Let recipes use the model loaded in Chat

studio/backend/routes/data_recipe/jobs.py

@@ -23,9 +23,96 @@
     RecipePayload,
 )
 
+from datetime import timedelta
+
 router = APIRouter()
 
 
+def _inject_local_providers(recipe: dict[str, Any], request_base_url: str) -> None:
+    """
+    Mutate recipe dict in-place: for any provider with is_local=True,
+    generate a 24h JWT and fill in the endpoint pointing at this server.
+    """
+    providers = recipe.get("model_providers")
+    if not providers:
+        return
+
+    # Collect local providers and pop is_local from ALL dicts unconditionally
+    local_indices: list[int] = []
+    for i, provider in enumerate(providers):
+        if not isinstance(provider, dict):
+            continue
+        if provider.pop("is_local", None):
+            local_indices.append(i)
+
+    if not local_indices:
+        return
+
+    # Only gate on model-loaded if a local provider is actually referenced
+    # by a model_config. Unused local provider nodes should not block runs.
+    local_names = {providers[i].get("name") for i in local_indices}
+    referenced_providers = {
+        mc.get("provider")
+        for mc in recipe.get("model_configs", [])
+        if isinstance(mc, dict)
+    }
+    if not local_names & referenced_providers:
+        # No model_config actually uses a local provider, just inject and move on
+        from urllib.parse import urlparse
+
+        parsed = urlparse(request_base_url)
+        port = parsed.port or 8888
+        endpoint = f"http://127.0.0.1:{port}/v1"
+        for i in local_indices:
+            providers[i]["endpoint"] = endpoint
+            providers[i]["api_key"] = ""
+            providers[i]["provider_type"] = "openai"
+        return
+
+    # Verify a model is loaded.
+    # NOTE: This is a point-in-time check (TOCTOU). The model could be unloaded
+    # or swapped after this check but before the recipe subprocess calls /v1.
+    # The inference endpoint returns a clear 400 in that case.
+    #
+    # Imports are deferred to avoid circular dependencies with inference modules.
+    from routes.inference import get_llama_cpp_backend
+    from core.inference import get_inference_backend
+
+    llama = get_llama_cpp_backend()
+    model_loaded = llama.is_loaded
+    if not model_loaded:
+        backend = get_inference_backend()
+        model_loaded = bool(backend.active_model_name)
+    if not model_loaded:
+        raise ValueError(
+            "No model loaded in Chat. Load a model first, then run the recipe."
+        )
+
+    from auth.authentication import (
+        create_access_token,
+    )  # deferred: avoids circular import
+
+    # Uses the "unsloth" admin subject. If the user changes their password,
+    # the JWT secret rotates and this token becomes invalid mid-run.
+    # Acceptable for v1 — recipes typically finish well within one session.
+    token = create_access_token(
+        subject = "unsloth",
+        expires_delta = timedelta(hours = 24),
+    )
+
+    # Always use loopback — request.base_url may reflect a proxy or 0.0.0.0
+    from urllib.parse import urlparse  # deferred: only needed for local providers
+
+    parsed = urlparse(request_base_url)
+    port = parsed.port or 8888
+    endpoint = f"http://127.0.0.1:{port}/v1"
+
+    for i in local_indices:
+        providers[i]["endpoint"] = endpoint
+        providers[i]["api_key"] = token
+        providers[i]["provider_type"] = "openai"
+
+
 def _normalize_run_name(value: Any) -> str | None:
     if value is None:
         return None
@@ -40,7 +127,7 @@ def _normalize_run_name(value: Any) -> str | None:
 
 
 @router.post("/jobs", response_class = JSONResponse, response_model = JobCreateResponse)
-def create_job(payload: RecipePayload):
+def create_job(payload: RecipePayload, request: Request):
     recipe = payload.recipe
     if not recipe.get("columns"):
         raise HTTPException(status_code = 400, detail = "Recipe must include columns.")
@@ -67,6 +154,11 @@ def create_job(payload: RecipePayload):
                 status_code = 400, detail = f"invalid run_config: {exc}"
             ) from exc
 
+    try:
+        _inject_local_providers(recipe, str(request.base_url))
+    except ValueError as exc:
+        raise HTTPException(status_code = 400, detail = str(exc)) from exc
+
     mgr = get_job_manager()
     try:
         job_id = mgr.start(recipe = recipe, run = run)

studio/backend/routes/data_recipe/validate.py

@@ -68,6 +68,15 @@ def _collect_validation_errors(recipe: dict[str, Any]) -> list[ValidateError]:
     return errors
 
