modao-prd-cli 0.1.0__py3-none-any.whl

modao_prd_cli/modao_prd/writers.py

@@ -0,0 +1,468 @@
+"""Render the normalized document to Agent and human-friendly formats."""
+
+from __future__ import annotations
+
+import json
+import re
+from pathlib import Path
+from typing import Any, Iterable
+
+from .evidence import EvidenceBundleWriter
+
+
+FORMATS = {"json", "markdown", "ndjson", "all"}
+
+
+def write_outputs(
+    document: dict[str, Any],
+    output_root: str | Path,
+    output_format: str,
+    force: bool = False,
+    *,
+    evidence_writer: EvidenceBundleWriter | None = None,
+) -> dict[str, Any]:
+    if output_format not in FORMATS:
+        raise ValueError(f"unsupported output format: {output_format}")
+    root = Path(output_root).expanduser().resolve()
+    root.mkdir(parents=True, exist_ok=True)
+    project_id = document.get("source", {}).get("project_id") or "unknown"
+    output_dir = root / project_id
+    output_dir.mkdir(parents=True, exist_ok=True)
+    selected = {"json", "markdown", "ndjson"} if output_format == "all" else {output_format}
+    paths = {name: output_dir / f"document.{name if name != 'markdown' else 'md'}" for name in selected}
+    existing = [path for path in paths.values() if path.exists()]
+    if existing and not force and evidence_writer is None:
+        raise FileExistsError(
+            "输出文件已存在；如需覆盖请显式使用 --force：" + ", ".join(str(path) for path in existing)
+        )
+
+    contents: dict[str, str] = {}
+    if "json" in selected:
+        # document.json is the machine/Agent entrypoint. Keep Markdown as the
+        # human-readable projection, while avoiding indentation whitespace in
+        # the JSON payload that Agents generally parse rather than display.
+        contents["json"] = json.dumps(document, ensure_ascii=False, separators=(",", ":"), default=str) + "\n"
+    if "markdown" in selected:
+        contents["markdown"] = render_markdown(document)
+    if "ndjson" in selected:
+        contents["ndjson"] = render_ndjson(document)
+    coverage = document.get("coverage") or {
+        "schema_version": "1.0",
+        "states": document.get("facts", {}).get("states", []),
+        "transitions": document.get("facts", {}).get("observed_interactions", []),
+        "summary": {"quality": document.get("stats", {}).get("quality", "unknown")},
+    }
+    coverage_path = output_dir / "coverage.json"
+    if evidence_writer is not None:
+        for name, content in contents.items():
+            relative = f"document.{name if name != 'markdown' else 'md'}"
+            media_type = "text/markdown" if name == "markdown" else ("application/x-ndjson" if name == "ndjson" else "application/json")
+            evidence_writer.add(relative, content, media_type=media_type, enforce_item_limit=False)
+            paths[name] = output_dir / relative
+        evidence_writer.add("coverage.json", json.dumps(coverage, ensure_ascii=False, indent=2, default=str) + "\n", media_type="application/json", enforce_item_limit=False)
+        if document.get("capture", {}).get("evidence") == "full":
+            network = document.get("network", [])
+            evidence_writer.add(
+                "evidence/network/index.ndjson",
+                "".join(json.dumps(item, ensure_ascii=False, default=str) + "\n" for item in network),
+                media_type="application/x-ndjson",
+                enforce_item_limit=False,
+            )
+        manifest_path = evidence_writer.finalize(
+            extra={
+                "project_id": project_id,
+                "document": "document.json" if "json" in selected else None,
+                "document_schema": document.get("schema_version"),
+                "document_profile": "agent_compact",
+                "coverage": "coverage.json",
+                "format": output_format,
+                "status": document.get("stats", {}).get("quality", "unknown"),
+                "capture": document.get("capture", {}),
+            }
+        )
+    else:
