docs(api): OpenAI server supports tool-calling#620
Open
jeswr wants to merge 1 commit into
Open
Conversation
The OpenAI coli serve section said tools 'return an explicit error'; the server ships full tool-calling (parse_tool_calls / render_chat tool_choice, test_openai_tools_e2e.py, JustVugg#401/JustVugg#408). Correct the stale sentence; leave the image/audio/stop/logprob/penalty items unchanged.
Owner
|
Thanks — and this docs fix is correct: tool-calling is supported on the OpenAI |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
docs/api.md(the OpenAIcoli servesection) currently says Tools "return an explicit error rather than being silently ignored." That's stale for Tools:c/openai_server.pyat HEAD ships full tool-calling —parse_tool_calls()(renders GLM tool markers back into OpenAItool_calls),render_chat(..., tools, tool_choice)(injects the<tools>XML and honourstool_choiceincludingnone/required/forced-function), plus a dedicatedtest_openai_tools_e2e.py. Tool schemas only 400 when malformed (landed via #401/#408). The Anthropic section of the same doc already documents full tools support, so the OpenAI paragraph contradicted both the code and its sibling section.This corrects only the Tools sentence; the image/audio input, custom stop sequences, log-probabilities, and token-penalty items are left unchanged.
Prepared for review — happy to adjust wording. (Heads-up: there may be a delay before I can respond to review comments.)