feat: add desktop app release packaging
This commit is contained in:
lutc5
570
README.md
570
README.md
@@ -1,344 +1,308 @@
|
||||
# lingma-ipc-proxy
|
||||
# Lingma IPC Proxy
|
||||
|
||||
[English](./README.md) | [简体中文](./README.zh-CN.md)
|
||||
|
||||
A standalone Go backend that talks to Lingma over Lingma's local pipe or websocket transport and exposes:
|
||||
Lingma IPC Proxy exposes Tongyi Lingma's local IDE plugin capability as standard **OpenAI-compatible** and **Anthropic-compatible** HTTP APIs. It can be used as a CLI proxy service or as a cross-platform desktop app for macOS and Windows.
|
||||
|
||||
- `GET /v1/models`
|
||||
- `POST /v1/messages`
|
||||
- `POST /v1/chat/completions`
|
||||
The project is designed for tools such as Claude Code, Cline, Continue, OpenCode, custom agents, and any client that can talk to OpenAI or Anthropic style APIs.
|
||||
|
||||
Current scope:
|
||||
## Current Version
|
||||
|
||||
- supports both non-streaming and streaming responses
|
||||
- one request at a time
|
||||
- supports Windows named-pipe transport and local websocket transport
|
||||
- directly uses Lingma IPC, not DOM/CDP
|
||||
- OpenAI-compatible `tools` / `tool_choice` support (tool emulation via prompt engineering)
|
||||
- Anthropic-compatible `tools` / `tool_choice` support
|
||||
The current desktop line is `v1.2.0`.
|
||||
|
||||
## Run
|
||||
Release builds are produced by GitHub Actions for:
|
||||
|
||||
```powershell
|
||||
cd C:\Workspace\Personal\lingma-ipc-proxy
|
||||
go run .\cmd\lingma-ipc-proxy
|
||||
| Asset | Platform | Purpose |
|
||||
| --- | --- | --- |
|
||||
| `lingma-ipc-proxy_<tag>_darwin_arm64.tar.gz` | macOS | CLI proxy |
|
||||
| `lingma-ipc-proxy_<tag>_windows_amd64.zip` | Windows | CLI proxy |
|
||||
| `lingma-ipc-proxy-desktop_<tag>_darwin_arm64.zip` | macOS | Desktop app |
|
||||
| `lingma-ipc-proxy-desktop_<tag>_windows_amd64.zip` | Windows | Desktop app |
|
||||
| `lingma-ipc-proxy_<tag>_sha256.txt` | all | Checksums |
|
||||
|
||||
## Desktop App
|
||||
|
||||
The desktop app wraps the proxy with a native-feeling control panel:
|
||||
|
||||
- Start, stop, and restart the proxy.
|
||||
- Inspect health, latency, recent requests, models, settings, and logs.
|
||||
- View full request and response bodies with internal scrolling and hidden scrollbars.
|
||||
- Copy endpoint URLs, model IDs, request logs, and response logs with visible feedback.
|
||||
- Detect Lingma IPC paths automatically on macOS and Windows, with manual fallback settings.
|
||||
- Follow system theme automatically, or switch light/dark mode manually.
|
||||
- Keep the proxy running when the window is closed; quit explicitly from the app/menu.
|
||||
|
||||
### Screenshots
|
||||
|
||||
Light mode:
|
||||
|
||||
|
||||
|
||||
Dark mode:
|
||||
|
||||
|
||||
|
||||
Narrow window layout:
|
||||
|
||||
|
||||
|
||||
## Supported APIs
|
||||
|
||||
| API | Endpoint | Support |
|
||||
| --- | --- | --- |
|
||||
| Health | `GET /` and `GET /health` | supported |
|
||||
| Models | `GET /v1/models` | supported |
|
||||
| OpenAI Chat Completions | `POST /v1/chat/completions` | streaming and non-streaming |
|
||||
| Anthropic Messages | `POST /v1/messages` | streaming and non-streaming |
|
||||
|
||||
## What This Fork Adds
|
||||
|
||||
Compared with the original protocol proof of concept, this repository focuses on making the proxy usable as a complete local product:
|
||||
|
||||
- **Function Calling / Tools** for both OpenAI and Anthropic clients.
|
||||
- **Tool result continuation** for multi-step agent loops.
