fix(desktop): keep background streams out of active chat (#654)

* fix: never auto-select embed-only models for chat

Ollama lists nomic-embed-text alongside chat models. Auto-picking
models[0] / recommending the only available id selected the embedder
and every generation failed with HTTP 400 "does not support chat".

- Filter embed-only ids out of GET /v1/models (chat picker)
- Exclude them from /v1/recommended-model; return empty when none left
- Frontend setModels prefers chat models and clears a bad embed selection
- Regression tests for mixed, embed-only, and classifier cases

* fix: harden chat model capability filtering

---------

Co-authored-by: Elliot Slusky <elliot@slusky.com>

frontend/src/App.tsx

@@ -31,7 +31,6 @@ export default function App() {
   const prevModelRef = useRef<string>('');
   const setModels = useAppStore((s) => s.setModels);
   const setModelsLoading = useAppStore((s) => s.setModelsLoading);
-  const setSelectedModel = useAppStore((s) => s.setSelectedModel);
   const selectedModel = useAppStore((s) => s.selectedModel);
   const setServerInfo = useAppStore((s) => s.setServerInfo);
   const setSavings = useAppStore((s) => s.setSavings);
@@ -70,7 +69,6 @@ export default function App() {
     fetchModels()
       .then((m) => {
         setModels(m);
-        if (!selectedModel && m.length > 0) setSelectedModel(m[0].id);
       })
       .catch(() => setModels([]))
       .finally(() => setModelsLoading(false));

frontend/src/components/Chat/ChatArea.tsx

@@ -15,6 +15,7 @@ function getGreeting(): string {
 }
 
 export function ChatArea() {
+  const activeId = useAppStore((s) => s.activeId);
   const messages = useAppStore((s) => s.messages);
   const streamState = useAppStore((s) => s.streamState);
   const systemPanelOpen = useAppStore((s) => s.systemPanelOpen);
@@ -24,6 +25,8 @@ export function ChatArea() {
   const shouldAutoScroll = useRef(true);
   const wasStreaming = useRef(false);
   const lastScrollTop = useRef(0);
+  const isCurrentChatStreaming = streamState.isStreaming && streamState.conversationId === activeId;
+  const currentStreamContent = isCurrentChatStreaming ? streamState.content : '';
 
   // Check if any data sources are connected
   const [hasConnectedSources, setHasConnectedSources] = useState<boolean | null>(null);
@@ -38,14 +41,14 @@ export function ChatArea() {
   useEffect(() => {
     // Sending a message always pins the view to the bottom, even if the
     // user had scrolled up to read earlier messages.
-    if (streamState.isStreaming && !wasStreaming.current) {
+    if (isCurrentChatStreaming && !wasStreaming.current) {
       shouldAutoScroll.current = true;
     }
-    wasStreaming.current = streamState.isStreaming;
+    wasStreaming.current = isCurrentChatStreaming;
     if (shouldAutoScroll.current && listRef.current) {
       listRef.current.scrollTop = listRef.current.scrollHeight;
     }
-  }, [messages, streamState.content, streamState.isStreaming]);
+  }, [messages, currentStreamContent, isCurrentChatStreaming]);
 
   const handleScroll = () => {
     if (!listRef.current) return;
@@ -66,7 +69,7 @@ export function ChatArea() {
     }
   };
 
-  const isEmpty = messages.length === 0 && !streamState.isStreaming;
+  const isEmpty = messages.length === 0 && !isCurrentChatStreaming;
 
   const PanelIcon = systemPanelOpen ? PanelRightClose : PanelRightOpen;
 
