OpenAI Responses: enable GPT-5 Pro + fixes - #720
Open
mikez93 wants to merge 2 commits into
Open
Conversation
- Include gpt-5-pro in FEATURE_SUPPORT gates (web_search, image_gen, functions, reasoning, reasoning_summary, verbosity) - Normalize model IDs by stripping any function/module prefixes before sending to OpenAI - Drop unsupported sampling params for GPT-5 family (temperature, top_p) with warnings - Log full 4xx response bodies for streaming and non-streaming requests to aid debugging
Author
|
Additional note from testing: deep‑research models (o3-deep-research, o4-mini-deep-research) work well with this manifold in OpenWebUI. In smoke tests they show visible thinking and behave as first‑class models. No special handling beyond enumeration was added in this PR; happy to follow up with any adjustments or validation details if maintainers prefer dedicated logic for deep‑research. |
… (2025-10-10) - GPT-5 Pro support across feature gates - Model ID normalization to strip function/module prefixes - Drop unsupported GPT-5 params (temperature, top_p) - Log full 4xx bodies (streaming and non-streaming) - Note: deep-research models verified in smoke tests
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR makes the OpenAI Responses API manifold work reliably with GPT‑5 Pro (and family) in OpenWebUI.\n\nKey changes\n- Add gpt-5-pro to FEATURE_SUPPORT gates (web_search, image_gen, functions, reasoning, reasoning_summary, verbosity) so the right capabilities surface\n- Normalize model IDs by stripping any function/module prefixes before sending to OpenAI (avoids model_not_found on e.g. openai_responses.* prefixes)\n- For GPT-5 family, drop unsupported sampling params (temperature, top_p) with warnings to prevent 4xx\n- Log full 4xx bodies from streaming and non‑streaming requests for faster diagnosis\n\nNotes\n- Tested locally via OpenWebUI custom function; with GPT‑5 Pro selected, requests now succeed and UI shows reasoning status when configured\n- If you see a 400 regarding reasoning.summary, set REASONING_SUMMARY to "detailed" (or disable) in valves\n- No secrets in code; all behavior is feature-gated by model family\n\nHappy to adjust naming or placement per maintainers’ guidance.