Skip to content

feat(mate): leave out a grant a bot's worker already holds on add - #33178

Merged
bolichen97 merged 1 commit into
mainfrom
dec/worker-kit-skip-held-grants
Nov 9, 2026
Merged

bolichen97 merged 1 commit into
mainfrom
dec/worker-kit-skip-held-grants

Conversation

@bolichen97

@bolichen97 bolichen97 commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: A Bot owner can add abilities from an agent such as Atlas whose tool settings grant only what the Bot's worker already has, and the worker still behaves exactly as the agent declares.

Add abilities refuses the whole agent, with its MCP servers, skills, prompt, hooks and permissions, when its toolsSettings holds a grant-only key. The preview answers 409 template_restrictions_uncarried with detail toolsSettings.web_fetch.trusted. For Atlas that key is the only blocker, and it grants nothing the worker lacks: the worker already lists web_fetch in its allowedTools, the agent carries a bare web_fetch allow, and KAS never applies the key.

Why it matters

An owner who picks Atlas under Add abilities gets nothing and is told to choose another agent. The only workaround is a hand-edited copy of the agent, which goes stale on every update of the agent. Every new agent template with such a key hits the same refusal.

Not a goal

  • Carrying grants KAS enforces, such as autoAllowReadonly, allowedPaths, or a trustedAgents list no carried allow covers. That is a separate decision.
  • Clearing agents refused for other reasons: a named permission bundle, allowedCommands entries Kiro Crew cannot parse, autoAllowReadonly, or availableAgents (fix(mate): carry a template's subagent.availableAgents onto a Bot's worker #31292).
  • Changing the worker merge at session start, existing Bot files or running sessions.
  • A new preview row kind or locale string.
  • Asking agent authors to change their specs.

What changed (motivation → approach → change)

Add abilities from Atlas succeeds. A grant-only tool setting that the Bot's worker already grants is left out of the agent's copy, and the preview lists it as a skipped toolsSettings row with the existing "Already has" label (id <tool>.<key>, for Atlas web_fetch.trusted). The worker behaves exactly as the agent declares, so no prompt appears or disappears.

Key Left out when Otherwise
web_fetch.trusted (or webFetch) the Bot's worker's own allowedTools derive a bare web_fetch allow (allow_granted_by_spec) refused by name, as on main: the base lacks web_fetch, the ceiling withholds it, the Bot's file excludes it or its owner revoked it
subagent.trustedAgents (or use_subagent) every entry is a literal agent name that a carried subagent allow with no exclude lists in its match refused by name: a pattern, a name the allow lacks, an ask rule, an empty list

Leaving the key out was chosen over carrying it because the worker already holds the grant, so nothing about what runs unasked changes, and over a new "not carried" row because that needs a new row kind in every locale. The proofs live in one table, HELD_GRANT_SETTINGS in src/kiro_crew/mate_spec_policy.py. _without_held_grants in src/kiro_crew/mate_worker_kit.py runs them before the restriction gates, against the worker the Bot runs once the add lands: the base and the agent (less those keys) merged, less the tools the Bot's file excludes and the approvals its owner revoked. Nothing is left out when the base or the revoked approvals cannot be read, when that merge refuses something else, or when either tool is written under two kiro-cli spellings; the refusal then names every key, as on main.

The leave-out runs at Add abilities time only. The worker merge at session start is unchanged, so a hand-edited Bot file holding either key still fails closed.

This is the maintainer's decision (Bolin Chen, 2026-11-07, set out in #32958). A new entry in docs/decisions/ records it, with its README row, and supersedes the 2026-11-02 template-policy entry in part; docs/system-specs/modules/crew-mode.md describes the leave-out in its Add abilities paragraph. There is no frontend or locale change.

Backwards compatibility

Compatible: only adds that main refuses are accepted. An add refused for any other reason is still refused, and the worker merge refuses the same keys as on main. A script that expects the 409 for an agent like Atlas gets a 200.

Removes nothing: no key, record, path or public function is taken away, and a key left out of the copy is one the worker already grants.

Tests

New file test/test_mate_worker_kit_held_grants.py, 21 cases.

