Repository navigation
Co-point gpt-medium/gpt-large at gpt-5.3-codex until a Responses API path exists - #655
Merged
Merged
Conversation
…ol loop)
The 2026-08-08 full-suite run showed openai/gpt-5.6-sol rejecting
function tools on chat completions ("use /v1/responses or set
reasoning_effort to 'none'"), failing both aliases at iteration 1.
Per the alias rules — capability at agentic coding is the admission
test and every alias must resolve to a runnable model — the OpenAI
ladder compresses fully onto the Codex line until a Responses API
path exists (tracked in issue 653).
Co-Authored-By: Claude Fable 5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up from the 2026-08-08 full-test-suite run.
openai/gpt-5.6-solcannot run rdb's agent loop: OpenAI rejects function tools with reasoning on chat completions for the 5.6 frontier family ("use /v1/responses or set reasoning_effort to 'none'"), so bothgpt-mediumandgpt-largefailed at iteration 1, twice, deterministically.Applying the alias rules as written: capability at agentic coding is the admission test, and every alias must resolve to a runnable model — so the OpenAI ladder compresses fully onto the Codex line (
gpt-5.3-codex, which passed its e2e run) until there's a Responses-API path. That makes OpenAI a one-model ladder for now, which is an honest statement about their current lineup as seen through litellm's chat-completions route: exactly one model class both codes well and speaks rdb's tool protocol. Restoring a distinct flagship tier is #653.Test plan
e2e.ymlwithtest=gpt-medium(andtest=gpt-large) — cheap single-test runs rather than a full suite🤖 Generated with Claude Code