update

Dockerfile

@@ -1,40 +1,40 @@
-# Simple Dockerfile for HF Spaces deployment
-# Uses standard Python base instead of openenv-base to avoid startup hangs
-
-FROM python:3.11-slim
-
-WORKDIR /app
-
-# Install system dependencies
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends curl git && \
-    rm -rf /var/lib/apt/lists/*
-
-# Install uv for fast dependency management
-RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
-    mv /root/.local/bin/uv /usr/local/bin/uv && \
-    mv /root/.local/bin/uvx /usr/local/bin/uvx
-
-# Copy environment code
-COPY . /app/env
-
-WORKDIR /app/env
-
-# Install dependencies
-RUN uv sync --no-editable
-
-# Set PATH to use the virtual environment
-ENV PATH="/app/env/.venv/bin:$PATH"
-
-# Set PYTHONPATH so imports work correctly
-ENV PYTHONPATH="/app/env:$PYTHONPATH"
-
-# Expose port
-EXPOSE 8000
-
-# Health check
-HEALTHCHECK --interval=30s --timeout=3s --start-period=10s --retries=3 \
-    CMD curl -f http://localhost:8000/health || exit 1
-
-# Run the FastAPI server directly (no web interface to avoid Gradio issues)
-CMD ["sh", "-c", "cd /app/env && uvicorn server.app:app --host 0.0.0.0 --port 8000"]
+# Simple Dockerfile for HF Spaces deployment
+# Uses standard Python base instead of openenv-base to avoid startup hangs
+
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends curl git && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install uv for fast dependency management
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
+    mv /root/.local/bin/uv /usr/local/bin/uv && \
+    mv /root/.local/bin/uvx /usr/local/bin/uvx
+
+# Copy environment code
+COPY . /app/env
+
+WORKDIR /app/env
+
+# Install dependencies
+RUN uv sync --no-editable
+
+# Set PATH to use the virtual environment
+ENV PATH="/app/env/.venv/bin:$PATH"
+
+# Set PYTHONPATH so imports work correctly
+ENV PYTHONPATH="/app/env:$PYTHONPATH"
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=3s --start-period=10s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Run the FastAPI server directly (no web interface to avoid Gradio issues)
+CMD ["sh", "-c", "cd /app/env && uvicorn server.app:app --host 0.0.0.0 --port 8000"]

README.md

@@ -158,6 +158,7 @@ python scripts/baseline_inference.py --mode llm
 
 ```
 api_debug_env/
+├── inference.py        # ★ MANDATORY hackathon inference script
 ├── models.py           # Pydantic Action & Observation models
 ├── scenarios.py        # 3 task scenarios with issues, logs, configs
 ├── client.py           # WebSocket client for the environment
@@ -168,9 +169,9 @@ api_debug_env/
 │   ├── api_debug_env_environment.py  # Core environment logic
 │   └── Dockerfile                    # Container build
 └── scripts/
-    └── baseline_inference.py         # Baseline agent script
+    └── baseline_inference.py         # Original baseline agent script
 ```
 
 ## License
 
-BSD-style license. See LICENSE file.
+BSD-style license. See LICENSE file

inference.py

@@ -91,7 +91,7 @@ def log_step(step: int, action: str, reward: float, done: bool, error: Optional[
 def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> None:
     rewards_str = ",".join(f"{r:.2f}" for r in rewards)
     print(
-        f"[END] success={str(success).lower()} steps={steps} score={score:.2f} rewards={rewards_str}",
+        f"[END] success={str(success).lower()} steps={steps} score={score:.3f} rewards={rewards_str}",
         flush=True,
     )
 
@@ -176,7 +176,7 @@ async def run_task(task_id: str, client: OpenAI) -> tuple:
 
     rewards: List[float] = []
     steps_taken = 0
-    score = 0.0
+    score = 0.001
     success = False
 
     log_start(task=task_id, env=BENCHMARK, model=MODEL_NAME)
@@ -208,8 +208,8 @@ async def run_task(task_id: str, client: OpenAI) -> tuple:
             if done:
                 break
 
-        score = env.grade()
-        score = min(max(score, 0.0), 1.0)
+        score = env.grade()  # already clamped to (0.001, 0.999)
+        score = max(0.001, min(0.999, score))
         success = score >= SUCCESS_SCORE_THRESHOLD
 
     except Exception as e:

server/Dockerfile

@@ -0,0 +1,40 @@
+# Simple Dockerfile for HF Spaces deployment
+# Uses standard Python base instead of openenv-base to avoid startup hangs
+
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends curl git && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install uv for fast dependency management
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
+    mv /root/.local/bin/uv /usr/local/bin/uv && \
+    mv /root/.local/bin/uvx /usr/local/bin/uvx
+
+# Copy environment code
+COPY . /app/env
+
+WORKDIR /app/env
+
+# Install dependencies
+RUN uv sync --no-editable
+
+# Set PATH to use the virtual environment
+ENV PATH="/app/env/.venv/bin:$PATH"
+
+# Set PYTHONPATH so imports work correctly
+ENV PYTHONPATH="/app/env:$PYTHONPATH"
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=3s --start-period=10s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Run the FastAPI server directly (no web interface to avoid Gradio issues)
+CMD ["sh", "-c", "cd /app/env && uvicorn server.app:app --host 0.0.0.0 --port 8000"]

server/api_debug_env_environment.py

@@ -417,7 +417,7 @@ class ApiDebugEnvironment(Environment):
 
         score = fix_ratio * efficiency_bonus + exploration_bonus
 
-        # Clamp strictly to (0.001, 0.999) — never exactly 0 or 1
+        # Clamp strictly to (0.001, 0.999) — NEVER exactly 0.0 or 1.0
         return max(0.001, min(0.999, round(score, 4)))
 
     def get_task_info(self) -> Dict[str, Any]:

server/app.py

@@ -133,7 +133,7 @@ async def run_grader(request: GraderRequest):
 
     return {
         "task_id": task_id,
-        "score": 0.0,
+        "score": 0.001,
         "message": "No completed episode found. Run the environment first.",
     }