  • Behaviour (red with the production change reverted): an Atlas-shaped add under the web_fetch and webFetch spellings previews a (toolsSettings, <tool>.trusted, skipped) row, adds no toolsSettings row, writes no toolsSettings, keeps the bare web_fetch allow, and the worker merges from the written file with web_fetch allowed. The same row appears when the owner revoked another tool's approval. A blocked list beside trusted is carried as an added row while trusted is skipped. trustedAgents that a carried subagent allow covers, under subagent and use_subagent, is skipped and no toolsSettings is written.
  • Pins (green both ways): web_fetch.trusted stays refused with the exact detail when the worker base lacks web_fetch, when the governance ceiling withholds it, when the owner revoked the web_fetch approval, when the Bot's own file excludes web_fetch, and when the revoked-approvals record cannot be read; the Bot file is untouched. When an agent is refused for an unenforceable deniedCommands too, the refusal still names web_fetch.trusted. A tool written under two kiro-cli spellings stays refused, naming the spelling kiro-cli drops and the key, and the Bot file is untouched. trustedAgents stays refused for a name the allow lacks, a pattern, an allow with exclude, an ask rule and an empty list. merge_worker_spec still raises SpecPolicyUncarried for a hand-edited file holding either key.

Proof: PROVEN test/test_mate_worker_kit_held_grants.py::test_a_web_fetch_trust_the_worker_already_grants_is_left_out_as_already_has[web_fetch], test/test_mate_worker_kit_held_grants.py::test_a_web_fetch_trust_the_worker_already_grants_is_left_out_as_already_has[webFetch], test/test_mate_worker_kit_held_grants.py::test_a_block_beside_the_trust_is_still_carried, test/test_mate_worker_kit_held_grants.py::test_an_approval_revoked_on_another_tool_still_leaves_the_trust_out, test/test_mate_worker_kit_held_grants.py::test_trusted_agents_a_carried_allow_names_are_left_out_as_already_has[subagent] (head 4d06c0a54215)

Every run below was on a Linux dev host, on tree a480eac61de1 (head 4d06c0a54215 on main 62ac53a); no test, build or gate ran on the author's machine.

  • Related tests: the new file with test_mate_worker_kit, test_mate_spec_policy, test_mate_config_migration and test_check_decisions_history_selftest (PYTHONPATH=src python -m pytest <files> -n0 -p no:cacheprovider): 241 passed.
  • Determinism: 20 runs of the new file at -n0, and 10 at -n 4 --dist loadgroup --max-worker-restart=2 beside test_mate_worker_kit and test_mate_spec_policy (181 passed each run), all green; a shuffled order with seed 27040, 21 passed.
  • Gates: every gates[] entry of the resolved profile other than the scoped backend and frontend suites and the Electron tests, plus test/test_flake_pattern_ratchet.py and semgrep scan --config semgrep/ --baseline-commit <merge-base> --error: 61 commands, all exit 0. jscpd ran after the website build, never beside it: run together, it reads the build's temporary output directory while that directory is being written.
  • Repro of A Bot refuses an agent whose toolsSettings grant only what its worker already has (web_fetch.trusted) #32958 (its step 1 agent spec, plus a subagent.trustedAgents twin, through mate_worker_kit.preview in a scratch home with the real governance ceiling): main refuses both with template_restrictions_uncarried and detail toolsSettings.web_fetch.trusted or toolsSettings.subagent.trustedAgents; this head previews each as one toolsSettings row (web_fetch.trusted, skipped) or (subagent.trustedAgents, skipped).
  • The full backend and frontend suites and the Electron tests run in CI, under the maintainer's gate policy; they were not run on the dev host.

Rebased onto main after review; patch unchanged (git range-diff shows the commit identical except the docs/decisions/README.md row's context: main's new 2026-11-08 row from #33003 is kept as it is, and this PR's row follows it). Re-run on a DevSpace on head 68ac577 (tree 18a32df75688, on main 1e3b894), every command exit 0 unless stated:

