ai-sdk-ollama 4.1.0 → 4.3.0

package/CHANGELOG.md

@@ -1,5 +1,27 @@
 # Changelog
 
+## 4.3.0
+
+### Minor Changes
+
+- 371f515: Track AI SDK 7.0.95 and open the provider up to custom Ollama clients.
+
+  - The `ai` peer range moves to `^7.0.95`, with `@ai-sdk/provider` and `@ai-sdk/provider-utils` updated to match.
+  - `OllamaClient` is a structural contract, so the official client, a maintained fork, or a custom adapter can be injected in both Node.js and browser builds. Streaming methods use the newly exported `AbortableStream` type.
+  - Per-request `AbortSignal`s are forwarded to the client, and an aborted request settles as a rejection across the reliability retry and fallback paths.
+  - Returned `message.thinking` is surfaced as AI SDK reasoning independently of the request's `think` setting, including on terminal stream chunks, and streamed text and reasoning blocks close symmetrically.
+  - Output usage carries the total token count Ollama reports and leaves the text/reasoning split unset, matching what the API provides.
+
+## 4.2.0
+
+### Minor Changes
+
+- a48c0e1: Add MCP Apps examples demonstrating the host flow for ui:// resources
+
+  - Node example: connect with mcpAppClientCapabilities, split tools by visibility, generateText with model-visible tools, read and fingerprint ui:// HTML resource, simulate iframe proxy allow/deny
+  - Browser example: Vite dev server hosts MCP Apps sandbox, proxies read-resource and call-tool requests, renders interactive dashboard via experimental_MCPAppRenderer
+  - Shared stdio MCP server with dashboard resource, model+app tool, and app-only refresh tool
+
 ## 4.1.0
 
 ### Minor Changes

package/README.md

@@ -740,7 +740,10 @@ const ollama = createOllama({ apiKey: process.env.OLLAMA_API_KEY });
 
 ### Using Existing Ollama Client
 
-You can also pass an existing Ollama client instance to reuse your configuration:
+You can also pass an existing Ollama client instance to reuse your configuration.
+The provider accepts the exported structural `OllamaClient` interface, so the
+official client, the maintained compatibility fork, or a custom adapter can be
+injected in Node.js and browser builds.
 
 ```typescript
 import { Ollama } from 'ollama';
@@ -756,13 +759,36 @@ const existingClient = new Ollama({
 const ollamaSdk = createOllama({ client: existingClient });
 
 // Use both clients as needed
-await ollamaRaw.list(); // Direct Ollama operations
+await existingClient.list(); // Direct Ollama operations
 const { text } = await generateText({
   model: ollamaSdk('llama3.2'),
   prompt: 'Hello!',
 });
 ```
 
+#### Custom client adapters
+
+`OllamaClient` is structural, so any object with the right shape works — no
+`Ollama` instance required. Streaming methods return an `AbortableStream`, an
+async iterable with an `abort()`:
+
+```typescript
+import type { AbortableStream, OllamaClient } from 'ai-sdk-ollama';
+import { createOllama } from 'ai-sdk-ollama';
+
+const client: OllamaClient = {
+  chat: myChat, // returns a ChatResponse, or an AbortableStream of them
+  embed: myEmbed,
+  webSearch: myWebSearch,
+  webFetch: myWebFetch,
+};
+
+const ollama = createOllama({ client });
+```
+
+Per-request cancellation is forwarded to the client as an `AbortSignal`, and an
+aborted request rejects rather than resolving with a retried or fallback result.
+
 ### Structured Output
 
 ```typescript
@@ -918,39 +944,38 @@ const { output: custom } = await generateText({
 
 ### Reasoning Support
 
-Some models like DeepSeek-R1 support reasoning (chain-of-thought) output. Enable this feature to see the model's thinking process:
+Use `think` to request reasoning generation from models that support it. Returned `message.thinking` is exposed as AI SDK reasoning, separately from final text, in both generation results and streams (including terminal chunks).
 
