Support MCP( WIP) #5974
Support MCP( WIP) #5974
Conversation
|
Deployment failed with the following error: View Documentation: https://vercel.com/docs/accounts/team-members-and-roles |
WalkthroughThis pull request introduces a comprehensive implementation of the Multi-Channel Protocol (MCP) system for NextChat. The changes span multiple files, adding new functionality for managing multiple AI clients, server configurations, and a dedicated market page for MCP servers. The implementation includes client management, logging, configuration handling, and a new user interface component for exploring and configuring MCP servers. Changes
Sequence DiagramsequenceDiagram
participant User
participant McpMarketPage
participant McpActions
participant McpClient
User->>McpMarketPage: Open MCP Market
McpMarketPage->>McpActions: Get MCP Config
McpActions-->>McpMarketPage: Return Config
User->>McpMarketPage: Add New Server
McpMarketPage->>McpActions: Add MCP Server
McpActions->>McpClient: Initialize Client
McpClient-->>McpActions: Client Created
McpActions-->>McpMarketPage: Server Added
Poem
Finishing Touches
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
|
Your build has completed! |
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (9)
app/store/chat.ts (1)
429-447: Validate JSON parsing & protect against malformed message content
- The regular expression approach to identify ```json:mcp blocks is functional, but consider graceful fallbacks if the block is missing or incomplete.
- You already catch JSON parsing errors, which is good. In case of invalid JSON from user-provided data, ensuring a user-facing error response could be beneficial.
- If multiple MCP calls can happen concurrently, verify the system’s concurrency handling to avoid race conditions.
app/mcp/actions.ts (1)
1-33: Leverage stronger typing and ensure concurrency safety
- Currently,
fsClientis typed asany—consider adding an explicit interface or type to make maintenance easier and reduce accidental misuse.- When multiple calls happen in quick succession, ensure
initFileSystemClientcan safely handle simultaneous initialization requests.app/mcp/logger.ts (1)
1-60: Ensure cross-platform log compatibility
- ANSI color codes might not display as intended across all terminals (e.g., some CI/CD environments or Windows shells).
- Consider adding timestamps or structured logging for easier troubleshooting and correlation with other logs.
app/mcp/client.ts (4)
1-5: Use absolute imports selectively.Imports from the "@modelcontextprotocol" package and Zod library are fine. However, ensure that these external imports remain minimal for faster builds and better maintainability. If future code only requires submodules, consider selective imports from large packages (e.g.,
import { ... } from "@modelcontextprotocol/sdk/client").
6-10: Clarify optional fields inServerConfiginterface.Currently,
argsandenvare optional. Provide doc comments describing the scenarios in which these fields would be omitted to improve code clarity.
44-47: ValidatePrimitivestructure and values.As
Primitive.valueis typed toany, adding a Zod schema or another validation layer for resource, tool, or prompt objects can improve type safety and help catch unexpected data structures from the server.
83-87: Use structured logging for request execution.Currently, you only do
console.log(r)after executing the request. Consider usinglogger.infoor a more structured approach to log request/response pairs for debugging and auditing.... const r = client.request(request, z.any()); - console.log(r); + logger.info("Request response:", r); return r; }tsconfig.json (1)
26-26: Cleanup references to removed files ininclude.Removing
"app/calcTextareaHeight.ts"from theincludearray is fine. Ensure that all references (e.g., imports) to that file are also removed throughout the codebase to avoid confusion.package.json (1)
25-25: Leverage the@modelcontextprotocol/sdkdependency effectively.Ensure that all relevant modules from the new SDK are utilized. If only a small subset is needed, consider partial imports or code splitting to reduce bundle size.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
yarn.lockis excluded by!**/yarn.lock,!**/*.lock
📒 Files selected for processing (9)
app/mcp/actions.ts(1 hunks)app/mcp/client.ts(1 hunks)app/mcp/example.ts(1 hunks)app/mcp/logger.ts(1 hunks)app/mcp/mcp_config.ts(1 hunks)app/store/chat.ts(2 hunks)next.config.mjs(3 hunks)package.json(2 hunks)tsconfig.json(2 hunks)
🔇 Additional comments (8)
app/store/chat.ts (1)
32-32: Add test coverage for 'executeMcpAction' usage
The new import integrates MCP action processing into the chat flow. To reduce the risk of unhandled edge cases (e.g., unavailable server, invalid JSON structures, etc.), please ensure the code path invoking executeMcpAction is tested thoroughly.
app/mcp/mcp_config.ts (1)
1-40: Secure storage of credentials and externalize paths
- The placeholders for API keys and tokens should never be replaced by real secrets in the repository; instead, reading from environment variables or a vault is recommended.
- The path
"/Users/kadxy/Desktop"is hard-coded. Consider making this path configurable for different environments.
app/mcp/example.ts (1)
1-92: Harden the file reading mechanism
- The code showcases reading arbitrary files from a specified path. Confirm that server-side controls or directory whitelisting is in place to guard against unauthorized access.
- Good job using Zod schemas for validation—this helps ensure the integrity of server responses.
app/mcp/client.ts (1)
49-81: Parallel asynchronous operations are well handled; keep an eye on performance.
The approach of collecting promises in an array and awaiting them simultaneously is a good practice. For large-scale data, ensure the server handles concurrent calls effectively to avoid resource contention or throttling.
next.config.mjs (2)
35-35: Ensure experimental features are stable enough for production.
serverActions: true is an experimental feature. Confirm that your production environment accepts potential breaking changes or instabilities. Consider adding a feature gate or fallback logic.
75-78: Maintain consistent pattern for rewrite placeholders.
Rewrite placeholders, such as :resource_name and :deploy_name, are used in the destination URL. Confirm that you handle all edge cases (like missing or invalid resource_name / deploy_name). Potentially add server-side validation to avoid runtime errors.
tsconfig.json (1)
3-3: Check compatibility of ES2022 target.
Confirm that your deployment environment supports ES2022 features, or use a transpilation step if targeting older browsers. Some hosting platforms may not yet fully support ES2022 natively.
package.json (1)
57-58: Check versions & synergy for zod and zustand.
zod is now widely used for schema validation. Keep an eye on potential conflicts when using zustand for state management if any store-based validations are needed.
app/mcp/client.ts
Outdated
| export async function createClient( | ||
| serverConfig: ServerConfig, | ||
| name: string, | ||
| ): Promise<Client> { | ||
| logger.info(`Creating client for server ${name}`); | ||
|
|
||
| const transport = new StdioClientTransport({ | ||
| command: serverConfig.command, | ||
| args: serverConfig.args, | ||
| env: serverConfig.env, | ||
| }); | ||
| const client = new Client( | ||
| { | ||
| name: `nextchat-mcp-client-${name}`, | ||
| version: "1.0.0", | ||
| }, | ||
| { | ||
| capabilities: { | ||
| roots: { | ||
| // listChanged indicates whether the client will emit notifications when the list of roots changes. | ||
| // listChanged 指示客户端在根列表更改时是否发出通知。 | ||
| listChanged: true, | ||
| }, | ||
| }, | ||
| }, | ||
| ); | ||
| await client.connect(transport); | ||
| return client; | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Consider robust error handling for client creation.
When creating the client and connecting to the transport (line 40), include error handling for potential failures (e.g., invalid command, environment issues). This ensures unexpected errors are caught gracefully.
...
await client.connect(transport);
+ // TODO: Consider wrapping this in try/catch:
+ // try {
+ // await client.connect(transport);
+ // } catch (err) {
+ // logger.error('Failed to connect to transport', err);
+ // throw err;
+ // }
return client;
}Committable suggestion skipped: line range outside the PR's diff.
| @@ -49,11 +50,12 @@ | |||
| "remark-breaks": "^3.0.2", | |||
| "remark-gfm": "^3.0.1", | |||
| "remark-math": "^5.1.1", | |||
| "rt-client": "https://github.com/Azure-Samples/aoai-realtime-audio-sdk/releases/download/js/v0.5.0/rt-client-0.5.0.tgz", | |||
There was a problem hiding this comment.
💡 Codebase verification
Warning: The rt-client dependency is actively used and cannot be removed
The rt-client package is an essential dependency that is actively used in the realtime chat functionality:
- It's imported and used extensively in
app/components/realtime-chat/realtime-chat.tsx - Core functionalities depend on it:
- Real-time audio streaming and processing
- Voice chat features
- Server communication for real-time responses
- Audio transcription and playback
Removing this dependency would break the real-time chat feature. The package should be kept unless there's a planned replacement or the real-time chat functionality is being removed.
🔗 Analysis chain
Confirm removal of the deprecated rt-client dependency.
Verify that no modules still rely on rt-client. Skipping this verification might lead to runtime errors if references remain.
Let me gather more information about the actual usage of rt-client in the code.
Let me check the actual usage in the realtime-chat.tsx file to understand if this is an active dependency.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Searching for references to rt-client in the codebase:
rg 'rt-client' -A 3 -B 3
Length of output: 2671
Script:
#!/bin/bash
# Check for imports and actual usage of rt-client in the realtime components
ast-grep --pattern 'import { $$$ } from "rt-client"'
# Check for any direct usage of rt-client package
rg -l 'new RTClient|RTClient\.'
Length of output: 675
Script:
#!/bin/bash
# Check the implementation in realtime-chat.tsx
cat app/components/realtime-chat/realtime-chat.tsx
Length of output: 10998
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (12)
app/mcp/actions.ts (3)
7-17: Global variables and maps
Storing clients in a globalMapand a globalinitializedflag may be problematic in multi-instance or serverless environments. Consider a more robust design (e.g., an initialization manager) if concurrency or horizontal scaling are required.
18-51: initializeMcpClients function
- Code loops over
conf.mcpServersand initializes each client with proper logging.- Catches errors and tracks failed clients in
errorClients.- Marks
initialized = trueto prevent reinitialization.- Logs final status and available clients.
This flow is user-friendly and understandable. Consider adding retries or fallback logic for partial initialization failures.
53-70: executeMcpAction function
- Fetches the client from
clientsMapby ID and executes the request.- Logs any execution errors and rethrows them.
Consider returning a standardized error object for better client-side handling, especially if this function may be extended for user-facing error messages in the future.app/store/chat.ts (2)
363-367: MCP check on new messages
Line 366 callscheckMcpJsonwhenever a new message arrives. This integration ensures automatic detection of MCP requests without additional code in the message pipeline. Be sure to handle potential performance impacts if message volume is very high.
773-798: checkMcpJson function
- Validates if message content matches MCP JSON format.
- On success, extracts the MCP payload and invokes
executeMcpAction.- Uses
onUserInputto feed back results as a new message.
This is a clean, modular approach. However, watch for large JSON payloads or malicious content. Consider adding rate-limits or size checks for production.app/mcp/utils.ts (2)
1-3: isMcpJson function
Returns the match result of a regex. This function is concise but slightly at risk of returning null or array. Consider returning a boolean explicitly (!!content.match(...)) if you only need a truthy check.
5-11: extractMcpJson function
CapturesclientIdand parses JSON from the second capture group. The approach is straightforward. A try-catch block for JSON parsing (or an upfront validity check) might guard against syntax errors or maliciously malformed JSON.app/page.tsx (1)
9-10: Await MCP initialization
Blocking initialization ensures MCP dependencies are ready before UI rendering. Ensure that this call won’t degrade page responsiveness for users if the initialization is slow. Consider deferring or parallelizing if needed.app/mcp/logger.ts (1)
24-65: Logging methods
- Provides functions for info, success, error, warn, and debug with consistent output formatting.
debugis controlled by a flag to prevent noisy logs.- A structured
formatMessagemethod safely handles objects.
Well-structured, though consider a fallback or custom transport in production to integrate with external logging systems (e.g., Winston, Bunyan).app/mcp/client.ts (3)
32-35: Document or remove commented capabilities configuration.The commented capabilities configuration lacks explanation. Either document why it's preserved for future use or remove it if unnecessary.
28-28: Consider extracting version to a configuration constant.The hardcoded version "1.0.0" should be moved to a configuration constant for better maintainability.
+const CLIENT_VERSION = "1.0.0"; export async function createClient( serverConfig: ServerConfig, name: string, ): Promise<Client> { // ... const client = new Client( { name: `nextchat-mcp-client-${name}`, - version: "1.0.0", + version: CLIENT_VERSION, }, // ... );
52-76: Refactor duplicate promise handling pattern.The promise handling pattern is repeated for resources, tools, and prompts. Consider extracting this to a helper function.
+const createPrimitivePromise = ( + client: Client, + type: Primitive["type"], + listFn: () => Promise<{ [key: string]: any[] }> +) => { + return listFn().then((result) => { + const items = result[`${type}s`]; + items.forEach((item) => primitives.push({ type, value: item })); + }); +}; if (capabilities?.resources) { - promises.push( - client.listResources().then(({ resources }) => { - resources.forEach((item) => - primitives.push({ type: "resource", value: item }), - ); - }), - ); + promises.push(createPrimitivePromise(client, "resource", () => client.listResources())); }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
yarn.lockis excluded by!**/yarn.lock,!**/*.lock
📒 Files selected for processing (10)
.eslintignore(1 hunks)app/mcp/actions.ts(1 hunks)app/mcp/client.ts(1 hunks)app/mcp/example.ts(1 hunks)app/mcp/logger.ts(1 hunks)app/mcp/mcp_config.json(1 hunks)app/mcp/utils.ts(1 hunks)app/page.tsx(1 hunks)app/store/chat.ts(4 hunks)package.json(3 hunks)
✅ Files skipped from review due to trivial changes (2)
- .eslintignore
- app/mcp/mcp_config.json
🚧 Files skipped from review as they are similar to previous changes (2)
- app/mcp/example.ts
- package.json
🔇 Additional comments (10)
app/mcp/actions.ts (3)
1-2: Use of "use server" directive
These lines establish a server-only execution context. Be mindful of referencing browser-specific APIs in server files to avoid runtime errors.
3-6: Import dependencies
Imports for createClient, executeRequest, MCPClientLogger, and the JSON config look consistent with the intended usage. Ensure that underlying modules handle errors gracefully.
72-77: getAvailableClients function
Filters out clients that failed to initialize. This is straightforward and aligns with the error management strategy. Ensure future expansions remain in sync (e.g., re-checking previously error-prone clients).
app/store/chat.ts (2)
32-33: New MCP imports
Imports from mcp/actions and mcp/utils introduce the MCP functionality into the chat store. This is a logical location given the store’s role in handling messages.
434-434: Asynchronous onFinish callback
This line suggests the onFinish callback is asynchronous. Confirm that all references to onFinish handle promises and potential errors correctly to avoid unhandled promise rejections.
app/page.tsx (1)
4-4: Import initializeMcpClients
This sets up a new dependency on actions.ts. Verify that all required environment variables and config references are available at runtime.
app/mcp/logger.ts (2)
1-10: Color codes definition
Defines ANSI codes for styling the log output. Straightforward and correct for Node.js environments.
12-22: Logger constructor and fields
The prefix and debugMode options provide flexible logging. This is a neat approach for customizing logs.
app/mcp/client.ts (2)
1-10: LGTM! Well-structured imports and interface definition.
The ServerConfig interface is well-designed with appropriate optional parameters for args and env configuration.
14-40: Add error handling for client creation and connection.
The client creation process should include proper error handling for transport creation and connection failures.
app/mcp/client.ts
Outdated
|
|
||
| interface Primitive { | ||
| type: "resource" | "tool" | "prompt"; | ||
| value: any; |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Replace 'any' type with a more specific type.
Using 'any' type reduces type safety. Consider defining specific types for resource, tool, and prompt values.
app/mcp/client.ts
Outdated
| /** Execute a request */ | ||
| export async function executeRequest(client: Client, request: any) { | ||
| return client.request(request, z.any()); | ||
| } |
There was a problem hiding this comment.
Improve request validation and error handling.
The current implementation has several concerns:
- Using
z.any()bypasses the benefits of Zod's type validation - No request validation before execution
- No error handling for failed requests
Consider implementing proper validation and error handling:
-export async function executeRequest(client: Client, request: any) {
- return client.request(request, z.any());
+export async function executeRequest(client: Client, request: unknown) {
+ const requestSchema = z.object({
+ // Define your request schema here
+ // Example:
+ // method: z.string(),
+ // params: z.record(z.unknown())
+ });
+
+ try {
+ const validatedRequest = requestSchema.parse(request);
+ return await client.request(validatedRequest, z.unknown());
+ } catch (error) {
+ if (error instanceof z.ZodError) {
+ throw new Error(`Invalid request format: ${error.message}`);
+ }
+ throw error;
+ }
+}Committable suggestion skipped: line range outside the PR's diff.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (6)
app/store/chat.ts (2)
Line range hint
376-402: Enhance type safety in onUserInput function.The function could benefit from improved type safety:
- The
isMcpResponseparameter should have a default value since it's optional- The content type assertion should be more explicit
Consider applying these changes:
async onUserInput( content: string, attachImages?: string[], - isMcpResponse?: boolean, + isMcpResponse: boolean = false, ) { const session = get().currentSession(); const modelConfig = session.mask.modelConfig; - let mContent: string | MultimodalContent[] = isMcpResponse + let mContent: string | MultimodalContent[] = isMcpResponse === true ? content : fillTemplateWith(content, modelConfig);
782-810: Enhance error handling and maintainability in checkMcpJson.Consider the following improvements:
- Add specific error type handling
- Add debug logging for the response formatting
- Extract JSON response formatting to a separate function
Consider applying these changes:
checkMcpJson(message: ChatMessage) { const content = getMessageTextContent(message); if (isMcpJson(content)) { try { const mcpRequest = extractMcpJson(content); if (mcpRequest) { console.debug("[MCP Request]", mcpRequest); executeMcpAction(mcpRequest.clientId, mcpRequest.mcp) .then((result) => { console.log("[MCP Response]", result); - const mcpResponse = - typeof result === "object" - ? JSON.stringify(result) - : String(result); + const mcpResponse = formatMcpResponse(result); + console.debug("[MCP Formatted Response]", mcpResponse); get().onUserInput( `\`\`\`json:mcp:${mcpRequest.clientId}\n${mcpResponse}\n\`\`\``, [], true, ); }) - .catch((error) => showToast(String(error))); + .catch((error) => { + console.error("[MCP Execution Error]", error); + showToast(error instanceof Error ? error.message : String(error)); + }); } - } catch (error) { + } catch (error: unknown) { console.error("[MCP Error]", error); + showToast("Failed to process MCP request"); } } }, + function formatMcpResponse(result: unknown): string { + return typeof result === "object" ? JSON.stringify(result) : String(result); + }app/mcp/types.ts (2)
1-2: Optional: Confirm the specification link remains stable.The comment references an external spec URL. If it’s crucial, ensure the link remains valid. If the spec is versioned, consider pinning a specific version for documentation stability.
21-32: Response interface structure is flexible and aligns well with standard JSON-RPC patterns.The
errorstructure is appropriately typed, ensuring systematic error reporting. Consider adding clearer distinction for success vs. error states if your logic requires it.app/mcp/client.ts (2)
43-46: Primitive interface uses 'any'.Using
anytype forvaluereduces type safety. Define a union or more explicit shape if the data is known.-interface Primitive { - type: "resource" | "tool" | "prompt"; - value: any; -} +interface Resource { /* shape */} +interface Tool { /* shape */} +interface Prompt { /* shape */} +type PrimitiveValue = Resource | Tool | Prompt; + +interface Primitive { + type: "resource" | "tool" | "prompt"; + value: PrimitiveValue; +}
48-80: listPrimitives merges capability checks with asynchronous calls.
- The approach is valid and merges results from multiple promises.
- Consider an early break if no capabilities exist to optimize performance in some edge cases.
- See if any concurrency issues might arise if the server is large or if many resources are loaded at once.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
app/mcp/actions.ts(1 hunks)app/mcp/client.ts(1 hunks)app/mcp/types.ts(1 hunks)app/store/chat.ts(7 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- app/mcp/actions.ts
🔇 Additional comments (14)
app/store/chat.ts (4)
Line range hint 1-37: LGTM! Import changes are well-organized.
The new imports for MCP functionality are properly structured and necessary for the implementation.
62-62: LGTM! Type extension is clean and minimal.
The addition of isMcpResponse to ChatMessage type is well-typed and follows TypeScript best practices.
368-372: LGTM! Clean integration of MCP checking.
The addition of checkMcpJson call is well-placed and maintains the existing message processing flow.
Line range hint 1-810: Verify integration with existing chat functionality.
