From 896a0da10e8a18f1773c396e99d2a6544aace0f5 Mon Sep 17 00:00:00 2001
From: William Valentin <william.valentin.info@gmail.com>
Date: Thu, 5 Feb 2026 10:47:42 -0800
Subject: [PATCH] feat(models): add streaming support to AnthropicClient

---
 src/models/anthropic.test.ts | 37 +++++++++++++++++++++++++++++++++
 src/models/anthropic.ts      | 40 ++++++++++++++++++++++++++++++++++--
 2 files changed, 75 insertions(+), 2 deletions(-)

diff --git a/src/models/anthropic.test.ts b/src/models/anthropic.test.ts
index 3aed256..d4fb0b6 100644
--- a/src/models/anthropic.test.ts
+++ b/src/models/anthropic.test.ts
@@ -10,6 +10,16 @@ vi.mock('@anthropic-ai/sdk', () => ({
         stop_reason: 'end_turn',
         usage: { input_tokens: 10, output_tokens: 5 },
       }),
+      stream: vi.fn().mockReturnValue({
+        [Symbol.asyncIterator]: async function* () {
+          yield { type: 'content_block_delta', delta: { type: 'text_delta', text: 'Hello ' } };
+          yield { type: 'content_block_delta', delta: { type: 'text_delta', text: 'from ' } };
+          yield { type: 'content_block_delta', delta: { type: 'text_delta', text: 'Claude!' } };
+        },
+        finalMessage: vi.fn().mockResolvedValue({
+          usage: { input_tokens: 10, output_tokens: 5 },
+        }),
+      }),
     },
   })),
 }));
@@ -31,3 +41,30 @@ describe('AnthropicClient', () => {
     expect(response.usage.outputTokens).toBe(5);
   });
 });
+
+describe('AnthropicClient streaming', () => {
+  it('streams messages chunk by chunk', async () => {
+    const client = new AnthropicClient({
+      apiKey: 'test-key',
+      model: 'claude-sonnet-4-20250514',
+    });
+
+    const chunks: string[] = [];
+    let finalUsage: { inputTokens: number; outputTokens: number } | undefined;
+
+    for await (const event of client.chatStream({
+      messages: [{ role: 'user', content: 'Hello' }],
+    })) {
+      if (event.type === 'content' && event.content) {
+        chunks.push(event.content);
+      }
+      if (event.type === 'done' && event.usage) {
+        finalUsage = event.usage;
+      }
+    }
+
+    expect(chunks.length).toBeGreaterThan(0);
+    expect(chunks.join('')).toBe('Hello from Claude!');
+    expect(finalUsage).toEqual({ inputTokens: 10, outputTokens: 5 });
+  });
+});
diff --git a/src/models/anthropic.ts b/src/models/anthropic.ts
index 70c44b0..5cf624d 100644
--- a/src/models/anthropic.ts
+++ b/src/models/anthropic.ts
@@ -1,8 +1,9 @@
 import Anthropic from '@anthropic-ai/sdk';
-import type { ChatRequest, ChatResponse, ModelClient } from './types.js';
+import type { ChatRequest, ChatResponse, ChatStreamEvent, ModelClient } from './types.js';
 
 export interface AnthropicClientConfig {
-  apiKey?: string;  // Falls back to ANTHROPIC_API_KEY env var
+  apiKey?: string;     // Falls back to ANTHROPIC_API_KEY env var
+  authToken?: string;  // Alternative: use auth token instead of API key
   model: string;
   maxTokens?: number;
 }
@@ -15,6 +16,7 @@ export class AnthropicClient implements ModelClient {
   constructor(config: AnthropicClientConfig) {
     this.client = new Anthropic({
       apiKey: config.apiKey,
+      authToken: config.authToken,
     });
     this.model = config.model;
     this.defaultMaxTokens = config.maxTokens ?? 4096;
@@ -43,4 +45,38 @@ export class AnthropicClient implements ModelClient {
       },
     };
   }
+
+  async *chatStream(request: ChatRequest): AsyncIterable<ChatStreamEvent> {
+    const stream = this.client.messages.stream({
+      model: this.model,
+      max_tokens: request.maxTokens ?? this.defaultMaxTokens,
+      system: request.system,
+      messages: request.messages.map((m) => ({
+        role: m.role,
+        content: m.content,
+      })),
+    });
+
+    try {
+      for await (const event of stream) {
+        if (event.type === 'content_block_delta' && event.delta.type === 'text_delta') {
+          yield { type: 'content', content: event.delta.text };
+        }
+      }
+
+      const finalMessage = await stream.finalMessage();
+      yield {
+        type: 'done',
+        usage: {
+          inputTokens: finalMessage.usage.input_tokens,
+          outputTokens: finalMessage.usage.output_tokens,
+        },
+      };
+    } catch (error) {
+      yield {
+        type: 'error',
+        error: error instanceof Error ? error : new Error(String(error)),
+      };
+    }
+  }
 }