fix(strix): honor GPT-5.4 tool reasoning contract - #1350
Merged
Conversation
seonghobae
enabled auto-merge (squash)
August 26, 2026 10:06
seonghobae
enabled auto-merge (squash)
August 26, 2026 12:26
Contributor
Author
|
@opencode-agent review the current exact head; this change owns the Strix reasoning-effort fallback repair. |
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This was referenced Aug 26, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Root cause
The required Strix workflow correctly exhausted NVIDIA NIM after HTTP 429/410 provider failures, then reached its direct OpenAI fallback. The pinned Strix scanner uses Chat Completions function tools, while direct OpenAI rejected
gpt-5.4when the inheritedreasoning_effort=highwas present. The fallback therefore produced no authoritative security evidence and remained fail closed.Repair
highreasoning for every existing supported model path.gpt-5.4fallback only, passreasoning_effort=none, as required by the provider's observed Chat Completions function-tool contract.Verification
STRIX_TEST_CASE_FILTER=nvidia-rate-limit-openai-direct-fallback-clears-api-base STRIX_TEST_PROCESS_TIMEOUT_SECONDS=3 STRIX_TEST_FAKE_SLEEP_SECONDS=5 bash scripts/ci/test_strix_quick_gate.shuv run --with pytest pytest -q tests/test_strix_nvidia_nim_not_found_fallback.py tests/test_strix_openai_fallback_api_base.py— 25 passedbash -n scripts/ci/strix_quick_gate.sh scripts/ci/test_strix_quick_gate.shgit diff --checkactionlint .github/workflows/strix.ymlreports only the existing SC2016 informational diagnostic at unchanged line 267.