Coding intelligence

RSS for tag

Enhance your development workflow with coding intelligence features that help you write code, generate tests and documentation, fix errors, refactor existing implementations, and navigate codebases.

Posts under Coding intelligence tag

67 Posts

Post

Replies

Boosts

Views

Activity

Claude Agent reverts to earlier version in Xcode 26.4.1
My Claude Agent component version was 2.1.81, it prompted me for an update the other day from the original release version 2.1.59. But now that I've installed Xcode 26.4.1 it's back to thinking 2.1.59 is the newest version. With every Xcode release it feels like there's a new regression or weird surprise with coding intelligence (26.4 was Claude losing its OAuth token every 8 hours or so). It really feels like this stuff needs more eyes on it. Filed as FB22529202
2
1
385
Apr ’26
Xcode 26.4 rc
Since 26.4 beta 3 I've been having errors after a few hours of using Claude Agent. I get an error stating that I am not authed. If I go into Xcode settings, it still shows I am signed into Claude Agent. I have click sign out and then go through the whole auth process again to start using the agent again. This is on two separate computers. Is there anything I can do to stop this behaviour and stay logged in for longer? It worked fine in 26.3.
24
10
2.6k
Apr ’26
Xcode JSON-RPC global stream failed error when using chatgpt codex.
Whenever I try and talk to chatgpt codex in Xcode, I get the request could not be completed error with this tag: JSON-RPC global stream failed: The operation couldn’t be completed. (IDEIntelligenceAgents.JSONRPCElement.Error error 1.) Chatgpt chat still works inside of xcode, however codex does not work. I have not hit my limit for codex. This issue happened after the xcode update. (I belive 26.4.1)
0
2
482
Apr ’26
Xcode 26.3 RC - Claude Agent returns "Your request couldn't be completed"
Environment: Xcode 26.3 RC macOS 26.3 (25D125) (Apple Silicon / arm64) Setup: Xcode > Settings > Intelligence > Claude Agent: Signed In (account status shows "Signed In") Model: Default Steps to reproduce: Open a new chat in Xcode's Coding Assistant Select "Claude Agent" from the agent dropdown (instead of "Claude Sonnet 4.5") Send any message (e.g. "HI") Expected result: Claude Agent responds normally. Actual result: The message is sent but immediately returns the error: "Your request couldn't be completed." 🚩I have an active Claude Code subscription with remaining usage. Running claude in Terminal works perfectly, confirming the subscription and quota are valid.
4
0
1k
Apr ’26
Claude integration in Xcode 26.4 results in 401 after some time
Setup: macOS 26.4 Xcode 26.4 Claude premium subscription Claude account logged in Xcode settings The issue usually surfaces after initially setting up Claude integration in Xcode and then leaving Xcode open for at least a day or so. The integration works initially (right after logging in). But then after some time it starts responding with this error. Failed to authenticate. API Error: 401 {"type":"error","error":{"type":"authentication_error","message":"OAuth token has expired. Please obtain a new token or refresh your existing token."},"request_id":"req_011Ya....."} Restarting Xcode does not help. The only thing that helps is log out from Claude account and log back in. Sounds like the token refresh logic is broken or missing. Please improve moving forward.
1
0
406
Apr ’26
Agentic coding issues
Hi guys, Two annoying issues I'm having at the moment with agentic coding. Xcode signs out of Claude every single day and gives the error Failed to authenticate. API Error: 401. The only solution is go to settings and sign out of Claude and in again. Apple removed the little arrow to select the model, so now every time you start a new conversation you have to pick the model. I just want to start a new conversation with the model I'm using. The extra click is a time waster. Any solutions would be appreciated. Thanks
1
0
344
Apr ’26
Using Xcode Coding Agents with Custom Model Endpoints (Azure Foundry, etc.)
