{
  "canonical_name": "deepchecks/deepchecks",
  "compilation_id": "pack_4e8c5582dfda4253b15f3b158d879102",
  "created_at": "2026-05-21T08:40:30.491208+00:00",
  "created_by": "project-pack-compiler",
  "feedback": {
    "carrier_selection_notes": [
      "viable_asset_types=skill, recipe, host_instruction, eval, preflight",
      "recommended_asset_types=skill, recipe, host_instruction, eval, preflight"
    ],
    "evidence_delta": {
      "confirmed_claims": [
        "identity_anchor_present",
        "capability_and_host_targets_present",
        "install_path_declared_or_better"
      ],
      "missing_required_fields": [],
      "must_verify_forwarded": [
        "Run or inspect `pip install deepchecks` in an isolated environment.",
        "Confirm the project exposes the claimed capability to at least one target host."
      ],
      "quickstart_execution_scope": "allowlisted_sandbox_smoke",
      "sandbox_command": "pip install deepchecks",
      "sandbox_container_image": "python:3.12-slim",
      "sandbox_execution_backend": "docker",
      "sandbox_planner_decision": "llm_execute_isolated_install",
      "sandbox_validation_id": "sbx_4a2efc6a36be4cf386c976a7dbfe28a5"
    },
    "feedback_event_type": "project_pack_compilation_feedback",
    "learning_candidate_reasons": [],
    "template_gaps": []
  },
  "identity": {
    "canonical_id": "project_6c553fd8a28346367d0c95c1314b64eb",
    "canonical_name": "deepchecks/deepchecks",
    "homepage_url": null,
    "license": "unknown",
    "repo_url": "https://github.com/deepchecks/deepchecks",
    "slug": "deepchecks",
    "source_packet_id": "phit_d55f8db4402f466191e8299df1d10cf0",
    "source_validation_id": "dval_eef55b74897b499aa53d08fbb3c60e74"
  },
  "merchandising": {
    "best_for": "需要信息检索与知识管理能力，并使用 local_cli的用户",
    "github_forks": 298,
    "github_stars": 4015,
    "one_liner_en": "Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.",
    "one_liner_zh": "Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.",
    "primary_category": {
      "category_id": "research-knowledge",
      "confidence": "high",
      "name_en": "Research & Knowledge",
      "name_zh": "信息检索与知识管理",
      "reason": "matched_keywords:research, search, source"
    },
    "target_user": "使用 local_cli 等宿主 AI 的用户",
    "title_en": "deepchecks",
    "title_zh": "deepchecks 能力包",
    "visible_tags": [
      {
        "label_en": "Security & Permissions",
        "label_zh": "安全审查与权限治理",
        "source": "repo_evidence_project_characteristics",
        "tag_id": "product_domain-security-permissions",
        "type": "product_domain"
      },
      {
        "label_en": "Knowledge Base Q&A",
        "label_zh": "知识库问答",
        "source": "repo_evidence_project_characteristics",
        "tag_id": "user_job-knowledge-base-q-a",
        "type": "user_job"
      },
      {
        "label_en": "Workflow Automation",
        "label_zh": "流程自动化",
        "source": "repo_evidence_project_characteristics",
        "tag_id": "core_capability-workflow-automation",
        "type": "core_capability"
      },
      {
        "label_en": "Automated Workflow",
        "label_zh": "自动化工作流",
        "source": "repo_evidence_project_characteristics",
        "tag_id": "workflow_pattern-automated-workflow",
        "type": "workflow_pattern"
      },
      {
        "label_en": "Evaluation Suite",
        "label_zh": "评测体系",
        "source": "repo_evidence_project_characteristics",
        "tag_id": "selection_signal-evaluation-suite",
        "type": "selection_signal"
      }
    ]
  },
  "packet_id": "phit_d55f8db4402f466191e8299df1d10cf0",
  "page_model": {
    "artifacts": {
      "artifact_slug": "deepchecks",
      "files": [
        "PROJECT_PACK.json",
        "QUICK_START.md",
        "PROMPT_PREVIEW.md",
        "HUMAN_MANUAL.md",
        "AI_CONTEXT_PACK.md",
        "BOUNDARY_RISK_CARD.md",
        "PITFALL_LOG.md",
        "REPO_INSPECTION.json",
        "REPO_INSPECTION.md",
        "CAPABILITY_CONTRACT.json",
        "EVIDENCE_INDEX.json",
        "CLAIM_GRAPH.json"
      ],
      "required_files": [
        "PROJECT_PACK.json",
        "QUICK_START.md",
        "PROMPT_PREVIEW.md",
        "HUMAN_MANUAL.md",
        "AI_CONTEXT_PACK.md",
        "BOUNDARY_RISK_CARD.md",
        "PITFALL_LOG.md",
        "REPO_INSPECTION.json"
      ]
    },
    "detail": {
      "capability_source": "Project Hit Packet + DownstreamValidationResult",
      "commands": [
        {
          "command": "pip install deepchecks",
          "label": "Python / pip · 官方安装入口",
          "source": "https://github.com/deepchecks/deepchecks#readme",
          "verified": true
        }
      ],
      "display_tags": [
        "安全审查与权限治理",
        "知识库问答",
        "流程自动化",
        "自动化工作流",
        "评测体系"
      ],
      "eyebrow": "信息检索与知识管理",
      "glance": [
        {
          "body": "判断自己是不是目标用户。",
          "label": "最适合谁",
          "value": "需要信息检索与知识管理能力，并使用 local_cli的用户"
        },
        {
          "body": "先理解能力边界，再决定是否继续。",
          "label": "核心价值",
          "value": "Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production."
        },
        {
          "body": "未完成验证前保持审慎。",
          "label": "继续前",
          "value": "publish to Doramagic.ai project surfaces"
        }
      ],
      "guardrail_source": "Boundary & Risk Card",
      "guardrails": [
        {
          "body": "Prompt Preview 只展示流程，不证明项目已安装或运行。",
          "label": "Check 1",
          "value": "不要把试用当真实运行"
        },
        {
          "body": "local_cli",
          "label": "Check 2",
          "value": "确认宿主兼容"
        },
        {
          "body": "publish to Doramagic.ai project surfaces",
          "label": "Check 3",
          "value": "先隔离验证"
        }
      ],
      "mode": "skill, recipe, host_instruction, eval, preflight",
      "pitfall_log": {
        "items": [
          {
            "body": "GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Blank html page after saving report using `save_as_html`",
            "category": "安装坑",
            "evidence": [
              "community_evidence:github | cevd_492bcbfbeaac498b94f2f869074b9edc | https://github.com/deepchecks/deepchecks/issues/2803 | 来源讨论提到 python 相关条件，需在安装/试用前复核。"
            ],
            "severity": "high",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：Blank html page after saving report using `save_as_html`",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered",
            "category": "安装坑",
            "evidence": [
              "community_evidence:github | cevd_4bac6c577dee471fa096434516861696 | https://github.com/deepchecks/deepchecks/issues/2794 | 来源类型 github_issue 暴露的待验证使用条件。"
            ],
            "severity": "high",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift",
            "category": "维护坑",
            "evidence": [
              "community_evidence:github | cevd_b9f771df5da2458d9e368765d829e5c7 | https://github.com/deepchecks/deepchecks/issues/2789 | 来源类型 github_issue 暴露的待验证使用条件。"
            ],
            "severity": "high",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Feature Request: EU AI Act compliance mapping for validation checks",
            "category": "安全/权限坑",
            "evidence": [
              "community_evidence:github | cevd_aaa0c0bcbdbf41d6855980523e0d7682 | https://github.com/deepchecks/deepchecks/issues/2813 | 来源类型 github_issue 暴露的待验证使用条件。"
            ],
            "severity": "high",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：Feature Request: EU AI Act compliance mapping for validation checks",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution Proposed.",
            "category": "安全/权限坑",
            "evidence": [
              "community_evidence:github | cevd_edf8cf14dc8f49898cbcab292f3abbeb | https://github.com/deepchecks/deepchecks/issues/2802 | 来源讨论提到 python 相关条件，需在安装/试用前复核。"
            ],
            "severity": "high",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution…",
            "user_impact": "可能影响授权、密钥配置或安全边界。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.0",
            "category": "安装坑",
            "evidence": [
              "community_evidence:github | cevd_4789fb40d7364096958752494c3054a2 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.0 | 来源讨论提到 python 相关条件，需在安装/试用前复核。"
            ],
            "severity": "medium",
            "suggested_check": "来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。",
            "title": "来源证据：0.18.0",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.1",
            "category": "安装坑",
            "evidence": [
              "community_evidence:github | cevd_53c2c4845d134a54b0989b29725c1c93 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.1 | 来源类型 github_release 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。",
            "title": "来源证据：0.18.1",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap",
            "category": "安装坑",
            "evidence": [
              "community_evidence:github | cevd_e24dd97e69674ab2b766fef25a401070 | https://github.com/deepchecks/deepchecks/issues/2812 | 来源类型 github_issue 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version",
            "category": "安装坑",
            "evidence": [
              "community_evidence:github | cevd_6e307650606b4ed380c4adc96caa8c28 | https://github.com/deepchecks/deepchecks/issues/2806 | 来源讨论提到 python 相关条件，需在安装/试用前复核。"
            ],
            "severity": "medium",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version",
            "user_impact": "可能影响升级、迁移或版本选择。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个配置相关的待验证问题：0.17.3",
            "category": "配置坑",
            "evidence": [
              "community_evidence:github | cevd_b64249b0551146afb696a981f404b3e6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.3 | 来源类型 github_release 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。",
            "title": "来源证据：0.17.3",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个配置相关的待验证问题：Issue when transforming WeakSegmentsPerformance() result to json",
            "category": "配置坑",
            "evidence": [
              "community_evidence:github | cevd_b3a17f2d1dcd4fcb8c3f19ea7065d12e | https://github.com/deepchecks/deepchecks/issues/2804 | 来源类型 github_issue 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。",
            "title": "来源证据：Issue when transforming WeakSegmentsPerformance() result to json",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个能力理解相关的待验证问题：0.17.1",
            "category": "能力坑",
            "evidence": [
              "community_evidence:github | cevd_e55595065e6b4c72b0409a303bb46b11 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.1 | 来源类型 github_release 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。",
            "title": "来源证据：0.17.1",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "README/documentation is current enough for a first validation pass.",
            "category": "能力坑",
            "evidence": [
              "capability.assumptions | github_repo:415969774 | https://github.com/deepchecks/deepchecks | README/documentation is current enough for a first validation pass."
