Jobdori a2351fe867 feat(harness+usage): add auto_compact and token_cost parity scenarios ...

Two new mock parity harness scenarios:

1. auto_compact_triggered (session-compaction category)
   - Mock returns 50k input tokens, validates auto_compaction key
     is present in JSON output
   - Validates format parity; trigger behavior covered by
     conversation::tests::auto_compacts_when_cumulative_input_threshold_is_crossed

2. token_cost_reporting (token-usage category)
   - Mock returns known token counts (1k input, 500 output)
   - Validates input/output token fields present in JSON output

Additional changes:
- Add estimated_cost to JSON prompt output (format_usd + pricing_for_model)
- Add final_text_sse_with_usage and text_message_response_with_usage helpers
  to mock-anthropic-service for parameterized token counts
- Add ScenarioCase.extra_env and ScenarioCase.resume_session fields
- Update mock_parity_scenarios.json: 10 -> 12 scenarios
- Update harness request count assertion: 19 -> 21

cargo test --workspace: 558 passed, 0 failed

2026-04-03 22:41:42 +09:00

..

src

feat(harness+usage): add auto_compact and token_cost parity scenarios

2026-04-03 22:41:42 +09:00

Cargo.toml

Lock down CLI-to-mock behavioral parity for Anthropic flows

2026-04-03 01:15:52 +00:00