@@ -174,12 +177,12 @@ export function ChatArea() {
                 <MessageBubble
                   key={msg.id}
                   message={msg}
-                  isLive={isLastAssistant && streamState.isStreaming}
+                  isLive={isLastAssistant && isCurrentChatStreaming}
                 />
               );
             })}
             {(() => {
-              if (!streamState.isStreaming || streamState.content !== '') return null;
+              if (!isCurrentChatStreaming || streamState.content !== '') return null;
               // For research messages the ResearchTimeline handles its own
               // pre-content loading state — suppress the generic dots.
               const last = messages[messages.length - 1];

frontend/src/components/Chat/InputArea.tsx

@@ -96,6 +96,7 @@ export function InputArea() {
   const deepResearch = useAppStore((s) => s.deepResearch);
   const setDeepResearch = useAppStore((s) => s.setDeepResearch);
   const corpusSync = useResearchCorpusSync(deepResearch);
+  const isCurrentChatStreaming = streamState.isStreaming && streamState.conversationId === activeId;
 
   const {
     state: speechState,
@@ -226,6 +227,7 @@ export function InputArea() {
     let ttftMs: number | undefined;
 
     setStreamState({
+      conversationId: convId,
       isStreaming: true,
       phase: deepResearch ? 'Researching...' : 'Generating...',
       elapsedMs: 0,
@@ -602,7 +604,7 @@ export function InputArea() {
           style={{ color: 'var(--color-text)', maxHeight: '200px' }}
           disabled={streamState.isStreaming || modelLoading}
         />
-        {streamState.isStreaming ? (
+        {isCurrentChatStreaming ? (
           <button
             onClick={stopStreaming}
             className="p-2 rounded-xl transition-colors shrink-0 cursor-pointer"
@@ -621,7 +623,7 @@ export function InputArea() {
             />
             <button
               onClick={sendMessage}
-              disabled={!input.trim() || modelLoading || !selectedModel}
+              disabled={streamState.isStreaming || !input.trim() || modelLoading || !selectedModel}
               title={selectedModel ? 'Send message' : 'Pick a model first (⌘K)'}
               className="p-2 rounded-xl transition-colors shrink-0 cursor-pointer disabled:opacity-30 disabled:cursor-default"
               style={{

frontend/src/components/SetupScreen.tsx

@@ -7,6 +7,7 @@ import {
   type SetupStatus,
 } from '../lib/api';
 import { useAppStore } from '../lib/store';
+import { isEmbedOnlyModel } from '../lib/model-capabilities';
 
 const STEPS = [
   { key: 'ollama_ready', label: 'Inference Engine', icon: Cpu, detail: 'Starting Ollama...' },
@@ -91,12 +92,14 @@ export function SetupScreen({ onReady }: { onReady: () => void }) {
           fetchRecommendedModel().catch(() => ({ model: '', reason: '' })),
         ]);
         const store = useAppStore.getState();
+        const hadSelection = !!store.selectedModel;
         store.setModels(models);
         store.setModelsLoading(false);
-        const recommended = rec.model && models.some((m) => m.id === rec.model)
+        const chatModels = models.filter((m) => !isEmbedOnlyModel(m.id));
+        const recommended = rec.model && chatModels.some((m) => m.id === rec.model)
           ? rec.model
-          : models[0]?.id || '';
-        if (recommended && !store.selectedModel) {
+          : chatModels[0]?.id || '';
+        if (recommended && !hadSelection) {
           store.setSelectedModel(recommended);
         }
       } catch {

frontend/src/components/Sidebar/ConversationList.tsx

@@ -22,6 +22,9 @@ export function ConversationList({ searchQuery }: Props) {
   const navigate = useNavigate();
   const conversations = useAppStore((s) => s.conversations);
   const activeId = useAppStore((s) => s.activeId);
+  const streamingConversationId = useAppStore((s) =>
+    s.streamState.isStreaming ? s.streamState.conversationId : null,
+  );
   const selectConversation = useAppStore((s) => s.selectConversation);
   const deleteConversation = useAppStore((s) => s.deleteConversation);
 