+        for name, content in contents.items():
+            paths[name].write_text(content, encoding="utf-8")
+        manifest_path = None
+    return {
+        "output_dir": str(output_dir),
+        "files": {name: str(path) for name, path in paths.items()},
+        "coverage": str(output_dir / "coverage.json") if evidence_writer is not None else None,
+        "manifest": str(manifest_path) if manifest_path else None,
+        "format": output_format,
+        "overwrote": bool(existing),
+    }
+
+
+def render_markdown(document: dict[str, Any]) -> str:
+    source = document.get("source", {})
+    facts = document.get("facts", {})
+    derived = document.get("derived", {})
+    model = document.get("document", {}) or {
+        "title": source.get("title"),
+        "screens": facts.get("screens", []),
+        "sections": [],
+        "blocks": facts.get("blocks", []),
+    }
+    model["screens"] = model.get("screens") or facts.get("screens", [])
+    model["blocks"] = model.get("blocks") or facts.get("blocks", [])
+    requirements = document.get("requirements") or derived.get("requirements", [])
+    interactions = document.get("interactions") or derived.get("declared_interactions", [])
+    tables = document.get("tables") or facts.get("tables", [])
+    assets = document.get("assets") or facts.get("assets", [])
+    stats = document.get("stats", {})
+    lines = [
+        f"# {source.get('title') or model.get('title') or '墨刀原型'}",
+        "",
+        "## 来源信息",
+        "",
+        f"- URL: {source.get('url', '')}",
+        f"- 访问方式: {source.get('access_mode', 'public_share')}",
+        f"- 抓取时间: {source.get('fetched_at', '')}",
+        f"- Schema: {document.get('schema_version', '')}",
+        "",
+        "## 抓取摘要",
+        "",
+        f"- 页面/画布：{stats.get('screen_count', 0)}",
+        f"- 页面分区：{stats.get('section_count', 0)}",
+        f"- 文本块：{stats.get('text_block_count', 0)}",
+        f"- 表格：{stats.get('table_count', 0)}",
+        f"- 图片：{stats.get('image_count', 0)}",
+        f"- 控件：{stats.get('control_count', 0)}",
+        f"- 业务规则：{stats.get('requirement_count', 0)}",
+        f"- 交互：{stats.get('interaction_count', 0)}",
+        f"- 解析质量：{stats.get('quality', 'unknown')}",
+        f"- 状态：{stats.get('state_count', len(facts.get('states', [])))}",
+        f"- 证据项：{stats.get('evidence_count', len(document.get('evidence', [])))}",
+        "",
+    ]
+    warnings = _unique_strings(document.get("warnings", []))
+    if warnings:
+        lines.extend(["## 待确认项", ""])
+        lines.extend(f"- {warning}" for warning in warnings)
+        lines.append("")
+    lines.extend([
+        "## 页面/画布",
+        "",
+    ])
+    blocks_by_id = {block.get("id"): block for block in model.get("blocks", [])}
+    requirements_by_block: dict[str, list[dict[str, Any]]] = {}
+    for requirement in requirements:
+        for block_id in requirement.get("source_block_ids", []):
+            requirements_by_block.setdefault(block_id, []).append(requirement)
+    interactions_by_block: dict[str, list[dict[str, Any]]] = {}
+    for interaction in interactions:
+        for block_id in interaction.get("source_block_ids", []):
+            interactions_by_block.setdefault(block_id, []).append(interaction)
+    tables_by_block = {
+        table.get("source_block_id"): table
+        for table in tables
+        if table.get("source_block_id")
+    }
+    assets_by_block = {
+        asset.get("block_id"): asset
+        for asset in assets
+        if asset.get("block_id")
+    }
+
+    sections = model.get("sections", []) or [
+        {"title": screen.get("title"), "screen_id": screen.get("id"), "block_ids": []}
+        for screen in model.get("screens", [])
+    ]
+    rendered_rule_keys: set[tuple[str, str]] = set()
+    rendered_interaction_keys: set[tuple[str, str]] = set()
+    rendered_table_ids: set[str] = set()
+    rendered_asset_sources: set[str] = set()
+    rendered_block_ids: set[str] = set()
+
+    for section in sections:
