fix: context placeholder + interrupt reasoning_duration - #930
Merged
Conversation
…dir shared memory isolation, mark tool denials as errors
…on log for replay
… targeted tool re-indexing
…nnounced in-conversation
…rning a usage intro
…of littering the workspace root
…at/webui_refractor
…at/webui_refractor
…mpty tool-call content serializes as null/tool_use); mark interrupt filler with content_placeholder; persist reasoning_duration on mid-thinking interrupt; default project skips unused workspace/ subdir
…at/webui_refractor # Conflicts: # ms_agent/agent/llm_agent.py # tests/agent/test_partial_round.py
…gs no longer pollute model input); keep reasoning_duration when a turn is cancelled after thinking ends
Contributor
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
…at/webui_refractor # Conflicts: # ms_agent/agent/llm_agent.py
alcholiclg
changed the title
alcholiclg
changed the title
wangxingjun778
approved these changes
Aug 3, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Change Summary
_dicts_to_messages) strips the legacyLet me do a tool calling.placeholder, so existing session logs no longer replay that fake utterance into the model input._persist_partial_roundreuses_last_reasoning_durationwhen a turn is cancelled after thinking ended (during body streaming), so replay shows the real thinking time instead of 0s.reasoning_duration.tests/session/test_context_assembler.pyand two cancel-point cases intest_partial_round.py—22 passedacross the related SDK suites.Related issue number
Checklist
pre-commit installandpre-commit run --all-filesbefore git commit, and passed lint check.