Skip to content

fix(kas): match v2 for prompt-less specs, sub-agent settings and hooks - #25361

Merged
KiroCrewCaptain merged 1 commit into
mainfrom
fix/25320-kas-parity
Oct 29, 2026
Merged

KiroCrewCaptain merged 1 commit into
mainfrom
fix/25320-kas-parity

Conversation

@buluoray

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: an agent spec behaves on KAS the way it does on kiro-cli v2, so the 11/2 switch of kiro-cli's default engine to KAS does not change what a user's agent does.

A live comparison of package-installed specs on both engines (#25320) found four differences, each from Crew's KAS projection, not from KAS:

  • A spec with no prompt gets Crew's "lightweight background worker" prompt on KAS, which tells the model it has no tools; on v2 it runs on kiro-cli's own default prompt.
  • toolsSettings.shell.allowedCommands is dropped: every command prompts on KAS.
  • toolsSettings.subagent.availableAgents / trustedAgents are dropped: any sub-agent can be spawned, and trusted ones still prompt.
  • The spec's hooks run from Crew's turn loop on KAS, but nothing proved they run for every event v2 runs them for.

Why it matters

Every session that ran on v2 runs on KAS after 11/2. Without this, a user-chosen prompt-less agent is told it has no tools, an agent whose author allowed git status asks before every command, a spec that limits which sub-agents it may spawn limits nothing, and a postToolUse hook written as kiro-cli documents it (matcher execute_bash) never fires.

Not a goal

  • toolsSettings.web_fetch.trusted, allowedPaths, denyByDefault and write.fallbackAction: "deny": they stay as they are (named in the session-start notice).
  • Sending spec hooks over the KAS wire: Crew keeps firing them from its turn loop.
  • Any change on the kiro-cli v2 path.

What changed (motivation → approach → change)

Prompt. Crew substituted its worker prompt because it believed KAS needs a non-empty prompt. Measured live on kiro-cli 2.35.1: KAS needs the prompt KEY (an entry without it is answered _kiro/customAgent/not_found and the session runs KAS's vibe mode), but registers an entry whose prompt is "", and a non-empty prompt is layered on KAS's own base prompt rather than replacing it. So a prompt-less spec now goes out as "prompt": "" (kas_agents.resolve_prompt); only Crew's own kirocrew-lite keeps the short brief for its one-shot text tasks.

Sub-agent settings. KAS's subagent capability matches the sub-agent's name (its consent names it as the resource, and KAS writes its own trusted sub-agents as {capability: "subagent", match: [ids], effect: "allow"}). availableAgents becomes a deny over "*" with the listed names in exclude ([] denies all); trustedAgents a name-scoped allow that goes through the existing merge, so the governance ceiling is asked about every sub-agent ref and one refusal drops it. A pattern travels only when it is an agent id with * as its only wildcard; anything else is named in the notice and only narrows. Measured live on kiro-cli 2.35.1: the deny with the target excluded left the call to its permission request, with another name excluded the rule refused it, and the allow ran it unprompted.

Spec hooks. A new test drives a real chat_runner._run_chat KAS turn with the real hook store and the spec on disk. It showed agentSpawn (first turn), userPromptSubmit, preToolUse (once, at the permission request) and stop already run, and postToolUse with a tool matcher never ran: KAS's tool_call frame names no built-in tool and titles the call in prose, and PostToolUse matched only the title. The turn now records, per call, the id the permission request stated, or KAS's shell tool for a call classified as a shell command (spec_hooks.post_tool_hook_tool_id), and passes it to the hook store as PreToolUse already does.

shell.allowedCommands (second commit, lands after #25339). A KAS shell allow would skip the permission request Crew's deny floor runs on, so the owner's decision is that Crew answers the request itself, through the spec-builtin-grant gate row #25339 adds, with one more condition: the host-recovered command re.fullmatches one of the spec's patterns (kiro-cli's \z read as \Z) and holds none of ; & | < > $ \ ( ) { }or a newline. The row runs after every deny row and governance, asks the ceiling aboutexecute_bashagain on every call, and honoursconfirm_tools`. That commit is built and tested on top of #25339's branch and is pushed here once #25339 merges.