+        section_title = str(section.get("title") or "未命名页面").strip()
+        lines.extend([f"### {section_title}", ""])
+        section_blocks = [blocks_by_id[block_id] for block_id in section.get("block_ids", []) if block_id in blocks_by_id]
+        section_block_ids = {block.get("id") for block in section_blocks}
+        rendered_block_ids.update(section_block_ids)
+
+        content_lines: list[str] = []
+        seen_content: set[tuple[str, str]] = set()
+        for block in section_blocks:
+            block_id = block.get("id")
+            block_type = block.get("type")
+            text = str(block.get("text") or "").strip()
+            if block_type in {"table", "image"} or not text or _is_noise_text(text):
+                continue
+            if block_type in {"heading", "tab"} and _is_section_heading(text, section_title):
+                continue
+            if block_type in {"text", "label"} and (block_id in requirements_by_block or block_id in interactions_by_block):
+                continue
+            key = (str(block_type), text)
+            if key in seen_content:
+                continue
+            seen_content.add(key)
+            if block_type in {"heading", "tab"}:
+                content_lines.extend([f"#### {text}", ""])
+            elif block_type == "button":
+                content_lines.append(f"- 按钮：{text}")
+            elif block_type == "label":
+                content_lines.extend([f"**{text}**", ""])
+            else:
+                content_lines.extend([text, ""])
+
+        if content_lines:
+            lines.extend(["#### 页面文案", ""])
+            lines.extend(content_lines)
+
+        section_requirements: list[dict[str, Any]] = []
+        section_examples: list[str] = []
+        seen_examples: set[str] = set()
+        for block_id in section_block_ids:
+            for requirement in requirements_by_block.get(block_id, []):
+                statement = str(requirement.get("statement") or "").strip()
+                if not statement:
+                    continue
+                if _is_example_statement(statement):
+                    if statement not in seen_examples:
+                        seen_examples.add(statement)
+                        section_examples.append(statement)
+                    continue
+                if _is_rule_noise(statement):
+                    continue
+                has_interaction = any(interactions_by_block.get(source_id) for source_id in requirement.get("source_block_ids", []))
+                if requirement.get("type") == "interaction" or (_is_interaction_like_rule(statement) and has_interaction):
+                    continue
+                key = (str(requirement.get("type") or "unknown"), statement)
+                if key in rendered_rule_keys or not key[1]:
+                    continue
+                rendered_rule_keys.add(key)
+                section_requirements.append(requirement)
+        if section_examples:
+            lines.extend(["#### 原型示例记录", ""])
+            lines.extend(f"- {statement}" for statement in section_examples)
+            lines.append("")
+        if section_requirements:
+            lines.extend(["#### 业务规则", ""])
+            for requirement in section_requirements:
+                _append_rule(lines, requirement)
+
+        section_interactions: list[dict[str, Any]] = []
+        for block_id in section_block_ids:
+            for interaction in interactions_by_block.get(block_id, []):
+                key = (str(interaction.get("trigger") or "").strip(), str(interaction.get("action") or "").strip())
+                if key in rendered_interaction_keys or not any(key):
+                    continue
+                rendered_interaction_keys.add(key)
+                section_interactions.append(interaction)
+        if section_interactions:
+            lines.extend(["#### 交互说明", ""])
+            for interaction in section_interactions:
+                _append_interaction(lines, interaction)
+
+        section_tables = []
