Hello, developers! Xcode 26.3 unlocks the power of agentic coding! Get ready to explore new features that released last Tuesday. If you haven't already, you can download Xcode 26.3 from the Apple Developer Downloads page Check out the official documentation for getting started and how to configure agents in Xcode: ‎ Writing code with intelligence in Xcode Generate code, fix bugs fast, and learn as you go with intelligence built directly into Xcode https://developer.apple.com/documentation/xcode/writing-code-with-intelligence-in-xcode/ ‎ Setting up coding intelligence Enable third-party coding tools that you want to use in the coding assistant https://developer.apple.com/documentation/xcode/setting-up-coding-intelligence ‎ Giving external agentic coding tools access to Xcode Let agentic coding tools access your project and Xcode capabilities using the Model Context Protocol https://developer.apple.com/documentation/xcode/giving-agentic-coding-tools-access-to-xcode ‎ Code-along: Experiment with coding intelligence in Xcode 26 Presented live at a Meet with Apple event: Learn how coding intelligence features can help you write code and fix errors with example prompts and resources. ‎ ‎We are also introducing a new tag to the forums Coding intelligence ✨. Use this tag when discussing these new features to increase visibility on the forums to help others chime in.

Codex will no longer be available in Xcode 26.3 starting on Friday, May 8th. Please upgrade to Xcode 26.4 or later to continue using Codex.

If you're on an Intel Mac, here's the reason and the fix. Cost me an evening, and I found nothing online except closed bug reports with the same symptom. The problem: The browser flow works fine. You authorize, the page confirms, Xcode acts like nothing happened, no error anywhere. Xcode only downloads the Apple Silicon (arm64) build of its agent binaries. On Intel they can't run at all. The process meant to receive your login dies instantly with "bad CPU type in executable" and Xcode never surfaces it. Check if this is you: file ~/Library/Developer/Xcode/CodingAssistant/Agents/claude/*/claude If it says arm64 and your Mac is Intel, that's the problem. The fix: Open the Info.plist next to the binary. It has the exact download URL. Download the x64 build of the same version. → Claude: change darwin-arm64 to darwin-x64 in that URL. → Codex: grab codex-x86_64-apple-darwin.tar.gz from the matching rust-v release on GitHub. Replace the binary and make it executable: chmod 755 Update the checksum in Info.plist. It's a plain SHA-512: shasum -a 512 Restart Xcode and sign in again. Bonus (Claude Pro / Max) Run claude setup-token in Terminal, then add the token to: ~/Library/Developer/Xcode/CodingAssistant/ClaudeAgentConfig/settings.json {"env": {"CLAUDE_CODE_OAUTH_TOKEN": "your-token"}} Pick "Authenticate with Configuration File" in the agent menu. Runs on your subscription no API key. Heads up: an Xcode update can re-download the wrong binary, so you may have to repeat this until Apple fixes the architecture detection.

Accepting a proposal in chat switches windows and no code change applied. (hoping part of issue might be chat window takes over right side rather than swapping with navigator like before in previous Xcode 26.5

Installed from the Mac App Store Signed in with my Apple ID in Xcode Apple Intelligence is enabled Chat providers work normally (ChatGPT, Claude, Google) What I expected According to Apple's documentation, the Intelligence settings should display built-in Agents such as: Claude Agent Codex with a Get button to install them. Reference: https://developer.apple.com/documentation/xcode/setting-up-coding-intelligence What actually happens After upgrading to Xcode 26.6, the Agents section only contains: Allow external agents to use Xcode tools Add an Agent... The built-in Agents (Claude Agent and Codex) are completely missing.

Never have this problem running in the first version of Xcode 27 until download the latest Xcode 27. At least "Fable" should be added in the dropdown to give a sense that it could be selected and be more careful (in dropdown only have "Sonnet", "Opus", "Sonnet+Opus" and more) I also submit Feedback request FB23973503 with screen capture & more Xcode Claude AI Investigation details

Nothing changed on my end, Pro subscription still active, but Xcode 26.5 (17F42) simply does not want to log into Codex anymore. It opens the OAuth flow and after finishing and closing the window, it still says "Not Signed In". Codex login works everywhere else, including the Codex app. What to do?

