Skip to content

fix(apps): let app turns follow the Auto approval mode - #38830

Open
buluoray wants to merge 1 commit into
mainfrom
crew/slack/app-turn-auto-approval
Open

buluoray wants to merge 1 commit into
mainfrom
crew/slack/app-turn-auto-approval

Conversation

@buluoray

@buluoray buluoray commented Nov 17, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Under the Auto approval mode, an app's agent turn runs the tool calls the tool gate allows without asking, as a channel chat does, so Meetings stops prompting on every notes-file read and write.

With the KAS harness and the approval mode set to Auto, the Meetings agents (note taker, sketch artist, task extractor) raise an approval prompt for every fs_read and fs_write on their own notes file: about one prompt every 30 seconds during a meeting. On 0.12 there were none.

Why it matters

Everyone who records a meeting on KAS with Auto on is hit. The prompts come faster than a person can answer them, and an unanswered prompt is denied after the short unattended window, so the notes stop updating. KAS is the harness we are stabilising for 0.13.

Not a goal

  • Changing what happens under the Interactive approval mode: the owner is still asked.
  • Granting the Meetings agent specs file access of their own (a scoped allowedTools grant).
  • Changing how cron jobs, the task runner, autonudge or subagents answer their calls.

What changed (motivation → approach → change)

Symptom: every file call of an app turn prompts under Auto on KAS.

Cause: an app turn (ctx.turns.run) sends each call the tool gate neither denies nor grants to the owner's approval prompt, the one cron jobs use. That prompt never reads the gateway's approval mode, so Auto does not reach app turns. A channel chat under Auto approves the same call. KAS raises a permission request for every fs_* call (they are withheld from KAS auto-approve), so on KAS each one became a prompt.

Change: the app-turn prompt now follows the gateway's approval mode, as a channel turn does, but only for a turn on one of the app's own agents. _interactive_approval takes follows_approval_mode; AgentTurnSDK.run sets it from _is_own_agent(app, <recorded agent>). That check asks session_agent_spec_path, the resolver for the file a session of that agent loads (the crewmate folder for the Bot conductor and worker, agent.spec_pins applied, links refused, a refusal when two files claim the name with no pin). It says yes only when that one file sits in the user agents folder and is named <app>--<agent>.json, the name the app bridge writes. No file, any other file (host, another app, a Bot service spec) and any resolver error ask the owner. The answer is decided once, when the SDK starts the session (the moment it loads that file), and a reused session keeps it: a later re-pin does not change what a live session runs. A reused session with no stored answer, or one now recording another agent, asks the owner; a reset session is judged again when it starts. Under Auto (the channel resolver _configured_approval_mode) an own-agent call is approved without asking and leaves an SEL audit row (app.approval_mode_auto_approve). Three cases still go to the owner's prompt: a call under a held Bot limit, a low-fidelity child request, and a host whose policy denies trust (checked per call, as a cron job's auto is). Gate denies are unchanged, since they run before the prompt.

Docs: the app-kit API reference, the app-kit platform spec and the src/kiro_crew/apps/agent_turn_sdk.py docstring say what Auto now means for ctx.turns.run.

Backwards compatibility

Compatible: the new keyword defaults to off, so every other caller of the prompt behaves as before; under Interactive app turns still ask.

Note: Auto is the default approval mode (agent.approval_mode). So on a default install this undoes the owner prompt that #35601 added, but only for app turns on the app's own agents: those turns run without a prompt again, as they did before #35601. A turn on the host agent or another app's agent keeps that prompt.

Removes nothing: the change only adds an approve path under Auto; no field, key, row or caller is removed or tightened.

Tests

  • test/test_app_agent_turn_approval.py: the gateway registers the app prompt with follows_approval_mode equal to own_agent, and run() passes _is_own_agent for the recorded agent. _is_own_agent has one real-file test per resolver branch: the app's own file (yes); a host file, another app's file, an app file under another agent's name, an app file named like a Bot service agent (no); twins with a pin on the app file (yes), a pin on the host file (no), no pin (no); no file (no); a resolver error (no). A cancel during that read releases the session lease. A reused session keeps the answer from its start in both directions (the re-pin case), and a reused session with no stored answer or another agent is not own. A parametrized test pins that an app call is approved without a prompt under Auto, asked under Interactive, asked when the CLI flag says Interactive over a config Auto, and asked for a prompt that does not follow the mode, and that each Auto approval writes one audit row. Another test pins that under Auto a held Bot limit, a policy that denies trust and a low-fidelity child request still reach the prompt.
  • test/test_slack_gateway_composition_contract.py: the pinned signature of _interactive_approval gains the new keyword.

