import asyncio
from maslul import Router, Request, Message

router = Router.from_toml("maslul.toml")           # tiers + classifier + providers, from config

async def main() -> None:
    resp = await router.complete(Request(messages=[Message(role="user", content="Hello!")]))
    print(resp.text, "·", resp.level_used, "·", resp.usage.output_tokens, "tokens")

asyncio.run(main())

pip install "maslul[anthropic,gemini,grok]"     # or just the providers you use

from maslul import Level

await router.complete(req, model="anthropic:claude-opus-4-8")  # 0. pin an exact model
await router.complete(req, level=Level.HARD)                   # 1. pin a difficulty tier
await router.complete(req)                                     # 2-4. let the router decide

def my_classifier(req):      # your own difficulty call (sync or async); None defers to the strategy
    return Level.SIMPLE if is_trivial(req) else None

def my_verifier(req, resp):  # VERIFY_CASCADE: True keeps the cheap answer, False escalates
    return "I don't know" not in resp.text

router = Router.from_toml("maslul.toml", classifier=my_classifier, verifier=my_verifier)

from maslul import Request, Message, ToolDef, ToolCall, MediaPart

# Tools — the router runs a provider-agnostic tool-use loop
async def get_weather(call: ToolCall) -> str:
    return f"18°C in {call.input['city']}"

req = Request(
    messages=[Message(role="user", content="Weather in Paris?")],
    tools=[ToolDef(name="get_weather", description="Current weather for a city.",
                   input_schema={"type": "object", "properties": {"city": {"type": "string"}},
                                 "required": ["city"]})],
    tool_executor=get_weather,
)

# Structured output — response_format → resp.structured (parsed)
req = Request(messages=[Message(role="user", content="Extract name + age")],
              response_format={"type": "object", "properties": {"name": {"type": "string"},
                                                                "age": {"type": "integer"}}})

# Vision — images / PDFs
req = Request(messages=[Message(role="user", content="What's in this image?")],
              media=[MediaPart(mime_type="image/png", data=png_bytes)])

# Web search — one flag, grounded on ANY provider (Anthropic web_search / Gemini Google Search /
# Grok Agent Tools); citations land in resp.sources regardless of which model answers.
req = Request(messages=[Message(role="user", content="Latest news on X?")], web_search=True)

def on_usage(resp):                         # per-model token breakdown for monitoring
    for rec in resp.usage_records:
        metrics.incr(f"{rec.provider}:{rec.model}", rec.usage.output_tokens)

router = Router.from_toml("maslul.toml", on_complete=on_usage)

[maslul.cache]
mode = "semantic"          # off | exact | semantic
max_entries = 1000
ttl_seconds = 86400
similarity_threshold = 0.95

router = Router.from_toml("maslul.toml", embed=my_async_embed)   # embed only needed for semantic

[maslul]
strategy = "route_default"        # route_default | classify | classify_and_answer | verify_cascade
default_level = "hard"            # default-to-capable for the ambiguous middle
min_tokens_to_classify = 40       # CLASSIFY budget guard
request_timeout = 60              # per-call seconds (optional)
max_retries = 2
fallback = true                   # escalate to a higher tier on persistent failure

[maslul.tiers.simple]
provider = "gemini"
model = "gemini-2.5-flash-lite"
[maslul.tiers.medium]
model = "anthropic:claude-haiku-4-5"   # or the provider:model shorthand
[maslul.tiers.hard]
model = "anthropic:claude-sonnet-4-6"

[maslul.classifier]               # required for the classify strategies
model = "anthropic:claude-haiku-4-5"

[maslul.providers.anthropic]
api_key_env = "ANTHROPIC_API_KEY"      # secrets by env-var name, never inlined
[maslul.providers.gemini]
vertex_project = "my-gcp-project"      # Vertex AI + Application Default Credentials (no key)
vertex_location = "global"
[maslul.providers.grok]
api_key_env = "XAI_API_KEY"