            ],
            "severity": "medium",
            "suggested_check": "将假设转成下游验证清单。",
            "title": "能力判断依赖假设",
            "user_impact": "假设不成立时，用户拿不到承诺的能力。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.2",
            "category": "维护坑",
            "evidence": [
              "community_evidence:github | cevd_1d041b1b08154f96bd89a083df4cd0a6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.2 | 来源类型 github_release 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。",
            "title": "来源证据：0.17.2",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.4",
            "category": "维护坑",
            "evidence": [
              "community_evidence:github | cevd_70c9f9ecef424b4285d991e8da70bec5 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.4 | 来源类型 github_release 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。",
            "title": "来源证据：0.17.4",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          },
          {
            "body": "GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.19.0",
            "category": "维护坑",
            "evidence": [
              "community_evidence:github | cevd_c3ee5d33ff214aef96b8df58fd89837a | https://github.com/deepchecks/deepchecks/releases/tag/0.19.0 | 来源类型 github_release 暴露的待验证使用条件。"
            ],
            "severity": "medium",
            "suggested_check": "来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。",
            "title": "来源证据：0.19.0",
            "user_impact": "可能增加新用户试用和生产接入成本。"
          }
        ],
        "source": "ProjectPitfallLog + ProjectHitPacket + validation + community signals",
        "summary": "发现 22 个潜在踩坑项，其中 5 个为 high/blocking；最高优先级：安装坑 - 来源证据：Blank html page after saving report using `save_as_html`。",
        "title": "踩坑日志"
      },
      "snapshot": {
        "contributors": 55,
        "forks": 298,
        "license": "unknown",
        "note": "站点快照，非实时质量证明；用于开工前背景判断。",
        "stars": 4015
      },
      "source_url": "https://github.com/deepchecks/deepchecks",
      "steps": [
        {
          "body": "不安装项目，先体验能力节奏。",
          "code": "preview",
          "title": "先试 Prompt"
        },
        {
          "body": "理解输入、输出、失败模式和边界。",
          "code": "manual",
          "title": "读说明书"
        },
        {
          "body": "把上下文交给宿主 AI 继续工作。",
          "code": "context",
          "title": "带给 AI"
        },
        {
          "body": "进入主力环境前先完成安装入口与风险边界验证。",
          "code": "verify",
          "title": "沙箱验证"
        }
      ],
      "subtitle": "Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.",
      "title": "deepchecks 能力包",
      "trial_prompt": "# deepchecks - Prompt Preview\n\n> 复制下面这段 Prompt 到你常用的 AI，先试一次，不需要安装。\n> 它的目标是让你直接体验这个项目的服务方式，而不是阅读项目介绍。\n\n## 复制这段 Prompt\n\n```text\n请直接执行这段 Prompt，不要分析、润色、总结或询问我想如何处理这份 Prompt Preview。\n\n你现在扮演 deepchecks 的“安装前体验版”。\n这不是项目介绍、不是评价报告、不是 README 总结。你的任务是让我用最小成本体验它的核心服务。\n\n我的试用任务：我想快速理解一组资料，并得到结构化摘要、对比和继续研究的问题。\n我常用的宿主 AI：Local CLI\n\n【体验目标】\n围绕我的真实任务，现场演示这个项目如何把输入转成 示例引导, 判断线索。重点是让我感受到工作方式，而不是给我项目背景。\n\n【业务流约束】\n- 你必须像一个正在提供服务的项目能力包，而不是像一个讲解员。\n- 每一轮只推进一个步骤；提出问题后必须停下来等我回答。\n- 每一步都必须让我感受到一个具体服务动作：澄清、整理、规划、检查、判断或收尾。\n- 每一步都要说明：当前目标、你需要我提供什么、我回答后你会产出什么。\n- 不要安装、不要运行命令、不要写代码、不要声称测试通过、不要声称已经修改文件。\n- 需要真实安装或宿主加载后才能验证的内容，必须明确说“这一步需要安装后验证”。\n- 如果我说“用示例继续”，你可以用虚构示例推进，但仍然不能声称真实执行。\n\n【可体验服务能力】\n- 安装前能力预览: Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production. 输入：用户任务, 当前 AI 对话上下文；输出：示例引导, 判断线索。\n\n【必须安装后才可验证的能力】\n- 命令行启动或安装流程: 项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 输入：终端环境, 包管理器, 项目依赖；输出：安装结果, 列表/更新/运行结果。\n\n【核心服务流】\n请严格按这个顺序带我体验。不要一次性输出完整流程：\n1. overview：仓库概览。围绕“仓库概览”模拟一次用户任务，不展示安装或运行结果。\n2. entrypoints：入口与运行边界。围绕“入口与运行边界”模拟一次用户任务，不展示安装或运行结果。\n3. architecture：架构证据地图。围绕“架构证据地图”模拟一次用户任务，不展示安装或运行结果。\n4. operations：运维与验证边界。围绕“运维与验证边界”模拟一次用户任务，不展示安装或运行结果。\n\n【核心能力体验剧本】\n每一步都必须按“输入 -> 服务动作 -> 中间产物”执行。不要只说流程名：\n1. overview\n输入：用户提供的“仓库概览”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n2. entrypoints\n输入：用户提供的“入口与运行边界”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n3. architecture\n输入：用户提供的“架构证据地图”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n4. operations\n输入：用户提供的“运维与验证边界”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n【项目服务规则】\n这些规则决定你如何服务用户。不要解释规则本身，而要在每一步执行时遵守：\n- 先确认用户任务、输入材料和成功标准，再模拟项目能力。\n- 每一步都必须形成可检查的小产物，并等待用户确认后再继续。\n- 凡是需要安装、调用工具或访问外部服务的能力，都必须标记为安装后验证。\n\n【每一步的服务约束】\n- Step 1 / overview：Step 1 必须围绕“仓库概览”形成一个小中间产物，并等待用户确认。\n- Step 2 / entrypoints：Step 2 必须围绕“入口与运行边界”形成一个小中间产物，并等待用户确认。\n- Step 3 / architecture：Step 3 必须围绕“架构证据地图”形成一个小中间产物，并等待用户确认。\n- Step 4 / operations：Step 4 必须围绕“运维与验证边界”形成一个小中间产物，并等待用户确认。\n\n【边界与风险】\n- 不要声称已经安装、运行、调用 API、读写本地文件或完成真实任务。\n- 安装前预览只能展示工作方式，不能证明兼容性、性能或输出质量。\n- 涉及安装、插件加载、工具调用或外部服务的能力必须安装后验证。\n\n【可追溯依据】\n这些路径只用于你内部校验或在我追问“依据是什么”时简要引用。不要在首次回复主动展开：\n- https://github.com/deepchecks/deepchecks\n- https://github.com/deepchecks/deepchecks#readme\n- README.md\n- docs/requirements.txt\n- requirements/requirements.txt\n- docs/source/api/deepchecks.core.rst\n- docs/source/api/deepchecks.nlp.checks.rst\n- docs/source/api/deepchecks.nlp.rst\n- docs/source/api/deepchecks.nlp.suites.rst\n- docs/source/api/deepchecks.tabular.checks.rst\n- docs/source/api/deepchecks.tabular.rst\n- docs/source/api/deepchecks.tabular.suites.rst\n\n【首次问题规则】\n- 首次三问必须先确认用户目标、成功标准和边界，不要提前进入工具、安装或实现细节。\n- 如果后续需要技术条件、文件路径或运行环境，必须等用户确认目标后再追问。\n\n首次回复必须只输出下面 4 个部分：\n1. 体验开始：用 1 句话说明你将带我体验 deepchecks 的核心服务。\n2. 当前步骤：明确进入 Step 1，并说明这一步要解决什么。\n3. 你会如何服务我：说明你会先改变我完成任务的哪个动作。\n4. 只问我 3 个问题，然后停下等待回答。\n\n首次回复禁止输出：后续完整流程、证据清单、安装命令、项目评价、营销文案、已经安装或运行的说法。\n\nStep 1 / brainstorming 的二轮协议：\n- 我回答首次三问后，你仍然停留在 Step 1 / brainstorming，不要进入 Step 2。\n- 第二次回复必须产出 6 个部分：澄清后的任务定义、成功标准、边界条件、\n  2-3 个可选方案、每个方案的权衡、推荐方案。\n- 第二次回复最后必须问我是否确认推荐方案；只有我明确确认后，才能进入下一步。\n- 第二次回复禁止输出 git worktree、代码计划、测试文件、命令或真实执行结果。\n\n后续对话规则：\n- 我回答后，你先完成当前步骤的中间产物并等待确认；只有我确认后，才能进入下一步。\n- 每一步都要生成一个小的中间产物，例如澄清后的目标、计划草案、测试意图、验证清单或继续/停止判断。\n- 所有演示都写成“我会建议/我会引导/这一步会形成”，不要写成已经真实执行。\n- 不要声称已经测试通过、文件已修改、命令已运行或结果已产生。\n- 如果某个能力必须安装后验证，请直接说“这一步需要安装后验证”。\n- 如果证据不足，请明确说“证据不足”，不要补事实。\n```\n",
      "voices": [
        {
          "body": "来源平台：github。github/github_issue: [BUG] GPU not being able to change runtime of Image Property Drift and I（https://github.com/deepchecks/deepchecks/issues/2789）；github/github_issue: Failed to load model class 'AnyModel' from module 'anywidget' Error: No （https://github.com/deepchecks/deepchecks/issues/2794）；github/github_issue: Feature Request: EU AI Act compliance mapping for validation checks（https://github.com/deepchecks/deepchecks/issues/2813）；github/github_issue: Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem（https://github.com/deepchecks/deepchecks/issues/2812）；github/github_issue: [BUG] neg_log_loss scorer incompatible with newer scikit-learn version（https://github.com/deepchecks/deepchecks/issues/2806）；github/github_issue: [BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation（https://github.com/deepchecks/deepchecks/issues/2802）；github/github_issue: Blank html page after saving report using `save_as_html`（https://github.com/deepchecks/deepchecks/issues/2803）；github/github_issue: Issue when transforming WeakSegmentsPerformance() result to json（https://github.com/deepchecks/deepchecks/issues/2804）；github/github_release: 0.19.1（https://github.com/deepchecks/deepchecks/releases/tag/0.19.1）；github/github_release: 0.19.0（https://github.com/deepchecks/deepchecks/releases/tag/0.19.0）；github/github_release: 0.18.1（https://github.com/deepchecks/deepchecks/releases/tag/0.18.1）；github/github_release: 0.18.0（https://github.com/deepchecks/deepchecks/releases/tag/0.18.0）。这些是项目级外部声音，不作为单独质量证明。",
          "items": [
            {
              "kind": "github_issue",
              "source": "github",
              "title": "[BUG] GPU not being able to change runtime of Image Property Drift and I",
              "url": "https://github.com/deepchecks/deepchecks/issues/2789"
            },
            {
              "kind": "github_issue",
              "source": "github",
              "title": "Failed to load model class 'AnyModel' from module 'anywidget' Error: No ",
              "url": "https://github.com/deepchecks/deepchecks/issues/2794"
            },
            {
              "kind": "github_issue",
              "source": "github",
              "title": "Feature Request: EU AI Act compliance mapping for validation checks",
              "url": "https://github.com/deepchecks/deepchecks/issues/2813"
            },
            {
              "kind": "github_issue",
              "source": "github",
              "title": "Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem",
              "url": "https://github.com/deepchecks/deepchecks/issues/2812"
            },
            {
              "kind": "github_issue",
              "source": "github",
              "title": "[BUG] neg_log_loss scorer incompatible with newer scikit-learn version",
              "url": "https://github.com/deepchecks/deepchecks/issues/2806"
            },
            {
              "kind": "github_issue",
              "source": "github",
              "title": "[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation",
              "url": "https://github.com/deepchecks/deepchecks/issues/2802"
            },
            {
              "kind": "github_issue",
              "source": "github",
              "title": "Blank html page after saving report using `save_as_html`",
              "url": "https://github.com/deepchecks/deepchecks/issues/2803"
            },
            {
              "kind": "github_issue",
              "source": "github",
              "title": "Issue when transforming WeakSegmentsPerformance() result to json",
              "url": "https://github.com/deepchecks/deepchecks/issues/2804"
            },
            {
              "kind": "github_release",
              "source": "github",
              "title": "0.19.1",
              "url": "https://github.com/deepchecks/deepchecks/releases/tag/0.19.1"
            },
            {
              "kind": "github_release",
              "source": "github",
              "title": "0.19.0",
              "url": "https://github.com/deepchecks/deepchecks/releases/tag/0.19.0"
            },
            {
              "kind": "github_release",
              "source": "github",
              "title": "0.18.1",
              "url": "https://github.com/deepchecks/deepchecks/releases/tag/0.18.1"
            },
            {
              "kind": "github_release",
              "source": "github",
              "title": "0.18.0",
              "url": "https://github.com/deepchecks/deepchecks/releases/tag/0.18.0"
            }
          ],
          "status": "已收录 12 条来源",
          "title": "社区讨论"
        }
      ]
    },
    "homepage_card": {
      "category": "信息检索与知识管理",
      "desc": "Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.",
      "effort": "安装已验证",
      "forks": 298,
