AirPlan-V2/lib/air_runtime/review.py

"""
并行审查模块 — V2 从 V1 迁移。
分析任务依赖、写集冲突、产出并行组和串行点。
"""

from __future__ import annotations

import re
from dataclasses import dataclass, field
from pathlib import Path
from air_runtime.todo_parser import parse_tasks


@dataclass
class ParallelGroup:
    name: str
    task_ids: list[str]
    reason: str = ""

    def to_dict(self) -> dict:
        return {"name": self.name, "task_ids": self.task_ids, "reason": self.reason}


@dataclass
class Conflict:
    task_a: str
    task_b: str
    reason: str = ""

    def to_dict(self) -> dict:
        return {"task_a": self.task_a, "task_b": self.task_b, "reason": self.reason}


@dataclass
class ReviewResult:
    parallel_groups: list[ParallelGroup] = field(default_factory=list)
    conflicts: list[Conflict] = field(default_factory=list)
    serialization_points: list[dict] = field(default_factory=list)
    edges: list[dict] = field(default_factory=list)

    def to_dict(self) -> dict:
        return {
            "parallelGroups": [{"name": g.name, "task_ids": g.task_ids, "reason": g.reason} for g in self.parallel_groups],
            "conflicts": [{"task_a": c.task_a, "task_b": c.task_b, "reason": c.reason} for c in self.conflicts],
            "serializationPoints": self.serialization_points,
            "edges": self.edges,
        }

    @classmethod
    def from_dict(cls, data: dict) -> ReviewResult:
        return cls(
            parallel_groups=[ParallelGroup(**g) for g in data.get("parallelGroups", [])],
            conflicts=[Conflict(**c) for c in data.get("conflicts", [])],
            serialization_points=data.get("serializationPoints", []),
            edges=data.get("edges", []),
        )


def build_parallel_review(todo_path: Path) -> ReviewResult:
    """分析 todo.md，产出并行组和冲突。"""
    tasks = parse_tasks(todo_path)
    result = ReviewResult()

    # 解析依赖：task 文本中的 "依赖 T-xxx" 或 Done When 中的引用
    edges = []
    for t in tasks:
        deps = re.findall(r"T-\d+[a-z]*", t.done_when)
        deps.extend(re.findall(r"依赖\s+(T-\d+[a-z]*)", t.task))
        for dep in deps:
            if dep != t.task_id:
                edges.append({"source": dep, "target": t.task_id, "kind": "dependency"})
                result.edges.append({"source": dep, "target": t.task_id, "kind": "dependency"})

    # 写集冲突检测
    file_map: dict[str, list[str]] = {}
    for t in tasks:
        if t.files_dirs:
            files = [f.strip() for f in t.files_dirs.split(",")]
            for f in files:
                file_map.setdefault(f, []).append(t.task_id)

    conflicts = []
    for fpath, tid_list in file_map.items():
        for i, tid_a in enumerate(tid_list):
            for tid_b in tid_list[i + 1:]:
                conflicts.append(Conflict(tid_a, tid_b, f"shared file: {fpath}"))
    result.conflicts = conflicts

    # 串行点：同文件不同任务的依赖链
    for fpath, tid_list in file_map.items():
        if len(tid_list) > 1:
            for tid in tid_list[1:]:
                result.serialization_points.append({
                    "taskId": tid,
                    "reasons": [f"serialized with {tid_list[0]} due to shared file: {fpath}"],
                })

    # 并行组：入度为 0 的任务
    target_count = {e["target"] for e in edges}
    ready = [t.task_id for t in tasks if t.task_id not in target_count and t.status == "TODO"]
    if ready:
        result.parallel_groups.append(ParallelGroup(
            name="wave-1", task_ids=ready,
            reason="no dependencies on other TODO tasks",
        ))

    return result


def render_review_markdown(review: ReviewResult) -> str:
    lines = ["# AirArc Parallel Review", ""]
    lines.append(f"## Summary")
    lines.append(f"- Parallel groups: {len(review.parallel_groups)}")
    lines.append(f"- Conflicts: {len(review.conflicts)}")
    lines.append(f"- Serialization points: {len(review.serialization_points)}")
    lines.append("")
    lines.append("## Parallel Groups")
    for g in review.parallel_groups:
        lines.append(f"### {g.name}")
        lines.append(f"Reason: {g.reason}")
        lines.append(f"Tasks: {', '.join(g.task_ids)}")
        lines.append("")
    lines.append("## Conflicts")
    for c in review.conflicts:
        lines.append(f"- {c.task_a} <-> {c.task_b}: {c.reason}")
    return "\n".join(lines)