Since this is a WIP PR adding MCP support, please ensure:
- The changes don't affect existing chat functionality
- Error states are properly propagated to the UI
- MCP responses don't break the chat history display
✅ Verification successful
Based on the verification results, I can now provide a final response:
MCP integration maintains existing chat functionality with proper error handling
The code review shows that the MCP (Message Control Protocol) integration:
-
Properly maintains existing chat functionality:
- Core message handling (
onNewMessage,onUserInput) remains intact - Message rendering and display components are unaffected
- Existing error states and UI feedback are preserved
- Core message handling (
-
Has appropriate error handling:
- MCP errors are caught and displayed via
showToast - Failed MCP actions are properly logged:
console.error("[MCP Error]", error) - Error states are propagated to the UI through existing message error flags
- MCP errors are caught and displayed via
-
Safely integrates with chat history:
- MCP responses are clearly marked with
isMcpResponseflag - Messages are properly added to chat history with correct formatting
- Template handling is properly skipped for MCP responses
- MCP responses are clearly marked with
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Check for potential regressions in chat functionality
echo "Checking for chat message handling..."
rg -A 5 "onUserInput|onNewMessage" --type ts
echo "Checking for error handling patterns..."
rg "showToast|console\.error" --type ts
echo "Checking for message display components..."
rg -A 5 "ChatMessage|renderMessage" --type tsx
Length of output: 10897
Script:
#!/bin/bash
# Let's check for message display components with proper extension
echo "Checking for message display components..."
rg -A 5 "ChatMessage|renderMessage" --type ts --type tsx
# Check for MCP-related changes
echo "Checking for MCP-related code..."
rg -A 5 "mcp|MCP" --type ts --type tsx
# Check for error handling in chat store
echo "Checking error handling in chat store..."
ast-grep --pattern 'onError(error) {
$$$
}'
Length of output: 464
Script:
#!/bin/bash
# Let's try with just ts extension first
echo "Checking for message display components..."
rg -A 5 "ChatMessage|renderMessage" ./*.ts ./app/**/*.ts
echo "Checking for MCP-related code..."
rg -A 5 "mcp|MCP" ./*.ts ./app/**/*.ts
echo "Checking error handling in chat store..."
rg -A 5 "onError.*{" ./app/store/chat.ts
# Check for message rendering components
echo "Checking message components..."
fd -e tsx . -x cat {} | rg -A 5 "ChatMessage|renderMessage"
Length of output: 23199
app/mcp/types.ts (5)
5-12: Interfaces with typed methods and flexible params are well structured.
The McpRequestMessage interface design uses a union for the id and retains flexibility in params. This is good for requests where the schema can evolve over time.
14-20: Schema validation ensures robust request handling.
Good use of Zod for optional jsonrpc and union types for id. This schema can mitigate malformed requests by typechecking at runtime.
34-47: Robust schema for JSON-RPC responses.
The optional error object’s shape is well-defined. Ensure the client code handles partial responses (e.g., result or error fields) gracefully.
49-55: Encapsulated notifications match JSON-RPC patterns.
Separating notifications into a distinct interface clarifies the difference between requests and notifications.
57-61: Notifications schema aligns with the interface.
The use of z.record(z.unknown()) for params preserves flexibility while still enforcing structural constraints.
app/mcp/client.ts (5)
1-6: Imports are consistent and descriptive.
All necessary dependencies (Client, StdioClientTransport, custom logger, and McpRequestMessage) are imported cleanly. The use of zod is appropriate for runtime type checks.
7-11: ServerConfig is concise and extendable.
Storing command, arguments, and environment variables in an interface fosters clarity. If future expansions are likely (e.g., working directories, timeouts), consider grouping them under optional sub-objects or adding additional properties.
13-14: Logger usage is straightforward.
A dedicated logger is beneficial for debugging and operational visibility. Ensure logging levels are adjustable in production environments if needed.
15-41: createClient handles basic client setup.
- Logging the server name is helpful for troubleshooting.
- Consider error handling around
client.connectin case the process fails to start or times out.
Would you like a script to search for unhandled promise rejections around connect calls and propose structured error-handling code if discovered?
82-88: 🛠️ Refactor suggestion
executeRequest returns data without intermediate validation or error handling.
Even though z.any() is used, you might want stronger type checks if the response format is critical. Also, consider how errors from client.request are caught and propagated.
export async function executeRequest(
client: Client,
request: McpRequestMessage,
) {
- return client.request(request, z.any());
+ try {
+ const response = await client.request(request, z.unknown());
+ // Potentially parse the response with the McpResponseMessageSchema
+ return McpResponseMessageSchema.parse(response);
+ } catch (err) {
+ logger.error('Failed to execute MCP request', err);
+ throw err;
+ }
}Likely invalid or redundant comment.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
app/mcp/actions.ts (1)
66-86: Enhance error handling with specific error types.The error handling could be more specific to help with debugging and user feedback.
export async function executeMcpAction( clientId: string, request: McpRequestMessage, ) { try { const client = clientsMap.get(clientId)?.client; if (!client) { - logger.error(`Client ${clientId} not found`); - return; + throw new Error(`MCP client '${clientId}' not found`); } logger.info(`Executing MCP request for ${clientId}`); return await executeRequest(client, request); } catch (error) { - logger.error(`MCP execution error: ${error}`); - throw error; + const errorMessage = error instanceof Error ? error.message : String(error); + logger.error(`MCP execution error for client '${clientId}':`, errorMessage); + throw new Error(`Failed to execute MCP action: ${errorMessage}`); } }app/store/chat.ts (1)
813-840: Enhance error handling in MCP JSON processing.The error handling could be more specific and provide better user feedback.
checkMcpJson(message: ChatMessage) { const content = getMessageTextContent(message); if (isMcpJson(content)) { try { const mcpRequest = extractMcpJson(content); if (mcpRequest) { console.debug("[MCP Request]", mcpRequest); executeMcpAction(mcpRequest.clientId, mcpRequest.mcp) .then((result) => { console.log("[MCP Response]", result); const mcpResponse = typeof result === "object" ? JSON.stringify(result) : String(result); get().onUserInput( `\`\`\`json:mcp-response:${mcpRequest.clientId}\n${mcpResponse}\n\`\`\``, [], true, ); }) - .catch((error) => showToast("MCP execution failed", error)); + .catch((error) => { + const errorMessage = error instanceof Error ? error.message : String(error); + showToast( + "MCP Execution Failed", + `Failed to execute MCP action for client '${mcpRequest.clientId}': ${errorMessage}` + ); + console.error("[MCP Execution Error]", error); + }); } } catch (error) { - console.error("[MCP Error]", error); + const errorMessage = error instanceof Error ? error.message : String(error); + console.error("[MCP Processing Error]", error); + showToast( + "MCP Processing Failed", + `Failed to process MCP message: ${errorMessage}` + ); } } }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
app/components/chat.tsx(11 hunks)app/constant.ts(1 hunks)app/mcp/actions.ts(1 hunks)app/mcp/client.ts(1 hunks)app/mcp/example.ts(1 hunks)app/store/chat.ts(11 hunks)
✅ Files skipped from review due to trivial changes (1)
- app/components/chat.tsx
🚧 Files skipped from review as they are similar to previous changes (1)
- app/mcp/example.ts
🔇 Additional comments (7)
app/constant.ts (2)
256-261: LGTM! Well-structured template for MCP primitives.The template clearly separates clientId and primitives sections with good formatting.
263-365: LGTM! Comprehensive system template with clear documentation.The template provides:
- Clear sections for tools, usage rules, and interaction flow
- Well-documented examples
- Proper markdown formatting for code blocks
app/mcp/client.ts (3)
43-46: 🛠️ Refactor suggestionReplace 'any' type with a more specific type.
The
valuefield uses theanytype which reduces type safety. Consider defining a proper type or interface.export interface Primitive { type: "resource" | "tool" | "prompt"; - value: any; + value: { + name: string; + description?: string; + parameters?: Record<string, unknown>; + }; }Likely invalid or redundant comment.
82-88: 🛠️ Refactor suggestionImprove request validation.
The function uses
z.any()which bypasses Zod's type validation benefits. Consider implementing proper validation schema.export async function executeRequest( client: Client, request: McpRequestMessage, ) { - return client.request(request, z.any()); + const responseSchema = z.object({ + // Define expected response schema + result: z.unknown(), + error: z.string().optional(), + }); + return client.request(request, responseSchema); }Likely invalid or redundant comment.
15-41:⚠️ Potential issueAdd error handling for client connection.
The client connection lacks error handling which could lead to unhandled promise rejections.
export async function createClient( serverConfig: ServerConfig, name: string, ): Promise<Client> { logger.info(`Creating client for server ${name}`); const transport = new StdioClientTransport({ command: serverConfig.command, args: serverConfig.args, env: serverConfig.env, }); const client = new Client( { name: `nextchat-mcp-client-${name}`, version: "1.0.0", }, { capabilities: { // roots: { // listChanged: true, // }, }, }, ); - await client.connect(transport); + try { + await client.connect(transport); + } catch (error) { + logger.error(`Failed to connect client ${name}:`, error); + throw new Error(`Failed to initialize MCP client ${name}: ${error.message}`); + } return client; }Likely invalid or redundant comment.
app/mcp/actions.ts (1)
28-63: LGTM! Well-implemented initialization with proper error handling.The function includes:
- Singleton pattern to prevent multiple initializations
- Comprehensive error handling
- Good logging of success and failure cases
app/store/chat.ts (1)
201-219: LGTM! Well-implemented system prompt generation.The function effectively:
- Filters relevant primitives
- Handles template replacement
- Maintains clear structure
There was a problem hiding this comment.
Actionable comments posted: 7
🧹 Nitpick comments (14)
app/constant.ts (1)
264-366: Consider enhancing the system template documentation.The template is well-structured with comprehensive documentation. Consider these improvements:
- Add version information to track template changes
- Use more realistic paths in examples (e.g.,
~/DesktoporC:\Users\username\Desktop)export const MCP_SYSTEM_TEMPLATE = ` +// Template Version: 1.0.0 You are an AI assistant with access to system tools... 5. EXAMPLE INTERACTION: User: "What files do I have on my desktop?" Assistant: "I'll check which directories I have access to. \`\`\`json:mcp:filesystem { "method": "tools/call", "params": { "name": "list_allowed_directories", "arguments": {} } } \`\`\`" User: "\`\`\`json:mcp-response:filesystem { - "directories": ["/path/to/desktop"] + "directories": ["~/Desktop"] } \`\`\`"app/mcp/actions.ts (3)
52-68: ConsolidatereinitializeMcpClientsandrestartAllClientsFunctionsThe functions
reinitializeMcpClients(lines 52-68) andrestartAllClients(lines 179-194) perform similar actions: closing clients, clearing states, and reinitializing MCP clients. To avoid code duplication and improve maintainability, consider refactoringrestartAllClientsto callreinitializeMcpClients.Apply this refactor:
export async function restartAllClients() { logger.info("Restarting all MCP clients..."); - // 清空状态 - clientsMap.clear(); - errorClients = []; - initialized = false; - - // 重新初始化 - await initializeMcpClients(); + // Delegate to reinitializeMcpClients + await reinitializeMcpClients(); return { success: errorClients.length === 0, errorClients, }; }
123-127: Improve Error Handling When Client Is Not FoundIn the
executeMcpActionfunction (lines 123-127), when a client is not found, the function logs an error but does not throw an exception or provide feedback to the caller. This could lead to silent failures. Consider throwing an error to ensure that the calling function can handle this scenario appropriately.Apply this change:
const client = clientsMap.get(clientId)?.client; if (!client) { logger.error(`Client ${clientId} not found`); - return; + throw new Error(`Client ${clientId} not found`); }
197-216: CombinegetAllClientStatusandgetClientErrorsFunctionsThe functions
getAllClientStatus(lines 197-205) andgetClientErrors(lines 208-216) both return a record of client IDs to their error messages. To reduce redundancy, consider combining these functions into one or clarifying their distinct purposes if they are intended to provide different information.app/components/mcp-market.tsx (2)
185-250: RefactorrenderConfigFormto Improve ReadabilityThe
renderConfigFormfunction (lines 181-250) handles multiple input types and contains nested loops and conditional logic, making it complex. Consider refactoring by extracting input field rendering into separate components to enhance readability and maintainability.
436-438: Handle Long Descriptions in Server InfoIn the server info section (lines 436-438), long descriptions may overflow or break the layout. Consider adding CSS styles to handle text overflow, such as ellipsis, or provide tooltips for full descriptions.
app/components/home.tsx (1)
77-83: Maintain Consistent Import OrderThe import order of
useEffectanduseState(line 5) deviates from the convention used in the rest of the file, where hooks are typically imported after other modules. Consider reorganizing the imports for consistency.app/mcp/types.ts (2)
5-61: LGTM! Well-structured message types with proper validation.The MCP message interfaces and schemas are well-defined and properly validated using Zod. The implementation follows the JSON-RPC 2.0 specification.
Consider adding:
- JSDoc comments for better IDE integration
- Examples of valid message structures
- Constants for common error codes
Example:
/** MCP request message following JSON-RPC 2.0 specification */ export interface McpRequestMessage { /** JSON-RPC version. Must be "2.0" when present */ jsonrpc?: "2.0"; // ... rest of the interface } /** Common MCP error codes */ export const McpErrorCodes = { PARSE_ERROR: -32700, INVALID_REQUEST: -32600, METHOD_NOT_FOUND: -32601, // ... add more error codes } as const;
63-99: LGTM! Well-designed server configuration types.The server configuration interfaces provide good type safety and flexibility for different server configurations.
Consider adding:
- Type guards for runtime validation
- Utility functions for configuration validation
- Constants for common server types
Example:
export const SERVER_TYPES = { FILESYSTEM: 'filesystem', DOCKER: 'docker-mcp', POSTGRES: 'postgres', // ... add more server types } as const; export type ServerType = typeof SERVER_TYPES[keyof typeof SERVER_TYPES]; export function isValidServerConfig(config: unknown): config is ServerConfig { // Add runtime validation logic }app/mcp/preset-server.json (2)
74-78: Enhance database connection securityBoth MongoDB and PostgreSQL configurations use plain connection strings. Consider:
- Supporting connection options (SSL, timeout, etc.)
- Implementing credential management
- Adding connection pooling configuration
Also applies to: 138-142
161-165: Add API configuration safeguardsFor both Brave Search and Google Maps APIs, consider adding:
- Rate limiting configuration
- Error handling guidance
- API key rotation support
Also applies to: 184-188
app/components/mcp-market.module.scss (3)
86-95: Extract status colors to CSS variablesReplace hardcoded colors with CSS variables for consistency:
- background-color: #10b981; + background-color: var(--status-success); - background-color: #ef4444; + background-color: var(--status-error); - background-color: #f59e0b; + background-color: var(--status-warning);
188-389: Reduce style duplication with mixinsConsider extracting common input styles into SCSS mixins:
- Form input styles
- Button hover/focus states
- Common transitions
574-612: Move global styles to a separate fileGlobal styles should be moved to a dedicated global stylesheet to:
- Prevent scope conflicts
- Improve maintainability
- Better separate concerns
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (2)
app/icons/mcp.svgis excluded by!**/*.svgyarn.lockis excluded by!**/yarn.lock,!**/*.lock
📒 Files selected for processing (13)
app/components/home.tsx(4 hunks)app/components/mcp-market.module.scss(1 hunks)app/components/mcp-market.tsx(1 hunks)app/components/sidebar.tsx(2 hunks)app/constant.ts(2 hunks)app/locales/cn.ts(1 hunks)app/mcp/actions.ts(1 hunks)app/mcp/mcp_config.json(1 hunks)app/mcp/preset-server.json(1 hunks)app/mcp/types.ts(1 hunks)app/mcp/utils.ts(1 hunks)app/store/chat.ts(11 hunks)next.config.mjs(2 hunks)
✅ Files skipped from review due to trivial changes (1)
- next.config.mjs
🚧 Files skipped from review as they are similar to previous changes (2)
- app/mcp/utils.ts
- app/store/chat.ts
🔇 Additional comments (11)
app/constant.ts (3)
50-50: LGTM! Path addition follows conventions.The new
McpMarketpath is well-structured and consistent with existing path definitions.
257-262: LGTM! Clean and focused template structure.The template follows the existing patterns and provides a clear structure for clientId and primitives interpolation.
257-367: LGTM! Well-integrated with existing constants.The new MCP-related constants are properly placed within the file's organization, maintaining logical grouping and following existing patterns.
app/mcp/actions.ts (1)
23-66:⚠️ Potential issueEnsure Thread-Safe Access to Shared State Variables
The module uses shared state variables (
clientsMap,initialized,errorClients) without synchronization mechanisms. If functions likeinitializeMcpClientsorreinitializeMcpClientsare called concurrently, it may lead to race conditions or inconsistent state. Consider implementing synchronization to ensure thread-safe operations.To verify concurrency issues, please review how and where these functions are invoked. If they can be called concurrently, synchronization mechanisms like mutexes or atomic variables should be introduced to protect shared state.
app/components/mcp-market.tsx (1)
253-270: Ensure Robust Error Handling When Loading PrimitivesIn the
loadPrimitivesfunction (lines 253-270), if the server is not running, an empty array is set forprimitives. Ensure that components consumingprimitivescan handle empty arrays without errors to prevent potential runtime issues.app/components/home.tsx (1)
77-83: Verify Dynamic Import Path forMcpMarketPageEnsure that the dynamic import path
'./mcp-market'(lines 77-83) correctly resolves to theMcpMarketPagecomponent. This is important for the component to load properly, especially in build and deployment environments.app/components/sidebar.tsx (1)
254-262: LGTM!The new MCP icon button is well-integrated into the sidebar, following the existing patterns for icon buttons and conditional rendering.
app/locales/cn.ts (1)
629-631: LGTM!The MCP localization entry follows the established pattern and maintains consistency with other localization entries.
app/mcp/preset-server.json (3)
11-16: Add path validation constraints for filesystem accessThe filesystem paths configuration lacks validation constraints. Consider adding:
- Path pattern restrictions
- Absolute/relative path validation
- Directory traversal prevention
35-39: Specify required GitHub token scopesThe GitHub PAT configuration should specify the minimum required scopes for security. Consider adding:
- List of required scopes in the description
- Scope validation in the implementation
199-204: Enhance Docker configuration securityThe Docker module lacks essential configuration options. Consider adding:
- Container resource limits
- Security options (e.g., no-new-privileges)
- Network access controls
app/mcp/actions.ts
Outdated
| } catch (error) { | ||
| console.error("Failed to read MCP config:", error); | ||
| return { mcpServers: {} }; | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Handle Missing Configuration File Gracefully
In the getMcpConfig function (lines 35-38), if the configuration file is missing (e.g., on the first run), it logs an error. Instead, consider checking if the error is due to the file not existing (ENOENT) and initialize with a default configuration without logging an error. This provides a smoother user experience.
Apply this change:
} catch (error) {
- console.error("Failed to read MCP config:", error);
- return { mcpServers: {} };
+ if (error.code === 'ENOENT') {
+ logger.warn("MCP config file not found, initializing with default configuration.");
+ return { mcpServers: {} };
+ } else {
+ logger.error("Failed to read MCP config:", error);
+ throw error;
+ }
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| } catch (error) { | |
| console.error("Failed to read MCP config:", error); | |
| return { mcpServers: {} }; | |
| } | |
| } catch (error) { | |
| if (error.code === 'ENOENT') { | |
| logger.warn("MCP config file not found, initializing with default configuration."); | |
| return { mcpServers: {} }; | |
| } else { | |
| logger.error("Failed to read MCP config:", error); | |
| throw error; | |
| } | |
| } |
app/components/mcp-market.tsx
Outdated
|
|
||
| try { | ||
| // 构建服务器配置 | ||
| const args = [...preset.baseArgs]; | ||
| const env: Record<string, string> = {}; | ||
|
|
There was a problem hiding this comment.
Add Null Checks for preset.configSchema Before Use
In the saveServerConfig function (lines 130-135), preset.configSchema is accessed without null checks. If preset.configSchema is undefined or null, it may cause runtime errors. Ensure that preset.configSchema is validated before accessing its properties.
Apply this change:
if (!preset || !preset.configSchema || !editingServerId) return;
+ if (!preset.configSchema) {
+ showToast("Server configuration schema is missing.");
+ return;
+ }Committable suggestion skipped: line range outside the PR's diff.
app/components/mcp-market.tsx
Outdated
| const bError = clientErrors[b.id] !== null; | ||
|
|
||
| if (aAdded !== bAdded) { | ||
| return aAdded ? -1 : 1; | ||
| } | ||
| if (aAdded && bAdded) { | ||
| if (aError !== bError) { | ||
| return aError ? -1 : 1; | ||
| } | ||
| } | ||
| return 0; | ||
| }) |
There was a problem hiding this comment.
Correct Sorting Logic for Server Error Status
In the server list sorting logic (lines 389-404), the comparison of aError and bError may be inverted, causing servers with errors to appear before those without. Adjust the sorting condition to ensure servers without errors are prioritized.
Apply this fix:
if (aAdded && bAdded) {
if (aError !== bError) {
- return aError ? -1 : 1;
+ return aError ? 1 : -1;
}
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const bError = clientErrors[b.id] !== null; | |
| if (aAdded !== bAdded) { | |
| return aAdded ? -1 : 1; | |
| } | |
| if (aAdded && bAdded) { | |
| if (aError !== bError) { | |
| return aError ? -1 : 1; | |
| } | |
| } | |
| return 0; | |
| }) | |
| const bError = clientErrors[b.id] !== null; | |
| if (aAdded !== bAdded) { | |
| return aAdded ? -1 : 1; | |
| } | |
| if (aAdded && bAdded) { | |
| if (aError !== bError) { | |
| return aError ? 1 : -1; | |
| } | |
| } | |
| return 0; | |
| }) |
app/mcp/mcp_config.json
Outdated
| { | ||
| "mcpServers": { | ||
| "filesystem": { | ||
| "command": "npx", | ||
| "args": [ | ||
| "-y", | ||
| "@modelcontextprotocol/server-filesystem", | ||
| "/Users/kadxy/Desktop" | ||
| ] | ||
| }, | ||
| "docker-mcp": { | ||
| "command": "uvx", | ||
| "args": ["docker-mcp"] | ||
| }, | ||
| "difyworkflow": { | ||
| "command": "mcp-difyworkflow-server", | ||
| "args": ["-base-url", "23"], | ||
| "env": { | ||
| "DIFY_WORKFLOW_NAME": "23", | ||
| "DIFY_API_KEYS": "23" | ||
| } | ||
| }, | ||
| "postgres": { | ||
| "command": "docker", | ||
| "args": ["run", "-i", "--rm", "mcp/postgres", null] | ||
| }, | ||
| "playwright": { | ||
| "command": "npx", | ||
| "args": ["-y", "@executeautomation/playwright-mcp-server"] | ||
| }, | ||
| "gdrive": { | ||
| "command": "npx", | ||
| "args": ["-y", "@modelcontextprotocol/server-gdrive"] | ||
| } | ||
| } | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add documentation and validation guidance.
The configuration file lacks documentation for server configurations and validation requirements.
Consider adding:
- A documentation section describing each server type and its purpose
- Required environment variables for each server
- Validation rules for configuration parameters
- Error handling guidance
Example structure:
{
"documentation": {
"version": "1.0",
"servers": {
"filesystem": {
"description": "Local filesystem MCP server",
"required_env": ["MCP_FILESYSTEM_PATH"],
"validation": {
"MCP_FILESYSTEM_PATH": "Must be a valid directory path"
}
},
// ... other servers
}
},
"mcpServers": {
// ... existing configurations
}
}
app/mcp/mcp_config.json
Outdated
| "postgres": { | ||
| "command": "docker", | ||
| "args": ["run", "-i", "--rm", "mcp/postgres", null] | ||
| }, |
There was a problem hiding this comment.
Fix null argument in postgres configuration.
The postgres server configuration contains a null argument which could cause runtime issues.
Remove the null argument or replace it with a valid value:
- "args": ["run", "-i", "--rm", "mcp/postgres", null]
+ "args": ["run", "-i", "--rm", "mcp/postgres"]📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "postgres": { | |
| "command": "docker", | |
| "args": ["run", "-i", "--rm", "mcp/postgres", null] | |
| }, | |
| "postgres": { | |
| "command": "docker", | |
| "args": ["run", "-i", "--rm", "mcp/postgres"] | |
| }, |
app/mcp/mcp_config.json
Outdated
| "difyworkflow": { | ||
| "command": "mcp-difyworkflow-server", | ||
| "args": ["-base-url", "23"], | ||
| "env": { | ||
| "DIFY_WORKFLOW_NAME": "23", | ||
| "DIFY_API_KEYS": "23" | ||
| } | ||
| }, |
There was a problem hiding this comment.
Replace placeholder values in difyworkflow configuration.
The configuration contains placeholder values "23" for base URL and API keys, which are not valid production values.
Consider using environment variables:
- "args": ["-base-url", "23"],
+ "args": ["-base-url", "${DIFY_BASE_URL}"],
"env": {
- "DIFY_WORKFLOW_NAME": "23",
- "DIFY_API_KEYS": "23"
+ "DIFY_WORKFLOW_NAME": "${DIFY_WORKFLOW_NAME}",
+ "DIFY_API_KEYS": "${DIFY_API_KEYS}"
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "difyworkflow": { | |
| "command": "mcp-difyworkflow-server", | |
| "args": ["-base-url", "23"], | |
| "env": { | |
| "DIFY_WORKFLOW_NAME": "23", | |
| "DIFY_API_KEYS": "23" | |
| } | |
| }, | |
| "difyworkflow": { | |
| "command": "mcp-difyworkflow-server", | |
| "args": ["-base-url", "${DIFY_BASE_URL}"], | |
| "env": { | |
| "DIFY_WORKFLOW_NAME": "${DIFY_WORKFLOW_NAME}", | |
| "DIFY_API_KEYS": "${DIFY_API_KEYS}" | |
| } | |
| }, |
app/mcp/mcp_config.json
Outdated
| "filesystem": { | ||
| "command": "npx", | ||
| "args": [ | ||
| "-y", | ||
| "@modelcontextprotocol/server-filesystem", | ||
| "/Users/kadxy/Desktop" | ||
| ] | ||
| }, |
There was a problem hiding this comment.
Remove hardcoded filesystem path.
The filesystem server configuration contains a hardcoded path /Users/kadxy/Desktop which will not work across different environments and could pose security risks.
Consider using environment variables or configuration parameters for the path:
- "/Users/kadxy/Desktop"
+ "${MCP_FILESYSTEM_PATH}"📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "filesystem": { | |
| "command": "npx", | |
| "args": [ | |
| "-y", | |
| "@modelcontextprotocol/server-filesystem", | |
| "/Users/kadxy/Desktop" | |
| ] | |
| }, | |
| "filesystem": { | |
| "command": "npx", | |
| "args": [ | |
| "-y", | |
| "@modelcontextprotocol/server-filesystem", | |
| "${MCP_FILESYSTEM_PATH}" | |
| ] | |
| }, |
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (1)
app/components/mcp-market.tsx (1)
640-646: 🛠️ Refactor suggestionAdd accessibility improvements to the search input.
The search input lacks proper accessibility attributes.
<input type="text" className={styles["search-bar"]} placeholder={"Search MCP Server"} autoFocus onInput={(e) => setSearchText(e.currentTarget.value)} + aria-label="Search MCP servers" + role="searchbox" + aria-describedby="search-description" /> +<span id="search-description" className="sr-only"> + Search for MCP servers by name, description, or tags +</span>
🧹 Nitpick comments (3)
app/components/mcp-market.tsx (3)
34-40: Enhance type safety of ConfigProperty interface.Consider improving type safety by:
- Making the
typefield more specific using a union type of allowed values- Adding validation for
minItemsto ensure it's positiveinterface ConfigProperty { - type: string; + type: 'string' | 'array' | 'number' | 'boolean'; description?: string; required?: boolean; - minItems?: number; + minItems?: number & { [K in number]: K extends number ? (K extends Positive ? K : never) : never }; }
43-54: Consider consolidating related state using useReducer.The component uses multiple useState hooks for related state management. Consider using useReducer to consolidate server-related states (config, status, tools) into a single reducer for better maintainability and state updates consistency.
interface ServerState { config: McpConfigData | undefined; clientStatuses: Record<string, ServerStatusResponse>; tools: ListToolsResponse["tools"] | null; isLoading: boolean; } type ServerAction = | { type: 'SET_CONFIG'; payload: McpConfigData } | { type: 'UPDATE_STATUS'; payload: { id: string; status: ServerStatusResponse } } | { type: 'SET_TOOLS'; payload: ListToolsResponse["tools"] | null } | { type: 'SET_LOADING'; payload: boolean };
285-304: Improve error handling in pauseServer function.The error handling could be more specific and informative. Consider:
- Adding error type checking
- Providing more detailed error messages
- Implementing retry logic for transient failures
try { setIsLoading(true); showToast("Stopping server..."); const newConfig = await pauseMcpServer(id); setConfig(newConfig); setClientStatuses((prev) => ({ ...prev, [id]: { status: "paused", errorMsg: null }, })); showToast("Server stopped successfully"); } catch (error) { - showToast("Failed to stop server"); - console.error(error); + const errorMessage = error instanceof Error + ? `Failed to stop server: ${error.message}` + : "Failed to stop server: Unknown error"; + logger.error(errorMessage, { serverId: id, error }); + showToast(errorMessage); } finally {
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
app/components/mcp-market.tsx(1 hunks)
🔇 Additional comments (2)
app/components/mcp-market.tsx (2)
364-373: 🛠️ Refactor suggestionAdd input validation and accessibility improvements.
The input field lacks validation and proper accessibility attributes.
<input type="text" value={value} + aria-label={`${itemLabel} ${index + 1}`} + aria-required={prop.required} placeholder={`${itemLabel} ${index + 1}`} onChange={(e) => { + const sanitizedValue = e.target.value.trim(); + if (prop.pattern && !new RegExp(prop.pattern).test(sanitizedValue)) { + showToast(`Invalid ${itemLabel} format`); + return; + } const newValue = [...currentValue] as string[]; - newValue[index] = e.target.value; + newValue[index] = sanitizedValue; setUserConfig({ ...userConfig, [key]: newValue }); }} />Likely invalid or redundant comment.
66-69: 🛠️ Refactor suggestionReplace console.error with proper error logging.
Console statements should not be used in production code. Consider implementing a proper logging service.
- console.error("Failed to load preset servers:", error); + logger.error("Failed to load preset servers:", error); showToast("Failed to load preset servers");Likely invalid or redundant comment.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
app/constant.ts (2)
258-263: Consider improving template readability.The template structure is functional but could be more maintainable.
Consider using this more structured format:
-export const MCP_TOOLS_TEMPLATE = ` -[clientId] -{{ clientId }} -[tools] -{{ tools }} -`; +export const MCP_TOOLS_TEMPLATE = ` +# Client Information +Client ID: {{ clientId }} + +# Available Tools +{{ tools }} +`;
265-380: Review and enhance the MCP system template.The template has several areas that could be improved:
- The example interaction shows Chinese text which may not be universally understood
- There are multiple exclamation marks used for emphasis which could be replaced with more professional formatting
- The error examples could be better structured
Consider these improvements:
4. INTERACTION FLOW: A. When user makes a request: - IMMEDIATELY use appropriate tool if available - DO NOT ask if user wants you to use the tool - DO NOT just describe what you could do B. After receiving tool response: - Explain results clearly - Take next appropriate action if needed C. If tools fail: - Explain the error - Try alternative approach immediately 5. EXAMPLE INTERACTION: - good example: + # Correct Example: + # List allowed directories ```json:mcp:filesystem { "method": "tools/call", "params": { "name": "list_allowed_directories", "arguments": {} } } ``` + # Write a file ```json:mcp-response:filesystem { "method": "tools/call", "params": { "name": "write_file", "arguments": { - "path": "/Users/river/dev/nextchat/test/joke.txt", - "content": "为什么数学书总是感到忧伤？因为它有太多的问题。" + "path": "/Users/example/docs/greeting.txt", + "content": "Hello, World!" } } } ``` - follwing is the wrong! mcp json example: + # Common Mistakes: + # 1. Incorrect method name ```json:mcp:filesystem { "method": "write_file", # Wrong: should be "tools/call" "params": { "path": "NextChat_Information.txt", "content": "1" } } ``` - This is wrong because the method is not tools/call. + # 2. Missing mcp prefix in code block ```{ "method": "search_repositories", "params": { "query": "2oeee" } } ``` - This is wrong because the method is not tools/call.!!!!!!!!!!! + # Correct Format Reference: - the right format is: ```json:mcp:filesystem { "method": "tools/call", "params": { "name": "search_repositories", "arguments": { "query": "2oeee" } } } ``` - please follow the format strictly ONLY use tools/call method!!!!!!!!!!! + Note: Always use the "tools/call" method and follow the format strictly.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
app/constant.ts(3 hunks)
🔇 Additional comments (3)
app/constant.ts (3)
50-50: LGTM! Path enum updated correctly.The new
McpMarketpath follows the existing naming convention and is properly formatted.
91-91: LGTM! StoreKey enum updated correctly.The new
Mcpkey follows the existing naming convention and is properly formatted.
258-380: Verify the usage of MCP constants across the codebase.Let's ensure these new constants are properly imported and used in other files.
✅ Verification successful
Constants are properly used across the codebase
The MCP constants are correctly imported and used in app/store/chat.ts with proper template substitution. No issues found with hardcoded values or inconsistent usage.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Check for imports of the new MCP constants echo "Checking imports of MCP constants..." rg -l "MCP_TOOLS_TEMPLATE|MCP_SYSTEM_TEMPLATE" --type ts --type tsx # Check for potential usages of hardcoded strings that should use these constants echo "Checking for hardcoded MCP strings that should use constants..." rg -l "tools/call" --type ts --type tsxLength of output: 385
Script:
#!/bin/bash # Find all TypeScript files including React ones echo "TypeScript files containing MCP constants:" fd -e ts -e tsx | xargs rg -l "MCP_TOOLS_TEMPLATE|MCP_SYSTEM_TEMPLATE" echo -e "\nFiles with potential hardcoded 'tools/call' usage:" fd -e ts -e tsx | xargs rg -l "tools/call" # Get context around tools/call usage to verify if they should use the constants echo -e "\nContext of tools/call usage:" fd -e ts -e tsx | xargs rg -C 3 "tools/call"Length of output: 3039
Script:
#!/bin/bash # Check how the constants are used in chat.ts echo "Usage of MCP constants in chat.ts:" rg -C 5 "MCP_.*_TEMPLATE" app/store/chat.tsLength of output: 872
There was a problem hiding this comment.
Actionable comments posted: 7
🧹 Nitpick comments (7)
app/mcp/actions.ts (2)
26-60: Consider refactoring status checks for better maintainability.The function has multiple return points and nested conditions. Consider using a single status object that's modified based on conditions, then returned at the end.
export async function getClientStatus( clientId: string, ): Promise<ServerStatusResponse> { + let status: ServerStatusResponse = { status: "undefined", errorMsg: null }; const clientData = clientsMap.get(clientId); const config = await getMcpConfigFromFile(); const serverConfig = config.mcpServers[clientId]; - if (!serverConfig) { - return { status: "undefined", errorMsg: null }; + if (serverConfig) { + if (serverConfig.status === "paused") { + status = { status: "paused", errorMsg: null }; + } else if (clientData) { + if (clientData.errorMsg) { + status = { status: "error", errorMsg: clientData.errorMsg }; + } else if (clientData.client) { + status = { status: "active", errorMsg: null }; + } else { + status = { status: "error", errorMsg: "Client not found" }; + } + } } - if (serverConfig.status === "paused") { - return { status: "paused", errorMsg: null }; - } - - if (!status) { - return { status: "undefined", errorMsg: null }; - } - - if (status.errorMsg) { - return { status: "error", errorMsg: status.errorMsg }; - } - - if (status.client) { - return { status: "active", errorMsg: null }; - } - - return { status: "error", errorMsg: "Client not found" }; + return status; }
68-72: Optimize client count calculation.The count can be calculated more efficiently using Array methods.
export async function getAvailableClientsCount() { - let count = 0; - clientsMap.forEach((map) => !map.errorMsg && count++); - return count; + return Array.from(clientsMap.values()).filter(map => !map.errorMsg).length; }app/components/mcp-market.module.scss (4)
8-14: Add ARIA attributes to loading indicator.Enhance accessibility for screen readers.
.loading-indicator { font-size: 12px; color: var(--primary); margin-left: 8px; font-weight: normal; opacity: 0.8; + &[aria-busy="true"] { + cursor: progress; + } }
30-30: Define animation duration as a variable.Extract the animation duration to a variable for better maintainability.
+$animation-duration: 0.3s; + animation: slide-in ease 0.3s;
115-116: Use CSS variables for consistent colors.Replace hardcoded color values with CSS variables for better maintainability.
- background-color: #16a34a; + background-color: var(--success-color); - background-color: #22c55e; + background-color: var(--active-color); - background-color: #ef4444; + background-color: var(--error-color); - background-color: #6b7280; + background-color: var(--disabled-color);Also applies to: 159-160, 163-164, 167-168
88-106: Optimize loading animation performance.Use
transforminstead ofopacityfor better performance, and consider usingwill-changefor hardware acceleration.&.loading { position: relative; &::after { content: ""; position: absolute; top: 0; left: 0; right: 0; bottom: 0; + will-change: transform; background: linear-gradient( 90deg, transparent, rgba(255, 255, 255, 0.2), transparent ); background-size: 200% 100%; - animation: loading-pulse 1.5s infinite; + animation: loading-pulse 1.5s infinite linear; } }app/components/mcp-market.tsx (1)
43-57: Consider using useReducer for complex state management.The component has multiple related state variables that could be managed more effectively with useReducer.
interface McpMarketState { searchText: string; userConfig: Record<string, string | string[]>; editingServerId?: string; tools: ListToolsResponse["tools"] | null; viewingServerId?: string; isLoading: boolean; config?: McpConfigData; clientStatuses: Record<string, ServerStatusResponse>; loadingPresets: boolean; presetServers: PresetServer[]; loadingStates: Record<string, string>; } type McpMarketAction = | { type: 'SET_SEARCH_TEXT'; payload: string } | { type: 'SET_USER_CONFIG'; payload: Record<string, string | string[]> } | { type: 'SET_EDITING_SERVER'; payload?: string } // ... other action types
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
app/components/mcp-market.module.scss(1 hunks)app/components/mcp-market.tsx(1 hunks)app/mcp/actions.ts(1 hunks)
🔇 Additional comments (6)
app/mcp/actions.ts (4)
259-281: Fix potential memory leak in removeMcpServer.The client's resources should be cleaned up before updating the configuration to prevent potential memory leaks.
284-306: Enhance error resilience in client restart process.Individual client failures during restart shouldn't prevent other clients from restarting.
337-344: Implement atomic file writes for configuration updates.Use temporary files and atomic rename operations to prevent corruption during writes.
117-124: Protect against concurrent initialization race conditions.Multiple clients initializing simultaneously could lead to race conditions. Consider adding a lock mechanism or using a queue for initialization.
Consider implementing a queue system for client initialization:
const initQueue = new PQueue({concurrency: 1}); await initQueue.add(() => initializeSingleClient(clientId, serverConfig));app/components/mcp-market.tsx (2)
143-215: Enhance error handling in saveServerConfig.The function should validate configuration values before saving.
682-688: Add accessibility improvements to the search input.The search input lacks proper accessibility attributes.
| export async function getMcpConfigFromFile(): Promise<McpConfigData> { | ||
| try { | ||
| const configStr = await fs.readFile(CONFIG_PATH, "utf-8"); | ||
| return JSON.parse(configStr); | ||
| } catch (error) { | ||
| logger.error(`Failed to load MCP config, using default config: ${error}`); | ||
| return DEFAULT_MCP_CONFIG; | ||
| } | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add configuration schema validation.
The configuration loading process should validate the structure of the loaded data against a schema to ensure integrity.
interface McpConfigSchema {
mcpServers: Record<string, ServerConfig>;
}
function validateConfig(config: unknown): config is McpConfigData {
const schema = z.object({
mcpServers: z.record(z.custom<ServerConfig>())
});
return schema.safeParse(config).success;
}
app/mcp/actions.ts
Outdated
| export async function reinitializeClient(clientId: string) { | ||
| const config = await getMcpConfigFromFile(); | ||
| const serverConfig = config.mcpServers[clientId]; | ||
| if (!serverConfig) { | ||
| throw new Error(`Server config not found for client ${clientId}`); | ||
| } | ||
| await initializeSingleClient(clientId, serverConfig); | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Enhance error handling in reinitializeClient.
The function should handle initialization failures gracefully and provide detailed error information.
export async function reinitializeClient(clientId: string) {
+ logger.info(`Attempting to reinitialize client [${clientId}]...`);
const config = await getMcpConfigFromFile();
const serverConfig = config.mcpServers[clientId];
if (!serverConfig) {
- throw new Error(`Server config not found for client ${clientId}`);
+ const error = `Server config not found for client ${clientId}`;
+ logger.error(error);
+ throw new Error(error);
+ }
+ try {
await initializeSingleClient(clientId, serverConfig);
+ logger.success(`Successfully reinitialized client [${clientId}]`);
+ } catch (error) {
+ const message = `Failed to reinitialize client [${clientId}]: ${error}`;
+ logger.error(message);
+ throw new Error(message);
}
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| export async function reinitializeClient(clientId: string) { | |
| const config = await getMcpConfigFromFile(); | |
| const serverConfig = config.mcpServers[clientId]; | |
| if (!serverConfig) { | |
| throw new Error(`Server config not found for client ${clientId}`); | |
| } | |
| await initializeSingleClient(clientId, serverConfig); | |
| } | |
| export async function reinitializeClient(clientId: string) { | |
| logger.info(`Attempting to reinitialize client [${clientId}]...`); | |
| const config = await getMcpConfigFromFile(); | |
| const serverConfig = config.mcpServers[clientId]; | |
| if (!serverConfig) { | |
| const error = `Server config not found for client ${clientId}`; | |
| logger.error(error); | |
| throw new Error(error); | |
| } | |
| try { | |
| await initializeSingleClient(clientId, serverConfig); | |
| logger.success(`Successfully reinitialized client [${clientId}]`); | |
| } catch (error) { | |
| const message = `Failed to reinitialize client [${clientId}]: ${error}`; | |
| logger.error(message); | |
| throw new Error(message); | |
| } | |
| } |
| &:focus { | ||
| background-color: var(--white); | ||
| border-color: var(--primary); | ||
| outline: none; | ||
| box-shadow: 0 0 0 2px var(--primary-10); | ||
| } |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Enhance focus visibility for accessibility.
Improve focus state visibility for keyboard navigation.
&:focus {
background-color: var(--white);
border-color: var(--primary);
outline: none;
- box-shadow: 0 0 0 2px var(--primary-10);
+ box-shadow: 0 0 0 3px var(--primary-20);
+ outline: 2px solid transparent;
+ outline-offset: 2px;
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| &:focus { | |
| background-color: var(--white); | |
| border-color: var(--primary); | |
| outline: none; | |
| box-shadow: 0 0 0 2px var(--primary-10); | |
| } | |
| &:focus { | |
| background-color: var(--white); | |
| border-color: var(--primary); | |
| outline: none; | |
| box-shadow: 0 0 0 3px var(--primary-20); | |
| outline: 2px solid transparent; | |
| outline-offset: 2px; | |
| } |
| export function McpMarketPage() { | ||
| const navigate = useNavigate(); | ||
| const [searchText, setSearchText] = useState(""); | ||
| const [userConfig, setUserConfig] = useState<Record<string, any>>({}); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Replace 'any' type with a proper type definition.
Using 'any' type reduces type safety and could lead to runtime errors.
