fix(streaming): don't throw after content delivered when [DONE] missing (Muse Spark) - #187
Merged
Merged
Conversation
This was referenced Aug 23, 2026
Fahad090NP
added a commit
to Fahad090NP/opencode-copilot-chat
that referenced
this pull request
Aug 24, 2026
…arguments (ltmoerdani#184) ltmoerdani#187 made content-delivered streams without [DONE]/finish_reason return successfully (Muse Spark). But for tool-calling streams that means a stream cut mid-arguments flushes a tool call whose truncated JSON silently becomes {} input via parseToolInput — the tool executes with corrupted input. - ToolCallAccumulator.hasCompletePendingCalls(): every named pending call must carry non-empty, parseable JSON-object arguments - OpenAiResponseExtractor.hasCompletePendingToolCalls() exposes it - engine: hasCompletePendingWork option — when it returns false on an unterminated stream, throw the truncation error instead of returning success (responses adapter wired; other transports unaffected) - 5 new unit tests
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
📝 What does this change?
Muse Spark on the Responses API delivers content successfully but closes the connection without sending
data: [DONE]orfinish_reason. The truncated-stream detector from #178 was throwing an error after content was already delivered to VS Code, creating a confusing error popup on an otherwise complete response.When the engine detects a stream without
[DONE]/finish_reasonbutextractedPartCount > 0, it now logs a[warn]line and returns successfully instead of throwing. The user received their content — the missing termination signals are a gateway quirk, not a failure.Files changed
src/transports/engine.tsextractedPartCount > 0branch in truncation check: log warning + emit summary + return (instead of throwing)docs/issues/79-20260822-issue-muse-spark-stream-completion.mdCHANGELOG.md[Unreleased]🧪 How did you test it?
Tested with
muse-spark-1.2-contributor-free, now works as intended.✅ Checklist
npm run compilepassesnpm run lintpassesnpm testpassesnpm run packageproduces a VSIX