      "icon": "search",
      "name": "deepchecks 能力包",
      "risk": "可发布",
      "slug": "deepchecks",
      "stars": 4015,
      "tags": [
        "安全审查与权限治理",
        "知识库问答",
        "流程自动化",
        "自动化工作流",
        "评测体系"
      ],
      "thumb": "blue",
      "type": "Skill Pack"
    },
    "manual": {
      "markdown": "# https://github.com/deepchecks/deepchecks 项目说明书\n\n生成时间: 2026-05-21 08:39:22 UTC\n\n## 目录\n\n- [仓库概览](#overview)\n- [入口与运行边界](#entrypoints)\n- [架构证据地图](#architecture)\n- [运维与验证边界](#operations)\n\n<a id='overview'></a>\n\n## 仓库概览\n\n### 相关页面\n\n相关主题：[入口与运行边界](#entrypoints), [架构证据地图](#architecture), [运维与验证边界](#operations)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 仓库概览\n\n本页在 Human Wiki provider 不可用时基于仓库证据生成，只使用 README、文件树和已选源码文件，不把模板描述冒充项目事实。\n\n## README 证据\n\n<!--\n   ~ ----------------------------------------------------------------------------\n   ~ Copyright (C) 2021-2023 Deepchecks (https://www.deepchecks.com)\n   ~\n   ~ This file is part of Deepchecks.\n   ~ Deepchecks is distributed under the terms of the GNU Affero General\n   ~ Public License (version 3 or later).\n   ~ You should have received a copy of the GNU Affero General Public License\n   ~ along with Deepchecks.  If not, see <http://www.gnu.org/licenses/>.\n   ~ ----------------------------------------------------------------------------\n   ~\n-->\n\n[![GitHub\nstars](https://img.shields.io/github/stars/deepchecks/deepchecks.svg?style=social&label=Star&maxAge=2592000)](https://GitHub.com/deepchecks/deepchecks/stargazers/)\n![build](https://github.com/deepchecks/deepchecks/actions/workflows/build.yml/badge.svg)\n![pkgVersion](https://img.shields.io/pypi/v/deepchecks)\n[![Coverage\nStatus](https://coveralls.io/repos/github/deepchecks/deepchecks/badge.svg?branch=main)](https://coveralls.io/github/deepchecks/deepchecks?branch=main) \n<!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->\n[![All Contributors](https://img.shields.io/badge/all_contributors-44-orange.svg?style=flat-round)](#https://github.com/deepchecks/deepchecks/blob/main/CONTRIBUTING.rst)\n<!-- ALL-CONTRIBUTORS-BADGE:END --> \n\n<!---\nthis badge takes quite some space, can re-add it if wanted\n![pyVersions](https://img.shields.io/pypi/pyversions/deepchecks)\n--->\n\n<h1 align=\"center\">\n   Deepchecks - Continuous Validation for AI & ML: Testing, CI & Monitoring\n</h1>\n\nDeepchecks is a holistic open-source solution for all of your AI & ML validation needs,\nenabling you to thoroughly test your data and models from research to production.\n\n<a target=\"_blank\" href=\"https://docs.deepchecks.com/?utm_source=github.com&utm_medium=referral&utm_campaign=readme&utm_content=logo\">\n   <picture>\n      <source media=\"(prefers-color-scheme: dark)\" srcset=\"docs/source/_static/images/readme/deepchecks_continuous_validation_dark.png\">\n      <source media=\"(prefers-color-scheme: light)\" srcset=\"docs/source/_static/images/readme/deepchecks_continuous_validation_light.png\">\n      <img alt=\"Deepchecks continuous validation parts.\" src=\"docs/source/_static/images//readme/deepchecks_continuous_validation_light.png\">\n   </picture>\n</a>\n\n<p align=\"center\">\n   &emsp;\n   <a href=\"https://www.deepchecks.com/slack\">👋 Jo\n\n[excerpt truncated]\n\n## 已选源码清单\n\n- `README.md`\n- `docs/requirements.txt`\n- `requirements/requirements.txt`\n- `docs/source/api/deepchecks.core.rst`\n- `docs/source/api/deepchecks.nlp.checks.rst`\n- `docs/source/api/deepchecks.nlp.rst`\n- `docs/source/api/deepchecks.nlp.suites.rst`\n- `docs/source/api/deepchecks.tabular.checks.rst`\n- `docs/source/api/deepchecks.tabular.rst`\n- `docs/source/api/deepchecks.tabular.suites.rst`\n- `docs/source/api/deepchecks.utils.rst`\n- `docs/source/api/deepchecks.vision.checks.rst`\n\n| 文件 | 证据角色 | 大小 |\n|---|---|---|\n| `README.md` | README/产品与使用证据 | 31857 bytes |\n| `docs/requirements.txt` | 仓库证据 | 557 bytes |\n| `requirements/requirements.txt` | 仓库证据 | 998 bytes |\n| `docs/source/api/deepchecks.core.rst` | 实现边界 | 459 bytes |\n| `docs/source/api/deepchecks.nlp.checks.rst` | 实现边界 | 268 bytes |\n| `docs/source/api/deepchecks.nlp.rst` | 实现边界 | 669 bytes |\n| `docs/source/api/deepchecks.nlp.suites.rst` | 实现边界 | 258 bytes |\n| `docs/source/api/deepchecks.tabular.checks.rst` | 实现边界 | 280 bytes |\n| `docs/source/api/deepchecks.tabular.rst` | 实现边界 | 929 bytes |\n| `docs/source/api/deepchecks.tabular.suites.rst` | 实现边界 | 284 bytes |\n| `docs/source/api/deepchecks.utils.rst` | 实现边界 | 546 bytes |\n| `docs/source/api/deepchecks.vision.checks.rst` | 实现边界 | 278 bytes |\n\n资料来源：`[README.md:1-120]()`\n\n---\n\n<a id='entrypoints'></a>\n\n## 入口与运行边界\n\n### 相关页面\n\n相关主题：[仓库概览](#overview), [架构证据地图](#architecture), [运维与验证边界](#operations)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 入口与运行边界\n\n下面文件是安装、启动、配置或宿主集成的高信号候选。这里给出证据地图，不推断未经执行验证的 API 契约。\n\n| 文件 | 证据角色 | 大小 |\n|---|---|---|\n| `README.md` | README/产品与使用证据 | 31857 bytes |\n| `docs/requirements.txt` | 仓库证据 | 557 bytes |\n| `requirements/requirements.txt` | 仓库证据 | 998 bytes |\n| `docs/source/api/deepchecks.core.rst` | 实现边界 | 459 bytes |\n| `docs/source/api/deepchecks.nlp.checks.rst` | 实现边界 | 268 bytes |\n| `docs/source/api/deepchecks.nlp.rst` | 实现边界 | 669 bytes |\n| `docs/source/api/deepchecks.nlp.suites.rst` | 实现边界 | 258 bytes |\n| `docs/source/api/deepchecks.tabular.checks.rst` | 实现边界 | 280 bytes |\n| `docs/source/api/deepchecks.tabular.rst` | 实现边界 | 929 bytes |\n| `docs/source/api/deepchecks.tabular.suites.rst` | 实现边界 | 284 bytes |\n| `docs/source/api/deepchecks.utils.rst` | 实现边界 | 546 bytes |\n| `docs/source/api/deepchecks.vision.checks.rst` | 实现边界 | 278 bytes |\n\n资料来源：`[README.md:1-120](https://github.com/deepchecks/deepchecks/blob/main/README.md)`\n\n---\n\n<a id='architecture'></a>\n\n## 架构证据地图\n\n### 相关页面\n\n相关主题：[仓库概览](#overview), [入口与运行边界](#entrypoints), [运维与验证边界](#operations)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 架构证据地图\n\n本节只根据仓库路径组织可能的架构区域；需要运行验证的行为不会在这里断言。\n\n- `.`: `README.md`\n- `docs`: `docs/requirements.txt`, `docs/source/api/deepchecks.core.rst`, `docs/source/api/deepchecks.nlp.checks.rst`, `docs/source/api/deepchecks.nlp.rst`, `docs/source/api/deepchecks.nlp.suites.rst`, `docs/source/api/deepchecks.tabular.checks.rst`\n- `requirements`: `requirements/requirements.txt`\n\n资料来源：`[docs/requirements.txt:1-120](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)`\n\n---\n\n<a id='operations'></a>\n\n## 运维与验证边界\n\n### 相关页面\n\n相关主题：[仓库概览](#overview), [入口与运行边界](#entrypoints), [架构证据地图](#architecture)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 运维与验证边界\n\n运维建议仅来自仓库中真实存在的文件。把该项目用于 agent 工作流前，仍需在 sandbox 中验证安装、quickstart 和运行行为。\n\n- Documentation signal: `README.md`\n- Source inspection signal: `docs/requirements.txt`\n- Source inspection signal: `requirements/requirements.txt`\n- Documentation signal: `docs/source/api/deepchecks.core.rst`\n- Documentation signal: `docs/source/api/deepchecks.nlp.checks.rst`\n- Documentation signal: `docs/source/api/deepchecks.nlp.rst`\n- Documentation signal: `docs/source/api/deepchecks.nlp.suites.rst`\n- Documentation signal: `docs/source/api/deepchecks.tabular.checks.rst`\n- Documentation signal: `docs/source/api/deepchecks.tabular.rst`\n- Documentation signal: `docs/source/api/deepchecks.tabular.suites.rst`\n\n资料来源：`[requirements/requirements.txt:1-120](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)`\n\n---\n\n---\n\n## Doramagic 踩坑日志\n\n项目：deepchecks/deepchecks\n\n摘要：发现 22 个潜在踩坑项，其中 5 个为 high/blocking；最高优先级：安装坑 - 来源证据：Blank html page after saving report using `save_as_html`。\n\n## 1. 安装坑 · 来源证据：Blank html page after saving report using `save_as_html`\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Blank html page after saving report using `save_as_html`\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_492bcbfbeaac498b94f2f869074b9edc | https://github.com/deepchecks/deepchecks/issues/2803 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 2. 安装坑 · 来源证据：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_4bac6c577dee471fa096434516861696 | https://github.com/deepchecks/deepchecks/issues/2794 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 3. 维护坑 · 来源证据：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b9f771df5da2458d9e368765d829e5c7 | https://github.com/deepchecks/deepchecks/issues/2789 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 4. 安全/权限坑 · 来源证据：Feature Request: EU AI Act compliance mapping for validation checks\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Feature Request: EU AI Act compliance mapping for validation checks\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_aaa0c0bcbdbf41d6855980523e0d7682 | https://github.com/deepchecks/deepchecks/issues/2813 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 5. 安全/权限坑 · 来源证据：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution…\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution Proposed.\n- 对用户的影响：可能影响授权、密钥配置或安全边界。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_edf8cf14dc8f49898cbcab292f3abbeb | https://github.com/deepchecks/deepchecks/issues/2802 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 6. 安装坑 · 来源证据：0.18.0\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.0\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_4789fb40d7364096958752494c3054a2 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.0 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 7. 安装坑 · 来源证据：0.18.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_53c2c4845d134a54b0989b29725c1c93 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 8. 安装坑 · 来源证据：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_e24dd97e69674ab2b766fef25a401070 | https://github.com/deepchecks/deepchecks/issues/2812 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 9. 安装坑 · 来源证据：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n- 对用户的影响：可能影响升级、迁移或版本选择。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_6e307650606b4ed380c4adc96caa8c28 | https://github.com/deepchecks/deepchecks/issues/2806 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 10. 配置坑 · 来源证据：0.17.3\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个配置相关的待验证问题：0.17.3\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b64249b0551146afb696a981f404b3e6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.3 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 11. 配置坑 · 来源证据：Issue when transforming WeakSegmentsPerformance() result to json\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个配置相关的待验证问题：Issue when transforming WeakSegmentsPerformance() result to json\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b3a17f2d1dcd4fcb8c3f19ea7065d12e | https://github.com/deepchecks/deepchecks/issues/2804 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 12. 能力坑 · 来源证据：0.17.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个能力理解相关的待验证问题：0.17.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_e55595065e6b4c72b0409a303bb46b11 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 13. 