Unverified50% confidenceFactExact time
OpenAI's Codex Prompting Guide recommends the apply_patch format for single-file edits and states that the model has been trained on this diff format, strongly recommending the use of OpenAI's official implementation.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedOpenAI has publicly discussed that their model was specifically trained to efficiently use the apply_patch tool.79% similarUnverifiedOpenAI 的 Codex 采用 apply_patch 机制，通过应用补丁的方式修改代码76% similarVerifiedDifferent models use different function-calling formats: OpenAI uses the tools parameter, Anthropic uses tool_use blocks, and open-source models each have their own template formats.75% similarUnverifiedDifferent frameworks define tool-calling formats differently (OpenAI format, Anthropic format, Ollama's own format), and models not trained for a specific format will produce malformed calls.72% similarUnverifiedThe OpenAI Batch API is a reasonable default when applications are built around OpenAI request shapes and structured output tooling, but applications are responsible for mapping output records back to the frozen list.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063853API
curl https://kongchang.com/api/v1/knowledge/claims/1063853MCP
get_claim(id=1063853)