2 Commits

Author	SHA1	Message	Date
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
Yeachan-Heo	85c5b0e01d	Expand parity harness coverage before behavioral drift lands ... The landed mock Anthropic harness now covers multi-tool turns, bash flows, permission prompt approve/deny paths, and an external plugin tool path. A machine-readable scenario manifest plus a diff/checklist runner keep the new scenarios tied back to PARITY.md so future additions stay honest. Constraint: Must build on the deterministic mock service and clean-environment CLI harness Rejected: Add an MCP tool scenario now | current MCP tool surface is still stubbed, so plugin coverage is the real executable path Confidence: high Scope-risk: moderate Reversibility: clean Directive: Keep rust/mock_parity_scenarios.json, mock_parity_harness.rs, and PARITY.md refs in lockstep Tested: cargo fmt --all Tested: cargo clippy --workspace --all-targets -- -D warnings Tested: cargo test --workspace Tested: python3 rust/scripts/run_mock_parity_diff.py Not-tested: Real MCP lifecycle handshakes; remote plugin marketplace install flows	2026-04-03 04:00:33 +00:00