multiplex-ai/muggle-ai-teams/cost-aware-llm-pipeline

MODEL_SONNET = "claude-sonnet-4-6"
MODEL_HAIKU = "claude-haiku-4-5-20251001"
_SONNET_TEXT_THRESHOLD = 10_000  # chars
_SONNET_ITEM_THRESHOLD = 30     # items
def select_model(
    text_length: int,
    item_count: int,
    force_model: str | None = None,
) -> str:
    """Select model based on task complexity."""
    if force_model is not None:
        return force_model
    if text_length >= _SONNET_TEXT_THRESHOLD or item_count >= _SONNET_ITEM_THRESHOLD:
        return MODEL_SONNET  # Complex task
    return MODEL_HAIKU  # Simple task (3-4x cheaper)

from dataclasses import dataclass
@dataclass(frozen=True, slots=True)
class CostRecord:
    model: str
    input_tokens: int
    output_tokens: int
    cost_usd: float
@dataclass(frozen=True, slots=True)
class CostTracker:
    budget_limit: float = 1.00
    records: tuple[CostRecord, ...] = ()
    def add(self, record: CostRecord) -> "CostTracker":
        """Return new tracker with added record (never mutates self)."""
        return CostTracker(
            budget_limit=self.budget_limit,
            records=(*self.records, record),
        )
    @property
    def total_cost(self) -> float:
        return sum(r.cost_usd for r in self.records)
    @property
    def over_budget(self) -> bool:
        return self.total_cost > self.budget_limit

from anthropic import (
    APIConnectionError,
    InternalServerError,
    RateLimitError,
)
_RETRYABLE_ERRORS = (APIConnectionError, RateLimitError, InternalServerError)
_MAX_RETRIES = 3
def call_with_retry(func, *, max_retries: int = _MAX_RETRIES):
    """Retry only on transient errors, fail fast on others."""
    for attempt in range(max_retries):
        try:
            return func()
        except _RETRYABLE_ERRORS:
            if attempt == max_retries - 1:
                raise
            time.sleep(2 ** attempt)  # Exponential backoff
    # AuthenticationError, BadRequestError etc. → raise immediately

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": system_prompt,
                "cache_control": {"type": "ephemeral"},  # Cache this
            },
            {
                "type": "text",
                "text": user_input,  # Variable part
            },
        ],
    }
]

def process(text: str, config: Config, tracker: CostTracker) -> tuple[Result, CostTracker]:
    # 1. Route model
    model = select_model(len(text), estimated_items, config.force_model)
    # 2. Check budget
    if tracker.over_budget:
        raise BudgetExceededError(tracker.total_cost, tracker.budget_limit)
    # 3. Call with retry + caching
    response = call_with_retry(lambda: client.messages.create(
        model=model,
        messages=build_cached_messages(system_prompt, text),
    ))
    # 4. Track cost (immutable)
    record = CostRecord(model=model, input_tokens=..., output_tokens=..., cost_usd=...)
    tracker = tracker.add(record)
    return parse_result(response), tracker