"""evalharness.model -- calling and deploying models.

Two plugin families, deliberately separate lifecycles:
  ModelAdapter  HOW to call (protocol): openai_compatible, mock, ...
  Deployer      HOW to run  (environment): vllm, sglang, external (docker-pinned)

Model spec grammar (strings everywhere, no config ceremony):
  mock / mock:boxed / mock:tool          offline
  openai/http://host:8000/v1?model_id    any OpenAI-protocol endpoint (vllm, sglang, cloud)
  deploy:vllm/qwen3-8b                   Deployer resolves endpoint (models.yaml pins env)

All adapters are async and return structured ModelOutput(text, tool_calls,
usage) -- the hinge the future agent loops hang on.
"""

from .adapter import (
    ADAPTER_REGISTRY,
    ModelAdapter,
    OpenAICompatible,
    MockAdapter,
    register_adapter,
    resolve_adapter,
    parse_model_spec,
)
from .deployer import (
    DEPLOYER_REGISTRY,
    Deployer,
    VLLMDeployer,
    SGLangDeployer,
    External,
    deploy,
    load_model_config,
    register_deployer,
    stop_all,
)
from .output import ModelOutput, ToolCall, Usage
from .runner import generate_predictions, run_eval

__all__ = [
    'ModelAdapter', 'OpenAICompatible', 'MockAdapter', 'register_adapter',
    'resolve_adapter', 'parse_model_spec', 'ADAPTER_REGISTRY',
    'Deployer', 'VLLMDeployer', 'SGLangDeployer', 'External',
    'register_deployer', 'deploy', 'stop_all', 'load_model_config', 'DEPLOYER_REGISTRY',
    'ModelOutput', 'ToolCall', 'Usage', 'generate_predictions', 'run_eval',
]