fix(proxy): ensure OpenAI tool call streaming emits proper delta chunks and increase body limit

- Emit tool call id+name in first SSE delta and arguments in subsequent deltas
- Split large tool arguments into 1000-char chunks to prevent framing issues
- Set FastifyAdapter bodyLimit to 10MB to handle large payloads
- Add TDD tests for tool call streaming verification

src/components/StatusBar.tsx

@@ -18,7 +18,7 @@ export const StatusBar: React.FC<StatusBarProps> = ({ isCollapsed = false }) =>
   const { data: isRunning, isLoading } = useQuery({
     queryKey: ['process', 'status'],
     queryFn: isProcessRunning,
-    refetchInterval: 30000,
+    refetchInterval: 10000,
   });
 
   const startMutation = useMutation({

src/ipc/database/cloudHandler.ts

@@ -521,20 +521,12 @@ export class CloudAccountRepo {
     try {
       const rows = orm.select().from(accounts).orderBy(desc(accounts.lastUsed)).all();
 
+      // DEBUG LOGS
       const activeRows = rows.filter((r) => r.isActive);
-      logger.debug(
-        `getAccounts: Found ${rows.length} accounts, ${activeRows.length} active.`,
+      logger.info(
+        `[DEBUG] getAccounts: Found ${rows.length} accounts, ${activeRows.length} active.`,
       );
-
-      // Auto-activate the single account if none are active
-      if (rows.length > 0 && activeRows.length === 0) {
-        const targetRow = rows[0];
-        logger.info(
-          `No active account found. Auto-activating account: ${targetRow.email} (${targetRow.id})`,
-        );
-        orm.update(accounts).set({ isActive: 1 }).where(eq(accounts.id, targetRow.id)).run();
-        targetRow.isActive = 1;
-      }
+      activeRows.forEach((r) => logger.info(`[DEBUG] Active Account: ${r.email} (${r.id})`));
 
       const cloudAccounts: CloudAccount[] = [];
       for (const normalizedRow of rows) {

src/server/main.ts

@@ -22,9 +22,13 @@ export async function bootstrapNestServer(config: ProxyConfig): Promise<boolean>
   setServerConfig(config);
 
   try {
-    app = await NestFactory.create<NestFastifyApplication>(AppModule, new FastifyAdapter(), {
-      logger: ['error', 'warn', 'log'],
-    });
+    app = await NestFactory.create<NestFastifyApplication>(
+      AppModule,
+      new FastifyAdapter({ bodyLimit: 10 * 1024 * 1024 }),
+      {
+        logger: ['error', 'warn', 'log'],
+      },
+    );
 
     // Enable CORS
     app.enableCors();

src/server/modules/proxy/interfaces/request-interfaces.ts

@@ -184,8 +184,6 @@ export interface OpenAIChatResponse {
     completion_tokens: number;
     total_tokens: number;
   };
-  /** Optional identifier for the model's configuration snapshot. Included for OpenAI-spec compliance. */
-  system_fingerprint?: string;
 }
 
 export interface OpenAIChoice {

src/server/modules/proxy/proxy.controller.ts

@@ -84,26 +84,8 @@ export class ProxyController {
   }
 
   @Post('chat/completions')
-  async chatCompletions(
-    @Body() body: OpenAIChatRequest,
-    @Req() req: FastifyRequest,
-    @Res() res: FastifyReply,
-  ) {
-    await this.respondOpenAIChatCompletions(body, res, req);
-  }
-
-  /**
-   * Alias route: some clients (e.g. OpenCode configured with baseURL ending in /v1/messages)
-   * send requests to /v1/messages/chat/completions. Forward to the same handler so those
-   * clients do not receive a 404.
-   */
-  @Post('messages/chat/completions')
-  async messagesCompletionsAlias(
-    @Body() body: OpenAIChatRequest,
-    @Req() req: FastifyRequest,
-    @Res() res: FastifyReply,
-  ) {
-    await this.respondOpenAIChatCompletions(body, res, req);
+  async chatCompletions(@Body() body: OpenAIChatRequest, @Res() res: FastifyReply) {
+    await this.respondOpenAIChatCompletions(body, res);
   }
 
   @Post('completions')
@@ -321,23 +303,13 @@ export class ProxyController {
     }
   }
 