- const [userConfig, setUserConfig] = useState<Record<string, any>>({});
+ const [userConfig, setUserConfig] = useState<Record<string, string | string[]>>({});📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| const [userConfig, setUserConfig] = useState<Record<string, any>>({}); | |
| const [userConfig, setUserConfig] = useState<Record<string, string | string[]>>({}); |
app/components/mcp-market.tsx
Outdated
| useEffect(() => { | ||
| const loadPresetServers = async () => { | ||
| try { | ||
| setLoadingPresets(true); | ||
| const response = await fetch("https://nextchat.club/mcp/list"); | ||
| if (!response.ok) { | ||
| throw new Error("Failed to load preset servers"); | ||
| } | ||
| const data = await response.json(); | ||
| setPresetServers(data?.data ?? []); | ||
| } catch (error) { | ||
| console.error("Failed to load preset servers:", error); | ||
| showToast("Failed to load preset servers"); | ||
| } finally { | ||
| setLoadingPresets(false); | ||
| } | ||
| }; | ||
| loadPresetServers().then(); | ||
| }, []); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Improve error handling in loadPresetServers.
Add proper error handling and remove console.error calls.
const loadPresetServers = async () => {
try {
setLoadingPresets(true);
const response = await fetch("https://nextchat.club/mcp/list");
if (!response.ok) {
- throw new Error("Failed to load preset servers");
+ throw new Error(`Failed to load preset servers: ${response.statusText}`);
}
const data = await response.json();
+ if (!data?.data) {
+ throw new Error("Invalid server response format");
+ }
setPresetServers(data?.data ?? []);
} catch (error) {
- console.error("Failed to load preset servers:", error);
+ logger.error("Failed to load preset servers:", error);
showToast("Failed to load preset servers");
} finally {
setLoadingPresets(false);
}
};Committable suggestion skipped: line range outside the PR's diff.
| // 获取服务器支持的 Tools | ||
| const loadTools = async (id: string) => { | ||
| try { | ||
| const result = await getClientTools(id); | ||
| if (result) { | ||
| setTools(result); | ||
| } else { | ||
| throw new Error("Failed to load tools"); | ||
| } | ||
| } catch (error) { | ||
| showToast("Failed to load tools"); | ||
| console.error(error); | ||
| setTools(null); | ||
| } | ||
| }; |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Improve error handling in loadTools.
Replace console.error with proper logging and add more specific error messages.
const loadTools = async (id: string) => {
try {
const result = await getClientTools(id);
if (result) {
setTools(result);
} else {
- throw new Error("Failed to load tools");
+ throw new Error(`Failed to load tools for server ${id}: No tools returned`);
}
} catch (error) {
- showToast("Failed to load tools");
- console.error(error);
+ const message = error instanceof Error ? error.message : "Unknown error";
+ logger.error(`Failed to load tools for server ${id}:`, message);
+ showToast(`Failed to load tools: ${message}`);
setTools(null);
}
};📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| // 获取服务器支持的 Tools | |
| const loadTools = async (id: string) => { | |
| try { | |
| const result = await getClientTools(id); | |
| if (result) { | |
| setTools(result); | |
| } else { | |
| throw new Error("Failed to load tools"); | |
| } | |
| } catch (error) { | |
| showToast("Failed to load tools"); | |
| console.error(error); | |
| setTools(null); | |
| } | |
| }; | |
| // 获取服务器支持的 Tools | |
| const loadTools = async (id: string) => { | |
| try { | |
| const result = await getClientTools(id); | |
| if (result) { | |
| setTools(result); | |
| } else { | |
| throw new Error(`Failed to load tools for server ${id}: No tools returned`); | |
| } | |
| } catch (error) { | |
| const message = error instanceof Error ? error.message : "Unknown error"; | |
| logger.error(`Failed to load tools for server ${id}:`, message); | |
| showToast(`Failed to load tools: ${message}`); | |
| setTools(null); | |
| } | |
| }; |
| <Modal | ||
| title={`Configure Server - ${editingServerId}`} | ||
| onClose={() => !isLoading && setEditingServerId(undefined)} | ||
| actions={[ | ||
| <IconButton | ||
| key="cancel" | ||
| text="Cancel" | ||
| onClick={() => setEditingServerId(undefined)} | ||
| bordered | ||
| disabled={isLoading} | ||
| />, | ||
| <IconButton | ||
| key="confirm" | ||
| text="Save" | ||
| type="primary" | ||
| onClick={saveServerConfig} | ||
| bordered | ||
| disabled={isLoading} | ||
| />, | ||
| ]} | ||
| > | ||
| <List>{renderConfigForm()}</List> | ||
| </Modal> | ||
| </div> |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Enhance modal accessibility.
Add proper ARIA attributes and keyboard navigation support to the modal.
<Modal
title={`Configure Server - ${editingServerId}`}
onClose={() => !isLoading && setEditingServerId(undefined)}
+ role="dialog"
+ aria-modal="true"
+ aria-labelledby="modal-title"
actions={[
<IconButton
key="cancel"
text="Cancel"
onClick={() => setEditingServerId(undefined)}
bordered
disabled={isLoading}
+ aria-label="Cancel configuration"
/>,
<IconButton
key="confirm"
text="Save"
type="primary"
onClick={saveServerConfig}
bordered
disabled={isLoading}
+ aria-label="Save configuration"
/>,
]}
>
+ <h2 id="modal-title" className="sr-only">
+ Configure Server - {editingServerId}
+ </h2>
<List>{renderConfigForm()}</List>
</Modal>📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| <Modal | |
| title={`Configure Server - ${editingServerId}`} | |
| onClose={() => !isLoading && setEditingServerId(undefined)} | |
| actions={[ | |
| <IconButton | |
| key="cancel" | |
| text="Cancel" | |
| onClick={() => setEditingServerId(undefined)} | |
| bordered | |
| disabled={isLoading} | |
| />, | |
| <IconButton | |
| key="confirm" | |
| text="Save" | |
| type="primary" | |
| onClick={saveServerConfig} | |
| bordered | |
| disabled={isLoading} | |
| />, | |
| ]} | |
| > | |
| <List>{renderConfigForm()}</List> | |
| </Modal> | |
| </div> | |
| <Modal | |
| title={`Configure Server - ${editingServerId}`} | |
| onClose={() => !isLoading && setEditingServerId(undefined)} | |
| role="dialog" | |
| aria-modal="true" | |
| aria-labelledby="modal-title" | |
| actions={[ | |
| <IconButton | |
| key="cancel" | |
| text="Cancel" | |
| onClick={() => setEditingServerId(undefined)} | |
| bordered | |
| disabled={isLoading} | |
| aria-label="Cancel configuration" | |
| />, | |
| <IconButton | |
| key="confirm" | |
| text="Save" | |
| type="primary" | |
| onClick={saveServerConfig} | |
| bordered | |
| disabled={isLoading} | |
| aria-label="Save configuration" | |
| />, | |
| ]} | |
| > | |
| <h2 id="modal-title" className="sr-only"> | |
| Configure Server - {editingServerId} | |
| </h2> | |
| <List>{renderConfigForm()}</List> | |
| </Modal> | |
| </div> |
There was a problem hiding this comment.
Actionable comments posted: 5
♻️ Duplicate comments (4)
app/components/mcp-market.tsx (4)
47-47: 🛠️ Refactor suggestionReplace 'any' type with a proper type definition.
Using 'any' type reduces type safety and could lead to runtime errors.
Apply this diff:
-const [userConfig, setUserConfig] = useState<Record<string, any>>({}); +const [userConfig, setUserConfig] = useState<Record<string, string | string[]>>({});
238-252: 🛠️ Refactor suggestionImprove error handling in loadTools.
Replace console.error with proper error messages.
Apply this diff:
const loadTools = async (id: string) => { try { const result = await getClientTools(id); if (result) { setTools(result); } else { - throw new Error("Failed to load tools"); + throw new Error(`Failed to load tools for server ${id}: No tools returned`); } } catch (error) { - showToast("Failed to load tools"); - console.error(error); + const message = error instanceof Error ? error.message : "Unknown error"; + showToast(`Failed to load tools: ${message}`); setTools(null); } };
701-707: 🛠️ Refactor suggestionAdd accessibility improvements to the search input.
The search input lacks proper accessibility attributes.
Apply this diff:
<input type="text" className={styles["search-bar"]} placeholder={"Search MCP Server"} autoFocus onInput={(e) => setSearchText(e.currentTarget.value)} + aria-label="Search MCP servers" + role="searchbox" + aria-describedby="search-description" /> +<span id="search-description" className="sr-only"> + Search for MCP servers by name, description, or tags +</span>
716-739: 🛠️ Refactor suggestionEnhance modal accessibility.
Add proper ARIA attributes and keyboard navigation support to the modal.
Apply this diff:
<Modal title={`Configure Server - ${editingServerId}`} onClose={() => !isLoading && setEditingServerId(undefined)} + role="dialog" + aria-modal="true" + aria-labelledby="modal-title" actions={[ <IconButton key="cancel" text="Cancel" onClick={() => setEditingServerId(undefined)} bordered disabled={isLoading} + aria-label="Cancel configuration" />, <IconButton key="confirm" text="Save" type="primary" onClick={saveServerConfig} bordered disabled={isLoading} + aria-label="Save configuration" />, ]} > + <h2 id="modal-title" className="sr-only"> + Configure Server - {editingServerId} + </h2> <List>{renderConfigForm()}</List> </Modal>
🧹 Nitpick comments (8)
app/locales/en.ts (1)
638-640: LGTM on structure, consider expanding the MCP label for clarity.The addition follows the file's structure and naming conventions correctly. However, since MCP (Multi-Channel Protocol) is a technical term, consider making it more user-friendly.
Consider this alternative to improve clarity:
Mcp: { - Name: "MCP", + Name: "Multi-Channel Protocol (MCP)", },app/mcp/actions.ts (4)
71-71: Improve readability of client counting logicThe use of logical AND (
&&) for incrementingcountwithingetAvailableClientsCountmay reduce code clarity.Consider refactoring the code for better readability:
- clientsMap.forEach((map) => !map.errorMsg && count++); + clientsMap.forEach((map) => { + if (!map.errorMsg) { + count++; + } + });
217-259: Handle client initialization failures without affecting configurationIn
resumeMcpServer, when client initialization fails, the server configuration is updated to"error"status, which may not be ideal as it persists an error state in the configuration file.Instead of modifying the server configuration on initialization failure, consider handling the error within the clients map only. This keeps the configuration file consistent and avoids unintended side effects:
// 初始化失败 clientsMap.set(clientId, { client: null, tools: null, errorMsg: error instanceof Error ? error.message : String(error), }); logger.error(`Failed to initialize client [${clientId}]: ${error}`); - return false; + // Do not modify the configuration file + return await getClientStatus(clientId).then( + (status) => status.status === "active" + );
64-66: Ensure consistent null checks ingetClientToolsThe function
getClientToolsreturnsnullif the client is not found or if tools are not available.For better consistency, consider explicitly checking if the client exists before accessing its tools:
export async function getClientTools(clientId: string) { - return clientsMap.get(clientId)?.tools ?? null; + const clientData = clientsMap.get(clientId); + if (clientData && clientData.tools) { + return clientData.tools; + } + return null; }
364-371: Avoid redundant error logging inisMcpEnabledIn
isMcpEnabled, logging the error may be unnecessary if the function simply returnsfalse.Consider removing the error logging to reduce noise:
export async function isMcpEnabled() { try { const serverConfig = getServerSideConfig(); return !!serverConfig.enableMcp; } catch (error) { - logger.error(`Failed to check MCP status: ${error}`); return false; } }app/layout.tsx (1)
9-9: Optimize import placement for better readabilityThe import of
getServerSideConfigcould be moved closer to its usage withinRootLayoutfor code clarity.If
getServerSideConfigis only used insideRootLayout, consider moving the import statement inside the function scope.app/config/server.ts (2)
85-85: Document the new environment variableENABLE_MCPThe addition of
ENABLE_MCPlacks documentation, which could cause confusion for other developers.Add a comment explaining the purpose and expected values of
ENABLE_MCP:ENABLE_MCP?: string; // Set to 'true' to enable MCP functionality
256-256: Consistent casting of environment variables to booleanIn the configuration object,
enableMcpuses!!to cast the environment variable to a boolean. Ensure this is consistent across all boolean configurations.Review other boolean configurations to ensure consistent usage:
return { ... enableMcp: !!process.env.ENABLE_MCP, // For consistency, cast other booleans similarly hideUserApiKey: !!process.env.HIDE_USER_API_KEY, disableGPT4: !!process.env.DISABLE_GPT4, hideBalanceQuery: !!process.env.ENABLE_BALANCE_QUERY, disableFastLink: !!process.env.DISABLE_FAST_LINK, ... };
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (11)
.env.template(1 hunks)Dockerfile(1 hunks)app/components/chat.tsx(15 hunks)app/components/home.tsx(6 hunks)app/components/mcp-market.tsx(1 hunks)app/components/sidebar.tsx(6 hunks)app/config/server.ts(3 hunks)app/layout.tsx(2 hunks)app/locales/en.ts(1 hunks)app/mcp/actions.ts(1 hunks)app/page.tsx(0 hunks)
💤 Files with no reviewable changes (1)
- app/page.tsx
🚧 Files skipped from review as they are similar to previous changes (1)
- app/components/chat.tsx
🔇 Additional comments (9)
app/mcp/actions.ts (4)
334-341: Handle missing configuration file gracefullyIn
getMcpConfigFromFile, if the configuration file is missing (e.g., on the first run), the error is logged, which might be confusing for users.This issue was previously noted. Consider checking if the error is due to the file not existing (
ENOENT) and initialize with a default configuration without logging an error.
345-351: Use atomic writes to prevent configuration file corruptionWhen updating the MCP configuration, writing directly to the file could lead to corruption if the process is interrupted.
As previously suggested, consider implementing atomic file writes using temporary files and renaming:
async function updateMcpConfig(config: McpConfigData): Promise<void> { try { + const tempPath = `${CONFIG_PATH}.tmp`; + await fs.writeFile(tempPath, JSON.stringify(config, null, 2)); + await fs.rename(tempPath, CONFIG_PATH); } catch (error) { + // Clean up temp file if it exists + try { + await fs.unlink(`${CONFIG_PATH}.tmp`); + } catch { + // Ignore cleanup errors + } throw error; } }
316-331: Add request validation to ensure correct executionThe
executeMcpActionfunction should validate the request structure to prevent potential errors during execution.This was highlighted earlier. Ensure that the request contains the necessary properties:
export async function executeMcpAction( clientId: string, request: McpRequestMessage, ) { try { + // Validate request structure + if (!request || typeof request !== 'object') { + throw new Error('Invalid request format'); + } + if (!request.action || typeof request.action !== 'string') { + throw new Error('Missing or invalid action in request'); + } const client = clientsMap.get(clientId); if (!client?.client) { throw new Error(`Client ${clientId} not found`); } logger.info(`Executing request for [${clientId}]`); return await executeRequest(client.client, request); } catch (error) { logger.error(`Failed to execute request for [${clientId}]: ${error}`); throw error; } }
291-313: 🛠️ Refactor suggestionEnsure all clients are restarted even if some fail
In
restartAllClients, a failure in one client could prevent other clients from restarting due to the synchronousforloops.Refactor the function to handle client restarts asynchronously and independently:
// 关闭所有客户端 - for (const client of clientsMap.values()) { - if (client.client) { - await removeClient(client.client); - } - } + await Promise.allSettled( + Array.from(clientsMap.values()).map(async (client) => { + if (client.client) { + try { + await removeClient(client.client); + } catch (error) { + logger.error(`Failed to remove client: ${error}`); + } + } + }) + ); // 清空状态 clientsMap.clear(); // 重新初始化 const config = await getMcpConfigFromFile(); - for (const [clientId, serverConfig] of Object.entries(config.mcpServers)) { - await initializeSingleClient(clientId, serverConfig); - } + await Promise.all( + Object.entries(config.mcpServers).map(([clientId, serverConfig]) => + initializeSingleClient(clientId, serverConfig) + ) + );Likely invalid or redundant comment.
Dockerfile (1)
45-45: Verify the existence of mcp_config.json.The COPY command assumes
mcp_config.jsonexists in the builder stage. If this file is missing, the build will fail..env.template (1)
10-14: LGTM!The documentation for the
ENABLE_MCPenvironment variable is clear, follows the existing pattern, and correctly specifies the default value and usage.app/components/home.tsx (1)
78-83: LGTM!The dynamic import for
McpMarketPagefollows the existing pattern and includes proper loading state handling.app/components/sidebar.tsx (1)
267-277: LGTM!The conditional rendering of the MCP button is well-implemented with proper icon, text, and navigation handling.
app/components/mcp-market.tsx (1)
76-94: 🛠️ Refactor suggestionImprove error handling in loadPresetServers.
The function uses console.error and could benefit from better error handling.
Apply this diff:
const loadPresetServers = async () => { if (!mcpEnabled) return; try { setLoadingPresets(true); const response = await fetch("https://nextchat.club/mcp/list"); if (!response.ok) { - throw new Error("Failed to load preset servers"); + throw new Error(`Failed to load preset servers: ${response.statusText}`); } const data = await response.json(); + if (!data?.data) { + throw new Error("Invalid server response format"); + } setPresetServers(data?.data ?? []); } catch (error) { - console.error("Failed to load preset servers:", error); showToast("Failed to load preset servers"); } finally { setLoadingPresets(false); } };Likely invalid or redundant comment.
| Mcp: { | ||
| Name: "MCP", | ||
| }, |
There was a problem hiding this comment.
💡 Codebase verification
Add comprehensive localization for MCP-related UI elements
The verification revealed that most MCP-related strings are not properly localized. Please add the following keys to the Mcp object in the locale files:
- Market page elements:
app/components/mcp-market.tsx: "MCP Market", "Search MCP Server", "servers configured"app/components/mcp-market.tsx: Status messages like "Creating MCP client...", "Starting server...", "Stopping server..."
- Error messages:
app/store/chat.ts: "MCP execution failed"app/components/mcp-market.tsx: "Failed to load preset servers"
- Button labels and tooltips in the market interface
🔗 Analysis chain
Verify comprehensive localization coverage for MCP feature.
As this is a WIP PR implementing the Multi-Channel Protocol system, ensure that all user-facing strings related to MCP functionality (such as error messages, tooltips, or configuration options) are properly localized.
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Search for potential unlocalized MCP-related strings in the codebase
echo "Searching for MCP-related strings that might need localization..."
rg -i "mcp" --type ts --type tsx --type js --type jsx -g '!app/locales/*' -g '!*test*'
Length of output: 255
Script:
#!/bin/bash
# Search for MCP-related strings in TypeScript and JavaScript files
echo "Searching for MCP-related strings in source files..."
rg -i "mcp" --type ts --type js -g '!app/locales/*' -g '!*test*' -g '!*.d.ts'
# Search specifically for string literals containing MCP
echo -e "\nSearching for potential string literals containing MCP..."
ast-grep --pattern 'StringLiteral: /.*[Mm][Cc][Pp].*/'
# Search for potential React components or features related to MCP
echo -e "\nSearching for MCP-related components or features..."
rg -i "mcp" --type ts --type js -g '!app/locales/*' -g '!*test*' -A 2 -B 2
Length of output: 54077
| const serverConfig = getServerSideConfig(); | ||
|
|
There was a problem hiding this comment.
Ensure server-side code is not executed on the client
The usage of getServerSideConfig inside a component may cause issues if the component is rendered on the client side.
Since getServerSideConfig accesses server-side environment variables, ensure that RootLayout is a server component or modify the code to prevent client-side execution.
|
|
||
| COPY --from=builder /app/public ./public | ||
| COPY --from=builder /app/.next/standalone ./ | ||
| COPY --from=builder /app/.next/static ./.next/static | ||
| COPY --from=builder /app/.next/server ./.next/server | ||
|
|
||
| RUN mkdir -p /app/app/mcp && chmod 777 /app/app/mcp |
There was a problem hiding this comment.
Restrict directory permissions for security.
Setting 777 permissions (read, write, execute for all users) on the /app/app/mcp directory is too permissive and poses a security risk. Consider using more restrictive permissions.
Apply this diff to use more restrictive permissions:
-RUN mkdir -p /app/app/mcp && chmod 777 /app/app/mcp
+RUN mkdir -p /app/app/mcp && chown node:node /app/app/mcp && chmod 755 /app/app/mcp📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| RUN mkdir -p /app/app/mcp && chmod 777 /app/app/mcp | |
| RUN mkdir -p /app/app/mcp && chown node:node /app/app/mcp && chmod 755 /app/app/mcp |
| const initMcp = async () => { | ||
| try { | ||
| const enabled = await isMcpEnabled(); | ||
| if (enabled) { | ||
| console.log("[MCP] initializing..."); | ||
| await initializeMcpSystem(); | ||
| console.log("[MCP] initialized"); | ||
| } | ||
| } catch (err) { | ||
| console.error("[MCP] failed to initialize:", err); | ||
| } | ||
| }; | ||
| initMcp(); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Remove console logs and improve error handling.
The initialization code includes console logs and could benefit from better error handling.
Apply this diff to improve the code:
const initMcp = async () => {
try {
const enabled = await isMcpEnabled();
if (enabled) {
- console.log("[MCP] initializing...");
await initializeMcpSystem();
- console.log("[MCP] initialized");
}
} catch (err) {
- console.error("[MCP] failed to initialize:", err);
+ showToast(
+ err instanceof Error
+ ? `Failed to initialize MCP: ${err.message}`
+ : "Failed to initialize MCP"
+ );
}
};Committable suggestion skipped: line range outside the PR's diff.
| useEffect(() => { | ||
| // 检查 MCP 是否启用 | ||
| const checkMcpStatus = async () => { | ||
| const enabled = await isMcpEnabled(); | ||
| setMcpEnabled(enabled); | ||
| console.log("[SideBar] MCP enabled:", enabled); | ||
| }; | ||
| checkMcpStatus(); | ||
| }, []); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Remove console logs and add missing dependency.
