Merge pull request #6001 from nesquena/stage/5994-fork-streaming

Release exp: fork-from-here during active streaming (#5994, closes #5993)

CHANGELOG.md

@@ -13,6 +13,8 @@
 
 ### Fixed
 
+- **"Fork from here" works during an active response.** The fork button was silently dead while the agent was generating — clicking it did nothing. You can now fork from any past (already-committed) message while a response streams; only the currently-streaming message and the just-sent (not-yet-committed) prompt are blocked, with a clear toast. Thanks @kertisalex. (#5994, #5993)
+
 - **No more false "No response from provider" after a completed answer that used tools.** When an assistant turn ended with a real final answer delivered as structured content following tool calls (common with reasoning models and multi-tool turns), the completion detector could miss the final text and render a spurious "No response from provider" card under the finished reply. Final-answer detection now understands structured content parts (text after tool-use boundaries), while genuine empty completions still correctly show the no-response notice, and a real terminal provider error still surfaces as an error (never masked as a final answer). Thanks @jtstothard. (#5990, #5686)
 
 - **Custom/proxy providers keep the full vendor namespace when you deliberately pick a non-default model (follow-up to the earlier #5979 fix).** The initial fix preserved `x-ai/grok-4.5` when it was your configured default or already in a warm model catalog, but a model you *selected in the picker* that wasn't your default (e.g. `x-ai/grok-composer-2.5-fast`) was still truncated to the bare `grok-composer-2.5-fast` when the models catalog was cold at send time — the normal state right after a restart, a settings save, or a cache expiry. The proxy then rejected the bare id with `HTTP 400`. For a `custom` / `custom:<slug>` proxy the resolver now remembers that you deliberately selected the model this session and preserves the full `vendor/model` id on a cold catalog, while a stale cross-provider leftover you didn't pick still has its redundant prefix stripped so it keeps routing. The send path also warms model-catalog provenance from the durable on-disk cache first (network-free, non-blocking, never triggers a live probe). Thanks @b3nw for the detailed follow-up and the CLI-vs-WebUI comparison that localized it. (#5979)

static/commands.js

@@ -1944,7 +1944,19 @@ async function cmdBranch(args){
 // count (_oldestIdx + msgIdx) BEFORE awaiting _ensureAllMessagesLoaded,
 // which resets _oldestIdx to 0 after its wholesale replace.  See #2184.
 async function forkFromMessage(msgIdx){
-  if(!S.session||S.busy)return;
+  if(!S.session)return;
+  // During streaming, only block fork if the clicked message is the
+  // currently-streaming (live) message itself.  Past messages that are
+  // already committed server-side can be forked immediately without
+  // waiting for the stream to finish.
+  if(S.busy){
+    const _msg=(Array.isArray(S.messages)&&S.messages[msgIdx-1])||null;
+    const _isLastMsg=msgIdx>=(Array.isArray(S.messages)?S.messages.length:0);
+    if((_msg&&(_msg._live||_msg._pending))||_isLastMsg){
+      showToast('Cannot fork a message still being generated.',3000);
+      return;
+    }
+  }
   const readOnlySession=typeof _isReadOnlySession==='function'
     ? _isReadOnlySession(S.session)
     : !!(S.session&&(S.session.read_only||S.session.is_read_only));
@@ -1959,7 +1971,9 @@ async function forkFromMessage(msgIdx){
   const absoluteKeepCount = _oldestIdx + msgIdx;
   // Ensure the full transcript is loaded so the forked session renders
   // correctly and subsequent operations see the complete history.
-  if(typeof _ensureAllMessagesLoaded==='function'){
+  // Skip during streaming to avoid visual flicker — the fork data
+  // (absoluteKeepCount) was already captured above and is unaffected.
+  if(!S.busy && typeof _ensureAllMessagesLoaded==='function'){
     await _ensureAllMessagesLoaded();
   }
   if(!S.session || S.session.session_id !== initialSid) return;

static/messages.js

@@ -1629,7 +1629,7 @@ async function send(){
   // upload window. _composerDraftClearPromise / _submittedDraftFilesForClear are
   // set there; nothing to re-declare here.
   const displayText=_slashDisplayTextOverride||text||(uploaded.length?`Uploaded: ${uploadedNames.join(', ')}`:'(file upload)');
-  const userMsg={role:'user',content:displayText,attachments:uploaded.length?uploadedNames:undefined,_ts:Date.now()/1000};
+  const userMsg={role:'user',content:displayText,attachments:uploaded.length?uploadedNames:undefined,_ts:Date.now()/1000,_pending:true};
   S.toolCalls=[];  // clear tool calls from previous turn
   clearLiveToolCards();  // clear any leftover live cards from last turn
   let optimisticMessages;
@@ -7733,7 +7733,11 @@ function showClarifyCard(pending) {
   _clarifySessionId = sid;
   _clarifyId = pending.clarify_id || null;
   _clarifySignature = sig;
-  _startClarifyCountdown(pending);
+  if (Number(pending.timeout_seconds) > 0) {
+    _startClarifyCountdown(pending);
+  } else {
+    _clearClarifyCountdownTimer();
+  }
   if (!sameClarify) {
     _clarifyVisibleSince = Date.now();
     _clearClarifyHideTimer();