feat: impl Responses API in oai-adapters#8417
Conversation
- Add GPT-5 Codex to llm-info package with 500k context and 150k max tokens - Add model definition to models.ts for UI configuration - Include GPT-5 Codex in OpenAI provider packages list - Model supports chat and edit roles with tool_use capability
Patrick-Erichsen
requested review from
RomneyDa
and removed request for
a team
dosubot
bot
added
the
size:XXL
|
✅ Review Complete Code Review Summary |
RomneyDa
left a comment
RomneyDa
left a comment
There was a problem hiding this comment.
Looks good, had several nitpicks but none are blocking. It would be nice to eliminate the >20 as any type casts
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
Reviewed changes from recent commits (found 1 issue).
1 issue found across 3 files
Prompt for AI agents (all 1 issues)
Understand the root cause of the following 1 issues and fix them.
<file name="packages/openai-adapters/src/apis/openaiResponses.ts">
<violation number="1" location="packages/openai-adapters/src/apis/openaiResponses.ts:191">
Please pass the original ResponseOutputText part into createOutputTextPart so that annotations/logprobs survive the round-trip back into Responses payloads.</violation>
</file>
React with 👍 or 👎 to teach cubic. Mention @cubic-dev-ai to give feedback, ask questions, or re-run the review.
github-actions
bot
added
the
tier 1
|
🎉 This PR is included in version 1.31.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
|
🎉 This PR is included in version 1.4.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
|
🎉 This PR is included in version 1.28.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
|
🎉 This PR is included in version 1.6.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
3 participants
Overview
This PR patches over the logic from #7891 into openai-adapters. It converts Responses objects back into chat completion objects for streaming, implements ternary logic for streaming vs non-streaming defined in
packages/openai-adapters/src/apis/base.ts, is non-stateful, and generally tries to adhere to the logic from #7891Testing
Create a
gpt5-codex-openai.yamlsomewhere, e.g.continue/rootthen run
npm run start -- --config /path/to/continue//gpt5-codex-openai.yamland perform general smoke testing.