Repository navigation
Expect Codex's plain-text form of a text-only tool result in the native function stream test - #147
Merged
Merged
Conversation
…per test Pinned Codex 0.153.4 sends a function result made of exactly one input_text item as a plain string output (function_tool_response in codex-rs/core/src/tools/context.rs, covered by its own tests). The daemon forwards the submitted content items unchanged and public history keeps the array, so only the synthetic model expectation changes.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This is a test-only fix.
TestNativePublicFunctionStreamHelperexpected the model to receive the text-only setup tool result as a one-item array. Pinned Codex 0.153.4 deliberately turns a result made of exactly oneinput_textitem into plain text (function_tool_responseincodex-rs/core/src/tools/context.rs, asserted by Codex's ownfunction_payloads_remain_function_outputs). Both forms are valid Responses input: the pinned SDK typesfunction_call_output.outputas a string or a list. Public history still keeps the array, and the test's SDK script checks that. The fake model server now expects the string, with a one-line comment explaining why.Verification
dc7f5663: passed. The Playwright browser cases were skipped on the server (Chrome unavailable; approved skip). Main has since moved only by Show the command that connects a self-hosted executor host #143, a Web-only change that doesn't touch this file.Need help on this PR? Tag
@codesmithwith what you need. Autofix is disabled.