Repository navigation
fix(python): preserve explicit LLMClient callbacks - #268
Open
Chen Yufeiyang (feiiiiii5) wants to merge 1 commit into
Open
Chen Yufeiyang (feiiiiii5) wants to merge 1 commit into
Chen Yufeiyang (feiiiiii5) wants to merge 1 commit into
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
This branch has not been 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
LLMClientaccepts explicit completion, embedding and moderation callbacks, but__post_init__overwrites them with SDK defaults after detecting customization. Requests therefore reach the SDK instead of the supplied callbacks; an explicitly supplied rate-limit exception class is also discarded.Configure each field only when it is
None, in both supported SDK configuration branches. Partial customization continues to configure the other methods automatically. This follows the explicit-method contract documented in the class and introduced by #121.Validation with the frozen lockfile, Python 3.12.8, OpenAI 2.41.0 and the dev/scipy/LiteLLM extras:
a5dd171; the fixedtest_oai.pypasses 35 tests.git diff --checkpasses; the lockfile is unchanged.The v1-interface tests use the real OpenAI SDK with
httpx.MockTransport; v0 uses the repository's existing compatibility fixture. Sync/async and full/partial customization exercise actual callback results, custom rate-limit retries and default-method requests. No live model calls were made.Offline test scope
The 16 omitted cases are the two live embedding tests, four live LLM tests, the moderation and partial live tests, and eight
test_ragas_retrievalparameter instances. A collection hook matches exact file/function names; mocked tests, including all nine LiteLLM cases, remain selected.Formatting command:
pre-commit run --files py/autoevals/oai.py py/autoevals/test_oai.py.