@mmmbuto/zai-codex-bridge 0.1.0 → 0.1.2

package/README.md

@@ -1,16 +1,16 @@
-# 🌉 Z.AI Codex Bridge
+# Z.AI Codex Bridge
 
-> **Local proxy that translates OpenAI Responses API format to Z.AI Chat Completions format**
+> Local proxy that translates OpenAI Responses API format to Z.AI Chat Completions format
 
-[![npm](https://img.shields.io/npm/v/@mmmbuto/zai-codex-bridge?style=flat-square&logo=npm)](https://www.npmjs.com/package/@mmmbuto/zai-codex-bridge)
-[![node](https://img.shields.io/node/v/@mmmbuto/zai-codex-bridge?style=flat-square&logo=node.js)](https://github.com/mmmbuto/zai-codex-bridge)
+[![npm](https://img.shields.io/npm/v/@mmmbuto/zai-codex-bridge?style=flat-square&logo=npm)](https://www.npmjs.org/package/@mmmbuto/zai-codex-bridge)
+[![node](https://img.shields.io/node/v/@mmmbuto/zai-codex-bridge?style=flat-square&logo=node.js)](https://github.com/DioNanos/zai-codex-bridge)
 [![license](https://img.shields.io/npm/l/@mmmbuto/zai-codex-bridge?style=flat-square)](LICENSE)
 
 ---
 
 ## What It Solves
 
-Codex uses the newer OpenAI **Responses API** format (with `instructions` and `input` fields), but Z.AI only supports the legacy **Chat Completions** format (with `messages` array).
+Codex uses the OpenAI **Responses API** format (with `instructions` and `input` fields), but Z.AI only supports the legacy **Chat Completions** format (with `messages` array).
 
 This proxy:
 1. Accepts Codex requests in **Responses format**
@@ -28,12 +28,11 @@ This proxy:
 
 ## Features
 
-✅ **Transparent translation** between Responses and Chat formats
-✅ **Streaming support** with SSE (Server-Sent Events)
-✅ **Zero dependencies** - uses Node.js built-ins only
-✅ **Auto-starting ZSH functions** - proxy runs only when Codex runs
-✅ **Health checks** at `/health` endpoint
-✅ **Configurable** via CLI flags and environment variables
+- Transparent translation between Responses and Chat formats
+- Streaming support with SSE (Server-Sent Events)
+- Zero dependencies - uses Node.js built-ins only
+- Health checks at `/health` endpoint
+- Configurable via CLI flags and environment variables
 
 ---
 
@@ -47,88 +46,40 @@ This proxy:
 
 ## Installation
 
-### Global Install (Recommended)
-
 ```bash
 npm install -g @mmmbuto/zai-codex-bridge
 ```
 
-### Local Install
+---
 
-```bash
-npm install @mmmbuto/zai-codex-bridge
-npx zai-codex-bridge
-```
+## Quick Start
 
-### From Source
+### 1. Start the Proxy
 
 ```bash
-git clone https://github.com/DioNanos/zai-codex-bridge.git
-cd zai-codex-bridge
-npm install
-npm link
+zai-codex-bridge
 ```
 
----
-
-## Quick Start
+The proxy will listen on `http://127.0.0.1:31415`
 
-### 1. Configure Codex
+### 2. Configure Codex
 
 Add to `~/.codex/config.toml`:
 
 ```toml
-[model_providers.zai_glm_proxy]
-name = "ZAI GLM via local proxy"
+[model_providers.zai_proxy]
+name = "ZAI via local proxy"
 base_url = "http://127.0.0.1:31415/v1"
 env_key = "OPENAI_API_KEY"
 wire_api = "responses"
 stream_idle_timeout_ms = 3000000
 ```
 
-### 2. Add ZSH Functions
-
-Add to `~/.zshrc`:
+### 3. Use with Codex
 
 ```bash
-_codex_glm_with_proxy () {
-  local KEY="$1"; shift
-  local HOST="127.0.0.1"
-  local PORT="31415"
-  local HEALTH="http://${HOST}:${PORT}/health"
-  local LOGFILE="${TMPDIR:-/tmp}/zai-codex-bridge.log"
-  local PROXY_PID=""
-
-  # Start proxy only if not responding
-  if ! curl -fsS "$HEALTH" >/dev/null 2>&1; then
-    zai-codex-bridge --host "$HOST" --port "$PORT" --log-level info >"$LOGFILE" 2>&1 &
-    PROXY_PID=$!
-    trap '[[ -n "$PROXY_PID" ]] && kill "$PROXY_PID" 2>/dev/null' EXIT INT TERM
-    for i in {1..40}; do
-      curl -fsS "$HEALTH" >/dev/null 2>&1 && break
-      sleep 0.05
-    done
-  fi
-
-  OPENAI_API_KEY="$KEY" codex -m "GLM-4.7" -c model_provider="zai_glm_proxy" "$@"
-}
-
-codex-glm-a () { _codex_glm_with_proxy "$ZAI_API_KEY_A" "$@"; }
-codex-glm-p () { _codex_glm_with_proxy "$ZAI_API_KEY_P" "$@"; }
-```
-
-### 3. Set API Keys
-
-```bash
-export ZAI_API_KEY_A="sk-your-key-here"
-export ZAI_API_KEY_P="sk-your-key-here"
-```
-
-### 4. Use It
-
-```bash
-source ~/.zshrc
-codex-glm-a
+export OPENAI_API_KEY="your-zai-api-key"
+codex -m "GLM-4.7" -c model_provider="zai_proxy"
 ```
 