  • Related tests: the new file with test_mate_worker_kit, test_mate_spec_policy, test_mate_config_migration and test_check_decisions_history_selftest (PYTHONPATH=src python -m pytest <files> -n0 -p no:cacheprovider): 243 passed. The new file run against main's production code: the 6 behaviour cases fail and the 15 pins pass, exit 1.
  • Repro of A Bot refuses an agent whose toolsSettings grant only what its worker already has (web_fetch.trusted) #32958 as a user meets it (repro.sh base|fix: a real kirocrew gateway in a scratch home with the real governance ceiling, the Atlas agent file copied into its agents folder beside the issue's step 1 spec and a subagent.trustedAgents twin, then the dashboard's Add abilities preview and apply calls over HTTP): main exit 1, all three previews answer 409 template_restrictions_uncarried naming toolsSettings.web_fetch.trusted or toolsSettings.subagent.trustedAgents; this head exit 0, each preview shows one toolsSettings row (web_fetch.trusted, skipped) or (subagent.trustedAgents, skipped), the apply writes no toolsSettings to the Bot's file, its worker still runs web_fetch unasked, and a hand-edited file holding web_fetch.trusted is still refused at session start.
  • Gates: check_black_formatting.py, check_subprocess_encoding.py, isort, flake8, mypy --platform linux, the comment-history, brand-name, harness-parity, decision-ledger-history (with its self-test) and file-line-cap checks, docs-lint, black --check on the touched Python files and the flake-pattern ratchet.

Manual verification

The #32958 repro above ran on this head through the Python API, not the dashboard. Still required: picking Atlas under a Bot's Abilities > Add abilities in the dashboard and seeing the "Already has" row, which the existing skipped row renders.

Screenshots / video

N/A: the diff changes no frontend file. The preview's existing skipped kind and its "Already has" label render the new row.

Related Issues

Fixes #32958

This head merges cleanly (git merge-tree) with the open #31292 and #31241, which edit the same files, with each and with both together. Once #31292 lands, its 2026-11-06 entry, which keeps trustedAgents refused until decided separately, can join this entry's Supersedes: line: this entry decides only the case a carried allow already covers.

The entry carries a Supersedes: line, so the recorded-decisions-are-not-regressions rule blocks this PR by design (decisions README rule 3). A maintainer's override of that rule is what lets it land, and it covers the entry and the code it authorizes together. The entry's Evidence links #32958, the issue the maintainer opened to set out this decision, as the on-record artifact decisions README rule 4 asks for.

Sibling sweep

N/A: a feat PR. The keys left out are one table, HELD_GRANT_SETTINGS, so there is no second site.

Pattern harvest

Not generalizable: the two keys and their proofs follow how KAS projects web_fetch and subagent grants, and a further key is one more entry in HELD_GRANT_SETTINGS, not a new site.

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

Contributed under the project's Apache-2.0 license.

@bolichen97
bolichen97 requested review from a team and KiroCrewCaptain as code owners November 8, 2026 13:04
@bolichen97
bolichen97 requested a review from Zedmor November 8, 2026 13:04
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 8, 2026
@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 68ac577458b01cc7696b8a5c4d4ee0df211a762d 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 8, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 68ac577458b01cc7696b8a5c4d4ee0df211a762d — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: the change only accepts adds that main refuses. A key is left out only when the merged worker already grants it, and the worker merge at session start still refuses either key in a file.

Notes

  • The proof holds only at the moment of the add. If the base later loses web_fetch, or the owner revokes an approval, the left-out key does not come back, so the worker prompts where the agent declared trust. That fails narrower, not wider, so it is acceptable, but the spec paragraph should say so.

[DESIGN-REVIEWED] 68ac577

Description read

[DESCRIPTION-READ] 353edd785d95fe75abe847b41c51e282e942ff17fd90677690686d6b14972c2c

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of 68ac577458b01cc7696b8a5c4d4ee0df211a762d — 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

The web_fetch.trusted leave-out answers the Atlas refusal reported in #32958. The subagent.trustedAgents half is backed only by symmetry: no failing agent is named.

Notes

  • Item 2 — inherited: the only defect reported is Atlas's toolsSettings.web_fetch.trusted. The description itself calls the trustedAgents case "a subagent.trustedAgents twin", which is symmetry, and no agent is shown being refused for it. Subtraction: delete _trusted_agents_held, _LITERAL_AGENT_NAME and the "subagent" row of HELD_GRANT_SETTINGS, then shrink the table to the single web_fetch.trusted check.

What this change ships

Inventory (6 items) — 5 justified

Intent: let a Bot owner add abilities from an agent like Atlas instead of having the whole add refused over a tool setting that grants nothing the worker lacks. A FIX, though the title types it feat.

