Skip to content

fix(agents+install): valid CC sub-agent tool names (#551) + exclude authoring-only prober (#552) - #571

Merged
artyhoo merged 1 commit into
stagingfrom
feature/agents-toolname-fix-551-552-8a5238
Jun 16, 2026
Merged

fix(agents+install): valid CC sub-agent tool names (#551) + exclude authoring-only prober (#552)#571
artyhoo merged 1 commit into
stagingfrom
feature/agents-toolname-fix-551-552-8a5238

Conversation

@artyhoo

@artyhoo artyhoo commented Jun 16, 2026

Copy link
Copy Markdown
Owner

Summary

Fixes #551 and #552. Built autonomously by aif-handoff (task 8a523805); harvested via the GitHub Git Data API (container git transport was blocked by a missing-actionlint pre-push hook).

§1.7 Forward-check applied

Checked this change against existing disciplines before shipping:

  • doc-authority-hierarchy.md — the SHIPPED_DOCSREQUIRED_HEADER_DOCS swap keeps the shipped-subset count at 18 and set-equal, satisfying the assertion at packages/core/principles/09-doc-authority-hierarchy.ts:139.
  • build-first-reuse-default.md — fix matches upstream AI Factory CC naming (ADOPT, not BUILD); the tools: line corrected at agents/compliance-verifier.md:4.
  • no-paid-llm-in-ci.md — no API-billed path introduced; verdict OK.

§1.7 Backward-check applied

Swept the existing artefacts under this change's scope:

🤖 Autonomous build via aif-handoff, harvested via gh API.

@artyhoo
artyhoo enabled auto-merge (squash) June 16, 2026 18:31
@artyhoo
artyhoo merged commit 81a0251 into staging Jun 16, 2026
26 checks passed
artyhoo added a commit that referenced this pull request Jun 16, 2026
…k-guard (#574)

- agents-toolname-fix-551-552-meta-launch/kickoff.md: /pipeline meta-launch
  dispatch record (routing fix→DIRECT/Mode-A, §1.7 PR-body mandate, principle-12 green).
- agents-toolname-fix-551-552/kickoff.md: add §4c park-don't-guess block so
  autonomous aif-handoff dispatch cannot silently guess design forks.

The #551/#552 code fix itself ships separately in PR #571.
artyhoo added a commit that referenced this pull request Jun 16, 2026
…551 regression-prevention)

Phase 1 of shipped-artifact-liveness-gap (research PR #566, Option C phased, scope (i)).
The 6 agents themselves were already fixed on staging by #571; this adds the
DETERMINISTIC GATE #571 did not — preventing any future non-canonical tool name
from shipping (the form-check that would have caught #551 at pre-push/CI).

- packages/core/principles/21-shipped-agent-tools-valid.test.ts (9 tests, paired-negative arm)
- prior-art-evaluations.md #121 (BUILD; own liveness family with #114/#115)

Built autonomously via aif-handoff (task 8cae6079); agent edits dropped as redundant with #571.

Prior-art: prior-art-evaluations.md#121 (BUILD - shipped-agent tools:-name allow-list gate; no upstream validator; own liveness family with #114/#115; T16 form-check distinct from #53/#115 behavioural eval).
artyhoo added a commit that referenced this pull request Jun 16, 2026
…551 regression-prevention)

Phase 1 of shipped-artifact-liveness-gap (research PR #566, Option C phased, scope (i)).
The 6 agents were already fixed on staging by #571; this adds the DETERMINISTIC GATE
#571 did not — preventing any future non-canonical tool name from shipping.

- packages/core/principles/21-shipped-agent-tools-valid.test.ts (9 tests, paired-negative)
- prior-art-evaluations.md #121 (BUILD; own liveness family with #114/#115)

Built autonomously via aif-handoff (task 8cae6079); agent edits dropped as redundant with #571.

§1.7: forward-check applied — no-paid-llm-in-ci compliant (deterministic vitest, zero API call), build-first-reuse BUILD #121 (no upstream validator), T16 form-check not behaviour-check; backward-check sweep — #571 already made the 6 agents canonical so this adds only the missing regression gate and supersedes nothing. Evidence: packages/core/principles/21-shipped-agent-tools-valid.test.ts:46
Prior-art: prior-art-evaluations.md#121 (BUILD - shipped-agent tools:-name allow-list gate; no upstream validator; own liveness family with #114/#115; T16 form-check distinct from #53/#115 behavioural eval).
artyhoo added a commit that referenced this pull request Jun 16, 2026
…551 regression-prevention) (#576)

Phase 1 of shipped-artifact-liveness-gap (research PR #566, Option C phased, scope (i)).
The 6 agents were already fixed on staging by #571; this adds the DETERMINISTIC GATE
#571 did not — preventing any future non-canonical tool name from shipping.

- packages/core/principles/21-shipped-agent-tools-valid.test.ts (9 tests, paired-negative)
- prior-art-evaluations.md #121 (BUILD; own liveness family with #114/#115)

Built autonomously via aif-handoff (task 8cae6079); agent edits dropped as redundant with #571.

§1.7: forward-check applied — no-paid-llm-in-ci compliant (deterministic vitest, zero API call), build-first-reuse BUILD #121 (no upstream validator), T16 form-check not behaviour-check; backward-check sweep — #571 already made the 6 agents canonical so this adds only the missing regression gate and supersedes nothing. Evidence: packages/core/principles/21-shipped-agent-tools-valid.test.ts:46
Prior-art: prior-art-evaluations.md#121 (BUILD - shipped-agent tools:-name allow-list gate; no upstream validator; own liveness family with #114/#115; T16 form-check distinct from #53/#115 behavioural eval).
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.

Shipped sub-agents declare non–Claude-Code tool names (read_file/list_files/run_command) → empty toolset → they fabricate when dispatched

1 participant