+        for block in section_blocks:
+            table = tables_by_block.get(block.get("id"))
+            if table and table.get("id") not in rendered_table_ids:
+                rendered_table_ids.add(table.get("id"))
+                section_tables.append(table)
+        if section_tables:
+            lines.extend(["#### 表格", ""])
+            for index, table in enumerate(section_tables, start=1):
+                table_title = _contextual_table_title(table, section_title, index)
+                lines.extend(_markdown_table(table, title=table_title))
+
+        section_assets = []
+        for block in section_blocks:
+            asset = assets_by_block.get(block.get("id"))
+            src = str((asset or {}).get("src") or "")
+            if asset and src and src not in rendered_asset_sources:
+                rendered_asset_sources.add(src)
+                section_assets.append(asset)
+        if section_assets:
+            lines.extend(["#### 图片资源", ""])
+            for asset in section_assets:
+                alt = asset.get("alt") or "图片"
+                lines.extend([f"![{alt}]({asset['src']})", ""])
+
+        if not content_lines and not section_requirements and not section_interactions and not section_tables and not section_assets:
+            lines.extend(["暂无可提取内容。", ""])
+
+    unassigned_requirements = [
+        requirement
+        for requirement in requirements
+        if requirement.get("type") != "interaction"
+        and not any(block_id in rendered_block_ids for block_id in requirement.get("source_block_ids", []))
+    ]
+    if unassigned_requirements:
+        lines.extend(["## 页面级规则", ""])
+        for requirement in unassigned_requirements:
+            _append_rule(lines, requirement)
+
+    lines.extend(["## 页面布局与状态", ""])
+    for state in facts.get("states", []):
+        state_id = state.get("id", "unknown")
+        evidence_ids = ", ".join(state.get("evidence_ids", [])) or "无"
+        lines.append(f"- `{state_id}`：深度 {state.get('depth', 0)}，证据 `{evidence_ids}`")
+    if not facts.get("states"):
+        lines.append("- 未记录状态快照。")
+    lines.append("")
+    lines.extend(["## 统计", ""])
+    for key, label in (
+        ("block_count", "内容块"),
+        ("text_block_count", "文本块"),
+        ("table_count", "表格"),
+        ("image_count", "图片"),
+        ("control_count", "控件"),
+        ("requirement_count", "业务规则"),
+        ("interaction_count", "交互"),
+        ("warning_count", "警告"),
+    ):
+        lines.append(f"- {label}：{stats.get(key, 0)}")
+    lines.append("")
+    lines.extend(["## 证据与覆盖范围", ""])
+    lines.append("- 原始事实应以 `document.json` 的 `facts` 和 `evidence` 为准。")
+    lines.append("- 本 Markdown 只提供可读摘要，不替代 HTML、DOM、ARIA、截图和网络证据。")
+    coverage = document.get("coverage") or {}
+    if coverage.get("partial_reason"):
+        lines.append(f"- 未覆盖原因：{coverage['partial_reason']}")
+    for item in coverage.get("skipped_actions", [])[:20]:
+        lines.append(f"- 跳过动作：{item.get('label', '')}（{item.get('reason', '')}）")
+    lines.append("")
+    return "\n".join(lines)
+
+
+def _append_rule(lines: list[str], requirement: dict[str, Any]) -> None:
+    label = {
+        "validation": "校验",
+        "persistence": "状态",
+        "limit": "限制",
+        "timing": "时间",
+        "probability": "概率",
+        "reward": "奖励",
+        "warning": "注意",
+        "interaction": "交互",
+    }.get(str(requirement.get("type")), str(requirement.get("type") or "规则"))
+    statement = str(requirement.get("statement") or "").strip()
+    statement_lines = statement.splitlines() or [""]
+    lines.append(f"- **{label}**：{statement_lines[0]}")
+    lines.extend(f"  {line}" for line in statement_lines[1:])
+    feedback = str(requirement.get("feedback") or "").strip()
+    if feedback and feedback not in statement:
+        lines.append(f"  - 反馈：{feedback}")
+    lines.append("")
+
+
+def _append_interaction(lines: list[str], interaction: dict[str, Any]) -> None:
+    trigger = _clean_trigger(str(interaction.get("trigger") or "用户操作").strip())
+    action = str(interaction.get("action") or "").strip()
+    if action.startswith(trigger):
+        action = action[len(trigger):].lstrip(" ，,：:")
+    if action and action != trigger:
+        lines.append(f"- **{trigger}**：{action}")
+    else:
+        lines.append(f"- **{trigger}**")
+    lines.append("")
+
+
+def _clean_trigger(trigger: str) -> str:
+    trigger = trigger.rstrip("，,：:；;。！？!?）)").strip()
+    trigger = re.sub(r"(?:和|或|的|即)$", "", trigger).strip()
+    if not trigger:
+        return "用户操作"
+    return trigger
+
+
+def _contextual_table_title(table: dict[str, Any], section_title: str, index: int) -> str:
+    title = str(table.get("title") or "").strip()
+    if not title or title in {"未命名表格", "表格"} or title == section_title:
+        return f"{section_title} - 表格 {index}"
+    return title
+
+
+def _is_noise_text(text: str) -> bool:
+    return bool(re.fullmatch(r"(?:x|×)?\d+[+]?", text, flags=re.IGNORECASE))
+
+
+def _is_section_heading(text: str, section_title: str) -> bool:
+    aliases = {
+        section_title,
+        re.sub(r"^TAB\s*\d+\s*[-—:：]\s*", "", section_title, flags=re.IGNORECASE),
+    }
+    return text in aliases
+
+
+def _is_rule_noise(statement: str) -> bool:
+    if len(statement) > 14:
+        return False
+    if re.fullmatch(r"(?:礼物名称|奖励|奖励记录|星海礼物|任务奖励|BUFF礼物|剩余奖励份数)(?:（[^）]*）)?", statement):
+        return True
+    meaningful_cues = (
+        "用户", "活动", "点击", "选择", "切换", "消耗", "购买", "获得", "领取", "展示",
+        "记录", "播报", "抽奖", "配置", "集齐", "抽中", "兑换", "有效期", "上限", "提示",
+    )
+    return not any(cue in statement for cue in meaningful_cues)
+
+
+def _is_interaction_like_rule(statement: str) -> bool:
+    if not re.search(r"点击|选择|切换|弹出|关闭|打开|输入|按键", statement):
+        return False
+    condition_cues = (
+        "若", "如果", "超过", "不足", "上限", "提示", "toast", "不可", "不能", "低于",
+        "达到", "最多", "至少", "概率", "随机",
+    )
+    return not any(cue in statement for cue in condition_cues)
+
+
+def _is_example_statement(statement: str) -> bool:
+    return bool(re.search(r"\b20\d{2}[./-]\d{1,2}[./-]\d{1,2}\b", statement))
+
+
+def _unique_strings(values: list[Any]) -> list[str]:
+    result: list[str] = []
+    seen: set[str] = set()
+    for value in values:
+        text = str(value).strip()
+        if text and text not in seen:
+            seen.add(text)
+            result.append(text)
+    return result
+
+
+def _markdown_table(table: dict[str, Any], *, title: str | None = None) -> list[str]:
+    columns = [str(column) for column in table.get("columns", [])]
+    if not columns:
+        return []
+    lines = [f"##### {title or table.get('title') or '表格'}", "", "| " + " | ".join(_escape_cell(column) for column in columns) + " |", "| " + " | ".join("---" for _ in columns) + " |"]
+    for row in table.get("rows", []):
+        lines.append("| " + " | ".join(_escape_cell(str(row.get(column, ""))) for column in columns) + " |")
+    lines.append("")
+    return lines
+
+
+def render_ndjson(document: dict[str, Any]) -> str:
+    facts = document.get("facts", {})
+    derived = document.get("derived", {})
+    units: list[dict[str, Any]] = [
+        {
+            "type": "metadata",
+            "schema_version": document.get("schema_version"),
+            "title": document.get("source", {}).get("title"),
+            "url": document.get("source", {}).get("url"),
+            "project_id": document.get("source", {}).get("project_id"),
+        }
+    ]
+    units.extend({"type": "screen", **screen} for screen in facts.get("screens", []) or document.get("document", {}).get("screens", []))
+    units.extend({"type": "state", **state} for state in facts.get("states", []))
+    units.extend({"type": "block", **block} for block in facts.get("blocks", []) or document.get("document", {}).get("blocks", []))
+    # One knowledge unit per derived rule. The previous output emitted the
+    # same rule once as ``rule`` and again as ``derived_rule``, doubling the
+    # amount of text an Agent had to index.
