Recover truncated tool calls, and never pass a leaked one off as an answer#3
Merged
Conversation
…nswer Small local models drift off the tool-call format, especially with a large tool schema in play. Two failures followed from that, both of which ended the turn looking like the model had simply stopped mid-sentence. Salvage handled well-formed Qwen/Hermes XML but gave up entirely on a call cut off partway through. It now takes the function name plus every parameter that actually closed. A trailing unterminated `<parameter=…>` is dropped rather than guessed, so a half-written path or file body can never reach a tool; if that leaves a required argument missing, the call fails validation and the model gets a corrective tool error, which is the agent loop working. Worse, a call that never parsed at all was reported as `status: completed` — indistinguishable from the model deciding it was done, leaving the user with narration trailing off into stray closing tags. It now ends on the error path, so the GUI offers Retry. That is the right affordance here: the drift is probabilistic, not deterministic, so the same model usually succeeds on a second attempt. Detection ignores fenced and inline code, so a model *explaining* tool-call syntax is still a real answer, and requires that tools were offered at all. Reported against qwen3.5-9b on LM Studio, 2026-07-26. Co-Authored-By: Claude <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Same change as upstream andrewyng/openworker#219, on top of this fork's
main(which already has the Developer persona and the LM Studio provider).Fixes two failures that both end a turn looking like the model simply stopped mid-sentence — the symptom seen with
qwen3.5-9bon LM Studio, though the cause is model-agnostic.Truncated calls are recovered. Salvage takes the function name plus every parameter that actually closed; a trailing unterminated
<parameter=…>is dropped rather than guessed, so a half-written path or file body can never reach a tool.A leaked call is no longer a "completed" answer. It ends on the error path so the GUI offers Retry — the right affordance, since this drift is probabilistic and retrying usually works. Detection strips fenced and inline code, so a model explaining tool-call syntax still counts as a real answer.
939 passedon this branch (+5).🤖 Generated with Claude Code