@@ -43,6 +46,7 @@ export function ConversationList({ searchQuery }: Props) {
     <div className="flex flex-col gap-0.5 py-1">
       {filtered.map((conv) => {
         const isActive = conv.id === activeId;
+        const isStreaming = conv.id === streamingConversationId;
         return (
           <div
             key={conv.id}
@@ -82,11 +86,18 @@ export function ConversationList({ searchQuery }: Props) {
                 e.stopPropagation();
                 deleteConversation(conv.id);
               }}
-              className="p-1.5 mr-1 rounded opacity-0 group-hover:opacity-100 transition-opacity cursor-pointer"
+              disabled={isStreaming}
+              className="p-1.5 mr-1 rounded opacity-0 group-hover:opacity-100 transition-opacity cursor-pointer disabled:cursor-not-allowed disabled:opacity-30"
               style={{ color: 'var(--color-text-tertiary)' }}
-              onMouseEnter={(e) => (e.currentTarget.style.color = 'var(--color-error)')}
+              onMouseEnter={(e) => {
+                if (!isStreaming) e.currentTarget.style.color = 'var(--color-error)';
+              }}
               onMouseLeave={(e) => (e.currentTarget.style.color = 'var(--color-text-tertiary)')}
-              title="Delete conversation"
+              title={
+                isStreaming
+                  ? 'Stop generating before deleting this conversation'
+                  : 'Delete conversation'
+              }
             >
               <Trash2 size={14} />
             </button>

frontend/src/lib/model-capabilities.test.ts

@@ -0,0 +1,19 @@
+import { describe, expect, it } from 'vitest';
+
+import { isEmbedOnlyModel } from './model-capabilities';
+
+describe('isEmbedOnlyModel', () => {
+  it.each([
+    'nomic-embed-text',
+    'mxbai-embed-large',
+    'text-embedding-3-small',
+    'all-minilm:latest',
+    'hf.co/BAAI/bge-m3:latest',
+  ])('classifies %s as embedding-only', (modelId) => {
+    expect(isEmbedOnlyModel(modelId)).toBe(true);
+  });
+
+  it.each(['qwen3.5:4b', 'codegemma:7b'])('keeps %s available for chat', (modelId) => {
+    expect(isEmbedOnlyModel(modelId)).toBe(false);
+  });
+});

frontend/src/lib/model-capabilities.ts

@@ -0,0 +1,22 @@
+const EMBEDDING_MODEL_PREFIXES = [
+  'all-minilm',
+  'bge-',
+  'bge_',
+  'e5-',
+  'e5_',
+  'gte-',
+  'gte_',
+  'jina-embeddings',
+  'nomic-bert',
+  'sentence-transformers',
+];
+
+export function isEmbedOnlyModel(modelId: string): boolean {
+  const name = (modelId || '').trim().toLowerCase();
+  const leaf = name.slice(name.lastIndexOf('/') + 1).split(':')[0];
+  return (
+    leaf.includes('embed') ||
+    leaf.includes('minilm') ||
+    EMBEDDING_MODEL_PREFIXES.some((prefix) => leaf.startsWith(prefix))
+  );
+}

frontend/src/lib/store.models.test.ts

@@ -0,0 +1,64 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+
+import type { ModelInfo } from '../types';
+
+class MemoryStorage {
+  private store = new Map<string, string>();
+
+  getItem(key: string): string | null {
+    return this.store.get(key) ?? null;
+  }
+
+  setItem(key: string, value: string): void {
+    this.store.set(key, String(value));
+  }
+}
+
+const model = (id: string): ModelInfo => ({
+  id,
+  object: 'model',
+  created: 0,
+  owned_by: 'openjarvis',
+});
+
+beforeEach(() => {
+  vi.resetModules();
+  (globalThis as unknown as { localStorage: MemoryStorage }).localStorage =
+    new MemoryStorage();
+});
+
+afterEach(() => {
+  (globalThis as unknown as { localStorage?: MemoryStorage }).localStorage =
+    undefined;
+});
+
+describe('setModels', () => {
+  it('does not select an embedding-only model', async () => {
+    const { useAppStore } = await import('./store');
+
+    useAppStore.getState().setModels([model('nomic-embed-text')]);
+
+    expect(useAppStore.getState().selectedModel).toBe('');
+  });
+
+  it('clears a missing selection when no chat fallback exists', async () => {
+    const { useAppStore } = await import('./store');
+    useAppStore.getState().setSelectedModel('deleted-chat-model');
+
+    useAppStore.getState().setModels([model('nomic-embed-text')]);
+
+    expect(useAppStore.getState().selectedModel).toBe('');
+  });
+
+  it('replaces an embedding selection with an available chat model', async () => {
+    const { useAppStore } = await import('./store');
+    useAppStore.getState().setSelectedModel('all-minilm:latest');
+
+    useAppStore.getState().setModels([
+      model('all-minilm:latest'),
+      model('qwen3.5:4b'),
+    ]);
+
+    expect(useAppStore.getState().selectedModel).toBe('qwen3.5:4b');
+  });
+});