-  private async respondOpenAIChatCompletions(
-    body: OpenAIChatRequest,
-    res: FastifyReply,
-    req?: FastifyRequest,
-  ) {
+  private async respondOpenAIChatCompletions(body: OpenAIChatRequest, res: FastifyReply) {
     const requestId = uuidv4();
     const startTime = Date.now();
     trafficLogger.logInbound(requestId, '/v1/chat/completions', body, undefined, { stream: body.stream });
 
-    // Extract x-session-affinity header so OpenCode session stickiness works even when
-    // the request body does not carry an explicit session_id field.
-    const headerSessionKey = req
-      ? (req.headers['x-session-affinity'] as string | undefined)
-      : undefined;
-
     try {
-      const result = await this.proxyService.handleChatCompletions(body, requestId, headerSessionKey);
+      const result = await this.proxyService.handleChatCompletions(body, requestId);
 
       if (body.stream && this.isObservableLike(result)) {
         this.writeSseResponse(res, result, requestId, '/v1/chat/completions', startTime);

src/server/modules/proxy/proxy.service.ts

@@ -692,12 +692,8 @@ export class ProxyService {
   async handleChatCompletions(
     request: OpenAIChatRequest,
     _requestId?: string,
-    headerSessionKey?: string,
   ): Promise<OpenAIChatResponse | Observable<string>> {
-    // Prefer the x-session-affinity header value (sent by OpenCode) over body-level session ids.
-    const sessionKey =
-      (headerSessionKey ? `openai:${headerSessionKey}` : undefined) ??
-      this.extractOpenAISessionKey(request);
+    const sessionKey = this.extractOpenAISessionKey(request);
 
     const targetModel = this.resolveTargetModel(request.model);
     const extraHeaders = this.createModelSpecificHeaders(request.model);
@@ -751,7 +747,7 @@ export class ProxyService {
               token.token.upstream_proxy_url,
               extraHeaders,
             );
-            return this.processStreamResponse(stream, request.model);
+            return this.processStreamResponse(stream, request.model, request.stream_options);
           } catch (streamError) {
             this.logger.warn(
               `Stream path failed for model=${request.model}; falling back to non-stream generation: ${
@@ -810,7 +806,7 @@ export class ProxyService {
                 token.token.upstream_proxy_url,
                 extraHeaders,
               );
-              return this.processStreamResponse(stream, request.model);
+              return this.processStreamResponse(stream, request.model, request.stream_options);
             }
 
             const response = await this.generateInternalWithStreamFallback(
@@ -957,19 +953,38 @@ export class ProxyService {
   private processStreamResponse(
     upstreamStream: NodeJS.ReadableStream,
     model: string,
+    streamOptions?: { include_usage?: boolean },
   ): Observable<string> {
     return new Observable<string>((subscriber) => {
       const decoder = new TextDecoder();
       let buffer = '';
       let hasEmittedChunk = false;
       let hasSentDone = false;
+      let isThinking = false;
       let toolCallIndex = 0;
+      let lastUsageMetadata: GeminiResponse['usageMetadata'];
 
       const streamId = `chatcmpl-${uuidv4()}`;
       const created = Math.floor(Date.now() / 1000);
 
+      // Emit initial role chunk immediately to prevent strict clients (like Hermes) from timing out during long TTFT
+      const initialChunk = {
+        id: streamId,
+        object: 'chat.completion.chunk',
+        created: created,
+        model: model,
+        choices: [
+          {
+            index: 0,
+            delta: { role: 'assistant', content: '' },
+            finish_reason: null,
+          },
+        ],
+      };
+      subscriber.next(`data: ${JSON.stringify(initialChunk)}\n\n`);
+      hasEmittedChunk = true;
+
       const pushChunk = (payload: Record<string, unknown>): void => {
-        hasEmittedChunk = true;
         subscriber.next(`data: ${JSON.stringify(payload)}\n\n`);
       };
 
@@ -990,10 +1005,17 @@ export class ProxyService {
             const candidate = json.candidates?.[0];
             const parts = candidate?.content?.parts || [];
 