 ---
@@ -136,7 +87,7 @@ codex-glm-a
 ## CLI Usage
 
 ```bash
-# Start with defaults (http://127.0.0.1:31415)
+# Start with defaults
 zai-codex-bridge
 
 # Custom port
@@ -163,130 +114,123 @@ export LOG_LEVEL=info
 
 ---
 
-## API Endpoints
-
-### `POST /responses`
-Accepts OpenAI Responses API format, translates to Chat, returns Responses format.
+## Auto-Starting Proxy with Codex
 
-### `POST /v1/responses`
-Same as `/responses` (for compatibility with Codex's path structure).
-
-### `GET /health`
-Health check endpoint.
-
----
-
-## Testing
+You can create a shell function that starts the proxy automatically when needed:
 
 ```bash
-# Set your Z.AI API key
-export ZAI_API_KEY="sk-your-key"
+codex-with-zai() {
+  local HOST="127.0.0.1"
+  local PORT="31415"
+  local HEALTH="http://${HOST}:${PORT}/health"
+  local PROXY_PID=""
 
-# Run test suite
-npm run test:curl
-```
+  # Start proxy only if not responding
+  if ! curl -fsS "$HEALTH" >/dev/null 2>&1; then
+    zai-codex-bridge --host "$HOST" --port "$PORT" >/dev/null 2>&1 &
+    PROXY_PID=$!
+    trap 'kill $PROXY_PID 2>/dev/null' EXIT INT TERM
+    sleep 2
+  fi
 
-### Manual Test
+  # Run codex
+  codex -m "GLM-4.7" -c model_provider="zai_proxy" "$@"
+}
+```
 
+Usage:
 ```bash
-# Start proxy
-zai-codex-bridge &
-
-# Test health
-curl http://127.0.0.1:31415/health
-
-# Test Responses API
-curl -X POST http://127.0.0.1:31415/v1/responses \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer $ZAI_API_KEY" \
-  -d '{
-    "model": "GLM-4.7",
-    "instructions": "Be brief",
-    "input": [{"role": "user", "content": "What is 2+2?"}],
-    "stream": false
-  }'
+codex-with-zai
+# Proxy auto-starts, Codex runs
+# Ctrl+D exits both
 ```
 
 ---
 
-## Architecture
-
-```
-Codex (Responses API)
-    ↓
-Proxy (localhost:31415)
-    ↓
-Translation: Responses → Chat
-    ↓
-Z.AI (Chat Completions)
-    ↓
-Translation: Chat → Responses
-    ↓
-Codex
-```
-
----
+## API Endpoints
 
-## Documentation
+### `POST /responses`
+Accepts OpenAI Responses API format, translates to Chat, returns Responses format.
 
-📚 **Complete Guide**: [docs/guide.md](docs/guide.md)
+### `POST /v1/responses`
+Same as `/responses` (for compatibility with Codex's path structure).
 
-The guide includes:
-- Detailed setup instructions
-- Usage examples
-- Troubleshooting
-- Function reference
-- Advanced configuration
+### `GET /health`
+Health check endpoint.
 
 ---
 
-## Troubleshooting
-
-### Port Already in Use
+## Translation Details
 
-```bash
-lsof -i :31415
-kill -9 <PID>
-```
+### Request: Responses → Chat
 
-### Connection Refused
+```javascript
+// Input (Responses format)
+{
+  model: "GLM-4.7",
+  instructions: "Be helpful",
+  input: [
+    { role: "user", content: "Hello" }
+  ],
+  max_output_tokens: 1000
+}
 
-```bash
-curl http://127.0.0.1:31415/health
-zai-codex-bridge --log-level debug
+// Output (Chat format)
+{
+  model: "GLM-4.7",
+  messages: [
+    { role: "system", content: "Be helpful" },
+    { role: "user", content: "Hello" }
+  ],
+  max_tokens: 1000
+}
 ```
 
-### Z.AI Errors
+### Response: Chat → Responses
 
-Verify API key and test Z.AI directly:
-```bash
-curl -X POST https://api.z.ai/api/coding/paas/v4/chat/completions \
-  -H "Authorization: Bearer $ZAI_API_KEY" \
-  -H "Content-Type: application/json" \
-  -d '{"model":"GLM-4.7","messages":[{"role":"user","content":"test"}]}'
+```javascript
+// Input (Chat format)
+{
+  choices: [{
+    message: { content: "Hi there!" }
+  }],
+  usage: {
+    prompt_tokens: 10,
+    completion_tokens: 5
+  }
+}
+
+// Output (Responses format)
+{
+  output: [{ value: "Hi there!", content_type: "text" }],
+  status: "completed",
+  usage: {
+    input_tokens: 10,
+    output_tokens: 5
+  }
+}
 ```
 
 ---
 
-## Development
+## Testing
 
 ```bash
-# Clone repo
-git clone https://github.com/DioNanos/zai-codex-bridge.git
-cd zai-codex-bridge
-
-# Run in development
-npm start
+# Set your Z.AI API key
+export ZAI_API_KEY="sk-your-key"
 
-# Run tests
+# Run test suite
 npm run test:curl
-
-# Link globally
-npm link
 ```
 
 ---
 
+## Documentation
+
+Complete usage guide: [docs/guide.md](docs/guide.md)
+
+---
+
 ## License
 
 MIT License - Copyright (c) 2026 Davide A. Guglielmi

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmmbuto/zai-codex-bridge",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "description": "Local proxy that translates OpenAI Responses API format to Z.AI Chat Completions format for Codex",
   "main": "src/server.js",
   "bin": {

package/src/server.js

@@ -188,8 +188,10 @@ async function makeUpstreamRequest(path, body, headers) {
     'Authorization': headers['authorization'] || headers['Authorization'] || ''
   };
 
-  log('debug', 'Upstream request:', {
+  log('info', 'Upstream request:', {
     url: url.href,
+    path: path,
+    base: ZAI_BASE_URL,
     hasAuth: !!upstreamHeaders.Authorization
   });