ericc-ch · luisbrandao · Oct 13, 2025 · Oct 13, 2025 · Oct 13, 2025 · Oct 13, 2025
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -0,0 +1,32 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.8.0] - 2025-01-31
+
+### Added
+- GitHub Enterprise Server/Cloud support
+  - New `--enterprise-url` flag for `auth` and `start` commands
+  - Interactive prompt during auth for enterprise configuration
+  - Persistent enterprise URL storage in `~/.local/share/copilot-api/enterprise_url`
+  - Automatic endpoint routing for enterprise instances
+- Comprehensive test suite with 41 new tests covering enterprise functionality
+- URL normalization utilities for enterprise host configuration
+
+### Changed
+- OAuth endpoints now use enterprise URLs when configured
+- Copilot API endpoints route to `copilot-api.{enterprise}` for enterprise users
+- GitHub API endpoints route to `api.{enterprise}` for enterprise users
+
+### Technical Details
+- Enterprise endpoint structure:
+  - OAuth: `https://{enterprise}/login/...`
+  - GitHub API: `https://api.{enterprise}/...`
+  - Copilot API: `https://copilot-api.{enterprise}/...`
+- 100% backwards compatible - defaults to github.com when no enterprise configured
+
+## [0.7.0] - Previous Release
+- See git history for details
diff --git a/CLAUDE.md b/CLAUDE.md
@@ -0,0 +1,41 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code when working with this repository.
+
+## Overview
+
+TypeScript CLI application using Bun runtime that exposes GitHub Copilot as OpenAI/Anthropic-compatible APIs.
+
+## Commands
+
+- `bun install` - Install dependencies
+- `bun run build` - Build distribution
+- `bun run dev` - Development with watch mode
+- `bun run start` - Production start
+- `bun run lint` - Lint code
+- `bun run typecheck` - Type checking
+- `bun test` - Run tests
+
+## Architecture
+
+- **Entry**: `src/main.ts` - CLI definition with subcommands (auth, start, check-usage, debug)
+- **Server**: `src/start.ts` - Orchestrates initialization and HTTP server
+- **Routes**: `src/routes/` - OpenAI & Anthropic compatible endpoints
+- **Services**:
+  - `src/services/github/` - GitHub OAuth and token management
+  - `src/services/copilot/` - Copilot API interactions
+- **Utilities**: `src/lib/` - State management, paths, token handling
+
+## GitHub Enterprise Support
+
+- Use `--enterprise-url` flag for GHE Server/Cloud
+- Interactive prompt during auth if no flag provided
+- Enterprise URL persisted in `~/.local/share/copilot-api/enterprise_url`
+- Endpoints: `https://{enterprise}/...` for OAuth, `https://api.{enterprise}/...` for GitHub API, `https://copilot-api.{enterprise}/...` for Copilot
+
+## Key Files
+
+- CLI flags: `src/start.ts:123`, `src/main.ts:10`
+- Routes: `src/server.ts`, `src/routes/*`
+- Models: `src/services/copilot/get-models.ts`
+- Token storage: `src/lib/paths.ts`, `src/lib/token.ts`
diff --git a/Dockerfile b/Dockerfile
@@ -10,6 +10,9 @@ RUN bun run build
 FROM oven/bun:1.2.19-alpine AS runner
 WORKDIR /app
 
+# Install tzdata for timezone support
+RUN apk add --no-cache tzdata
+
 COPY ./package.json ./bun.lock ./
 RUN bun install --frozen-lockfile --production --ignore-scripts --no-cache
 

diff --git a/README.md b/README.md
@@ -39,6 +39,7 @@ A reverse-engineered proxy for the GitHub Copilot API that exposes it as an Open
 - **Token Visibility**: Option to display GitHub and Copilot tokens during authentication and refresh for debugging (`--show-token`).
 - **Flexible Authentication**: Authenticate interactively or provide a GitHub token directly, suitable for CI/CD environments.
 - **Support for Different Account Types**: Works with individual, business, and enterprise GitHub Copilot plans.
+- **GitHub Enterprise Support**: Compatible with GitHub Enterprise Server and GitHub Enterprise Cloud installations.
 
 ## Demo
 
@@ -163,13 +164,15 @@ The following command line options are available for the `start` command:
 | --claude-code  | Generate a command to launch Claude Code with Copilot API config              | false      | -c    |
 | --show-token   | Show GitHub and Copilot tokens on fetch and refresh                           | false      | none  |
 | --proxy-env    | Initialize proxy from environment variables                                   | false      | none  |
+| --enterprise-url | GitHub Enterprise host to use (eg. https://ghe.example.com)               | none       | none  |
 
 ### Auth Command Options
 
 | Option       | Description               | Default | Alias |
 | ------------ | ------------------------- | ------- | ----- |
 | --verbose    | Enable verbose logging    | false   | -v    |
 | --show-token | Show GitHub token on auth | false   | none  |
+| --enterprise-url | GitHub Enterprise host (eg. https://ghe.example.com) | none | none |
 
 ### Debug Command Options
 
@@ -204,10 +207,35 @@ These endpoints are designed to be compatible with the Anthropic Messages API.
 