|
||||
- **Image input** for OpenAI `image_url` and Anthropic image blocks.
|
||||
- **More request parameter compatibility** so stricter clients can connect without custom patches.
|
||||
- **Full request and response recording** in the desktop app for debugging 400/500 errors.
|
||||
- **macOS and Windows desktop app** with start/stop/restart, settings, logs, model discovery, themes, and window lifecycle handling.
|
||||
- **Cross-platform release packaging** for CLI and desktop builds.
|
||||
|
||||
### OpenAI Compatibility
|
||||
|
||||
The proxy accepts common OpenAI request fields:
|
||||
|
||||
- `model`, `messages`, `stream`
|
||||
- `temperature`, `top_p`, `stop`
|
||||
- `max_tokens`, `max_completion_tokens`
|
||||
- `presence_penalty`, `frequency_penalty`
|
||||
- `tools`, `tool_choice`, `parallel_tool_calls`
|
||||
- `response_format`, `seed`, `user`, `reasoning_effort`
|
||||
- image input through `image_url` data URLs or HTTP URLs
|
||||
|
||||
### Anthropic Compatibility
|
||||
|
||||
The proxy accepts common Anthropic request fields:
|
||||
|
||||
- `model`, `system`, `messages`, `stream`
|
||||
- `temperature`, `top_p`, `top_k`, `stop_sequences`
|
||||
- `max_tokens`, `metadata`
|
||||
- `tools`, `tool_choice`
|
||||
- image blocks through base64 sources
|
||||
- tool result continuation blocks
|
||||
|
||||
## Architecture
|
||||
|
||||
```mermaid
|
||||
flowchart LR
|
||||
Client["OpenAI / Anthropic Client"] --> HTTP["HTTP API Layer"]
|
||||
Desktop["Desktop App"] --> AppBridge["Wails Go Bridge"]
|
||||
AppBridge --> Service["Proxy Service"]
|
||||
HTTP --> Service
|
||||
Service --> Session["Session Manager"]
|
||||
Service --> Tools["Tool Emulation"]
|
||||
Service --> Models["Model Discovery"]
|
||||
Service --> Transport["Lingma Transport"]
|
||||
Transport --> Pipe["Windows Named Pipe"]
|
||||
Transport --> WS["macOS / Windows WebSocket"]
|
||||
Pipe --> Lingma["Tongyi Lingma IDE Plugin"]
|
||||
WS --> Lingma
|
||||
```
|
||||
|
||||
## Config File
|
||||
### Module Layout
|
||||
|
||||
The proxy can load a JSON config file so you do not need to carry a long command line every time.
|
||||
| Path | Responsibility |
|
||||
| --- | --- |
|
||||
| `cmd/lingma-ipc-proxy` | CLI entrypoint, config loading, signal handling |
|
||||
| `internal/httpapi` | OpenAI/Anthropic HTTP routes, streaming SSE responses, request recording |
|
||||
| `internal/service` | request orchestration, sessions, model discovery, proxy lifecycle |
|
||||
| `internal/lingmaipc` | Lingma JSON-RPC transport over Named Pipe and WebSocket |
|
||||
| `internal/toolemulation` | tool definition injection, action block parsing, tool result projection |
|
||||
| `desktop` | Wails desktop shell, native window commands, proxy control bridge |
|
||||
| `desktop/frontend` | Vue UI for dashboard, requests, models, settings, and logs |
|
||||
| `.github/workflows/release.yml` | CI release pipeline for macOS and Windows CLI/Desktop packages |
|
||||
|
||||
Default lookup:
|
||||
## Transport Detection
|
||||
|
||||
| Platform | Default transport | Detection |
|
||||
| --- | --- | --- |
|
||||
| macOS | WebSocket | reads Lingma `SharedClientCache` files under user application support paths |
|
||||
| Windows | Named Pipe / WebSocket | scans Lingma named pipes and shared cache hints |
|
||||
| Linux | WebSocket | manual `--ws-url` is recommended |
|
||||
|
||||
If auto detection fails, set the path manually in the desktop Settings page or pass CLI flags:
|
||||
|
||||
```bash
|
||||
lingma-ipc-proxy --transport websocket --ws-url ws://127.0.0.1:36510 --port 8095
|
||||
lingma-ipc-proxy --transport pipe --pipe-name '\\.\pipe\lingma-ipc'