Trying to use the new built-in coding agents in Xcode (Claude / Codex), but running into a limitation with enterprise model setups. Our org accesses models through Microsoft Foundry (Azure-hosted endpoints), and we can connect to those models in Xcode using a custom endpoint / URL. That part works. However, that setup doesn’t seem to work with the built-in coding agents themselves. Those still appear to require direct account login or native API keys, with no way (that I can find) to point them at a custom endpoint or provider-backed deployment. Anyone figured out a way to get the agent experience working with enterprise setups like Foundry (or proxy layers)? Or is that not supported yet?
0
0
324
Mar ’26
Xcode's built-in AI chat feature (IDEIntelligenceChat) crashes.
According tho Claude, The crash is clearly a bug in Xcode's built-in AI chat feature (IDEIntelligenceChat), not an authentication issue or anything on your end. What the crash log shows: The crash is happening in IDEIntelligenceChat — specifically in ChatInputEditorView.updateView and SourceEditorDataSource.ideChat_gracefullyApplyChangesToReflect. It's a SIGTRAP (assertion/precondition failure) triggered while SwiftUI is trying to lay out the AI chat panel. This is an Apple bug in Xcode 26.2 itself.
1
0
275
Mar ’26
How to manually/offline install Claude Agent for Xcode?
Hi everyone, I'm working in a strictly offline (intranet) environment and cannot use the standard online installation process to download and install the Claude Agent for Xcode. What I've tried: I manually copied the Agent binary/folder from an online machine to the following path: ~/Library/Developer/Xcode/CodingAssistant/Agents/Versions/26.3/claude The Issue: Even though the files are in the correct directory, Xcode fails to recognize the agent. It doesn't appear in the settings, and the Coding Assistant remains unavailable. Questions: Is there a specific metadata file (e.g., a .plist or .json index) that needs to be updated for Xcode to "see" the manually added agent? Are there any code signing or quarantine issues (like xattr) that need to be addressed when moving the agent between machines? Does anyone know if there are other dependencies or cache folders (besides ~/Library/Developer/Xcode/CodingAssistant/) that need to be synchronized? Environment: macOS: 26.3 (25D122) Xcode: 26.3 (17C519) Any guidance on the manual registration process for these agents would be greatly appreciated. Thanks!
1
0
244
Mar ’26
Working in parallel on 2 projects with Claude Code agents. Agents should be able to communicate with each other.
When working in parallel on 2 projects (i.e. a server and a client app project). The Claude Code agents in those projects should be able to communicate with each other to improve the flow of information (i.e. changes in models, DTOs). The developer should supervise the communication and can block, if necessary.
0
0
122
Mar ’26
ChatGPT in Xcode - Networking error
In the Coding Intelligence feature introduced in Xcode 26, when I send a message using ChatGPT in Xcode, the message “Your request couldn't be completed. Networking error.” appears and I’m unable to use the feature. I suspect the issue may be related to the VPN or network proxy connected to my Mac and am attempting to investigate. However, Xcode does not display any specific error details, nor does it provide a way to view them, which makes a detailed investigation difficult. Next to the error message, there is a feedback button rather than a stethoscope (🩺) button, and the feedback window does not provide access to the underlying error information. Is there a way to view the detailed network error logs generated by ChatGPT in Xcode? (I am using Xcode 26.0.1.)
3
0
443
Mar ’26
How can I use private AI agents in Xcode 26.3?
I work on some proprietary codebases and can only use private AI services with them (currently MiniMax M2.1 and GLM 4.7). It all works great with both Claude Code and OpenCode agents, and I'd like to leverage the new agentic capabilities that are now in Xcode 26.3. I'm not seeing any option to connect to OpenCode, and both the Anthropic and OpenAI providers require an enterprise account (which I don't have access to). Are there any options that I'm missing here?
