docs(building_applications): add Claude Code integration guide#5571
Open
cdoern wants to merge 5 commits intoogx-ai:mainfrom
Open
docs(building_applications): add Claude Code integration guide#5571cdoern wants to merge 5 commits intoogx-ai:mainfrom
cdoern wants to merge 5 commits intoogx-ai:mainfrom
Conversation
Added comprehensive documentation for using Claude Code CLI with Llama Stack, covering: - Quick start instructions for different providers (OpenAI, vLLM, Ollama) - How the Messages API translation works - Model configuration and aliasing (including upcoming PR ogx-ai#5471 feature) - Provider-specific features and compatibility matrix - Configuration examples for multiple use cases - Troubleshooting common issues - Performance considerations - Differences from native Anthropic Claude Also added both claude_code_integration and codex_cli_integration to the sidebar navigation (codex was missing). Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> Signed-off-by: Charlie Doern <cdoern@redhat.com>
meta-cla
Bot
added
the
CLA Signed
leseb
requested changes
Apr 16, 2026
| Claude Code sends requests to the Anthropic Messages API (`/v1/messages`). Llama Stack implements this API with full compatibility, translating between formats as needed: | ||
|
|
||
| ``` | ||
| Claude Code → /v1/messages → Llama Stack → Provider |
Collaborator
There was a problem hiding this comment.
this reads as if /v1/messages was not llama stack but it is, can clarify it?
gyliu513
reviewed
Apr 21, 2026
| export ANTHROPIC_DEFAULT_OPUS_MODEL="openai/o1" | ||
|
|
||
| # Claude Code will route based on which model name it sends | ||
| claude "Quick task" # Uses haiku → vLLM |
Contributor
There was a problem hiding this comment.
May I know how does claude define which is the default model to use here?
Address review feedback from leseb on PR ogx-ai#5571: - Clarify that /v1/messages is Llama Stack's endpoint in the flow diagram - Remove Bedrock from native passthrough list (uses OpenAI translation) - Update model configuration section to reflect that model aliasing is now available - Emphasize that users always specify real Llama Stack models with --model flag - Explain that provider_id: "all" handles Claude Code's internal requests automatically Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> Signed-off-by: Charlie Doern <cdoern@redhat.com>
Co-authored-by: Guangya Liu <gyliu513@gmail.com>
Co-authored-by: Guangya Liu <gyliu513@gmail.com>
cdoern
requested review from
ashwinb,
bbrowning,
ehhuang,
franciscojavierarceo,
mattf and
raghotham
as code owners
franciscojavierarceo
approved these changes
Apr 24, 2026
Collaborator
Author
|
@leseb PTAL |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds comprehensive documentation for using Claude Code CLI with Llama Stack.
Changes
docs/docs/building_applications/claude_code_integration.mdxDocumentation Covers
Quick Start
ANTHROPIC_BASE_URLenvironment variableHow It Works
/v1/messagesis Llama Stack's endpoint)Model Configuration
--modelflag (e.g.,vllm/Qwen/Qwen3-8B)provider_id: "all"handles Claude Code's internal requests automaticallySupported Features
Configuration Examples
Troubleshooting
Performance Considerations
Differences from Anthropic Claude
Advanced Configuration
Recent Updates
Addressed review feedback from @leseb:
/v1/messagesflow diagram to show it's Llama Stack's endpoint--modelwith real Llama Stack modelsRelated
Testing
🤖 Generated with Claude Code