+            if (json.usageMetadata) {
+              lastUsageMetadata = json.usageMetadata;
+            }
+
             for (const part of parts) {
               if (part.thought && part.text) {
-                // Reasoning/thinking parts: emit via reasoning_content delta field
-                // so clients that support it can display thinking separately.
+                let textToEmit = part.text;
+                if (!isThinking) {
+                  isThinking = true;
+                  textToEmit = `<think>\n${textToEmit}`;
+                }
                 const reasoningChunk = {
                   id: streamId,
                   object: 'chat.completion.chunk',
@@ -1002,7 +1024,7 @@ export class ProxyService {
                   choices: [
                     {
                       index: 0,
-                      delta: { reasoning_content: part.text },
+                      delta: { content: textToEmit },
                       finish_reason: null,
                     },
                   ],
@@ -1013,7 +1035,11 @@ export class ProxyService {
 
               if (part.functionCall) {
                 const currentToolIndex = toolCallIndex++;
-                const toolCallChunk = {
+                const toolCallId = part.functionCall.id || `${part.functionCall.name}-${uuidv4()}`;
+                const argsJson = JSON.stringify(part.functionCall.args || {});
+
+                // First delta: id, type, name, empty arguments
+                pushChunk({
                   id: streamId,
                   object: 'chat.completion.chunk',
                   created: created,
@@ -1025,11 +1051,11 @@ export class ProxyService {
                         tool_calls: [
                           {
                             index: currentToolIndex,
-                            id: part.functionCall.id || `${part.functionCall.name}-${uuidv4()}`,
+                            id: toolCallId,
                             type: 'function',
                             function: {
                               name: part.functionCall.name,
-                              arguments: JSON.stringify(part.functionCall.args || {}),
+                              arguments: '',
                             },
                           },
                         ],
@@ -1037,8 +1063,35 @@ export class ProxyService {
                       finish_reason: null,
                     },
                   ],
-                };
-                pushChunk(toolCallChunk);
+                });
+
+                // Subsequent deltas: only arguments (split if large to respect SSE framing)
+                const ARG_CHUNK_SIZE = 1000;
+                for (let i = 0; i < argsJson.length; i += ARG_CHUNK_SIZE) {
+                  const slice = argsJson.slice(i, i + ARG_CHUNK_SIZE);
+                  pushChunk({
+                    id: streamId,
+                    object: 'chat.completion.chunk',
+                    created: created,
+                    model: model,
+                    choices: [
+                      {
+                        index: 0,
+                        delta: {
+                          tool_calls: [
+                            {
+                              index: currentToolIndex,
+                              function: {
+                                arguments: slice,
+                              },
+                            },
+                          ],
+                        },
+                        finish_reason: null,
+                      },
+                    ],
+                  });
+                }
                 continue;
               }
 
@@ -1064,6 +1117,11 @@ export class ProxyService {
               }
 
               if (part.text) {
+                let textToEmit = part.text;
+                if (isThinking && !part.thought) {
+                  isThinking = false;
+                  textToEmit = `\n</think>\n\n${textToEmit}`;
+                }
                 const contentChunk = {
                   id: streamId,
                   object: 'chat.completion.chunk',
@@ -1072,7 +1130,7 @@ export class ProxyService {
                   choices: [
                     {
                       index: 0,
-                      delta: { content: part.text },
+                      delta: { content: textToEmit },
                       finish_reason: null,
                     },
                   ],
@@ -1082,13 +1140,23 @@ export class ProxyService {
             }
 
             if (candidate?.finishReason) {
-              // Per the OpenAI spec, finish_reason must be "tool_calls" when the
-              // response contains function calls. Gemini always sends "STOP" even
-              // for tool call responses, so we infer from toolCallIndex.
-              const mappedFinishReason =
-                toolCallIndex > 0
-                  ? 'tool_calls'
-                  : this.mapGeminiFinishReasonToOpenAIFinishReason(candidate.finishReason);
+              if (isThinking) {
+                isThinking = false;
+                const closingChunk = {
+                  id: streamId,
+                  object: 'chat.completion.chunk',
+                  created: created,
+                  model: model,
+                  choices: [
+                    {
+                      index: 0,
+                      delta: { content: '\n</think>\n\n' },
+                      finish_reason: null,
+                    },
+                  ],
+                };
+                pushChunk(closingChunk);
+              }
 