The effect includes console logs and is missing mcpEnabled in its dependency array.
Apply this diff to improve the code:
useEffect(() => {
- // 检查 MCP 是否启用
const checkMcpStatus = async () => {
const enabled = await isMcpEnabled();
setMcpEnabled(enabled);
- console.log("[SideBar] MCP enabled:", enabled);
if (!enabled) {
navigate(Path.Home);
}
};
checkMcpStatus();
-}, [navigate]);
+}, [navigate, mcpEnabled]);Committable suggestion skipped: line range outside the PR's diff.
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
app/mcp/actions.ts (1)
337-352: 🛠️ Refactor suggestionAdd request validation in
executeMcpActionIn
executeMcpAction, therequestobject is used without validation, which could lead to unexpected errors or security vulnerabilities. Consider validating the structure and content of therequestparameter to ensure it meets the expected format.Apply this change:
export async function executeMcpAction( clientId: string, request: McpRequestMessage, ) { try { + // Validate request structure + if (!request || typeof request !== 'object') { + throw new Error('Invalid request format'); + } + if (!request.action || typeof request.action !== 'string') { + throw new Error('Missing or invalid action in request'); + } + const client = clientsMap.get(clientId); if (!client?.client) { throw new Error(`Client ${clientId} not found`); } logger.info(`Executing request for [${clientId}]`); return await executeRequest(client.client, request); } catch (error) { logger.error(`Failed to execute request for [${clientId}]: ${error}`); throw error; } }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
app/components/mcp-market.module.scss(1 hunks)app/components/mcp-market.tsx(1 hunks)app/mcp/actions.ts(1 hunks)app/mcp/types.ts(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- app/mcp/types.ts
🔇 Additional comments (6)
app/mcp/actions.ts (2)
355-363: Handle missing configuration file gracefullyIn
getMcpConfigFromFile, when the configuration file is missing (e.g., on the first run), it logs an error and returns the default configuration. Instead, consider checking if the error is due to the file not existing (ENOENT) and avoid logging an error in that case. This provides a smoother user experience.Apply this change:
} catch (error) { - logger.error(`Failed to load MCP config, using default config: ${error}`); - return DEFAULT_MCP_CONFIG; + if (error.code === 'ENOENT') { + logger.warn("MCP config file not found, using default configuration."); + return DEFAULT_MCP_CONFIG; + } else { + logger.error(`Failed to load MCP config: ${error}`); + throw error; + } }
366-372: Implement atomic file writes for configuration updatesWhen updating the MCP configuration file in
updateMcpConfig, there is a risk of file corruption if the write operation is interrupted. Consider using a temporary file and an atomic rename operation to ensure the configuration file remains consistent.Apply this change:
async function updateMcpConfig(config: McpConfigData): Promise<void> { try { + const tempPath = `${CONFIG_PATH}.tmp`; + await fs.writeFile(tempPath, JSON.stringify(config, null, 2)); + await fs.rename(tempPath, CONFIG_PATH); } catch (error) { + // Clean up temp file if it exists + try { + await fs.unlink(`${CONFIG_PATH}.tmp`); + } catch { + // Ignore cleanup errors + } throw error; } }app/components/mcp-market.module.scss (1)
269-274: Enhance focus visibility for better accessibilityThe focus styles on input elements can be improved to enhance keyboard navigation and accessibility. Consider adjusting the
box-shadowand addingoutline-offsetto make focused elements more noticeable.Apply this change:
&:focus { background-color: var(--white); border-color: var(--primary); outline: none; - box-shadow: 0 0 0 2px var(--primary-10); + box-shadow: 0 0 0 3px var(--primary-20); + outline: 2px solid transparent; + outline-offset: 2px; }app/components/mcp-market.tsx (3)
47-47: Replace 'any' with specific types inuserConfigUsing
anyreduces type safety and can lead to runtime errors. Specify the expected types to enhance type checking.Apply this change:
- const [userConfig, setUserConfig] = useState<Record<string, any>>({}); + const [userConfig, setUserConfig] = useState<Record<string, string | string[]>>({});
676-682: Improve accessibility of the search inputAdd ARIA attributes to the search input to enhance accessibility for users relying on assistive technologies.
Apply this change:
<input type="text" className={styles["search-bar"]} placeholder={"Search MCP Server"} autoFocus onInput={(e) => setSearchText(e.currentTarget.value)} + aria-label="Search MCP servers" + role="searchbox" />
691-714: Enhance modal accessibilityInclude appropriate ARIA attributes in the modal to improve accessibility for assistive technologies.
Apply this change:
<Modal title={`Configure Server - ${editingServerId}`} onClose={() => !isLoading && setEditingServerId(undefined)} + role="dialog" + aria-modal="true" + aria-labelledby="modal-title" actions={[ // Actions... ]} > + <h2 id="modal-title" className="sr-only"> + Configure Server - {editingServerId} + </h2> <List>{renderConfigForm()}</List> </Modal>
| export async function getAvailableClientsCount() { | ||
| let count = 0; | ||
| clientsMap.forEach((map) => !map.errorMsg && count++); | ||
| return count; | ||
| } |
There was a problem hiding this comment.
Ensure accurate count of available clients
In getAvailableClientsCount, clients with errorMsg set to null are counted as available. However, during initialization, errorMsg is null, but the client may not yet be fully initialized. To accurately count only active clients, consider checking if map.client is not null and errorMsg is null.
Apply this diff to fix the issue:
export async function getAvailableClientsCount() {
let count = 0;
- clientsMap.forEach((map) => !map.errorMsg && count++);
+ clientsMap.forEach((map) => map.client && !map.errorMsg && count++);
return count;
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| export async function getAvailableClientsCount() { | |
| let count = 0; | |
| clientsMap.forEach((map) => !map.errorMsg && count++); | |
| return count; | |
| } | |
| export async function getAvailableClientsCount() { | |
| let count = 0; | |
| clientsMap.forEach((map) => map.client && !map.errorMsg && count++); | |
| return count; | |
| } |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
app/constant.ts (1)
277-392: Consider improving the system template structure and examples.While the template is comprehensive, there are a few areas for improvement:
- The example section mixes Chinese and English content
- The error examples contain excessive exclamation marks
- The formatting could be more consistent
Consider these improvements:
- follwing is the wrong! mcp json example: + Following are examples of incorrect MCP JSON format: - This is wrong because the method is not tools/call.!!!!!!!!!!! + This is incorrect because the method is not "tools/call". - please follow the format strictly ONLY use tools/call method!!!!!!!!!!! + Please strictly follow the format and ONLY use the "tools/call" method. - "content": "为什么数学书总是感到忧伤？因为它有太多的问题。" + "content": "Why do math books look sad? Because they have too many problems."app/store/chat.ts (1)
Line range hint
403-429: Consider adding validation for MCP response content.While the implementation handles MCP responses correctly, it would be beneficial to add validation for the response content.
Consider adding validation:
async onUserInput( content: string, attachImages?: string[], isMcpResponse?: boolean, ) { + if (isMcpResponse && !content.trim()) { + console.warn("[MCP] Empty response content"); + return; + } const session = get().currentSession(); const modelConfig = session.mask.modelConfig;
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (8)
README_CN.md(3 hunks)app/components/chat.tsx(15 hunks)app/components/sidebar.tsx(6 hunks)app/config/server.ts(2 hunks)app/constant.ts(3 hunks)app/locales/cn.ts(1 hunks)app/locales/en.ts(1 hunks)app/store/chat.ts(11 hunks)
🚧 Files skipped from review as they are similar to previous changes (6)
- app/locales/en.ts
- README_CN.md
- app/locales/cn.ts
- app/config/server.ts
- app/components/sidebar.tsx
- app/components/chat.tsx
🔇 Additional comments (8)
app/constant.ts (3)
52-52: LGTM!The new path follows the existing naming convention and is appropriately placed in the enum.
94-94: LGTM!The new store key follows the existing naming convention and is appropriately placed in the enum.
270-275: LGTM!The template is well-structured and provides clear placeholders for dynamic content.
app/store/chat.ts (5)
Line range hint
1-39: LGTM!The imports are well-organized and include all necessary dependencies for the MCP functionality.
64-64: LGTM!The
isMcpResponseflag is appropriately added to the ChatMessage type.
201-220: Add error handling and validation in getMcpSystemPrompt.The implementation needs improvements in error handling and validation as previously suggested.
395-399: LGTM!The MCP JSON check is appropriately added to the message processing flow.
817-845: Address security concerns in MCP JSON handling.The implementation needs security improvements as previously suggested.
commit f5f3ce94f63bceadff24ca1beff3ae85d142f92e Author: RiverRay <[email protected]> Date: Fri Feb 21 08:56:43 2025 +0800 Update README.md commit 2b5f6003086f65f5361ccfc5dc83242f2ca813b8 Author: RiverRay <[email protected]> Date: Fri Feb 21 08:55:40 2025 +0800 Update README.md commit b96610711763d5b5e64d138f6599008c0065accc Merge: 377480b4 90827fc5 Author: RiverRay <[email protected]> Date: Mon Feb 17 22:58:01 2025 +0800 Merge pull request #6235 from DBCDK/danish-locale Translation to danish commit 377480b448798488db5ef03f4d5c44d2d930693c Merge: 8bd0d6a1 12863f52 Author: river <[email protected]> Date: Sun Feb 16 10:50:07 2025 +0800 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web commit 8bd0d6a1a7abccc736769b9f2b2b9c9ee75b81a8 Author: river <[email protected]> Date: Sun Feb 16 10:48:54 2025 +0800 chore: Update NextChatAI domain from nextchat.dev to nextchat.club commit 90827fc593f2e756264c0d309e638491105b669b Author: Rasmus Erik Voel Jensen <[email protected]> Date: Sat Feb 15 13:08:58 2025 +0100 danish rewording / improved button label commit 008e339b6d1c227c47a9cb4877ba8bb064f41043 Author: Rasmus Erik Voel Jensen <[email protected]> Date: Sat Feb 15 12:52:44 2025 +0100 danish locale commit 12863f52131bba9d75b29038970c9293f3b54cb5 Merge: 48cd4b11 cf140d42 Author: RiverRay <[email protected]> Date: Thu Feb 13 14:53:47 2025 +0800 Merge pull request #6204 from bestsanmao/ali_bytedance_reasoning_content add 3 type of reasoning_content support (+deepseek-r1@OpenAI @Alibaba @ByteDance), parse <think></think> from SSE commit cf140d422863e313ad1609dfd33fd19ea5463ff3 Merge: 476d946f 48cd4b11 Author: suruiqiang <[email protected]> Date: Wed Feb 12 17:54:50 2025 +0800 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web into ali_bytedance_reasoning_content commit 476d946f961a551ffedc7734dcce28faa7dc30fe Author: suruiqiang <[email protected]> Date: Wed Feb 12 17:49:54 2025 +0800 fix bug (trim eats space or \n mistakenly), optimize timeout by model commit 97142583224faa28e7cdd43eba75b77828f280af Author: suruiqiang <[email protected]> Date: Tue Feb 11 18:57:16 2025 +0800 support deepseek-r1@OpenAI's reasoning_content, parse <think></think> from stream commit 48cd4b11b5dd14b333350a80be597a2b98391d1c Merge: 77c78b23 18fa2cc3 Author: RiverRay <[email protected]> Date: Tue Feb 11 18:37:47 2025 +0800 Merge pull request #6190 from siliconflow/refine-emoji-siliconflow Fix model icon on SiliconFlow commit 77c78b230a8e0a06f7a6fb8d09837cf5056c0a8c Merge: b44686b8 2137aa65 Author: RiverRay <[email protected]> Date: Tue Feb 11 18:37:22 2025 +0800 Merge pull request #6193 from siliconflow/get-models-siliconflow Model listing of SiliconFlow commit b44686b887c9f9f6495b67c4dda77ed5111c30b7 Merge: 34bdd4b9 9f91c2d0 Author: RiverRay <[email protected]> Date: Tue Feb 11 18:36:50 2025 +0800 Merge pull request #6189 from bestsanmao/bug_fix fix avatar for export message preview and saved image commit 34bdd4b945bea213d660fec4c15796d70b2c137b Merge: a029b433 86f86962 Author: RiverRay <[email protected]> Date: Tue Feb 11 18:35:02 2025 +0800 Merge pull request #6194 from siliconflow/vl-support-on-sf Support VLM on SiliconFlow commit b0758cccde8709af7fa31aed8c019029c97be82b Author: suruiqiang <[email protected]> Date: Tue Feb 11 16:08:30 2025 +0800 optimization commit 98a11e56d2c55d7d89dfc4c8905045781863bf98 Author: suruiqiang <[email protected]> Date: Tue Feb 11 12:46:46 2025 +0800 support alibaba and bytedance's reasoning_content commit 86f86962fb0725b888cee6ebd9eb9f818a0c9cee Author: Shenghang Tsai <[email protected]> Date: Mon Feb 10 13:37:48 2025 +0800 Support VLM on SiliconFlow commit 2137aa65bfaeda33bdbfad7f1ae36bfdde8c9edf Author: Shenghang Tsai <[email protected]> Date: Mon Feb 10 11:03:49 2025 +0800 Model listing of SiliconFlow commit 18fa2cc30d96fbb452efd9226db7ca6021cacb3e Author: Shenghang Tsai <[email protected]> Date: Sun Feb 9 18:49:26 2025 +0800 fix model icon on siliconflow commit 0bfc6480855640032ec3593960b434fc5e1c1de5 Author: Shenghang Tsai <[email protected]> Date: Sun Feb 9 18:47:57 2025 +0800 fix model icon on siliconflow commit 9f91c2d05c21c7fea604a88a0974679a07293c81 Author: suruiqiang <[email protected]> Date: Sun Feb 9 16:52:46 2025 +0800 fix avatar for export message preview and saved image commit a029b4330b89f8f2d1258e46fa68ba87c998a745 Merge: c2edfec1 2842b264 Author: RiverRay <[email protected]> Date: Sun Feb 9 11:05:43 2025 +0800 Merge pull request #6188 from ChatGPTNextWeb/Leizhenpeng-patch-4 Update LICENSE commit 2842b264e06b08de9cfdcb84982ee6571fa45881 Author: RiverRay <[email protected]> Date: Sun Feb 9 11:05:32 2025 +0800 Update LICENSE commit c2edfec16fc97446b58149312706f1539e60fc58 Merge: 6406ac99 97a4aafc Author: RiverRay <[email protected]> Date: Sun Feb 9 11:03:44 2025 +0800 Merge pull request #6172 from bestsanmao/bug_fix fix several bugs commit 6406ac99a30659abd7a93e47a5faa2def9464f46 Merge: c6199dbf d8f533e1 Author: RiverRay <[email protected]> Date: Sun Feb 9 11:02:13 2025 +0800 Merge pull request #6175 from itsevin/main Add other Xai model commit 97a4aafc9276760443c2044bad5c454c7d9435a4 Merge: 1ae5fdbf c6199dbf Author: suruiqiang <[email protected]> Date: Sun Feb 9 09:46:07 2025 +0800 Merge remote-tracking branch 'remotes/origin/main' into bug_fix commit d8f533e1f35b75905ef822cbc50e62c3f228b148 Merge: fdbaddde c6199dbf Author: GH Action - Upstream Sync <[email protected]> Date: Sun Feb 9 01:22:47 2025 +0000 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web commit c6199dbf9f1a9f729eebff28944b59d3bcc2c6a4 Merge: 4273aa08 acf75ce6 Author: RiverRay <[email protected]> Date: Sat Feb 8 23:40:39 2025 +0800 Merge pull request #6186 from siliconflow/fix-truc-of-reasoning-model Fix formatting of reasoning model on SiliconFlow commit 4273aa0803b5b7267730b77995c55fd7f674b0d4 Merge: bf265d33 2a3996e0 Author: RiverRay <[email protected]> Date: Sat Feb 8 23:39:49 2025 +0800 Merge pull request #6185 from siliconflow/larger_timeout_for_siliconflow Larger timeout for SiliconFlow commit acf75ce68f7152972fe5924b4880b3ae06c0ca65 Author: Shenghang Tsai <[email protected]> Date: Sat Feb 8 16:34:17 2025 +0800 Remove unnecessary trimming commit 1ae5fdbf013349a2c32e6083b41500cbf2c4000d Author: suruiqiang <[email protected]> Date: Sat Feb 8 16:15:10 2025 +0800 mini optimizations commit 2a3996e0d66e41a99bfd4373c2bd9dec4d78652a Author: Shenghang Tsai <[email protected]> Date: Sat Feb 8 14:38:12 2025 +0800 Update siliconflow.ts commit fdbaddde37165b293ba7d246108ea1a5610b92da Merge: c4e9cb03 bf265d33 Author: GH Action - Upstream Sync <[email protected]> Date: Sat Feb 8 01:16:56 2025 +0000 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web commit d74f79e9c5ee36fa9c3a59f8390a444857417b1e Merge: a5a97682 bf265d33 Author: suruiqiang <[email protected]> Date: Sat Feb 8 08:29:34 2025 +0800 Merge remote-tracking branch 'remotes/origin/HEAD' into bug_fix commit c4e9cb03a92751b37ec0b9615ef5ec056fa20bde Author: itsevin <[email protected]> Date: Fri Feb 7 20:29:21 2025 +0800 Add Xai model commit bf265d33759dfada0d91248cbcb5ae22326e745f Merge: 17f391d9 51384ddc Author: RiverRay <[email protected]> Date: Fri Feb 7 20:25:20 2025 +0800 Merge pull request #6164 from ZhangYichi-ZYc/main Fix: Set consistent fill color for OpenAI/MoonShot/Grok SVG to prevent color inversion in dark mode commit 17f391d929a0281f67e22d87a95f06ed9c811cf8 Merge: 78186c27 e5e5fde9 Author: RiverRay <[email protected]> Date: Fri Feb 7 20:23:47 2025 +0800 Merge pull request #6158 from dupl/main update the lastest Gemini models commit 78186c27fb70fdeeafb8a9ac6ab7a3b43bb9c8e0 Merge: add9ca20 a780b39c Author: RiverRay <[email protected]> Date: Fri Feb 7 20:23:01 2025 +0800 Merge pull request #6168 from xiexin12138/fix-env Fix: 补充 env 中硅基流动的环境变量；追加硅基流动 2 个支持的付费模型 commit a5a976824591a7e2c228dbb257616b98fd7a53ed Author: suruiqiang <[email protected]> Date: Fri Feb 7 16:34:14 2025 +0800 change request timeout for thinking mode commit 3fe55b4f7ff1791cf6e8c5d9da02b69a240e98a8 Author: suruiqiang <[email protected]> Date: Fri Feb 7 16:20:07 2025 +0800 fix bug that gemini has multiple candidates part commit f156430cc5f9451618b13e6432148d1d0dd35c5c Author: suruiqiang <[email protected]> Date: Fri Feb 7 16:18:15 2025 +0800 fix emoji issue for doubao and glm's congview & congvideox commit f30c6a4348fb25fead1d1ba4f4ff6717a45496fb Author: suruiqiang <[email protected]> Date: Fri Feb 7 16:14:19 2025 +0800 fix doubao and grok not upload image commit a780b39c17a271eb44421ac2f027fcf91c3b77cf Author: xiexin12138 <[email protected]> Date: Fri Feb 7 15:43:50 2025 +0800 fix: 补充硅基流动对 DeepSeek 支持的付费模型 commit 1010db834ce52f6a832bf50d3645527f3b42697e Author: xiexin12138 <[email protected]> Date: Fri Feb 7 15:41:40 2025 +0800 fix: 补充硅基流动的 env 环境变量 commit 51384ddc5feff6ca31028c77cf6b17b751a0ab24 Author: ZhangYichi <[email protected]> Date: Fri Feb 7 11:13:22 2025 +0800 Fix: Set consistent fill color for OpenAI/MoonShot/Grok SVG to prevent color inversion in dark mode commit e5e5fde924a7598a6c447c079cce7337294b9d81 Author: dupl <[email protected]> Date: Fri Feb 7 06:50:31 2025 +0800 update the lastest Gemini models commit add9ca200cf91e467c2d6b770e4a8f140aff18e8 Merge: 28cbe56c 5225a6e1 Author: RiverRay <[email protected]> Date: Thu Feb 6 18:08:08 2025 +0800 Merge pull request #6144 from Eric-2369/add-more-llm-icons feat: add more llm icons commit 5225a6e1921d170803ab11aa8ba09957cf0b678b Author: Eric-2369 <[email protected]> Date: Wed Feb 5 12:34:00 2025 +0800 feat: add more llm icons commit 28cbe56cec390c2309a3995b300c8d5aa1387c0a Merge: bb4832e6 ad9ab9d4 Author: RiverRay <[email protected]> Date: Tue Feb 4 21:29:02 2025 +0800 Merge pull request #6141 from siliconflow/provider_silicon New provider SiliconFlow and Its Latest DeekSeek Models commit ad9ab9d45afa384718a59bce23d9b70e3e8ed08a Author: Shenghang Tsai <[email protected]> Date: Tue Feb 4 15:02:18 2025 +0800 New provider SiliconFlow and Its Latest DeekSeek Models Update README.md Update constant.ts Update README_CN.md commit bb4832e6e71626184c339cce86eab94dbc3f8a59 Merge: 32b60909 39b3487e Author: RiverRay <[email protected]> Date: Tue Feb 4 09:38:04 2025 +0800 Merge pull request #6129 from MonadMonAmi/update_knowledge_cutoff_date chore: add knowledge cut off dates for o1 and o3 commit 39b3487ea0f62065ffbe5f743c298af8247e9834 Merge: 2e7cac32 32b60909 Author: RiverRay <[email protected]> Date: Tue Feb 4 09:37:55 2025 +0800 Merge branch 'main' into update_knowledge_cutoff_date commit 32b60909ae37948aca97a0fbec218372086e938f Merge: 5db6775c 4c4d44e2 Author: RiverRay <[email protected]> Date: Tue Feb 4 09:35:43 2025 +0800 Merge pull request #6132 from RetiredQQ/main temporary fix for o3-mini commit 5db6775cb85917c99d171905c38efa4a368bb873 Merge: b6881c77 92f57fb1 Author: RiverRay <[email protected]> Date: Tue Feb 4 09:34:43 2025 +0800 Merge pull request #6134 from zcong1993/main fix: fix isModelNotavailableInServer logic for bytedance models commit b6881c77978b50debfd3907a863f2481e51ff299 Merge: 9943a522 60fa3580 Author: RiverRay <[email protected]> Date: Tue Feb 4 09:33:13 2025 +0800 Merge pull request #6127 from dupl/main add gemini-2.0-flash-thinking-exp, gemini-2.0-flash-thinking-exp-01-21 commit 9943a52295e36b0c296110f31643090f5fe0bb35 Author: RiverRay <[email protected]> Date: Tue Feb 4 09:31:16 2025 +0800 Update README.md commit 1db4d25370d5754576c2bddc29ee75c6869b2696 Author: RiverRay <[email protected]> Date: Tue Feb 4 09:29:56 2025 +0800 Update README.md commit 92f57fb18fe40e73a425842747d4b5654493f275 Author: zcong1993 <[email protected]> Date: Mon Feb 3 16:58:42 2025 +0800 fix: fix isModelNotavailableInServer logic for bytedance models commit 4c4d44e2f831ec3296bbfd9f3c9e8b201e6bf18d Author: Sky <[email protected]> Date: Sun Feb 2 21:45:30 2025 +0000 fix commit 8f12beb8f0b65d9b3de009348b0a8b2397e5574c Author: Sky <[email protected]> Date: Sun Feb 2 21:43:30 2025 +0000 support o3-mini commit 2e7cac32185e52f648d30a76a61474951295c0be Author: AndrewS <[email protected]> Date: Sun Feb 2 19:44:53 2025 +0100 chore: add knowledge cut off dates for o1 and o3 commit 60fa358010125894dc85f19618081040eccce15c Author: dupl <[email protected]> Date: Sun Feb 2 23:27:45 2025 +0800 typo: OpanAI -> OpenAI commit 034b7d4655c55ecd5a8e6abd5a130356e4f6b38a Author: dupl <[email protected]> Date: Sun Feb 2 23:11:07 2025 +0800 add gemini-2.0-flash-thinking-exp, gemini-2.0-flash-thinking-exp-01-21 commit 1e20b64048769b4a11ec4691670a1a34711d962e Merge: 3ef59930 4f28fca5 Author: RiverRay <[email protected]> Date: Sun Feb 2 20:57:21 2025 +0800 Merge pull request #6121 from ChatGPTNextWeb/feat/support-openai-o3-mini feat(model): add support for OpenAI o3-mini model commit 4f28fca506980306c7d5810d4b6c9365503dce7f Author: Kadxy <[email protected]> Date: Sat Feb 1 15:02:06 2025 +0800 feat: Support OpenAI o3-mini commit 3ef599308512b41134a67a2087111e729b25d35c Merge: 31e52cb4 09ad7c18 Author: RiverRay <[email protected]> Date: Fri Jan 31 08:18:47 2025 +0800 Merge pull request #6119 from ChatGPTNextWeb/Leizhenpeng-patch-3 Update README.md commit 09ad7c187556da8af88fa1adf42bc475e22e50eb Author: RiverRay <[email protected]> Date: Fri Jan 31 08:18:13 2025 +0800 Update README.md commit 31e52cb47e61c4aa39e3f66f94ed0018968f5bd9 Author: RiverRay <[email protected]> Date: Fri Jan 31 06:53:39 2025 +0800 更新 README.md commit 9a69c5bd7c6bd496e3920f9d87bc8899737c25f2 Merge: c41e86fa be645aab Author: RiverRay <[email protected]> Date: Fri Jan 31 06:48:00 2025 +0800 Merge pull request #6118 from ChatGPTNextWeb/feat/issue-6104-deepseek-reasoning-content commit be645aab37121ed488ce0c0e41c6d41a0e32c39d Author: Kadxy <[email protected]> Date: Fri Jan 31 00:59:03 2025 +0800 fix: revert unintended changes commit c41e86faa6aea948811770d1871f4ca034c6fefd Merge: 553b8c9f 143be69a Author: RiverRay <[email protected]> Date: Fri Jan 31 00:52:18 2025 +0800 Merge pull request #6116 from ChatGPTNextWeb/feat/issue-6104-deepseek-reasoning-content Support DeepSeek API streaming reasoning content commit 143be69a7ffc68f5498328152c6eb6aaa67294fe Author: river <[email protected]> Date: Fri Jan 31 00:50:03 2025 +0800 chore: remove log commit 63b7626656d2d8a221aa9edb491bf6912460e449 Author: river <[email protected]> Date: Fri Jan 31 00:49:09 2025 +0800 chore: change md commit dabb7c70d5e4438b3f6f8cd67ed729c966d3da37 Author: Kadxy <[email protected]> Date: Fri Jan 31 00:30:08 2025 +0800 feat: Remove reasoning_contentfor DeepSeek API messages commit c449737127dcdde4547a8b0caa6070ab1c17b45c Author: Kadxy <[email protected]> Date: Fri Jan 31 00:07:52 2025 +0800 feat: Support DeepSeek API streaming with thinking mode commit 553b8c9f284bff6ec059b4d69f3f91c10105fbc0 Author: RiverRay <[email protected]> Date: Mon Jan 27 13:05:17 2025 +0800 Update .env.template commit 19314793b8d379cb9936b6ba1205bd701f48c320 Merge: 2f9cb5a6 86801829 Author: river <[email protected]> Date: Mon Jan 27 12:55:31 2025 +0800 Merge branch 'bestsanmao-bug_fix' commit 86801829215e8efd5f935eb8221b104a6456c177 Author: river <[email protected]> Date: Mon Jan 27 12:48:59 2025 +0800 feat: Add DeepSeek API key and fix MCP environment variable parsing commit 2173c82bb55e1cd7c7bf994dcb6e0d7484c71daf Author: suruiqiang <[email protected]> Date: Thu Jan 23 18:47:22 2025 +0800 add deepseek-reasoner, and change deepseek's summary model to deepseek-chat commit 0d5e66a9aeca9dd454df46fbdd1f12d69ba9b5a2 Author: suruiqiang <[email protected]> Date: Thu Jan 23 18:24:38 2025 +0800 not insert mcpSystemPrompt if not ENABLE_MCP commit 2f9cb5a68f59c512508a341f76b30f807d1e17fe Merge: 6a862372 55cacfb7 Author: RiverRay <[email protected]> Date: Wed Jan 22 21:40:37 2025 +0800 Merge pull request #6084 from ChatGPTNextWeb/temp-fix fix: missing mcp_config.json files required for building commit 55cacfb7e22034f15bb3541813ad6f3f621f2fcc Author: Kadxy <[email protected]> Date: Wed Jan 22 21:28:29 2025 +0800 fix: missing files required for building commit 6a862372f7e4b1d8b188fd97d016081dc371cbdb Merge: b2b6fd81 81bd83eb Author: RiverRay <[email protected]> Date: Wed Jan 22 13:11:11 2025 +0800 Merge pull request #6082 from ChatGPTNextWeb/Leizhenpeng-patch-2 Update README_CN.md commit 81bd83eb444ed5d0ebd6f7169de5944549bda32d Author: RiverRay <[email protected]> Date: Wed Jan 22 13:08:33 2025 +0800 Update README_CN.md commit b2b6fd81bedeb55043a13ec41ee6775df48ef5b3 Merge: 8111acff f22cfd7b Author: RiverRay <[email protected]> Date: Mon Jan 20 10:44:46 2025 +0800 Merge pull request #6075 from Kadxy/main commit f22cfd7b33a81c8f245001ccd772c94a6162a54b Author: Kadxy <[email protected]> Date: Mon Jan 20 10:10:52 2025 +0800 Update chat.tsx commit 8111acff34189ab980baca279c4fa811f63aac8b Author: RiverRay <[email protected]> Date: Mon Jan 20 00:17:47 2025 +0800 Update README.md commit 4cad55379d8b32d6b46c2f6c7bd42a8f3dd17877 Merge: 93652db6 a3d3ce3f Author: RiverRay <[email protected]> Date: Mon Jan 20 00:07:41 2025 +0800 Merge pull request #5974 from ChatGPTNextWeb/feat-mcp Support MCP( WIP) commit a3d3ce3f4cb95837811deb366459f40447f7af6d Merge: 611e97e6 93652db6 Author: Kadxy <[email protected]> Date: Sun Jan 19 23:28:12 2025 +0800 Merge branch 'main' into feat-mcp commit 611e97e641d9d8b6c80e36da29fa21a2705f972d Author: Kadxy <[email protected]> Date: Sun Jan 19 23:20:58 2025 +0800 docs: update README.md commit bfeea4ed4996c103d5ee36a908d6726e82472300 Author: Kadxy <[email protected]> Date: Sun Jan 19 01:02:01 2025 +0800 fix: prevent MCP operations from blocking chat interface commit bc71ae247bd1110658aef933eaf301b344181122 Author: Kadxy <[email protected]> Date: Sat Jan 18 21:19:01 2025 +0800 feat: add ENABLE_MCP env var to toggle MCP feature globally and in Docker commit 0112b54bc7b0d929b6f127daf00cfb0f2e05d1bc Author: Kadxy <[email protected]> Date: Thu Jan 16 22:35:26 2025 +0800 fix: missing en translation commit 65810d918bb599716e35c8ea515a265da909cf2f Author: Kadxy <[email protected]> Date: Thu Jan 16 21:30:15 2025 +0800 feat: improve async operations and UI feedback commit 4d535b1cd0c641d573a97e03fb5d9cb84a9f5ce5 Author: river <[email protected]> Date: Thu Jan 16 20:54:24 2025 +0800 chore: enhance mcp prompt commit 588d81e8f19047110a87196259df9fc2e8dbc0ce Author: Kadxy <[email protected]> Date: Thu Jan 16 09:17:08 2025 +0800 feat: remove unused files commit d4f499ee41c8ab1c044fb690b980dc3d903d4e25 Author: Kadxy <[email protected]> Date: Thu Jan 16 09:11:53 2025 +0800 feat: adjust form style commit 4d63d73b2e8b7b382a4cc1f60fdd20cb8c5f953a Author: Kadxy <[email protected]> Date: Thu Jan 16 09:00:57 2025 +0800 feat: load MCP preset data from server commit 07c63497dcbacee489d24db890281f84c2793e78 Author: Kadxy <[email protected]> Date: Thu Jan 16 08:52:54 2025 +0800 feat: support stop/start MCP servers commit e440ff56c89d11b29cdbb303eb8a9a71cddc2553 Author: Kadxy <[email protected]> Date: Wed Jan 15 18:47:05 2025 +0800 fix: env not work commit c89e4883b29142cfcb9254b7ff9815a5fe0b8d67 Author: river <[email protected]> Date: Wed Jan 15 17:31:18 2025 +0800 chore: update icon commit ac3d940de8d949e40a91d903d17901384d55e79c Merge: a70e9a3c be59de56 Author: river <[email protected]> Date: Wed Jan 15 17:29:43 2025 +0800 Merge branch 'feat-mcp' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web into feat-mcp commit be59de56f0074c4fde7358465f844d09b48ab273 Author: Kadxy <[email protected]> Date: Wed Jan 15 17:24:04 2025 +0800 feat: Display the number of clients instead of the number of available tools. commit a70e9a3c01dccb887fc41c3d60f2c101d0b1cf2e Author: river <[email protected]> Date: Wed Jan 15 17:23:10 2025 +0800 chore：update mcp icon commit 8aa9a500fdee762abe5fd8e0bba00065be1725f4 Author: Kadxy <[email protected]> Date: Wed Jan 15 16:52:54 2025 +0800 feat: Optimize MCP configuration logic commit 93652db688d2697abc7a6d4bdbe672fb8b509e33 Author: RiverRay <[email protected]> Date: Mon Jan 13 16:57:50 2025 +0800 Update README.md commit 8421c483e880d39405404ba1697a2169becee9f3 Author: RiverRay <[email protected]> Date: Sun Jan 12 12:56:13 2025 +0800 Update README.md commit 4ac27fdd4d98e6d339976b676b5be709973014cf Merge: b6b2c501 840c151a Author: Dogtiti <[email protected]> Date: Sat Jan 11 16:19:02 2025 +0800 Merge pull request #6033 from lvguanjun/fix_fork_session fix: prevent message sync between forked sessions by generating unique IDs commit b6b2c501fd58c8b533ff7890c00ce8eee887617d Merge: 0af04e0f c56587c4 Author: Dogtiti <[email protected]> Date: Sat Jan 11 16:17:32 2025 +0800 Merge pull request #6034 from dupl/main Correct the typos in user-manual-cn.md commit ce13cf61a74f7b0682c230efed2742db91c7d1b7 Author: Kadxy <[email protected]> Date: Thu Jan 9 20:15:47 2025 +0800 feat: ignore mcp_config.json commit a3af563e894286654bf1e7cf1f66190d9c467a79 Author: Kadxy <[email protected]> Date: Thu Jan 9 20:13:16 2025 +0800 feat: Reset mcp_config.json to empty commit e95c94d7be72490668d8e022fd126cfe637b5f2a Author: Kadxy <[email protected]> Date: Thu Jan 9 20:10:10 2025 +0800 fix: inaccurate content commit 125a71feade05ad5f5a75dc8f979c1efc946cdab Author: Kadxy <[email protected]> Date: Thu Jan 9 20:07:24 2025 +0800 fix: unnecessary initialization commit b410ec399cefc78b7313ff387537edbe87ef4235 Author: Kadxy <[email protected]> Date: Thu Jan 9 20:02:27 2025 +0800 feat: auto scroll to bottom when MCP response commit 7d51bfd42e0f60a328abed353ab1ef717b6f3ba8 Author: Kadxy <[email protected]> Date: Thu Jan 9 19:51:01 2025 +0800 feat: MCP market commit 0c14ce6417821d512d04dec5a5755bf35deed51d Author: Kadxy <[email protected]> Date: Thu Jan 9 13:41:17 2025 +0800 fix: MCP execution content matching failed. commit f2a2b40d2c07172db28cdd685fa8c9098c995acc Author: Kadxy <[email protected]> Date: Thu Jan 9 10:20:56 2025 +0800 feat: carry mcp primitives content as a system prompt commit 77be190d763189915c520d431fc4aa889ca96c7e Author: Kadxy <[email protected]> Date: Thu Jan 9 10:09:46 2025 +0800 feat: carry mcp primitives content as a system prompt commit c56587c438611e55251d930d038878e660145ad1 Author: dupl <[email protected]> Date: Sun Jan 5 20:34:18 2025 +0800 Correct the typos in user-manual-cn.md commit 840c151ab9ea7e384be37b774ea339264b5c0dc6 Author: lvguanjun <[email protected]> Date: Sun Jan 5 11:22:53 2025 +0800 fix: prevent message sync between forked sessions by generating unique IDs commit 0af04e0f2f5af2c39cdd771b2ebb496d9ca47f28 Merge: 63c5baaa d184eb64 Author: RiverRay <[email protected]> Date: Tue Dec 31 16:23:10 2024 +0800 Merge pull request #5468 from DDMeaqua/feat-shortcutkey feat: #5422 快捷键清除上下文 commit d184eb64585562de7f75e1ff7d291eb242b2f076 Author: DDMeaqua <[email protected]> Date: Tue Dec 31 14:50:54 2024 +0800 chore: cmd + shift+ backspace commit c5d9b1131ec932e53cd0394c283e24549f6426cb Author: DDMeaqua <[email protected]> Date: Tue Dec 31 14:38:58 2024 +0800 fix: merge bug commit e13408dd2480c1726d0333d8ede3a937187f7991 Merge: aba4baf3 63c5baaa Author: DDMeaqua <[email protected]> Date: Tue Dec 31 14:30:09 2024 +0800 Merge branch 'main' into feat-shortcutkey commit aba4baf38403dd717ee04f5555ba81749d9ee6c8 Author: DDMeaqua <[email protected]> Date: Tue Dec 31 14:25:43 2024 +0800 chore: update commit 6d84f9d3ae62da0c5d1617645f961d9f9e1a1a27 Author: DDMeaqua <[email protected]> Date: Tue Dec 31 13:27:15 2024 +0800 chore: update commit 63c5baaa80878cb4c1a883ed658e8115b8006dce Merge: defefba9 266e9efd Author: Dogtiti <[email protected]> Date: Tue Dec 31 09:56:46 2024 +0800 Merge pull request #6010 from code-october/fix-visionModels 修复 VISION_MDOELS 在 docker 运行阶段不生效的问题 commit defefba925ef20b639d04cbab1ca3fdad3919eb6 Merge: d56566cd 90c531c2 Author: Dogtiti <[email protected]> Date: Mon Dec 30 19:27:20 2024 +0800 Merge pull request #6016 from bestsanmao/add_deepseek fix issue #6009 add setting items for deepseek commit 90c531c2249c1e2070e4f605d25a8e31c315ebdb Author: suruiqiang <[email protected]> Date: Mon Dec 30 18:23:18 2024 +0800 fix issue #6009 add setting items for deepseek commit 266e9efd2e004664d73f0aa7f93a8684c0e5c55e Author: code-october <[email protected]> Date: Mon Dec 30 09:13:12 2024 +0000 rename the function commit 57c88c0717bf21f29395642f32a306dc2388018d Author: code-october <[email protected]> Date: Mon Dec 30 08:58:41 2024 +0000 修复 VISION_MDOELS 在 docker 运行阶段不生效的问题 commit 5b5dea1c59605f26b382d780b5a558169d1a1021 Author: DDMeaqua <[email protected]> Date: Mon Dec 30 12:11:50 2024 +0800 chore: 更换快捷键 commit d56566cd73b1936a66f3ad2e8a30dd351aa96464 Merge: f9e9129d b5d104c9 Author: Dogtiti <[email protected]> Date: Mon Dec 30 09:42:22 2024 +0800 Merge pull request #6001 from bestsanmao/add_deepseek docs: add DEEPSEEK_API_KEY and DEEPSEEK_URL in README commit b5d104c908fb9442ddadb9bd4e544b7fa974c9fd Merge: 2a8a1839 f9e9129d Author: suruiqiang <[email protected]> Date: Mon Dec 30 09:04:40 2024 +0800 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web into add_deepseek commit f9e9129d527a644d8baad97e12ece04601035b2c Author: RiverRay <[email protected]> Date: Sun Dec 29 19:57:27 2024 +0800 Update README.md commit 2a8a18391ebc563a9a552dfdac8a0a66d833e0d7 Author: suruiqiang <[email protected]> Date: Sun Dec 29 15:31:50 2024 +0800 docs: add DEEPSEEK_API_KEY and DEEPSEEK_URL in README commit e1cb8e36fab99faa1e60fecc6d7fd57607177cd2 Merge: c0062ff2 67338ff9 Author: Dogtiti <[email protected]> Date: Sun Dec 29 12:35:21 2024 +0800 Merge pull request #5989 from bestsanmao/add_deepseek since #5984, add DeepSeek as a new ModelProvider (with deepseek-chat&deepseek-coder models), so that user can use openai and deepseek at same time with different api url & key commit b948d6bf86ba4410c854a3c73df275c42be89baa Author: suruiqiang <[email protected]> Date: Sun Dec 29 11:24:57 2024 +0800 bug fix commit fe67f79050c7f4b8971f9b9aabc22c5fd23bac07 Author: Kadxy <[email protected]> Date: Sun Dec 29 09:24:52 2024 +0800 feat: MCP message type commit 67338ff9b73eebe5f8fcc317f0f3d93d32bff836 Author: suruiqiang <[email protected]> Date: Sun Dec 29 08:58:45 2024 +0800 add KnowledgeCutOffDate for deepseek commit 