@nemesis-oss/ollama-sdk 1.20.0 → 1.21.0

package/dist/index.d.cts

@@ -230,6 +230,17 @@ interface ModelCapabilities {
      */
     readonly parallelToolCalls: ParallelToolCallBehavior;
 }
+/**
+ * Classifies the server behind `baseUrl` from its hostname alone (no network call).
+ *
+ * - `cloud`: the hosted Ollama Cloud API (`ollama.com`, `*.ollama.com`). This is the only host
+ *   known to reject structured output (`format`), so only it is refused pre-flight.
+ * - `local`: a private-network server — loopback, RFC 1918 / ULA addresses, `*.localhost`,
+ *   `*.local`, `*.internal`, or a single-label name such as a Docker or Kubernetes service
+ *   (`http://ollama:11434`).
+ * - `unknown`: any other hostname, including self-hosted servers on public domains. Those are
+ *   not refused for `format`, and they are not assumed to be local either.
+ */
 declare function inferRuntimeMode(baseUrl: string): RuntimeMode;
 /**
  * Scans `/api/show`'s `model_info` for the model's **native** context length
@@ -2508,8 +2519,14 @@ declare class OllamaClient {
      *
      * For the low-level generated API (without the generic wrapper), use
      * `client.native.systemOne(request)` directly.
+     *
+     * @param options.signal Cancels the whole call, including the cloud-model
+     *   version probe that runs first, so the gate never extends a caller's
+     *   deadline. An abort rejects with an {@link OllamaAbortError}.
      */
-    systemOne<Q extends SystemOneQuestions = SystemOneQuestions>(request: SystemOneRequest<Q>): Promise<SystemOneResponse<Q>>;
+    systemOne<Q extends SystemOneQuestions = SystemOneQuestions>(request: SystemOneRequest<Q>, options?: {
+        readonly signal?: AbortSignal;
+    }): Promise<SystemOneResponse<Q>>;
     /**
      * Cloud-model version gate for {@link systemOne} — throws
      * {@link OllamaCloudModelVersionError} when a cloud model is requested

package/dist/index.d.ts

@@ -230,6 +230,17 @@ interface ModelCapabilities {
      */
     readonly parallelToolCalls: ParallelToolCallBehavior;
 }
+/**
+ * Classifies the server behind `baseUrl` from its hostname alone (no network call).
+ *
+ * - `cloud`: the hosted Ollama Cloud API (`ollama.com`, `*.ollama.com`). This is the only host
+ *   known to reject structured output (`format`), so only it is refused pre-flight.
+ * - `local`: a private-network server — loopback, RFC 1918 / ULA addresses, `*.localhost`,
+ *   `*.local`, `*.internal`, or a single-label name such as a Docker or Kubernetes service
+ *   (`http://ollama:11434`).
+ * - `unknown`: any other hostname, including self-hosted servers on public domains. Those are
+ *   not refused for `format`, and they are not assumed to be local either.
+ */
 declare function inferRuntimeMode(baseUrl: string): RuntimeMode;
 /**
  * Scans `/api/show`'s `model_info` for the model's **native** context length
@@ -2508,8 +2519,14 @@ declare class OllamaClient {
      *
      * For the low-level generated API (without the generic wrapper), use
      * `client.native.systemOne(request)` directly.
+     *
+     * @param options.signal Cancels the whole call, including the cloud-model
+     *   version probe that runs first, so the gate never extends a caller's
+     *   deadline. An abort rejects with an {@link OllamaAbortError}.
      */
-    systemOne<Q extends SystemOneQuestions = SystemOneQuestions>(request: SystemOneRequest<Q>): Promise<SystemOneResponse<Q>>;
+    systemOne<Q extends SystemOneQuestions = SystemOneQuestions>(request: SystemOneRequest<Q>, options?: {
+        readonly signal?: AbortSignal;
+    }): Promise<SystemOneResponse<Q>>;
     /**
      * Cloud-model version gate for {@link systemOne} — throws
      * {@link OllamaCloudModelVersionError} when a cloud model is requested

package/dist/index.js

@@ -1606,16 +1606,23 @@ async function checkEndpointHealth(endpoint, fetchImpl, timeoutMs = 5e3, middlew
 
