Repository navigation
fix(agent): normalize null thinking text before Anthropic replay - #126
Open
rudycelekli wants to merge 1 commit into
Open
rudycelekli wants to merge 1 commit into
rudycelekli wants to merge 1 commit into
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The compatibility middleware repairs a missing thinking field but forwards an explicit null unchanged. The locked LangChain formatter preserves that null and the locked Anthropic ThinkingBlock schema rejects it as a nonstring.
Repair null thinking text with the same empty string used for absent text. Preserve signatures, cache metadata, message IDs and original graph history in sync and async calls.
Validation: native regression tests failed on the pinned base (2 failures), then the complete agent suite passed (113 tests) after the fix. Command:
python -m pytest -q -p no:cacheprovider, using the locked Python dependencies. Provider traffic is mocked; no live model or Wikimedia calls are part of these tests.AI-assisted implementation and test review. This work has not been human-reviewed or published by this lane.
Combined integration checks pass: 249 Node tests, 157 Python tests, TypeScript, frontend lint (0 errors, 2 warnings), and the production workspace build. These combined results belong to the private integration branch; each PR also has its own focused regression and relevant suite results above. Live provider behavior is untested.
Independent AI review passed on this exact head. Nine isolated production-browser checks passed for the combined chat shell/key dialog and QR request flow; no page errors. No live provider calls were made.