               const finishChunk = {
                 id: streamId,
@@ -1099,7 +1167,9 @@ export class ProxyService {
                   {
                     index: 0,
                     delta: {},
-                    finish_reason: mappedFinishReason,
+                    finish_reason: this.mapGeminiFinishReasonToOpenAIFinishReason(
+                      candidate.finishReason,
+                    ),
                   },
                 ],
               };
@@ -1109,7 +1179,7 @@ export class ProxyService {
               subscriber.complete();
             }
           } catch {
-            // ignore parse errors on individual SSE lines
+            // ignore parse errors
           }
         }
       });
@@ -1130,6 +1200,23 @@ export class ProxyService {
             ],
           });
         }
+        if (streamOptions?.include_usage && lastUsageMetadata) {
+          const usageChunk = {
+            id: streamId,
+            object: 'chat.completion.chunk',
+            created,
+            model,
+            choices: [],
+            usage: {
+              prompt_tokens: lastUsageMetadata.promptTokenCount || 0,
+              completion_tokens: lastUsageMetadata.candidatesTokenCount || 0,
+              total_tokens:
+                (lastUsageMetadata.promptTokenCount || 0) +
+                (lastUsageMetadata.candidatesTokenCount || 0),
+            },
+          };
+          pushChunk(usageChunk);
+        }
         if (!hasSentDone) {
           subscriber.next('data: [DONE]\n\n');
           hasSentDone = true;
@@ -1137,12 +1224,17 @@ export class ProxyService {
         subscriber.complete();
       });
 
-      upstreamStream.on('error', (err: unknown) => {
-        // Convert to clean Error to avoid circular reference issues (socket objects)
+      upstreamStream.on('error', (err) => {
+        this.logger.error('OpenAI-compatible stream error:', err);
         const cleanError = err instanceof Error ? new Error(err.message) : new Error(String(err));
-        this.logger.error(`OpenAI-compatible stream error: ${cleanError.message}`);
         subscriber.error(cleanError);
       });
+
+      return () => {
+        if (typeof (upstreamStream as any).destroy === 'function') {
+          (upstreamStream as any).destroy();
+        }
+      };
     });
   }
 
@@ -1153,42 +1245,10 @@ export class ProxyService {
       const model = response.model;
       const choice = response.choices?.[0];
       const finishReason = choice?.finish_reason ?? 'stop';
-      const toolCalls = choice?.message?.tool_calls;
       const content =
         choice?.message && isString(choice.message.content) ? choice.message.content : '';
       const chunkSize = 80;
 
-      // Emit tool_call deltas first when the fallback non-streaming response contains tool calls.
-      // Without this, tool calls are silently dropped when the primary stream path fails.
-      if (toolCalls && toolCalls.length > 0) {
-        for (let tcIndex = 0; tcIndex < toolCalls.length; tcIndex++) {
-          const tc = toolCalls[tcIndex];
-          const tcChunk = {
-            id: streamId,
-            object: 'chat.completion.chunk',
-            created,
-            model,
-            choices: [
-              {
-                index: 0,
-                delta: {
-                  tool_calls: [
-                    {
-                      index: tcIndex,
-                      id: tc.id,
-                      type: tc.type,
-                      function: tc.function,
-                    },
-                  ],
-                },
-                finish_reason: null,
-              },
-            ],
-          };
-          subscriber.next(`data: ${JSON.stringify(tcChunk)}\n\n`);
-        }
-      }
-
       if (content.length === 0) {
         const finishChunk = {
           id: streamId,
@@ -1595,14 +1655,12 @@ export class ProxyService {
       object: 'chat.completion',
       created: Math.floor(Date.now() / 1000),
       model: model,
-      system_fingerprint: 'fp_gemininexus',
       choices: [
         {
           index: 0,
           message: {
             role: 'assistant',
-            // When tool_calls are present, content must be null per OpenAI spec.
-            content: toolCalls.length > 0 ? null : (finalContent || ''),
+            content: finalContent ? finalContent : toolCalls.length > 0 ? null : '',
             tool_calls: toolCalls.length > 0 ? toolCalls : undefined,
           },
           finish_reason: this.mapAnthropicStopReasonToOpenAIFinishReason(
@@ -1670,7 +1728,9 @@ export class ProxyService {
     if (error instanceof UpstreamRequestError) {
       const status = error.status;
       if (status === 401) {
-        this.logger.warn(`Upstream returned 401 for account ${accountId}; attempting token refresh`);
+        this.logger.warn(
+          `Upstream returned 401 for account ${accountId}; attempting token refresh`,
+        );
         const refreshed = await this.tokenManager.forceRefreshToken(accountId);
         if (refreshed) {
           this.logger.log(`Token refreshed successfully for account ${accountId}; retry permitted`);

