Troubleshooting stream issue by hh54188 · Pull Request #10 · hh54188/ai-assistant-chrome-extension

hh54188 · 2025-09-25T00:20:12Z

No description provided.

- Added a new method `streamGeminiFake` to simulate chunked streaming responses for debugging purposes, allowing developers to test without actual API calls. - Updated the chat route to include a `useFakeStream` parameter, enabling the use of the fake stream when requested. - Adjusted the chat service to pass the `useFakeStream` flag, facilitating easier debugging of streaming interactions.

…package-lock.json

…ilotApp

…g functionality - Updated the App component to render CopilotApp instead of ChatListTroubleshooting. - Modified CopilotSidebar to include onFirstChunk callback for improved message status handling during streaming. - Adjusted chatService to support onFirstChunk callback, ensuring accurate status updates when the first chunk of data is received.

gemini-code-assist · 2025-09-25T00:20:31Z

Summary of Changes

Hello @hh54188, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a robust fake streaming mechanism for Gemini AI responses, primarily aimed at enhancing debugging capabilities for streaming-related issues without incurring API costs. It integrates this fake stream into the backend API, updates the frontend to better reflect streaming states, and provides extensive documentation and test scripts for its usage. Additionally, it includes a minor dependency update and a new UI component for chat list troubleshooting.

Highlights

Fake Stream Implementation: A new streamGeminiFake method has been added to aiService.js to simulate Gemini streaming responses for debugging purposes, complete with configurable delays, chunking, and tool call simulation.
API Integration for Debugging: The backend's /api/chat/stream endpoint now accepts a useFakeStream parameter, allowing developers to easily switch to the fake Gemini stream for testing without hitting actual AI APIs.
Enhanced Frontend Streaming Status: The CopilotSidebar.jsx component now utilizes an onFirstChunk callback to update the UI message status to 'streaming' as soon as the initial data chunk is received, improving user experience by providing immediate feedback.
Comprehensive Debugging Tools & Documentation: New example usage scripts (example-fake-stream-usage.js, test-fake-stream.js, test-fake-stream-api.js) and a detailed FAKE_STREAM_DEBUG_README.md have been introduced to guide developers on effectively using and customizing the fake streaming feature.
Dependency Update: The @ant-design/x dependency in the Chrome extension has been updated from version ^1.4.0 to ^1.6.1.
Chat List Troubleshooting Component: A new ChatListTroubleshooting.jsx component and ChatListTest.jsx have been added to the Chrome extension's proof-of-concept section, providing a dedicated environment for testing and debugging the chat list UI's streaming behavior.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request introduces a valuable fake streaming mechanism for debugging Gemini API responses, which is a great addition for development and troubleshooting. The implementation spans the backend and frontend, including new test scripts and documentation. The frontend also sees a nice UX improvement with the onFirstChunk callback to better indicate streaming activity. My review includes a few suggestions to enhance the new code, such as fixing an incorrect import path, making console.log statements conditional to keep logs clean, removing some leftover debugging code, and correcting commands in the new documentation. Overall, this is a solid contribution that will improve the development workflow.

gemini-code-assist · 2025-09-25T00:22:36Z

backend/tests/test-fake-stream.js

+ * This helps debug streaming response issues without making real API calls
+ */
+
+import aiService from './services/aiService.js';


The import path './services/aiService.js' is relative to the current working directory, which makes the script fragile. It's better to use a path relative to the file's location to ensure it works regardless of where it's executed from.

Suggested change

import aiService from './services/aiService.js';

import aiService from '../services/aiService.js';

gemini-code-assist · 2025-09-25T00:22:36Z

backend/example-fake-stream-usage.js

+    console.log('─'.repeat(60));
+    console.log(`Total chunks: ${chunkCount}`);
+    console.log(`Total length: ${totalLength} characters`);
+    console.log(`Average chunk size: ${Math.round(totalLength / chunkCount)} characters`);


There's a potential division by zero error here if chunkCount is 0, which would happen if the stream is empty. It's good practice to add a guard to prevent this.

Suggested change

console.log(`Average chunk size: ${Math.round(totalLength / chunkCount)} characters`);

console.log(`Average chunk size: ${chunkCount > 0 ? Math.round(totalLength / chunkCount) : 0} characters`);

gemini-code-assist · 2025-09-25T00:22:36Z

backend/services/aiService.js

+        console.log('🔧 Using FAKE Gemini stream for debugging');
+        console.log('Message:', message);
+        console.log('Model:', model);
+        console.log('Session ID:', sessionId);
+        console.log('Files:', files);
+        console.log('Use MCP Tools:', useMCPTools);


These console.log statements are useful for debugging but can create a lot of noise if this code is ever used in a staging or production environment. It's a good practice to wrap them in a condition that checks for a development environment, like if (process.env.NODE_ENV === 'development') { ... }.