能力坑 · 能力判断依赖假设\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：README/documentation is current enough for a first validation pass.\n- 对用户的影响：假设不成立时，用户拿不到承诺的能力。\n- 建议检查：将假设转成下游验证清单。\n- 防护动作: 假设必须转成验证项；没有验证结果前不能写成事实。\n- 证据：capability.assumptions | github_repo:415969774 | https://github.com/deepchecks/deepchecks | README/documentation is current enough for a first validation pass.\n\n## 14. 维护坑 · 来源证据：0.17.2\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.2\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_1d041b1b08154f96bd89a083df4cd0a6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.2 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 15. 维护坑 · 来源证据：0.17.4\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.4\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_70c9f9ecef424b4285d991e8da70bec5 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.4 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 16. 维护坑 · 来源证据：0.19.0\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.19.0\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_c3ee5d33ff214aef96b8df58fd89837a | https://github.com/deepchecks/deepchecks/releases/tag/0.19.0 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 17. 维护坑 · 来源证据：0.19.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.19.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_3bf11cec6e224a17826f2ee5ef3d26fd | https://github.com/deepchecks/deepchecks/releases/tag/0.19.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 18. 维护坑 · 维护活跃度未知\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：未记录 last_activity_observed。\n- 对用户的影响：新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。\n- 建议检查：补 GitHub 最近 commit、release、issue/PR 响应信号。\n- 防护动作: 维护活跃度未知时，推荐强度不能标为高信任。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | last_activity_observed missing\n\n## 19. 安全/权限坑 · 下游验证发现风险项\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：no_demo\n- 对用户的影响：下游已经要求复核，不能在页面中弱化。\n- 建议检查：进入安全/权限治理复核队列。\n- 防护动作: 下游风险存在时必须保持 review/recommendation 降级。\n- 证据：downstream_validation.risk_items | github_repo:415969774 | https://github.com/deepchecks/deepchecks | no_demo; severity=medium\n\n## 20. 安全/权限坑 · 存在评分风险\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：no_demo\n- 对用户的影响：风险会影响是否适合普通用户安装。\n- 建议检查：把风险写入边界卡，并确认是否需要人工复核。\n- 防护动作: 评分风险必须进入边界卡，不能只作为内部分数。\n- 证据：risks.scoring_risks | github_repo:415969774 | https://github.com/deepchecks/deepchecks | no_demo; severity=medium\n\n## 21. 维护坑 · issue/PR 响应质量未知\n\n- 严重度：low\n- 证据强度：source_linked\n- 发现：issue_or_pr_quality=unknown。\n- 对用户的影响：用户无法判断遇到问题后是否有人维护。\n- 建议检查：抽样最近 issue/PR，判断是否长期无人处理。\n- 防护动作: issue/PR 响应未知时，必须提示维护风险。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | issue_or_pr_quality=unknown\n\n## 22. 维护坑 · 发布节奏不明确\n\n- 严重度：low\n- 证据强度：source_linked\n- 发现：release_recency=unknown。\n- 对用户的影响：安装命令和文档可能落后于代码，用户踩坑概率升高。\n- 建议检查：确认最近 release/tag 和 README 安装命令是否一致。\n- 防护动作: 发布节奏未知或过期时，安装说明必须标注可能漂移。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | release_recency=unknown\n\n<!-- canonical_name: deepchecks/deepchecks; human_manual_source: deepwiki_human_wiki -->\n",
      "markdown_key": "deepchecks",
      "pages": "draft",
      "source_refs": [
        {
          "evidence_id": "github_repo:415969774",
          "kind": "repo",
          "supports_claim_ids": [
            "claim_identity",
            "claim_distribution",
            "claim_capability"
          ],
          "url": "https://github.com/deepchecks/deepchecks"
        },
        {
          "evidence_id": "art_4d7700ab19594554b2adb38d9f05aaaf",
          "kind": "docs",
          "supports_claim_ids": [
            "claim_identity",
            "claim_distribution",
            "claim_capability"
          ],
          "url": "https://github.com/deepchecks/deepchecks#readme"
        }
      ],
      "summary": "DeepWiki/Human Wiki 完整输出，末尾追加 Discovery Agent 踩坑日志。",
      "title": "deepchecks 说明书",
      "toc": [
        "https://github.com/deepchecks/deepchecks 项目说明书",
        "目录",
        "仓库概览",
        "README 证据",
        "已选源码清单",
        "入口与运行边界",
        "架构证据地图",
        "运维与验证边界",
        "Doramagic 踩坑日志"
      ]
    }
  },
  "quality_gate": {
    "blocking_gaps": [],
    "category_confidence": "medium",
    "compile_status": "ready_for_review",
    "five_assets_present": true,
    "install_sandbox_verified": true,
    "missing_evidence": [],
    "next_action": "publish to Doramagic.ai project surfaces",
    "prompt_preview_boundary_ok": true,
    "publish_status": "publishable",
    "quick_start_verified": true,
    "repo_clone_verified": true,
    "repo_commit": "98475d17b08a21fca29d533b94b8ec3c70544a85",
    "repo_inspection_error": null,
    "repo_inspection_files": [
      "README.md",
      "docs/source/conf.py",
      "docs/source/_static/switcher.json",
      "docs/source/tabular/tutorials/quickstarts/plot_quick_model_evaluation.py",
      "docs/source/tabular/tutorials/quickstarts/plot_quick_data_integrity.py",
      "docs/source/tabular/tutorials/quickstarts/plot_quick_train_test_validation.py",
      "docs/source/tabular/tutorials/quickstarts/plot_quickstart_in_5_minutes.py",
      "docs/source/tabular/tutorials/other/plot_add_a_custom_check.py",
      "docs/source/tabular/tutorials/other/plot_phishing_urls.py",
      "docs/source/general/usage/customizations/plot_configure_check_conditions.py",
      "docs/source/general/usage/customizations/plot_create_a_custom_suite.py",
      "docs/source/general/usage/customizations/plot_create_a_custom_check.py",
      "docs/source/general/usage/exporting_results/plot_export_suite_results_as_html.py",
      "docs/source/general/usage/exporting_results/plot_exports_output_to_wandb.py",
      "docs/source/general/usage/exporting_results/plot_export_outputs_to_json.py",
      "docs/source/checks/tabular/data_integrity/plot_string_length_out_of_bounds.py",
      "docs/source/checks/tabular/data_integrity/plot_special_chars.py",
      "docs/source/checks/tabular/data_integrity/plot_string_mismatch.py",
      "docs/source/checks/tabular/data_integrity/plot_data_duplicates.py",
      "docs/source/checks/tabular/data_integrity/plot_percent_of_nulls.py",
      "docs/source/checks/tabular/data_integrity/plot_outlier_sample_detection.py",
      "docs/source/checks/tabular/data_integrity/plot_is_single_value.py",
      "docs/source/checks/tabular/data_integrity/plot_feature_feature_correlation.py",
      "docs/source/checks/tabular/data_integrity/plot_columns_info.py",
      "docs/source/checks/tabular/data_integrity/plot_mixed_data_types.py",
      "docs/source/checks/tabular/data_integrity/plot_mixed_nulls.py",
      "docs/source/checks/tabular/data_integrity/plot_feature_label_correlation.py",
      "docs/source/checks/tabular/data_integrity/plot_conflicting_labels.py",
      "docs/source/checks/tabular/data_integrity/plot_class_imbalance.py",
      "docs/source/checks/tabular/data_integrity/plot_identifier_label_correlation.py",
      "docs/source/checks/tabular/model_evaluation/plot_boosting_overfit.py",
      "docs/source/checks/tabular/model_evaluation/plot_confusion_matrix_report.py",
      "docs/source/checks/tabular/model_evaluation/plot_multi_model_performance_report.py",
      "docs/source/checks/tabular/model_evaluation/plot_model_info.py",
      "docs/source/checks/tabular/model_evaluation/plot_roc_report.py",
      "docs/source/checks/tabular/model_evaluation/plot_calibration_score.py",
      "docs/source/checks/tabular/model_evaluation/plot_regression_systematic_error.py",
      "docs/source/checks/tabular/model_evaluation/plot_weak_segments_performance.py",
      "docs/source/checks/tabular/model_evaluation/plot_train_test_performance.py",
      "docs/source/checks/tabular/model_evaluation/plot_single_dataset_performance.py"
    ],
    "repo_inspection_verified": true,
    "review_reasons": [],
    "tag_count_ok": true,
    "unsupported_claims": []
  },
  "schema_version": "0.1",
  "user_assets": {
    "ai_context_pack": {
      "asset_id": "ai_context_pack",
      "filename": "AI_CONTEXT_PACK.md",
      "markdown": "# deepchecks - Doramagic AI Context Pack\n\n> 定位：安装前体验与判断资产。它帮助宿主 AI 有一个好的开始，但不代表已经安装、执行或验证目标项目。\n\n## 充分原则\n\n- **充分原则，不是压缩原则**：AI Context Pack 应该充分到让宿主 AI 在开工前理解项目价值、能力边界、使用入口、风险和证据来源；它可以分层组织，但不以最短摘要为目标。\n- **压缩策略**：只压缩噪声和重复内容，不压缩会影响判断和开工质量的上下文。\n\n## 给宿主 AI 的使用方式\n\n你正在读取 Doramagic 为 deepchecks 编译的 AI Context Pack。请把它当作开工前上下文：帮助用户理解适合谁、能做什么、如何开始、哪些必须安装后验证、风险在哪里。不要声称你已经安装、运行或执行了目标项目。\n\n## Claim 消费规则\n\n- **事实来源**：Repo Evidence + Claim/Evidence Graph；Human Wiki 只提供显著性、术语和叙事结构。\n- **事实最低状态**：`supported`\n- `supported`：可以作为项目事实使用，但回答中必须引用 claim_id 和证据路径。\n- `weak`：只能作为低置信度线索，必须要求用户继续核实。\n- `inferred`：只能用于风险提示或待确认问题，不能包装成项目事实。\n- `unverified`：不得作为事实使用，应明确说证据不足。\n- `contradicted`：必须展示冲突来源，不得替用户强行选择一个版本。\n\n## 它最适合谁\n\n- **想在安装前理解开源项目价值和边界的用户**：当前证据主要来自项目文档。 证据：`README.md` Claim：`clm_0002` supported 0.86\n\n## 它能做什么\n\n- **命令行启动或安装流程**（需要安装后验证）：项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 证据：`README.md` Claim：`clm_0001` supported 0.86\n\n## 怎么开始\n\n- `pip install deepchecks -U --user` 证据：`README.md` Claim：`clm_0003` supported 0.86\n- `pip install deepchecks-installer` 证据：`README.md` Claim：`clm_0004` supported 0.86\n\n## 继续前判断卡\n\n- **当前建议**：仅建议沙盒试装\n- **为什么**：项目存在安装命令、宿主配置或本地写入线索，不建议直接进入主力环境，应先在隔离环境试装。\n\n### 30 秒判断\n\n- **现在怎么做**：仅建议沙盒试装\n- **最小安全下一步**：先跑 Prompt Preview；若仍要安装，只在隔离环境试装\n- **先别相信**：真实输出质量不能在安装前相信。\n- **继续会触碰**：命令执行、本地环境或项目文件、宿主 AI 上下文\n\n### 现在可以相信\n\n- **适合人群线索：想在安装前理解开源项目价值和边界的用户**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0002` supported 0.86\n- **能力存在：命令行启动或安装流程**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`README.md` Claim：`clm_0001` supported 0.86\n- **存在 Quick Start / 安装命令线索**（supported）：可以相信项目文档出现过启动或安装入口；不要因此直接在主力环境运行。 证据：`README.md` Claim：`clm_0003` supported 0.86\n\n### 现在还不能相信\n\n- **真实输出质量不能在安装前相信。**（unverified）：Prompt Preview 只能展示引导方式，不能证明真实项目中的结果质量。\n- **宿主 AI 版本兼容性不能在安装前相信。**（unverified）：Claude、Cursor、Codex、Gemini 等宿主加载规则和版本差异必须在真实环境验证。\n- **不会污染现有宿主 AI 行为，不能直接相信。**（inferred）：Skill、plugin、AGENTS/CLAUDE/GEMINI 指令可能改变宿主 AI 的默认行为。\n- **可安全回滚不能默认相信。**（unverified）：除非项目明确提供卸载和恢复说明，否则必须先在隔离环境验证。\n- **真实安装后是否与用户当前宿主 AI 版本兼容？**（unverified）：兼容性只能通过实际宿主环境验证。\n- **项目输出质量是否满足用户具体任务？**（unverified）：安装前预览只能展示流程和边界，不能替代真实评测。\n- **安装命令是否需要网络、权限或全局写入？**（unverified）：这影响企业环境和个人环境的安装风险。 证据：`README.md`\n\n### 继续会触碰什么\n\n- **命令执行**：包管理器、网络下载、本地插件目录、项目配置或用户主目录。 原因：运行第一条命令就可能产生环境改动；必须先判断是否值得跑。 证据：`README.md`\n- **本地环境或项目文件**：安装结果、插件缓存、项目配置或本地依赖目录。 原因：安装前无法证明写入范围和回滚方式，需要隔离验证。 证据：`README.md`\n- **宿主 AI 上下文**：AI Context Pack、Prompt Preview、Skill 路由、风险规则和项目事实。 原因：导入上下文会影响宿主 AI 后续判断，必须避免把未验证项包装成事实。\n\n### 最小安全下一步\n\n- **先跑 Prompt Preview**：用安装前交互式试用判断工作方式是否匹配，不需要授权或改环境。（适用：任何项目都适用，尤其是输出质量未知时。）\n- **只在隔离目录或测试账号试装**：避免安装命令污染主力宿主 AI、真实项目或用户主目录。（适用：存在命令执行、插件配置或本地写入线索时。）\n- **安装后只验证一个最小任务**：先验证加载、兼容、输出质量和回滚，再决定是否深用。（适用：准备从试用进入真实工作流时。）\n\n### 退出方式\n\n- **保留安装前状态**：记录原始宿主配置和项目状态，后续才能判断是否可恢复。