 
+def _patch_local_providers(recipe: dict[str, Any]) -> None:
+    """Strip is_local and fill a dummy endpoint so validation doesn't choke."""
+    for provider in recipe.get("model_providers", []):
+        if not isinstance(provider, dict):
+            continue
+        if provider.pop("is_local", None):
+            provider["endpoint"] = "http://127.0.0.1"
+
+
 @router.post("/validate", response_model = ValidateResponse)
 def validate(payload: RecipePayload) -> ValidateResponse:
     recipe = payload.recipe
@@ -77,6 +86,8 @@ def validate(payload: RecipePayload) -> ValidateResponse:
             errors = [ValidateError(message = "Recipe must include columns.")],
         )
 
+    _patch_local_providers(recipe)
+
     try:
         validate_recipe(recipe)
     except RuntimeError as exc:

studio/frontend/src/features/recipe-studio/blocks/render-dialog.tsx

@@ -28,6 +28,7 @@ export function renderBlockDialog(
   categoryOptions: SamplerConfig[],
   modelConfigAliases: string[],
   modelProviderOptions: string[],
+  localProviderNames: Set<string>,
   toolProfileAliases: string[],
   datetimeOptions: string[],
   onUpdate: (id: string, patch: Partial<NodeConfig>) => void,
@@ -109,6 +110,7 @@ export function renderBlockDialog(
         <ModelConfigDialog
           config={config}
           providerOptions={modelProviderOptions}
+          localProviderNames={localProviderNames}
           onUpdate={update}
         />
       ) : null;

studio/frontend/src/features/recipe-studio/components/inline/inline-model.tsx

@@ -15,6 +15,15 @@ type InlineModelProps = {
 
 export function InlineModel(props: InlineModelProps): ReactElement {
   if (props.config.kind === "model_provider") {
+    if (props.config.is_local) {
+      return (
+        <div className="flex items-center gap-2 px-1 py-0.5">
+          <span className="text-xs font-medium text-muted-foreground">
+            Local model (Chat)
+          </span>
+        </div>
+      );
+    }
     return (
       <div className="grid gap-3 sm:grid-cols-2">
         <InlineField label="Endpoint">

studio/frontend/src/features/recipe-studio/dialogs/config-dialog.tsx

@@ -18,6 +18,7 @@ type ConfigDialogProps = {
   categoryOptions: SamplerConfig[];
   modelConfigAliases: string[];
   modelProviderOptions: string[];
+  localProviderNames: Set<string>;
   toolProfileAliases: string[];
   datetimeOptions: string[];
   onUpdate: (id: string, patch: Partial<NodeConfig>) => void;
@@ -32,6 +33,7 @@ export function ConfigDialog({
   categoryOptions,
   modelConfigAliases,
   modelProviderOptions,
+  localProviderNames,
   toolProfileAliases,
   datetimeOptions,
   onUpdate,
@@ -101,6 +103,7 @@ export function ConfigDialog({
                 categoryOptions,
                 modelConfigAliases,
                 modelProviderOptions,
+                localProviderNames,
                 toolProfileAliases,
                 datetimeOptions,
                 onUpdate,

studio/frontend/src/features/recipe-studio/dialogs/models/model-config-dialog.tsx

@@ -26,14 +26,17 @@ import { NameField } from "../shared/name-field";
 type ModelConfigDialogProps = {
   config: ModelConfig;
   providerOptions: string[];
+  localProviderNames: Set<string>;
   onUpdate: (patch: Partial<ModelConfig>) => void;
 };
 
 export function ModelConfigDialog({
   config,
   providerOptions,
+  localProviderNames,
   onUpdate,
 }: ModelConfigDialogProps): ReactElement {
+  const isLinkedToLocal = localProviderNames.has(config.provider);
   const [optionalOpen, setOptionalOpen] = useState(false);
   const modelId = `${config.id}-model`;
   const providerId = `${config.id}-provider`;
@@ -84,7 +87,17 @@ export function ModelConfigDialog({
             filteredItems={providerOptions}
             filter={null}
             value={config.provider || null}
-            onValueChange={(value) => updateField("provider", value ?? "")}
+            onValueChange={(value) => {
+              const selectedProvider = value ?? "";
+              const isLocal = localProviderNames.has(selectedProvider);
+              if (isLocal && !config.model.trim()) {
+                onUpdate({ provider: selectedProvider, model: "local" });
+              } else if (!isLocal && config.model === "local") {
+                onUpdate({ provider: selectedProvider, model: "" });
+              } else {
+                updateField("provider", selectedProvider);
+              }
+            }}
             onInputValueChange={(value) => {
               providerInputRef.current = value;
             }}
@@ -124,12 +137,12 @@ export function ModelConfigDialog({
         <FieldLabel
           label="Model ID"
           htmlFor={modelId}
-          hint="The exact model name sent to the connection."
+          hint={isLinkedToLocal ? "Uses the model loaded in Chat. Any value works here." : "The exact model name sent to the connection."}
         />
         <Input
           id={modelId}
           className="nodrag"
-          placeholder="gpt-4o-mini"
+          placeholder={isLinkedToLocal ? "local" : "gpt-4o-mini"}
           value={config.model}
           onChange={(event) => updateField("model", event.target.value)}
         />