+    units.extend({"type": "derived_rule", **rule} for rule in derived.get("requirements", []) or document.get("requirements", []))
+    units.extend({"type": "interaction", **item} for item in derived.get("declared_interactions", []) or document.get("interactions", []))
+    units.extend({"type": "observed_interaction", **item} for item in facts.get("observed_interactions", []))
+    units.extend({"type": "table", **table} for table in facts.get("tables", []) or document.get("tables", []))
+    units.extend({"type": "evidence_ref", **item} for item in document.get("evidence", []))
+    units.append({"type": "coverage", **(document.get("coverage") or {})})
+    units.extend({"type": "warning", "message": warning} for warning in document.get("warnings", []))
+    return "\n".join(json.dumps(unit, ensure_ascii=False, default=str) for unit in units) + "\n"
+
+
+def _escape_cell(value: str) -> str:
+    return value.replace("|", "\\|").replace("\n", "<br>")

modao_prd_cli-0.1.0.dist-info/METADATA

@@ -0,0 +1,108 @@
+Metadata-Version: 2.4
+Name: modao-prd-cli
+Version: 0.1.0
+Summary: Extract public Modao prototype shares into agent-friendly JSON, Markdown, and NDJSON
+Author: modao-prd-cli contributors
+License-Expression: MIT
+Keywords: modao,prototype,prd,cli,agent,playwright
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Documentation
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: click<9.0,>=8.1
+Requires-Dist: playwright<2.0,>=1.62
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: pytest>=7; extra == "dev"
+Requires-Dist: twine>=5; extra == "dev"
+Dynamic: license-file
+
+# modao-prd-cli
+
+`modao-prd-cli` 将墨刀公开分享页采集为便于 Agent 读取的结构化文档和证据包。它使用本机 Chrome/Chromium 渲染页面，不登录墨刀、不保存 Cookie、不调用远程解析服务。
+
+## 安装
+
+```bash
+python3 -m pip install modao-prd-cli
+python3 -m playwright install chromium  # doctor 未发现可用浏览器时执行
+modao-prd-cli doctor --json
+```
+
+## 使用
+
+```bash
+modao-prd-cli inspect "https://modao.cc/proto/<project-id>/sharing?view_mode=inspect" --json
+
+modao-prd-cli export "https://modao.cc/proto/<project-id>/sharing?view_mode=inspect" \
+  --format all
+```
+
+不传 `--output` 时，工具会从当前工作目录向上查找最近的 Git 根目录，并将结果写入该项目根目录下的 `.modao-prd/<project-id>/`。如果当前目录不属于 Git 项目，则使用当前工作目录作为项目根目录。首次默认导出会在项目根目录的 `.gitignore` 中幂等加入 `/.modao-prd/`。
+
+如需指定其他位置，显式传入 `--output` 即可；此时不会修改项目的 `.gitignore`：
+
+```bash
+modao-prd-cli export "<墨刀公开分享链接>" \
+  --format all --output ./modao-export
+```
+
+导出默认使用精简证据模式：保留结构化事实、DOM 布局快照、整页截图、可读画布截图和有效原型图片，过滤运行时代码、埋点资源和常见 UI 图标。DOM 快照也会排除 `script/style` 等运行时节点，避免把框架代码混进需求证据。需要排查渲染问题或核对视觉/无障碍细节时，再显式开启完整证据（debug/full）模式：
+
+```bash
+modao-prd-cli export "<墨刀公开分享链接>" --format all \
+  --evidence full --headed --explore safe --max-states 50 --max-depth 3 \
