Merged
Conversation
GPT-5 is a reasoning model that does not support temperature, top_p, presence_penalty, or frequency_penalty parameters. Remove these and use max_completion_tokens instead of max_tokens.
GPT-5 is a reasoning model that requires temperature=1 (explicit to override langchain default of 0.7) and higher max_completion_tokens (4096) to accommodate reasoning overhead. Also filter empty content chunks during streaming to prevent client-side errors. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Read AZURE_OPENAI_DEPLOYMENT_NAME from env instead of hardcoding the model name in config.py - Remove unused GAR_IMAGE/GAR_MEMORY from .env.example - Add missing env vars: embedding model, FB_CLIENT_EMAIL, Slack, and processor service URL Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
temperature=1.0(overrides langchain default of 0.7 which GPT-5 rejects),max_completion_tokens=4096(up from 512, needed for reasoning overhead)AZURE_OPENAI_DEPLOYMENT_NAMEenv var instead of hardcoding.env.example: remove unused vars (GAR_IMAGE,GAR_MEMORY), add missing vars (embedding model,FB_CLIENT_EMAIL, Slack, processor URL)Known issues
Chat UI does not render markdown formatting — response text appears as a wall of text with no newlines, bullet points, or headings. This makes responses hard to read, especially for longer answers. See #278.
Test plan
finish_reason: stop)BadRequestErrorfor unsupported temperature values🤖 Generated with Claude Code