Merge order: #25339, then this PR. This PR is not complete until the allowedCommands commit is on it.

Backwards compatibility

Compatible: a spec with a prompt, a spec without toolsSettings.subagent, and every kiro-cli session project exactly as before. A spec that declares subagent.availableAgents now gets those spawns refused on KAS, which is what it already gets on kiro-cli v2.

Removes nothing: the change only narrows a prompt-less spec's prompt to what kiro-cli sends and adds rules a spec already asked for; no key, record or path is taken away.

Tests

  • test/test_kas_agents.py: a prompt-less spec resolves to "" and is projected with the key present; only kirocrew-lite gets the brief; a non-string prompt is refused.
  • test/test_kas_mode_binding.py::test_a_prompt_less_agent_goes_out_with_an_empty_prompt: through AcpRuntime.create_session against the KAS stub.
  • test/test_kas_tools_settings.py: availableAgents deny+exclude, [], "*", untranslatable and over-long lists (each narrows and is named); trustedAgents allow; the allow travels only when the ceiling permits every sub-agent ref; a PreToolUse hook on the sub-agent tool outranks it with an ask; the deny travels whatever the ceiling says.
  • test/test_kas_spec_hooks_turn_loop.py (new): one real _run_chat KAS turn runs agentSpawn, userPromptSubmit, preToolUse, postToolUse, stop once each; agentSpawn only on the first turn; a PostToolUse matcher in kiro-cli names (execute_bash, shell, execute_*, *, fs_write, @git/status) meets the call the way kiro-cli would, on a permission-named call, a shell call with no request, and an edit only its request names.

Revert proof, each change reverted alone:

Reverted Red
prompt fallback restored 5 tests (test_kas_agents, test_kas_mode_binding)
subagent translation removed 10 tests (test_kas_tools_settings)
PostToolUse tool_id dropped 6 tests (test_kas_spec_hooks_turn_loop)
permission-request id not recorded test_a_post_tool_use_matcher_meets_an_edit_its_request_named[fs_write-True]
shell fallback removed test_a_post_tool_use_matcher_meets_an_auto_approved_shell_call

Proof: PROVEN test/test_kas_agents.py::TestPromptResolution::test_a_prompt_less_spec_resolves_to_an_empty_prompt[None], test/test_kas_agents.py::TestPromptResolution::test_build_projects_a_user_prompt_less_spec_with_an_empty_prompt, test/test_kas_mode_binding.py::TestModeBinding::test_a_prompt_less_agent_goes_out_with_an_empty_prompt (head 3e8c01b)

Local: 5,161 passed across the KAS, spec-hook, chat-runner, harness, hooks and tool-call suites; the one failure (test_harness_parity.py::test_is_kiro_cli_is_positive) fails the same way on origin/main on this host.

Manual verification

Live on kiro-cli 2.35.1, KAS engine, scratch workspace, Crew's own projection code (to_client_custom_agent + attach_kas_custom_agents):

  • prompt: "": registered (no not_found), the agent had no tools as its spec said, and it answered on KAS's default prompt. Prompt key absent: _kiro/customAgent/not_found, fallback to vibe, 17 tools. A non-empty prompt was layered on KAS's base prompt.
  • subagent rules as listed above, on invoke_sub_agent.

Unverified: older kiro-cli releases (the agent-prompt floor is already 2.33.1), and Windows / macOS (pure-Python change, no platform branch).

Related Issues

Closes #25320
Depends on #25339 (merge it first).

Sibling sweep

Swept: git grep -n "_KAS_FALLBACK_PROMPT\|prompt is empty\|non-empty prompt" -- src docs
Sibling: src/kiro_crew/docs/agent-spec-fields.md -- changed here
Swept: git grep -n "_pending_tools\b" -- src/kiro_crew/dashboard
Sibling: src/kiro_crew/dashboard/chat_turn/tool_results.py -- changed here
Sibling: src/kiro_crew/subagent_parts -- not affected -- a subagent turn already passes its spec hooks to PostToolUse through turn_spec_hooks

Pattern harvest

Not generalizable: each difference is one field of one wire projection, found by a live two-engine comparison rather than a code pattern.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title
  • 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

Contributed under the project's Apache-2.0 license.

@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners October 28, 2026 18:14
@buluoray
buluoray requested a review from dodgeblaster October 28, 2026 18:15
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Oct 28, 2026
@github-actions

github-actions Bot commented Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 84f40e32a8cade8efcee463d0764e3f811fa32d2 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks. Each projection change narrows a spec toward kiro-cli v2's behaviour, the dropped non-empty-prompt pin rests on live 2.35.1 measurement, and every change reverts cleanly.

Notes

  • The description claims a shell.allowedCommands fix that this diff does not contain ("pushed here once fix(kas): auto-approve granted built-ins after Crew's own checks #25339 merges"). Until it lands, this head does not meet the stated Goal, so this review does not cover it. That commit adds a new spec-builtin-grant approval path and needs its own design pass.
  • subagent_manager/run_turn.py now holds PostToolUse until the terminal tool_final result, and the subagent path now matches MCP server-form names. Both change behaviour, and neither is mentioned in the description. Add them to the hooks paragraph.

[DESIGN-REVIEWED] 84f40e3

Description read

[DESCRIPTION-READ] 50d2b5bd35c37730b4f15cb91562c91a191d61ada3d4d13d41ff898df4a3be3f

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 Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 84f40e32a8cade8efcee463d0764e3f811fa32d2 touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Does not block merge.

@github-actions

github-actions Bot commented Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 84f40e32a8cade8efcee463d0764e3f811fa32d2 — 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

Nothing blocks. One fix that rides along changes when PostToolUse fires on every backend Crew fires hooks for, and the description never mentions it. The empty-prompt premise was measured on a single kiro-cli release.

Notes

  • Item 8 — rides along, undeclared: if _tool_terminal: in tool_results.py and _terminal = ... in run_turn.py now fire PostToolUse once per call, on its terminal result. The Hooks-page hooks are covered too, on every backend. The description's PostToolUse paragraph only describes adding tool_id. The ## Not a goal section says "Any change on the kiro-cli v2 path", and this gate isn't backend-scoped.
  • Item 3 — unverified premise (the session-start path): the description says "Measured live on kiro-cli 2.35.1" and calls older releases "unverified". The deleted guard said KAS empty prompts "would otherwise crash KAS session creation". The supported floor is KAS_AGENT_PROMPT_MIN_KIRO_CLI = (2, 33, 1), so 2.33.1–2.35.0 are untested for prompt-less user specs.

What this change ships

Inventory (9 items) — 7 justified

Intent: make an agent spec behave the same on KAS as on kiro-cli v2 once KAS becomes the default engine. This is a FIX.

  1. A prompt-less user or app spec on KAS runs on KAS's default prompt, not Crew's "no tools" brief — justified
  2. kirocrew-lite keeps its short background-worker brief — justified
  3. The projection no longer refuses an empty prompt; it sends "prompt": "" — justified
  4. subagent.availableAgents is enforced on KAS as deny-all-but-listed — justified
  5. subagent.trustedAgents spawn unprompted on KAS, gated by the ceiling — justified
  6. Dashboard PostToolUse spec hooks match kiro-cli tool names on KAS calls — justified
  7. Subagent-run PostToolUse spec hooks match the same way — justified
  8. PostToolUse fires once per call, only on the terminal result, in both loops — rides along, undeclared, not limited to KAS
  9. The postToolUse title-matcher warning is gone; an unknown matcher is warned about the same way as on PreToolUse — justified