 New endpoints for monitoring your Copilot usage and quotas.
 
-| Endpoint     | Method | Description                                                  |
-| ------------ | ------ | ------------------------------------------------------------ |
-| `GET /usage` | `GET`  | Get detailed Copilot usage statistics and quota information. |
-| `GET /token` | `GET`  | Get the current Copilot token being used by the API.         |
+| Endpoint      | Method | Description                                                  |
+| ------------- | ------ | ------------------------------------------------------------ |
+| `GET /usage`  | `GET`  | Get detailed Copilot usage statistics and quota information. |
+| `GET /token`  | `GET`  | Get the current Copilot token being used by the API.         |
+| `GET /metrics`| `GET`  | Prometheus metrics endpoint exposing token usage per model.  |
+
+### Prometheus Metrics
+
+The `/metrics` endpoint exposes Prometheus-compatible metrics for monitoring token usage:
+
+**Available Metrics:**
+- `copilot_api_tokens_in_total` - Total input tokens processed per model
+- `copilot_api_tokens_out_total` - Total output tokens generated per model  
+- `copilot_api_requests_total` - Total number of requests per model and endpoint
+
+Example metrics output:
+```
+# HELP copilot_api_tokens_in_total Total number of input tokens processed per model
+# TYPE copilot_api_tokens_in_total counter
+copilot_api_tokens_in_total{model="gpt-4o"} 1523
+
+# HELP copilot_api_tokens_out_total Total number of output tokens generated per model
+# TYPE copilot_api_tokens_out_total counter
+copilot_api_tokens_out_total{model="gpt-4o"} 342
+
+# HELP copilot_api_requests_total Total number of requests per model
+# TYPE copilot_api_requests_total counter
+copilot_api_requests_total{model="gpt-4o",endpoint="chat-completions"} 15
+```
 
 ## Example Usage
 
@@ -255,6 +283,15 @@ npx copilot-api@latest debug --json
 
 # Initialize proxy from environment variables (HTTP_PROXY, HTTPS_PROXY, etc.)
 npx copilot-api@latest start --proxy-env
+
+# Use GitHub Enterprise / GitHub Enterprise Server
+npx copilot-api@latest start --account-type enterprise --enterprise-url https://ghe.example.com
+
+# Authenticate with GitHub Enterprise interactively (will prompt for enterprise host)
+npx copilot-api@latest auth
+
+# Authenticate with GitHub Enterprise using CLI flag (for scripting)
+npx copilot-api@latest auth --enterprise-url ghe.example.com
 ```
 
 ## Using the Usage Viewer
@@ -349,3 +386,8 @@ bun run start
   - `--rate-limit <seconds>`: Enforces a minimum time interval between requests. For example, `copilot-api start --rate-limit 30` will ensure there's at least a 30-second gap between requests.
   - `--wait`: Use this with `--rate-limit`. It makes the server wait for the cooldown period to end instead of rejecting the request with an error. This is useful for clients that don't automatically retry on rate limit errors.
 - If you have a GitHub business or enterprise plan account with Copilot, use the `--account-type` flag (e.g., `--account-type business`). See the [official documentation](https://docs.github.com/en/enterprise-cloud@latest/copilot/managing-copilot/managing-github-copilot-in-your-organization/managing-access-to-github-copilot-in-your-organization/managing-github-copilot-access-to-your-organizations-network#configuring-copilot-subscription-based-network-routing-for-your-enterprise-or-organization) for more details.
+- For GitHub Enterprise Server/Cloud users: Use `--enterprise-url` to specify your enterprise host (e.g., `--enterprise-url https://ghe.example.com`). The interactive auth command (`copilot-api auth`) will prompt you for your enterprise host if you don't provide it via the CLI flag.
+
+
+
+export ANTHROPIC_BASE_URL=http://localhost:4141 ANTHROPIC_AUTH_TOKEN=dummy ANTHROPIC_MODEL=claude-sonnet-4.5 ANTHROPIC_DEFAULT_SONNET_MODEL=claude-sonnet-4.5 ANTHROPIC_SMALL_FAST_MODEL=gpt-5-mini ANTHROPIC_DEFAULT_HAIKU_MODEL=gpt-5-mini DISABLE_NON_ESSENTIAL_MODEL_CALLS=1 CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 && claude
diff --git a/bun.lock b/bun.lock