Skip to content

fix(kas): backport #35244 #35262 #35272 #35278 to 0.12 - #35389

Merged
buluoray merged 4 commits into
release/0.12.0from
crew/slack/kas-picks-0120-batch2
Nov 11, 2026
Merged

buluoray merged 4 commits into
release/0.12.0from
crew/slack/kas-picks-0120-batch2

Conversation

@buluoray

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Bring four KAS/ACP fixes merged on main on 2026-11-11 (#35244, #35262, #35272, #35278) onto release/0.12.0 for the next 0.12.x, one commit each.

Each fixes something a 0.12 user on KAS can hit today: the whole steering tree sent where only matching files belong (#35244), setup asking for Node on the bundled KAS route (#35262), every runtime start sleeping on an empty process-tree scan, worst on Windows (#35272), and Kiro Crew's own MCP servers connecting last behind an agent's servers (#35278).

Why it matters

These hit every KAS chat, sub-agent and setup run on the 0.12 line. Merge with Rebase and merge so each pick keeps its own commit.

Not a goal

What changed (motivation → approach → change)

Each main squash commit was cherry-picked with -x onto release/0.12.0 @ 8f9e308c72, in main merge order. 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 conflict
1 #35244 send may-be-auto steering files by path Bolin Chen 7eecd4a11e b38b501199 none
2 #35262 stop asking for node on the bundled kas route Bolin Chen dbb3160d65 077647e1a0 none
3 #35272 stop a runtime start from waiting on an empty tree scan Bolin Chen 70203ee0de 1b07e24eed docs, docstring, test imports
4 #35278 connect Kiro Crew's MCP servers before the agent's own Bolin Chen 265b3ac944 1dabd86cf3 docs, docstring, test import

Picks 1 and 2 have the same patch-id as their main commits.

Prerequisites. None picked. The conflicts in picks 3 and 4 come from main-only features (the /proc task-children reader, Kiro Cloud Sessions, the MCP connect-queue tracker). Those are features, not fixes, and the hunks that touch them are comments, docs and imports only.

Hand-resolved hunks (@bolichen97, please check these; no code line was hand-edited):

  • fix(acp): stop a runtime start from waiting on an empty tree scan #35272
    • src/kiro_crew/acp/runtime_process_tree.py _direct_children docstring: kept the release text and took main's new last line ("Returns [] where the walk cannot see a descendant (walk_observes_descendants)"). Main's Linux paragraph names _read_task_children, which release does not have.
    • docs/system-specs/modules/acp-client.md: left out main's "Child enumeration on Linux" bullet, which describes that same reader. The descendant-scan hunk that names walk_observes_descendants() applied cleanly.
    • test/test_process_tree.py: added from types import SimpleNamespace and from kiro_crew.acp import runtime_process_tree as rpt, which main's file already had.
  • fix(kas): connect Kiro Crew's MCP servers before the agent's own #35278
    • src/kiro_crew/acp/harness/base.py session_request docstring: main's text without its sentence on KasCloudSandboxHarness (no harness/kas_cloud.py here).
    • test/test_kas_mode_binding.py: imports START_AGENT_ID only. Main's kas_cloud import is used by no test in this file.
    • docs/system-specs/modules/providers.md: dropped the conflicting block, which is main's whole "Kiro Cloud Sessions" section. This PR only edited one line inside it.
    • docs/system-specs/modules/acp-client.md "KAS managed MCP readiness": kept this PR's sentences on queue order and the server-less start agent. Left out main's surrounding text on the four-slot queue and McpConnectProgress, which describe code release does not have.

Backwards compatibility

Compatible: each fix keeps its main PR's compatibility notes; nothing here changes stored data or config beyond what those PRs shipped on main.

Removes nothing: no key, record or public function is removed; the only removals are doc and docstring text that describes main-only code.

Tests

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

Manual verification

N/A - each fix was verified on its own main PR. The 0.12.x RC soak is the end-to-end check.

