copilot-custom-endpoint 1.0.3 → 1.0.5

package/README.md

@@ -43,6 +43,66 @@ The Kimi and Qwen setups require editing the same VS Code config file:
 | macOS   | `~/Library/Application Support/Code/User/chatLanguageModels.json` |
 | Linux   | `~/.config/Code/User/chatLanguageModels.json`                     |
 
+### Full example config
+
+Here's a complete, real-world example of `chatLanguageModels.json` combining all the providers documented in this repo.
+
+```json
+[
+  {
+    "name": "Qwen",
+    "vendor": "customendpoint",
+    "apiKey": "<your-dashscope-key>",
+    "apiType": "chat-completions",
+    "models": [
+      {
+        "id": "qwen3.7-max",
+        "name": "Qwen 3.7 Max",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
+        "toolCalling": true,
+        "vision": false,
+        "streaming": true,
+        "requestBody": {
+          "enable_thinking": false
+        }
+      },
+      {
+        "id": "qwen3.6-plus",
+        "name": "Qwen 3.6 Plus",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
+        "toolCalling": true,
+        "vision": true,
+        "streaming": true,
+        "requestBody": {
+          "enable_thinking": false
+        }
+      }
+    ]
+  },
+  {
+    "name": "Kimi",
+    "vendor": "customendpoint",
+    "apiKey": "<your-moonshot-key>",
+    "apiType": "chat-completions",
+    "models": [
+      {
+        "id": "kimi-k2.6",
+        "name": "Kimi K2.6",
+        "url": "http://127.0.0.1:3457/v1/chat/completions",
+        "requestBody": {
+          "temperature": 1
+        },
+        "toolCalling": true,
+        "vision": true,
+        "streaming": true,
+        "maxInputTokens": 262144,
+        "maxOutputTokens": 32768
+      }
+    ]
+  }
+]
+```
+
 ### Kimi K2.6 (Moonshot)
 
 #### 1. Grab a Moonshot API key
@@ -53,18 +113,32 @@ Sign up at [platform.moonshot.ai](https://platform.moonshot.ai) and create an AP
 
 The proxy rewrites VS Code's requests into shapes Kimi actually accepts (fixed `temperature`, `top_p`, and disabling "thinking" during tool calls).
 
+> **Local config:** Create a `.env` file in this repo root to set environment variables like `KIMI_PROXY_PORT`, `KIMI_UPSTREAM_URL`, etc. It's loaded automatically via `dotenv` — no need to prefix commands.
+
+Run Kimi proxy
+
 ```bash
-# from this repo — Kimi only
 npm run proxy:kimi
-# from this repo — both proxies concurrently
+```
+
+Run all proxies
+
+```bash
 npm run proxy
-# or with npx
+```
+
+Run globally (from any directory)
+
+```bash
+# Kimi only
 npx copilot-custom-endpoint kimi
-npx copilot-custom-endpoint       # starts both proxies
-# or directly
-node proxy/kimi-proxy.mjs
+# All proxies
+npx copilot-custom-endpoint
+```
+
+Clean up debug logs
 
-# clean up debug logs
+```bash
 npm run clean:logs
 # or with npx
 npx copilot-custom-endpoint clean
@@ -155,18 +229,30 @@ Sign up at [dashscope.aliyun.com](https://dashscope.aliyun.com) and create an AP
 
 The proxy dynamically enables thinking in plain chat and disables it during tool calls:
 
+Run Qwen proxy
+
 ```bash
-# from this repo — Qwen only
 npm run proxy:qwen
-# from this repo — both proxies concurrently
+```
+
+Run all proxies
+
+```bash
 npm run proxy
-# or with npx
+```
+
+Run globally (from any directory)
+
+```bash
+# Qwen only
 npx copilot-custom-endpoint qwen
-npx copilot-custom-endpoint       # starts both proxies
-# or directly
-node proxy/qwen-proxy.mjs
+# All proxies
+npx copilot-custom-endpoint
+```
 
-# clean up debug logs
+Clean up debug logs
+
+```bash
 npm run clean:logs
 # or with npx
 npx copilot-custom-endpoint clean

package/cli.mjs

@@ -1,4 +1,5 @@
 #!/usr/bin/env node
+import 'dotenv/config'
 import { fileURLToPath } from 'node:url'
 import { dirname, resolve } from 'node:path'
 import { fork } from 'node:child_process'

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "copilot-custom-endpoint",
-  "version": "1.0.3",
+  "version": "1.0.5",
   "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2 & Qwen 3.x",
   "license": "MIT",
   "type": "module",
@@ -47,5 +47,8 @@
     "eslint-config-prettier": "^10.1.8",
     "globals": "^17.6.0",
     "prettier": "^3.8.3"
+  },
+  "dependencies": {
+    "dotenv": "^17.4.2"
   }
 }

package/proxy/kimi-proxy.mjs

@@ -1,4 +1,5 @@
 #!/usr/bin/env node
+import 'dotenv/config'
 import { fileURLToPath } from 'node:url'
 import { createProxy } from '../lib/create-proxy.mjs'
 
@@ -16,7 +17,10 @@ import { createProxy } from '../lib/create-proxy.mjs'
  */
 const upstreamUrl =
   process.env.KIMI_UPSTREAM_URL ?? 'https://api.moonshot.ai/v1/chat/completions'
-const port = Number.parseInt(process.env.PORT ?? '3457', 10)
+const port = Number.parseInt(
+  process.env.KIMI_PROXY_PORT ?? process.env.PORT ?? '3457',
+  10
+)
 const forcedTemperature = Number(
   process.env.KIMI_PROXY_FORCE_TEMPERATURE ?? '1'
 )
@@ -37,7 +41,7 @@ if (process.argv.includes('--help')) {
 Starts a local HTTP proxy that rewrites the outbound chat-completions request body to use Kimi-compatible sampling values.
 
 Environment variables:
-  PORT                         Local listen port. Default: 3457
+  KIMI_PROXY_PORT              Local listen port. Default: 3457 (falls back to PORT)
   KIMI_UPSTREAM_URL            Upstream Moonshot chat-completions URL.
                                Default: https://api.moonshot.ai/v1/chat/completions
   KIMI_PROXY_FORCE_TEMPERATURE Temperature to force into the request body. Default: 1

package/proxy/qwen-proxy.mjs

@@ -1,4 +1,5 @@
 #!/usr/bin/env node
+import 'dotenv/config'
 import { fileURLToPath } from 'node:url'
 import { createProxy } from '../lib/create-proxy.mjs'
 
@@ -14,7 +15,10 @@ import { createProxy } from '../lib/create-proxy.mjs'
 const upstreamUrl =
   process.env.QWEN_UPSTREAM_URL ??
   'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions'
-const port = Number.parseInt(process.env.PORT ?? '3458', 10)
+const port = Number.parseInt(
+  process.env.QWEN_PROXY_PORT ?? process.env.PORT ?? '3458',
+  10
+)
 const disableThinkingWithTools =
   (process.env.QWEN_PROXY_DISABLE_THINKING_WITH_TOOLS ?? '1') !== '0'
 const defaultLogPath = fileURLToPath(
@@ -30,7 +34,7 @@ when the request includes a tools array, letting Qwen hybrid-thinking models
 show reasoning in plain chat while keeping tool loops stable.
 
 Environment variables:
-  PORT                         Local listen port. Default: 3458
+  QWEN_PROXY_PORT              Local listen port. Default: 3458 (falls back to PORT)
   QWEN_UPSTREAM_URL            Upstream DashScope chat-completions URL.
                                Default: https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
   QWEN_PROXY_DISABLE_THINKING_WITH_TOOLS