src/services/GoogleAPIService.ts

@@ -848,34 +848,6 @@ export class GoogleAPIService {
   ): Promise<{ credits: number; expiryDate: string } | null> {
     try {
       const fetchOptions = this.getFetchOptions(proxyUrl);
-
-      // Try loadCodeAssist first — fetchCredits returns 404 for many accounts
-      // and loadCodeAssist provides the same paid tier credit data.
-      const discoveryVersion = resolveLocalInstalledVersion() ?? FALLBACK_VERSION;
-      const loadAssistResponse = await fetch(URLS.DAILY_LOAD_PROJECT, {
-        method: 'POST',
-        headers: buildInternalApiHeaders(accessToken),
-        body: JSON.stringify({
-          metadata: {
-            ide_type: 'ANTIGRAVITY',
-            ide_version: discoveryVersion,
-            ide_name: 'geminiNexus',
-          },
-        }),
-        signal: createTimeoutSignal(REQUEST_TIMEOUT_MS),
-        ...fetchOptions,
-      });
-
-      if (loadAssistResponse.ok) {
-        const loadAssistData = (await loadAssistResponse.json()) as LoadProjectResponse;
-        const credits = extractAiCreditsFromProjectContext(loadAssistData);
-        if (credits) {
-          return credits;
-        }
-      }
-
-      // Fallback to the legacy fetchCredits endpoint if loadCodeAssist
-      // did not return usable credit data.
       const response = await fetch(URLS.FETCH_CREDITS, {
         method: 'POST',
         headers: buildInternalApiHeaders(accessToken),
@@ -895,7 +867,34 @@ export class GoogleAPIService {
         return toAiCredits(data);
       }
 
-      return null;
+      if (response.status !== 404) {
+        return null;
+      }
+
+      // `fetchCredits` has started returning 404 for some accounts. Reuse the
+      // internal `loadCodeAssist` payload, which also exposes paid tier credits.
+      logger.warn('[GoogleAPIService] fetchCredits returned 404, falling back to loadCodeAssist');
+      const discoveryVersion = resolveLocalInstalledVersion() ?? FALLBACK_VERSION;
+      const fallbackResponse = await fetch(URLS.DAILY_LOAD_PROJECT, {
+        method: 'POST',
+        headers: buildInternalApiHeaders(accessToken),
+        body: JSON.stringify({
+          metadata: {
+            ide_type: 'ANTIGRAVITY',
+            ide_version: discoveryVersion,
+            ide_name: 'geminiNexus',
+          },
+        }),
+        signal: createTimeoutSignal(REQUEST_TIMEOUT_MS),
+        ...fetchOptions,
+      });
+
+      if (!fallbackResponse.ok) {
+        return null;
+      }
+
+      const fallbackData = (await fallbackResponse.json()) as LoadProjectResponse;
+      return extractAiCreditsFromProjectContext(fallbackData);
     } catch {
       return null;
     }