frontend/src/lib/store.stream-ownership.test.ts

@@ -0,0 +1,82 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+
+class MemoryStorage {
+  private store = new Map<string, string>();
+
+  getItem(key: string): string | null {
+    return this.store.get(key) ?? null;
+  }
+
+  setItem(key: string, value: string): void {
+    this.store.set(key, String(value));
+  }
+
+  removeItem(key: string): void {
+    this.store.delete(key);
+  }
+}
+
+beforeEach(() => {
+  vi.resetModules();
+  (globalThis as unknown as { localStorage: MemoryStorage }).localStorage =
+    new MemoryStorage();
+});
+
+afterEach(() => {
+  (globalThis as unknown as { localStorage?: MemoryStorage }).localStorage =
+    undefined;
+});
+
+async function freshStore() {
+  return (await import('./store')).useAppStore;
+}
+
+describe('conversation stream ownership', () => {
+  it('persists background stream updates without replacing the active messages', async () => {
+    const store = await freshStore();
+    const sourceId = store.getState().createConversation('test-model');
+    store.getState().addMessage(sourceId, {
+      id: 'assistant',
+      role: 'assistant',
+      content: '',
+      timestamp: 1,
+    });
+
+    const activeId = store.getState().createConversation('test-model');
+    store.getState().setStreamState({
+      conversationId: sourceId,
+      isStreaming: true,
+      content: 'streamed response',
+    });
+    store.getState().updateLastAssistant(sourceId, 'streamed response');
+
+    expect(store.getState().activeId).toBe(activeId);
+    expect(store.getState().messages).toEqual([]);
+
+    store.getState().selectConversation(sourceId);
+    expect(store.getState().messages).toHaveLength(1);
+    expect(store.getState().messages[0].content).toBe('streamed response');
+  });
+
+  it('keeps the stream-owning conversation until generation stops', async () => {
+    const store = await freshStore();
+    const sourceId = store.getState().createConversation('test-model');
+    const activeId = store.getState().createConversation('test-model');
+    store.getState().setStreamState({
+      conversationId: sourceId,
+      isStreaming: true,
+    });
+
+    store.getState().deleteConversation(sourceId);
+    expect(
+      store.getState().conversations.map((conversation) => conversation.id),
+    ).toContain(sourceId);
+    expect(store.getState().activeId).toBe(activeId);
+
+    store.getState().resetStream();
+    store.getState().deleteConversation(sourceId);
+    expect(
+      store.getState().conversations.map((conversation) => conversation.id),
+    ).not.toContain(sourceId);
+  });
+});

frontend/src/lib/store.ts

@@ -15,6 +15,7 @@ import type {
   TokenUsage,
 } from '../types';
 import type { ManagedAgent } from './api';
+import { isEmbedOnlyModel } from './model-capabilities';
 
 export interface CachedConnector {
   connector_id: string;
@@ -110,6 +111,7 @@ function saveSettings(settings: Settings): void {
 // ── Store ─────────────────────────────────────────────────────────────
 
 const INITIAL_STREAM: StreamState = {
+  conversationId: null,
   isStreaming: false,
   phase: '',
   elapsedMs: 0,
@@ -351,6 +353,9 @@ export const useAppStore = create<AppState>((set, get) => {
     },
 
     deleteConversation: (id: string) => {
+      const streamState = get().streamState;
+      if (streamState.isStreaming && streamState.conversationId === id) return;
+
       const store = loadConversations();
       delete store.conversations[id];
       if (store.activeId === id) {
@@ -393,12 +398,14 @@ export const useAppStore = create<AppState>((set, get) => {
           (message.content.length > 50 ? '...' : '');
       }
       saveConversations(store);
-      set({
-        messages: [...conv.messages],
-        conversations: Object.values(store.conversations).sort(
-          (a, b) => b.updatedAt - a.updatedAt,
-        ),
-      });
+      const conversations = Object.values(store.conversations).sort(
+        (a, b) => b.updatedAt - a.updatedAt,
+      );
+      if (get().activeId === conversationId) {
+        set({ messages: [...conv.messages], conversations });
+      } else {
+        set({ conversations });
+      }
     },
 
     updateLastAssistant: (
@@ -425,7 +432,9 @@ export const useAppStore = create<AppState>((set, get) => {
         if (researchSources) lastMsg.researchSources = researchSources;
         conv.updatedAt = Date.now();
         saveConversations(store);
-        set({ messages: [...conv.messages] });
+        if (get().activeId === conversationId) {
+          set({ messages: [...conv.messages] });
+        }
       }
     },
 
@@ -444,11 +453,36 @@ export const useAppStore = create<AppState>((set, get) => {
     // ── Models & server ────────────────────────────────────────────
 
     setModels: (models: ModelInfo[]) =>
-      set((state) =>
-        !state.selectedModel && models.length > 0
-          ? { models, selectedModel: models[0].id }
-          : { models },
-      ),
+      set((state) => {
+        // Ollama returns embed-only models (e.g. nomic-embed-text) in the
+        // same list as chat models. Auto-picking models[0] selected the
+        // embedder and every chat failed with HTTP 400 "does not support
+        // chat". Prefer a real chat model for selection / fallback.
+        const chatModels = models.filter((m) => !isEmbedOnlyModel(m.id));
+        const preferred =
+          (state.settings.defaultModel &&
+            chatModels.some((m) => m.id === state.settings.defaultModel) &&
+            state.settings.defaultModel) ||
+          chatModels[0]?.id ||
+          models.find((m) => !isEmbedOnlyModel(m.id))?.id ||
+          '';
+
+        const currentIsBad =
+          !!state.selectedModel && isEmbedOnlyModel(state.selectedModel);
+        const currentMissing =
+          !!state.selectedModel &&
+          !models.some((m) => m.id === state.selectedModel);
+
+        if (!state.selectedModel || currentIsBad || currentMissing) {
+          // Prefer a real chat model. If none exist, clear a bad/missing
+          // selection rather than keeping an embed-only id that 400s on chat.
+          return {
+            models,
+            selectedModel: preferred,
+          };
+        }
+        return { models };
+      }),
     setModelsLoading: (loading: boolean) => set({ modelsLoading: loading }),
     setSelectedModel: (model: string) => set({ selectedModel: model }),
     setServerInfo: (info: ServerInfo | null) => set({ serverInfo: info }),

frontend/src/types/index.ts

@@ -147,6 +147,7 @@ export interface ConversationStore {
 // --- Stream State ---
 
 export interface StreamState {
+  conversationId: string | null;
   isStreaming: boolean;
   phase: string;
   elapsedMs: number;

src/openjarvis/cli/daemon_cmd.py

@@ -17,18 +17,64 @@ _PID_FILE = DEFAULT_CONFIG_DIR / "server.pid"
 _LOG_FILE = DEFAULT_CONFIG_DIR / "server.log"
 
 
+def _pid_alive(pid: int) -> bool:
+    """Return whether *pid* identifies a running process without signaling it."""
+    if pid <= 0:
+        return False
+
+    if os.name == "nt":
+        import ctypes
+        from ctypes import wintypes
+
+        error_invalid_parameter = 87
+        synchronize = 0x00100000
+        wait_object_0 = 0x00000000
+
+        kernel32 = ctypes.WinDLL("kernel32", use_last_error=True)
+        kernel32.OpenProcess.argtypes = [wintypes.DWORD, wintypes.BOOL, wintypes.DWORD]
+        kernel32.OpenProcess.restype = wintypes.HANDLE
+        kernel32.WaitForSingleObject.argtypes = [wintypes.HANDLE, wintypes.DWORD]
+        kernel32.WaitForSingleObject.restype = wintypes.DWORD
+        kernel32.CloseHandle.argtypes = [wintypes.HANDLE]
+        kernel32.CloseHandle.restype = wintypes.BOOL
+
+        handle = kernel32.OpenProcess(synchronize, False, pid)
+        if not handle:
+            # OpenProcess reports ERROR_INVALID_PARAMETER when the PID does not
+            # exist. For access-denied and other inconclusive failures, retain
+            # the PID file rather than declaring a potentially live daemon dead.
+            return ctypes.get_last_error() != error_invalid_parameter
+
+        try:
+            wait_result = kernel32.WaitForSingleObject(handle, 0)
+            # WAIT_OBJECT_0 proves the process exited. WAIT_TIMEOUT proves it
+            # is live; unexpected failures are inconclusive, so retain the PID.
+            return wait_result != wait_object_0
+        finally:
+            kernel32.CloseHandle(handle)
+
+    try:
+        os.kill(pid, 0)
+    except ProcessLookupError:
+        return False
+    except PermissionError:
+        return True
+    return True
+
+
 def _read_pid() -> int | None:
     """Read PID from pid file, return None if not found or stale."""
     if not _PID_FILE.exists():
         return None
     try:
         pid = int(_PID_FILE.read_text().strip())
-        # Check if process is still running
-        os.kill(pid, 0)
-        return pid
-    except (ValueError, OSError):
+    except (OSError, ValueError):
         _PID_FILE.unlink(missing_ok=True)
         return None
+    if not _pid_alive(pid):
+        _PID_FILE.unlink(missing_ok=True)
+        return None
+    return pid
 
 
 def _write_pid(pid: int) -> None:
@@ -127,14 +173,13 @@ def stop() -> None:
         # Wait up to 10 seconds for graceful shutdown
         for _ in range(20):
             time.sleep(0.5)
-            try:
-                os.kill(pid, 0)
-            except OSError:
+            if not _pid_alive(pid):
                 break
         else:
-            # Force kill if still running
+            # SIGKILL is POSIX-only. On Windows SIGTERM already maps to
+            # TerminateProcess, so repeating it is the available escalation.
             try:
-                os.kill(pid, signal.SIGKILL)
+                os.kill(pid, getattr(signal, "SIGKILL", signal.SIGTERM))
             except OSError:
                 pass
     except OSError:

src/openjarvis/server/agent_manager_routes.py

@@ -20,6 +20,7 @@ from openjarvis.agents.tool_resolver import (
 from openjarvis.agents.tool_resolver import (
     ensure_registries_populated as _ensure_registries_populated,
 )
+from openjarvis.server.model_capabilities import is_embed_only_model
 
 try:
     from fastapi import APIRouter, HTTPException, Request
@@ -332,16 +333,29 @@ _CLOUD_PREFIXES = ("gpt-", "claude-", "gemini-", "o1-", "o3-", "o4-")
 def _pick_recommended_model(
     model_ids: list[str],
 ) -> dict[str, str]:
-    """Pick the second-largest local model from a list."""
-    local = [m for m in model_ids if not any(m.startswith(p) for p in _CLOUD_PREFIXES)]
+    """Pick the second-largest local *chat* model from a list.
+
+    Embedding-only models (nomic-embed-text, etc.) are excluded — they return
+    HTTP 400 "does not support chat" when used as the generation model.
+    """
+    local = [
+        m
+        for m in model_ids
+        if not any(m.startswith(p) for p in _CLOUD_PREFIXES)
+        and not is_embed_only_model(m)
+    ]
     if not local:
+        # Fall back to any non-cloud model, still skipping embedders.
+        local = [m for m in model_ids if not is_embed_only_model(m)]
+    if not local:
+        # Never recommend an embed-only model — chat would 400.
         return {
-            "model": model_ids[0] if model_ids else "",
-            "reason": "Only model available",
+            "model": "",
+            "reason": "No local chat model available",
         }
     sized = sorted(local, key=_parse_param_count, reverse=True)
     if len(sized) == 1:
-        return {"model": sized[0], "reason": "Only local model available"}
+        return {"model": sized[0], "reason": "Only local chat model available"}
     pick = sized[1]  # second-largest
     params = _parse_param_count(pick)
     return {

