Merge pull request #1 from lishhh06/test

.env.example

@@ -1,7 +1,16 @@
+# Default profile: Hugging Face Router (OpenAI-compatible API)
 API_BASE_URL=https://router.huggingface.co/v1
 MODEL_NAME=Qwen/Qwen2.5-72B-Instruct
-OPENAI_API_KEY=<your_openai_compatible_api_key>
-HF_TOKEN=<optional_fallback_token>
+HF_TOKEN=<your_openai_or_router_api_key>
+
+# Optional alias. If both are set, OPENAI_API_KEY is used first by inference.py.
+OPENAI_API_KEY=
+
+# OpenAI direct profile (uncomment for OpenAI access token usage):
+# API_BASE_URL=https://api.openai.com/v1
+# MODEL_NAME=gpt-4o-mini
+# HF_TOKEN=<your_openai_access_token>
+# OPENAI_API_KEY=<optional_same_token_as_hf_token>
 
 # Optional runtime knobs
 LOCAL_IMAGE_NAME=

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -10,4 +10,4 @@ COPY . .
 ENV PORT=7860
 EXPOSE 7860
 
-CMD ["python", "-m", "uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["python", "-m", "server.app"]

README.md

@@ -213,13 +213,23 @@ Environment variables:
 ```bash
 export API_BASE_URL="https://router.huggingface.co/v1"
 export MODEL_NAME="Qwen/Qwen2.5-72B-Instruct"
-export OPENAI_API_KEY="<your_openai_compatible_api_key>"
-# Optional backward-compatible fallback variable used if OPENAI_API_KEY is not set:
-export HF_TOKEN="<your_token>"
+export HF_TOKEN="<your_openai_compatible_api_key>"
+# Optional alias; if set, this takes precedence over HF_TOKEN in inference.py
+export OPENAI_API_KEY="<same_token_optional>"
 # Optional, only if your inference spins environments from local images.
 export LOCAL_IMAGE_NAME="<local_env_image_name>"
 ```
 
+If you want to use an OpenAI access token directly:
+
+```bash
+export API_BASE_URL="https://api.openai.com/v1"
+export MODEL_NAME="gpt-4o-mini"
+export HF_TOKEN="<your_openai_access_token>"
+# Optional alias:
+export OPENAI_API_KEY="<same_token_optional>"
+```
+
 ## 8. Run Inference
 
 Offline/local mode:
@@ -330,6 +340,43 @@ Server endpoints used by validators:
 - `GET /state`
 - `GET /health`
 
-## 12. One-line Presentation Summary
+## 12. Deploy to Hugging Face Space (OpenAI Token)
+
+This repository is already configured for Docker Spaces (`sdk: docker` in this README front matter).
+
+1. Create a new Hugging Face Space with SDK set to `Docker`.
+2. Push this repository to the Space git remote.
+3. In Space Settings -> Variables and secrets, add these Secrets:
+
+```text
+OPENAI_API_KEY=<your_openai_access_token>
+API_BASE_URL=https://api.openai.com/v1
+MODEL_NAME=gpt-4o-mini
+```
+
+4. Optional Secrets:
+
+```text
+HF_TOKEN=<optional_fallback_token>
+OFFLINE_INFERENCE=0
+MAX_STEPS=8
+TEMPERATURE=0.2
+MAX_TOKENS=120
+```
+
+5. Keep the app port as `7860` (already configured).
+6. Wait for build completion, then verify:
+
+```bash
+curl -sS https://<your-space-name>.hf.space/health
+curl -sS -X POST https://<your-space-name>.hf.space/reset -H 'Content-Type: application/json' -d '{}'
+```
+
+Notes:
+
+- `.env.example` is for local development reference only. Hugging Face Spaces use Secrets/Variables from Space Settings.
+- Runtime code reads `OPENAI_API_KEY` first and falls back to `HF_TOKEN` when `OPENAI_API_KEY` is not provided.
+
+## 13. One-line Presentation Summary
 
 We built an OpenEnv-compliant reinforcement learning environment where AI agents learn to debug real CI/CD pipelines using multi-step reasoning, hybrid grading, anti-hacking safeguards, and robust reward shaping.

inference.py

@@ -16,7 +16,9 @@ from inference.visualize import save_metrics_json, save_reward_curve, save_succe
 
 API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
 MODEL_NAME = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-72B-Instruct")
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") or os.getenv("HF_TOKEN")
+HF_TOKEN = os.getenv("HF_TOKEN")
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+API_KEY = OPENAI_API_KEY or HF_TOKEN
 LOCAL_IMAGE_NAME = os.getenv("LOCAL_IMAGE_NAME")
 DEFAULT_TASK_ID = os.getenv("MY_ENV_V4_TASK", "easy-command-typo")
 DEFAULT_BENCHMARK = os.getenv("MY_ENV_V4_BENCHMARK", "cicd_debugger_env")
@@ -172,11 +174,11 @@ async def run_episode(args: argparse.Namespace) -> int:
 
     env = CICDDebuggerEnvironment(max_steps=max(1, int(args.max_steps)))
 
-    offline_mode = bool(args.offline or not OPENAI_API_KEY)
+    offline_mode = bool(args.offline or not API_KEY)
     client: OpenAI | None = None
     if not offline_mode:
         try:
-            client = OpenAI(base_url=API_BASE_URL, api_key=OPENAI_API_KEY)
+            client = OpenAI(base_url=API_BASE_URL, api_key=API_KEY)
         except Exception:
             client = None
             offline_mode = True

requirements.txt

@@ -1,5 +1,9 @@
 pyyaml
 fastapi
-uvicorn
+uvicorn[standard]
 openenv-core
 openai
+pydantic>=2.0.0
+transformers>=4.30.0
+torch>=2.0.0
+pytest>=7.0.0

server/app.py

@@ -100,6 +100,14 @@ def _build_step_response(session: RuntimeSession) -> StepResponse:
     )
 
 
+@app.get("/")
+def root() -> dict[str, Any]:
+    return {
+        "message": "CI/CD Debugger Environment is running 🚀",
+        "endpoints": ["/health", "/reset", "/step", "/state"],
+    }
+
+
 @app.get("/health")
 def health() -> dict[str, str]:
     return {"status": "ok"}