Merge branch 'Gitlawb:main' into development

src/services/api/client.test.ts

@@ -0,0 +1,121 @@
+import { afterEach, beforeEach, expect, test } from 'bun:test'
+import { getAnthropicClient } from './client.js'
+
+type FetchType = typeof globalThis.fetch
+
+type ShimClient = {
+  beta: {
+    messages: {
+      create: (params: Record<string, unknown>) => Promise<unknown>
+    }
+  }
+}
+
+const originalFetch = globalThis.fetch
+const originalMacro = (globalThis as Record<string, unknown>).MACRO
+const originalEnv = {
+  CLAUDE_CODE_USE_GEMINI: process.env.CLAUDE_CODE_USE_GEMINI,
+  GEMINI_API_KEY: process.env.GEMINI_API_KEY,
+  GEMINI_MODEL: process.env.GEMINI_MODEL,
+  GEMINI_BASE_URL: process.env.GEMINI_BASE_URL,
+  GOOGLE_API_KEY: process.env.GOOGLE_API_KEY,
+  OPENAI_API_KEY: process.env.OPENAI_API_KEY,
+  OPENAI_BASE_URL: process.env.OPENAI_BASE_URL,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
+  ANTHROPIC_API_KEY: process.env.ANTHROPIC_API_KEY,
+  ANTHROPIC_AUTH_TOKEN: process.env.ANTHROPIC_AUTH_TOKEN,
+}
+
+beforeEach(() => {
+  ;(globalThis as Record<string, unknown>).MACRO = { VERSION: 'test-version' }
+  process.env.CLAUDE_CODE_USE_GEMINI = '1'
+  process.env.GEMINI_API_KEY = 'gemini-test-key'
+  process.env.GEMINI_MODEL = 'gemini-2.0-flash'
+  process.env.GEMINI_BASE_URL = 'https://gemini.example/v1beta/openai'
+
+  delete process.env.GOOGLE_API_KEY
+  delete process.env.OPENAI_API_KEY
+  delete process.env.OPENAI_BASE_URL
+  delete process.env.OPENAI_MODEL
+  delete process.env.ANTHROPIC_API_KEY
+  delete process.env.ANTHROPIC_AUTH_TOKEN
+})
+
+afterEach(() => {
+  ;(globalThis as Record<string, unknown>).MACRO = originalMacro
+  process.env.CLAUDE_CODE_USE_GEMINI = originalEnv.CLAUDE_CODE_USE_GEMINI
+  process.env.GEMINI_API_KEY = originalEnv.GEMINI_API_KEY
+  process.env.GEMINI_MODEL = originalEnv.GEMINI_MODEL
+  process.env.GEMINI_BASE_URL = originalEnv.GEMINI_BASE_URL
+  process.env.GOOGLE_API_KEY = originalEnv.GOOGLE_API_KEY
+  process.env.OPENAI_API_KEY = originalEnv.OPENAI_API_KEY
+  process.env.OPENAI_BASE_URL = originalEnv.OPENAI_BASE_URL
+  process.env.OPENAI_MODEL = originalEnv.OPENAI_MODEL
+  process.env.ANTHROPIC_API_KEY = originalEnv.ANTHROPIC_API_KEY
+  process.env.ANTHROPIC_AUTH_TOKEN = originalEnv.ANTHROPIC_AUTH_TOKEN
+  globalThis.fetch = originalFetch
+})
+
+test('routes Gemini provider requests through the OpenAI-compatible shim', async () => {
+  let capturedUrl: string | undefined
+  let capturedHeaders: Headers | undefined
+  let capturedBody: Record<string, unknown> | undefined
+
+  globalThis.fetch = (async (input, init) => {
+    capturedUrl =
+      typeof input === 'string'
+        ? input
+        : input instanceof URL
+          ? input.toString()
+          : input.url
+    capturedHeaders = new Headers(init?.headers)
+    capturedBody = JSON.parse(String(init?.body)) as Record<string, unknown>
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-gemini',
+        model: 'gemini-2.0-flash',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'gemini ok',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 8,
+          completion_tokens: 3,
+          total_tokens: 11,
+        },
+      }),
+      {
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = (await getAnthropicClient({
+    maxRetries: 0,
+    model: 'gemini-2.0-flash',
+  })) as unknown as ShimClient
+
+  const response = await client.beta.messages.create({
+    model: 'gemini-2.0-flash',
+    system: 'test system',
+    messages: [{ role: 'user', content: 'hello' }],
+    max_tokens: 64,
+    stream: false,
+  })
+
+  expect(capturedUrl).toBe('https://gemini.example/v1beta/openai/chat/completions')
+  expect(capturedHeaders?.get('authorization')).toBe('Bearer gemini-test-key')
+  expect(capturedBody?.model).toBe('gemini-2.0-flash')
+  expect(response).toMatchObject({
+    role: 'assistant',
+    model: 'gemini-2.0-flash',
+  })
+})

src/services/api/client.ts

@@ -156,7 +156,8 @@ export async function getAnthropicClient({
   }
   if (
     isEnvTruthy(process.env.CLAUDE_CODE_USE_OPENAI) ||
-    isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
+    isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB) ||
+    isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
   ) {
     const { createOpenAIShimClient } = await import('./openaiShim.js')
     return createOpenAIShimClient({

src/services/api/codexShim.ts

@@ -85,7 +85,7 @@ function makeUsage(usage?: {
 }
 
 function makeMessageId(): string {
-  return `msg_${Math.random().toString(36).slice(2)}${Date.now().toString(36)}`
+  return `msg_${crypto.randomUUID().replace(/-/g, '')}`
 }
 
 function normalizeToolUseId(toolUseId: string | undefined): {

src/services/api/openaiShim.ts

@@ -231,7 +231,7 @@ function convertMessages(
               input?: unknown
               extra_content?: Record<string, unknown>
             }) => ({
-              id: tu.id ?? `call_${Math.random().toString(36).slice(2)}`,
+              id: tu.id ?? `call_${crypto.randomUUID().replace(/-/g, '')}`,
               type: 'function' as const,
               function: {
                 name: tu.name ?? 'unknown',
@@ -389,7 +389,7 @@ interface OpenAIStreamChunk {
 }
 
 function makeMessageId(): string {
-  return `msg_${Math.random().toString(36).slice(2)}${Date.now().toString(36)}`
+  return `msg_${crypto.randomUUID().replace(/-/g, '')}`
 }
 
 function convertChunkUsage(
@@ -610,6 +610,23 @@ async function* openaiStreamToAnthropic(
               : choice.finish_reason === 'length'
                 ? 'max_tokens'
                 : 'end_turn'
+          if (choice.finish_reason === 'content_filter' || choice.finish_reason === 'safety') {
+            // Gemini/Azure content safety filter blocked the response.
+            // Emit a visible text block so the user knows why output was truncated.
+            if (!hasEmittedContentStart) {
+              yield {
+                type: 'content_block_start',
+                index: contentBlockIndex,
+                content_block: { type: 'text', text: '' },
+              }
+              hasEmittedContentStart = true
+            }
+            yield {
+              type: 'content_block_delta',
+              index: contentBlockIndex,
+              delta: { type: 'text_delta', text: '\n\n[Content blocked by provider safety filter]' },
+            }
+          }
           lastStopReason = stopReason
 
           yield {
@@ -841,7 +858,14 @@ class OpenAIShimMessages {
     }
 
     const apiKey = process.env.OPENAI_API_KEY ?? ''
-    const isAzure = /cognitiveservices\.azure\.com|openai\.azure\.com/.test(request.baseUrl)
+    // Detect Azure endpoints by hostname (not raw URL) to prevent bypass via
+    // path segments like https://evil.com/cognitiveservices.azure.com/
+    let isAzure = false
+    try {
+      const { hostname } = new URL(request.baseUrl)
+      isAzure = hostname.endsWith('.azure.com') &&
+        (hostname.includes('cognitiveservices') || hostname.includes('openai') || hostname.includes('services.ai'))
+    } catch { /* malformed URL — not Azure */ }
 
     if (apiKey) {
       if (isAzure) {
@@ -1003,6 +1027,13 @@ class OpenAIShimMessages {
           ? 'max_tokens'
           : 'end_turn'
 
+    if (choice?.finish_reason === 'content_filter' || choice?.finish_reason === 'safety') {
+      content.push({
+        type: 'text',
+        text: '\n\n[Content blocked by provider safety filter]',
+      })
+    }
+
     return {
       id: data.id ?? makeMessageId(),
       type: 'message',

src/utils/model/openaiContextWindows.ts

@@ -50,9 +50,11 @@ const OPENAI_CONTEXT_WINDOWS: Record<string, number> = {
   'gemini-2.5-flash':       1_048_576,
 
   // Ollama local models
-  'llama3.3:70b':               8_192,
-  'llama3.1:8b':                8_192,
-  'llama3.2:3b':                8_192,
+  // Llama 3.1+ models support 128k context natively (Meta official specs).
+  // Ollama defaults to num_ctx=8192 but users can configure higher values.
+  'llama3.3:70b':             128_000,
+  'llama3.1:8b':              128_000,
+  'llama3.2:3b':              128_000,
   'qwen2.5-coder:32b':        32_768,
   'qwen2.5-coder:7b':         32_768,
   'deepseek-coder-v2:16b':    163_840,
@@ -122,7 +124,11 @@ const OPENAI_MAX_OUTPUT_TOKENS: Record<string, number> = {
 
 function lookupByModel<T>(table: Record<string, T>, model: string): T | undefined {
   if (table[model] !== undefined) return table[model]
-  for (const key of Object.keys(table)) {
+  // Sort keys by length descending so the most specific prefix wins.
+  // Without this, 'gpt-4-turbo-preview' could match 'gpt-4' (8k) instead
+  // of 'gpt-4-turbo' (128k) depending on V8's key iteration order.
+  const sortedKeys = Object.keys(table).sort((a, b) => b.length - a.length)
+  for (const key of sortedKeys) {
     if (model.startsWith(key)) return table[key]
   }
   return undefined