[FIRST-PRINCIPLES-REVIEWED] 84f40e3

Description read

[DESCRIPTION-READ] 1c9818ba12aab26980f7808f6eeb7a8524386d27c5112df2350e4304b2639fc7

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 Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 84f40e32a8cade8efcee463d0764e3f811fa32d2 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 84f40e3

Verdict parsed from the review's SHA-scoped output markers for commit 84f40e32a8cade8efcee463d0764e3f811fa32d2.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 84f40e32a8cade8efcee463d0764e3f811fa32d2 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Oct 28, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 84f40e32a8cade8efcee463d0764e3f811fa32d2 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 84f40e3

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 84f40e32a8cade8efcee463d0764e3f811fa32d2 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 Oct 28, 2026
@buluoray
buluoray force-pushed the fix/25320-kas-parity branch from 3e8c01b to f4e3d88 Compare October 28, 2026 18:52
@buluoray

buluoray commented Oct 28, 2026 •

Copy link
Copy Markdown
Contributor Author

🤖 Kiro Crew Auto-Pipeline [operator: buluoray#ce473fca]: review dispositions for f4e3d88 (the previous head's commit, fixed up in place):

  • Opus 5.5, spec_hooks.py:265 warning and stale docs: fixed. The "postToolUse matcher is compared with the call's title" warning is gone; a PostToolUse matcher is now read like a PreToolUse one (warned only when it names no tool in Crew's tables). The module docstring and the hooks row of src/kiro_crew/docs/agent-spec-fields.md now describe id matching. test_spec_hook_kas_tool_names.py::test_a_post_tool_use_matcher_is_read_like_a_pre_tool_use_one pins the warning.
  • GPT 6.1, tool_results.py:913 identity popped on a non-terminal result: fixed. The dashboard turn fires PostToolUse and retires the call's title and id only on the terminal result (_tool_terminal). test_kas_spec_hooks_turn_loop.py::test_post_tool_use_runs_once_on_the_terminal_result sends an in_progress result with partial output first and asserts the hook ran once, with the final output; it goes red with the gate removed.
  • First Principles, subagent PostToolUse sibling (subagent_manager/run_turn.py): fixed in this PR, since the warning above could only go if every PostToolUse spec-hook site matched by id. The subagent run records the same per-call id, passes extra_hooks_tool_names, and fires once on the terminal result. Pinned by test_kas_spec_hook_gaps.py::test_a_kas_subagent_post_tool_use_meets_the_id_its_request_stated and ::test_a_kas_subagent_post_tool_use_waits_for_the_terminal_result, each red with its line reverted.
  • First Principles / Design, allowedCommands not in this revision: intended. It is a second commit built on fix(kas): auto-approve granted built-ins after Crew's own checks #25339's spec-builtin-grant row and pushed here after fix(kas): auto-approve granted built-ins after Crew's own checks #25339 merges; the description's merge order says so.
  • Design note, trustedAgents allow runs with no per-call deny: acknowledged. It is the shape kiro-cli's own trustedAgents has (no prompt), it passes the governance ceiling for every sub-agent ref, a PreToolUse hook on the sub-agent tool outranks it with an ask, and an availableAgents deny still wins over it.

@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: action required A blocking check or review needs attention labels Oct 28, 2026
@buluoray
buluoray enabled auto-merge (squash) October 28, 2026 18:53
@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 Oct 28, 2026
…tToolUse hooks

- A spec with no prompt goes out as "prompt": "" instead of Crew's
  background-worker brief, so a user-chosen agent runs on KAS's own default
  prompt as it does on kiro-cli. Only kirocrew-lite keeps the brief.
- toolsSettings.subagent.availableAgents becomes a subagent deny over "*"
  with the listed names excluded; trustedAgents a name-scoped subagent allow
  that goes through the governance ceiling like any authored allow.
- A PostToolUse spec hook's tool matcher meets KAS calls: the turn records
  the id the permission request stated, or KAS's shell tool for a call
  classified as a shell command, and passes it to the hook store.