When will this be available? (Opencode + LMStudio + Qwen 3.6 27B) FB23978071

As of May 8th, 2026, after I upgraded to "codex-cli 0.129.0" via Xcode, I can no longer sign into my ChatGPT account in Xcode Intelligence Settings. The Log In window is always successful, but the settings never update to show the login being successful. It's a constant loop. Perhaps a hand-shake fail. Versions: Tahoe 26.3.1, Xcode 26.4.1, codex-cli 0.129.0.

Environment: macOS: Tahoe 26.4 Xcode: 26.5 ChatGPT account successfully authenticated Codex CLI installed and working Codex App installed and working Steps to reproduce: Install Xcode Codex/OpenAI component version where GPT-5.4 is the highest available model. Sign in with ChatGPT account. Confirm Codex works in Xcode. Update the OpenAI/Codex component in Xcode. Attempt to sign in again. Expected result: Xcode completes authentication and shows signed-in status. Actual result: Browser successfully completes authentication and displays "Signed in to Codex." Xcode remains in a sign-in loop or shows "Not Signed In." Authentication never completes. Additional observations: Codex CLI authentication succeeds. Codex App authentication succeeds. ChatGPT web/app access succeeds. Anthropic/Claude component updates continue to work normally in Xcode. Issue appears specific to the updated OpenAI/Codex Xcode component. Older component (GPT-5.4 maximum model available) authenticates successfully.

I've been trying for months to get Gemini 3.5 Flash to work with Xcode 27 Beta (1-3) agentic coding but have failed. Xcode currently uses Gemini CLI v0.42.0 from last year, so it can't call Gemini 3.5 Flash even though all that needs to change is a few characters in the API call. Gemini users are currently forced to choose between 3.1 Pro and 3.1 Flash Preview--both weren't the best choices two months ago, but with the release of 3.6 Flash which is better at coding that 3.1 Pro and miles cheaper, these choices are now unsuitable for any serious workload. I live in Hong Kong, where OpenAI and Anthropic services aren't offered, so Google is the only (native) AI provider for Xcode agentic coding. The cost issue from funneling all the work into 3.1 Pro is terrible especially with some agent bugs that have yet to be ironed out. Given Apple's close partnership with Google on AI, I'm genuinely surprised that after 4 Betas we're still using a Gemini CLI from 2025 that forces users to choose between two very unappealing models. Xcode is basically forcing Google users to switch to OpenAI/Anthropic. Questions: I'd like to know if this will be fixed soon and whether Google users should expect slower updates (i.e. be forced to use older models). Does anyone know of any workarounds?

How do I select between GPT and Claude, and the model, when opening a new task for the coding agent with the ‘New Conversation’ button in the toolbar?

I’m seeing a reproducible issue in both Xcode 26 and Xcode 27 where Coding Assistant appears to stop autocompleting when a project contains a larger number of Swift Package dependencies. Symptoms: Autocomplete suggestions from Coding Assistant stop appearing. File targeting with @ stops working. The issue typically appears shortly after opening the project If I start a brand-new chat immediately after opening the project, Coding Assistant sometimes works briefly before failing Reducing or removing Swift Package dependencies fixes the issue I’ve created a sample project that reproduces the problem and have also filed Feedback Assistant report: FB23341243 The issue seems related to package count or project complexity rather than any specific package, although I haven’t yet identified the exact threshold that triggers it. Has anyone else run into this or has anyone found a workaround?

It is not possible to log into my Claude account in Xcode 27 beta 1 for the coding intelligence chat. When I click "Sign In," the browser opens, I authorize, the browser closes, and that's it. Nothing happens. Xcode does not recognize the login. I'm on MacOS 26.4.1 (25E253) and using Xcode 27.0 beta (27A5194q)

I set up Gemini in Xcode 27 beta in Settings using an API key from Google AI studio. When I select "New Conversation" and "Gemini" and type "hi" it just spins forever (many minutes) - no reply or error message. Is there any way to figure out what's wrong?

