Harden evidence trace semantics

This commit is contained in:
aruo
2026-07-04 22:36:30 +08:00
parent 246c99b954
commit dc6cd32a67
24 changed files with 1096 additions and 141 deletions
@@ -190,3 +190,17 @@ Verifier facts SHALL be linkable to the evidence summaries used during verificat
- **WHEN** the ChatService persists `verifier_evaluation`
- **THEN** it SHALL include `traceability_version`
- **AND** it SHALL include the `tool_trace_summary` snapshot used by the Verifier
### Requirement: Verifier inputs SHALL tolerate hardened no-evidence semantics
The verifier integration SHALL continue to work when evidence summaries distinguish failed calls, no-hit calls, and deduped retrievals more explicitly.
#### Scenario: Failed evidence remains a verifier-visible gap
- **WHEN** an evidence-bearing tool invocation fails
- **THEN** the verifier-facing trace summary SHALL preserve that failure as a gap
- **AND** the verifier flow SHALL continue without crashing
#### Scenario: Deduped retrievals do not count as fresh support
- **WHEN** the verifier-facing trace summary contains deduped `lookup_knowledge` entries
- **THEN** those entries SHALL be treated as no-new-evidence
- **AND** they SHALL NOT be interpreted as fresh direct support for the answer