\n- **记录安装命令和写入路径**：没有明确卸载说明时，至少要知道哪些目录或配置需要手动清理。\n- **如果没有回滚路径，不进入主力环境**：不可回滚是继续前阻断项，不应靠信任或运气继续。\n\n## 哪些只能预览\n\n- 解释项目适合谁和能做什么\n- 基于项目文档演示典型对话流程\n- 帮助用户判断是否值得安装或继续研究\n\n## 哪些必须安装后验证\n\n- 真实安装 Skill、插件或 CLI\n- 执行脚本、修改本地文件或访问外部服务\n- 验证真实输出质量、性能和兼容性\n\n## 边界与风险判断卡\n\n- **把安装前预览误认为真实运行**：用户可能高估项目已经完成的配置、权限和兼容性验证。 处理方式：明确区分 prompt_preview_can_do 与 runtime_required。 Claim：`clm_0005` inferred 0.45\n- **命令执行会修改本地环境**：安装命令可能写入用户主目录、宿主插件目录或项目配置。 处理方式：先在隔离环境或测试账号中运行。 证据：`README.md` Claim：`clm_0006` supported 0.86\n- **待确认**：真实安装后是否与用户当前宿主 AI 版本兼容？。原因：兼容性只能通过实际宿主环境验证。\n- **待确认**：项目输出质量是否满足用户具体任务？。原因：安装前预览只能展示流程和边界，不能替代真实评测。\n- **待确认**：安装命令是否需要网络、权限或全局写入？。原因：这影响企业环境和个人环境的安装风险。\n\n## 开工前工作上下文\n\n### 加载顺序\n\n- 先读取 how_to_use.host_ai_instruction，建立安装前判断资产的边界。\n- 读取 claim_graph_summary，确认事实来自 Claim/Evidence Graph，而不是 Human Wiki 叙事。\n- 再读取 intended_users、capabilities 和 quick_start_candidates，判断用户是否匹配。\n- 需要执行具体任务时，优先查 role_skill_index，再查 evidence_index。\n- 遇到真实安装、文件修改、网络访问、性能或兼容性问题时，转入 risk_card 和 boundaries.runtime_required。\n\n### 任务路由\n\n- **命令行启动或安装流程**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`README.md` Claim：`clm_0001` supported 0.86\n\n### 上下文规模\n\n- 文件总数：733\n- 重要文件覆盖：40/733\n- 证据索引条目：53\n- 角色 / Skill 条目：5\n\n### 证据不足时的处理\n\n- **missing_evidence**：说明证据不足，要求用户提供目标文件、README 段落或安装后验证记录；不要补全事实。\n- **out_of_scope_request**：说明该任务超出当前 AI Context Pack 证据范围，并建议用户先查看 Human Manual 或真实安装后验证。\n- **runtime_request**：给出安装前检查清单和命令来源，但不要替用户执行命令或声称已执行。\n- **source_conflict**：同时展示冲突来源，标记为待核实，不要强行选择一个版本。\n\n## Prompt Recipes\n\n### 适配判断\n\n- 目标：判断这个项目是否适合用户当前任务。\n- 预期输出：适配结论、关键理由、证据引用、安装前可预览内容、必须安装后验证内容、下一步建议。\n\n```text\n请基于 deepchecks 的 AI Context Pack，先问我 3 个必要问题，然后判断它是否适合我的任务。回答必须包含：适合谁、能做什么、不能做什么、是否值得安装、证据来自哪里。所有项目事实必须引用 evidence_refs、source_paths 或 claim_id。\n```\n\n### 安装前体验\n\n- 目标：让用户在安装前感受核心工作流，同时避免把预览包装成真实能力或营销承诺。\n- 预期输出：一段带边界标签的体验剧本、安装后验证清单和谨慎建议；不含真实运行承诺或强营销表述。\n\n```text\n请把 deepchecks 当作安装前体验资产，而不是已安装工具或真实运行环境。\n\n请严格输出四段：\n1. 先问我 3 个必要问题。\n2. 给出一段“体验剧本”：用 [安装前可预览]、[必须安装后验证]、[证据不足] 三种标签展示它可能如何引导工作流。\n3. 给出安装后验证清单：列出哪些能力只有真实安装、真实宿主加载、真实项目运行后才能确认。\n4. 给出谨慎建议：只能说“值得继续研究/试装”“先补充信息后再判断”或“不建议继续”，不得替项目背书。\n\n硬性边界：\n- 不要声称已经安装、运行、执行测试、修改文件或产生真实结果。\n- 不要写“自动适配”“确保通过”“完美适配”“强烈建议安装”等承诺性表达。\n- 如果描述安装后的工作方式，必须使用“如果安装成功且宿主正确加载 Skill，它可能会……”这种条件句。\n- 体验剧本只能写成“示例台词/假设流程”：使用“可能会询问/可能会建议/可能会展示”，不要写“已写入、已生成、已通过、正在运行、正在生成”。\n- Prompt Preview 不负责给安装命令；如用户准备试装，只能提示先阅读 Quick Start 和 Risk Card，并在隔离环境验证。\n- 所有项目事实必须来自 supported claim、evidence_refs 或 source_paths；inferred/unverified 只能作风险或待确认项。\n\n```\n\n### 角色 / Skill 选择\n\n- 目标：从项目里的角色或 Skill 中挑选最匹配的资产。\n- 预期输出：候选角色或 Skill 列表，每项包含适用场景、证据路径、风险边界和是否需要安装后验证。\n\n```text\n请读取 role_skill_index，根据我的目标任务推荐 3-5 个最相关的角色或 Skill。每个推荐都要说明适用场景、可能输出、风险边界和 evidence_refs。\n```\n\n### 风险预检\n\n- 目标：安装或引入前识别环境、权限、规则冲突和质量风险。\n- 预期输出：环境、权限、依赖、许可、宿主冲突、质量风险和未知项的检查清单。\n\n```text\n请基于 risk_card、boundaries 和 quick_start_candidates，给我一份安装前风险预检清单。不要替我执行命令，只说明我应该检查什么、为什么检查、失败会有什么影响。\n```\n\n### 宿主 AI 开工指令\n\n- 目标：把项目上下文转成一次对话开始前的宿主 AI 指令。\n- 预期输出：一段边界明确、证据引用明确、适合复制给宿主 AI 的开工前指令。\n\n```text\n请基于 deepchecks 的 AI Context Pack，生成一段我可以粘贴给宿主 AI 的开工前指令。这段指令必须遵守 not_runtime=true，不能声称项目已经安装、运行或产生真实结果。\n```\n\n\n## 角色 / Skill 索引\n\n- 共索引 5 个角色 / Skill / 项目文档条目。\n\n- **🧩 Components**（project_doc）：. ~ ---------------------------------------------------------------------------- ~ -- 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`README.md`\n- **Reference Issues/PRs**（project_doc）：Example: Fixes 1234. See also 3456. Please use keywords e.g., Fixes to create link to the issues or pull requests you resolved, so that they will automatically be closed when your pull request is merged. See https://github.com/blog/1506-closing-issues-via-pull-requests 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`.github/pull_request_template.md`\n- **Contributor Covenant Code of Conduct**（project_doc）：. ~ ---------------------------------------------------------------------------- ~ -- 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`CODE_OF_CONDUCT.md`\n- **Bug report**（project_doc）：Describe the bug A clear and concise description of what the bug is. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`.github/ISSUE_TEMPLATE/bug_report.md`\n- **Feature request**（project_doc）：Is your feature request related to a problem? Please describe. A clear and concise description of what the problem is. Ex. I'm always frustrated when ... 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`.github/ISSUE_TEMPLATE/feature_request.md`\n\n## 证据索引\n\n- 共索引 53 条证据。\n\n- **🧩 Components**（documentation）：. ~ ---------------------------------------------------------------------------- ~ -- 证据：`README.md`\n- **License**（source_file）：Deepchecks Continuous Validation and Testing for ML Models & Data 证据：`LICENSE`\n- **Reference Issues/PRs**（documentation）：Example: Fixes 1234. See also 3456. Please use keywords e.g., Fixes to create link to the issues or pull requests you resolved, so that they will automatically be closed when your pull request is merged. See https://github.com/blog/1506-closing-issues-via-pull-requests 证据：`.github/pull_request_template.md`\n- **Contributor Covenant Code of Conduct**（documentation）：. ~ ---------------------------------------------------------------------------- ~ -- 证据：`CODE_OF_CONDUCT.md`\n- **Bug Report**（documentation）：Describe the bug A clear and concise description of what the bug is. 证据：`.github/ISSUE_TEMPLATE/bug_report.md`\n- **Feature Request**（documentation）：Is your feature request related to a problem? Please describe. A clear and concise description of what the problem is. Ex. I'm always frustrated when ... 证据：`.github/ISSUE_TEMPLATE/feature_request.md`\n- **Asv.Conf**（structured_config）：// ---------------------------------------------------------------------------- // Copyright C 2021-2023 Deepchecks https://www.deepchecks.com // // This file is part of Deepchecks. // Deepchecks is distributed under the terms of the GNU Affero General // Public License version 3 or later . // You should have received a copy of the GNU Affero General Public License // along with Deepchecks. If not, see . // ---------------------------------------------------------------------------- // { // The version of the config file format. Do not change, unless // you know what you are doing. \"version\": 1, 证据：`benchmarks/asv.conf.json`\n- **Switcher**（structured_config）：{ \"version\": \"dev\", \"name\": \"dev\", \"url\": \"https://docs.deepchecks.com/dev/\" }, { \"version\": \"stable\", \"name\": \"0.18 stable \", \"url\": \"https://docs.deepchecks.com/stable/\" }, { \"version\": \"0.18\", \"url\": \"https://docs.deepchecks.com/0.18/\" }, { \"version\": \"0.17\", \"url\": \"https://docs.deepchecks.com/0.17/\" }, { \"version\": \"0.14\", \"url\": \"https://docs.deepchecks.com/0.14/\" }, { \"version\": \"0.13\", \"url\": \"https://docs.deepchecks.com/0.13/\" }, { \"version\": \"0.12\", \"url\": \"https://docs.deepchecks.com/0.12/\" }, { \"version\": \"0.11\", \"url\": \"https://docs.deepchecks.com/0.11/\" }, { \"version\": \"0.10\", \"url\": \"https://docs.deepchecks.com/0.10/\" } 证据：`docs/source/_static/switcher.json`\n- **.all-contributorsrc**（source_file）：{ \"files\": \"README.md\" , \"skipCi\": \"true\", \"imageSize\": 100, \"contributorsPerLine\": 7, \"contributors\": { \"login\": \"ItayGabbay\", \"name\": \"Itay Gabbay\", \"avatar url\": \"https://avatars.githubusercontent.com/u/20860465?v=4\", \"profile\": \"https://github.com/ItayGabbay\", \"contributions\": \"code\", \"doc\", \"ideas\" }, { \"login\": \"matanper\", \"name\": \"matanper\", \"avatar url\": \"https://avatars.githubusercontent.com/u/9868530?v=4\", \"profile\": \"https://github.com/matanper\", \"contributions\": \"doc\", \"ideas\", \"code\" }, { \"login\": \"JKL98ISR\", \"name\": \"JKL98ISR\", \"avatar url\": \"https://avatars.githubusercontent.com/u/26321553?v=4\", \"profile\": \"https://github.com/JKL98ISR\", \"contributions\": \"ideas\", \"code\", \"doc\"… 证据：`.all-contributorsrc`\n- **This is a comment.**（source_file）：This is a comment. Each line is a file pattern followed by one or more owners. 证据：`.github/CODEOWNERS`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- history/ 证据：`.gitignore`\n- **.Licenserc Fix**（source_file）：header: license: spdx-id: AGPL-3.0-only copyright-owner: Deepchecks content: ---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com 证据：`.licenserc_fix.yaml`\n- **This Pylint rcfile contains a best-effort configuration to uphold the**（source_file）：This Pylint rcfile contains a best-effort configuration to uphold the best-practices and style described in the Google Python style guide: https://google.github.io/styleguide/pyguide.html Its canonical open-source location is: https://google.github.io/styleguide/pylintrc 证据：`.pylintrc`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- .readthedocs.yaml Read the Docs configuration file See https://docs.readthedocs.io/en/stable/config-file/v2.html for details 证据：`.readthedocs.yaml`\n- **About**（source_file）：. ~ ---------------------------------------------------------------------------- ~ -- 证据：`ABOUT.rst`\n- **Citation**（source_file）：cff-version: 1.2.0 title: \"Deepchecks: A Library for Testing and Validating Machine Learning Models and Data\" message: \"If you use this software, please cite it using the metadata from this file.\" type: software authors: - family-names: Chorev given-names: Shir email: shir@deepchecks.com affiliation: Deepchecks Ltd. - family-names: Tannor given-names: Philip email: philip@deepchecks.com affiliation: Deepchecks Ltd. - family-names: Ben Israel given-names: Dan email: danb@deepchecks.com affiliation: Deepchecks Ltd. - family-names: Bressler given-names: Noam email: noam@deepchecks.com affiliation: Deepchecks Ltd. - family-names: Gabbay given-names: Itay email: itay@deepchecks.com affiliation:… 证据：`CITATION.cff`\n- **Execute NLP tests**（source_file）：. ~ ---------------------------------------------------------------------------- ~ -- 证据：`CONTRIBUTING.rst`\n- **Description**（source_file）：build pkgVersion pyVersions Maintainability Coverage Status 证据：`DESCRIPTION.rst`\n- **Faq**（source_file）：. ~ ---------------------------------------------------------------------------- ~ -- 证据：`FAQ.rst`\n- **Manifest**（source_file）：include requirements/requirements.txt include requirements/vision-requirements.txt include requirements/nlp-requirements.txt include requirements/dev-requirements.txt include requirements/nlp-prop-requirements.txt include LICENSE include VERSION include README.md include DESCRIPTION.rst recursive-include deepchecks/core/resources recursive-include deepchecks/vision/fonts recursive-include deepchecks/vision/datasets/assets 证据：`MANIFEST.in`\n- **Version**（source_file）：0.18.0.dev1 证据：`VERSION`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- 证据：`benchmarks/__init__.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- import inspect from typing import Callable 证据：`benchmarks/tabular_bench.