Related Issues

Backport to the 0.12 line of #35244, #35262, #35272 (closes #35252 on main) and #35278.

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.

…#35244)

On KAS, a workspace whose steering tree held one file that may be
`inclusion: auto` kept the whole-tree `file://.kiro/steering/**/*.md`
entry, so KAS injected every steering file on every turn beside its own
native copy. Send just those files, each by its own path, in the
entry's place. Keep the entry whenever the paths might load less than
it did: a glob character in a name, another file entry before it or
another steering entry, or more than KAS's resource budget. The user
docs say the same.

Closes #32153

Original author: Bolin Chen (#35244)
(cherry picked from commit 7eecd4a)
On the KAS bundle route the engine runs the Node its bundle ships, and
`kirocrew doctor` already reports a missing node as not needed there.
`kirocrew setup` still printed "node not found on PATH - install
Node.js", sending a new user to install a runtime the selected backend
never uses.

Setup's prerequisites notice now asks the route predicate doctor asks;
on the bundle route it names the bundle's own Node instead of the
install advice. Off the bundle route the warning is unchanged.

Fixes #34944

Original author: Bolin Chen (#35262)
(cherry picked from commit dbb3160)
…5272)

A runtime start records its descendant processes once the agent has
answered initialize. When that scan saw no descendant it slept 0.5 s
and walked again, on the path the caller was waiting on. On Windows
the walk returns nothing by design (the teardown walks the tree itself
through its owned handles and taskkill /T), so every start slept and
then found nothing: every chat session, the background runtime, every
sub-agent.

walk_observes_descendants() now states once, beside the walk, whether
it can see a descendant on this platform. Where it cannot, the runtime
scan, the failed-start scan and the one-shot client's scan read
nothing and wait for nothing. Where it can, a start whose scan sees no
descendant returns at once and its one retry runs as a task of its own
after the same delay: an ordinary pass, serialized and bracketed by the
root's identity like every other, which the kill cancels.

The guarded pass itself no longer sleeps. Nothing a teardown or a
sweep reaps is recorded later or less than before, and no kill path
signals differently.

Closes #35252

Original author: Bolin Chen (#35272)
(cherry picked from commit 70203ee)

Backport note: comments, docs and test imports resolved by hand. The
release branch does not have main's /proc task-children reader
(_read_task_children, _CHILDREN_INTERFACE), so:
- runtime_process_tree._direct_children docstring: kept release's text
  and took main's new last line (Returns [] where the walk cannot see a
  descendant); main's Linux paragraph names a reader release lacks.
- acp-client.md: left out main's "Child enumeration on Linux" bullet,
  which describes that same reader; the bullet's new sentence about
  walk_observes_descendants is covered by the hunk that applied cleanly
  in the descendant-scan section.
- test_process_tree.py: added the two imports main's file already had
  (types.SimpleNamespace, runtime_process_tree as rpt).
No code line was hand-edited.
)

A new KAS session waits for Kiro Crew's own MCP servers before its
first prompt. The engine connects four servers at a time, in the
order a session declares them, and it declares the running agent's
servers ahead of the session-level array that carries Kiro Crew's.
So the first prompt waited for every server the agent declares:
about 2 s with none, about 35 s with 60.

Start the session in a server-less start agent when its own agent
declares servers. The set_mode every KAS start already sends then
switches to the session's own agent, which queues that agent's
servers behind Kiro Crew's. The agent's servers keep the bounded
wait they already had (5 s) and connect in the background after it.

The session starts in its own agent, as before, when that agent
declares no server, mounts the engine's sub-agent tool, or the batch
cannot take one more entry. session/load is unchanged.