7380c8a2c10bfd314f5a1afd1e5b1b401733e485 Merge: 081daf93 c0062ff2 Author: suruiqiang <[email protected]> Date: Sun Dec 29 08:43:25 2024 +0800 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web into add_deepseek commit e1ba8f1b0f122a73194b2f3716fdb78173647e05 Author: Kadxy <[email protected]> Date: Sun Dec 29 08:29:02 2024 +0800 feat: Send MCP response as a user commit c0062ff2802a6d921895517aa4ab17b1c897fe72 Merge: f8b10ad8 39e593da Author: Dogtiti <[email protected]> Date: Sun Dec 29 00:22:13 2024 +0800 Merge pull request #5998 from dupl/main Use regular expressions to make the code more concise. commit 39e593da48cf63df840e9133e9ee4ad5f8dbc986 Author: dupl <[email protected]> Date: Sat Dec 28 23:49:28 2024 +0800 Use regular expressions to make the code more concise. commit f8b10ad8b173927861c6d1df12e07470465c9a1e Merge: 5f96804f 8a22c9d6 Author: Dogtiti <[email protected]> Date: Sat Dec 28 23:34:44 2024 +0800 Merge pull request #5997 from ChatGPTNextWeb/feature/glm-4v feature: support glm-4v commit 8a22c9d6dbe2d1e041c9f9daed5768a8bdd0f7a9 Author: Dogtiti <[email protected]> Date: Sat Dec 28 23:29:39 2024 +0800 feature: support glm-4v commit 5f96804f3b1155fc870547a79588c0856283b66a Merge: 13430ea3 93c5320b Author: RiverRay <[email protected]> Date: Sat Dec 28 22:05:37 2024 +0800 Merge pull request #5920 from fishshi/i18n Use i18n for DISCOVERY commit 13430ea3e261290881d1fbf4c65b52624cba9d0b Merge: 9df24e56 87b5e3bf Author: RiverRay <[email protected]> Date: Sat Dec 28 22:02:02 2024 +0800 Merge pull request #5965 from zmhuanf/temp Fix issue #5964: Prevents character loss in gemini-2.0-flash-thinking-exp-1219 responses commit 664879b9df8c431664b06346962cff0319a3e85e Author: Kadxy <[email protected]> Date: Sat Dec 28 21:06:26 2024 +0800 feat: Create all MCP Servers at startup commit 9df24e568b5ec280aa05cb8da7dd29c64f06c0b4 Merge: e467ce02 bc322be4 Author: Dogtiti <[email protected]> Date: Sat Dec 28 20:25:25 2024 +0800 Merge pull request #5996 from ChatGPTNextWeb/feature/cogview Feature/cogview commit bc322be448136a0dcb3f8adf93faae698b28b5d3 Author: Dogtiti <[email protected]> Date: Fri Dec 27 22:35:40 2024 +0800 fix: type error commit a867adaf046395b7a6ee88b402bc1c3c477696f2 Author: Dogtiti <[email protected]> Date: Fri Dec 27 21:57:23 2024 +0800 fix: size commit 0cb186846a03b95dfc4dd0d3b1f25dac48ac1026 Author: Dogtiti <[email protected]> Date: Fri Dec 27 21:52:22 2024 +0800 feature: support glm Cogview commit e467ce028d61f717b86bebf71b9ded1ac41cb3d5 Merge: d91af7f9 cdfe907f Author: Dogtiti <[email protected]> Date: Sat Dec 28 17:55:29 2024 +0800 Merge pull request #5994 from ConnectAI-E/fix/failed-test fix: failed unit test commit cdfe907fb506c467324a5a53e4b33f883a30eba3 Author: Dogtiti <[email protected]> Date: Sat Dec 28 17:54:21 2024 +0800 fix: failed unit test commit d91af7f9831a44a4bcafc9aef8b38dfef5739880 Merge: 0c3d4462 cc5e16b0 Author: Dogtiti <[email protected]> Date: Sat Dec 28 14:47:35 2024 +0800 Merge pull request #5883 from code-october/fix/model-leak fix model leak issue commit c3108ad333419ecb0d16a031d4f4603f0f781832 Author: Kadxy <[email protected]> Date: Sat Dec 28 14:31:43 2024 +0800 feat: simple MCP example commit 081daf937e4c18eb787662ca1a0fad561f54b9c6 Author: suruiqiang <[email protected]> Date: Fri Dec 27 16:46:44 2024 +0800 since #5984, add DeepSeek as a new ModelProvider (with deepseek-chat&deepseek-corder models), so that user can use openai and deepseek at same time with different api url&key commit 0c3d4462caa2abe5187856a2619b871ce8c33488 Merge: 1d156667 3c859fc2 Author: RiverRay <[email protected]> Date: Mon Dec 23 22:47:59 2024 +0800 Merge pull request #5976 from ChatGPTNextWeb/Leizhenpeng-patch-1 Update README.md commit 3c859fc29fc11ac9c229ed024d2d25366b8d2d99 Author: RiverRay <[email protected]> Date: Mon Dec 23 22:47:16 2024 +0800 Update README.md commit e1c7c54dfaf82c37450d0ed3a124f8598bc0249b Author: river <[email protected]> Date: Mon Dec 23 22:32:36 2024 +0800 chore: change md commit 87b5e3bf6252be247b32385a19d9897bede5cdf0 Author: zmhuanf <[email protected]> Date: Sun Dec 22 15:44:47 2024 +0800 修复bug； commit 1d15666713c27f89912cf913387176a76fc00f66 Merge: acc2e97a a127ae1f Author: Dogtiti <[email protected]> Date: Sun Dec 22 10:37:57 2024 +0800 Merge pull request #5919 from Yiming3/feature/flexible-visual-model feat: runtime configuration of vision-capable models commit a127ae1fb45d641b9f138057e56a10ece96b2964 Author: Yiming Zhang <[email protected]> Date: Sat Dec 21 13:12:41 2024 -0500 docs: add VISION_MODELS section to README files commit ea1329f73e516546dab7193425e1e7dfdd232eb6 Author: Yiming Zhang <[email protected]> Date: Sat Dec 21 04:07:58 2024 -0500 fix: add optional chaining to prevent errors when accessing visionModels commit 149d732cb78287c51edcd67d1fd5b16a5f334813 Merge: 210b29bf acc2e97a Author: Yiming Zhang <[email protected]> Date: Sat Dec 21 03:53:05 2024 -0500 Merge remote-tracking branch 'upstream/main' into feature/flexible-visual-model commit 210b29bfbecaebc53c4f37ed23c5df28d28d41fb Author: Yiming Zhang <[email protected]> Date: Sat Dec 21 03:51:54 2024 -0500 refactor: remove NEXT_PUBLIC_ prefix from VISION_MODELS env var commit acc2e97aab7437030db157605796482686a96f90 Merge: eceec092 93ac0e50 Author: Dogtiti <[email protected]> Date: Sat Dec 21 16:30:09 2024 +0800 Merge pull request #5959 from dupl/gemini add gemini-exp-1206, gemini-2.0-flash-thinking-exp-1219 commit 93ac0e501737f8e01d046a367d0aeb0055c15633 Author: dupl <[email protected]> Date: Sat Dec 21 15:26:33 2024 +0800 Reorganized the Gemini model commit ed8c3580c8fce9c12c42e2a8ac086ea2f8887953 Author: Yiming Zhang <[email protected]> Date: Fri Dec 20 19:07:00 2024 -0500 test: add unit tests for isVisionModel utility function commit 0a056a7c5c0be993321174706d8b679e7ffde038 Author: dupl <[email protected]> Date: Sat Dec 21 08:00:37 2024 +0800 add gemini-exp-1206, gemini-2.0-flash-thinking-exp-1219 commit 74c4711cdd2c38c8136490fb27eb878cc1c8b001 Merge: a433d160 eceec092 Author: Yiming Zhang <[email protected]> Date: Fri Dec 20 18:34:07 2024 -0500 Merge remote-tracking branch 'upstream/main' into feature/flexible-visual-model commit eceec092cfc57f4024a8aab3869e39f6eebfef30 Merge: 42743410 46a0b100 Author: Dogtiti <[email protected]> Date: Sat Dec 21 00:43:02 2024 +0800 Merge pull request #5932 from fengzai6/update-google-models Update google models to add gemini-2.0 commit 42743410a8ce5028cc359863c97baddc16ad8d64 Merge: 0f04756d acdded81 Author: Dogtiti <[email protected]> Date: Sat Dec 21 00:41:45 2024 +0800 Merge pull request #5940 from ChatGPTNextWeb/dependabot/npm_and_yarn/testing-library/react-16.1.0 chore(deps-dev): bump @testing-library/react from 16.0.1 to 16.1.0 commit 0f04756d4cda9b2bfd0308c72652268b3ec8b5b3 Merge: 83cea3a9 e939ce5a Author: Dogtiti <[email protected]> Date: Sat Dec 21 00:40:45 2024 +0800 Merge pull request #5936 from InitialXKO/main 面具“以文搜图”改成“AI文生图”，微调提示让图片生成更稳定无水印 commit acdded8161860def9fe0f3806798bcdc57754644 Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon Dec 16 10:57:34 2024 +0000 chore(deps-dev): bump @testing-library/react from 16.0.1 to 16.1.0 Bumps [@testing-library/react](https://github.com/testing-library/react-testing-library) from 16.0.1 to 16.1.0. - [Release notes](https://github.com/testing-library/react-testing-library/releases) - [Changelog](https://github.com/testing-library/react-testing-library/blob/main/CHANGELOG.md) - [Commits](https://github.com/testing-library/react-testing-library/compare/v16.0.1...v16.1.0) --- updated-dependencies: - dependency-name: "@testing-library/react" dependency-type: direct:development update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]> commit e939ce5a027150d2481508691e1c4f818a4f9130 Author: InitialXKO <[email protected]> Date: Fri Dec 13 22:29:14 2024 +0800 面具“以文搜图”改成“AI文生图”，微调提示让图片生成更稳定无水印 commit 46a0b100f73058d651b884341b43e126e2c04a00 Author: Nacho.L <[email protected]> Date: Fri Dec 13 08:29:43 2024 +0800 Update versionKeywords commit e27e8fb0e16ee61865d11606682f2c4cbd075e73 Author: Nacho.L <[email protected]> Date: Fri Dec 13 07:22:16 2024 +0800 Update google models commit 93c5320bf29a8da64e12d3870ea932631ad51b2a Author: fishshi <[email protected]> Date: Tue Dec 10 15:56:04 2024 +0800 Use i18n for DISCOVERY commit a433d1606cc9f24cec7f7cc0a947e416373a5d7b Author: Yiming Zhang <[email protected]> Date: Tue Dec 10 00:22:45 2024 -0500 feat: use regex patterns for vision models and allow adding capabilities to models through env var NEXT_PUBLIC_VISION_MODELS. commit cc5e16b0454481fab48b1115eda9b8fb11ce0054 Author: code-october <[email protected]> Date: Sat Nov 30 07:30:52 2024 +0000 update unit test commit 54f6feb2d74b9ac81fa5f826f24f73929c7cb238 Author: code-october <[email protected]> Date: Sat Nov 30 07:28:38 2024 +0000 update unit test commit e1ac0538b8143f93074c1c248a5739358b3ddfd1 Author: code-october <[email protected]> Date: Sat Nov 30 07:22:24 2024 +0000 add unit test commit 1a678cb4d832fe47f5d04e614bb267907bbf2677 Author: code-october <[email protected]> Date: Fri Nov 29 15:47:28 2024 +0000 fix model leak issue commit 83cea3a90d115f9564d96f6a6af400f467f2d3b4 Merge: 2623a927 759a09a7 Author: Dogtiti <[email protected]> Date: Thu Nov 28 12:02:42 2024 +0800 Merge pull request #5879 from frostime/textline-custom-model 🎨 style(setting): Place custom-model's input a separated row. commit 759a09a76c8c6cd97cd4546da022f38f426618f2 Author: frostime <[email protected]> Date: Wed Nov 27 13:11:18 2024 +0800 🎨 style(setting): Place custom-model's input a seperated row. commit 2623a9276388668d65f34e1ad2206bec55acde79 Merge: 3932c594 ef24d3e6 Author: Dogtiti <[email protected]> Date: Mon Nov 25 12:31:36 2024 +0800 Merge pull request #5850 from code-october/fix-o1 Fix o1 commit 3932c594c71a4d52968c5bd19ab75cba2197ea76 Merge: a2adfbbd b7acb890 Author: Dogtiti <[email protected]> Date: Fri Nov 22 20:59:30 2024 +0800 Merge pull request #5861 from code-october/update-model update new model for gpt-4o and gemini-exp commit b7acb890969fe5af9135bb49533fad610ac52e69 Author: code-october <[email protected]> Date: Fri Nov 22 09:48:50 2024 +0000 update new model for gpt-4o and gemini-exp commit ef24d3e63360eea8868334f884d83f747cfd8f73 Author: code-october <[email protected]> Date: Thu Nov 21 03:46:10 2024 +0000 use stream when request o1 commit 23350c842b1b102ebdbb17ccbb2b5cfa7b25b893 Author: code-october <[email protected]> Date: Thu Nov 21 03:45:07 2024 +0000 fix o1 in disableGPT4 commit a2adfbbd3242cb38c685c48a1a8d2cba2c2b28cd Merge: f22cec1e 19facc7c Author: Dogtiti <[email protected]> Date: Sat Nov 16 15:24:46 2024 +0800 Merge pull request #5821 from Sherlocksuper/scroll feat: support more user-friendly scrolling commit f22cec1eb4a92fc9c388595ba3ca23d2820ba56e Merge: b08ce563 e5621654 Author: Lloyd Zhou <[email protected]> Date: Fri Nov 15 16:03:27 2024 +0800 Merge pull request #5827 from ConnectAI-E/fix/markdown-embed-codeblock fix: 代码块嵌入小代码块时渲染错误 commit e56216549efe58c1b734f5094eb77bfaa6654c69 Author: opchips <[email protected]> Date: Fri Nov 15 11:56:26 2024 +0800 fix: 代码块嵌入小代码块时渲染错误 commit 19facc7c85a0e509b5d4ca1eaa98782f29477c9a Author: Sherlock <[email protected]> Date: Thu Nov 14 21:31:45 2024 +0800 feat: support mort user-friendly scrolling commit b08ce5630c5c24491459cca2e3bcc9c8b6a68114 Merge: a392daab b41c012d Author: Lloyd Zhou <[email protected]> Date: Wed Nov 13 15:17:44 2024 +0800 Merge pull request #5819 from ConnectAI-E/fix-gemini-summary Fix gemini summary commit b41c012d27d5495bec12f6aa6f9537ebb6873083 Author: DDMeaqua <[email protected]> Date: Wed Nov 13 15:12:46 2024 +0800 chore: shouldStream commit a392daab716d66a7a9fb95e30e2574bf87716bb4 Merge: 819d249a 9a86c42c Author: Lloyd Zhou <[email protected]> Date: Wed Nov 13 14:58:33 2024 +0800 Merge pull request #5816 from ConnectAI-E/feature/artifacts-svg artifacts support svg commit 0628ddfc6f36479650d50281e3fa0ba1a847f777 Author: DDMeaqua <[email protected]> Date: Wed Nov 13 14:27:41 2024 +0800 chore: update commit 7eda14f13882be635c9e6e5b8077617df8c5339b Author: DDMeaqua <[email protected]> Date: Wed Nov 13 14:24:44 2024 +0800 fix: [#5308] gemini对话总结 commit 9a86c42c95be5b2bb85f44c0bdeb7714dc526a49 Author: opchips <[email protected]> Date: Tue Nov 12 16:33:55 2024 +0800 update commit 819d249a099ba84017afc5b5c20ae8309889b060 Merge: 7cf89b53 8d66fedb Author: Lloyd Zhou <[email protected]> Date: Tue Nov 12 15:04:11 2024 +0800 Merge pull request #5815 from LovelyGuYiMeng/main 更新视觉模型匹配关键词 commit 8d66fedb1f5093d6e29ac06a839316edb535512d Author: LovelyGuYiMeng <[email protected]> Date: Tue Nov 12 14:28:11 2024 +0800 Update visionKeywords commit 7cf89b53ce129ec3c51181571b34b658894673b2 Merge: 459c373f 1d14a991 Author: Lloyd Zhou <[email protected]> Date: Tue Nov 12 13:49:51 2024 +0800 Merge pull request #5812 from ConnectAI-E/fix/rerender-chat fix: use current session id to trigger rerender commit 459c373f130d04cec80761a81cbb651afc485135 Merge: 38fa3056 05ef5adf Author: Dogtiti <[email protected]> Date: Mon Nov 11 20:59:56 2024 +0800 Merge pull request #5807 from ChatGPTNextWeb/dependabot/npm_and_yarn/testing-library/jest-dom-6.6.3 chore(deps-dev): bump @testing-library/jest-dom from 6.6.2 to 6.6.3 commit 1d14a991eedb17a492d6e840de71567c8a6884a7 Author: Dogtiti <[email protected]> Date: Mon Nov 11 20:30:59 2024 +0800 fix: use current session id to trigger rerender commit 05ef5adfa72d2a519a07c36aca4e6c1a965da7d2 Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon Nov 11 10:53:00 2024 +0000 chore(deps-dev): bump @testing-library/jest-dom from 6.6.2 to 6.6.3 Bumps [@testing-library/jest-dom](https://github.com/testing-library/jest-dom) from 6.6.2 to 6.6.3. - [Release notes](https://github.com/testing-library/jest-dom/releases) - [Changelog](https://github.com/testing-library/jest-dom/blob/main/CHANGELOG.md) - [Commits](https://github.com/testing-library/jest-dom/compare/v6.6.2...v6.6.3) --- updated-dependencies: - dependency-name: "@testing-library/jest-dom" dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]> commit 38fa3056df5fd9db915a9d4d1c5e11477de22ff6 Author: lloydzhou <[email protected]> Date: Mon Nov 11 13:26:08 2024 +0800 update version commit 289aeec8af234f2ff6092722f2ea955c5768f342 Merge: f8f69541 7d71da93 Author: Lloyd Zhou <[email protected]> Date: Mon Nov 11 13:19:26 2024 +0800 Merge pull request #5786 from ConnectAI-E/feature/realtime-chat Feature/realtime chat commit 7d71da938fab927758f6c80921c4eee371deec70 Author: lloydzhou <[email protected]> Date: Mon Nov 11 13:15:09 2024 +0800 remove close-24 svg commit f8f6954115a5fd0caad88470a530ff7c2378c43a Merge: 6e03f328 64aa760e Author: Lloyd Zhou <[email protected]> Date: Mon Nov 11 13:13:09 2024 +0800 Merge pull request #5779 from ConnectAI-E/feature/model/claude35haiku add claude35haiku & not support vision commit 6e03f3287123bb0bffc2aafd0f0a3c72566540a2 Merge: 108069a0 18a65718 Author: Lloyd Zhou <[email protected]> Date: Mon Nov 11 13:10:00 2024 +0800 Merge pull request #5795 from JingSyue/main fix: built-in plugin dalle3 error #5787 commit 18a657188339ac96905f0eaadd0583fdd6001f65 Author: JingSyue <[email protected]> Date: Mon Nov 11 12:59:29 2024 +0800 Update proxy.ts Update proxy.ts commit 14f444e1f0ca4253b65534140f9239d0504e1af6 Author: Dogtiti <[email protected]> Date: Mon Nov 11 11:47:41 2024 +0800 doc: realtime chat commit 2b0f2e5f9d064bc8107414b0c2e7efe61c03cdef Author: JingSyue <[email protected]> Date: Sun Nov 10 10:28:25 2024 +0800 fix: built-in plugin dalle3 error #5787 commit 4629b39c297f51cf1a7e1685c62043578f653d21 Author: Dogtiti <[email protected]> Date: Sat Nov 9 16:22:01 2024 +0800 chore: comment context history commit d33e772fa592c24e4adc03f127c887c9e4727913 Author: Dogtiti <[email protected]> Date: Fri Nov 8 22:39:17 2024 +0800 feat: voice print commit 89136fba32dbf731e4aaed03508684cfeb54614b Author: Dogtiti <[email protected]> Date: Fri Nov 8 22:18:39 2024 +0800 feat: voice print commit 8b4ca133fda68ed7034ee5bbae8d622d66bf81f9 Author: Dogtiti <[email protected]> Date: Fri Nov 8 22:02:31 2024 +0800 feat: voice print commit a4c9eaf6cd5f889fc77877885a52d45866579841 Author: lloydzhou <[email protected]> Date: Fri Nov 8 13:43:13 2024 +0800 do not save empty audio file commit 50e63109a35b6aff7056c129e30d745d74835226 Author: lloydzhou <[email protected]> Date: Fri Nov 8 13:21:40 2024 +0800 merge code and get analyser data commit 48a1e8a58469eceb92dfa41559638ad2583fca70 Author: Dogtiti <[email protected]> Date: Thu Nov 7 21:32:47 2024 +0800 chore: i18n commit e44ebe3f0eda9ab6f08dc6a58601e333dd46101b Author: Dogtiti <[email protected]> Date: Thu Nov 7 21:28:23 2024 +0800 feat: realtime config commit 108069a0c6d1689c089ed2257a8e085c754a25b9 Merge: fbb9385f d5bda290 Author: Lloyd Zhou <[email protected]> Date: Thu Nov 7 20:06:30 2024 +0800 Merge pull request #5788 from ConnectAI-E/fix-o1-maxtokens chore: o1模型使用max_completion_tokens commit d5bda2904dcb7279d4addff8bbc93cb206fdc7d6 Author: DDMeaqua <[email protected]> Date: Thu Nov 7 19:45:27 2024 +0800 chore: o1模型使用max_completion_tokens commit 283caba8ce0e874e1876e6ef83a8d380e83f985f Author: lloydzhou <[email protected]> Date: Thu Nov 7 18:57:57 2024 +0800 stop streaming play after get input audio. commit b78e5db81759ada7bb2813ae17d2d94bfae47d68 Author: lloydzhou <[email protected]> Date: Thu Nov 7 17:55:51 2024 +0800 add temperature config commit 46c469b2d7b95d21c8dc2c4c239c0646f3b43665 Author: lloydzhou <[email protected]> Date: Thu Nov 7 17:47:55 2024 +0800 add voice config commit c00ebbea4f774e15358c0a9410f807177931cff0 Author: lloydzhou <[email protected]> Date: Thu Nov 7 17:40:03 2024 +0800 update commit c526ff80b50ae2e284230093f0c51dc415b5cb46 Author: lloydzhou <[email protected]> Date: Thu Nov 7 17:23:20 2024 +0800 update commit 0037b0c94414c10b78ec2a152b36adc1d35bda2f Author: lloydzhou <[email protected]> Date: Thu Nov 7 17:03:04 2024 +0800 ts error commit 6f81bb3b8a18f370cf3225c3c26fcaf7522e1317 Author: lloydzhou <[email protected]> Date: Thu Nov 7 16:56:15 2024 +0800 add context after connected commit 7bdc45ed3eb62833fee131ce93165823c1e4459f Author: lloydzhou <[email protected]> Date: Thu Nov 7 16:41:24 2024 +0800 connect realtime model when open panel commit 88cd3ac122cfe0a93f3c87e441d9e1e59c8bfb33 Author: Dogtiti <[email protected]> Date: Thu Nov 7 12:16:11 2024 +0800 fix: ts error commit 4988d2ee26f5cd65b128dae8924942c54a9da3ee Author: Dogtiti <[email protected]> Date: Thu Nov 7 11:56:58 2024 +0800 fix: ts error commit 8deb7a92ee7a9f15f749a93216abc789ac502718 Author: lloydzhou <[email protected]> Date: Thu Nov 7 11:53:01 2024 +0800 hotfix for update target session commit db060d732abeab3724f61eeae9ed6f5b4c93c9be Author: lloydzhou <[email protected]> Date: Thu Nov 7 11:45:38 2024 +0800 upload save record wav file commit 522627820a1aa641ee5746930626e8a4153cd611 Author: lloydzhou <[email protected]> Date: Thu Nov 7 09:36:22 2024 +0800 upload save wav file logic commit cf46d5ad63bc13dd4e7f938689fdb3c65a09e929 Author: lloydzhou <[email protected]> Date: Thu Nov 7 01:12:08 2024 +0800 upload response audio, and update audio_url to session message commit a4941521d0973943bbd0abba86dc7295b444f2b5 Author: Dogtiti <[email protected]> Date: Wed Nov 6 22:30:02 2024 +0800 feat: audio to message commit f6e1f8398b261b8d0a65c971e62ac0fa5178e743 Author: Dogtiti <[email protected]> Date: Wed Nov 6 22:07:33 2024 +0800 wip commit d544eead3818f69413de20c25c5f3578439b7a4d Author: Dogtiti <[email protected]> Date: Wed Nov 6 21:14:45 2024 +0800 feat: realtime chat ui commit fbb9385f23246e86147df4c4efb29b2efad893b0 Merge: 6ded4e96 18144c3d Author: Lloyd Zhou <[email protected]> Date: Wed Nov 6 20:33:51 2024 +0800 Merge pull request #5782 from ConnectAI-E/style/classname style: improve classname by clsx commit 18144c3d9c91e8047b5d56ace69fb9e9829f7a78 Author: Dogtiti <[email protected]> Date: Wed Nov 6 20:16:38 2024 +0800 chore: clsx commit 64aa760e58f31ab45ce720b988c859dd53c491ca Author: opchips <[email protected]> Date: Wed Nov 6 19:18:05 2024 +0800 update claude rank commit e0bbb8bb68429d160c50af512eaa5181b50dc2c3 Author: Dogtiti <[email protected]> Date: Wed Nov 6 16:58:26 2024 +0800 style: improve classname by clsx commit 6667ee1c7fe655cd24bd56ed4e8611bfca5978cd Merge: 3086a2fa 6ded4e96 Author: opchips <[email protected]> Date: Wed Nov 6 15:08:18 2024 +0800 merge main commit 6ded4e96e76fd4a9896d49a729520faabb47d112 Merge: f4c9410c 85cdcab8 Author: Lloyd Zhou <[email protected]> Date: Wed Nov 6 15:04:46 2024 +0800 Merge pull request #5778 from ConnectAI-E/fix/5436 fix: botMessage reply date commit 85cdcab850cadbbd346d38b34603e3eb00e3e715 Author: Dogtiti <[email protected]> Date: Wed Nov 6 14:53:08 2024 +0800 fix: botMessage reply date commit f4c9410c29ac5b8d1979566c269ced96b74b2f57 Merge: f526d6f5 adf7d820 Author: Lloyd Zhou <[email protected]> Date: Wed Nov 6 14:02:20 2024 +0800 Merge pull request #5776 from ConnectAI-E/feat-glm fix: glm chatpath commit adf7d8200b63ba9e389c3df2b801b82a272a85bf Author: DDMeaqua <[email protected]> Date: Wed Nov 6 13:55:57 2024 +0800 fix: glm chatpath commit 3086a2fa77d2815af05236bae4a13a4da387730b Author: opchips <[email protected]> Date: Wed Nov 6 12:56:24 2024 +0800 add claude35haiku not vision commit f526d6f56094a5dc3e24b6a608681b2b0842f1d3 Merge: f3603e59 106461a1 Author: Lloyd Zhou <[email protected]> Date: Wed Nov 6 11:16:33 2024 +0800 Merge pull request #5774 from ConnectAI-E/feature/update-target-session fix: updateCurrentSession => updateTargetSession commit 106461a1e72b3c62395903945fac27fe165e9e4b Merge: c4e19dbc f3603e59 Author: Dogtiti <[email protected]> Date: Wed Nov 6 11:08:41 2024 +0800 Merge branch 'main' of https://github.com/ConnectAI-E/ChatGPT-Next-Web into feature/update-target-session commit c4e19dbc59e59b71c81cf33600f7a2be235b0ccc Author: Dogtiti <[email protected]> Date: Wed Nov 6 11:06:18 2024 +0800 fix: updateCurrentSession => updateTargetSession commit f3603e59faa182313a408f58012b0c83eb2b8956 Merge: 00d6cb27 8e2484fc Author: Dogtiti <[email protected]> Date: Wed Nov 6 10:49:28 2024 +0800 Merge pull request #5769 from ryanhex53/fix-model-multi@ Custom model names can include the `@` symbol by itself. commit 8e2484fcdf476a1248ae91541d6d491e5881b49b Author: ryanhex53 <[email protected]> Date: Tue Nov 5 13:52:54 2024 +0000 Refactor: Replace all provider split occurrences with getModelProvider utility method commit 00d6cb27f719caffd24518db3dd656b7380a9062 Author: lloydzhou <[email protected]> Date: Tue Nov 5 17:42:55 2024 +0800 update version commit b844045d231658b9e40fa0582936c6746e7a7ef4 Author: ryanhex53 <[email protected]> Date: Tue Nov 5 07:44:12 2024 +0000 Custom model names can include the `@` symbol by itself. To specify the model's provider, append it after the model name using `@` as before. This format supports cases like `google vertex ai` with a model name like `claude-3-5-sonnet@20240620`. For instance, `claude-3-5-sonnet@20240620@vertex-ai` will be split by `split(/@(?!.*@)/)` into: `[ 'claude-3-5-sonnet@20240620', 'vertex-ai' ]`, where the former is the model name and the latter is the custom provider. commit e49fe976d9bd00106c163766aca915b291cb4956 Merge: 14f75196 e49466fa Author: Lloyd Zhou <[email protected]> Date: Tue Nov 5 15:07:52 2024 +0800 Merge pull request #5765 from ConnectAI-E/feature/onfinish feat: update real 'currentSession' commit 14f751965f7a55bb9896f1a02c066591e8b22057 Merge: 820ab54e 0ec42338 Author: Dogtiti <[email protected]> Date: Tue Nov 5 11:07:52 2024 +0800 Merge pull request #5767 from ConnectAI-E/feat-glm chore: update readme commit 0ec423389fa08e4e4b046db5ad147194622b6218 Author: DDMeaqua <[email protected]> Date: Tue Nov 5 11:06:20 2024 +0800 chore: update readme commit 820ab54e2d8c0ce09c0b88d479b364f998b8d244 Merge: 0dc4071c a6c1eb27 Author: Dogtiti <[email protected]> Date: Tue Nov 5 10:54:52 2024 +0800 Merge pull request #5766 from ConnectAI-E/feature/add-claude-haiku3.5 Feature/add claude haiku3.5 commit a6c1eb27a82f4f18b043a0c382d5f694f8bd63aa Merge: 801dc412 0dc4071c Author: lloydzhou <[email protected]> Date: Tue Nov 5 10:23:15 2024 +0800 add claude 3.5 haiku commit 0dc4071ccce53fed990598da494316a6b199a3ee Merge: aef535f1 4d394971 Author: Lloyd Zhou <[email protected]> Date: Tue Nov 5 01:10:06 2024 +0800 Merge pull request #5464 from endless-learner/main Added 1-click deployment link for Alibaba Cloud. commit 4d3949718a979ff7db1c10d30b7ab66793c95892 Author: Lloyd Zhou <[email protected]> Date: Tue Nov 5 01:09:27 2024 +0800 merge main commit aef535f1a7af3196a90cfc7f1887cfb432ea3d06 Merge: 686a80e7 fbb7a1e8 Author: Dogtiti <[email protected]> Date: Mon Nov 4 21:41:11 2024 +0800 Merge pull request #5753 from ChatGPTNextWeb/feat-bt-doc Feat bt doc commit 686a80e727f13bd828d37bb865742f801611d1e3 Merge: 5733e3c5 4b933708 Author: Dogtiti <[email protected]> Date: Mon Nov 4 21:37:34 2024 +0800 Merge pull request #5764 from ChatGPTNextWeb/dependabot/npm_and_yarn/testing-library/react-16.0.1 chore(deps-dev): bump @testing-library/react from 16.0.0 to 16.0.1 commit e49466fa054c702898780967812abe2dabd4ba6b Author: Dogtiti <[email protected]> Date: Mon Nov 4 21:25:56 2024 +0800 feat: update real 'currentSession' commit 4b93370814b41e256de7cddc6264705883265d56 Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon Nov 4 10:24:30 2024 +0000 chore(deps-dev): bump @testing-library/react from 16.0.0 to 16.0.1 Bumps [@testing-library/react](https://github.com/testing-library/react-testing-library) from 16.0.0 to 16.0.1. - [Release notes](https://github.com/testing-library/react-testing-library/releases) - [Changelog](https://github.com/testing-library/react-testing-library/blob/main/CHANGELOG.md) - [Commits](https://github.com/testing-library/react-testing-library/compare/v16.0.0...v16.0.1) --- updated-dependencies: - dependency-name: "@testing-library/react" dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]> commit 5733e3c588f7467e20cc7782b2327f149c7663e8 Merge: d66bfc63 44fc5b5c Author: Dogtiti <[email protected]> Date: Mon Nov 4 17:16:44 2024 +0800 Merge pull request #5759 from ConnectAI-E/feature/onfinish Feature/onfinish commit 44fc5b5cbf44b7a362a916fbc3b1c3a34cc8e7cb Author: Dogtiti <[email protected]> Date: Mon Nov 4 17:00:45 2024 +0800 fix: onfinish responseRes commit 2d3f7c922f5a3e52da30f45b67a74f0df908e147 Author: Dogtiti <[email protected]> Date: Wed Oct 16 15:17:08 2024 +0800 fix: vision model dalle3 commit fe8cca3730ba261548dfc06ea20b6a0824a7b5da Merge: adf97c6d d66bfc63 Author: GH Action - Upstream Sync <[email protected]> Date: Sat Nov 2 01:12:09 2024 +0000 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web commit fbb7a1e853334a9de54034aa41a18119e4e86028 Author: weige <[email protected]> Date: Fri Nov 1 18:20:16 2024 +0800 fix commit fb2c15567dc218edc1ce4f6bfac746a25607fd9d Author: weige <[email protected]> Date: Fri Nov 1 17:45:50 2024 +0800 fix commit c2c52a1f605f2eeeac1865a7342968a7cfc36cf6 Author: weige <[email protected]> Date: Fri Nov 1 17:35:34 2024 +0800 fix commit 106ddc17cd3267201d4c620c50bfdce641e04ff0 Author: weige <[email protected]> Date: Fri Nov 1 17:35:09 2024 +0800 fix commit 17d5209738a114db34484838c18786924430cc5c Author: weige <[email protected]> Date: Fri Nov 1 17:28:20 2024 +0800 add bt install doc commit d66bfc6352fd2aea34eaaeeb15e109206549b75e Merge: 36bfa2ef 4d75b23e Author: Dogtiti <[email protected]> Date: Fri Nov 1 14:16:50 2024 +0800 Merge pull request #5752 from ConnectAI-E/feat-glm fix: ts error commit 4d75b23ed1b41a042e28805e46ad2b5c8111cc3d Author: DDMeaqua <[email protected]> Date: Fri Nov 1 14:15:12 2024 +0800 fix: ts error commit 36bfa2ef7c4638c55fe12579f7751310db1f422c Merge: 0581e372 afe12c21 Author: Dogtiti <[email protected]> Date: Fri Nov 1 13:57:30 2024 +0800 Merge pull request #5741 from ConnectAI-E/feat-glm feat: [#5714] 支持GLM commit afe12c212e51bd2d27c5db5700f881c32a0bd3ba Author: DDMeaqua <[email protected]> Date: Fri Nov 1 13:53:43 2024 +0800 chore: update commit adf97c6d8bbce8c705437fb8251b87eea574e755 Merge: 7c466c9b 0581e372 Author: GH Action - Upstream Sync <[email protected]> Date: Fri Nov 1 01:18:59 2024 +0000 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web commit 7a8d557ea37e9b02fc26d8416fc631f4b7adda56 Author: DDMeaqua <[email protected]> Date: Thu Oct 31 11:37:19 2024 +0800 chore: 开启插件 commit d3f0a77830073684dd8da25e34d5d8eb0a94ecdb Author: DDMeaqua <[email protected]> Date: Thu Oct 31 11:23:06 2024 +0800 chore: update Provider commit 0581e37236a11b7d7925be25fe44320445914f7e Merge: a0fa4d7e 44383a8b Author: Dogtiti <[email protected]> Date: Thu Oct 31 11:19:34 2024 +0800 Merge pull request #5744 from mrcore/main add claude-3-5-sonnet-latest and claude-3-opus-latest commit 44383a8b331ed283f06213c5176bf60fe98bbcc0 Author: Core <[email protected]> Date: Thu Oct 31 11:00:45 2024 +0800 add claude-3-5-sonnet-latest and claude-3-opus-latest add claude-3-5-sonnet-latest and claude-3-opus-latest commit 7c466c9b9c29a1823a19c05aeba4ba2f348e8455 Merge: b0d28eb7 a0fa4d7e Author: GH Action - Upstream Sync <[email protected]> Date: Thu Oct 31 01:14:28 2024 +0000 Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web commit a0fa4d7e7251c66e048825d770f8b107095191e7 Merge: d0bd1bf8 736cbdbd Author: Dogtiti <[email protected]> Date: Thu Oct 31 00:13:16 2024 +0800 Merge pull request #5737 from hyiip/claude3.5 add constant to claude 3.5 sonnet 20241022 commit d357b45e84eb773c2e0c142d0d849c4f20be2975 Author: DDMeaqua <[email protected]> Date: Wed Oct 30 19:24:03 2024 +0800 feat: [#5714] 支持GLM commit d0bd1bf8fd1a87ede56859b3d5b6a64e8ce461d2 Merge: 613d67ea 86ffa1e6 Author: Lloyd Zhou <[email protected]> Date: Wed Oct 30 16:56:53 2024 +0800 Merge pull request #5740 from yuxuan-ctrl/main feat: 新增阿里系模型代码配置 commit 86ffa1e6430b0a34893665bb284130c1f144e399 Author: yuxuan-ctrl <[email protected]> Date: Wed Oct 30 16:30:01 2024 +0800 feat: 新增阿里系模型代码配置 commit b0d28eb77ebec3a58f57605fb79fdf38e282e22a Merge: 064e964d 613d67ea Author: endless-learner <[email protected]> Date: Tue Oct 29 14:38:49 2024 -0700 Merge branch 'main' into main commit 736cbdbdd12d340e9b08b69724f9a1321befd645 Author: hyiip <[email protected]> Date: Wed Oct 30 02:18:41 2024 +0800 add constant to claude 3.5 sonnet 20241022 commit 613d67eada996176335142cc2486bfe09be66700 Merge: 56bc77d2 89cea189 Author: Dogtiti <[email protected]> Date: Tue Oct 29 19:39:59 2024 +0800 Merge pull request #5729 from ConnectAI-E/feature/jest chore: improve jest commit 89cea18955a6d3ac73d053014f9f0d70338623e8 Merge: 49d42bb4 56bc77d2 Author: Dogtiti <[email protected]> Date: Tue Oct 29 19:26:52 2024 +0800 Merge branch 'main' of https://github.com/ConnectAI-E/ChatGPT-Next-Web into feature/jest commit 56bc77d20bc102af8166c48c8406f11f82cd4cae Merge: 6d93d379 a4d7a2c6 Author: Dogtiti <[email protected]> Date: Mon Oct 28 21:52:08 2024 +0800 Merge pull request #5731 from ChatGPTNextWeb/dependabot/npm_and_yarn/testing-library/jest-dom-6.6.2 Bump @testing-library/jest-dom from 6.4.8 to 6.6.2 commit 6d93d37963faf087bc21dea147fe2e9b0e96cee7 Merge: 4f496263 24df85cf Author: Dogtiti <[email protected]> Date: Mon Oct 28 21:51:59 2024 +0800 Merge pull request #5732 from ChatGPTNextWeb/dependabot/npm_and_yarn/types/jest-29.5.14 Bump @types/jest from 29.5.13 to 29.5.14 commit 24df85cf9d3ab2a307baa1539922c9463949ffa9 Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon Oct 28 10:31:34 2024 +0000 Bump @types/jest from 29.5.13 to 29.5.14 Bumps [@types/jest](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/jest) from 29.5.13 to 29.5.14. - [Release notes](https://github.com/DefinitelyTyped/DefinitelyTyped/releases) - [Commits](https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/jest) --- updated-dependencies: - dependency-name: "@types/jest" dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]> commit a4d7a2c6e3ef4d325a8039b5dd5bb9445d496c02 Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon Oct 28 10:31:27 2024 +0000 Bump @testing-library/jest-dom from 6.4.8 to 6.6.2 Bumps [@testing-library/jest-dom](https://github.com/testing-library/jest-dom) from 6.4.8 to 6.6.2. - [Release notes](https://github.com/testing-library/jest-dom/releases) - [Changelog](https://github.com/testing-library/jest-dom/blob/main/CHANGELOG.md) - [Commits](https://github.com/testing-library/jest-dom/compare/v6.4.8...v6.6.2) --- updated-dependencies: - dependency-name: "@testing-library/jest-dom" dependency-type: direct:development update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]> commit 49d42bb45d50141c6f7321ea650b0c5d58697591 Author: Dogtiti <[email protected]> Date: Mon Oct 28 16:47:05 2024 +0800 chore: improve jest commit 4f49626303127cac6f66ab9386d5b5076ed4d1d1 Merge: 82994843 45db20c1 Author: Lloyd Zhou <[email protected]> Date: Sat Oct 26 12:09:09 2024 +0800 Merge pull request #5722 from ElricLiu/main Update README.md commit 45db20c1c37279ebfe610d75a80dc09a21a14c54 Author: ElricLiu <[email protected]> Date: Sat Oct 26 11:16:43 2024 +0800 Update README.md commit 82994843f5f9923d8c1c7e4b9e4f6ab79fb17110 Merge: 1110a087 90ced928 Author: Lloyd Zhou <[email protected]> Date: Fri Oct 25 20:34:15 2024 +0800 Merge pull request #5719 from ConnectAI-E/hotfix/status_text_error hotfix for statusText is non ISO-8859-1 #5717 commit 1110a087a0268a7b8a523c547698b961dbd478b6 Merge: 4745706c f0b3e10a Author: Dogtiti <[email protected]> Date: Fri Oct 25 18:25:46 2024 +0800 Merge pull request #5720 from ConnectAI-E/hotfix/gemini_invald_argument hotfix for gemini invald argument #5715 commit f0b3e10a6caf55bf91325183b5ad84de2a05db04 Author: lloydzhou <[email protected]> Date: Fri Oct 25 18:19:22 2024 +0800 hotfix for gemini invald argument #5715 commit f89872b833d27c48b33281e60157640037e17a99 Author: lloydzhou <[email protected]> Date: Fri Oct 25 18:12:09 2024 +0800 hotfix for gemini invald argument #5715 commit 90ced9287626492898f2eb9bfd3b079171faf6ea Author: lloydzhou <[email protected]> Date: Fri Oct 25 18:05:29 2024 +0800 update commit 2c745590101b5201c677243f151616cb7023186e Author: lloydzhou <[email protected]> Date: Fri Oct 25 18:02:51 2024 +0800 hitfix commit e3ca7e8b4433bea43376035b9417fe233fe5f6f0 Author: lloydzhou <[email protected]> Date: Fri Oct 25 17:52:08 2024 +0800 hotfix for statusText is non ISO-8859-1 #5717 commit 4745706c42a390117e5e0f700af3d5f06e18f312 Author: lloydzhou <[email protected]> Date: Thu Oct 24 15:32:27 2024 +0800 update version to v2.15.6 commit 801dc412f99937dfd64a895309d9304429d94cac Author: lloydzhou <[email protected]> Date: Thu Oct 24 15:28:05 2024 +0800 add claude-3.5-haiku commit c7c2c0211a8b8906dc8b2de695bb74c6b22da92e Merge: 06f897f3 65bb962f Author: Dogtiti <[email protected]> Date: Wed Oct 23 14:13:17 2024 +0800 Merge pull request #5704 from ConnectAI-E/feature/xai xAi support commit 65bb962fc0b6eaa0cb1e15451d954df216b1956f Author: lloydzhou <[email protected]> Date: Wed Oct 23 12:00:59 2024 +0800 hotfix commit e791cd441d544a18126ddb825651d0e627402…
💻 变更类型 | Change Type
🔀 变更说明 | Description of Change
📝 补充信息 | Additional Information
Summary by CodeRabbit
Release Notes
New Features
Model Support
User Interface
Performance
Documentation
Chores
.gitignoreformcp_config.json.