* Add actual LLM token usage fields to RetainResult RetainResult now carries llm_input_tokens, llm_output_tokens, and llm_total_tokens populated from the engine's TokenUsage, so downstream operation validator extensions can access actual LLM token counts. * Test that RetainResult includes actual LLM token usage |
||
|---|---|---|
| .. | ||
| builtin | ||
| __init__.py | ||
| base.py | ||
| context.py | ||
| http.py | ||
| loader.py | ||
| mcp.py | ||
| operation_validator.py | ||
| tenant.py | ||