|
||||
```
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Desktop App
|
||||
|
||||
1. Install VS Code and the Tongyi Lingma extension.
|
||||
2. Log in to Tongyi Lingma and verify the Lingma panel can chat normally.
|
||||
3. Download the desktop asset from [Releases](https://github.com/Lutiancheng1/lingma-ipc-proxy/releases).
|
||||
4. Start `Lingma IPC Proxy`.
|
||||
5. Click `探测模型` after the proxy is running.
|
||||
6. Configure clients to use `http://127.0.0.1:8095`.
|
||||
|
||||
### CLI
|
||||
|
||||
```bash
|
||||
git clone https://github.com/Lutiancheng1/lingma-ipc-proxy.git
|
||||
cd lingma-ipc-proxy
|
||||
go build -o ./dist/lingma-ipc-proxy ./cmd/lingma-ipc-proxy
|
||||
./dist/lingma-ipc-proxy --host 127.0.0.1 --port 8095 --session-mode auto
|
||||
```
|
||||
|
||||
Windows:
|
||||
|
||||
```powershell
|
||||
.\scripts\build.ps1
|
||||
.\dist\lingma-ipc-proxy.exe --host 127.0.0.1 --port 8095 --session-mode auto
|
||||
```
|
||||
|
||||
## Client Configuration
|
||||
|
||||
### Claude Code
|
||||
|
||||
```bash
|
||||
export ANTHROPIC_BASE_URL="http://127.0.0.1:8095"
|
||||
export ANTHROPIC_API_KEY="any"
|
||||
```
|
||||
|
||||
Then select a model in Claude Code:
|
||||
|
||||
```text
|
||||
/model Qwen3-Coder
|
||||
```
|
||||
|
||||
### Cline
|
||||
|
||||
- Provider: `OpenAI Compatible`
|
||||
- Base URL: `http://127.0.0.1:8095/v1`
|
||||
- API Key: `any`
|
||||
- Model ID: `Qwen3-Coder`
|
||||
|
||||
### Continue
|
||||
|
||||
```json
|
||||
{
|
||||
"models": [
|
||||
{
|
||||
"title": "Lingma Proxy",
|
||||
"provider": "openai",
|
||||
"model": "Qwen3-Coder",
|
||||
"apiKey": "any",
|
||||
"apiBase": "http://127.0.0.1:8095/v1"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Models
|
||||
|
||||
The proxy reports the models exposed by the Lingma plugin. The desktop app does not force a global model switch; the calling client should specify the `model` field. Clicking a model in the desktop app copies its model ID.
|
||||
|
||||
Observed model IDs include:
|
||||
|
||||
- `Auto`
|
||||
- `Kimi-K2.6`
|
||||
- `MiniMax-M2.7`
|
||||
- `Qwen3-Coder`
|
||||
- `Qwen3-Max`
|
||||
- `Qwen3-Thinking`
|
||||
- `Qwen3.6-Plus`
|
||||
|
||||
For tool-heavy coding workflows, `Qwen3-Coder` is the recommended first choice.
|
||||
|
||||
## Configuration
|
||||
|
||||
Default config file:
|
||||
|
||||
```text
|
||||
./lingma-ipc-proxy.json
|
||||
```
|
||||
|
||||
You can also point to an explicit file:
|
||||
|
||||
```powershell
|
||||
.\dist\lingma-ipc-proxy.exe --config .\config.example.json
|
||||
```
|
||||
|
||||
Resolution order:
|
||||
|
||||
- built-in defaults
|
||||
- JSON config file
|
||||
- environment variables
|
||||
- command-line flags
|
||||
|
||||
An example config is included at:
|
||||
|
||||
- `config.example.json`
|
||||
|
||||
A practical setup is to copy it to `lingma-ipc-proxy.json`, adjust the values once, and then start the proxy without a long flag list.
|
||||
|
||||
Recommended layout:
|
||||
Example:
|
||||
|
||||
```json
|
||||
{
|
||||
"host": "127.0.0.1",
|
||||
"port": 8095,
|
||||
"transport": "auto",
|
||||
"mode": "chat",
|
||||
"session_mode": "reuse",
|
||||
"timeout": 120,
|
||||
"cwd": "C:/Workspace/Personal/lingma-ipc-proxy",
|
||||
"shell_type": "powershell",
|
||||
"current_file_path": "",
|
||||
"pipe": "",
|
||||
"websocket_url": ""
|
||||
}
|
||||
```
|
||||
|
||||
## macOS / Linux
|
||||
|
||||
This project also works on macOS and Linux via **WebSocket transport**. The Windows named-pipe transport is automatically skipped on non-Windows platforms.
|
||||
|
||||
### Run on macOS
|
||||
|
||||
```bash
|
||||
cd ~/OpenSources/lingma-ipc-proxy
|
||||
go run ./cmd/lingma-ipc-proxy --transport websocket --port 8095
|
||||
|
||||
# Or use auto-detect (will discover websocket port from Lingma's shared client cache)
|
||||
go run ./cmd/lingma-ipc-proxy --port 8095
|
||||
```
|
||||
|
||||
### Build on macOS / Linux
|
||||
|
||||
```bash
|
||||
cd ~/OpenSources/lingma-ipc-proxy
|
||||
go build -o ./dist/lingma-ipc-proxy ./cmd/lingma-ipc-proxy
|
||||
```
|
||||
|
||||
### macOS Config Example
|
||||
|
||||
```json
|
||||
{
|
||||
"host": "127.0.0.1",
|
||||
"port": 8095,
|
||||
"transport": "websocket",
|
||||
"mode": "agent",
|
||||
"shell_type": "zsh",
|
||||
"session_mode": "auto",
|
||||
"timeout": 120
|
||||
"timeout": 120,
|
||||
"cwd": "/Users/you/project",
|
||||
"current_file_path": ""
|
||||
}
|
||||
```
|
||||
|
||||
## Build
|
||||
Priority order:
|
||||
|
||||
Build a Windows executable:
|
||||
1. built-in defaults
|
||||
2. JSON config file
|
||||
3. environment variables
|
||||
4. command-line flags
|
||||
5. desktop Settings page updates
|
||||
|
||||
## Function Calling / Tool Calling
|
||||
|
||||
Lingma does not expose a native public OpenAI/Anthropic tool-call protocol, so this proxy emulates tool calling:
|
||||
|
||||
1. Normalize OpenAI or Anthropic tool definitions.
|
||||
2. Inject tool contracts into the Lingma prompt.
|
||||
3. Parse model action blocks from the response.
|
||||
4. Convert parsed actions back into OpenAI `tool_calls` or Anthropic `tool_use`.
|
||||
5. Feed tool results back into Lingma for continuation.
|
||||
|
||||
This is most reliable with `Qwen3-Coder`.
|
||||
|
||||
## Local Desktop Build
|
||||
|
||||
Install Wails:
|
||||
|
||||
```bash
|
||||
go install github.com/wailsapp/wails/v2/cmd/wails@v2.12.0
|
||||
```
|
||||
|
||||
Build macOS:
|
||||
|
||||
```bash
|
||||
npm ci --prefix desktop/frontend
|
||||
cd desktop
|
||||
wails build -platform darwin/arm64 -clean
|
||||
```
|
||||
|
||||
Build Windows on Windows:
|
||||
|
||||
```powershell
|
||||
cd C:\Workspace\Personal\lingma-ipc-proxy
|
||||
.\scripts\build.ps1
|
||||
npm ci --prefix desktop/frontend
|
||||
cd desktop
|
||||
wails build -platform windows/amd64 -clean
|
||||
```
|
||||
|
||||
Default output:
|
||||
The desktop bundle name is always `Lingma IPC Proxy`.
|
||||
|
||||
```text
|
||||
dist\lingma-ipc-proxy.exe
|
||||
```
|
||||
## Release Plan
|
||||
|
||||
## Release
|
||||
The release workflow is triggered by:
|
||||
|
||||
GitHub Actions can publish a GitHub Release automatically.
