docs(integrations): add DaoXE multi-protocol gateway guide

[seven7763]

Summary

Adds a Gateways integration page for DaoXE, a multi-model multi-protocol API gateway.

DaoXE exposes OpenAI-compatible Chat Completions / Responses, Anthropic Messages (Claude protocol), and image-compatible endpoints where available. This page documents the Langfuse path via the OpenAI SDK drop-in (from langfuse.openai import openai) with:

• base_url=https://daoxe.com/v1
• account-scoped model ID placeholders (no hardcoded public catalog)
• simple + nested @observe() examples matching neighboring gateway pages (e.g. Anannas / OpenRouter)

Files

• content/integrations/gateways/daoxe.mdx — new integration page
• content/integrations/gateways/meta.json — register daoxe alphabetically
• public/images/integrations/daoxe_icon.png — brand mark for the integration card

Notes

• Multi-protocol context is documented; this page instruments the Chat Completions surface because that is what the Langfuse OpenAI wrapper traces
• DaoXE is not available in mainland China
• Disclosure: I maintain DaoXE. Examples: https://github.com/seven7763/DaoXE-AI

Test plan

• Docs page renders at /integrations/gateways/daoxe
• Sidebar Gateways list includes DaoXE between Anannas and Helicone
• Internal links resolve (openai-py, observability get-started, OpenTelemetry)
• Icon loads on the integration page

Greptile Summary

This PR adds a new DaoXE gateway integration page to the Langfuse docs, following the same structure as neighboring pages like Anannas and OpenRouter. The page documents tracing DaoXE's OpenAI-compatible Chat Completions endpoint via the Langfuse OpenAI SDK wrapper (from langfuse.openai import openai), with a simple example and a nested @observe() example.

• content/integrations/gateways/daoxe.mdx — new integration guide with setup, two code examples (simple call and nested @observe() tracing), a multi-protocol note, availability disclaimer, and maintainer disclosure.
• content/integrations/gateways/meta.json — daoxe inserted alphabetically between anannas and helicone.
• public/images/integrations/daoxe_icon.png — brand icon for the integration card.

Confidence Score: 4/5

Safe to merge; the changes are purely additive documentation and a PNG asset with no impact on application logic.

The page follows the established gateway docs pattern closely and the sidebar registration is correct. The only gap is a missing example trace screenshot after the nested LLM calls example, which both anannas and openrouter include to help readers visualize the Langfuse output.

content/integrations/gateways/daoxe.mdx — consider adding an example trace screenshot or public trace link after the nested example to match the pattern of neighboring gateway pages.

Sequence Diagram

%%{init: {'theme': 'neutral'}}%%
sequenceDiagram
    participant App as User Application
    participant LW as Langfuse OpenAI Wrapper
    participant DX as DaoXE Gateway (daoxe.com/v1)
    participant LLM as Upstream LLM Provider
    participant LF as Langfuse Platform

    App->>LW: client.chat.completions.create(model, messages)
    LW->>DX: POST /v1/chat/completions (OpenAI schema)
    DX->>LLM: Route request to provider
    LLM-->>DX: Completion response
    DX-->>LW: Completion response
    LW-->>App: response object
    LW--)LF: Async trace (generation, tokens, latency)
    Note over LW,LF: @observe() spans wrap nested calls,<br/>creating a parent-child trace hierarchy

Loading

%%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%%
sequenceDiagram
    participant App as User Application
    participant LW as Langfuse OpenAI Wrapper
    participant DX as DaoXE Gateway (daoxe.com/v1)
    participant LLM as Upstream LLM Provider
    participant LF as Langfuse Platform

    App->>LW: client.chat.completions.create(model, messages)
    LW->>DX: POST /v1/chat/completions (OpenAI schema)
    DX->>LLM: Route request to provider
    LLM-->>DX: Completion response
    DX-->>LW: Completion response
    LW-->>App: response object
    LW--)LF: Async trace (generation, tokens, latency)
    Note over LW,LF: @observe() spans wrap nested calls,<br/>creating a parent-child trace hierarchy

Loading

Prompt To Fix All With AI

Fix the following 1 code review issue. Work through them one at a time, proposing concise fixes.

---

### Issue 1 of 1
content/integrations/gateways/daoxe.mdx:111-135
**Missing example trace screenshot after nested call example**

Both neighboring gateway pages include a visual of the resulting Langfuse trace after the nested LLM calls example — `anannas.mdx` uses a `<Frame>` block and `openrouter.mdx` uses a bare image with a caption and a public trace link. The DaoXE page ends the code block without any screenshot or trace link, so readers have no preview of what to expect in the Langfuse UI. Adding a `<Frame>` with a screenshot (or a public trace link) would bring this page in line with the established pattern.

_{Reviews (1): Last reviewed commit: "docs(integrations): add DaoXE multi-prot..." | Re-trigger Greptile}

[claude]

Claude Code Review

This pull request is from a fork — automated review is disabled. A repository maintainer can comment @claude review to run a one-time review.

[vercel]

@seven7763 is attempting to deploy a commit to the langfuse Team on Vercel.

A member of the Team first needs to authorize it.

[CLAassistant]

All committers have signed the CLA.

[seven7763]

I have read the CLA Document and I hereby sign the CLA

[seven7763]

I have read the CLA Document and I hereby sign the CLA

recheck

[seven7763]

I have read the CLA Document and I hereby sign the CLA

recheck

[seven7763]

I have read the CLA Document and I hereby sign the CLA

recheck

[seven7763]

recheck

[seven7763]

recheck

[seven7763]

CLA is signed. This is a docs-only integration guide for DaoXE as an OpenAI-compatible gateway. Happy to adjust wording or placement if needed.