Skip to content

fix: 0.13 backport batch 1, part 1 of 3 (KAS and user-reported fixes) - #37323

Merged
buluoray merged 28 commits into
release/0.13.0from
crew/slack/backport-0.13.0-batch1
Nov 14, 2026
Merged

buluoray merged 28 commits into
release/0.13.0from
crew/slack/backport-0.13.0-batch1

Conversation

@buluoray

@buluoray buluoray commented Nov 14, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Bring the KAS fixes and the user-reported fixes that merged on main after the 0.13 cut to release/0.13.0, so 0.13 ships them.

Backport batch 1 onto release/0.13.0 (head 0740c4ddf333, v0.13.0-rc.1). The branch was cut from main at a29fcc3c2e6b (#36271). Since then 248 fix and perf commits merged on main. Batch 1 carries the 38 that fix KAS or that users reported, plus 23 prerequisites, so every pick applies with its main context instead of a hand port. Its diff is over the 1 MB that the AI review lanes accept, so it lands as three PRs in main's merge order. This PR is part 1 of 3: 14 picks and 14 prerequisites. Parts 2 and 3 open on top of it once it merges, and the other fix and perf commits follow in later batches.

One commit per pick, each made with git cherry-pick -x in main's merge order. 27 applied with no conflict. One needed a hand-resolved hunk, listed below.

Pick Main commit Tag What 0.13 users get
#36603 5275a5d20578 KAS Skip the kas engine's own title request on new sessions.
#36534 ac459818278e KAS Refuse a KAS shell command batched after an unfinished file write.
#35510 94155a140d1d KAS Show a refused kiro-cli credential as an error on kas.
#36818 4c7a87435736 KAS Read a custom agent's prompt the way KAS does on every backend.
#29602 848e002464ab user report Show a container's memory limit, not the host's.
#36621 6fa4982ce7e8 user report Keep the chat column at scroll offset 0 after an undone paste.
#36829 911bde870db3 KAS, user report Show the project hook-files notice once per chat.
#36207 ecf7d5690d14 KAS, user report Drop the dead use button on the kiro cli row.
#36819 918a1c8b7fca KAS Show the policy cache to managed MCPs under a central ceiling.
#36783 ebdd1312b6d6 user report Let a settings reset wait for a running turn.
#36744 58d688e592a3 user report Keep a bundled server's env keys when a user entry shares its name.
#36913 ed9d0b0161f9 user report Show the memory now figure while sharing is off.
#36878 8c58e1835667 user report Show the blocked link card in a bot's chat.
#31546 d1f38d7f4384 KAS, user report Re-create a reclaimed one-run work dir before a KAS session starts.
Prerequisite Main commit Needed by What it is
#36536 3b22e3343dd2 #30062 Let the rm root row pass a plain rm of /tmp entries.
#36538 e80a1310a88c #36813 Add a harness requirements checklist and per-harness gap analysis.
#36530 5ea941c85433 #37093 Lighter own servers and fewer tool loads on the default chat.
#36362 62f35ec10920 #37097 Log an offline catalog miss as one line, not a traceback.
#36558 ee81308536c7 #37097 Stop spawned app backends when graceful shutdown runs out of time.
#36238 db39373e2128 #36845 One scheduler for crew-workers reads.
#36593 aeb98ebf5760 #37097 Take the process-tree record and per-server config reads off the prompt.
#35590 712d24f0514c #37097 App grants find store servers, enable reaches open chats.
#36262 b77f3df1defd #36845 Bound a slot-detail page by bytes and revalidate it.
#36550 a67f6ed09030 #30062 Start a fresh opencode session when a chat's folder changed.
#36845 714b0d5355a3 #36878 Refresh a slot by echoing its cursor, never read it unbounded.
#36069 21b6680926a3 #36135 Show a paused share on the rail and name an env-only change. Hand-resolved, see below.
#36756 0b32483700fa #36813 Name a Windows policy block on the direct client spawn.
#36586 45793882e566 #37097 Log one warning while adoption waits for a pending config review.

Each prerequisite is itself a fix or perf commit from main, except #36538, which changes docs only. Each one has its own tests on main, and none changes behaviour beyond what its own PR describes. "Needed by" names the pick whose conflict pulled it in, which may land in part 2 or 3: without the prerequisite, that pick conflicts on code it added.

Why it matters

0.12.2 was the last 0.12 release, so 0.13 is the next release users get. The KAS picks in this part fix a shell command batched after an unfinished file write (#36534), a refused kiro-cli credential shown as success (#35510), custom agent prompts (#36818), managed MCPs under a central policy (#36819), a reclaimed work dir (#31546), and the title request every new KAS chat sends (#36603). The other picks fix bugs that users reported after the cut.

Not a goal

  • Features, refactors, tests-only and docs-only commits from main, unless a pick needs one (only the docs prerequisite above).
  • Batch 1 parts 2 and 3, and the other fix and perf commits: they come in later PRs.

What changed (motivation → approach → change)

Hand-resolved hunk

No code line was hand-resolved. Original authorship is named in the commit message.

Backwards compatibility

Compatible. Each pick behaves as it does on main, where it was reviewed. Nothing is removed: no key, path or record.

Tests

Test changes come from the picks.

Release PRs get no backend test lanes in CI, so the backend tests ran locally: one pytest process per batch of 20 files, no xdist.

  • This part, head d3e548c41c29: 1,857 test files (every test file the picks touch, plus every test file that imports a module they change). 79,533 passed, 253 failed. Every failing batch fails the same tests on a clean release/0.13.0 checkout run the same way. The four files that fail only inside one batch (test_agent_panel_routes_dashboard.py, test_agent_publish_endpoint.py, test_agent_refactor_contracts.py, test_agent_refactor_fork_refresh.py) pass when run alone, here and on clean release.
  • All of batch 1 together (parts 1 to 3, head 6827ef9267da): 2,775 test files, 117,266 passed, 146 failed, all of which also fail on clean release.

Frontend, all of batch 1: tsc -p tsconfig.app.json is clean. The 27 vitest files the picks touch: 26 pass. The other one, CrewChatWindow.test.tsx ("draws a code fence in a peer USER row copy-only too"), fails the same way on a clean release/0.13.0.

flake8 and black on every Python file in the diff: clean.

Manual verification

N/A. Unit coverage above; the same changes are on main.

Screenshots / video

Why no screenshot: every frontend change here is a backport of a main PR that carried its own screenshots.

Related Issues

Backport of the main PRs listed above.

Sibling sweep

Siblings: none -- the backport touches the same sites the picked PRs changed on main

Pattern harvest

Not generalizable: backport of already-reviewed fixes

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: ...). A backport batch keeps one commit per pick.
  • 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.

iamwhatever and others added 28 commits November 14, 2026 18:16
…36536)

The local-destructive-rm-rf-root row matches its pattern anywhere in the
text, so `rm -rf /tmp/build && mkdir -p /tmp/build` was refused as a
deletion rooted at the filesystem root. Only the literal -rf spelling is
refused: -fr, -r -f and --recursive --force already pass on main, so the
row protected nothing for these paths and only pushed agents to respell.

The row now reads a view of the command in which the words of each plain
`rm` whose every operand is a direct /tmp/<name> entry are blanked. The
rm must be the unquoted program word (after kiro-cli's "Running:" title
prefix at most), every word literal (no $, glob, brace, paren, quote or
escape), no `--`, nothing glued on either edge (a backtick or paren
there lets bash add operands), and each operand exactly one component
under /tmp, so no folder on the way can be a symlink an earlier command
planted. Redirections stay in the text. Every other row, and the rm
floor for / and ~, still read the full text.

Four existing tests used /tmp/<name> as an always-refused example; they
now use /srv/<name> (or /etc), keeping what each test checks.

Replay of 25 recorded rm-row false positives: 17 now allowed; every
recorded true positive is still refused. No catalog regex changed.

Co-authored-by: Joe Guo <zejiangg@amazon.com>
(cherry picked from commit 3b22e33)
…is (#36538)

Co-authored-by: Joe Guo <zejiangg@amazon.com>
(cherry picked from commit e80a131)
…36603)

The KAS engine sends one extra model request at a session's first
prompt to title the session for kiro-cli's own session list. Crew
titles its chats itself and never reads that title, so apply_spawn_env
sets KIRO_DISABLE_SESSION_TITLE_LLM=true on both routes; an inherited
value wins.

Closes #35799

(cherry picked from commit 5275a5d)
…at (#36530)

Every chat starts Kiro Crew's own MCP servers, and each loads its tool
handlers right after its tool list. kirocrew-guide, kirocrew-mate and
kirocrew-cron imported all of kiro_crew.mcp_core for its HTTP verbs and
identity resolvers, which loads the whole core server: about 970
package modules and 90 MB per process, three times per chat.