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- from typing import Callable 证据：`benchmarks/vision_bench.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- {% set data = load setup py data %} 证据：`conda-recipe/meta.yaml`\n- **This file contains a list of match patterns that instructs**（source_file）：This file contains a list of match patterns that instructs anaconda-project to exclude certain files or directories when building a project archive. The file format is a simplfied version of Git's .gitignore file format. In fact, if the project is hosted in a Git repository, these patterns can be merged into the .gitignore file and this file removed. See the anaconda-project documentation for more details. 证据：`deepchecks/.projectignore`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- \"\"\"Deepchecks.\"\"\" import os import sys import types import warnings from importlib. bootstrap import init module attrs 证据：`deepchecks/__init__.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- \"\"\"Alternative way to import tabular checks. 证据：`deepchecks/checks.py`\n- **Copied from https://github.com/8080labs/ppscore, version 1.2.0**（source_file）：\"\"\"PPS Predictive Power Score module.\"\"\" 证据：`deepchecks/ppscore.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- \"\"\"Alternative way to import tabular suites. 证据：`deepchecks/suites.py`\n- **links within plotly js scripts**（source_file）：^https://www\\.googletagmanager\\.com/gtm\\.js\\?id=$ ^. static/. pathto\\ ' static/. $ ^. split\\ n\\.wrapSplitCharacter\\ . $ 证据：`docs/.lycheeignore`\n- **Minimal makefile for Sphinx documentation**（source_file）：Minimal makefile for Sphinx documentation 证据：`docs/Makefile`\n- **ipywidgets @ git+https://github.com/deepchecks/ipywidgets.git@8ac487b64ffd48dbeaa0a47d1997be27f6052dbc**（source_file）：sphinx==4.5.0 nbsphinx =0.8.7 pydata-sphinx-theme =0.7.2, =0.4.0 sphinx-gallery =0.10.1, =1.0.2, =1.0.2, =2.0.0, =1.0.3, =1.1.5, =1.1.0 pypandoc =1.7.2 sphinx-reredirects =0.0.1 sphinx-design =0.3.0 ipywidgets @ git+https://github.com/deepchecks/ipywidgets.git@8ac487b64ffd48dbeaa0a47d1997be27f6052dbc docutils 证据：`docs/requirements.txt`\n- **Readme**（source_file）：Open from Docs - Recommended ============================== 证据：`examples/README.rst`\n- **Passing strings example**（source_file）：Passing strings example from deepchecks.tabular.checks import TrainTestPerformance from deepchecks.tabular.datasets.classification import adult train ds, test ds = adult.load data data format='Dataset', as train test=True model = adult.load fitted model 证据：`examples/examples_metrics_guide.py`\n- **In classification, predicted values can be supplied via the y pred train, y pred test**（source_file）：from deepchecks.tabular.datasets.classification.iris import load data, load fitted model from deepchecks.tabular.suites import model evaluation 证据：`examples/examples_supported_models.py`\n- **Requirements Extensive Tests**（source_file）：catboost xgboost boto3 fsspec s3fs joblib 证据：`extensive_testing/requirements_extensive-tests.txt`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- \"\"\"Runs extensive tests for all checks in suites using the datasets & models in deepchecks-extensive-test-assets\"\"\" import json import pprint import sys import time from io import BytesIO 证据：`extensive_testing/run_extensive_tests.py`\n- **MIT**（source_file）：Licenses authorized licenses: bsd new bsd bsd license new bsd license simplified bsd BSD 3-Clause BSD-3-Clause 2-clause BSD BSD-2-Clause 证据：`liccheck.ini`\n- **This makefile helps with deepchecks Development environment**（source_file）：This makefile helps with deepchecks Development environment including syntax checking, virtual environments creation, test running and coverage This Makefile is based on Makefile by jidn: https://github.com/jidn/python-Makefile/blob/master/Makefile 证据：`makefile`\n- **NLP**（source_file）：NLP nltk =3.8.1; python version = '3.7' not directly required, pinned by Snyk to avoid a vulnerability datasets textblob transformers =4.0.0 sentence transformers =3.0.0 证据：`requirements/dev-nlp-requirements.txt`\n- **pandas 1.3.5 is the last version to support Python 3.7**（source_file）：pylint==2.13.5 pydocstyle flake8==4.0.1 flake8-spellcheck flake8-eradicate flake8-rst isort 证据：`requirements/dev-requirements.txt`\n- **Nlp Prop Requirements**（source_file）：fasttext-wheel =0.8.0, <0.9.3 证据：`requirements/nlp-prop-requirements.txt`\n- **Nlp Requirements**（source_file）：seqeval =1.0.0 nltk =3.8.1; python version = '3.7' not directly required, pinned by Snyk to avoid a vulnerability textblob =0.17.1 umap-learn transformers =4.0.0 huggingface hub sentence transformers =3.0.0, = '3.8' 证据：`requirements/nlp-requirements.txt`\n- **require for python 3.8+**（source_file）：pandas =1.1.5 numpy =1.19; python version =1.22.2; python version = '3.8' scikit-learn =0.23.2 jsonpickle =2 PyNomaly==0.3.4 证据：`requirements/requirements.txt`\n- **Vision Requirements**（source_file）：pytorch-ignite =0.4.8 opencv-python =4.5.5.62 albumentations =1.1.0, =0.4.0 seaborn =0.1.0 imagehash =4.0.0 lxml =4.0.0 证据：`requirements/vision-requirements.txt`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- import pathlib import re import typing as t from functools import lru cache 证据：`setup.py`\n- **Spelling Allowlist**（source_file）：pylint Deepchecks deepchecks Affero Dataframe dataframe MLC 0E ipython colorbar reproducibility dataset Dataset iqr IQR unsubscriptable chi2 C0103 2D 3D 4D Matplotlib backends params PCA ppscore encodings plotly Multiclass numpy sklearn proba dtypes groupby r2 tqdm nan nans kaggle colab CategoryMismatchTrainTest datasets VisionDataset num bboxes yolo ultralytics Detections xyxy pred bbox gts dt dts dets albumentations overridded repo heatmap grayscale RGB preprocessors PIL yolo Detections xyxy pred formatters formatter imgs cv2 quantile quantiles toplevel ious renormalization jsonpickle dtype dataloader KDE renderers NotebookRenderer requirejs CDN CustomNotebookRenderer Wandb hotfix pyplot… 证据：`spelling-allowlist.txt`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- 证据：`tests/__init__.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- pylint: disable=unused-wildcard-import, wildcard-import \"\"\"Common functions.\"\"\" import typing as t 证据：`tests/common.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- \"\"\"Represents fixtures for unit testing using pytest.\"\"\" import logging import random pylint: skip-file from typing import Tuple 证据：`tests/conftest.py`\n- **----------------------------------------------------------------------------**（source_file）：---------------------------------------------------------------------------- Copyright C 2021-2023 Deepchecks https://www.deepchecks.com This file is part of Deepchecks. Deepchecks is distributed under the terms of the GNU Affero General Public License version 3 or later . You should have received a copy of the GNU Affero General Public License along with Deepchecks. If not, see . ---------------------------------------------------------------------------- import inspect import os import sys from urllib.parse import urlparse 证据：`tests/examples_validation.py`\n- **install pytest in the virtualenv where commands will be executed**（source_file）：; ---------------------------------------------------------------------------- ; Copyright C 2021-2023 Deepchecks https://www.deepchecks.com ; ; This file is part of Deepchecks. ; Deepchecks is distributed under the terms of the GNU Affero General ; Public License version 3 or later . ; You should have received a copy of the GNU Affero General Public License ; along with Deepchecks. If not, see . ; ---------------------------------------------------------------------------- ; tox envlist = python36,python37,python38,python39,python310 证据：`tox.ini`\n\n## 宿主 AI 必须遵守的规则\n\n- **把本资产当作开工前上下文，而不是运行环境。**：AI Context Pack 只包含证据化项目理解，不包含目标项目的可执行状态。 证据：`README.md`, `LICENSE`, `.github/pull_request_template.md`\n- **回答用户时区分可预览内容与必须安装后才能验证的内容。**：安装前体验的消费者价值来自降低误装和误判，而不是伪装成真实运行。 证据：`README.md`, `LICENSE`, `.github/pull_request_template.md`\n\n## 用户开工前应该回答的问题\n\n- 你准备在哪个宿主 AI 或本地环境中使用它？\n- 你只是想先体验工作流，还是准备真实安装？\n- 你最在意的是安装成本、输出质量、还是和现有规则的冲突？\n\n## 验收标准\n\n- 所有能力声明都能回指到 evidence_refs 中的文件路径。\n- AI_CONTEXT_PACK.md 没有把预览包装成真实运行。\n- 用户能在 3 分钟内看懂适合谁、能做什么、如何开始和风险边界。\n\n---\n\n## Doramagic Context Augmentation\n\n下面内容用于强化 Repomix/AI Context Pack 主体。Human Manual 只提供阅读骨架；踩坑日志会被转成宿主 AI 必须遵守的工作约束。\n\n## Human Manual 骨架\n\n使用规则：这里只是项目阅读路线和显著性信号，不是事实权威。具体事实仍必须回到 repo evidence / Claim Graph。\n\n宿主 AI 硬性规则：\n- 不得把页标题、章节顺序、摘要或 importance 当作项目事实证据。\n- 解释 Human Manual 骨架时，必须明确说它只是阅读路线/显著性信号。\n- 能力、安装、兼容性、运行状态和风险判断必须引用 repo evidence、source path 或 Claim Graph。\n\n- **仓库概览**：importance `high`\n  - source_paths: README.md, docs/requirements.txt, requirements/requirements.txt, docs/source/api/deepchecks.core.rst, docs/source/api/deepchecks.nlp.checks.rst\n- **入口与运行边界**：importance `high`\n  - source_paths: README.md, docs/requirements.txt, requirements/requirements.txt, docs/source/api/deepchecks.core.rst, docs/source/api/deepchecks.nlp.checks.rst\n- **架构证据地图**：importance `high`\n  - source_paths: README.md, docs/requirements.txt, requirements/requirements.txt, docs/source/api/deepchecks.core.rst, docs/source/api/deepchecks.nlp.checks.rst\n- **运维与验证边界**：importance `high`\n  - source_paths: README.md, docs/requirements.txt, requirements/requirements.txt, docs/source/api/deepchecks.core.rst, docs/source/api/deepchecks.nlp.checks.rst\n\n## Repo Inspection Evidence / 源码检查证据\n\n- repo_clone_verified: true\n- repo_inspection_verified: true\n- repo_commit: `98475d17b08a21fca29d533b94b8ec3c70544a85`\n- inspected_files: `README.md`, `docs/source/conf.py`, `docs/source/_static/switcher.json`, `docs/source/tabular/tutorials/quickstarts/plot_quick_model_evaluation.py`, `docs/source/tabular/tutorials/quickstarts/plot_quick_data_integrity.py`, `docs/source/tabular/tutorials/quickstarts/plot_quick_train_test_validation.py`, `docs/source/tabular/tutorials/quickstarts/plot_quickstart_in_5_minutes.py`, `docs/source/tabular/tutorials/other/plot_add_a_custom_check.py`, `docs/source/tabular/tutorials/other/plot_phishing_urls.py`, `docs/source/general/usage/customizations/plot_configure_check_conditions.py`, `docs/source/general/usage/customizations/plot_create_a_custom_suite.py`, `docs/source/general/usage/customizations/plot_create_a_custom_check.py`, `docs/source/general/usage/exporting_results/plot_export_suite_results_as_html.py`, `docs/source/general/usage/exporting_results/plot_exports_output_to_wandb.py`, `docs/source/general/usage/exporting_results/plot_export_outputs_to_json.py`, `docs/source/checks/tabular/data_integrity/plot_string_length_out_of_bounds.py`, `docs/source/checks/tabular/data_integrity/plot_special_chars.py`, `docs/source/checks/tabular/data_integrity/plot_string_mismatch.py`, `docs/source/checks/tabular/data_integrity/plot_data_duplicates.py`, `docs/source/checks/tabular/data_integrity/plot_percent_of_nulls.py`\n\n宿主 AI 硬性规则：\n- 没有 repo_clone_verified=true 时，不得声称已经读过源码。