"""Describe recorded provenance without turning a source into a verified assertion."""

import hashlib
from uuid import UUID
import json


SOURCE_KINDS = {"android", "computer", "terminal", "api", "file", "other"}


def _step_reference(step: dict) -> dict:
    value = step.get("step_id")
    return {
        "step_id": str(value) if isinstance(value, (str, UUID)) else None,
        "step_number": step.get("step_number"),
    }


def recorded_sources(steps: list[dict], *, limit: int = 100) -> dict:
    sources = {}
    unattributed = []
    for step in steps:
        result = step.get("last_execution_result")
        execution = result.get("execution") if isinstance(result, dict) else None
        records = execution if isinstance(execution, list) else step.get("action_taken")
        records = records if isinstance(records, list) else [records]
        found = False
        missing = False
        for record in records:
            if not isinstance(record, dict) or not isinstance(record.get("source"), dict):
                missing = True
                continue
            source = record["source"]
            raw_kind = source.get("kind")
            kind = raw_kind if isinstance(raw_kind, str) and raw_kind in SOURCE_KINDS else "other"
            target = source.get("target_id")
            if not isinstance(target, str) or not target:
                missing = True
                continue
            found = True
            plugin = str(record.get("plugin_id") or "")[:100]
            key = (plugin, kind, target[:256])
            if key not in sources:
                sources[key] = {
                    "id": hashlib.sha256(json.dumps(key).encode()).hexdigest()[:20],
                    "kind": kind,
                    "plugin_id": plugin,
                    "target_id": target[:256],
                    "label": str(source.get("label") or "")[:500],
                    "category": "interface" if kind in {"android", "computer"} else "auxiliary",
                    "references": [],
                    "reference_count": 0,
                }
            reference = _step_reference(step)
            for field in ("call_id", "source_id"):
                if isinstance(record.get(field), str) and record[field]:
                    reference[field] = record[field][:256]
            if isinstance(record.get("read_only"), bool):
                reference["read_only"] = record["read_only"]
            entry = sources[key]
            entry["reference_count"] += 1
            if len(entry["references"]) < 8:
                entry["references"].append(reference)
        if not found or missing:
            # A screenshot or a model-authored URL does not supply missing provenance.
            unattributed.append(_step_reference(step))
    values = list(sources.values())
    return {
        "schema_version": 1,
        "sources": values[:limit],
        "total_sources": len(values),
        "sources_omitted": max(0, len(values) - limit),
        "unattributed_step_count": len(unattributed),
        "unattributed_references": unattributed[:8],
        "note": "来源清单仅来自执行记录，不代表断言已验证。界面证据与接口、终端、文件来源分开；界面结果不能单独证明后端持久状态。逐项结论及未验证边界以正式验收依据为准。缺失来源不按网址或业务名称推断执行平台。",
    }