The verbs (_send, _get, _post, _patch, _put, _delete) move to the
gateway owner, mcp_core_parts/gateway.py, beside the target resolution
they already used. mcp_core stays their import path and patch surface
through its mirror facade. The three servers import the verbs and the
identity resolvers from mcp_core_parts, so their handler modules load
about 310 to 430 package modules and never the core server. The listing
import-budget test now also bounds each small server's handler import.

The default agent's never-defer row also gains its six most used small
own tools (autonudge_stop, memory_recall, nothing_to_do,
search_chat_history, skill_search, wait), picked by how many default-
agent sessions called each at least once. A first use of one no longer
costs a tool-load model call. The row grows by 1,491 schema tokens; its
budget moves from 3,300 to 4,950.

(cherry picked from commit 5ea941c)
…36362)

While the official catalog is unreachable, or the listing is backing
off after a failed fetch, every store listing raised CatalogUnavailable
into a broad except that logged a full stack trace at WARNING. That is
an expected answer and it recurs on every listing, so the log filled
with identical tracebacks. Both listing paths had it: list_registry's
inventory, and the catalog-first listing's _catalog_installable_rows.

Catch CatalogUnavailable first at both sites and log through one
helper, official_catalog.log_unavailable: one WARNING line naming the
cause, the stack at DEBUG. Any other exception keeps its traceback at
WARNING, since that one is a bug, not an outage. The app-kit-platform
spec records the split.

(cherry picked from commit 62f35ec)
#36558)

The sweep that stops the app backends a gateway spawned is a dashboard
cleanup hook, and aiohttp runs cleanup hooks only after in-flight
requests drain (up to 60s). An open /api/logs stream holds that drain
past the 10s graceful budget, so the budget cuts the shutdown before
the sweep runs and os._exit leaves every backend and its sandbox
wrapper running under PID 1, still holding its port.

The exit path now runs the same sweep after the graceful shutdown,
before its hard exit. When the cleanup hook already ran, the tracking
table is empty and the sweep returns at once. Adopted backends stay
excluded, as before.

(cherry picked from commit ee81308)
* perf(crew): one scheduler for crew-workers reads: no overlap, capped, backoff, If-None-Match (Refs #36154)

A page that is hidden no longer re-reads the list, a re-read never cancels
or doubles one in flight, at most two list requests are out per origin so a
send always finds a free connection, slow answers widen the wait, and the
client sends the last ETag and keeps its cached list on a 304.

* fix(crew): crew-workers reads wait for a free slot; ETag read by lowercase name (Refs #36154)

A read over the cap now waits in a FIFO queue and reads fresh data instead
of resolving with the cached list, cold loads obey the cap too, and a
rejected read frees its slot. Header names are case-insensitive, so the ETag
is read in lowercase, which the untranslated-literal gate does not flag.

---------

Co-authored-by: kirocrew-agent <agent@kirocrew.local>
(cherry picked from commit db39373)
… write (#36534)

Co-authored-by: Joe Guo <zejiangg@amazon.com>
(cherry picked from commit ac45981)
…e prompt (#36593)

* perf(acp): record the process tree beside the start and the turn end

The runtime walked its process tree in front of the person three
times: after the initialize handshake, after session/new or
session/load, and at the end of every turn. On macOS that walk starts
a pgrep per process and a ps per pid, 352 ms with no servers and
954 ms with 64 on the first prompt alone, and 68 to 105 ms at the end
of each warm turn.

Only a kill or a teardown reads that record. So the spawn, every
session start and the shared runtime's turn end now start the same
guarded pass as a task, and every reader that signals or takes a kill
handle waits for it first: _kill_inner before it signals the root,
and refresh_process_tree before its own walk. The identity data and
its checks are unchanged; the record is written before anything acts
on it.

Part of #36582

* perf(kas): read the MCP config scopes once per agent projection

The KAS custom-agent projection asked mcp_server_muted_in_any_store
about each declared server, and each call re-read every MCP config
scope through the sensitive-path fence. Two loops did that per start,
so the projection grew with the user's servers: 214 ms with 30 servers
on Linux against 45 ms with none, and 359 ms with 64 on macOS.

Both loops now read mcp_scope_muted_aliases once and hand the set to
the predicate, through the same reader and patch seam. The answer per
server and the payload are the same.

