fix(realtime): consume ChatDeltas when C++ autoparser clears Response#9538
Merged
Conversation
The llama.cpp C++-side chat autoparser clears Reply.Message and delivers parsed content/reasoning/tool-calls via Reply.chat_deltas. chat.go handles this (non-SSE path uses ToolCallsFromChatDeltas/ContentFromChatDeltas/ ReasoningFromChatDeltas), but realtime.go only read pred.Response, so any model routed through the autoparser (Qwen2.5/3 and friends) produced a silent reply: backend emitted N tokens, the session surface saw zero. Mirror the non-SSE chat path in realtime's triggerResponse: when deltas carry tool calls or content, use them directly; otherwise fall back to the existing raw-text parsing. Assisted-by: claude-opus-4-7-1M [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com>
mudler
approved these changes
Apr 24, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The llama.cpp C++-side chat autoparser clears Reply.Message and delivers
parsed content/reasoning/tool-calls via Reply.chat_deltas. chat.go handles
this (non-SSE path uses ToolCallsFromChatDeltas/ContentFromChatDeltas/
ReasoningFromChatDeltas), but realtime.go only read pred.Response, so any
model routed through the autoparser (Qwen2.5/3 and friends) produced a
silent reply: backend emitted N tokens, the session surface saw zero.
Mirror the non-SSE chat path in realtime's triggerResponse: when deltas
carry tool calls or content, use them directly; otherwise fall back to
the existing raw-text parsing.
Notes for Reviewers
I'm not sure if this should be handled in every call site of the predict wrapper function?
Signed commits