feat(OllamaProvider): add model options, streaming support, and thinking tokens

- Add IOllamaModelOptions interface for runtime options (num_ctx, temperature, etc.)
- Extend IOllamaProviderOptions with defaultOptions and defaultTimeout
- Add IOllamaChatOptions for per-request overrides
- Add IOllamaStreamChunk and IOllamaChatResponse interfaces
- Add chatStreamResponse() for async iteration with options
- Add collectStreamResponse() for streaming with progress callback
- Add chatWithOptions() for non-streaming with full options
- Update chat() to use defaultOptions and defaultTimeout

test/test.audio.openai.ts

@@ -1,8 +1,9 @@
 import { expect, tap } from '@git.zone/tstest/tapbundle';
 import * as qenv from '@push.rocks/qenv';
-import * as smartfile from '@push.rocks/smartfile';
+import { SmartFs, SmartFsProviderNode } from '@push.rocks/smartfs';
 
 const testQenv = new qenv.Qenv('./', './.nogit/');
+const smartfs = new SmartFs(new SmartFsProviderNode());
 
 import * as smartai from '../ts/index.js';
 
@@ -26,7 +27,7 @@ tap.test('OpenAI Audio: should create audio response', async () => {
     chunks.push(chunk as Uint8Array);
   }
   const audioBuffer = Buffer.concat(chunks);
-  await smartfile.fs.toFs(audioBuffer, './.nogit/testoutput.mp3');
+  await smartfs.file('./.nogit/testoutput.mp3').write(audioBuffer);
   console.log(`Audio Buffer length: ${audioBuffer.length}`);
   // Assert that the resulting buffer is not empty.
   expect(audioBuffer.length).toBeGreaterThan(0);