Part of #36582

(cherry picked from commit aeb98eb)
…35590)

An app agent such as Mochi took a granted server's launch spec only
from its template, the Kiro global mcp.json and the managed servers,
so a server added on the MCP Management page, installed from a
registry or contributed by the edition was skipped with "no launch
spec found" while the app reported the policy applied. A built-in
app's grant now reads the default agent's own spec ahead of the
global file, the rebuild's merge of those sources with the store
winning a tie, and leaves out other apps' own servers. A
user-installed app writes its own grant file and no owner consent
covers what it names, so its grant keeps main's sources. A copied
entry that is muted is withheld: turned off, not yet consented, or a
secret:// reference the rebuild withholds.

Enabling an app, or re-installing an installed one from the registry
(how a registry-sourced app updates), wrote its <app>:<server> entries
into the agent spec and stopped, so on a harness that does not watch
the spec file a chat already open never got the change. These routes
now end with the step an MCP page write ends with, as update, disable
and uninstall already do; the enable decides it from the app's record
as it stands inside the lifecycle lock. A fresh install registers
nothing for the disabled record it writes, so it needs no step.

Closes #33020

(cherry picked from commit 712d24f)
…36194) (#36262)

A slot-detail page stops at 1.5 MB of serialized rows, cut from the old end;
the newest row is always sent, so a row over the budget goes alone and is never
dropped. next_before and has_more point at the first row actually sent. The
finished body goes through conditional_json_response: ETag/304 and gzip, no
change to the response shape.

Co-authored-by: kirocrew-agent <agent@kirocrew.local>
(cherry picked from commit b77f3df)
)

opencode 1.x keeps a saved session on the directory it was created in.
A session/load naming another cwd split the session across two of its
instances: approval replies went to the wrong one and were dropped, and
the MCP servers sent with the load (Kiro Crew's own tools) were mounted
where the model was not.

Add ACP_BACKENDS_CWD_BOUND_SESSIONS (opencode). When the stored cwd of
a member's saved session differs from the folder the chat now starts
in, the allocator does not hand the client the resume sid, so the start
opens session/new in the new folder and the conversation is replayed
as text. kiro-cli takes the cwd from each load and keeps native resume.

Fixes #35459

(cherry picked from commit a67f6ed)
On a KAS main harness with no stored Kiro Crew sign-in, agents run on
kiro-cli's login. When the usage API refused that credential, the Kiro
account popup showed the passive "No active Kiro sign-in" notice, as if
nobody had signed in, with no error and no agent hand-off.

The usage reply now marks a refused credential with
credential_rejected, and the popup shows that state as the error
notice with the agent hand-off. A missing credential keeps the passive
notice, and a stored Kiro Crew sign-in keeps its own lapsed notice.

Closes #35483

(cherry picked from commit 94155a1)
…36818)

The shared reader behind the [AGENT SYSTEM PROMPT] block now takes
kiro-cli's systemPrompt spelling, expands $VAR and ~ in a file:// path,
checks the resolved path with the same rule the KAS reader uses, and
names a prompt file it cannot use in one WARNING. It reuses
acp/kas_prompt.py (spec_prompt, the new expand_prompt_ref) and
acp/kas_prompt_paths.py rather than copying them.

Co-authored-by: Joe Guo <zejiangg@amazon.com>
(cherry picked from commit 4c7a874)
Inside a memory-limited container /proc/meminfo reports the VM or node
the container runs on, so /api/system showed that machine's total and
free memory while spawn admission sized against the container's cgroup
limit. On an 8 GiB Fargate task with a 7.75 GiB container limit the
gauge read 15.4 GB total.

The cgroup walk admission uses now also returns the tightest limit
(_container_cgroup_reading). Session import's (limit, headroom) reader,
_cgroup_memory_bounds, drops its own limit loop and reads that walk, and
/api/system calls it, so the Linux memory figures are bounded by the
limit and the headroom under it. The agents slice stays out of the
gauge: it caps agent processes, not the machine.

(cherry picked from commit 848e002)
…nded (Refs #36194) (#36845)

Turn-end and reconnect refreshes (refreshSlot, warmSlotCache, switchSlot and
the pane hydrate all read the newest bounded page through api.chatSlotDetail)
now ask for a cursor (cursor=1) and echo it on the next read, with
If-None-Match set to the last ETag. A refresh that missed nothing gets a 304;
one that missed rows gets only the rows from since on. A cursor the server
rejects (400) or a delta that does not fit the held page is read whole.

A cursor-mode page is now cut by the same byte budget as a plain page, so the
dashboard's reads keep the bound from #36262.

warmSlotCache no longer reads the whole transcript when the count-matched
bound declines (legacy rows with no timestamp): it reads one clamp-sized page
and walks older pages, as refreshSlot and switchSlot do.