Refs #25320
@buluoray
buluoray force-pushed the fix/25320-kas-parity branch from f4e3d88 to 84f40e3 Compare October 28, 2026 19:53
@buluoray

Copy link
Copy Markdown
Contributor Author

🤖 Kiro Crew Auto-Pipeline [operator: buluoray#ce473fca]: GPT 6.1 finding on f4e3d88 (tool_results.py:925, MCP identity lost on PostToolUse): fixed in 84f40e3.

Each call now keeps its harness id together with its canonical tool name and trusted MCP server (spec_hooks.PostToolIdentity, filled from the tool_call frame and topped up by the permission request). The dashboard turn passes all three to _fire (tool_identity, mcp_server), and the subagent run builds its spec names through hooks.pre_tool_match_names with the same three, so an @probefs/read_file or mcp__probefs__read_file matcher meets the call as it does on PreToolUse.

Pinned by test_kas_spec_hooks_turn_loop.py::test_a_post_tool_use_matcher_meets_an_mcp_call_by_its_server_form (both MCP forms run, @other/* does not) and test_kas_spec_hook_gaps.py::test_a_kas_subagent_post_tool_use_meets_an_mcp_call_by_its_server_form; removing the mcp_server pass-through reddens each.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention readiness: passed Eligible automated validation passed for the current revision and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Oct 28, 2026

@CrysisDeu CrysisDeu left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Comment, not approving yet at 84f40e32. The code is sound and every change narrows toward kiro-cli v2; two things stop an approve while auto-merge is on.

  1. The PR says it is incomplete. Body: "not complete until the allowedCommands commit is on it" and "merge order: #25339, then this PR". #25339 is open. An approve now merges a head that does not meet its own Goal and does not close #25320, and the follow-up commit (a new shell auto-approve) would land on an already-approved PR. Either remove that sentence and re-scope the body to what this head does, or wait for #25339 and push the commit; I approve on the next head either way.
  2. No security lane looked at it. Sensitive Change Review and Security Scope both logged "no sensitive path" for this head, because .github/scripts/sensitive_change_review.py:46 SENSITIVE_GLOBS covers hooks.py, hook_runtime/*, acp_tool_gate.py, agent_sdk/tool_gate.py but not acp/kas_permissions.py, agent_sdk/spec_hooks.py or dashboard/chat_turn/tool_approval.py. This PR emits a new KAS allow (trustedAgents) and makes spec postToolUse hook commands run on KAS where they never matched before. Add those three paths to the list in this PR (same gap I flagged on #25106) and post the template for this head.

What newly runs without asking, for the record: a spawn of a sub-agent listed in trustedAgents (still gated by may_skip_gate_now("use_subagent"), any PreToolUse ask covering subagent, and an availableAgents deny); spec postToolUse hooks with a tool matcher. No new hook kinds; worker kit and claude path untouched. That part is fine.

Also: subagent_manager/run_turn.py:1557, dashboard/chat_turn/tool_results.py:913: PostToolUse now fires only on a terminal frame, on every backend, and the body does not say so; a call whose frames never carry a terminal status now fires no hook. Document it and add a test for the no-terminal-status case. acp/kas_agents.py:336-342: the empty-prompt guard is gone but "" was only tested on kiro-cli 2.35.1 while the floor is 2.33.1; pin or verify. No live KAS fixture for any of the three changes; the turn-loop test uses hand-built events. Stale comments at kas_permissions.py:1061 ("No ALLOW is emitted") and mate_worker.py:582-583.

Posted by code-reviewer (Kiro Crew member) on behalf of @CrysisDeu. Full report on file.

@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.

Approved on behalf of the watch holder (bolichen). Design and First Principles pass on this head, UX skipped or pass, all checks green, no conflict, no open change request.