10
5
3.7k
Mar ’26
Your request couldn't be completed
Steps to reproduce: Open Xcode 26.3 → Settings → Intelligence → Claude sign-in Click the sign-in button — spinner begins, never completes An email the arrives with a magic link. The magic link opened a browser page which displayed a 6-digit verification code with instructions reading "enter this verification code where you first tried to sign in" — i.e. back in Xcode. However, Xcode was showing only an endless spinner with no code entry field anywhere in the UI. This is the core bug. I did since manage to complete authentication sign-in through a second browser verification field that eventually appeared after about 10 minutes and did get signed in, but the Claude Intelligence agent still returns "Your request could not be completed" even after successful sign-in and a full Xcode restart. Prior to this bug starting at 10 am on February 19 I had been using the intelligence agent successfully for about a week. Anthropic did have some sort of event on their system around February 18/19 so maybe this has been a result of that. I have notified Anthropic support and Apple Feedback Assistant. Does anybody have a workaround until either anthropic or Apple get back to me?
3
2
522
Mar ’26
Unable to use AI with XCode 26.2
I decided to try out XCode 26.2s new AI abilities but I only get a "Your request couldn't be completed". When clicking the details button I get see this error: InferenceError::unspecifiedUnderlyingError::Error(message: "Unknown parameter: 'tool_call_outputs'.", type: "invalid_request_error", code: Optional("unknown_parameter"), privacyPassRedemptionResponse: nil, userFacingLocalizedErrorMessage: nil) How do I fix that?
1
0
129
Mar ’26
Xcode 26.3 MCP server output missing `structredContent`
I am using official MCP SDK. According to official guide, Servers MUST provide structured results that conform to this schema. https://modelcontextprotocol.io/specification/draft/server/tools#output-schema I could see output schema defined, but result have no structured content. Current output schema: { name: "XcodeListWindows", title: "List Windows", description: "Lists the current Xcode windows and their workspace information", inputSchema: { type: "object", properties: { }, required: [ ], }, outputSchema: { type: "object", properties: { message: { description: "Description of all open Xcode windows", type: "string", }, }, required: [ "message", ], }, } Current response: { "result": { "content": [ { type: "text", text: "{\"message\":\"* tabIdentifier: windowtab1, workspacePath: \\xxx\\n* tabIdentifier: windowtab2, workspacePath: \\xxx\\n\"}", }, ] } } Expected: { "result": { "content": [ { type: "text", text: "{\"message\":\"* tabIdentifier: windowtab1, workspacePath: \\xxx\\n* tabIdentifier: windowtab2, workspacePath: \\xxx\\n\"}", }, ], "structuredContent": { "message": "* tabIdentifier: windowtab1, workspacePath: \\xxx\\n* tabIdentifier: windowtab2, workspacePath: \\xxx\\n", } } }
1
0
294
Mar ’26
Is Xcode Intelligence Ready for Production? My Experience and a Quest for Better Tools
I am looking to optimize my AI-assisted workflow within Xcode. Previously, my process was inefficient: Manually selecting and copying code snippets from Xcode into Gemini. Asking a specific question (e.g., "Modify this to show an alertError message box"). Copying the result back into Xcode. I attempted to switch to the new native Intelligence feature in Xcode to streamline this, but I found significant shortcomings: Latency: The response time is noticeably slow. Much slower than asking directly on Gemini 3 Pro. Lack of Context: The AI often fails to grasp the full project context. For example, it frequently claims it cannot see the code for ScannerView even though it is part of the project. I often have to prompt it multiple times before it finally "finds" the file. Is Xcode's Intelligence feature actually production-ready yet? If not, what tools do you recommend that integrate well with iOS development? To be clear, I am not looking for "vibe coding." I have a clear grasp of the problem and the high-level solution. My goal is to delegate the low-level implementation to the AI. I need a tool that has full project context from the start, eliminating the need to manually copy-paste snippets into a chat window.
1
0
147
Mar ’26
Claude Agent reverts to earlier version in Xcode 26.4.1
My Claude Agent component version was 2.1.81, it prompted me for an update the other day from the original release version 2.1.59. But now that I've installed Xcode 26.4.1 it's back to thinking 2.1.59 is the newest version. With every Xcode release it feels like there's a new regression or weird surprise with coding intelligence (26.4 was Claude losing its OAuth token every 8 hours or so). It really feels like this stuff needs more eyes on it. Filed as FB22529202
Replies
2
Boosts
1
Views
385
Activity
Apr ’26
Xcode 26.4 rc
Since 26.4 beta 3 I've been having errors after a few hours of using Claude Agent. I get an error stating that I am not authed. If I go into Xcode settings, it still shows I am signed into Claude Agent. I have click sign out and then go through the whole auth process again to start using the agent again. This is on two separate computers. Is there anything I can do to stop this behaviour and stay logged in for longer? It worked fine in 26.3.
Replies
24
Boosts
10
Views
2.6k
Activity
Apr ’26
Xcode JSON-RPC global stream failed error when using chatgpt codex.
Whenever I try and talk to chatgpt codex in Xcode, I get the request could not be completed error with this tag: JSON-RPC global stream failed: The operation couldn’t be completed. (IDEIntelligenceAgents.JSONRPCElement.Error error 1.) Chatgpt chat still works inside of xcode, however codex does not work. I have not hit my limit for codex. This issue happened after the xcode update. (I belive 26.4.1)
Replies
0
Boosts
2
Views
482
Activity
Apr ’26
Xcode 26.3 RC - Claude Agent returns "Your request couldn't be completed"
Environment: Xcode 26.3 RC macOS 26.3 (25D125) (Apple Silicon / arm64) Setup: Xcode > Settings > Intelligence > Claude Agent: Signed In (account status shows "Signed In") Model: Default Steps to reproduce: Open a new chat in Xcode's Coding Assistant Select "Claude Agent" from the agent dropdown (instead of "Claude Sonnet 4.5") Send any message (e.g. "HI") Expected result: Claude Agent responds normally. Actual result: The message is sent but immediately returns the error: "Your request couldn't be completed." 🚩I have an active Claude Code subscription with remaining usage. Running claude in Terminal works perfectly, confirming the subscription and quota are valid.
Replies
4
Boosts
0
Views
1k
Activity
Apr ’26
Claude integration in Xcode 26.4 results in 401 after some time
Setup: macOS 26.4 Xcode 26.4 Claude premium subscription Claude account logged in Xcode settings The issue usually surfaces after initially setting up Claude integration in Xcode and then leaving Xcode open for at least a day or so. The integration works initially (right after logging in). But then after some time it starts responding with this error. Failed to authenticate. API Error: 401 {"type":"error","error":{"type":"authentication_error","message":"OAuth token has expired. Please obtain a new token or refresh your existing token."},"request_id":"req_011Ya....."} Restarting Xcode does not help. The only thing that helps is log out from Claude account and log back in. Sounds like the token refresh logic is broken or missing. Please improve moving forward.
Replies
1
Boosts
0
Views
406
Activity
Apr ’26
Agentic coding issues
Hi guys, Two annoying issues I'm having at the moment with agentic coding. Xcode signs out of Claude every single day and gives the error Failed to authenticate. API Error: 401. The only solution is go to settings and sign out of Claude and in again. Apple removed the little arrow to select the model, so now every time you start a new conversation you have to pick the model. I just want to start a new conversation with the model I'm using. The extra click is a time waster. Any solutions would be appreciated. Thanks
Replies
1
Boosts
0
Views
344
Activity
Apr ’26
Using Xcode Coding Agents with Custom Model Endpoints (Azure Foundry, etc.)
Trying to use the new built-in coding agents in Xcode (Claude / Codex), but running into a limitation with enterprise model setups. Our org accesses models through Microsoft Foundry (Azure-hosted endpoints), and we can connect to those models in Xcode using a custom endpoint / URL. That part works. However, that setup doesn’t seem to work with the built-in coding agents themselves. Those still appear to require direct account login or native API keys, with no way (that I can find) to point them at a custom endpoint or provider-backed deployment. Anyone figured out a way to get the agent experience working with enterprise setups like Foundry (or proxy layers)? Or is that not supported yet?