Closes #35245

Original author: Bolin Chen (#35278)
(cherry picked from commit 265b3ac)

Backport note: comments, docs and one test import resolved by hand; no
code line was hand-edited. release/0.12.0 has neither Kiro Cloud
Sessions (acp/harness/kas_cloud.py) nor the connect-queue progress
tracker (acp/mcp_connect_progress.py), so:
- harness/base.py session_request docstring: main's text without its
  sentence about KasCloudSandboxHarness.
- test_kas_mode_binding.py: imports START_AGENT_ID only; main's
  kas_cloud import is used by no test in this file.
- providers.md: dropped the conflicting block, which is main's whole
  "Kiro Cloud Sessions" section; this PR only edited one line of it.
- acp-client.md "KAS managed MCP readiness": kept this PR's sentences on
  queue order and the start agent; left out main's surrounding text on
  the four-slot queue and McpConnectProgress, which describe code
  release lacks.
@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners November 11, 2026 16:29
@buluoray
buluoray requested review from bolichen97 and cruisercohen and removed request for a team November 11, 2026 16:29
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 11, 2026
@github-actions

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 1dabd86cf32c4000362e1ab95ede7298ec60037a touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Does not block merge.

@github-actions

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 1dabd86cf32c4000362e1ab95ede7298ec60037a — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: this ports four fixes already merged on main, and the seams they use (kas_bundle_route, installed_bundle, mounts_subagent_tool, KAS_MAX_CUSTOM_AGENTS) exist on this branch.

Notes

  • The Manual verification: N/A line is acceptable here. The only platform-specific branch, walk_observes_descendants() returning False on Windows, skips the scan just as the old IS_WINDOWS early returns did.

[DESIGN-REVIEWED] 1dabd86

Description read

[DESCRIPTION-READ] bfd2d2fc07cde3c1a43f79b3842de6643e00889cb7e12273ca3df0dc592da52d

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

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 1dabd86cf32c4000362e1ab95ede7298ec60037a — 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 PR backports four fixes already merged on main, one commit each. Each item restores a defect fix that has its own merged PR, and no item adds new scope.

What this change ships

Inventory (6 items) — 6 justified

Intent: give 0.12 KAS users the four fixes main already carries (steering, setup, spawn latency, MCP connect order). This is a FIX.

  1. On KAS, only the steering files that may be auto are sent, each by its own path, instead of the whole tree — justified
  2. Setup stops asking for Node when the bundled KAS route is in use — justified
  3. A runtime start no longer sleeps on an empty process-tree scan; the retry runs later as a background task — justified
  4. On Windows, the descendant scan is skipped entirely (walk_observes_descendants, 3 consumers) — justified
  5. A KAS session whose agent declares MCP servers starts in a server-less start agent, so Kiro Crew's servers connect first — justified
  6. Session-start readiness keeps the MCP status reports received while the session was in the start agent (start_mode_ran_servers seam, KAS override) — justified

[FIRST-PRINCIPLES-REVIEWED] 1dabd86

Description read

[DESCRIPTION-READ] 4b44d9ea40b611d715b6f1f7e849860bd3c2649bb26a2dabe443c304ff84d84a

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

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 1dabd86cf32c4000362e1ab95ede7298ec60037a and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 1dabd86

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 1dabd86cf32c4000362e1ab95ede7298ec60037a false-positive: <reason, 20 to 500 characters>

@github-actions

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 1dabd86cf32c4000362e1ab95ede7298ec60037a — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 1dabd86

Verdict parsed from the review's SHA-scoped output markers for commit 1dabd86cf32c4000362e1ab95ede7298ec60037a.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 1dabd86cf32c4000362e1ab95ede7298ec60037a false-positive: <reason, 20 to 500 characters>

@buluoray
buluoray merged commit 8546bd7 into release/0.12.0 Nov 11, 2026
20 of 23 checks passed
@buluoray
buluoray deleted the crew/slack/kas-picks-0120-batch2 branch November 11, 2026 16:44
@github-actions github-actions Bot removed the readiness: checking Automated validation is still running label Nov 11, 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