@KiroCrewCaptain
KiroCrewCaptain merged commit 37e0106 into main Oct 29, 2026
110 of 112 checks passed
@KiroCrewCaptain
KiroCrewCaptain deleted the fix/25320-kas-parity branch October 29, 2026 01:30
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 29, 2026
bolichen97 pushed a commit that referenced this pull request Oct 31, 2026
Backport to release/0.11.0, one commit:

- fix(install): download the pinned kas engine in cli installers (#26384)
  (cherry picked from commit 0a49fdb); docs/system-specs/modules/cli.md
  took only this PR's sentence on the `kas install` row.
- fix(electron): never spawn a gateway once the app is quitting (#26445)
  (cherry picked from commit 6a4d4e0), clean.
- fix: hold the remaining dropped asyncio tasks until they finish (#26463)
  (cherry picked from commit 8b3c698); adapted: the five sites in modules
  0.11.0 has (crew_log, artifact_ingest, remote_session/worker,
  subagent_manager admission gate and terminal). shared_crew/admission_entry.py,
  sprites_session/terminal.py and their tests are not on 0.11.0, so neither is
  the dropped-task guard test that lists them. The crew-log publisher test
  gains the held-task assertions, with `_flush` stubbed as on main.
- fix(kas): refuse a file write a fallbackAction deny spec does not cover
  (#26597) (cherry picked from commit 84c2aaa); doc and comment
  conflicts only: kept 0.11.0's wording around the sub-agent rules (#25361
  is not on 0.11.0) and dropped main's "v2 parity" acp-client block for the
  same reason.

Not picked: #26456 needs main-only `security/argv_rules.py` and the s3
download narrowing of #24562 in `deny_gate.py`. The v0.11.1-rc.1 Release
run's test failures are fixed by #26729.

All three version files move from 0.11.1-rc.1 to 0.11.1-rc.2, and the
in-flight [0.11.1] CHANGELOG section gains the four fixes and the
filelock bump of #26536 and the cron label fix of #26729 (#24718), both
already on the branch. #26149 and #25703 are test-only and have no
reader-visible line.
bolichen97 added a commit that referenced this pull request Oct 31, 2026
Backport to release/0.11.0, one commit:

- fix(install): download the pinned kas engine in cli installers (#26384)
  (cherry picked from commit 0a49fdb); docs/system-specs/modules/cli.md
  took only this PR's sentence on the `kas install` row.
- fix(electron): never spawn a gateway once the app is quitting (#26445)
  (cherry picked from commit 6a4d4e0), clean.
- fix: hold the remaining dropped asyncio tasks until they finish (#26463)
  (cherry picked from commit 8b3c698); adapted: the five sites in modules
  0.11.0 has (crew_log, artifact_ingest, remote_session/worker,
  subagent_manager admission gate and terminal). shared_crew/admission_entry.py,
  sprites_session/terminal.py and their tests are not on 0.11.0, so neither is
  the dropped-task guard test that lists them. The crew-log publisher test
  gains the held-task assertions, with `_flush` stubbed as on main.
- fix(kas): refuse a file write a fallbackAction deny spec does not cover
  (#26597) (cherry picked from commit 84c2aaa); doc and comment
  conflicts only: kept 0.11.0's wording around the sub-agent rules (#25361
  is not on 0.11.0) and dropped main's "v2 parity" acp-client block for the
  same reason.

Not picked: #26456 needs main-only `security/argv_rules.py` and the s3
download narrowing of #24562 in `deny_gate.py`. The v0.11.1-rc.1 Release
run's test failures are fixed by #26729.

All three version files move from 0.11.1-rc.1 to 0.11.1-rc.2, and the
in-flight [0.11.1] CHANGELOG section gains the four fixes and the
filelock bump of #26536 and the cron label fix of #26729 (#24718), both
already on the branch. #26149 and #25703 are test-only and have no
reader-visible line.

Co-authored-by: w <w@k.local>
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.

KAS parity: prompt fallback, toolsSettings and spec hooks differ from v2

3 participants