+  --max-actions 200 --timeout 30 --max-duration 120 \
+  --max-item-mb 10 --max-total-mb 200
+```
+
+只支持 HTTPS 的墨刀公开分享路径：`https://modao.cc/proto/<project-id>/sharing`。
+
+## 输出
+
+```text
+.modao-prd/<project-id>/
+├── manifest.json
+├── document.json
+├── document.md
+├── document.ndjson
+├── coverage.json
+└── evidence/
+    ├── state-001.dom.json
+    ├── state-001.screen-001.png          # essential/full：每个画布一张完整大图
+    ├── state-001.full.png                # --evidence full
+    ├── state-001.rendered.html            # --evidence full
+    ├── state-001.aria.yaml               # --evidence full
+    ├── assets/                           # 过滤后的原型图片
+    └── network/                           # --evidence full
+```
+
+读取顺序建议为 `manifest.json → document.json → coverage.json → evidence/`。
+
+- `document.json` 使用 schema 2.1，是面向 Agent 的紧凑精简投影，区分 `facts`（页面事实）和 `derived`（确定性启发式推导）；需要人读时使用 `document.md`，需要逐条检索时使用 `document.ndjson`。
+- `document.md` 是人工阅读摘要，不替代原始证据。
+- `document.ndjson` 是逐行知识单元，适合 RAG、向量化和增量处理。
+- 默认精简模式输出 DOM/布局证据、可读画布截图和过滤后的原型图片；`--evidence full` 额外保存浏览器整页截图、渲染 HTML、ARIA、相关 JSON/HTML 网络正文和网络索引。精简模式不会为了“完整”保存无助于需求分析的浏览器整页截图、JS、CSS、埋点或通用图标。
+- 每个画布默认只生成一张原始比例的完整大图，例如 `screen-001.png`，不再切分成多张图片；Agent 可按需放大图片，具体文本和结构优先从 `document.json`、`dom.json` 读取。
+- `--headed` 只控制是否显示浏览器窗口，便于 debug，不会单独切换证据级别；完整证据必须显式指定 `--evidence full`。
+- `coverage.json` 记录访问到的状态、动作、跳过项和部分完成原因。
+
+`document.json` 不重复内嵌完整 DOM 父子关系，也不重复输出旧版的 `document.blocks`、顶层 `requirements`、`tables` 等别名；布局树保存在 `evidence/state-*.dom.json`，主文档通过状态和精简证据引用回查。所有页面事实尽量带 `state_id`、`screen_id` 和核心 `evidence_ids`。发生冲突时，以截图、HTML、DOM、ARIA 和原始表格为准；`derived` 只作为分析线索。
+
+退出码为 `0`（在策略范围内完成）、`2`（得到可用但部分完成的证据包）、`1`（未得到可用文档）。
+
+## 限制
+
+- 不支持私有项目、登录态、评论和评审记录。
+- 不点击抽奖、支付、购买、领取、提交、保存、发布、删除等高风险控件。
+- 不访问页面中的外部链接；跨域 iframe、Canvas、视觉表格和图片文字只保存证据并标记未结构化区域。
+- 不承诺理解业务语义；原型示例、日期、概率和外部文档引用需要人工确认。
+
+Agent 使用说明见 [`skills/modao-prd-cli/SKILL.md`](skills/modao-prd-cli/SKILL.md)。

modao_prd_cli-0.1.0.dist-info/RECORD

@@ -0,0 +1,32 @@
+modao_prd_cli/__init__.py,sha256=8frud5wgkIUB8JCwDKuQJ7CqxlYyDh4SgppNCpDiMX0,49
+modao_prd_cli/modao_prd/__init__.py,sha256=DQNC6xk7n2O-z8ljAGANkClf0aPRanXYp4M8zo1ySos,69
+modao_prd_cli/modao_prd/__main__.py,sha256=JxLLND8sn_QRTC_gQwEzNef0C5uNVXCQX4viGAIY_oI,131
+modao_prd_cli/modao_prd/browser.py,sha256=AzLtu54y_Wv3knqqFskfM0CbgbhlD9Vuw8PbyWuoGTw,22412
+modao_prd_cli/modao_prd/capture_evidence.py,sha256=XHLvk4SrKo8mEw78g4rgs9MjTnf36YEGGoJbJsEerU0,23698
+modao_prd_cli/modao_prd/classifier.py,sha256=iTUqptOStYfCFD8QMzZDzvnvR62PF2CPnbLxCya3ej8,4235
+modao_prd_cli/modao_prd/cli.py,sha256=zjCcMPvA6y530-ux399tHvnQOGtGmRZ85kW5AfAP5RE,8417
+modao_prd_cli/modao_prd/errors.py,sha256=c6N3m9KJ-BCv3D72PabKrXx9c0YU4kkCaB1Nf0eU2sQ,801
