feat(agents): upgrade oracle model from GPT-5.1 to GPT-5.2 #19
Conversation
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
OpenAI released GPT-5.2 today with significant improvements: - 38% fewer errors in thinking responses - Better at coding, planning, and multi-step tasks - Improved performance on SWE-Bench Pro and GPQA Diamond
Owner
Author
|
Kinda funny that i use cc here but like i made this PR on my iphone with just one prompt |
Instead of hardcoding specific GPT versions (5.1, 5.2, etc.), use regex pattern to support all GPT 5+ models: - gpt-5, gpt-5.1, gpt-5.2, gpt-6, gpt-10, etc. - Variants like gpt-5.2-codex -> gpt-5.2-codex-high - Effort levels like gpt-5.2-medium -> gpt-5.2-high
Add explicit high variant mappings for: - GPT-5: base, codex, low/medium effort levels - GPT-5.1: base, codex, codex-max, low/medium effort levels - GPT-5.2: base, instant, thinking, pro, codex, low/medium effort levels Also include xhigh variants in ALREADY_HIGH set (new in GPT-5.2 API).
- gpt-5.2 = Thinking (default) - gpt-5.2-chat-latest = Instant - gpt-5.2-pro = Pro (supports medium/high/xhigh) - Added gpt-5-mini - Removed non-existent instant/thinking/codex variants
Removed fake model IDs with reasoning effort suffixes (-low/-medium/-high/-xhigh). These are NOT valid model IDs - reasoning effort is passed as a separate parameter. Valid GPT models: - GPT-5: gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-pro, gpt-5-chat-latest - GPT-5.1: gpt-5.1, gpt-5.1-chat-latest, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-codex-max - GPT-5.2: gpt-5.2, gpt-5.2-chat-latest, gpt-5.2-pro The "-high" suffix in HIGH_VARIANT_MAP output is an internal convention to signal that reasoning_effort should be set to "high" for these models.
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.
OpenAI released GPT-5.2 today with significant improvements:
Haha now we got the most brilliant oracle here