Co-authored-by: kirocrew-agent <agent@kirocrew.local>
(cherry picked from commit 714b0d5)
On KAS, a chat whose project has files in .kiro/hooks got the "hook
files in .kiro/hooks do not run" notice again on every new backend
session, so each reconnect, reload or restart added one more copy.

The chat now keeps a mark of the project folder and the sorted file
names, the way the KAS telemetry notice does, and saves it on the
chat's metadata line. The notice shows again only for another folder
or another set of files.

Closes #36821

(cherry picked from commit 911bde8)
With Kiro CLI saved as the harness on a computer where Kiro CLI runs
on Kiro Agent, the Kiro CLI row in Settings > Agent Harness said "New
sessions switch from Kiro Agent to Kiro CLI." and showed a "Use Kiro
CLI" button. The button saved the value that was already saved, so
nothing changed and the panel showed the same two lines again.

The row now shows no button in that state and says that Kiro CLI runs
on Kiro Agent. Every other row keeps its button, and so does the Kiro
CLI row when Kiro CLI does not run on Kiro Agent.

Closes #36170

(cherry picked from commit ecf7d56)
…#36069)

A shared MCP server that waits for an approval showed nowhere outside
the MCP Servers page, so a pause could go unseen for days. The Customize rail
row and its MCP Servers tab carry the count of such servers, read by
the shell from the same status query the servers list's notice uses;
the tab's label is a plural catalog key. The gateway
records a refusal when it starts, so the socket's connect handler marks
that read stale and the shell's own poll runs only every five minutes.

The paused row's hint compared the approved and the new command lines
as lists. One line is drawn per launch, so one program listed twice
before and three times after read as a changed command although only
its env differed. The lines are compared as a set, and the env hint
says the program is the same and only its environment variables
changed. A line that carries a redaction tag never reads as the same
program.

(cherry picked from commit 21b6680)
)

The harnesses AcpClient starts directly (claude, OpenCode, goose, pi,
Copilot, DeepSeek) do not go through the runtime's retrying spawn factory,
so a CreateProcess refusal with winerror 5 or 1260 reached the chat as a
generic error. The shared launch tail now marks such an error at process
creation, naming the binary; ensure_ready keeps its one retry and then
raises the existing AcpSpawnBlocked for a marked error only, so the chat
shows the policy card. An access denied after the process started (a file
cleanup) is not marked and is unchanged. Detection only: nothing changes
how or whether the binary is started.

Co-authored-by: Joe Guo <zejiangg@amazon.com>
(cherry picked from commit 0b32483)
…ng (#36819)

On a host whose ceiling came from central distribution, KAS-managed MCP
children exited before MCP initialize ("Connection closed"): the sandbox
masked policy_cache, so a cache-only child found no ceiling.

The sandbox's existing read-only cache lift (enterprise_policy_cache_view)
now applies when central_ceiling_installed(), not only in an LTS build, and
keeps its refusals. The gateway derives the cache-only markers
(policy_cache_only_env) for the harness env, managed MCP declarations, the
KAS projection and the discovery probe. A cache-only child accepts a
source-less distribution block.

Closes #36775
Supersedes #36710

Co-authored-by: Joe Guo <zejiangg@amazon.com>
Co-authored-by: Pedro Evangelista <pedro.evangelista@mindera.com>
(cherry picked from commit 918a1c8)
The MCP page's sharing card hid its whole memory row whenever either
figure was missing. With sharing off no stub runs, so "with sharing"
has no stub price and is null, and the row vanished exactly when the
reading of what MCP servers use now matters most.

"Using now" now shows whenever it was read, on its own. "With sharing"
and its arrow show only when that figure was read too. No placeholder
stands in for a missing figure.

Part of #36884

(cherry picked from commit ed9d0b0)
…#36586)

While config.json has a change made outside Kiro Crew pending review,
every trust write the built-in adoption APPLY pass makes is refused
with PendingEditBlocksSave. The pass caught it as an unexpected error
and logged a full traceback at ERROR for each pinned app on every
boot, although nothing is wrong: the built-in keeps running and the
staged ledger is retried at the next start.

Treat that refusal as the expected state it is. The pin's outcome is
waiting_for_review, its ledger is left untouched, and the pass logs one
warning naming the pending file and every waiting app, with each trace
at DEBUG. Recording the legacy nav of an already adopted app waits the
same way, at DEBUG only.