gemini-code-assist · 2025-09-25T00:22:36Z

backend/services/aiService.js

+                    timestamp: new Date().toISOString()
+                };
+
+                console.log(`📦 Chunk ${i + 1}/${chunks.length}: "${chunks[i].trim()}"`);


This log inside the generator loop can be very verbose. Consider making it conditional, for example, by wrapping it in an if (process.env.NODE_ENV === 'development') block, to avoid cluttering logs in other environments.

gemini-code-assist · 2025-09-25T00:22:36Z

backend/tests/test-fake-stream-api.js

+        const response = await fetch(`${API_BASE_URL}/api/chat/test`);
+        if (response.ok) {
+            console.log('✅ Server is running');
+            return true;
+        }


The checkServer function is missing a return false in the if block, which means it will implicitly return undefined if the server is running but the /api/chat/test endpoint returns a non-OK status. It's better to explicitly return false in that case.

const response = await fetch(`${API_BASE_URL}/api/chat/test`); if (response.ok) { console.log('✅ Server is running'); return true; } return false;

gemini-code-assist · 2025-09-25T00:22:36Z

chrome-extension/src/App.jsx

 import ComponentHandleStream from './proof-of-concept/ComponentHandleStream';
 import StorageDemo from './proof-of-concept/StorageDemo';
 import ScreenCaptureTest from './proof-of-concept/ScreenCaptureTest';
+import ChatListTroubleshooting from './proof-of-concept/ChatListTroubleshooting';


The ChatListTroubleshooting component is imported but not used. This unused import should be removed to keep the code clean.

gemini-code-assist · 2025-09-25T00:22:36Z

chrome-extension/src/components/ChatListTest.jsx

+    const loadingMessage = messages.find(message => message.status === 'loading');
+    console.log(loadingMessage?.message?.content);


This console.log statement appears to be for debugging. It should be removed to avoid cluttering the browser console.

gemini-code-assist · 2025-09-25T00:22:36Z

chrome-extension/src/components/ChatListTest.jsx

+                        // loading: i.status === 'loading',
+                        // typing: i.status === 'loading' ? { step: 5, interval: 20, suffix: <>💗</> } : false,


This code is commented out. If it's no longer needed, it should be removed to improve code clarity.

gemini-code-assist · 2025-09-25T00:22:37Z

chrome-extension/src/proof-of-concept/ChatListTroubleshooting.jsx

+                // Reset to start over
+                currentIndex = 0;
+            }
+        }, 100); // Update every 500ms


The comment indicates an update interval of 500ms, but the code uses 100ms. The comment should be updated to match the code for accuracy.

Suggested change

}, 100); // Update every 500ms

}, 100); // Update every 100ms

gemini-code-assist · 2025-09-25T00:22:37Z

docs/features/FAKE_STREAM_DEBUG_README.md

+#### Test Direct Method
+```bash
+cd backend
+node test-fake-stream.js
+```
+
+#### Test API Endpoint
+```bash
+cd backend
+node test-fake-stream-api.js
+```


The commands for running the test scripts are incorrect because the scripts are located in the tests/ subdirectory. The paths should be updated to reflect their correct location.

Suggested change

#### Test Direct Method

```bash

cd backend

node test-fake-stream.js

```

#### Test API Endpoint

```bash

cd backend

node test-fake-stream-api.js

```

#### Test Direct Method

```bash

cd backend

node tests/test-fake-stream.js

Test API Endpoint

cd backend node tests/test-fake-stream-api.js

github-actions · 2025-09-25T01:14:43Z

DOCS_SYNC: docs/troubleshooting-stream-issue

Updated docs for fake stream debugging. Compare and open PR:
master...docs/troubleshooting-stream-issue

hh54188 and others added 4 commits September 23, 2025 10:02

Update @ant-design/x dependency to version 1.6.1 in package.json and …

75094e4

…package-lock.json

Update App component to render ChatListTroubleshooting instead of Cop…

b90637a

…ilotApp

gemini-code-assist bot reviewed Sep 25, 2025

View reviewed changes

hh54188 merged commit b0d04d9 into master Sep 25, 2025
3 checks passed

	import aiService from './services/aiService.js';
	import aiService from '../services/aiService.js';

	console.log(`Average chunk size: ${Math.round(totalLength / chunkCount)} characters`);
	console.log(`Average chunk size: ${chunkCount > 0 ? Math.round(totalLength / chunkCount) : 0} characters`);

		const loadingMessage = messages.find(message => message.status === 'loading');
		console.log(loadingMessage?.message?.content);

		// loading: i.status === 'loading',
		// typing: i.status === 'loading' ? { step: 5, interval: 20, suffix: <>💗</> } : false,

	}, 100); // Update every 500ms
	}, 100); // Update every 100ms

Conversation

hh54188 commented Sep 25, 2025

Uh oh!

gemini-code-assist bot commented Sep 25, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Sep 25, 2025

Choose a reason for hiding this comment

Test API Endpoint

Uh oh!

Uh oh!

github-actions bot commented Sep 25, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant