← Back to the capability index
AI · ai.groundingSpec Grounding Mutations
Source evaluation — counted evidence Pro
Evidence by type
| Evidence type | Detail | Result |
|---|---|---|
| Route entries & proving tests | 2 route entries | 11 proving tests (implemented: 2) |
SDK coverage
| SDK | Status | Entry points | Note |
|---|---|---|---|
| honua-sdk-js | not-covered | — | — |
| honua-sdk-dotnet | not-covered | — | — |
| honua-sdk-python | not-covered | — | — |
Executable samples
No executable sample published for this capability yet.
Known gaps
Gaps are attached at the category level (cap/ai label), not the individual capability key — none of the open issues in this category parsed a capability key matching this specific capability (honua-io/honua-evidence#5).
- #3411 feat(control-plane): WS1b — canonical operation instance/evidence envelope and durable approval bridge
- #3424 feat(ai proxy): sign canonical real-model transcript provenance
- #3430 fix(mcp): authenticate OAuth before tenant resolution and canonically bind sessions
- #3431 fix(mcp): preserve OAuth scope narrowing through Studio and approved operation replay
- #3474 fix(mcp): make model-facing control-plane tools proposal-only and authorization-bound
- #3475 fix(observability): publish source freshness and completeness envelopes for agent evidence
Raw receipts
- capability-keys.v1.json — canonical key definition for
ai.grounding. - capability-matrix.v1.json — honua-server's Phase-A evidence snapshot (entry/test counts, CITE, parity, interop, geobench).
- sdk-js coverage · sdk-dotnet coverage · sdk-python coverage
- honua-samples run-samples CI — executable sample run history.
- docs/cite-status.md — CITE evidence freshness ("Last reviewed" date + source sha).
- data/producers/dr-drills/ · data/producers/live-canary/ — pushed evidence envelopes (see docs/producer-contracts.md).
- capability-matrix.v1.json — the full enriched aggregate backing this page.