Part of #26967

(cherry picked from commit 4579388)
A Bot's chat is a ChatPane, whose replies go through the shared bubble
(renderAssistantBubble). That bubble passed meta.redactions but never
meta.blocked_links, so a removed link stayed as its raw
"[REDACTED: suspicious URL to <host>]" text: no chip, no card, no
"Allow for this host". The bubble now passes the records on the same
local-slot rule as the lock tags, so a window drawing another gateway's
rows keeps the plain text and what can be allowed does not change.

After Allow or Undo, the chat page reloads only the slot it shows. A
pane now re-reads its own slot on the same event, so the restored link
replaces the chip in a Bot's chat too.

Closes #36862

(cherry picked from commit 8c58e18)
…ts (#31546)

A provider marks its one-run work directory (cron_<job>_<run>, subagent_<id>,
...) once, in start(), and its shutdown reclaim removes it. A runtime started
or resumed again for the same session after that reclaim -- a failed resume
that starts fresh, a killed runtime that respawns -- handed KAS a deleted cwd.
Node's spawn reports a missing cwd as "spawn <command> ENOENT", so every
managed MCP server failed naming a binary that exists, e.g.:

  KAS managed MCP initialization failed: kirocrew-cron: failed
  (spawn .../python3.12/bin/python3.12 ENOENT)

Defense in depth:
- Prevent: on the unbound (non-macOS) path, _session_work_dir re-creates a
  missing directory whose name has a one-run shape and whose parent is the
  workspace root, through mark_run_dir, so the reclaim and the sweep see the
  same provenance. A one-run name anywhere else is never created, only
  logged. Any other cwd skips the check and its thread hop, so a chat or
  title start reaches the admission gate in the same order as before.
  Errors are swallowed; the guard never adds a start failure.
- Diagnose: a managed MCP readiness failure with ENOENT names the
  session cwd when it no longer exists.

Docs: acp-client.md run work directory section.

Co-authored-by: Ray Xu <buluoray@gmail.com>
Co-authored-by: RAVI KUMAR <14358622+kingravi17@users.noreply.github.com>
(cherry picked from commit d1f38d7)
@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners November 14, 2026 19:47
@buluoray
buluoray requested review from cruisercohen and removed request for a team November 14, 2026 19:47
@github-actions

github-actions Bot commented Nov 14, 2026 •

Copy link
Copy Markdown
Contributor

Sensitive Change Review

Sensitive files changed:

  • src/kiro_crew/sandbox_tiers.py

  • src/kiro_crew/sandbox_wrap.py

  • src/kiro_crew/security/deny_gate.py

  • src/kiro_crew/security/rm_floor.py

  • No reasoning template for d3e548c 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: d3e548c41c299d111ac3c04e9e082e2a8d9d8488
- 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 14, 2026
@github-actions

github-actions Bot commented Nov 14, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of d3e548c41c299d111ac3c04e9e082e2a8d9d8488 — 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

This is a cherry-pick backport of fixes already merged on main. Each pick names its main commit, and each prerequisite names the pick whose conflict pulled it in. No item adds surface that main lacks.

Notes

What this change ships

Inventory (10 items) — 9 justified

Intent: give 0.13 users the KAS fixes and the user-reported fixes that merged on main after the cut. FIX.

