Honor final output contracts on terminal stop responses#271
Merged
Conversation
OpenAI Responses can surface native terminal states such as "completed" even when spoon-core has already normalized finish_reason to "stop". Depending on the native field kept final answers inside the tool loop, and the tool-budget fallback prompt still nudged the model toward summaries instead of the user's requested format. Constraint: Keep provider-specific termination handling inside spoon-core. Rejected: Fixing only spoon-bot prompts while leaving core to keep looping on normalized stop responses. Confidence: high Scope-risk: low Reversibility: high Directive: Trust normalized stop termination and preserve strict final-output contracts in the terminal tool-budget prompt. Tested: python -m pytest tests/test_agent_llm_integration.py::TestAgentLLMIntegration::test_toolcall_agent_terminates_on_stop_even_when_native_reason_is_completed tests/test_agent_llm_integration.py::TestAgentLLMIntegration::test_toolcall_agent_uses_final_tool_free_summary_after_budget_exhaustion -q Not-tested: Full core integration suite Related: PR 270 follow-up
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
finish_reason="stop"even when the provider-native terminal status iscompletedTesting
python -m pytest tests/test_agent_llm_integration.py::TestAgentLLMIntegration::test_toolcall_agent_terminates_on_stop_even_when_native_reason_is_completed tests/test_agent_llm_integration.py::TestAgentLLMIntegration::test_toolcall_agent_uses_final_tool_free_summary_after_budget_exhaustion -q