Merge pull request #3000 from mpeter/fix/anthropic-small-model-base-url

fix(small-model): route anthropic provider through configured baseURL

CHANGELOG.md

@@ -90,6 +90,7 @@ All notable changes to this project will be documented in this file.
 - Git: pull-request checks in Work status stay current as their status changes.
 - UI: the default dialog close button is easier to click or tap (thanks to @rockinrimmer).
 - Desktop/Windows: the close button now aligns correctly with the rest of the window chrome.
+- Session assist: recaps and suggested follow-ups now work when the Anthropic provider is configured to use a custom endpoint; they previously failed every time instead of using that configured connection.
 
 ## [1.19.0] - 2026-08-19
 

packages/web/server/lib/small-model/DOCUMENTATION.md

@@ -103,7 +103,10 @@ other runtime API.
     `https://chatgpt.com/backend-api/codex/responses` with
     `ChatGPT-Account-Id`; expired tokens are refreshed against
     `auth.openai.com` (single-flight) and written back to `auth.json`.
-  - **Anthropic** (`type: api`): `/v1/messages` with `x-api-key`.
+  - **Anthropic** (`type: api`): `/messages` with `x-api-key`, against
+    `provider.anthropic.options.baseURL` when configured (used as-is, matching
+    `@ai-sdk/anthropic` — no `/v1` is inserted) or `https://api.anthropic.com/v1`
+    otherwise.
   - **Google** (`type: api`): `generateContent` with `x-goog-api-key`; Gemini 3
     uses `thinkingLevel`, Gemini 2.x uses `thinkingBudget: 0`, and all other
     models omit `thinkingConfig` entirely.

packages/web/server/lib/small-model/call.js

@@ -340,8 +340,11 @@ const callMessages = async ({ url, headers, modelID, prompt, system, maxOutputTo
   return text;
 };
 
-const callAnthropic = async ({ apiKey, modelID, prompt, system, maxOutputTokens, responseSchema, timeoutMs, signal }) => callMessages({
-  url: 'https://api.anthropic.com/v1/messages',
+const callAnthropic = async ({ apiKey, baseURL, modelID, prompt, system, maxOutputTokens, responseSchema, timeoutMs, signal }) => callMessages({
+  // Matches @ai-sdk/anthropic: baseURL is the full API prefix (commonly
+  // already ending in /v1), so it gets /messages appended as-is rather than
+  // having /v1/messages appended, which would double up a configured /v1.
+  url: `${(baseURL || 'https://api.anthropic.com/v1').replace(/\/+$/, '')}/messages`,
   headers: {
     'x-api-key': apiKey,
     'anthropic-version': '2023-06-01',
@@ -705,7 +708,7 @@ export async function callSmallModel({ auth, catalog, workingDirectory, provider
   }
 
   if (providerID === 'anthropic') {
-    return callAnthropic({ apiKey, modelID, prompt, system, maxOutputTokens: tokens, responseSchema, timeoutMs, signal });
+    return callAnthropic({ apiKey, baseURL: providerConfig?.baseURL, modelID, prompt, system, maxOutputTokens: tokens, responseSchema, timeoutMs, signal });
   }
   if (providerID === 'google') {
     return callGoogle({ apiKey, modelID, prompt, system, maxOutputTokens: tokens, responseSchema, timeoutMs, signal });

packages/web/server/lib/small-model/call.test.js

@@ -316,6 +316,69 @@ describe('callSmallModel — custom provider config', () => {
     });
   });
 
+  describe('anthropic provider custom baseURL override', () => {
+    const anthropicOk = (text) => ({
+      ok: true,
+      status: 200,
+      json: async () => ({ content: [{ type: 'text', text }] }),
+    });
+
+    it('respects provider.anthropic.options.baseURL over the hardcoded Anthropic endpoint', async () => {
+      readConfig.mockReturnValue({
+        provider: { anthropic: { options: { baseURL: 'http://127.0.0.1:3456/v1' } } },
+      });
+      fetchMock.mockResolvedValue(anthropicOk('ok'));
+
+      await callSmallModel({
+        auth: { anthropic: { type: 'api', key: 'dummy' } },
+        catalog: {},
+        workingDirectory: '/proj',
+        providerID: 'anthropic',
+        modelID: 'claude-haiku-4-5',
+        prompt: 'hi',
+      });
+
+      const { url, init } = lastCall(fetchMock);
+      expect(url).toBe('http://127.0.0.1:3456/v1/messages');
+      expect(url).not.toContain('api.anthropic.com');
+      expect(init.headers['x-api-key']).toBe('dummy');
+    });
+
+    it('uses a bare-host baseURL as-is without inserting /v1, matching @ai-sdk/anthropic', async () => {
+      readConfig.mockReturnValue({
+        provider: { anthropic: { options: { baseURL: 'http://127.0.0.1:3456' } } },
+      });
+      fetchMock.mockResolvedValue(anthropicOk('ok'));
+
+      await callSmallModel({
+        auth: { anthropic: { type: 'api', key: 'dummy' } },
+        catalog: {},
+        workingDirectory: '/proj',
+        providerID: 'anthropic',
+        modelID: 'claude-haiku-4-5',
+        prompt: 'hi',
+      });
+
+      expect(lastCall(fetchMock).url).toBe('http://127.0.0.1:3456/messages');
+    });
+
+    it('falls back to https://api.anthropic.com when no anthropic baseURL override is configured', async () => {
+      readConfig.mockReturnValue({});
+      fetchMock.mockResolvedValue(anthropicOk('ok'));
+
+      await callSmallModel({
+        auth: { anthropic: { type: 'api', key: 'sk-ant' } },
+        catalog: {},
+        workingDirectory: '/proj',
+        providerID: 'anthropic',
+        modelID: 'claude-haiku-4-5',
+        prompt: 'hi',
+      });
+
+      expect(lastCall(fetchMock).url).toBe('https://api.anthropic.com/v1/messages');
+    });
+  });
+
   describe('catalog-based base URL (no config override)', () => {
     it('uses the catalog api field when no config baseURL is set', async () => {
       readConfig.mockReturnValue({});