pair; a test replays it through the real parser.

Original author: Bolin Chen
(cherry picked from commit 28cb680)

# Conflicts:
#	src/kiro_crew/docs/agent-spec-fields.md
A spec hook Crew runs in kiro-cli's place (KAS, goose, opencode, strands,
claude observer events) now reads the payload kiro-cli's V2 engine sends:
camelCase hook_event_name, tool_name as kiro-cli's full name (shell, read,
write, subagent, @server/tool), tool_tags, and assistant_response on stop.
~/.kiro/hooks file hooks and Hooks-page hooks keep their names. Governance's
events check still reads the store's PascalCase event.

Original author: Joe Guo
(cherry picked from commit 2ee2df5)
…estart to the offline state (#33059)

Fixes #32966

Original author: Zezhen Xu
(cherry picked from commit df553b0)
A webhook token can pin only an agent template, and its call runs that
template on the shared default memory. The mate editor's Webhooks pane
and its rail count matched a token's agent against the mate's name, so
no token ever matched and the default mate's pane said nothing was
bound even with a token on the kirocrew template it runs.

Match on what a call actually runs as: a token belongs to a mate when
the mate has no memory of its own and runs the token's template, the
same line the agent picker draws for a covered mate. A mate with its
own memory still lists nothing, because no token can start its turns.

Closes #30412

Original author: Bolin Chen
(cherry picked from commit de25ac3)
…le they save (#33108)

Original author: Rohan Khanderia
(cherry picked from commit 9b1933a)
…uns (#33128)

The setup panel's Clone was natively disabled while the clone ran,
which took it out of the tab order and dropped the focus of the
keyboard user who pressed it, though the repository step stays on
screen. Enter in the URL field could also start a second clone. Mark
the busy Clone with aria-disabled, route the button and Enter through
one start that claims the clone synchronously so a double press in one
tick starts one clone, give the busy state the muted look of a disabled
primary button, and keep disabling it for an empty URL.

A clone request that failed outright left nothing on screen once the
spinner cleared; both that failure and the backend's own refusal now
show through ErrorNotice.

Original author: Rohan Khanderia
(cherry picked from commit 48cac3a)
On a harness-managed backend (KAS) at an explicit threshold, a /compact
whose wait gives up with no status keeps the session with the failure
cooldown. The abandoned /compact can still finish, and the next turn's
pre-turn drain drops its late frames only after that turn's prompt is
built, so nothing restored the session-start context. That failure now
arms the one-shot re-injection; a status KAS reported (a refusal is
failed) arms nothing.

Closes #32247

Original author: Bolin Chen
(cherry picked from commit 44877d2)
… runs (#33131)

The Ops Mission Control board's Poll & claim button set native
`disabled` while the dispatch cycle ran. A disabled button leaves the
tab order, so a keyboard user who pressed it lost focus to the page for
the whole cycle. It now uses `aria-disabled` with the same dimmed look,
and the click claims the cycle in a ref, so a second press is ignored
even before the pending state re-renders.

Original author: Rohan Khanderia
(cherry picked from commit ce879f3)
…hinese (#33160)

#33111 joined the chip parts with a unit list. CLDR's zh unit list has no
separator, so a mixed-status request read "1 项进行中1 项已完成". A narrow
conjunction list keeps English as "1 in progress, 1 done" and gives zh and
ja "、". A zh-CN test pins the separator.

Original author: Ray Xu
(cherry picked from commit 02d4cbe)
KAS reads no cli.json, so kiro-cli's telemetry.enabled opt-out and the
KIRO_DISABLE_TELEMETRY / Q_DISABLE_TELEMETRY switches did nothing. Crew now
sends _meta.kiro.telemetryEnabled at initialize, failing closed on an
unreadable file, and shows a session notice because KAS does not confirm
the opt-out (or, for a folder-only opt-out on a shared process, that it was
not applied).

