luxferre/gr2gw
1
0
Fork 0
Code Actions Projects Activity

docs: enforce sentence-case in headers, subheadings and list items

Browse Source
This commit is contained in:
Luxferre
2026-09-07 08:02:09 +03:00
parent 662a4d66b7
commit eb1ae22bab
2 changed files with 32 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+22 -22
View File
@@ -1,4 +1,4 @@
# gr2gw: Universal Gradio to OpenAI LLM Gateway
# gr2gw: Universal Gradio to OpenAI LLM gateway
A zero-dependency, high-performance Go proxy server that introspects any Gradio chat space (such as Hugging Face Spaces or custom deployments) and exposes a standards-compliant OpenAI `/v1/chat/completions` and `/v1/models` HTTP API.
@@ -8,34 +8,34 @@ Default demo space: `https://ghost2513-openai-gpt-oss-120b.hf.space`
## Features
- **Zero External Dependencies**: Pure Go standard library (`net/http`, `encoding/json`, `bufio`, etc.).
- **Automatic Space Introspection**: Dynamically queries `/gradio_api/info`, `/config`, and Hugging Face space metadata to discover models, endpoints, and input parameter mappings.
- **Native Tencent Hunyuan 3 (`tencent-hy3`) Support**:
- **Zero external dependencies**: Pure Go standard library (`net/http`, `encoding/json`, `bufio`, etc.).
- **Automatic space introspection**: Dynamically queries `/gradio_api/info`, `/config`, and Hugging Face space metadata to discover models, endpoints, and input parameter mappings.
- **Native Tencent Hunyuan 3 (`tencent-hy3`) support**:
- Full native zero-degradation handling for official spaces like `https://tencent-hy3.hf.space`.
- Maps `functions_json_str` natively without polluting the system prompt.
- Preserves multi-turn reasoning content and tool call history in standard OpenAI message schemas.
- Maps `reasoning_effort` (`no_think`, `low`, `high`) directly to `think_level`.
- **Universal Multi-turn Handling**:
- **Universal multi-turn handling**:
- Automatically formats conversation history into structured inputs when the space supports them.
- Transparently composes multi-turn dialogue (`System`, `User`, `Assistant`) into single prompt inputs when the space only accepts a single message textbox.
- Automatically pads hidden/State inputs (e.g. Gradio State components) to prevent backend argument count mismatches.
- **Real-Time Streaming & Accumulation Filter**:
- **Real-time streaming & accumulation filter**:
- Automatically computes token deltas from cumulative or incremental Gradio SSE output streams (including 2D Hy3 frames `[[content, reasoning, tool_calls, history]]`).
- Emits standards-compliant `chat.completion.chunk` SSE events in real time.
- **Thinking & Reasoning Token Separation**:
- **Thinking & reasoning token separation**:
- Streams native reasoning chunks as `delta.reasoning_content` in real time.
- Detects `<think>...</think>` tags in real time as fallback for standard spaces.
- Separates reasoning into `delta.reasoning_content` (streaming) and `message.reasoning_content` (non-streaming).
- Keeps `content` clean without tag leakage.
- **Full Tool Calling & Function Interception**:
- **Full tool calling & function interception**:
- Formats schemas into native `functions_json_str` (Hy3) or system prompts (standard spaces).
- **`StreamToolCallFilter`**: Stateful sliding-window filter that prevents `<tool_call>` tags from leaking into `delta.content`. Emits structured OpenAI `delta.tool_calls` chunks and sets `finish_reason: "tool_calls"`.
- Seamlessly maintains multi-turn context when tool results are submitted back via `role: "tool"`.
- **Built-in SOCKS5 Proxy Client**:
- **Built-in SOCKS5 proxy client**:
- Full RFC 1928 / RFC 1929 implementation with domain resolution (`socks5h://`), IPv4, IPv6, and username/password auth.
- **Dynamic Space Override**:
- **Dynamic space override**:
- Switch the target Gradio space on-the-fly per request using the `X-Gradio-Space` or `X-Space-URL` HTTP headers.
- **Fibonacci Retry Engine**:
- **Fibonacci retry engine**:
- Resilient backoff retry mechanism (1s, 1s, 2s, 3s, 5s) for transient network hiccups.
---
@@ -57,7 +57,7 @@ make test
## Usage
### Quick Start
### Quick start
Run with the default space (`https://ghost2513-openai-gpt-oss-120b.hf.space`):
```bash
@@ -74,7 +74,7 @@ With SOCKS5 proxy:
./bin/gr2gw -space https://ghost2513-openai-gpt-oss-120b.hf.space -socks socks5://127.0.0.1:1080
```
### CLI Flags
### CLI flags
| Flag | Default | Description |
|------|---------|-------------|
@@ -85,16 +85,16 @@ With SOCKS5 proxy:
| `-user-agent`, `-ua` | Firefox string | Custom User-Agent header |
| `-timeout` | `300` | Upstream request timeout in seconds |
### Environment Variables
### Environment variables
- `GRADIO_SPACE_URL`: Default Gradio space URL fallback.
- `ALL_PROXY`, `SOCKS5_PROXY`, `SOCKS_PROXY`: Default SOCKS5 proxy URL fallback.
- `GRADIO_SPACE_URL`: default Gradio space URL fallback.
- `ALL_PROXY`, `SOCKS5_PROXY`, `SOCKS_PROXY`: default SOCKS5 proxy URL fallback.
---
## API Examples
## API examples
### List Models
### List models
```bash
curl http://localhost:8080/v1/models
@@ -121,7 +121,7 @@ Response:
}
```
### Chat Completions (Non-Streaming)
### Chat completions (non-streaming)
```bash
curl http://localhost:8080/v1/chat/completions \
@@ -159,7 +159,7 @@ Response:
}
```
### Chat Completions (Streaming)
### Chat completions (streaming)
```bash
curl -N http://localhost:8080/v1/chat/completions \
@@ -173,7 +173,7 @@ curl -N http://localhost:8080/v1/chat/completions \
}'
```
### Tool Calling
### Tool calling
```bash
curl http://localhost:8080/v1/chat/completions \
@@ -235,7 +235,7 @@ Response:
}
```
### Dynamic Target Space Override
### Dynamic target space override
Override the target space per request without restarting the server: