fix: parse complete cloud chat SSE frames - #544
Open
rudycelekli wants to merge 1 commit into
Open
rudycelekli wants to merge 1 commit into
rudycelekli wants to merge 1 commit into
Conversation
Signed-off-by: Rudy Celekli <47457359+rudycelekli@users.noreply.github.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cloud chat currently parses individual lines only when they start with
data:, so valid compact or multiline SSE frames lose answer text and can hide a midstream error after a partial answer.Assemble data fields at blank event boundaries for both streaming views, following SSE's optional single space, newline joining, UTF-8/BOM and incomplete-EOF rules. Preserve citation metadata,
[DONE], error propagation and response cleanup. Existing mocked SSE fixtures now include their event separators.Validation: native localhost HTTP regressions failed before the fix (27 cases). The focused stream suite passes 29 tests; removing the text parser's error check makes both corresponding error regressions fail. The complete local
python -m pytest -qpasses 612 tests, 218 skipped on macOS/Python 3.12/PDFium 5 without optional agent frameworks. The repository's hosted Python 3.10/3.13/framework/PDFium matrix remains required. No live provider calls were used.