  1. Add abilities from an agent whose only blocker is web_fetch.trusted now succeeds when the worker already allows web_fetch — justified
  2. A subagent.trustedAgents list that a carried subagent allow already names is also left out — undeclared as a separate need; symmetry with item 1
  3. The preview shows each left-out key as an "Already has" toolsSettings row — justified
  4. Hand-edited Bot files holding either key still fail closed at session start — justified
  5. New decision entry and README row, partly superseding the 2026-11-02 template-policy entry — justified
  6. The crew-mode spec's Add abilities paragraph describes the leave-out — justified

[FIRST-PRINCIPLES-REVIEWED] 68ac577

Description read

[DESCRIPTION-READ] fd38f4df4efdd0268df82cc2cafdb9728f6ebde044f5b2ab1d9f3014c8b16832

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ human override accepted

Reviewed 68ac577458b01cc7696b8a5c4d4ee0df211a762d — this comment is updated in place on each push.

Human judgment by @bolichen97 overrides the Opus 5.5 finding for 68ac577458b01cc7696b8a5c4d4ee0df211a762d; the recorded reason is authoritative for this commit.

[OPUS-OVERRIDE] 68ac577

Verdict recorded from an authorized human decision for commit 68ac577458b01cc7696b8a5c4d4ee0df211a762d.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 68ac577458b01cc7696b8a5c4d4ee0df211a762d false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ human override accepted

Human judgment by @bolichen97 overrides the GPT 6.1 finding for 68ac577458b01cc7696b8a5c4d4ee0df211a762d; the recorded reason is authoritative for this commit.

[GPT-OVERRIDE] 68ac577

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 68ac577458b01cc7696b8a5c4d4ee0df211a762d false-positive: <reason, 20 to 500 characters>

@bolichen97
bolichen97 enabled auto-merge (squash) November 8, 2026 13:14
@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention merge conflict Branch has merge conflicts with its base — author must resolve before merge and removed readiness: checking Automated validation is still running labels Nov 8, 2026
@bolichen97
bolichen97 force-pushed the dec/worker-kit-skip-held-grants branch from 7ba0f6e to 8da2047 Compare November 8, 2026 18:07
@github-actions github-actions Bot removed the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Nov 8, 2026
@bolichen97

Copy link
Copy Markdown
Contributor Author

Rebased: main moved in docs/decisions/README.md since this head was built (a2a0da4 -> 2da9ec8); CI re-running. The rebase clears a conflict in the docs/decisions/README.md index (main's two new rows kept as they are, this PR's one row added after them). The change itself is the same as on 7ba0f6e.

[operator: bolichen97]

@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: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Nov 8, 2026
@bolichen97

Copy link
Copy Markdown
Contributor Author

self-added: no

  • The PR adds a decision entry that supersedes part of the 2026-11-02 template-policy entry (span=3cf431811ff0)

Needs a decision: the recorded-decisions-are-not-regressions rule flags every superseding entry by design, and no code change clears it. A maintainer is asked to rule on whether the partial supersede of the 2026-11-02 entry stands, and to record that ruling on this head.
The lane found no code defect: Design, First Principles and UX pass on this head. The decision behind the entry is set out in #32958.
This head only re-synced onto main (8da2047 on 2da9ec8) to clear a conflict in the docs/decisions/README.md index; the change is the same as on 7ba0f6e.

[operator: bolichen97]

@bolichen97

Copy link
Copy Markdown
Contributor Author

self-added: no

  • Superseding the recorded policy requires a maintainer override (span=32d7ea92c8f6)

Needs a decision: this is the same recorded-decisions-are-not-regressions gate the Opus lane raises, on the same line. It is fenced as security-class, so it is left to a maintainer: no rebuttal and no override is posted here.
A maintainer is asked to rule on whether the partial supersede of the 2026-11-02 entry stands, and to record that ruling on this head. The decision behind the entry is set out in #32958.
This head only re-synced onto main (8da2047 on 2da9ec8) to clear a conflict in the docs/decisions/README.md index; the change is the same as on 7ba0f6e.

[operator: bolichen97]

@github-actions github-actions Bot added the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Nov 8, 2026
@bolichen97
bolichen97 force-pushed the dec/worker-kit-skip-held-grants branch from 8da2047 to dd06f3b Compare November 8, 2026 19:21
@bolichen97

Copy link
Copy Markdown
Contributor Author

Rebased: main moved in docs/decisions/README.md since this head was built (2da9ec8 -> 3cd4522); CI re-running. The rebase clears a second conflict in the docs/decisions/README.md index (main's new row kept as it is, this PR's one row added after it). The change itself is the same as on 8da2047.

