fix: preserve latest session tool outputs and keep orphan calls in non-resume input prep #2411
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Outdated suggestions cannot be applied.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.
This pull request fixes duplicate tool-output handling (caused by #2230) so the latest item wins consistently when entries share the same stable identifier (for example call_id). It addresses a regression where older session/history outputs could silently override newer outputs, causing model input and persisted session state to diverge from the latest tool result.
This pull request updates deduplication behavior in runtime paths that prepare model input (call_model_input_filter for both non-streamed and streamed runs) and in session persistence (save_result_to_session), and adds a shared latest-wins helper for internal item deduplication. It also keeps resume and non-resume behavior aligned for orphan tool-call normalization to avoid interruption-dependent context drift.