Direct answer
Preserve source references, artifact identity, result state, edits, and user approval as visible elements of the export. Do not infer anything beyond what these items themselves show, and ensure each one remains explicitly labeled and traceable in the produced file. Their presence must be unmistakable rather than implied.
Evidence to collect
The claim becomes reviewable only when the following evidence is attached to the same artifact and test run:
- Session export schema
- Redaction and preview test
- Round-trip verification
A privacy claim needs a data inventory and traffic evidence. A local-model label by itself is not proof.
Implementation workflow
Record the session export schema, the redaction and preview test, and the round-trip verification together so they can be reviewed side by side. Treating these items as connected evidence allows reviewers to confirm that the schema matches what was tested and that the round-trip confirmation reflects the same exported structure.
- Inventory every content and metadata type.
- Enumerate every destination and trigger.
- Map user action to code path and request fields.
- Verify the core task in airplane mode.
- Capture traffic for setup, inference, diagnostics, and export.
- Update public disclosure in the same release as behavior.
Failure patterns to prevent
- Exporting hidden diagnostics
- Losing partial or edited state
Avoid exporting hidden diagnostics and avoid losing partial or edited state, as both undermine confidence in the record. Limit any wording about release to what the recorded evidence itself establishes, and keep the scope of concerns aligned with the documented items.
Minimum reproducibility record
| Layer | Record |
|---|---|
| Device | Manufacturer, model, chipset, RAM class, operating-system build |
| Software | Application version and git commit |
| Model | Family, variant, revision, format, file length, hash, quantization |
| Runtime | Name, revision, requested backend, observed backend evidence |
| Workload | Fixture revision, input hash, prompt hash, output policy |
| Outcome | Completed, failed, cancelled, fallback, and privacy-safe diagnostics |
Release checklist
- ☐ The primary query is answered without an unsupported number.
- ☐ Every artifact and runtime is pinned.
- ☐ The representative task and failure policy are explicit.
- ☐ Lifecycle, cancellation, cleanup, and fallback are tested.
- ☐ User-content and network boundaries are documented.
- ☐ Result wording applies only to the recorded configuration.
- ☐ The page links to raw method or evidence when results are added.
Sources and related evidence
This page relies on the Cove fact ledger and benchmark policy. Results remain blocked until raw records exist.
Chinese deployment and troubleshooting content is organized in the .奇连 AI 端侧专题.