+modao_prd_cli/modao_prd/evidence.py,sha256=WbhomxpCVrMlDSYD7MkWoDCLvIbiR7FmwI5vUI4B6jY,8536
+modao_prd_cli/modao_prd/explorer.py,sha256=WYNPdnDYP3OYdWR0-QMvAycdZzAvKh0CUkmir5YQtFc,12117
+modao_prd_cli/modao_prd/extractor.py,sha256=OWPeMkhJf-EPd2L6UKoXuS5l3LkdsFXSOxLIlh8ghiM,20129
+modao_prd_cli/modao_prd/models.py,sha256=E7PDuaSZyPndv4r06a7bi1vDWsJUumOWSqZdB8knIpI,1296
+modao_prd_cli/modao_prd/normalizer.py,sha256=BxHSkaHbupGoz2GLmZW8-48IwqLBDtGBNCyU7uUb-jo,5171
+modao_prd_cli/modao_prd/writers.py,sha256=bOM8uaQ58aK55qtATTqcT62tJh4sh3iHha3ltIbVqCs,21393
+modao_prd_cli/modao_prd/schemas/coverage-1.0.json,sha256=rYrkpuUReO9KxLVE2HTBDwIvbJsJ_cZV17SdYEfa9Jk,476
+modao_prd_cli/modao_prd/schemas/document-2.0.json,sha256=Zp59aS5h9MUiDE1v85ncsQYqaL0USQabJKSDnQYfj88,908
+modao_prd_cli/modao_prd/schemas/document-2.1.json,sha256=KnXl-uuZDLQFV5HuwCwg74fUgCVboXewhn7rxVlSWSM,1114
+modao_prd_cli/modao_prd/schemas/manifest-1.0.json,sha256=B3aKAc59To8Y1pzkMk5fKjVJDfIM4e4T9B8pRnQcq8s,927
+modao_prd_cli/modao_prd/tests/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+modao_prd_cli/modao_prd/tests/test_browser.py,sha256=wUyptN_JP_bj3-BJNfsMp5eGXbvdX3p9bQGmaRQT2gM,1795
+modao_prd_cli/modao_prd/tests/test_classifier.py,sha256=9zdzZoVNlCrR-3qgiKN444jn7DX_N933zQEeRcmK6q8,1133
+modao_prd_cli/modao_prd/tests/test_cli.py,sha256=0-e6UP-8RYKj1uaGKnSFmIZ471N13a1-psASieYU44Q,3216
+modao_prd_cli/modao_prd/tests/test_extractor.py,sha256=FR0_d_Q9wlpN7E83Y528xAlafG8h8cUci8m2ZIkP-5A,2602
+modao_prd_cli/modao_prd/tests/test_full_e2e.py,sha256=dXybSUd_h9SOjtOkmYXxLmiEPxDKpX9j7_-c1S_wdyg,887
+modao_prd_cli/modao_prd/tests/test_writers.py,sha256=iBRucC220VIQy0YCELqQ1J7xCBVB-nyjz5x8nZGsxn8,3038
+modao_prd_cli/modao_prd/tests/fixtures/modao_sample.html,sha256=bXR-HlNAacntbR7Pq8fLKc9AbweHgLshnKO__bMTRUw,951
+modao_prd_cli-0.1.0.dist-info/licenses/LICENSE,sha256=lj2zmRPE10Lsf0i8ObqRf7KfXlau8tnE3lp_d3B8MMI,1084
+modao_prd_cli-0.1.0.dist-info/METADATA,sha256=G3jz661WE2-PcUUPLLfq0XeexPD98A4dYz8l1dj6snI,5930
+modao_prd_cli-0.1.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+modao_prd_cli-0.1.0.dist-info/entry_points.txt,sha256=52aJZY_q68cBiIvelyhOXwOqgkh-VZ2yji8VBZ_xxKs,67
+modao_prd_cli-0.1.0.dist-info/top_level.txt,sha256=u4ESjIM5czfnE7XzXEOmJ95CDu6lN0s6gTYpPwOQ35w,14
+modao_prd_cli-0.1.0.dist-info/RECORD,,

modao_prd_cli-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

modao_prd_cli-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+modao-prd-cli = modao_prd_cli.modao_prd.cli:main

modao_prd_cli-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2026 modao-prd-cli contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

modao_prd_cli-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+modao_prd_cli