# Real Omni analysis

Acceptance: Audio, Video, and Audio/video Analysis must submit actual media to
the Omni comprehension runtime. Missing weights or an unavailable runtime must
never yield synthetic scene entities, events, or a successful mock answer.

## Findings

- The production AV registry seeded deterministic mock adapters. The browser
  modes sent identical requests, and any live role labeled the entire result live.
- The old Python sidecar implements detection/tracking only; it cannot make its
  advertised semantic roles real merely by downloading weights.
- The reference `qwen-omni-adapters-main` runtime exposes adapter v1 on `/api/chat`.
  Its model response echoes the request and is not runtime identity attestation.
- Read-only inspection found an existing Ornith Omni bridge on GPU 1. This differs
  from the earlier GPU 0/Qwen instruction. The user selected that existing Ornith/GPU 1 lane for live verification.
  Actual placement and manifest identity were verified before inference; no service changed.

## Work

- [x] Delegate discovery across browser, execution, and reference runtime.
- [x] Implement one bounded, cancellable Omni media client with real input
  conversion, strict adapter/provenance validation, and explicit configuration.
- [x] Remove implicit production mock fallback; keep explicit offline fixtures.
- [x] Route the native AV tool and browser modes through the same client.
- [x] Show model configuration/readiness and distinct transcript/audio/visual
  evidence; do not claim continuous live capture for a local-file form.
- [x] Preserve project/session/request identity and same-origin authenticated API.
- [x] Document shared weight ownership, runtime configuration, and limitations.
- [x] Verify client, route, frontend, and required chat transport regressions.
- [x] Exercise the source-bundled browser in a private fixture server.
- [x] Perform live inference only after exact endpoint/model/GPU verification.
- [x] Commit scoped source changes and push the tracked main branch.

## Delivery boundaries

Do not overwrite unrelated dirty work, shared build outputs, publishing artifacts,
or restart the user's running daemon. Test fixtures may simulate the upstream
contract but must never be reachable as production fallback adapters.

## Verification and remaining model limitations

- Execution: 71 tests across 9 suites; CLI source routes and required chat
  transport: 76 tests across 5 suites. Final route/browser runtime rerun: 54 tests
  across 2 suites, including the additional project-alias regression.
- Private source Chromium: 36 checks across desktop/tablet/phone and both themes.
- CLI + execution source typecheck passed without shared build output.
- Seven genuine requests used the approved existing Ornith adapter on GPU 1.
  Red → blue → red freshness and speech in audio-only/combined video passed.
- **Model quality remains imperfect:** the deployed Ornith bridge missed a real
  440 Hz tone, and one combined answer contradicted its correct blue-screen
  observation. These failures were preserved; no mock answer or alternate model
  was substituted. Improving those weights is a separate model-quality repair.
- Publishing and daemon state were preserved. Configure the deployed process as
  documented in [Omni analysis](../reference/omni-analysis.md).

Receipts:
[execution](../work-orders/evidence/omni-analysis-execution-verification-20261017.json),
[browser](../work-orders/evidence/omni-analysis-browser-20261017.json),
[integration and live results](../work-orders/evidence/omni-analysis-integration-verification-20261017.json).