I’m attempting to set up Gemini agentic support in Xcode 26.6 RC (and I'm assuming the process is the same in 27), but since I need to use Gemini with a corporate account, I have a Google Cloud Project ID, not an API key, so it seems like the configuration file route is the right path? After consulting Gemini and filling out the .env file and settings.json files, Xcode is complaining about needing to be authenticated, and I can’t seem to see how to trigger the auth, like one might do in Gemini CLI. I'd appreciate any suggestions or advice at this point. Thanks in advance!

I can't use cloud-based AI providers, so I'm very excited about the potential of local models with Xcode's Coding Assistant. I've been playing around with a local MLX model, and have been generally pretty satisfied with it. But I'm curious - what features am I missing out on by using a local model instead of a larger, cloud-based model? Is Xcode's ability to run tests, build the project, etc. limited by the use of a local model? Does it limit the ability to do more complex agentic workflows? If so, how? Basically, local models in Xcode seem to be working pretty well for me, and I'm curious to know what cloud-based models can offer that I don't already have.

Is anyone else finding model switching a bit disruptive during longer coding sessions? As we start using different models for exploration, implementation and review, having to go through settings interrupts the workflow. I would love to see model and reasoning controls directly inside the Coding Assistant UI.

Has anyone managed to get Copilot working using the new ACP integration in Xcode 26.6 and Xcode 27 beta? I have tried setting it up using the path to the copilot binary as instructed and the flags --acp --stdio but Xcode just displays a "Your request couldn't be completed" error: JSON-RPC global stream failed: The operation couldn’t be completed. (IDEIntelligenceProtocol.JSONRPCElement.Error error 1.) I am running the latest version of copilot cli and it works in many other IDEs.

Since today (5th June), my Codex seems to be broken. First there is no response (wait for hours), now it just crash with this error whenever I issue a command: JSON-RPC global stream failed: The operation couldn’t be completed. (IDEIntelligenceProtocol.JSONRPCElement.Error error 1.) I have a ChatGPT Pro subscription and I don't know what to do. I have restarted Xcode, sign out and in of my account, delete DerivedData, restart machine, reinstall Xcode.

I gave Xcode 27 Beta 1 + Claude Agent my app codebase and set it to work on reviewing the SwiftUI related codebase and suggest improvements in the areas view performance and SwiftUI conformance. I am extremely happy with the results I got. From my experience the Xcode backed Claude Agent is far more versed in SwiftUI related task than pure Claude Code or Claude Code + SwiftUI skill extensions. I was able to visibly increase the performance of several complex views in my app. In addition the Xcode backed agent solved a Liquid Glass related bug with view tinting that I was not able to solve with Claude Code before on its first try. However, in Beta 1 Claude Agent BURNS through tokens at a mind boggling speed. I perceive the agent as a bit to verbose in telling me what it is doing. Allowing the agent to start a simulator and use the app for exploration is setting tokens on fire. I hope that we see refinements in these areas before Xcode 27 is released.

I'm trying to use Codex via the Xcode interface, and I can not find a way to set the reasoning level. There are no settings to be found anywhere. What am I missing? I mean, I can continue to use Codex's own app, but I was hoping to use Xcode's new agentic interface, which seems superior to v26 and somewhat more useful. But if it's going to default to medium and I have no control over it, of course, I would continue using Codex's app rather than Xcode. What's weird, I get responses like this when I ask about: What's your current reasoning level and how can I adjust it? This session appears to be using the default reasoning level: medium. You generally adjust it outside my reply, in the model/session settings for Codex or the API request. Typical options are: • low: faster, cheaper, best for simple edits or direct questions • medium: default balance • high: better for complex debugging, architecture, tricky code changes • xhigh: deepest reasoning, slower, useful for hard multi-step work Inside this chat, I can’t change my own base reasoning level mid-response. You can still tell me “use high reasoning for this” and I’ll treat the task more deliberately, but the actual runtime setting has to be changed in the client/session configuration. So, it doesn't even know the level it's using or how to adjust.