1.3 KiB
1.3 KiB
1. Executor V2 Prompt
- 1.1 Update
src/main/resources/prompts/chat-executor-prompt.mdso the final contract usesanswer_version="executor_evidence_v2". - 1.2 Remove
diagnosis_summaryanduser_facing_answerfrom the required Executor output schema and validation rules. - 1.3 Keep claims, hypotheses, recommended actions, missing information, and evidence-binding rules.
- 1.4 Keep Planner and tool-use behavior unchanged.
2. Runtime Rendering Safety
- 2.1 Update
ChatServicePASS handling so V2 structured output is rendered into readable Chinese instead of raw JSON. - 2.2 Preserve V1
user_facing_answerextraction for compatibility. - 2.3 Ensure fallback behavior does not expose raw Executor JSON when structured rendering fails.
3. Parser Compatibility
- 3.1 Keep
VerifierInputHookparse-only behavior compatible with V2 output. - 3.2 Add or update tests proving V2 output without
user_facing_answerparses intoexecutor_structured_output.
4. Tests And Verification
- 4.1 Add or update ChatService tests for PASS with
executor_evidence_v2. - 4.2 Add or update tests proving final user answer does not contain raw JSON contract text.
- 4.3 Run targeted tests for ChatService and VerifierInputHook.
- 4.4 Validate this OpenSpec change.