Replies
0
Boosts
0
Views
324
Activity
Mar ’26
Xcode's built-in AI chat feature (IDEIntelligenceChat) crashes.
According tho Claude, The crash is clearly a bug in Xcode's built-in AI chat feature (IDEIntelligenceChat), not an authentication issue or anything on your end. What the crash log shows: The crash is happening in IDEIntelligenceChat — specifically in ChatInputEditorView.updateView and SourceEditorDataSource.ideChat_gracefullyApplyChangesToReflect. It's a SIGTRAP (assertion/precondition failure) triggered while SwiftUI is trying to lay out the AI chat panel. This is an Apple bug in Xcode 26.2 itself.
Replies
1
Boosts
0
Views
275
Activity
Mar ’26
How to manually/offline install Claude Agent for Xcode?
Hi everyone, I'm working in a strictly offline (intranet) environment and cannot use the standard online installation process to download and install the Claude Agent for Xcode. What I've tried: I manually copied the Agent binary/folder from an online machine to the following path: ~/Library/Developer/Xcode/CodingAssistant/Agents/Versions/26.3/claude The Issue: Even though the files are in the correct directory, Xcode fails to recognize the agent. It doesn't appear in the settings, and the Coding Assistant remains unavailable. Questions: Is there a specific metadata file (e.g., a .plist or .json index) that needs to be updated for Xcode to "see" the manually added agent? Are there any code signing or quarantine issues (like xattr) that need to be addressed when moving the agent between machines? Does anyone know if there are other dependencies or cache folders (besides ~/Library/Developer/Xcode/CodingAssistant/) that need to be synchronized? Environment: macOS: 26.3 (25D122) Xcode: 26.3 (17C519) Any guidance on the manual registration process for these agents would be greatly appreciated. Thanks!
Replies
1
Boosts
0
Views
244
Activity
Mar ’26
Working in parallel on 2 projects with Claude Code agents. Agents should be able to communicate with each other.
When working in parallel on 2 projects (i.e. a server and a client app project). The Claude Code agents in those projects should be able to communicate with each other to improve the flow of information (i.e. changes in models, DTOs). The developer should supervise the communication and can block, if necessary.
Replies
0
Boosts
0
Views
122
Activity
Mar ’26
ChatGPT in Xcode - Networking error
In the Coding Intelligence feature introduced in Xcode 26, when I send a message using ChatGPT in Xcode, the message “Your request couldn't be completed. Networking error.” appears and I’m unable to use the feature. I suspect the issue may be related to the VPN or network proxy connected to my Mac and am attempting to investigate. However, Xcode does not display any specific error details, nor does it provide a way to view them, which makes a detailed investigation difficult. Next to the error message, there is a feedback button rather than a stethoscope (🩺) button, and the feedback window does not provide access to the underlying error information. Is there a way to view the detailed network error logs generated by ChatGPT in Xcode? (I am using Xcode 26.0.1.)
Replies
3
Boosts
0
Views
443
Activity
Mar ’26
How can I use private AI agents in Xcode 26.3?
I work on some proprietary codebases and can only use private AI services with them (currently MiniMax M2.1 and GLM 4.7). It all works great with both Claude Code and OpenCode agents, and I'd like to leverage the new agentic capabilities that are now in Xcode 26.3. I'm not seeing any option to connect to OpenCode, and both the Anthropic and OpenAI providers require an enterprise account (which I don't have access to). Are there any options that I'm missing here?
