fix(llm_client): remove response_format json_object for local LLM compatibility#122
Open
ImL1s wants to merge 1 commit into666ghj:mainfrom
Open
fix(llm_client): remove response_format json_object for local LLM compatibility#122ImL1s wants to merge 1 commit into666ghj:mainfrom
ImL1s wants to merge 1 commit into666ghj:mainfrom
Conversation
…patibility LM Studio and Ollama do not support response_format: json_object, only json_schema or text. This causes errors when using local LLMs. The existing markdown fence cleanup logic in chat_json() already handles parsing JSON from raw LLM output, making response_format unnecessary. This change follows the same pattern as commit 985f89f which improved compatibility with diverse model outputs. Tested with: LM Studio + qwen3.5-9b (full predict pipeline passes)
dosubot
bot
added
size:XS
ImL1s
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
chat_json()usesresponse_format={"type": "json_object"}, but LM Studio and Ollama do not support this parameter (onlyjson_schemaortext), causing API calls to fail when using local LLMs.Related references:
Solution
Remove
response_formatfromchat_json(). The method already has robust markdown code fence cleanup logic (L93-97) that correctly parses JSON from raw LLM output, makingresponse_formatunnecessary.This follows the same approach as commit 985f89f (handling
<think>tags from reasoning models) — improving compatibility with diverse model outputs.Changed Files
backend/app/utils/llm_client.py: Removeresponse_formatinchat_json(), rely on prompt instructions + markdown cleanupTesting