Repository navigation
chore(evals): Switch Sonnet defaults to GPT 6 Luna - #569
Closed
sentry-junior[bot] wants to merge 1 commit into
Closed
sentry-junior[bot] wants to merge 1 commit into
sentry-junior[bot] wants to merge 1 commit into
Conversation
Move every eval suite, scenario YAML, judge, and verification default from Claude Sonnet 4.6 to openai/gpt-6-luna, and point the CI eval default at openrouter/openai/gpt-6-luna. Bump Pi to 0.87.1, the first release whose model catalog includes GPT 6 Luna. Co-Authored-By: David Cramer <23610+dcramer@users.noreply.github.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Moves every place the evals actually ran on Claude Sonnet 4.6 over to GPT 6 Luna:
code-review,security-review,integrity-review,verify, and the scenario YAMLs now useopenai/gpt-6-luna.DEFAULT_EVAL_MODEL,DEFAULT_VERIFICATION_MODEL, andDEFAULT_JUDGE_MODEL.WARDEN_EVAL_MODELis nowopenrouter/openai/gpt-6-luna, which still uses the existingWARDEN_OPENROUTER_API_KEY.openai/gpt-6-lunaas the example.This also bumps Pi (
pi-aiandpi-coding-agent) from^0.86.1to^0.87.1. 0.86.1's catalog doesn't includegpt-6-luna; 0.87.1 is the first release that does, under bothopenaiandopenrouter.Two behavior changes come with this:
DEFAULT_EVAL_RUNTIMEis nowpiinstead ofclaude, because the default model is no longer an Anthropic model. Every checked-in YAML already setsruntime: pi.WARDEN_EVAL_MODELset, local evals now turn on when an OpenAI key (WARDEN_OPENAI_API_KEY/OPENAI_API_KEY) is present, not an Anthropic key.Not changed: the docs pages, the benchmark data, the
BASELINE.mdfiles (they record the model each baseline was measured with), and the test fixtures inpackages/warden. Roach has no recordings for the new model yet, so the first CI eval run will record them.via @dcramer.
--
View Session [Sentry]