 ```typescript
 import { ollama } from 'ai-sdk-ollama';
 import { generateText } from 'ai';
 
 // Enable reasoning for models that support it (e.g., deepseek-r1:7b)
-const model = ollama('deepseek-r1:7b', { reasoning: true });
+const model = ollama('deepseek-r1:7b', { think: true });
 
 // Generate text with reasoning
-const { text } = await generateText({
+const { text, reasoningText } = await generateText({
   model,
   prompt:
     'Solve: If I have 3 boxes, each with 4 smaller boxes, and each smaller box has 5 items, how many items total?',
 });
 
 console.log('Answer:', text);
-// DeepSeek-R1 includes reasoning in the output with <think> tags:
-// <think>
-// First, I'll calculate the number of smaller boxes: 3 × 4 = 12
-// Then, the total items: 12 × 5 = 60
-// </think>
-// You have 60 items in total.
+console.log('Reasoning:', reasoningText);
 
 // Compare with reasoning disabled
-const modelNoReasoning = ollama('deepseek-r1:7b', { reasoning: false });
+const modelNoReasoning = ollama('deepseek-r1:7b', { think: false });
 const { text: noReasoningText } = await generateText({
   model: modelNoReasoning,
   prompt: 'Calculate 3 × 4 × 5',
 });
-// Output: 60 (without showing the thinking process)
+console.log('Answer:', noReasoningText);
 ```
 
+`think` controls the request, not filtering of the response. If the server returns thinking with `think` omitted or `false`, the adapter still preserves it as reasoning; it does not turn it into final text. If no thinking is returned, no reasoning content is added.
+
+Ollama supplies a combined output token count. The adapter preserves that total and the raw counters, but leaves the text/reasoning token breakdown unknown instead of attributing all output tokens to text.
+
 **Recommended Reasoning Models**:
 
 - `deepseek-r1:7b` - Balanced performance and reasoning capability (5GB)
@@ -1029,6 +1054,8 @@ For detailed testing information, see [Integration Tests Documentation](./src/in
 
 🔗 **[MCP Tools Example](../../examples/node/src/mcp-tools-example.ts)** - Model Context Protocol integration
 
+🧩 **[MCP Apps Example](../../examples/node/src/mcp-apps-example.ts)** - MCP Apps host flow (ui:// resources, split tools, iframe proxy)
+
 🔧 **[JSON repair example](../../examples/node/src/json-repair-example.ts)** - Object generation with repair options and custom repair
 
 🔀 **[Cascade repair example](../../examples/node/src/test-cascade-repair.ts)** - `cascadeRepairText` and `enhancedRepairText` (jsonrepair + Ollama-specific)

package/dist/functions/generate-text.d.ts

@@ -0,0 +1,63 @@
+/**
+ * generateText - Enhanced generateText with Ollama-specific reliability
+ *
+ * This wrapper provides response synthesis and enhanced tool calling reliability
+ * that addresses the core Ollama limitation: tools execute but no final text is generated.
+ */
+import { generateText as _generateText } from 'ai';
+/**
+ * Enhanced options for Ollama-specific reliability features
+ */
+export interface EnhancedOptions {
+    /**
+     * Enable response synthesis when tools are called but no text is generated
+     * @default true
+     */
+    enableSynthesis?: boolean;
+    /**
+     * Custom synthesis prompt template
+     */
+    synthesisPrompt?: string;
+    /**
+     * Maximum attempts for synthesis
+     * @default 2
+     */
+    maxSynthesisAttempts?: number;
+    /**
+     * Minimum response length to consider valid
+     * @default 10
+     */
+    minResponseLength?: number;
+    /**
+     * EXPERIMENTAL: Enable tool calling with structured output (output)
+     *