|
||||
- pushing a tag such as `v1.2.0`
|
||||
- manually running the `Release` workflow with a tag input
|
||||
|
||||
Trigger rules:
|
||||
Planned improvements:
|
||||
|
||||
- push a tag matching `v*`, for example `v0.1.0`
|
||||
- or run the `Release` workflow manually and pass a tag
|
||||
- macOS signing and notarization
|
||||
- Windows installer packaging
|
||||
- configurable log retention
|
||||
- request export/import
|
||||
- richer model metadata display
|
||||
- optional Linux desktop packaging after the Lingma transport story is stable
|
||||
|
||||
Example:
|
||||
## Acknowledgements
|
||||
|
||||
```powershell
|
||||
git tag v0.1.0
|
||||
git push origin v0.1.0
|
||||
```
|
||||
|
||||
Release assets:
|
||||
|
||||
- `lingma-ipc-proxy_<tag>_windows_amd64.exe`
|
||||
- `lingma-ipc-proxy_<tag>_windows_amd64.zip`
|
||||
- `lingma-ipc-proxy_<tag>_sha256.txt`
|
||||
|
||||
Direct Go build command:
|
||||
|
||||
```powershell
|
||||
$env:CGO_ENABLED = "0"
|
||||
$env:GOOS = "windows"
|
||||
$env:GOARCH = "amd64"
|
||||
go build -trimpath -ldflags "-s -w" -o .\dist\lingma-ipc-proxy.exe .\cmd\lingma-ipc-proxy
|
||||
```
|
||||
|
||||
Run the built binary:
|
||||
|
||||
```powershell
|
||||
.\dist\lingma-ipc-proxy.exe --host 127.0.0.1 --port 8095 --session-mode auto
|
||||
.\dist\lingma-ipc-proxy.exe --transport websocket --ws-url ws://127.0.0.1:36510 --port 8095
|
||||
```
|
||||
|
||||
## Windows Service
|
||||
|
||||
For this project, the correct deployment shape is a native local process, not Docker. The proxy talks to Lingma over local pipe or websocket transport, so it should run on the same host as Lingma itself.
|
||||
|
||||
### NSSM
|
||||
|
||||
Build first:
|
||||
|
||||
```powershell
|
||||
.\scripts\build.ps1
|
||||
```
|
||||
|
||||
Install with NSSM:
|
||||
|
||||
```powershell
|
||||
.\scripts\install-nssm-service.ps1 -NssmPath C:\Tools\nssm\nssm.exe
|
||||
```
|
||||
|
||||
This wraps:
|
||||
|
||||
```powershell
|
||||
nssm.exe install LingmaIpcProxy C:\Workspace\Personal\lingma-ipc-proxy\dist\lingma-ipc-proxy.exe --host 127.0.0.1 --port 8095 --session-mode auto
|
||||
nssm.exe set LingmaIpcProxy AppDirectory C:\Workspace\Personal\lingma-ipc-proxy
|
||||
nssm.exe start LingmaIpcProxy
|
||||
```
|
||||
|
||||
### WinSW
|
||||
|
||||
Prepare the executable:
|
||||
|
||||
```powershell
|
||||
.\scripts\build.ps1
|
||||
```
|
||||
|
||||
Put a WinSW binary at:
|
||||
|
||||
```text
|
||||
dist\WinSW-x64.exe
|
||||
```
|
||||
|
||||
Then generate the wrapper files:
|
||||
|
||||
```powershell
|
||||
.\scripts\install-winsw-service.ps1
|
||||
```
|
||||
|
||||
That script creates:
|
||||
|
||||
- `LingmaIpcProxy.exe`
|
||||
- `LingmaIpcProxy.xml`
|
||||
|
||||
Then install/start:
|
||||
|
||||
```powershell
|
||||
.\LingmaIpcProxy.exe install
|
||||
.\LingmaIpcProxy.exe start
|
||||
```
|
||||
|
||||
The WinSW XML template lives at:
|
||||
|
||||
- `scripts\lingma-ipc-proxy.xml.template`
|
||||
|
||||
## Flags
|
||||
|
||||
```powershell
|
||||
go run .\cmd\lingma-ipc-proxy --port 8095 --session-mode auto
|
||||
```
|
||||
|
||||
- `--host`
|
||||
- `--port`
|
||||
- `--transport`
|
||||
- `--pipe`
|
||||
- `--ws-url`
|
||||
- `--cwd`
|
||||
- `--current-file-path`
|
||||
- `--mode`
|
||||
- `--shell-type`
|
||||
- `--session-mode`
|
||||
- `reuse`: keep using the sticky Lingma session
