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
This commit is contained in:
Jobdori
2026-04-03 22:41:42 +09:00
parent 6325add99e
commit a2351fe867
4 changed files with 286 additions and 18 deletions

View File

@@ -46,7 +46,7 @@ use runtime::{
ConversationRuntime, MessageRole, OAuthAuthorizationRequest, OAuthConfig,
OAuthTokenExchangeRequest, PermissionMode, PermissionPolicy, ProjectContext, PromptCacheEvent,
ResolvedPermissionMode, RuntimeError, Session, TokenUsage, ToolError, ToolExecutor,
UsageTracker,
UsageTracker, ModelPricing, format_usd, pricing_for_model,
};
use serde_json::json;
use tools::GlobalToolRegistry;
@@ -1899,7 +1899,13 @@ impl LiveCli {
"output_tokens": summary.usage.output_tokens,
"cache_creation_input_tokens": summary.usage.cache_creation_input_tokens,
"cache_read_input_tokens": summary.usage.cache_read_input_tokens,
}
},
"estimated_cost": format_usd(
summary.usage.estimate_cost_usd_with_pricing(
pricing_for_model(&self.model)
.unwrap_or_else(runtime::ModelPricing::default_sonnet_tier)
).total_cost_usd()
)
})
);
Ok(())