src/openjarvis/server/model_capabilities.py

@@ -0,0 +1,34 @@
+"""Model capability helpers shared by server model-selection routes."""
+
+_EMBEDDING_MODEL_PREFIXES = (
+    "all-minilm",
+    "bge-",
+    "bge_",
+    "e5-",
+    "e5_",
+    "gte-",
+    "gte_",
+    "jina-embeddings",
+    "nomic-bert",
+    "sentence-transformers",
+)
+
+
+def is_embed_only_model(model_name: str) -> bool:
+    """Return whether a model identifier denotes a non-chat embedder.
+
+    Ollama does not expose capabilities through its model-list response, so
+    model selection needs a conservative name-based guard.  Most embedding
+    models contain ``embed``; the explicit prefixes cover common families
+    such as MiniLM, BGE, E5, and GTE whose names do not.
+    """
+    name = (model_name or "").strip().lower()
+    leaf = name.rsplit("/", 1)[-1].split(":", 1)[0]
+    return (
+        "embed" in leaf
+        or "minilm" in leaf
+        or leaf.startswith(_EMBEDDING_MODEL_PREFIXES)
+    )
+
+
+__all__ = ["is_embed_only_model"]

src/openjarvis/server/routes.py

@@ -12,6 +12,7 @@ from fastapi.responses import StreamingResponse
 
 from openjarvis.core.paths import get_config_dir
 from openjarvis.core.types import Message, Role
+from openjarvis.server.model_capabilities import is_embed_only_model
 from openjarvis.server.models import (
     ChatCompletionChunk,
     ChatCompletionRequest,
@@ -892,6 +893,11 @@ async def list_models(request: Request) -> ModelListResponse:
     if not model_ids:
         model_ids = await list_local_models()
 
+    # Keep embed-only models out of the chat model picker. They still work for
+    # memory/retrieval via the embedder path; putting them in /v1/models made
+    # the UI auto-select nomic-embed-text and fail every generation with 400.
+    model_ids = [m for m in model_ids if not is_embed_only_model(m)]
+
     return ModelListResponse(
         data=[
             ModelObject(

tests/cli/test_daemon_cmd.py

@@ -2,14 +2,17 @@
 
 from __future__ import annotations
 
+import os
 import subprocess
+import sys
+import time
 from pathlib import Path
 from unittest.mock import MagicMock, patch
 
 from click.testing import CliRunner
 
 from openjarvis.cli import cli
-from openjarvis.cli.daemon_cmd import _read_pid, _write_pid
+from openjarvis.cli.daemon_cmd import _pid_alive, _read_pid, _write_pid
 
 
 class TestDaemonCommands:
@@ -45,12 +48,12 @@ class TestDaemonCommands:
             assert _read_pid() is None
 
     def test_write_and_read_pid(self, tmp_path: Path) -> None:
-        """Write a PID, then read it back (mock os.kill to succeed)."""
+        """Write a PID, then read it back with a successful liveness probe."""
         pid_file = tmp_path / "server.pid"
         with (
             patch("openjarvis.cli.daemon_cmd._PID_FILE", pid_file),
             patch("openjarvis.cli.daemon_cmd.DEFAULT_CONFIG_DIR", tmp_path),
-            patch("os.kill", return_value=None),
+            patch("openjarvis.cli.daemon_cmd._pid_alive", return_value=True),
         ):
             _write_pid(12345)
             assert pid_file.exists()
@@ -82,6 +85,53 @@ class TestDaemonCommands:
         assert "already running" in result.output
 
