Add GPT-5.6 Sol support - #36
Open
BenKBreen wants to merge 2 commits into
Open
Conversation
- Add gpt_5_6_sol LLM config (openai:gpt-5.6-sol, effort=high) with an explicit request timeout and bounded retries so a stalled request fails fast instead of hanging. - Strip client-only parsed_arguments from replayed function_call blocks in agentic_loop; the OpenAI Responses API rejects it when tools are combined with structured output, breaking the proposer loop. Co-authored-by: Cursor <cursoragent@cursor.com>
gpt-5.6-sol (and other models newer than langchain-openai's profile registry) have no max_input_tokens in their profile, returning None and crashing the < 1000 startup check. Default to 200000 when unknown. Co-authored-by: Cursor <cursoragent@cursor.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adding functionality for GPT-5.6 Sol
Note
Medium Risk
Changes the shared LLM agentic loop and prover token limits used on every proposal; fixes are targeted but affect all OpenAI tool+schema flows.
Overview
Adds a reusable
gpt_5_6_solentry inllms.yamlforopenai:gpt-5.6-solwith high reasoning effort, a 600s request timeout, and a 6-attempt exponential-jitter retry policy suited to long reasoning runs.ProverAgent now defaults
max_input_tokensto 200,000 when the LangChain model profile omits it (e.g. newer models), so context truncation logic still behaves safely.The agentic tool loop strips
parsed_argumentsfrom OpenAIfunction_callcontent blocks before messages are replayed, fixing Responses API rejections when combining structured output with tool calling.Reviewed by Cursor Bugbot for commit 5f67604. Bugbot is set up for automated code reviews on this repo. Configure here.