Repository navigation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes the schema being applied only to the first request in a chain that uses tools. After a tool runs, the follow-up prompt is rebuilt without
schema, so the final answer is no longer constrained and that response is logged without aschema_id.ChainResponse,AsyncChainResponseand the resumed-chain path rebuild the prompt for the tool-result turn but only carriedsystem,system_fragmentsandoptions. They now carryschematoo.Test:
pytest tests/test_tools.py::test_chain_carries_schema_through_tool_rounds tests/test_tools.py::test_async_chain_carries_schema_through_tool_rounds tests/test_pause_resume.py::test_resumed_chain_keeps_the_schemafails onaebaca2withassert [schema, None] == [schema, schema]and passes on this branch. Also ranpytest tests/test_tools.py tests/test_pause_resume.py(74 passed), plusblack --checkandruff checkon the touched files.Details
- `llm/models.py:2911` (`_resume_prompt`), `:2998` (sync chain loop) and `:3142` (async chain loop) rebuild the prompt and now pass `prompt.schema`. - `llm/default_plugins/openai_models.py` builds `response_format` / `text.format` from `prompt.schema`, so this applies to every provider that relies on the prompt. - No live API call was made; the tests use the mock model and assert the schema each round receives.