 
+class TestPidLiveness:
+    """Regression coverage for Windows-safe PID liveness checks."""
+
+    def test_pid_alive_current_process(self) -> None:
+        assert _pid_alive(os.getpid()) is True
+
+    def test_pid_alive_nonpositive(self) -> None:
+        assert _pid_alive(0) is False
+        assert _pid_alive(-1) is False
+
+    def test_pid_alive_dead_pid(self) -> None:
+        proc = subprocess.Popen([sys.executable, "-c", "pass"])
+        proc.wait()
+
+        for _ in range(20):
+            if not _pid_alive(proc.pid):
+                break
+            time.sleep(0.1)
+
+        assert _pid_alive(proc.pid) is False
+
+    def test_read_pid_stale_pid_returns_none(self, tmp_path: Path) -> None:
+        proc = subprocess.Popen([sys.executable, "-c", "pass"])
+        proc.wait()
+        pid_file = tmp_path / "server.pid"
+        pid_file.write_text(str(proc.pid))
+
+        with patch("openjarvis.cli.daemon_cmd._PID_FILE", pid_file):
+            assert _read_pid() is None
+
+        assert not pid_file.exists()
+
+    def test_read_pid_live_pid_returns_it(self, tmp_path: Path) -> None:
+        proc = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(10)"])
+        try:
+            pid_file = tmp_path / "server.pid"
+            pid_file.write_text(str(proc.pid))
+
+            with patch("openjarvis.cli.daemon_cmd._PID_FILE", pid_file):
+                assert _read_pid() == proc.pid
+
+            assert pid_file.exists()
+        finally:
+            proc.terminate()
+            proc.wait()
+
+
 class TestDaemonDetachment:
     """The spawned server must outlive the console that started it.
 

tests/server/test_model_management.py

@@ -265,6 +265,28 @@ class TestModelsEndpointExtended:
         assert "qwen3.5:9b" in ids
         assert "qwen3:0.6b" in ids
 
+    def test_models_list_filters_embedding_only_models(self):
+        engine = _make_engine(
+            models=["nomic-embed-text", "all-minilm:latest", "qwen3.5:4b"],
+        )
+        client = TestClient(create_app(engine, "qwen3.5:4b"))
+
+        resp = client.get("/v1/models")
+
+        assert resp.status_code == 200
+        assert [m["id"] for m in resp.json()["data"]] == ["qwen3.5:4b"]
+
+    def test_models_list_returns_empty_when_only_embedders_are_installed(self):
+        engine = _make_engine(
+            models=["nomic-embed-text", "hf.co/BAAI/bge-m3:latest"],
+        )
+        client = TestClient(create_app(engine, "nomic-embed-text"))
+
+        resp = client.get("/v1/models")
+
+        assert resp.status_code == 200
+        assert resp.json()["data"] == []
+
     def test_models_empty_engine(self):
         """When engine.list_models() returns empty, endpoint still succeeds."""
         engine = _make_engine(models=[])

tests/server/test_recommended_model.py

@@ -50,3 +50,42 @@ def test_parse_param_count():
     assert _parse_param_count("qwen3.5:0.8b") == 0.8
     assert _parse_param_count("qwen3.5:35b") == 35.0
     assert _parse_param_count("gpt-4o") == 0.0
+
+
+@pytest.mark.skipif(not HAS_FASTAPI, reason="fastapi not installed")
+def test_recommended_model_skips_embed_only():
+    """Embed-only models must never be recommended for chat."""
+    from openjarvis.server.agent_manager_routes import _pick_recommended_model
+
+    models = [
+        "nomic-embed-text",
+        "qwen3.5:4b",
+        "mxbai-embed-large",
+        "qwen3.5:9b",
+    ]
+    result = _pick_recommended_model(models)
+    assert result["model"] == "qwen3.5:4b"
+    assert "embed" not in result["model"]
+
+
+@pytest.mark.skipif(not HAS_FASTAPI, reason="fastapi not installed")
+def test_recommended_model_embed_only_returns_empty():
+    """If only embedders are installed, recommend nothing (not nomic-embed)."""
+    from openjarvis.server.agent_manager_routes import _pick_recommended_model
+
+    result = _pick_recommended_model(["nomic-embed-text", "mxbai-embed-large"])
+    assert result["model"] == ""
+    assert "No local chat model" in result["reason"]
+
+
+@pytest.mark.skipif(not HAS_FASTAPI, reason="fastapi not installed")
+def test_is_embed_only_model():
+    from openjarvis.server.model_capabilities import is_embed_only_model
+
+    assert is_embed_only_model("nomic-embed-text")
+    assert is_embed_only_model("mxbai-embed-large")
+    assert is_embed_only_model("text-embedding-3-small")
+    assert is_embed_only_model("all-minilm:latest")
+    assert is_embed_only_model("hf.co/BAAI/bge-m3:latest")
+    assert not is_embed_only_model("qwen3.5:4b")
+    assert not is_embed_only_model("codegemma:7b")