Original author: Joe Guo
(cherry picked from commit 4a75e4c)
A single MCP tool switched off from the dashboard could still be called
on the default backend, because that switch is saved outside the agent
spec and only the spec's own switches were applied there. Apply every
per-tool switch the other backends already read, the same way the
spec's own are applied, and pin it with a test.

Closes #25034

Original author: Bolin Chen
(cherry picked from commit 34ba4ff)
@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners November 8, 2026 14:05
@buluoray
buluoray requested review from Zedmor and removed request for a team November 8, 2026 14:05
@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Sensitive Change Review

Sensitive files changed:

  • src/kiro_crew/hook_runtime/script_hooks.py

  • No reasoning template for b6ac0e2 yet.

How to clear this check:

  1. The PR author posts the template below as a PR comment, with
    every field filled (N/A needs a reason). Keep the
    Head commit line: it must name the current head SHA.
  2. The check turns green within a minute, with no push.
  3. A new push resets this check: post it again for the new head.

Only the author's comment counts this way. A reviewer can instead
paste the filled template into an "Approve" review on this head.
Merging still needs a reviewer's approval.

## Sensitive change review
- Head commit: b6ac0e20924582e158fff90c09dc669230eeba68
- What rule changed:
- Before -> after (what was allowed/blocked, now):
- Worst case if wrong (breaks commands / leaks secret / locks user out):
- Evidence checked (which sandbox result proves it):
- No regression:
  - Tools still work (which tools/commands were run, result):
  - Backward compatible (old config / old data / old callers still work, how checked):
  - Existing tests (which suites passed on this head):
- How to undo:

@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 8, 2026
@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ✅ PASS (a BLOCK with no Trigger and no Outcome does not block)

UX-level review of b6ac0e20924582e158fff90c09dc669230eeba68 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

UX-Verdict: PASS

cannot evaluate: missing screenshots. This backport changes several dashboard surfaces, but the description attaches no image, so the blind read was not performed and nobody has looked at any of them.

Evidence gaps

  • Bot webhooks pane: the list now shows the tokens that run as the mate, because CrewWebhookSection takes the crew record (editingAgent) instead of a name string. A screenshot of the pane with a bound token listed would close this.
  • Design tweak request chip: the count separator now comes from fmtList(parts, { type: 'conjunction', style: 'narrow' }). Screenshots of the chip in English and in zh, showing "、", would close this.
  • KAS engine notice, KiroSignInNotice and the KasBundleCard error: during a gateway restart these alerts are now hidden (if (outageFailure) return null, statusFailed), and the card keeps only its Retry. Two screenshots would close this: the offline state with no alert, and the card's error after the gateway is back.
  • Worlds page: an unknown saved scene now falls back to office. A screenshot of the page after loading with a stale scene key would close this.
  • Dismiss/undo and auto improvement clone buttons: while saving, these now use aria-disabled instead of disabled. A screenshot of the busy state, at 50% opacity with focus kept, would close this.

[UX-REVIEWED] b6ac0e2

Description read

[DESCRIPTION-READ] 837782f25c0285ada4a29934e0847016f8e2518298b91c8d7a79a1d58d4a116d

That sha256 names everything this verdict read: the PR description, plus the 3 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 8, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of b6ac0e20924582e158fff90c09dc669230eeba68 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

This backports fixes already merged on main, and the one hand port (#33149's compaction reported tracking) is narrow and complete. Nothing blocks.

Notes

  • website/scripts/capture-32966-restart-alerts.mjs is a new screenshot harness that doesn't ship. That goes against "No … internal dev-tooling change" under Not a goal. Remove it, or account for it under What changed.
  • ## Backwards compatibility reads "None: …" rather than the Removes nothing: <why> shape. The only take-away is the CrewWebhookSection prop type, and its one caller (CrewEditorNextDialog.tsx:908) is updated in this patch.