[operator: bolichen97]

@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: action required A blocking check or review needs attention merge conflict Branch has merge conflicts with its base — author must resolve before merge readiness: checking Automated validation is still running labels Nov 8, 2026
@bolichen97

Copy link
Copy Markdown
Contributor Author

self-added: no

  • Superseding the recorded policy requires a maintainer override (span=32d7ea92c8f6)

Needs a decision: this is the same recorded-decisions-are-not-regressions gate the Opus lane raises, on the same line. It is fenced as security-class, so it is left to a maintainer: no rebuttal and no override is posted here.
A maintainer is asked to rule on whether the partial supersede of the 2026-11-02 entry stands, and to record that ruling on this head. The decision behind the entry is set out in #32958.
This head only re-synced onto main (dd06f3b on 3cd4522) to clear a conflict in the docs/decisions/README.md index; the change is the same as on 8da2047 and 7ba0f6e.

[operator: bolichen97]

@bolichen97
bolichen97 force-pushed the dec/worker-kit-skip-held-grants branch from dd06f3b to 2f19c42 Compare November 8, 2026 23:43
@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 8, 2026
@bolichen97

Copy link
Copy Markdown
Contributor Author

self-added: no

  • Superseding the recorded policy requires a maintainer override (span=32d7ea92c8f6)

Needs a decision: the same recorded-decisions-are-not-regressions BLOCK on the decision file's Supersedes: line, which that rule flags by design. It is fenced as security-class, so it is left to a maintainer: no rebuttal and no override is posted here.
A maintainer is asked to rule on whether the partial supersede of the 2026-11-02 entry stands, and to record that ruling on this head. The decision behind the entry is set out in #32958.
This head only re-synced onto main (2f19c42 on b358303) to pick up main's re-pin of the lazy-import count that failed Backend Tests shard 6; git range-diff shows the change identical to dd06f3b.

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention merge conflict Branch has merge conflicts with its base — author must resolve before merge and removed readiness: checking Automated validation is still running labels Nov 8, 2026
Add abilities refused a whole agent (its servers, skills and prompt)
when its toolsSettings held a grant-only key the Bot's worker already
grants. Atlas is the case: its only blocker is web_fetch.trusted, a key
KAS never applies, while the worker base already lists web_fetch in its
allowedTools.

At kit time only, before the restriction gates, a grant-only key is now
left out of the template's copy when the Bot's worker already grants
what it grants, and the preview lists it as a skipped toolsSettings row
("Already has", id <tool>.<key>): web_fetch.trusted when the worker's
own allowedTools derive a bare web_fetch allow, and
subagent.trustedAgents when every entry is a literal name a carried
subagent allow (no exclude) lists. The proof reads the worker the Bot
runs: the base and the agent merged, less the Bot file's excludedTools
and the approvals its owner revoked. Patterns, uncovered names, a
withheld, excluded or revoked web_fetch, an unreadable revocation
record, a tool written under two kiro-cli spellings and a template
refused for anything else stay refused by name. The worker merge is
unchanged, so a hand-edited Bot file holding either key still fails
closed at session start.

The superseding decision entry, its README row and the crew-mode spec
land in this commit.
@bolichen97
bolichen97 force-pushed the dec/worker-kit-skip-held-grants branch from 2f19c42 to 68ac577 Compare November 9, 2026 01:55
@github-actions github-actions Bot removed the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Nov 9, 2026
@bolichen97

Copy link
Copy Markdown
Contributor Author

self-added: no

  • Superseding the recorded policy requires a maintainer override (span=32d7ea92c8f6)

Needs a decision: the same recorded-decisions-are-not-regressions BLOCK on the decision file's Supersedes: line, which that rule flags by design ("a maintainer's override of this flag is what lets it land"). It is fenced as security-class, so it is left to a maintainer: no rebuttal and no override is posted here.
Reproduced on 68ac577 on a Linux DevSpace: main (1e3b894) refuses Add abilities from Atlas with 409 template_restrictions_uncarried, detail toolsSettings.web_fetch.trusted; this head previews one (web_fetch.trusted, skipped) row, writes no toolsSettings, and a hand-edited Bot file holding the key is still refused at session start. That is the partial supersede the entry records.
A maintainer is asked to rule on whether the partial supersede of the 2026-11-02 entry stands, and to record it on the head it should land on: /ai-review override gpt <head> owner-decision: <link to the ruling comment>. The class needs a #issuecomment-<id> link, and #32958, the issue the entry rests on, has no comment yet.
This head only re-synced onto main (68ac577 on 1e3b894) to clear a conflict in the docs/decisions/README.md index; git range-diff shows the change identical to 2f19c42 apart from that row's context.