\n- 没有 repo_inspection_verified=true 时，不得把 README/docs/package 文件判断写成事实。\n- 没有 quick_start_verified=true 时，不得声称 Quick Start 已跑通。\n\n## Doramagic Pitfall Constraints / 踩坑约束\n\n这些规则来自 Doramagic 发现、验证或编译过程中的项目专属坑点。宿主 AI 必须把它们当作工作约束，而不是普通说明文字。\n\n### Constraint 1: 来源证据：Blank html page after saving report using `save_as_html`\n\n- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Blank html page after saving report using `save_as_html`\n- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_492bcbfbeaac498b94f2f869074b9edc | https://github.com/deepchecks/deepchecks/issues/2803 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 2: 来源证据：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n\n- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_4bac6c577dee471fa096434516861696 | https://github.com/deepchecks/deepchecks/issues/2794 | 来源类型 github_issue 暴露的待验证使用条件。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 3: 来源证据：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n\n- Trigger: GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_b9f771df5da2458d9e368765d829e5c7 | https://github.com/deepchecks/deepchecks/issues/2789 | 来源类型 github_issue 暴露的待验证使用条件。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 4: 来源证据：Feature Request: EU AI Act compliance mapping for validation checks\n\n- Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Feature Request: EU AI Act compliance mapping for validation checks\n- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_aaa0c0bcbdbf41d6855980523e0d7682 | https://github.com/deepchecks/deepchecks/issues/2813 | 来源类型 github_issue 暴露的待验证使用条件。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 5: 来源证据：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution…\n\n- Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution Proposed.\n- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- Why it matters: 可能影响授权、密钥配置或安全边界。\n- Evidence: community_evidence:github | cevd_edf8cf14dc8f49898cbcab292f3abbeb | https://github.com/deepchecks/deepchecks/issues/2802 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 6: 来源证据：0.18.0\n\n- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.0\n- Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_4789fb40d7364096958752494c3054a2 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.0 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 7: 来源证据：0.18.1\n\n- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.1\n- Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_53c2c4845d134a54b0989b29725c1c93 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.1 | 来源类型 github_release 暴露的待验证使用条件。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 8: 来源证据：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n\n- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_e24dd97e69674ab2b766fef25a401070 | https://github.com/deepchecks/deepchecks/issues/2812 | 来源类型 github_issue 暴露的待验证使用条件。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 9: 来源证据：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n\n- Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n- Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- Why it matters: 可能影响升级、迁移或版本选择。\n- Evidence: community_evidence:github | cevd_6e307650606b4ed380c4adc96caa8c28 | https://github.com/deepchecks/deepchecks/issues/2806 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n\n### Constraint 10: 来源证据：0.17.3\n\n- Trigger: GitHub 社区证据显示该项目存在一个配置相关的待验证问题：0.17.3\n- Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- Why it matters: 可能增加新用户试用和生产接入成本。\n- Evidence: community_evidence:github | cevd_b64249b0551146afb696a981f404b3e6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.3 | 来源类型 github_release 暴露的待验证使用条件。\n- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。\n",
      "summary": "给宿主 AI 的上下文和工作边界。",
      "title": "AI Context Pack / 带给我的 AI"
    },
    "boundary_risk_card": {
      "asset_id": "boundary_risk_card",
      "filename": "BOUNDARY_RISK_CARD.md",
      "markdown": "# Boundary & Risk Card / 安装前决策卡\n\n项目：deepchecks/deepchecks\n\n## Doramagic 试用结论\n\n当前结论：可以进入发布前推荐检查；首次使用仍应从最小权限、临时目录和可回滚配置开始。\n\n## 用户现在可以做\n\n- 可以先阅读 Human Manual，理解项目目的和主要工作流。\n- 可以复制 Prompt Preview 做安装前体验；这只验证交互感，不代表真实运行。\n- 可以把官方 Quick Start 命令放到隔离环境中验证，不要直接进主力环境。\n\n## 现在不要做\n\n- 不要把 Prompt Preview 当成项目实际运行结果。\n- 不要把 metadata-only validation 当成沙箱安装验证。\n- 不要把未验证能力写成“已支持、已跑通、可放心安装”。\n- 不要在首次试用时交出生产数据、私人文件、真实密钥或主力配置目录。\n\n## 安装前检查\n\n- 宿主 AI 是否匹配：local_cli\n- 官方安装入口状态：已发现官方入口\n- 是否在临时目录、临时宿主或容器中验证：必须是\n- 是否能回滚配置改动：必须能\n- 是否需要 API Key、网络访问、读写文件或修改宿主配置：未确认前按高风险处理\n- 是否记录了安装命令、实际输出和失败日志：必须记录\n\n## 当前阻塞项\n\n- 无阻塞项。\n\n## 项目专属踩坑\n\n- 来源证据：Blank html page after saving report using `save_as_html`（high）：可能增加新用户试用和生产接入成本。 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 来源证据：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered（high）：可能增加新用户试用和生产接入成本。 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 来源证据：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift（high）：可能增加新用户试用和生产接入成本。 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 来源证据：Feature Request: EU AI Act compliance mapping for validation checks（high）：可能增加新用户试用和生产接入成本。 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 来源证据：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution…（high）：可能影响授权、密钥配置或安全边界。 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n\n## 风险与权限提示\n\n- no_demo: medium\n\n## 证据缺口\n\n- 暂未发现结构化证据缺口。\n",
      "summary": "安装、权限、验证和推荐前风险。",
      "title": "Boundary & Risk Card / 边界与风险卡"
    },
    "human_manual": {
      "asset_id": "human_manual",
      "filename": "HUMAN_MANUAL.md",
      "markdown": "# https://github.com/deepchecks/deepchecks 项目说明书\n\n生成时间: 2026-05-21 08:39:22 UTC\n\n## 目录\n\n- [仓库概览](#overview)\n- [入口与运行边界](#entrypoints)\n- [架构证据地图](#architecture)\n- [运维与验证边界](#operations)\n\n<a id='overview'></a>\n\n## 仓库概览\n\n### 相关页面\n\n相关主题：[入口与运行边界](#entrypoints), [架构证据地图](#architecture), [运维与验证边界](#operations)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 仓库概览\n\n本页在 Human Wiki provider 不可用时基于仓库证据生成，只使用 README、文件树和已选源码文件，不把模板描述冒充项目事实。\n\n## README 证据\n\n<!--\n   ~ ----------------------------------------------------------------------------\n   ~ Copyright (C) 2021-2023 Deepchecks (https://www.deepchecks.com)\n   ~\n   ~ This file is part of Deepchecks.\n   ~ Deepchecks is distributed under the terms of the GNU Affero General\n   ~ Public License (version 3 or later).\n   ~ You should have received a copy of the GNU Affero General Public License\n   ~ along with Deepchecks.  If not, see <http://www.gnu.org/licenses/>.\n   ~ ----------------------------------------------------------------------------\n   ~\n-->\n\n[![GitHub\nstars](https://img.shields.io/github/stars/deepchecks/deepchecks.svg?style=social&label=Star&maxAge=2592000)](https://GitHub.com/deepchecks/deepchecks/stargazers/)\n![build](https://github.com/deepchecks/deepchecks/actions/workflows/build.yml/badge.svg)\n![pkgVersion](https://img.shields.io/pypi/v/deepchecks)\n[![Coverage\nStatus](https://coveralls.io/repos/github/deepchecks/deepchecks/badge.svg?branch=main)](https://coveralls.io/github/deepchecks/deepchecks?branch=main) \n<!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->\n[![All Contributors](https://img.shields.io/badge/all_contributors-44-orange.svg?style=flat-round)](#https://github.com/deepchecks/deepchecks/blob/main/CONTRIBUTING.rst)\n<!-- ALL-CONTRIBUTORS-BADGE:END --> \n\n<!---\nthis badge takes quite some space, can re-add it if wanted\n![pyVersions](https://img.shields.io/pypi/pyversions/deepchecks)\n--->\n\n<h1 align=\"center\">\n   Deepchecks - Continuous Validation for AI & ML: Testing, CI & Monitoring\n</h1>\n\nDeepchecks is a holistic open-source solution for all of your AI & ML validation needs,\nenabling you to thoroughly test your data and models from research to production.\n\n<a target=\"_blank\" href=\"https://docs.deepchecks.com/?utm_source=github.com&utm_medium=referral&utm_campaign=readme&utm_content=logo\">\n   <picture>\n      <source media=\"(prefers-color-scheme: dark)\" srcset=\"docs/source/_static/images/readme/deepchecks_continuous_validation_dark.png\">\n      <source media=\"(prefers-color-scheme: light)\" srcset=\"docs/source/_static/images/readme/deepchecks_continuous_validation_light.png\">\n      <img alt=\"Deepchecks continuous validation parts.\" src=\"docs/source/_static/images//readme/deepchecks_continuous_validation_light.png\">\n   </picture>\n</a>\n\n<p align=\"center\">\n   &emsp;\n   <a href=\"https://www.deepchecks.com/slack\">👋 Jo\n\n[excerpt truncated]\n\n## 已选源码清单\n\n- `README.md`\n- `docs/requirements.txt`\n- `requirements/requirements.txt`\n- `docs/source/api/deepchecks.core.rst`\n- `docs/source/api/deepchecks.nlp.checks.rst`\n- `docs/source/api/deepchecks.nlp.rst`\n- `docs/source/api/deepchecks.nlp.suites.rst`\n- `docs/source/api/deepchecks.tabular.checks.rst`\n- `docs/source/api/deepchecks.tabular.rst`\n- `docs/source/api/deepchecks.tabular.suites.rst`\n- `docs/source/api/deepchecks.utils.rst`\n- `docs/source/api/deepchecks.vision.checks.rst`\n\n| 文件 | 证据角色 | 大小 |\n|---|---|---|\n| `README.md` | README/产品与使用证据 | 31857 bytes |\n| `docs/requirements.txt` | 仓库证据 | 557 bytes |\n| `requirements/requirements.txt` | 仓库证据 | 998 bytes |\n| `docs/source/api/deepchecks.core.rst` | 实现边界 | 459 bytes |\n| `docs/source/api/deepchecks.nlp.checks.rst` | 实现边界 | 268 bytes |\n| `docs/source/api/deepchecks.nlp.rst` | 实现边界 | 669 bytes |\n| `docs/source/api/deepchecks.nlp.suites.rst` | 实现边界 | 258 bytes |\n| `docs/source/api/deepchecks.tabular.checks.rst` | 实现边界 | 280 bytes |\n| `docs/source/api/deepchecks.tabular.rst` | 实现边界 | 929 bytes |\n| `docs/source/api/deepchecks.tabular.suites.rst` | 实现边界 | 284 bytes |\n| `docs/source/api/deepchecks.utils.rst` | 实现边界 | 546 bytes |\n| `docs/source/api/deepchecks.vision.checks.rst` | 实现边界 | 278 bytes |\n\n资料来源：`[README.md:1-120]()`\n\n---\n\n<a id='entrypoints'></a>\n\n## 入口与运行边界\n\n### 相关页面\n\n相关主题：[仓库概览](#overview), [架构证据地图](#architecture), [运维与验证边界](#operations)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 入口与运行边界\n\n下面文件是安装、启动、配置或宿主集成的高信号候选。这里给出证据地图，不推断未经执行验证的 API 契约。\n\n| 文件 | 证据角色 | 大小 |\n|---|---|---|\n| `README.md` | README/产品与使用证据 | 31857 bytes |\n| `docs/requirements.txt` | 仓库证据 | 557 bytes |\n| `requirements/requirements.txt` | 仓库证据 | 998 bytes |\n| `docs/source/api/deepchecks.core.rst` | 实现边界 | 459 bytes |\n| `docs/source/api/deepchecks.nlp.checks.rst` | 实现边界 | 268 bytes |\n| `docs/source/api/deepchecks.nlp.rst` | 实现边界 | 669 bytes |\n| `docs/source/api/deepchecks.nlp.suites.rst` | 实现边界 | 258 bytes |\n| `docs/source/api/deepchecks.tabular.checks.rst` | 实现边界 | 280 bytes |\n| `docs/source/api/deepchecks.tabular.rst` | 实现边界 | 929 bytes |\n| `docs/source/api/deepchecks.tabular.suites.rst` | 实现边界 | 284 bytes |\n| `docs/source/api/deepchecks.utils.rst` | 实现边界 | 546 bytes |\n| `docs/source/api/deepchecks.vision.checks.rst` | 实现边界 | 278 bytes |\n\n资料来源：`[README.md:1-120](https://github.com/deepchecks/deepchecks/blob/main/README.md)`\n\n---\n\n<a id='architecture'></a>\n\n## 架构证据地图\n\n### 相关页面\n\n相关主题：[仓库概览](#overview), [入口与运行边界](#entrypoints), [运维与验证边界](#operations)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 架构证据地图\n\n本节只根据仓库路径组织可能的架构区域；需要运行验证的行为不会在这里断言。