[DESIGN-REVIEWED] b6ac0e2

Description read

[DESCRIPTION-READ] b5ac5b0af71b5d74a0a86a27cfa30f098f3ca49d21a705368a9165dd4942fd37

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 8, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of b6ac0e20924582e158fff90c09dc669230eeba68 — 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

Every item is a fix already merged on main, cherry-picked as is. The one hand port is declared and takes only the reported tracking that #33149 needs.

Notes

What this change ships

Inventory (10 items) — 9 justified

Intent: ship 16 user-visible fixes already merged on main to 0.12.0 users in the 0.12.1 release (FIX).

  1. Agent spec hooks on KAS get kiro-cli's stdin field names — justified
  2. A claude PreToolUse hook now matches claude's built-in tools (Bash/Edit/WebFetch) — justified
  3. The kiro-cli telemetry opt-out reaches KAS, with the facade import fix kept beside it — justified
  4. An MCP tool switched off in the dashboard stays off on the default backend — justified
  5. The agent role comes back after a KAS compaction times out (hand-ported reported tracking) — justified
  6. KAS status reads that fail during a gateway restart show offline, not an error alert — justified
  7. The wake judge retries once before a provider error fires a turn — justified
  8. Keyboard focus stays on the dismiss/undo, clone and poll/claim buttons while they run — justified
  9. Fixes for Chinese chip separators, the Worlds scene fallback, page embed reset and the webhook token list — justified
  10. Screenshot harness capture-32966-restart-alerts.mjs added — rides along, undeclared dev tooling

[FIRST-PRINCIPLES-REVIEWED] b6ac0e2

Description read

[DESCRIPTION-READ] 6ac5a1a9010a3797b648e0c1038aa8692e549e9723a0bf1fc4a24caad15eda7d

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 Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of b6ac0e20924582e158fff90c09dc669230eeba68 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] b6ac0e2

False positive or not applicable? A repository writer can comment:
/ai-review override gpt b6ac0e20924582e158fff90c09dc669230eeba68 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Security Scope Review -- ✅ PASS

Which legitimate operations does b6ac0e20924582e158fff90c09dc669230eeba68 newly refuse? Updated in place on each push. A script-confirmed regression blocks; the model proposes candidates and never decides a refusal.

Verdict basis: adjudicated, zero confirmed regressions.

Security scope review -- adjudicated candidates

  • macos-latest (platform posix): 8 classified, 0 newly refused, 8 still allowed.
  • ubuntu-latest (platform posix): 8 classified, 0 newly refused, 8 still allowed.
  • windows-latest (platform windows): 7 classified, 0 newly refused, 7 still allowed.

No candidate flipped from allowed to refused.

Scope-Verdict: PASS

Reason: The patch does not touch the shell deny composite (SHELL_DENY_TIERS in src/kiro_crew/hooks.py and its sensitive-bash / exfil / deny-rules tiers are unchanged), and the classifier has given no confirmed regression. The real tightenings are outside the composite and could not be adjudicated: Hooks-page PreToolUse matchers now reach claude built-ins, per-tool MCP switches are newly applied to KAS excludedTools, and a send that cannot record its embed line is now refused with a 503. All three are named below.

TIGHTENING: hook tool-name matching on the claude backend -- a Hooks-page PreToolUse deny hook written in kiro-cli names now meets claude's built-ins, so a claude call the user's hook means to refuse is no longer let through for lack of a name match: + ACP_BACKEND_CLAUDE: CLAUDE_TOOL_IDS_BY_KIRO_TOOL, with + "execute_bash": ("Bash",), / + "fs_write": ("Write", "Edit", "MultiEdit", "NotebookEdit"), (src/kiro_crew/acp/harness_tool_names.py).