src/tests/unit/proxy-tool-streaming.test.ts

@@ -0,0 +1,173 @@
+import { describe, expect, it } from 'vitest';
+import { EventEmitter } from 'events';
+import { ProxyService } from '../../server/modules/proxy/proxy.service';
+import { Observable } from 'rxjs';
+
+// Subclass to access private method
+class TestableProxyService extends ProxyService {
+  constructor() {
+    super({} as any, {} as any);
+  }
+
+  public testProcessStream(
+    stream: any,
+    model: string = 'model',
+    streamOptions?: { include_usage?: boolean },
+  ): Observable<string> {
+    return (this as any).processStreamResponse(stream, model, streamOptions);
+  }
+}
+
+function parseSseChunk(raw: string): Record<string, unknown> {
+  const lines = raw.split('\n').filter((l) => l.trim().startsWith('data: '));
+  if (lines.length === 0) return {};
+  const payload = lines[0].slice(6).trim();
+  try {
+    return JSON.parse(payload) as Record<string, unknown>;
+  } catch {
+    return {};
+  }
+}
+
+describe('ProxyService Tool Streaming (OpenAI format)', () => {
+  it('should emit tool call deltas with id+name first, then arguments separately', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStream(stream, 'gpt-4o');
+
+    const chunks: string[] = [];
+    const done = new Promise<void>((resolve, reject) => {
+      observable.subscribe({
+        next: (chunk) => chunks.push(chunk),
+        error: reject,
+        complete: resolve,
+      });
+    });
+
+    const payload = JSON.stringify({
+      candidates: [
+        {
+          content: {
+            parts: [
+              { functionCall: { id: 'call_123', name: 'get_weather', args: { location: 'NYC' } } },
+            ],
+          },
+          finishReason: 'STOP',
+        },
+      ],
+    });
+
+    stream.emit('data', Buffer.from(`data: ${payload}\n`));
+    stream.emit('end');
+
+    await done;
+
+    const toolCallChunks = chunks.filter((c) => c.includes('"tool_calls"'));
+    expect(toolCallChunks.length).toBeGreaterThanOrEqual(2);
+
+    const first = parseSseChunk(toolCallChunks[0]);
+    const firstDeltas = (first.choices as any)?.[0]?.delta?.tool_calls as any[];
+    expect(firstDeltas).toBeDefined();
+    expect(firstDeltas[0].index).toBe(0);
+    expect(firstDeltas[0].id).toBe('call_123');
+    expect(firstDeltas[0].type).toBe('function');
+    expect(firstDeltas[0].function.name).toBe('get_weather');
+    expect(firstDeltas[0].function.arguments).toBe('');
+
+    const second = parseSseChunk(toolCallChunks[1]);
+    const secondDeltas = (second.choices as any)?.[0]?.delta?.tool_calls as any[];
+    expect(secondDeltas).toBeDefined();
+    expect(secondDeltas[0].index).toBe(0);
+    expect(secondDeltas[0].function.arguments).toBe('{"location":"NYC"}');
+    // Subsequent deltas must NOT repeat id/type/name to keep strict clients happy
+    expect(secondDeltas[0].id).toBeUndefined();
+    expect(secondDeltas[0].type).toBeUndefined();
+    expect(secondDeltas[0].function.name).toBeUndefined();
+  });
+
+  it('should split large tool arguments into multiple argument deltas', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStream(stream, 'gpt-4o');
+
+    const chunks: string[] = [];
+    const done = new Promise<void>((resolve, reject) => {
+      observable.subscribe({
+        next: (chunk) => chunks.push(chunk),
+        error: reject,
+        complete: resolve,
+      });
+    });
+
+    const bigArgs = { code: 'a'.repeat(5000) };
+    const payload = JSON.stringify({
+      candidates: [
+        {
+          content: {
+            parts: [{ functionCall: { id: 'call_456', name: 'write_file', args: bigArgs } }],
+          },
+          finishReason: 'STOP',
+        },
+      ],
+    });
+
+    stream.emit('data', Buffer.from(`data: ${payload}\n`));
+    stream.emit('end');
+
+    await done;
+
+    const toolCallChunks = chunks.filter((c) => c.includes('"tool_calls"'));
+    // At least: 1st (id+name) + one or more argument deltas
+    expect(toolCallChunks.length).toBeGreaterThanOrEqual(2);
+
+    const first = parseSseChunk(toolCallChunks[0]);
+    expect((first.choices as any)[0].delta.tool_calls[0].function.arguments).toBe('');
+
+    // Concatenate all argument deltas
+    let argsConcat = '';
+    for (let i = 1; i < toolCallChunks.length; i++) {
+      const parsed = parseSseChunk(toolCallChunks[i]);
+      const argDelta = (parsed.choices as any)?.[0]?.delta?.tool_calls?.[0]?.function?.arguments;
+      if (typeof argDelta === 'string') {
+        argsConcat += argDelta;
+      }
+    }
+    expect(argsConcat).toBe(JSON.stringify(bigArgs));
+  });
+
+  it('should not break normal text streaming when no tools are present', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStream(stream, 'gpt-4o');
+
+    const chunks: string[] = [];
+    const done = new Promise<void>((resolve, reject) => {
+      observable.subscribe({
+        next: (chunk) => chunks.push(chunk),
+        error: reject,
+        complete: resolve,
+      });
+    });
+
+    const payload = JSON.stringify({
+      candidates: [
+        {
+          content: {
+            parts: [{ text: 'hello world' }],
+          },
+          finishReason: 'STOP',
+        },
+      ],
+    });
+
+    stream.emit('data', Buffer.from(`data: ${payload}\n`));
+    stream.emit('end');
+
+    await done;
+
+    const output = chunks.join('');
+    expect(output).toContain('"content":"hello world"');
+    expect(output).toContain('data: [DONE]');
+    expect(output).not.toContain('"tool_calls"');
+  });
+});