upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-30 09:57:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

ui : only send the conversation id header to llama.cpp

Browse Source 
Assisted-by: pi:llama.cpp/DeepSeek-V4.1-Flash
This commit is contained in:
Aleksander Grygier
2026-09-28 12:10:10 +02:00
parent 22670d9fda
commit 74cbaa2ce1
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/ui/src/lib/services/chat.service.ts
+3 -2
View File
@@ -1330,8 +1330,9 @@ export class ChatService {
// tag streaming requests with the conversation id, this single header is the opt in for the
// server side replay buffer and powers discoverActiveStream on tab reopen. with an explicit
// model the ::model suffix keeps the per model session distinct
if (stream && conversationId) {
// model the ::model suffix keeps the per model session distinct. external providers do not
// know the header and their CORS preflight rejects it, so only llama.cpp gets it
if (stream && conversationId && serverStore.capabilities.resumableStreams) {
headers[HEADERS.X_CONVERSATION_ID_HEADER] = streamIdentity(conversationId, options.model);
// persist the pending stream before the fetch: a reload during the model load or
// the prompt processing must still find its way back to the session once it exists