Avoid tools for direct answer prompts

This commit is contained in:
mirivlad 2026-05-22 21:31:50 +08:00
parent 1291281d7e
commit 282085c384
2 changed files with 11 additions and 0 deletions

View File

@ -18,6 +18,10 @@ Available tools:
Args: {"task_description": "what to build or analyze", "language": "python", "context": "optional context"} Args: {"task_description": "what to build or analyze", "language": "python", "context": "optional context"}
Return actions=[] when the user can be answered directly without tools. Return actions=[] when the user can be answered directly without tools.
Return actions=[] for simple arithmetic, translation, explanation, formatting,
summarization, brainstorming, general knowledge, or any request where the
thinker can answer from the conversation alone. Do not run shell commands like
`echo`, `python`, `bc`, or calculators for simple arithmetic.
When tool_observations are already present, request only genuinely missing When tool_observations are already present, request only genuinely missing
follow-up information. Return actions=[] when the observations are sufficient follow-up information. Return actions=[] when the observations are sufficient
for the thinker to answer. for the thinker to answer.

View File

@ -14,3 +14,10 @@ def test_models_config_maps_roles_to_same_qwen_non_mtp_model():
assert roles["action"]["structured_output"] is True assert roles["action"]["structured_output"] is True
assert roles["thinker"]["max_output_tokens"] == 8192 assert roles["thinker"]["max_output_tokens"] == 8192
def test_action_prompt_forbids_tools_for_simple_arithmetic():
prompt = Path("prompts/roles/action.md").read_text()
assert "Return actions=[] for simple arithmetic" in prompt
assert "Do not run shell commands like" in prompt