  1. KAS shell grants: allowed commands now run beside denyByDefault, deniedCommands and plain redirects (fix(kas): run allowed commands beside denyByDefault and deniedCommands #36541, fix(kas): grant allowedCommands beside plain output redirects #36813) — justified
  2. KAS sign-in goes through the proxy, and a waiting MCP sign-in is named in chat (fix(kas-auth): send sign-in and renewal through the proxy #36978, fix(mcp): say in chat when a kas server waits for a sign-in #36135, fix(mcp): name a dropped oauth block on every harness, not only KAS #36993) — justified
  3. kiro-cli 3.x is detected as the chat binary, and a sandbox launcher exit reads as unknown (fix(kas): treat a standalone kiro-cli 3.x as the chat binary, not a launcher #36975, fix(kas): read a sandbox launcher exit as unknown, not as no engine flag #37203) — justified
  4. A new KAS chat stops repeating start-up work: title request, projection, tool loads, session-stable prompt blocks (perf(acp): skip the kas engine's own title request on new sessions #36603, perf(acp): stop the KAS projection repeating work every new chat #37097, perf(kas): send a new chat's session-stable blocks as the agent prompt #37108, perf(kas): defer the default servers' tools on a custom agent #37093) — justified
  5. A reclaimed one-run work dir is re-created, and a resumed conversation goes back into its scratch tree (fix: re-create a reclaimed one-run work dir before a KAS session starts #31546, fix(scratch): resume a conversation into the scratch tree it had #30062) — justified
  6. Notices (hook files, session-start spec) show once per chat (fix(chat): show the project hook-files notice once per chat #36829, fix(chat): show each session-start spec notice once per chat #36955) — justified
  7. Fixes to memory figures and container limits (fix(dashboard): show a container's memory limit, not the host's #29602, fix(mcp): show the memory now figure while sharing is off #36913, fix(mcp): price "with sharing" from one idle stub while sharing is off #36922) — justified
  8. Dashboard fixes: scroll offset, blocked link card, dead kiro cli use button removed, settings reset waits for a running turn (fix(chat): keep the chat column at scroll offset 0 after an undone paste #36621, fix(chat): show the blocked link card in a bot's chat #36878, fix(settings): drop the dead use button on the kiro cli row #36207, fix(sessions): let a settings reset wait for a running turn #36783) — justified
  9. Two new architecture docs (requirements checklist, gap analysis) carried as a prerequisite — rides along; the gap snapshot is stale on this branch
  10. 21 code prerequisites (slot-detail paging, app catalog routes, governance leaf pins, and others) carried so the picks apply without hand ports — justified

[FIRST-PRINCIPLES-REVIEWED] d3e548c

Description read

[DESCRIPTION-READ] d8b17094a94974c0a7c450c26362db5ddce5406704ac9749fb27cfd0b5100a22

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

Security Scope Review -- 🔴 could not complete (fails closed)

No scope verdict for 6827ef9267da6aa5d1b2ed082827cc38bc57f7dd (the candidate stage failed). This lane fails CLOSED: an unmeasured tightening must not read as "nothing newly refused". See the job logs, then re-run -- or record /ai-review override scope 6827ef9267da6aa5d1b2ed082827cc38bc57f7dd <class>: <reason> if a human has judged the scope by hand.

@github-actions

github-actions Bot commented Nov 14, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ human override accepted

Human judgment by @buluoray overrides the GPT 6.1 finding for d3e548c41c299d111ac3c04e9e082e2a8d9d8488; the recorded reason is authoritative for this commit.

[GPT-OVERRIDE] d3e548c

This comment is updated in place on each push.

The model was not re-run because an authorized human decision supersedes it.

False positive or not applicable? A repository writer can comment:
/ai-review override gpt d3e548c41c299d111ac3c04e9e082e2a8d9d8488 false-positive: <reason, 20 to 500 characters>

@buluoray
buluoray force-pushed the crew/slack/backport-0.13.0-batch1 branch from 6827ef9 to d3e548c Compare November 14, 2026 20:06
@github-actions

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 d3e548c41c299d111ac3c04e9e082e2a8d9d8488 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

UX-Verdict: PASS

cannot evaluate: missing screenshots. The PR attaches and commits no image, so nobody did a blind read. The diff still adds or changes several dashboard surfaces a user will see.

Evidence gaps

  • Settings → Developer → Agent Backend, Kiro CLI row (AgentBackendTab.tsx). It adds the line "Kiro CLI now runs on Kiro Agent. New sessions already use Kiro Agent, so there is nothing to switch here." and hides the row's Use button. Needed: a screenshot of that row with the saved Kiro CLI choice running on Kiro Agent.
  • Customize item in the nav sidebar (railBadges.ts). It adds a count badge for MCP servers set to share that are waiting for approval. Needed: a screenshot of the badge with a count above zero.
  • MCP Management hero (McpManagementHero.tsx). The memory figure for right now can now show on its own, with no arrow and no "with sharing" figure next to it. Needed: a screenshot with sharing turned off.
  • Kiro account dialog (KiroAccountModal.tsx). It adds a new signin-rejected state, where the usage service refused a stored Kiro sign-in. With no sign-in stored, this state now shows the error notice instead of the "sign in to see usage" line. Needed: a screenshot of that state.
  • Chat column scroll position after an undone paste (usePinnedScrollOrigin.ts). Needed: before and after screenshots.

[UX-REVIEWED] d3e548c

Description read

[DESCRIPTION-READ] 3efbbaf23cd3d8bfc8e4c41faa313d50c4d9cb0b3920a93bfe81cea439602521

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

Copy link
Copy Markdown
Contributor

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

Design-level review of d3e548c41c299d111ac3c04e9e082e2a8d9d8488 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

cannot evaluate: missing screenshots of the reshaped dashboard surfaces this batch brings to release/0.13.0. The evidence list shows zero downloaded or committed images or recordings.