 // src/capabilities/capabilities.ts
 function inferRuntimeMode(baseUrl) {
+  let host;
   try {
-    const url = new URL(baseUrl);
-    const host = url.hostname.toLowerCase().replace(/^\[|\]$/g, "");
-    if (host === "localhost" || host === "127.0.0.1" || host === "::1" || host.endsWith(".local") || host.startsWith("192.168.") || host.startsWith("10.")) {
-      return "local";
-    }
-    return "cloud";
+    host = new URL(baseUrl).hostname.toLowerCase().replace(/^\[|\]$/g, "");
   } catch {
     return "unknown";
   }
+  if (host === "ollama.com" || host.endsWith(".ollama.com")) return "cloud";
+  if (isPrivateNetworkHost(host)) return "local";
+  return "unknown";
+}
+function isPrivateNetworkHost(host) {
+  if (!host.includes(".") && !host.includes(":")) return true;
+  if (host.endsWith(".localhost") || host.endsWith(".local") || host.endsWith(".internal"))
+    return true;
+  if (host === "::1" || host === "0.0.0.0") return true;
+  if (host.includes(":") && /^f[cd][0-9a-f]{0,2}:/.test(host)) return true;
+  return /^(?:127|10)\.\d{1,3}\.\d{1,3}\.\d{1,3}$/.test(host) || /^192\.168\.\d{1,3}\.\d{1,3}$/.test(host) || /^172\.(?:1[6-9]|2\d|3[01])\.\d{1,3}\.\d{1,3}$/.test(host);
 }
 function extractContextLength(modelInfo) {
   if (!modelInfo) return void 0;
@@ -2617,6 +2624,24 @@ function createTimeoutSignal(timeoutMs, userSignal) {
   };
   return { signal: controller.signal, cancel };
 }
+function untilAborted(promise, signal, message) {
+  if (signal === void 0) return promise;
+  return new Promise((resolve, reject) => {
+    const onAbort = () => reject(new OllamaAbortError(message));
+    promise.then(
+      (value) => {
+        signal.removeEventListener("abort", onAbort);
+        resolve(value);
+      },
+      (error) => {
+        signal.removeEventListener("abort", onAbort);
+        reject(error);
+      }
+    );
+    if (signal.aborted) onAbort();
+    else signal.addEventListener("abort", onAbort, { once: true });
+  });
+}
 
 // src/keep-alive.ts
 var KEEP_ALIVE_UNLOAD = 0;
@@ -5644,15 +5669,13 @@ var FailoverHttpClient = class {
   async request(options) {
     const { model, ...httpOptions } = options;
     return this.client.executeWithFailover(
-      async (http, signal) => {
-        const mergedOptions = {
-          ...httpOptions,
-          ...httpOptions.signal !== void 0 ? { signal } : { signal }
-        };
-        return http.request(mergedOptions);
-      },
+      // The signal handed to the operation already combines the caller's signal
+      // (passed below) with the failover scope and timeout. Using it, rather than
+      // the caller's, keeps the request cancellable by `destroy()` as well.
+      async (http, signal) => http.request({ ...httpOptions, signal }),
       {
         singleEndpoint: false,
+        ...httpOptions.signal !== void 0 ? { signal: httpOptions.signal } : {},
         ...model !== void 0 ? { model } : {}
       }
     );
@@ -6492,12 +6515,18 @@ var OllamaClient = class _OllamaClient {
    *
    * For the low-level generated API (without the generic wrapper), use
    * `client.native.systemOne(request)` directly.
+   *
+   * @param options.signal Cancels the whole call, including the cloud-model
+   *   version probe that runs first, so the gate never extends a caller's
+   *   deadline. An abort rejects with an {@link OllamaAbortError}.
    */
-  async systemOne(request) {
-    await this.assertCloudModelSupported(request.model);
-    return this.native.systemOne(
-      request
-    );
+  async systemOne(request, options = {}) {
+    await this.assertCloudModelSupported(request.model, options.signal);
+    return this.runtime.invoke({
+      operation: systemOneOp,
+      body: request,
+      ...options.signal !== void 0 ? { signal: options.signal } : {}
+    });
   }
   /**
    * Cloud-model version gate for {@link systemOne} — throws
@@ -6509,19 +6538,25 @@ var OllamaClient = class _OllamaClient {
    * so a later gated call retries), so at most one extra round-trip happens
    * across all gated calls.
    */
-  async assertCloudModelSupported(model) {
+  async assertCloudModelSupported(model, signal) {
     if (!isCloudModel(model)) return;
     const candidates = this.registry.candidates();
     const baseUrl = candidates[0]?.baseUrl ?? DEFAULT_BASE_URL;
     if (inferRuntimeMode(baseUrl) !== "local") return;
+    if (this.serverVersionCache === void 0) {
+      this.serverVersionCache = this.native.version().then((v) => v.version);
+    }
+    const probe = this.serverVersionCache;
     let version;
     try {
-      if (this.serverVersionCache === void 0) {
-        this.serverVersionCache = this.native.version().then((v) => v.version);
-      }
-      version = await this.serverVersionCache;
-    } catch {
-      this.serverVersionCache = void 0;
+      version = await untilAborted(
+        probe,
+        signal,
+        "System One call aborted while probing the Ollama server version"
+      );
+    } catch (error) {
+      if (signal?.aborted) throw error;
+      if (this.serverVersionCache === probe) this.serverVersionCache = void 0;
       return;
     }
     if (version && compareOllamaVersions(version, CLOUD_MODEL_MIN_OLLAMA_VERSION) < 0) {