Fix critical crash bug + audit fixes

1. CRASH FIX: grader_hard.py line 213 — critical_caught was
undefined (NameError). Now computed from _bugs_caught() before use.
This would crash if any LLM approved a critical-severity PR.

2. README: Fixed stale references:
- Language enum: 4 → 7 (rust, typescript, ruby added)
- Test count: 19 → 21
- HF URL: openenv → ragavrida
- Validation count: 15 → 17

3. inference.py: Added 3-attempt retry with exponential backoff
for LLM API calls to handle transient failures.

4. env/models.py: Updated language comment to match validator.

All verified: 21/21 tests, 17/17 validation, baseline runs.

README.md

@@ -136,7 +136,7 @@ Each file in `files` contains:
 | Field | Type | Description |
 |-------|------|-------------|
 | `filename` | `str` | File path (e.g. `UserService.java`) |
-| `language` | `str ∈ {python, javascript, java, go}` | Programming language |
+| `language` | `str ∈ {python, javascript, java, go, rust, typescript, ruby}` | Programming language |
 | `diff` | `str` | Unified diff of changes |
 | `lines_changed` | `int` | Number of modified lines |
 | `has_tests` | `bool` | Whether the PR includes test coverage |
@@ -463,13 +463,13 @@ The inference script emits structured stdout logs in the **mandatory** `[START]`
 
 | Check | Command / Verification | Status |
 |-------|----------------------|--------|
-| HF Space deploys | `curl https://openenv-code-review-env.hf.space/health` returns 200 | ✅ |
-| OpenEnv spec compliance | `python validate.py` — all 15 checks pass | ✅ |
+| HF Space deploys | `curl https://ragavrida-code-review-env.hf.space/health` returns 200 | ✅ |
+| OpenEnv spec compliance | `python validate.py` — all 17 checks pass | ✅ |
 | Dockerfile builds | `docker build -t code-review-env .` | ✅ |
 | Baseline reproduces | `python baseline.py` completes end-to-end without errors | ✅ |
 | LLM inference | `python inference.py` completes with API key, saves `baseline/results.json` | ✅ |
 | 3+ tasks with graders | `easy`, `medium`, `hard` — all graders produce scores in `[0.0, 1.0]` | ✅ |
-| Tests pass | `pytest tests/ -v` — 19 tests across 5 categories | ✅ |
+| Tests pass | `pytest tests/ -v` — 21 tests across 6 categories | ✅ |
 | `API_BASE_URL` defined | Used by `inference.py` | ✅ |
 | `MODEL_NAME` defined | Used by `inference.py` | ✅ |
 | `HF_TOKEN` defined | Used by `inference.py` | ✅ |

env/models.py

@@ -18,7 +18,7 @@ from typing import List, Optional, Dict, Any
 class PRFile(BaseModel):
     """A single file within a pull request diff."""
     filename: str
-    language: str  # python | javascript | java | go
+    language: str  # python | javascript | java | go | rust | typescript | ruby
     diff: str
     lines_changed: int
     has_tests: bool

graders/grader_hard.py

@@ -210,6 +210,8 @@ class HardGrader:
 
         # ── Exploit: approve with unaddressed critical bug ───────────
         breakdown["critical_approve_penalty"] = 0.0
+        bugs = self._bugs_caught(comments, gt)
+        critical_caught = bugs.get("critical", 0)
         if decision == "approve" and true_severity == "critical" and critical_caught == 0:
             breakdown["critical_approve_penalty"] = -0.5
             self.episode_penalties += -0.5

inference.py

@@ -86,23 +86,27 @@ def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> No
 
 # ─── LLM Interface ──────────────────────────────────────────────────────────
 
-def call_llm(client: OpenAI, system_prompt: str, user_prompt: str) -> str:
-    """Call the LLM using OpenAI Client. Returns response text."""
-    try:
-        completion = client.chat.completions.create(
-            model=MODEL_NAME,
-            messages=[
-                {"role": "system", "content": system_prompt},
-                {"role": "user", "content": user_prompt},
-            ],
-            temperature=TEMPERATURE,
-            max_tokens=MAX_TOKENS,
-            stream=False,
-        )
-        return (completion.choices[0].message.content or "").strip()
-    except Exception as exc:
-        print(f"[DEBUG] Model request failed: {exc}", file=sys.stderr, flush=True)
-        return ""
+def call_llm(client: OpenAI, system_prompt: str, user_prompt: str, max_retries: int = 3) -> str:
+    """Call the LLM using OpenAI Client with retry. Returns response text."""
+    for attempt in range(max_retries):
+        try:
+            completion = client.chat.completions.create(
+                model=MODEL_NAME,
+                messages=[
+                    {"role": "system", "content": system_prompt},
+                    {"role": "user", "content": user_prompt},
+                ],
+                temperature=TEMPERATURE,
+                max_tokens=MAX_TOKENS,
+                stream=False,
+            )
+            return (completion.choices[0].message.content or "").strip()
+        except Exception as exc:
+            print(f"[DEBUG] Attempt {attempt+1}/{max_retries} failed: {exc}", file=sys.stderr, flush=True)
+            if attempt < max_retries - 1:
+                import time
+                time.sleep(2 ** attempt)
+    return ""
 
 
 def parse_json_response(response: str) -> Optional[Dict]: