qwen_test_runner/vision/__init__.py

"""
qwen_test_runner.vision — image→JSON benchmark harness.

Extends the text testbed to vision: a per-category task registry (mirroring the
caption SLOT_REGISTRY), coordinate normalization, ground-truth metrics that
replace substring grounding, a multi-model VLM runner over the Qwen3.5 / Qwen3-VL
ladder, and an orchestrator that ranks models for the no-finetune labeler verdict.

The data-driven modules (coords, model_registry, tasks_vision, metrics) are
torch-free and import eagerly. The VLM runner and orchestrator are imported lazily
so `import qwen_test_runner.vision` stays cheap on a CPU box.
"""

from __future__ import annotations

from .coords import BBox, CoordSpace, to_canonical, from_canonical, detect_space, prompt_hint_for
from .model_registry import (
    MODEL_REGISTRY, ModelSpec, get_model, model_keys, models_that_fit,
    reasoning_variants, get_runner,
)
from .tasks_vision import (
    VISION_TASK_REGISTRY, VisionTaskSpec, get_task, category_names, pilot_categories,
    model_for, json_schema_for, gbnf_for, tool_schema_for, resolved_system_prompt,
)
from .metrics import (
    MetricResult, VisionRunMetrics, labeler_score,
    score_vision_sample, score_vision_run,
)


def __getattr__(name: str):
    # StubVLMRunner + VLMResult are torch-free; VLMRunner pulls torch.
    if name in ("StubVLMRunner",):
        from .stub_runner import StubVLMRunner
        return StubVLMRunner
    if name == "VLMResult":
        from .runner_types import VLMResult
        return VLMResult
    if name == "VLMRunner":
        from .runners import VLMRunner
        return VLMRunner
    if name == "run_bench":
        from .bench import run_bench
        return run_bench
    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")


__all__ = [
    # coords
    "BBox", "CoordSpace", "to_canonical", "from_canonical", "detect_space", "prompt_hint_for",
    # model registry
    "MODEL_REGISTRY", "ModelSpec", "get_model", "model_keys", "models_that_fit",
    "reasoning_variants", "get_runner",
    # tasks
    "VISION_TASK_REGISTRY", "VisionTaskSpec", "get_task", "category_names", "pilot_categories",
    "model_for", "json_schema_for", "gbnf_for", "tool_schema_for", "resolved_system_prompt",
    # metrics
    "MetricResult", "VisionRunMetrics", "labeler_score",
    "score_vision_sample", "score_vision_run",
    # lazy
    "VLMRunner", "StubVLMRunner", "run_bench",
]