fix(trajectory): detect incomplete scratchpad with ordered tag depth - #11244
Closed
wangzhe19991 wants to merge 1 commit into
Closed
fix(trajectory): detect incomplete scratchpad with ordered tag depth#11244wangzhe19991 wants to merge 1 commit into
wangzhe19991 wants to merge 1 commit into
Conversation
Made-with: Cursor
alt-glitch
added
type/bug
Collaborator
cphowiehuang
added a commit
to elmtree-askmo/hermes-agent
that referenced
this pull request
Jul 6, 2026
…orkaround (semconv says output includes reasoning; revert when fixed)
cphowiehuang
added a commit
to elmtree-askmo/hermes-agent
that referenced
this pull request
Jul 6, 2026
…int buckets); document Langfuse NousResearch#11244 status + aggregate key-name semantics
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Replace the substring-based
has_incomplete_scratchpadcheck with a left-to-right depth counter over<REASONING_SCRATCHPAD>/</REASONING_SCRATCHPAD>tokens. This prevents a later unclosed block from being misclassified as "complete" when an earlier closing tag exists elsewhere in the same string.Related: #11194 (same symptom class: false detection around incomplete scratchpads).
Changes
agent/trajectory.py: ordered open/close matching; ignore orphan closing tags when depth is zero.tests/agent/test_trajectory_scratchpad.py: regression coverage for paired blocks, a second unclosed block after a closed pair, and orphan-close + open tail cases.Test plan