+     * The official AI SDK doesn't support combining toolChoice: 'required' with output.
+     * When enabled, this uses a two-phase approach:
+     * 1. Execute tools first (without output)
+     * 2. Generate structured output with tool results injected as context
+     *
+     * This is NOT standard AI SDK behavior - only enable if you need both features together.
+     *
+     * @default false
+     */
+    enableToolsWithStructuredOutput?: boolean;
+}
+/**
+ * Enhanced generateText options that extend the official AI SDK options
+ */
+export type GenerateTextOptions = Parameters<typeof _generateText>[0] & {
+    /**
+     * Enhanced options for Ollama-specific reliability features
+     */
+    enhancedOptions?: EnhancedOptions;
+};
+/**
+ * Enhanced generateText function with Ollama-specific reliability improvements
+ *
+ * This function applies synthesis by default when tools execute but return empty responses.
+ * The enhancement preserves the original response prototype and all methods/getters.
+ *
+ * Type parameters are inferred from the options, preserving AI SDK's type inference.
+ */
+export declare function generateText(options: GenerateTextOptions): Promise<Awaited<ReturnType<typeof _generateText>>>;
+//# sourceMappingURL=generate-text.d.ts.map

package/dist/functions/generate-text.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"generate-text.d.ts","sourceRoot":"","sources":["../../src/functions/generate-text.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAEH,OAAO,EAAE,YAAY,IAAI,aAAa,EAAe,MAAM,IAAI,CAAC;AAqBhE;;GAEG;AACH,MAAM,WAAW,eAAe;IAC9B;;;OAGG;IACH,eAAe,CAAC,EAAE,OAAO,CAAC;IAE1B;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IAEzB;;;OAGG;IACH,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAE9B;;;OAGG;IACH,iBAAiB,CAAC,EAAE,MAAM,CAAC;IAE3B;;;;;;;;;;;OAWG;IACH,+BAA+B,CAAC,EAAE,OAAO,CAAC;CAC3C;AAED;;GAEG;AACH,MAAM,MAAM,mBAAmB,GAAG,UAAU,CAAC,OAAO,aAAa,CAAC,CAAC,CAAC,CAAC,GAAG;IACtE;;OAEG;IACH,eAAe,CAAC,EAAE,eAAe,CAAC;CACnC,CAAC;AAEF;;;;;;;GAOG;AACH,wBAAsB,YAAY,CAChC,OAAO,EAAE,mBAAmB,GAC3B,OAAO,CAAC,OAAO,CAAC,UAAU,CAAC,OAAO,aAAa,CAAC,CAAC,CAAC,CA4NpD"}

package/dist/functions/stream-text.d.ts

@@ -0,0 +1,25 @@
+import { streamText as _streamText } from 'ai';
+type AIStreamTextOptions = Parameters<typeof _streamText>[0];
+export type StreamTextOptions = AIStreamTextOptions & {
+    enhancedOptions?: {
+        /**
+         * @default true
+         */
+        enableToolLogging?: boolean;
+        /**
+         * @default true
+         */
+        enableStreamingSynthesis?: boolean;
+        /**
+         * @default 10
+         */
+        minStreamLength?: number;
+        /**
+         * @default 3000
+         */
+        synthesisTimeout?: number;
+    };
+};
+export declare function streamText(options: StreamTextOptions): Promise<Awaited<ReturnType<typeof _streamText>>>;
+export {};
+//# sourceMappingURL=stream-text.d.ts.map

package/dist/functions/stream-text.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"stream-text.d.ts","sourceRoot":"","sources":["../../src/functions/stream-text.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,IAAI,WAAW,EAAe,MAAM,IAAI,CAAC;AAE5D,KAAK,mBAAmB,GAAG,UAAU,CAAC,OAAO,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC;AAsC7D,MAAM,MAAM,iBAAiB,GAAG,mBAAmB,GAAG;IACpD,eAAe,CAAC,EAAE;QAChB;;WAEG;QACH,iBAAiB,CAAC,EAAE,OAAO,CAAC;QAC5B;;WAEG;QACH,wBAAwB,CAAC,EAAE,OAAO,CAAC;QACnC;;WAEG;QACH,eAAe,CAAC,EAAE,MAAM,CAAC;QACzB;;WAEG;QACH,gBAAgB,CAAC,EAAE,MAAM,CAAC;KAC3B,CAAC;CACH,CAAC;AAUF,wBAAsB,UAAU,CAC9B,OAAO,EAAE,iBAAiB,GACzB,OAAO,CAAC,OAAO,CAAC,UAAU,CAAC,OAAO,WAAW,CAAC,CAAC,CAAC,CAsclD"}