Skip to content

Conversation

@onlylhf
Copy link
Contributor

@onlylhf onlylhf commented Jan 16, 2026

  • Add endpoint_url configuration to provider and model credential schemas
  • Implement _normalize_endpoint_url() method to handle user-provided URLs
  • Ensure endpoint URL is properly formatted with /v1 suffix
  • Update dify-plugin dependency to 0.7.1
  • Bump version to 0.0.32

OpenRouter reverse proxy script example

package main

import (
	"log"
	"net/http"
	"net/http/httputil"
	"net/url"
	"os"
)

// Configuration for the target host
const TargetHost = "https://openrouter.ai"

func main() {
	// 1. Parse the target URL
	targetURL, err := url.Parse(TargetHost)
	if err != nil {
		log.Fatalf("Failed to parse target URL: %v", err)
	}

	// 2. Create the reverse proxy
	proxy := httputil.NewSingleHostReverseProxy(targetURL)

	// 3. Custom Director to modify the request
	originalDirector := proxy.Director
	proxy.Director = func(req *http.Request) {
		// Execute default forwarding logic
		originalDirector(req)

		// -------------------------------------------------------
		// Key Step: Hide Source IP
		// -------------------------------------------------------
		// Explicitly remove headers usually added by proxies to ensure
		// OpenRouter sees this server's IP, not the original client's.
		req.Header.Del("X-Forwarded-For")
		req.Header.Del("X-Real-Ip")
		req.Header.Del("Forwarded")

		// Set the Host header to match the target.
		// This is crucial for passing Cloudflare checks.
		req.Host = targetURL.Host

		log.Printf("Forwarding request: Path=%s, Method=%s", req.URL.Path, req.Method)
	}

	// 4. Custom ModifyResponse (Optional)
	// Used to handle CORS headers
	proxy.ModifyResponse = func(resp *http.Response) error {
		resp.Header.Set("Access-Control-Allow-Origin", "*")
		resp.Header.Set("Access-Control-Allow-Headers", "*")
		return nil
	}

	// 5. Set up the handler function
	http.HandleFunc("/", func(w http.ResponseWriter, r *http.Request) {
		// Handle CORS preflight requests (OPTIONS)
		if r.Method == http.MethodOptions {
			w.Header().Set("Access-Control-Allow-Origin", "*")
			w.Header().Set("Access-Control-Allow-Headers", "*")
			w.WriteHeader(http.StatusOK)
			return
		}

		// Execute proxy
		proxy.ServeHTTP(w, r)
	})

	// 6. Start the server
	port := os.Getenv("PORT")
	if port == "" {
		port = "8080"
	}
	log.Printf("OpenRouter proxy server started on :%s -> %s", port, TargetHost)
	if err := http.ListenAndServe(":"+port, nil); err != nil {
		log.Fatalf("Server failed to start: %v", err)
	}
}

Related Issues or Context

This PR contains Changes to Non-Plugin

  • Documentation
  • Other

This PR contains Changes to Non-LLM Models Plugin

  • I have Run Comprehensive Tests Relevant to My Changes

This PR contains Changes to LLM Models Plugin

  • My Changes Affect Message Flow Handling (System Messages and User→Assistant Turn-Taking)
  • My Changes Affect Tool Interaction Flow (Multi-Round Usage and Output Handling, for both Agent App and Agent Node)
  • My Changes Affect Multimodal Input Handling (Images, PDFs, Audio, Video, etc.)
  • My Changes Affect Multimodal Output Generation (Images, Audio, Video, etc.)
  • My Changes Affect Structured Output Format (JSON, XML, etc.)
  • My Changes Affect Token Consumption Metrics
  • My Changes Affect Other LLM Functionalities (Reasoning Process, Grounding, Prompt Caching, etc.)
  • Other Changes (Add New Models, Fix Model Parameters etc.)

Version Control (Any Changes to the Plugin Will Require Bumping the Version)

  • I have Bumped Up the Version in Manifest.yaml (Top-Level Version Field, Not in Meta Section)

Dify Plugin SDK Version

  • I have Ensured dify_plugin>=0.3.0,<0.6.0 is in requirements.txt (SDK docs)

Environment Verification (If Any Code Changes)

Local Deployment Environment

  • Dify Version is: , I have Tested My Changes on Local Deployment Dify with a Clean Environment That Matches the Production Configuration.

SaaS Environment

  • I have Tested My Changes on cloud.dify.ai with a Clean Environment That Matches the Production Configuration

- Add endpoint_url configuration to provider and model credential schemas
- Implement _normalize_endpoint_url() method to handle user-provided URLs
- Ensure endpoint URL is properly formatted with /v1 suffix
- Update dify-plugin dependency to 0.7.1
- Bump version to 0.0.32
@dosubot dosubot bot added the size:M This PR changes 30-99 lines, ignoring generated files. label Jan 16, 2026
@onlylhf onlylhf deployed to models/openrouter January 16, 2026 03:31 — with GitHub Actions Active
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @onlylhf, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a significant enhancement to the OpenRouter integration by enabling users to define a custom API endpoint URL. This change provides greater flexibility, particularly for those who wish to route requests through a proxy or use a self-hosted OpenRouter instance. The implementation includes robust URL normalization to maintain consistency and proper API interaction. Additionally, core dependencies have been updated to ensure compatibility and leverage the latest features, alongside a standard version bump for the plugin.

Highlights

  • Custom API Endpoint Support: Added the ability to configure a custom API endpoint URL for OpenRouter, allowing users to specify alternative hosts or proxy servers.
  • Endpoint URL Normalization: Implemented a new static method _normalize_endpoint_url to ensure that user-provided endpoint URLs are correctly formatted, specifically by stripping trailing slashes and appending /v1 if missing.
  • Dependency Updates: Updated the dify-plugin dependency to version 0.7.1 and adjusted several other Python package versions in requirements.txt.
  • Plugin Version Bump: The OpenRouter plugin version has been incremented from 0.0.31 to 0.0.32.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

@dosubot dosubot bot added the enhancement New feature or request label Jan 16, 2026
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request adds support for a custom API endpoint URL for OpenRouter, which is a valuable feature for users with proxy setups or custom deployments. The implementation across the YAML configuration and Python code is solid. I have one suggestion to refactor the URL normalization logic in llm.py to improve its clarity and maintainability. The dependency updates seem appropriate for this feature addition.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request size:M This PR changes 30-99 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant