Judge Worker

class ContentJudge:
    def __init__(self, api_key: str, model: str = "google/gemini-2.0-flash-001"):
        self.api_key = api_key
        self.model = model

OPENROUTER_API_KEY=sk-or-v1-...
OPENROUTER_MODEL=google/gemini-2.0-flash-001  # Optional

async def screen(self, query: str) -> str:
    prompt = JUDGE_PROMPT.format(query=query)
    
    async with httpx.AsyncClient() as client:
        resp = await client.post(
            OPENROUTER_URL,
            headers={
                "Authorization": f"Bearer {self.api_key}",
                "Content-Type": "application/json",
            },
            json={
                "model": self.model,
                "messages": [{"role": "user", "content": prompt}],
            },
            timeout=60.0,
        )
        resp.raise_for_status()
        data = resp.json()
    
    text = data["choices"][0]["message"]["content"].strip()
    # Parse JSON...
    result = json.loads(text)
    verdict = result.get("verdict", "reject")
    
    if verdict in ("approve", "sensitive"):
        return verdict
    return "reject"

JUDGE_PROMPT = """You are a content moderation system for a historical education platform.

Evaluate this query for a historical scene generation:
"{query}"

Classify as ONE of:
- "approve" — innocuous historical topic, safe to generate
- "sensitive" — involves violence, controversy, or mature themes but is historically significant and educational; approve with a disclaimer
- "reject" — harmful, hateful, exploitative, or not a genuine historical query

Return ONLY a JSON object: {{"verdict": "approve"|"sensitive"|"reject", "reason": "brief explanation"}}"""

judge = ContentJudge(api_key="...")

verdict = await judge.screen("Moon landing 1969")
# Returns: "approve"
# Reason: "Innocuous historical event"

verdict = await judge.screen("Battle of Stalingrad 1942")
# Returns: "sensitive"
# Reason: "Significant WWII battle but involves graphic violence"

verdict = await judge.screen("Make a video game level")
# Returns: "reject"
# Reason: "Not a historical query"

judge = ContentJudge(settings.OPENROUTER_API_KEY)

# Before generating a scene
verdict = await judge.screen(user_query)

if verdict == "reject":
    raise ValueError("Query rejected by content moderation")
elif verdict == "sensitive":
    # Add disclaimer to response
    disclaimer = "This historical event involves mature themes."
# Proceed with generation...

text = data["choices"][0]["message"]["content"].strip()
if text.startswith("```"):
    text = text.split("\n", 1)[1] if "\n" in text else text[3:]
    if text.endswith("```"):
        text = text[:-3]
    text = text.strip()

result = json.loads(text)
verdict = result.get("verdict", "reject")

logger = logging.getLogger("clockchain.judge")
logger.info(
    "Judge verdict for %r: %s (%s)", 
    query, 
    verdict, 
    result.get("reason", "")
)

2026-03-06 10:45:12 INFO clockchain.judge Judge verdict for 'D-Day invasion 1944': sensitive (Involves wartime violence but historically significant)

try:
    verdict = await judge.screen(query)
except httpx.HTTPStatusError as e:
    if e.response.status_code == 429:
        # Rate limited - queue for retry
        verdict = "reject"
    else:
        # Other API error - fail safe
        verdict = "reject"
except json.JSONDecodeError:
    # LLM returned invalid JSON
    logger.error("Failed to parse judge response")
    verdict = "reject"
except httpx.TimeoutException:
    # 60-second timeout exceeded
    verdict = "reject"

judge = ContentJudge(
    api_key="sk-or-v1-...",
    model="anthropic/claude-3-haiku"  # Alternative model
)