Proof: PROVEN test/test_app_agent_turn_approval.py::test_the_apps_own_file_is_own, test/test_app_agent_turn_approval.py::test_a_host_file_is_not_own, test/test_app_agent_turn_approval.py::test_another_apps_file_is_not_own, test/test_app_agent_turn_approval.py::test_an_app_file_under_another_agents_name_is_not_own, test/test_app_agent_turn_approval.py::test_an_app_file_named_like_a_mate_service_agent_is_not_own (head 12b0f02)

Mutations, each red on the named test: disabling the Auto branch reddens test_an_app_prompt_follows_the_gateway_approval_mode[None-auto-True-False]; dropping the trust policy check reddens test_under_auto_a_held_policy_denied_or_child_call_still_asks[policy]; passing own_agent=True for every turn reddens test_the_prompt_is_told_whether_the_turn_runs_the_apps_own_agent[False]; dropping the file-name check reddens the host, other-app, wrong-name and pinned-host tests; resolving only in the user folder reddens test_an_app_file_named_like_a_mate_service_agent_is_not_own; a resolver that ignores pins reddens the pinned-app-file test; moving the read out of the release guard reddens test_a_cancel_during_the_ownership_read_releases_the_session; judging on every turn again reddens test_a_reused_session_keeps_the_verdict_from_its_start and the two unknown-session tests.

Determinism: the changed test file ran 20/20 green at -n0 and 10/10 at -n 4 --dist loadgroup beside test_app_agent_turn_sdk.py and test_background_approval_routing.py; a shuffled run (seed 4911) passed 31/31.

Manual verification

Checked that the reported case still takes the new path (read-only, no live run). The meeting app's file-writing turns (ctx.turns.run) name the agents its manifest declares: the default note-taker and sketch agents come from its stored defaults, and the task extractor is a fixed constant. An enabled app's declared agents are materialized as ~/.kiro/agents/<app>--<agent>.json with their bare name kept, and the session records that bare name (a launch copy renames only the wire name), so _is_own_agent answers true and Auto applies. A user who points a meeting agent at the host default agent in the app's settings gets the owner prompt, as intended. No new control is needed: Auto is the existing Settings choice.

Related Issues

Closes #38816

Sibling sweep

Swept: git grep -n "_interactive_approval(" -- src/
Sibling: src/kiro_crew/slack/gateway_runtime/cron_turn.py -- not affected -- a cron job carries its own per-job approval mode
Sibling: src/kiro_crew/slack/gateway_runtime/nudge_channel_fire.py -- not affected -- an autonudge cycle is not an app turn and is out of this goal
Sibling: src/kiro_crew/slack/gateway_runtime/subagent_wiring.py -- not affected -- a parentless spawn already reads the global approval mode at spawn
Sibling: src/kiro_crew/slack/gateway_runtime/service_boot.py -- changed here

Pattern harvest

Not generalizable: the defect is one surface (app turns) that copied the cron prompt without the channel's approval-mode read; the other prompt users each have a deliberate mode of their own.

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

@buluoray
buluoray requested review from a team and KiroCrewCaptain as code owners November 17, 2026 23:42
@buluoray
buluoray requested a review from CrysisDeu November 17, 2026 23:42
@buluoray
buluoray enabled auto-merge (squash) November 17, 2026 23:43
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 17, 2026
@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 12b0f020332ed4523adaf2ac2e1c1564d08bd906 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 Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 12b0f020332ed4523adaf2ac2e1c1564d08bd906 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: under Auto, only the app's own <app>--<agent>.json session skips the prompt; gate denies, Bot limits, child requests and the trust policy still apply.

Notes

  • _own_agent_by_session is a process-global map, and an entry is removed only on SDK reset. A session closed by any other path leaves a stale (app, agent, verdict) entry. The is_new overwrite on the next start replaces it, so nothing breaks today. Removing the entry wherever the session manager closes a session would make it hold up if session keys are ever reused.

[DESIGN-REVIEWED] 12b0f02

Description read

[DESCRIPTION-READ] 5420a787fbb758930f3b6b7fbd241340e0926760b274fcb174cebf0e060af36a

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 18, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 12b0f020332ed4523adaf2ac2e1c1564d08bd906 — 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 scoped fix for a reported regression (#38816), and the description names the #35601 prompt it partly undoes. No duplicate, zero-consumer surface or product-shape item without a recorded decision was found.

Notes

  • Item 4 — oversized: the stored per-session result (_own_agent_by_session, "shortcut: an entry is dropped only when the SDK resets the session") adds module-level state that outlives the session and has stale-entry behaviour. Subtraction: none. Re-checking _is_own_agent on every turn would let a later re-pin onto <app>--<agent>.json auto-approve a session still running the host's file, so this state is justified.

What this change ships

Inventory (6 items) — 5 justified

Intent: Meetings on KAS under Auto stops asking the owner to approve every read and write of its notes file. FIX.

  1. Under Auto, a call the gate neither denies nor grants in an app turn on the app's own agent runs without a prompt — justified
  2. A turn on the host agent or another app's agent still prompts under Auto — justified
  3. A held Bot limit, a low-fidelity child request or a policy that denies trust still prompts under Auto — justified
  4. Whether the agent is the app's own is decided once when the session starts, and a reused session keeps it — oversized (state outlives the session)
  5. Each Auto approval writes an app.approval_mode_auto_approve SEL audit row — justified
  6. The API reference, platform spec and docstring describe the Auto behaviour — justified

[FIRST-PRINCIPLES-REVIEWED] 12b0f02

Description read

[DESCRIPTION-READ] ff29595df59fd5d6923d1fbe1ff11cfa41cffe2c58f683bdc5f816861f8095a8

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 18, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 12b0f020332ed4523adaf2ac2e1c1564d08bd906 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 12b0f02

Verdict parsed from the review's SHA-scoped output markers for commit 12b0f020332ed4523adaf2ac2e1c1564d08bd906.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 12b0f020332ed4523adaf2ac2e1c1564d08bd906 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 12b0f020332ed4523adaf2ac2e1c1564d08bd906 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 12b0f02

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 12b0f020332ed4523adaf2ac2e1c1564d08bd906 false-positive: <reason, 20 to 500 characters>

@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Nov 18, 2026
@buluoray
buluoray force-pushed the crew/slack/app-turn-auto-approval branch from a0d26d3 to a69fbcb Compare November 18, 2026 01:09
@buluoray

Copy link
Copy Markdown
Contributor Author

Rebased: main moved in docs/system-specs/modules/acp-client.md, docs/system-specs/modules/crew-mode.md, docs/system-specs/modules/shared-crew.md, test/test_shared_crew_teammate_owner_access.py since this head went green (1aa4eae -> f05269b); CI re-running.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: passed Eligible automated validation passed for the current revision and removed readiness: passed Eligible automated validation passed for the current revision readiness: checking Automated validation is still running labels Nov 18, 2026
@buluoray
buluoray force-pushed the crew/slack/app-turn-auto-approval branch from a69fbcb to 42bfbae Compare November 18, 2026 02:36
@buluoray

Copy link
Copy Markdown
Contributor Author

Rebased: main moved in docs/system-specs/modules/app-kit-platform.md, src/kiro_crew/slack/gateway_runtime/cron_exec.py, src/kiro_crew/slack/gateway_runtime/cron_failure.py, test/test_agent_spec_fields_doc.py and other same-dir files since this head went green (f05269b -> cda68bf); CI re-running.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention and removed readiness: passed Eligible automated validation passed for the current revision readiness: checking Automated validation is still running labels Nov 18, 2026
@buluoray
buluoray force-pushed the crew/slack/app-turn-auto-approval branch from 42bfbae to 396a652 Compare November 18, 2026 05:23
@github-actions github-actions Bot added readiness: checking Automated validation is still running 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 Nov 18, 2026
@KiroCrewCaptain

KiroCrewCaptain commented Nov 18, 2026 •

Copy link
Copy Markdown
Collaborator

Code change approver recommendation: A person should decide

Why: the decider thinks the change is probably fine but estimates a 13% chance that this change introduces a defect, above the 12% limit for approving on its own.

Under Auto, an app turn now approves a call the gate neither denies nor grants, but only when the session runs the app's own <app>--<agent>.json spec, as judged by session_agent_spec_path (pins followed, links refused, failing closed). The new branch sits after the held-call and low-fidelity-child checks and adds a per-call trust policy check. It uses the channel dispatchers' own mode resolver and matches how a channel turn treats Auto. The verdict is decided once when the session starts and stored per key. A reused session with no stored verdict or a different agent falls back to the prompt, and a reset session is judged again. The trust model fits governance, where an app's background spawn already always runs as auto and app Python runs in-gateway. The default keyword keeps every other caller unchanged. Tests cover each branch, and CI and all review lanes are green.

Tier: 2, held for a person: changes requested.

An automated recommendation, not a review: a maintainer still decides. It approves on its own only when the estimated chance of a defect is at most 12% and the change has at most 400 changed lines. Decider v3c (217fe607) · commit 12b0f02033 · 537 changed lines. If this recommendation is wrong, reply here: replies are how the approver is evaluated.

@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 Nov 18, 2026
@buluoray
buluoray force-pushed the crew/slack/app-turn-auto-approval branch from 3b1e7c7 to 48f29c8 Compare November 18, 2026 08:54
@buluoray

Copy link
Copy Markdown
Contributor Author

span=8bb09d4e6923
self-added: yes
mechanism: app-turn ownership check read the de-duplicated agent roster

  • Deduplicated discovery misidentifies a pinned host agent as app-owned

fixed in 48f29c8: _is_own_agent now reads the name through declared_spec_claim, the hardened resolver the session start uses (agent.spec_pins applied), not list_agents().
It returns true only when the running file and every claimant carry the <app>-- prefix, so a host twin (identical, or the pinned one) or another app's claimant is not own; a refused claim or unreadable directory is not own.
Tests: test_a_pin_choosing_the_host_twin_is_not_own and the twin rows of test_only_an_agent_file_under_the_apps_prefix_is_its_own use real files; accepting any one app claimant reddens both.

@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 18, 2026
@buluoray
buluoray force-pushed the crew/slack/app-turn-auto-approval branch from 48f29c8 to 91cfe5d Compare November 18, 2026 09:43
@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 Nov 18, 2026
@buluoray

Copy link
Copy Markdown
Contributor Author

span=51784250351d
self-added: yes
mechanism: app-turn ownership check now reads the exact file the session loads
resolution: narrowed to the session resolver; the folder and name reasoning is removed

  • _is_own_agent only looks for the agent's spec in the user-level agents dir

fixed in 91cfe5d: _is_own_agent asks session_agent_spec_path, the resolver for the file a session of the agent loads (crewmate folder for the Bot conductor and worker, agent.spec_pins applied, links refused, refusal on unpinned twins).
It says yes only when that one file is in the user agents folder and named <app>--<agent>.json; a Bot service spec resolves in the crewmate folder, so it fails by construction, and no file or a resolver error asks the owner.
test_an_app_file_named_like_a_mate_service_agent_is_not_own reddens when the read skips the crewmate folder; one real-file test covers each other resolver branch.

@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 18, 2026
@buluoray
buluoray force-pushed the crew/slack/app-turn-auto-approval branch from 91cfe5d to 2c55246 Compare November 18, 2026 10:08
@buluoray

Copy link
Copy Markdown
Contributor Author

span=8bb09d4e6923
self-added: yes
mechanism: app-turn ownership is judged once, when the SDK starts the session

  • Determine ownership from the running session, not the current pin

fixed in 2c55246: AgentTurnSDK.run judges _is_own_agent only when get_or_create starts a new session, the moment it loads that file, and stores the answer per session key with the app and recorded agent.
A reused session keeps that answer, so a later re-pin cannot turn a host-spec session into an own-agent one; a reused session with no stored answer, or one now recording another agent, asks the owner, and a reset drops the answer.
test_a_reused_session_keeps_the_verdict_from_its_start[False] is the re-pin case; judging on every turn again reddens it and the two unknown-session tests.