|
||||
- `fresh`: create a temporary session for the request and delete it after completion
|
||||
- `auto`: single-turn requests reuse; requests with system/history use a temporary fresh session and delete it after completion
|
||||
- `--timeout`
|
||||
|
||||
## Environment
|
||||
|
||||
- `LINGMA_PROXY_TRANSPORT`
|
||||
- `LINGMA_IPC_PIPE`
|
||||
- `LINGMA_PROXY_WS_URL`
|
||||
- `LINGMA_PROXY_HOST`
|
||||
- `LINGMA_PROXY_PORT`
|
||||
- `LINGMA_PROXY_CWD`
|
||||
- `LINGMA_PROXY_CURRENT_FILE_PATH`
|
||||
- `LINGMA_PROXY_MODE`
|
||||
- `LINGMA_PROXY_SHELL_TYPE`
|
||||
- `LINGMA_PROXY_SESSION_MODE`
|
||||
- `LINGMA_PROXY_TIMEOUT_SECONDS`
|
||||
|
||||
## Examples
|
||||
|
||||
Anthropic non-streaming:
|
||||
|
||||
```powershell
|
||||
$body = @{
|
||||
model = "dashscope_qwen3_coder"
|
||||
messages = @(
|
||||
@{ role = "user"; content = "请只回复：ANTHROPIC_OK" }
|
||||
)
|
||||
stream = $false
|
||||
} | ConvertTo-Json -Depth 8
|
||||
|
||||
Invoke-RestMethod `
|
||||
-Method Post `
|
||||
-Uri http://127.0.0.1:8095/v1/messages `
|
||||
-ContentType "application/json" `
|
||||
-Body $body
|
||||
```
|
||||
|
||||
Anthropic streaming:
|
||||
|
||||
```powershell
|
||||
$body = @{
|
||||
model = "dashscope_qwen3_coder"
|
||||
messages = @(
|
||||
@{ role = "user"; content = "请只回复：ANTHROPIC_STREAM_OK" }
|
||||
)
|
||||
stream = $true
|
||||
} | ConvertTo-Json -Depth 8
|
||||
|
||||
curl.exe -N `
|
||||
-H "Content-Type: application/json" `
|
||||
-d $body `
|
||||
http://127.0.0.1:8095/v1/messages
|
||||
```
|
||||
|
||||
OpenAI non-streaming:
|
||||
|
||||
```powershell
|
||||
$body = @{
|
||||
model = "dashscope_qwen3_coder"
|
||||
messages = @(
|
||||
@{ role = "user"; content = "请只回复：OPENAI_OK" }
|
||||
)
|
||||
stream = $false
|
||||
} | ConvertTo-Json -Depth 8
|
||||
|
||||
Invoke-RestMethod `
|
||||
-Method Post `
|
||||
-Uri http://127.0.0.1:8095/v1/chat/completions `
|
||||
-ContentType "application/json" `
|
||||
-Body $body
|
||||
```
|
||||
|
||||
OpenAI streaming:
|
||||
|
||||
```powershell
|
||||
$body = @{
|
||||
model = "dashscope_qwen3_coder"
|
||||
messages = @(
|
||||
@{ role = "user"; content = "请只回复：OPENAI_STREAM_OK" }
|
||||
)
|
||||
stream = $true
|
||||
} | ConvertTo-Json -Depth 8
|
||||
|
||||
curl.exe -N `
|
||||
-H "Content-Type: application/json" `
|
||||
-d $body `
|
||||
http://127.0.0.1:8095/v1/chat/completions
|
||||
```
|
||||
|
||||
## Streaming shape
|
||||
|
||||
Anthropic streaming emits SSE events compatible with the `messages` API shape:
|
||||
|
||||
- `message_start`
|
||||
- `content_block_start`
|
||||
- `content_block_delta`
|
||||
- `content_block_stop`
|
||||
- `message_delta`
|
||||
- `message_stop`
|
||||
|
||||
OpenAI streaming emits `chat.completion.chunk` payloads as `data:` lines and ends with:
|
||||
|
||||
- `data: [DONE]`
|
||||
This project is based on the protocol insight and initial discovery work from [coolxll/lingma-ipc-proxy](https://github.com/coolxll/lingma-ipc-proxy). The core idea of connecting to Lingma's private local IPC protocol and exposing standard API endpoints came from that project. This fork extends the implementation with broader OpenAI/Anthropic compatibility, tool emulation, image handling, desktop app support, request/log inspection, cross-platform packaging, and release automation.
|
||||
|
||||
Reference in New Issue
Block a user