orcs-oss/orcs-code
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: prevent duplicate responses in OpenAI streaming

Browse Source 
When certain OpenAI-compatible APIs (LM Studio, some proxies) send
multiple stream chunks with finish_reason set, the finish block ran
multiple times — emitting content_block_stop and message_delta for
each one. Each content_block_stop caused claude.ts to create and yield
a new assistant message, making every response appear twice in the UI.

Fix: add hasProcessedFinishReason flag (same pattern as the existing
hasEmittedFinalUsage flag) so the finish block only executes once per
response regardless of how many chunks contain finish_reason.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
gnanam1990
2026-04-01 18:14:41 +05:30
parent 4ca94b2454
commit cb86f73c06
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/services/api/openaiShim.ts
View File

@@ -292,6 +292,7 @@ async function* openaiStreamToAnthropic(
let hasEmittedContentStart = false let hasEmittedContentStart = false
let lastStopReason: 'tool_use' | 'max_tokens' | 'end_turn' | null = null let lastStopReason: 'tool_use' | 'max_tokens' | 'end_turn' | null = null
let hasEmittedFinalUsage = false let hasEmittedFinalUsage = false
let hasProcessedFinishReason = false
// Emit message_start // Emit message_start
yield { yield {
@@ -422,8 +423,11 @@ async function* openaiStreamToAnthropic(
} }
} }
// Finish // Finish — guard ensures we only process finish_reason once even if
if (choice.finish_reason) { // multiple chunks arrive with finish_reason set (some providers do this)
if (choice.finish_reason && !hasProcessedFinishReason) {
hasProcessedFinishReason = true
// Close any open content blocks // Close any open content blocks
if (hasEmittedContentStart) { if (hasEmittedContentStart) {
yield { yield {