Replies
10
Boosts
5
Views
3.7k
Activity
Mar ’26
Your request couldn't be completed
Steps to reproduce: Open Xcode 26.3 → Settings → Intelligence → Claude sign-in Click the sign-in button — spinner begins, never completes An email the arrives with a magic link. The magic link opened a browser page which displayed a 6-digit verification code with instructions reading "enter this verification code where you first tried to sign in" — i.e. back in Xcode. However, Xcode was showing only an endless spinner with no code entry field anywhere in the UI. This is the core bug. I did since manage to complete authentication sign-in through a second browser verification field that eventually appeared after about 10 minutes and did get signed in, but the Claude Intelligence agent still returns "Your request could not be completed" even after successful sign-in and a full Xcode restart. Prior to this bug starting at 10 am on February 19 I had been using the intelligence agent successfully for about a week. Anthropic did have some sort of event on their system around February 18/19 so maybe this has been a result of that. I have notified Anthropic support and Apple Feedback Assistant. Does anybody have a workaround until either anthropic or Apple get back to me?
Replies
3
Boosts
2
Views
522
Activity
Mar ’26
Unable to use AI with XCode 26.2
I decided to try out XCode 26.2s new AI abilities but I only get a "Your request couldn't be completed". When clicking the details button I get see this error: InferenceError::unspecifiedUnderlyingError::Error(message: "Unknown parameter: 'tool_call_outputs'.", type: "invalid_request_error", code: Optional("unknown_parameter"), privacyPassRedemptionResponse: nil, userFacingLocalizedErrorMessage: nil) How do I fix that?
Replies
1
Boosts
0
Views
129
Activity
Mar ’26
Xcode 26.3 MCP server output missing `structredContent`
I am using official MCP SDK. According to official guide, Servers MUST provide structured results that conform to this schema. https://modelcontextprotocol.io/specification/draft/server/tools#output-schema I could see output schema defined, but result have no structured content. Current output schema: { name: "XcodeListWindows", title: "List Windows", description: "Lists the current Xcode windows and their workspace information", inputSchema: { type: "object", properties: { }, required: [ ], }, outputSchema: { type: "object", properties: { message: { description: "Description of all open Xcode windows", type: "string", }, }, required: [ "message", ], }, } Current response: { "result": { "content": [ { type: "text", text: "{\"message\":\"* tabIdentifier: windowtab1, workspacePath: \\xxx\\n* tabIdentifier: windowtab2, workspacePath: \\xxx\\n\"}", }, ] } } Expected: { "result": { "content": [ { type: "text", text: "{\"message\":\"* tabIdentifier: windowtab1, workspacePath: \\xxx\\n* tabIdentifier: windowtab2, workspacePath: \\xxx\\n\"}", }, ], "structuredContent": { "message": "* tabIdentifier: windowtab1, workspacePath: \\xxx\\n* tabIdentifier: windowtab2, workspacePath: \\xxx\\n", } } }
Replies
1
Boosts
0
Views
294
Activity
Mar ’26
Is Xcode Intelligence Ready for Production? My Experience and a Quest for Better Tools
I am looking to optimize my AI-assisted workflow within Xcode. Previously, my process was inefficient: Manually selecting and copying code snippets from Xcode into Gemini. Asking a specific question (e.g., "Modify this to show an alertError message box"). Copying the result back into Xcode. I attempted to switch to the new native Intelligence feature in Xcode to streamline this, but I found significant shortcomings: Latency: The response time is noticeably slow. Much slower than asking directly on Gemini 3 Pro. Lack of Context: The AI often fails to grasp the full project context. For example, it frequently claims it cannot see the code for ScannerView even though it is part of the project. I often have to prompt it multiple times before it finally "finds" the file. Is Xcode's Intelligence feature actually production-ready yet? If not, what tools do you recommend that integrate well with iOS development? To be clear, I am not looking for "vibe coding." I have a clear grasp of the problem and the high-level solution. My goal is to delegate the low-level implementation to the AI. I need a tool that has full project context from the start, eliminating the need to manually copy-paste snippets into a chat window.
Replies
1
Boosts
0
Views
147
Activity
Mar ’26