@bolichen97

Copy link
Copy Markdown
Contributor Author

self-added: no

  • The PR adds a decision entry that supersedes part of the 2026-11-02 template-policy entry (span=3cf431811ff0)

Needs a decision: the recorded-decisions-are-not-regressions rule flags every superseding entry by design, and the lane's own Fix line says no code change clears it. A maintainer is asked to rule on whether the partial supersede of the 2026-11-02 entry stands, and to record that ruling on the head it should land on.
Reproduced on 68ac577 on a Linux DevSpace: main (1e3b894) refuses Add abilities from Atlas with 409 template_restrictions_uncarried naming toolsSettings.web_fetch.trusted; this head previews it as one (web_fetch.trusted, skipped) row, and the session-start merge still refuses the key in a hand-edited Bot file. The lane found no code defect: Design and First Principles pass on this head.
The record is /ai-review override fable <head> owner-decision: <link to the ruling comment>; the class needs a #issuecomment-<id> link, and #32958, the issue the entry rests on, has no comment yet.

@bolichen97

Copy link
Copy Markdown
Contributor Author

Maintainer decision (Bolin Chen, bolichen97, Kiro Crew maintainer): I accept superseding part of docs/decisions/2026-11-02-a-crewmates-worker-carries-its-template-policy.md, as recorded in docs/decisions/2026-11-07-add-abilities-leaves-out-a-grant-the-worker-already-holds.md. At Add abilities time only, web_fetch.trusted and subagent.trustedAgents that the merged worker already grants are left out instead of refused by name; every other refusal in the 2026-11-02 entry stands. This is option 2 of the worker-kit memo, decided on 2026-11-07 (context #32958). Posted by my agent at my instruction.

@bolichen97

Copy link
Copy Markdown
Contributor Author

/ai-review override gpt 68ac577 owner-decision: agent: maintainer Bolin Chen accepted superseding the 2026-11-02 template-policy entry for grants the worker already holds (worker-kit memo option 2); decision: #33178 (comment)

@bolichen97

Copy link
Copy Markdown
Contributor Author

/ai-review override fable 68ac577 owner-decision: agent: maintainer Bolin Chen accepted superseding the 2026-11-02 template-policy entry for grants the worker already holds (worker-kit memo option 2); decision: #33178 (comment)

@github-actions

github-actions Bot commented Nov 9, 2026

Copy link
Copy Markdown
Contributor

Human judgment recorded

@bolichen97 recorded a owner-decision release (class owner-decision) for the fable AI finding on 68ac577458b01cc7696b8a5c4d4ee0df211a762d.

agent: maintainer Bolin Chen accepted superseding the 2026-11-02 template-policy entry for grants the worker already holds (worker-kit memo option 2); decision: #33178 (comment)

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

@github-actions

github-actions Bot commented Nov 9, 2026

Copy link
Copy Markdown
Contributor

Human judgment recorded

@bolichen97 recorded a owner-decision release (class owner-decision) for the gpt AI finding on 68ac577458b01cc7696b8a5c4d4ee0df211a762d.

agent: maintainer Bolin Chen accepted superseding the 2026-11-02 template-policy entry for grants the worker already holds (worker-kit memo option 2); decision: #33178 (comment)

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

@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: action required A blocking check or review needs attention labels Nov 9, 2026
@bolichen97
bolichen97 merged commit 7432436 into main Nov 9, 2026
99 of 109 checks passed
@bolichen97
bolichen97 deleted the dec/worker-kit-skip-held-grants branch November 9, 2026 05:41
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Nov 9, 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.

A Bot refuses an agent whose toolsSettings grant only what its worker already has (web_fetch.trusted)

2 participants