chore(spec): govern ai (Agent/Tool/Skill) + allowlist mode in the liveness gate#1932
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
…iveness gate
Third category for the spec-liveness gate. Two gate capabilities make noisy
categories tractable:
- allowlist mode (`"mode":"allowlist"` + `"governed":[...]`) — only the named
authorable schemas are checked; the rest of the category is out of scope. The
json-schema categories don't map to authorable types (ai is mostly embedder/
knowledge/model DTOs), so blanket per-category classification doesn't scale. A
governed name that no longer resolves is reported (catches renames).
- auto-classify ADR-0010 framework provenance/lock fields (_lock*, _provenance,
_packageId/Version, _lockDocsUrl, protection) as `live`, so every type's ledger
doesn't repeat them.
ai ledger seeded from docs/audits/2026-06-{agent,tool,skill}schema-*.md:
- 63 props: 46 live / 5 experimental / 12 dead, 0 unclassified.
- Agent: core + model/skills/tools/active/planning live; access/permissions/
visibility/tenantId/knowledge DEAD (access-control is a no-op — chat route
hardcodes ['ai:chat','ai:agents'], ADR-0049 #1884); lifecycle/memory/guardrails/
structuredOutput experimental (aspirational autonomy).
- Tool: write-only metadata — name/description/parameters/objectName live (via the
parallel AIToolDefinition); category/requiresConfirmation/active/builtIn/
permissions dead; outputSchema experimental.
- Skill: name/label/description/instructions/tools/triggerConditions/active live;
triggerPhrases dead (no matcher), permissions dead (+ requiredPermissions drift).
Stacked on #1924 (identity). GOVERNED = security, identity, ai.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
os-zhuang
force-pushed
the
chore/spec-liveness-ai
branch
from
June 16, 2026 02:35
37c1d01 to
e40e7b6
Compare
github-actions
Bot
added
documentation
Contributor
📓 Docs Drift CheckThis PR changes 1 package(s): 89 hand-written doc(s) reference the affected code and may need an implementation-accuracy re-verification:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Third category for the spec-liveness gate, plus the refactor needed to make noisy categories tractable.
Why the refactor
The json-schema categories don't map to "authorable metadata types" —
aiis mostly embedder/knowledge/model/runtime DTOs, with only Agent/Tool/Skill author-written. Blanket "classify every object schema" doesn't scale. Two additions:"mode":"allowlist"+"governed":["Agent","Tool","Skill"]; only those are checked, the rest of the category is out of scope. Agovernedname that no longer resolves is reported (catches renames silently dropping coverage)._lock*,_provenance,_packageId/Version,protection) appear on every type and are system-stamped; the gate auto-classifies themliveso ledgers don't repeat them.aifindings (seeded from the agent/tool/skill audits)63 props: 46 live / 5 experimental / 12 dead, 0 unclassified.
access/permissions/visibility/tenantIdDEAD — "who can chat with this agent" is a no-op (the chat route hardcodes['ai:chat','ai:agents'],agent-routes.ts:109; ADR-0049 [P0][security] Agent access control is a no-op (permissions/visibility/access) #1884).knowledgedead (shape drift).lifecycle/memory/guardrails/structuredOutputexperimental (aspirational autonomy).model.provider/topPdead within a livemodel.AIToolDefinition). name/description/parameters/objectName live; category/requiresConfirmation/active/builtIn/permissions dead; outputSchema experimental.triggerConditions/active live;triggerPhrasesdead (no intent matcher exists);permissionsdead (+requiredPermissionsnaming drift).Gate result
🤖 Generated with Claude Code