Blockers

No rendered evidence for the UI changes in this revision
Trigger: the batch reshapes existing control sets and adds new UI under website/src/: the AgentBackendTab Kiro CLI row drops its Use button and gains a "kiro_row_runs_on_kas" notice ("Drop the dead use button on the kiro cli row", #36207); railBadges.ts/navRow.tsx and McpShareRefusedNotice.tsx gain a paused-share badge (#36069); McpManagementHero.tsx, CapabilitiesPage.tsx, kiroUsageReadout.tsx and the crewmate blocked-link card in transcriptRenderers.tsx also change.
Outcome: the evidence list names no image or recording → nobody can check how these surfaces look on the rc.1 base, where 6 picks needed a hand-resolved hunk and #36069 and #36347 touch UI → a backport can render differently from main, and that would go out unreviewed in the next user-facing release.
Fix: attach screenshots taken on this branch (not the main PRs' images, which show another tree's state) of the Agent Backend tab's Kiro CLI row while KAS runs it, the paused-share rail badge and refused notice, the MCP management hero, and the blocked link card in a bot's chat.
Clears when: github.com/user-attachments images or committed temp-screenshots/ media of those surfaces at this head appear in the workflow's evidence list.

Notes

  • The design itself is sound: cherry-pick -x in main's merge order, with each prerequisite tied to the pick that needs it. Nothing else blocks.
  • I skipped the take-away check because the description was truncated before ## Backwards compatibility.

[DESIGN-REVIEWED] d3e548c

Description read

[DESCRIPTION-READ] 86dd56a3221c0aa4c31632ea2e79117576203c26a7ea8b6ba5911f731f6c7e8b

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 added readiness: action required A blocking check or review needs attention and removed readiness: checking Automated validation is still running labels Nov 14, 2026
@buluoray buluoray changed the title fix: 0.13 backport batch 1 (KAS and user-reported fixes) fix: 0.13 backport batch 1, part 1 of 3 (KAS and user-reported fixes) Nov 14, 2026
@buluoray

Copy link
Copy Markdown
Contributor Author

span=b18f17d4c8c8

  • Report failed MCP approval-count reads

Rebutted: not a change this backport makes. useMcpShareRefusedCount and its use at website/src/pages/CapabilitiesPage.tsx:58 are byte-identical to origin/main (#36069 picked with git cherry-pick -x; diff of mcpShareRefusedQuery.ts against main is empty, and main's CapabilitiesPage.tsx:58 is the same line).
This PR only brings main's reviewed fix to release/0.13.0. Changing it here would make 0.13 differ from main; an improvement belongs on main first and is then picked like every other fix.
Harm is low (adjudication agrees): a failed status read leaves the badge at 0, and the MCP Servers tab still shows its own failure notice.

@buluoray

Copy link
Copy Markdown
Contributor Author

span=e8bbf6fd8ce6

  • No rendered evidence for the UI changes in this revision

Rebutted: this batch adds no UI of its own. Every website/src/ change is a git cherry-pick -x of a main PR whose final head passed Design Review and UX Review on main: #35510, #36069, #36207, #36238, #36262, #36621, #36845, #36878, #36913.
The surfaces render as they do on main, where they were reviewed with their evidence, so new screenshots here would repeat that review.

@buluoray

Copy link
Copy Markdown
Contributor Author

/ai-review override gpt d3e548c not-applicable: agent: the flagged useMcpShareRefusedCount code is byte-identical to main (#36069 cherry-picked); this release backport must match main, so any change belongs on main first.

@github-actions

Copy link
Copy Markdown
Contributor

Human judgment recorded

@buluoray recorded a not-applicable release (class not-applicable) for the gpt AI finding on d3e548c41c299d111ac3c04e9e082e2a8d9d8488.

agent: the flagged useMcpShareRefusedCount code is byte-identical to main (#36069 cherry-picked); this release backport must match main, so any change belongs on main first.

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

@buluoray
buluoray merged commit 1fe3510 into release/0.13.0 Nov 14, 2026
28 of 37 checks passed
@buluoray
buluoray deleted the crew/slack/backport-0.13.0-batch1 branch November 14, 2026 21:08
@github-actions github-actions Bot removed the readiness: action required A blocking check or review needs attention label Nov 14, 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.

7 participants