fix(tools): recover tool calls from tool_use_failed errors and update default space to digital-twin

README.md

@@ -1,13 +1,13 @@
-# 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.
 
-Default demo space: `https://ghost2513-openai-gpt-oss-120b.hf.space`
+Default demo space: `https://lucasmarchettidelima-digital-twin.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.
+- **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.
@@ -27,7 +27,8 @@ Default demo space: `https://ghost2513-openai-gpt-oss-120b.hf.space`
   - Keeps `content` clean without tag leakage.
 - **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"`.
+  - Intercepts and recovers tool calls from upstream `tool_use_failed` errors containing `failed_generation`.
+  - **`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**:
   - Full RFC 1928 / RFC 1929 implementation with domain resolution (`socks5h://`), IPv4, IPv6, and username/password auth.
@@ -59,7 +60,7 @@ make test
 
 ### Quick start
 
-Run with the default space (`https://ghost2513-openai-gpt-oss-120b.hf.space`):
+Run with the default space (`https://lucasmarchettidelima-digital-twin.hf.space`):
 ```bash
 ./bin/gr2gw -port 8080
 ```
@@ -71,14 +72,14 @@ Target any other Gradio space:
 
 With SOCKS5 proxy:
 ```bash
-./bin/gr2gw -space https://ghost2513-openai-gpt-oss-120b.hf.space -socks socks5://127.0.0.1:1080
+./bin/gr2gw -space https://lucasmarchettidelima-digital-twin.hf.space -socks socks5://127.0.0.1:1080
 ```
 
 ### CLI flags
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `-space`, `-url` | `https://ghost2513-openai-gpt-oss-120b.hf.space` | Target Gradio space URL |
+| `-space`, `-url` | `https://lucasmarchettidelima-digital-twin.hf.space` | Target Gradio space URL |
 | `-port` | `8080` | Port to listen on |
 | `-host` | `0.0.0.0` | Host interface to bind to |
 | `-socks`, `-proxy`, `-socks5` | `""` | SOCKS5 proxy URL (`socks5://user:pass@host:port`) |
@@ -104,13 +105,7 @@ Response:
   "object": "list",
   "data": [
     {
-      "id": "openai/gpt-oss-120b",
-      "object": "model",
-      "created": 1788756307,
-      "owned_by": "gradio"
-    },
-    {
-      "id": "gpt-oss-120b",
+      "id": "digital-twin",
       "object": "model",
       "created": 1788756307,
       "owned_by": "gradio"
@@ -125,7 +120,7 @@ Response:
 curl http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "openai/gpt-oss-120b",
+    "model": "digital-twin",
     "messages": [
       {"role": "user", "content": "What is the capital of France?"}
     ]
@@ -138,7 +133,7 @@ Response:
   "id": "chatcmpl-16425f9d-c350-47a1-9a6d-e9ce10871545",
   "object": "chat.completion",
   "created": 1788756310,
-  "model": "openai/gpt-oss-120b",
+  "model": "digital-twin",
   "choices": [
     {
       "index": 0,
@@ -163,7 +158,7 @@ Response:
 curl -N http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "openai/gpt-oss-120b",
+    "model": "digital-twin",
     "messages": [
       {"role": "user", "content": "Count from 1 to 5."}
     ],
@@ -177,7 +172,7 @@ curl -N http://localhost:8080/v1/chat/completions \
 curl http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "openai/gpt-oss-120b",
+    "model": "digital-twin",
     "messages": [
       {"role": "user", "content": "What is the weather in Tokyo?"}
     ],
@@ -204,7 +199,7 @@ Response:
   "id": "chatcmpl-32727c62-ef2a-4866-855b-f1c7ec2b8023",
   "object": "chat.completion",
   "created": 1788756322,
-  "model": "openai/gpt-oss-120b",
+  "model": "digital-twin",
   "choices": [
     {
       "index": 0,
@@ -239,7 +234,7 @@ Response:
 curl http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "openai/gpt-oss-120b",
+    "model": "digital-twin",
     "messages": [
       {"role": "user", "content": "What is the weather in Tokyo?"},
       {
@@ -284,7 +279,7 @@ Response:
   "id": "chatcmpl-4903ba12-f12b-4cd3-a801-7290bc91a421",
   "object": "chat.completion",
   "created": 1788756335,
-  "model": "openai/gpt-oss-120b",
+  "model": "digital-twin",
   "choices": [
     {
       "index": 0,