ADJUDICATED: 15 candidates, 0 confirmed newly-refused

PLATFORM COVERAGE: posix and windows. The diff makes path assumptions in kas_cli_settings._settings_files (<kiro home>/settings/cli.json and <work_dir>/.kiro/settings/cli.json) and reads env switches (KIRO_DISABLE_TELEMETRY / Q_DISABLE_TELEMETRY). Each operation on those paths and switches has a posix row (~, /, VAR=1 cmd) and a windows row (%USERPROFILE%, \, set VAR=1 && cmd, .exe). The maintainers' test runs and the gateway log read are covered both ways. No any rows were written, because every row names a path or an executable. The claude tool-name mapping itself assumes no platform. One gap: the agent-spec read row (~/.kiro/agents/kirocrew.json) is posix only.

UNADJUDICATED:

  • Hook matching on claude (ScriptHookStore fire, reached from build_permission_event → qualified_harness_tool_id(harness_backend, harness_tool_name_cache.get(...)) → harness_tool_match_names → the CLAUDE_TOOL_IDS_BY_KIRO_TOOL row). Before this change an existing Hooks-page PreToolUse hook with matcher execute_bash, fs_write, shell, write, read or use_subagent did not meet a claude Bash/Edit/Write/Read/Task/Agent call. Now it fires on every claude permission request. A broad deny hook written for KAS/goose/opencode would newly refuse ordinary claude edits and shell commands, for example an fs_write hook that exits 2 outside an allowed directory, now applied to Edit on a file in the checkout. This is hook policy, not composite text, so no row can carry it. The inputs I would have submitted: a claude Edit of src/example.py, a claude Bash call running git status --porcelain, and a claude Task subagent spawn, each under a pre-existing fs_write / execute_bash / use_subagent deny hook.
  • The stdin payload of spec-origin hooks (run_script_hook ← ScriptHookStore: payload = spec_event if hook.spec_origin in ("user", "project")). A spec hook that branched on tool_name == "fs_write" or "execute_bash", or on hook_event_name == "PreToolUse", now sees write/shell and preToolUse. If it denies on unrecognised names, it now refuses calls it used to pass. Input I would have submitted: a spec preToolUse hook that allows only when tool_name is execute_bash, against a KAS run_command of git status. I could not check the events policy path: run_script_hook uppercases firing_event's first letter, but whether the policy's events list compares case-sensitively against the other names was not verified.
  • with_switched_off_tools (KasHarness custom-agent build → session_mcp_disabled_tools(agent, spec=spec) → excludedTools). A tool switched off in the global settings file is now excluded from every KAS custom agent, Crew's own servers included. Candidate: a kirocrew-core tool switched off globally while an app agent's spec still grants it.
  • The chat-send 503 (_api_chat_send: elif embed_line and not await ensure_slot_recorded(...) → history_unavailable). A person's first send from an app embed is now refused when the history store is unwritable, where before it ran without the record. Candidate: a first send with a valid embed_app while the conversation log is read-only.
  • The KAS telemetry opt-out fails closed (kiro_cli_telemetry_enabled returns False on an unreadable or blank cli.json). This refuses no operation, but a user's telemetry is turned off without their asking.

[SCOPE-REVIEWED] b6ac0e2

@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 8, 2026
…ade (#33221)

Original author: Ray Xu
(cherry picked from commit 0826d05)
@github-actions github-actions Bot removed the readiness: action required A blocking check or review needs attention label Nov 8, 2026
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 8, 2026
@github-actions

github-actions Bot commented Nov 8, 2026

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed b6ac0e20924582e158fff90c09dc669230eeba68 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] b6ac0e2

Verdict parsed from the review's SHA-scoped output markers for commit b6ac0e20924582e158fff90c09dc669230eeba68.

False positive or not applicable? A repository writer can comment:
/ai-review override fable b6ac0e20924582e158fff90c09dc669230eeba68 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 8, 2026
@buluoray
buluoray merged commit 55bd57d into release/0.12.0 Nov 8, 2026
25 of 29 checks passed
@buluoray
buluoray deleted the crew/slack/0.12.1-late-4 branch November 8, 2026 16:15
@github-actions github-actions Bot removed the readiness: action required A blocking check or review needs attention label Nov 8, 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.

1 participant