docs: update Codex model references and add auth setup#8
Merged
Conversation
- Model resolution chain: --model flag > variant.toml model > nasde.toml [defaults] model. Error if no model found at any level. - Remove hardcoded "claude-sonnet-4-6" default that silently broke Codex variants (Codex accepts invalid model names but produces garbage results). - Add load_variant_config() to read full variant.toml including model field. - Add model = "gpt-5.3-codex" to all Codex variant.toml files in examples. - Replace outdated model names (o3, o4-mini, codex-mini-latest) with current OpenAI Codex models (gpt-5.4, gpt-5.3-codex, gpt-5.3-codex-spark). - Add authentication setup section to benchmark-runner skill (OAuth token script + CODEX_API_KEY from .env). - Add warnings about Docker OOM with parallel Claude runs. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
szjanikowski
force-pushed
the
docs/update-codex-models-and-auth
branch
from
0395289 to
39f9a66
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
o3,o4-mini,codex-mini-latest) with current Codex models (gpt-5.4,gpt-5.3-codex,gpt-5.3-codex-spark, etc.) across CLAUDE.md and skillsclaude-sonnet-4-6) producing garbage results (0% pass rate)Test plan
codex-vanillawith--model gpt-5.3-codexscored 87/100 (vs 0-45 with wrong model)o3,o4-mini,gpt-4o,gpt-4.1, orcodex-mini-latest🤖 Generated with Claude Code