From ce550a127b7dc972651bd15b9f09979a2c38688f Mon Sep 17 00:00:00 2001 From: tanaka takashi Date: Wed, 12 Aug 2026 00:02:23 +0900 Subject: feat: harden Python workflow and structured planning Replace the uv-specific skill with a portable Python skill and rewrite the default user system prompt as a concise, structured Markdown execution policy. Normalize a single fenced structured-JSON response, retry invalid skill selection with think disabled, validate selected skill output, and make coding plans keep editing and verification in one task. Document the file_edit patch payload, expose that contract in the tool catalog, and convert malformed patch input into a retryable tool failure instead of terminating the agent task. Update configuration and runtime tests for the Python skill, exact tool catalog, structured-output retry, and implementation-and-verification planning guidance. Verified with 82 Agent.Core tests and an agent-mcp Python scheduling scenario with 49 passing unittest cases. --- skills/python/agents/openai.yaml | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 skills/python/agents/openai.yaml (limited to 'skills/python/agents') diff --git a/skills/python/agents/openai.yaml b/skills/python/agents/openai.yaml new file mode 100644 index 0000000..dff8b03 --- /dev/null +++ b/skills/python/agents/openai.yaml @@ -0,0 +1,4 @@ +interface: + display_name: "Python" + short_description: "Create, run, and verify Python programs safely" + default_prompt: "Use $python to create and run Python code, then verify the result." -- cgit v1.2.3