@buluoray

Copy link
Copy Markdown
Contributor Author

span=8bb09d4e6923
self-added: yes
mechanism: app-turn ownership is judged once, when the SDK starts the session
resolution: kept as is; no further patch on this span

  • Bind ownership to the spec actually consumed during startup

Rebutted: not a privilege gain. The trigger needs the owner to change agent.spec_pins (owner-only: the dashboard pin route requires the owner, or kirocrew agent pin on the host) during the few seconds get_or_create starts the session.
The only effect is that calls the tool gate already allowed run without the owner's prompt, under the Auto mode the owner chose; the owner can already approve those calls or switch the mode, and gate denies and a trust-denying policy still apply.
A reused session keeps its start-time answer (test_a_reused_session_keeps_the_verdict_from_its_start), and a session with no stored answer asks (test_a_reused_session_with_no_stored_verdict_is_not_own). Per the design review this span gets no further patch.

@buluoray

Copy link
Copy Markdown
Contributor Author

/ai-review override gpt 2c55246 not-applicable: Owner-only race at session startup: it needs the owner to re-pin agent.spec_pins while the session starts. No privilege gain; the owner holds the approval anyway (Auto is the owner's choice, and the owner can approve these calls or switch the mode). Gate denies and the trust policy still apply.

@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 2c552468a80d5c1a8835580cbbefa6c07b6e10af.

Owner-only race at session startup: it needs the owner to re-pin agent.spec_pins while the session starts. No privilege gain; the owner holds the approval anyway (Auto is the owner's choice, and the owner can approve these calls or switch the mode). Gate denies and the trust policy still apply.

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

@buluoray
buluoray force-pushed the crew/slack/app-turn-auto-approval branch from 2c55246 to 12b0f02 Compare November 18, 2026 10:46
@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 Nov 18, 2026
@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Nov 18, 2026
@KiroCrewCaptain

Copy link
Copy Markdown
Collaborator

This follows up on my change request on head 396a652. I rechecked head 12b0f02.

Earlier items:

  1. Auto-approve for agent="", a host agent or another app's agent: fixed. _is_own_agent in src/kiro_crew/apps/agent_turn_sdk.py asks session_agent_spec_path and accepts only <agents dir>/<app>--<agent>.json. test_a_host_file_is_not_own and test_another_apps_file_is_not_own pin it.
  2. Backwards compatibility should say Auto is the default and that this undoes the fix(apps): ask the owner before an app turn's unsettled tool call runs #35601 prompt: fixed in the body.
  3. Optional, repeated mode resolver: fixed. The branch now calls events_queue._configured_approval_mode.
  4. Optional, redundant not _held_call clause: fixed.
  5. Optional, Proof line: fixed. It names this head.

My blocking item is resolved. I am still not approving, because two points need a person:

  • On a default install, own-agent app turns now run calls the gate neither denies nor grants with no owner prompt. That partly reverses fix(apps): ask the owner before an app turn's unsettled tool call runs #35601. A maintainer asked on this PR for a sign-off on that trust change, and none is recorded yet.
  • The author marked the GPT lane's finding on 2c55246 ("Bind ownership to the spec actually consumed during startup") as not applicable. That finding says the new approve path could cover a session that loaded a host file. This head differs from 2c55246 by one import line only. A maintainer should confirm that release before merge.

What this review found on this head: a gate deny still wins, because _resolve_permission rejects it before the prompt runs. A held Bot limit, a low-fidelity child request and a policy that denies trust still reach the prompt. Each Auto approval writes an SEL row. In this review, test/test_app_agent_turn_approval.py passed 31 of 31, and each mutation named in the body turned its named test red. Done well: the ownership check fails closed on every branch and is tested with real files and pins.

Optional:

  • Replacing the "file sits in the user agents folder" check in _is_own_agent with True turns no test red. A test with a correctly named <app>--<agent>.json in the crewmate folder would pin it.
  • _own_agent_by_session has no conftest reset. Clearing it in the existing _forget_app_turn_approver fixture would stop entries from leaking between tests.
  • The link name _safe_link_name(_namespace(app, agent)) + ".json" is now built in three places. One shared helper would keep them in step.

@KiroCrewCaptain
KiroCrewCaptain dismissed their stale review November 18, 2026 12:07

Withdrawn: every item in this review is fixed or answered on the current head (see the follow-up comment). Other holds on this PR are listed there.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: passed Eligible automated validation passed for the current revision and removed readiness: passed Eligible automated validation passed for the current revision readiness: checking Automated validation is still running labels Nov 18, 2026

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

readiness: passed Eligible automated validation passed for the current revision

Projects

None yet

Development

Successfully merging this pull request may close these issues.

App turns ignore the Auto approval mode: Meetings agents prompt on every file read and write under KAS

3 participants