\n\n- `.`: `README.md`\n- `docs`: `docs/requirements.txt`, `docs/source/api/deepchecks.core.rst`, `docs/source/api/deepchecks.nlp.checks.rst`, `docs/source/api/deepchecks.nlp.rst`, `docs/source/api/deepchecks.nlp.suites.rst`, `docs/source/api/deepchecks.tabular.checks.rst`\n- `requirements`: `requirements/requirements.txt`\n\n资料来源：`[docs/requirements.txt:1-120](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)`\n\n---\n\n<a id='operations'></a>\n\n## 运维与验证边界\n\n### 相关页面\n\n相关主题：[仓库概览](#overview), [入口与运行边界](#entrypoints), [架构证据地图](#architecture)\n\n<details>\n<summary>相关源码文件</summary>\n\n以下源码文件用于生成本页说明：\n\n- [README.md](https://github.com/deepchecks/deepchecks/blob/main/README.md)\n- [docs/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/docs/requirements.txt)\n- [requirements/requirements.txt](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)\n- [docs/source/api/deepchecks.core.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.core.rst)\n- [docs/source/api/deepchecks.nlp.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.checks.rst)\n- [docs/source/api/deepchecks.nlp.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.rst)\n- [docs/source/api/deepchecks.nlp.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.nlp.suites.rst)\n- [docs/source/api/deepchecks.tabular.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.checks.rst)\n- [docs/source/api/deepchecks.tabular.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.rst)\n- [docs/source/api/deepchecks.tabular.suites.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.tabular.suites.rst)\n- [docs/source/api/deepchecks.utils.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.utils.rst)\n- [docs/source/api/deepchecks.vision.checks.rst](https://github.com/deepchecks/deepchecks/blob/main/docs/source/api/deepchecks.vision.checks.rst)\n</details>\n\n# 运维与验证边界\n\n运维建议仅来自仓库中真实存在的文件。把该项目用于 agent 工作流前，仍需在 sandbox 中验证安装、quickstart 和运行行为。\n\n- Documentation signal: `README.md`\n- Source inspection signal: `docs/requirements.txt`\n- Source inspection signal: `requirements/requirements.txt`\n- Documentation signal: `docs/source/api/deepchecks.core.rst`\n- Documentation signal: `docs/source/api/deepchecks.nlp.checks.rst`\n- Documentation signal: `docs/source/api/deepchecks.nlp.rst`\n- Documentation signal: `docs/source/api/deepchecks.nlp.suites.rst`\n- Documentation signal: `docs/source/api/deepchecks.tabular.checks.rst`\n- Documentation signal: `docs/source/api/deepchecks.tabular.rst`\n- Documentation signal: `docs/source/api/deepchecks.tabular.suites.rst`\n\n资料来源：`[requirements/requirements.txt:1-120](https://github.com/deepchecks/deepchecks/blob/main/requirements/requirements.txt)`\n\n---\n\n---\n\n## Doramagic 踩坑日志\n\n项目：deepchecks/deepchecks\n\n摘要：发现 22 个潜在踩坑项，其中 5 个为 high/blocking；最高优先级：安装坑 - 来源证据：Blank html page after saving report using `save_as_html`。\n\n## 1. 安装坑 · 来源证据：Blank html page after saving report using `save_as_html`\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Blank html page after saving report using `save_as_html`\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_492bcbfbeaac498b94f2f869074b9edc | https://github.com/deepchecks/deepchecks/issues/2803 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 2. 安装坑 · 来源证据：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_4bac6c577dee471fa096434516861696 | https://github.com/deepchecks/deepchecks/issues/2794 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 3. 维护坑 · 来源证据：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b9f771df5da2458d9e368765d829e5c7 | https://github.com/deepchecks/deepchecks/issues/2789 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 4. 安全/权限坑 · 来源证据：Feature Request: EU AI Act compliance mapping for validation checks\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Feature Request: EU AI Act compliance mapping for validation checks\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_aaa0c0bcbdbf41d6855980523e0d7682 | https://github.com/deepchecks/deepchecks/issues/2813 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 5. 安全/权限坑 · 来源证据：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution…\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution Proposed.\n- 对用户的影响：可能影响授权、密钥配置或安全边界。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_edf8cf14dc8f49898cbcab292f3abbeb | https://github.com/deepchecks/deepchecks/issues/2802 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 6. 安装坑 · 来源证据：0.18.0\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.0\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_4789fb40d7364096958752494c3054a2 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.0 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 7. 安装坑 · 来源证据：0.18.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_53c2c4845d134a54b0989b29725c1c93 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 8. 安装坑 · 来源证据：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_e24dd97e69674ab2b766fef25a401070 | https://github.com/deepchecks/deepchecks/issues/2812 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 9. 安装坑 · 来源证据：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n- 对用户的影响：可能影响升级、迁移或版本选择。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_6e307650606b4ed380c4adc96caa8c28 | https://github.com/deepchecks/deepchecks/issues/2806 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 10. 配置坑 · 来源证据：0.17.3\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个配置相关的待验证问题：0.17.3\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b64249b0551146afb696a981f404b3e6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.3 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 11. 配置坑 · 来源证据：Issue when transforming WeakSegmentsPerformance() result to json\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个配置相关的待验证问题：Issue when transforming WeakSegmentsPerformance() result to json\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b3a17f2d1dcd4fcb8c3f19ea7065d12e | https://github.com/deepchecks/deepchecks/issues/2804 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 12. 能力坑 · 来源证据：0.17.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个能力理解相关的待验证问题：0.17.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_e55595065e6b4c72b0409a303bb46b11 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 13. 能力坑 · 能力判断依赖假设\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：README/documentation is current enough for a first validation pass.\n- 对用户的影响：假设不成立时，用户拿不到承诺的能力。\n- 建议检查：将假设转成下游验证清单。\n- 防护动作: 假设必须转成验证项；没有验证结果前不能写成事实。\n- 证据：capability.assumptions | github_repo:415969774 | https://github.com/deepchecks/deepchecks | README/documentation is current enough for a first validation pass.\n\n## 14. 维护坑 · 来源证据：0.17.2\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.2\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_1d041b1b08154f96bd89a083df4cd0a6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.2 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 15. 维护坑 · 来源证据：0.17.4\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.4\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_70c9f9ecef424b4285d991e8da70bec5 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.4 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 16. 维护坑 · 来源证据：0.19.0\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.19.0\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_c3ee5d33ff214aef96b8df58fd89837a | https://github.com/deepchecks/deepchecks/releases/tag/0.19.0 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 17. 维护坑 · 来源证据：0.19.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.19.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_3bf11cec6e224a17826f2ee5ef3d26fd | https://github.com/deepchecks/deepchecks/releases/tag/0.19.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 18. 维护坑 · 维护活跃度未知\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：未记录 last_activity_observed。\n- 对用户的影响：新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。\n- 建议检查：补 GitHub 最近 commit、release、issue/PR 响应信号。\n- 防护动作: 维护活跃度未知时，推荐强度不能标为高信任。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | last_activity_observed missing\n\n## 19. 安全/权限坑 · 下游验证发现风险项\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：no_demo\n- 对用户的影响：下游已经要求复核，不能在页面中弱化。\n- 建议检查：进入安全/权限治理复核队列。\n- 防护动作: 下游风险存在时必须保持 review/recommendation 降级。\n- 证据：downstream_validation.risk_items | github_repo:415969774 | https://github.com/deepchecks/deepchecks | no_demo; severity=medium\n\n## 20. 安全/权限坑 · 存在评分风险\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：no_demo\n- 对用户的影响：风险会影响是否适合普通用户安装。\n- 建议检查：把风险写入边界卡，并确认是否需要人工复核。\n- 防护动作: 评分风险必须进入边界卡，不能只作为内部分数。\n- 证据：risks.scoring_risks | github_repo:415969774 | https://github.com/deepchecks/deepchecks | no_demo; severity=medium\n\n## 21. 维护坑 · issue/PR 响应质量未知\n\n- 严重度：low\n- 证据强度：source_linked\n- 发现：issue_or_pr_quality=unknown。\n- 对用户的影响：用户无法判断遇到问题后是否有人维护。\n- 建议检查：抽样最近 issue/PR，判断是否长期无人处理。\n- 防护动作: issue/PR 响应未知时，必须提示维护风险。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | issue_or_pr_quality=unknown\n\n## 22. 维护坑 · 发布节奏不明确\n\n- 严重度：low\n- 证据强度：source_linked\n- 发现：release_recency=unknown。\n- 对用户的影响：安装命令和文档可能落后于代码，用户踩坑概率升高。\n- 建议检查：确认最近 release/tag 和 README 安装命令是否一致。\n- 防护动作: 发布节奏未知或过期时，安装说明必须标注可能漂移。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | release_recency=unknown\n\n<!-- canonical_name: deepchecks/deepchecks; human_manual_source: deepwiki_human_wiki -->\n",
      "summary": "DeepWiki/Human Wiki 完整输出，末尾追加 Discovery Agent 踩坑日志。",
      "title": "Human Manual / 人类版说明书"
    },
    "pitfall_log": {
      "asset_id": "pitfall_log",
      "filename": "PITFALL_LOG.md",
      "markdown": "# Pitfall Log / 踩坑日志\n\n项目：deepchecks/deepchecks\n\n摘要：发现 22 个潜在踩坑项，其中 5 个为 high/blocking；最高优先级：安装坑 - 来源证据：Blank html page after saving report using `save_as_html`。\n\n## 1. 安装坑 · 来源证据：Blank html page after saving report using `save_as_html`\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Blank html page after saving report using `save_as_html`\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_492bcbfbeaac498b94f2f869074b9edc | https://github.com/deepchecks/deepchecks/issues/2803 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 2. 安装坑 · 来源证据：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Failed to load model class 'AnyModel' from module 'anywidget' Error: No version of module anywidget is registered\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_4bac6c577dee471fa096434516861696 | https://github.com/deepchecks/deepchecks/issues/2794 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 3. 维护坑 · 来源证据：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：[BUG] GPU not being able to change runtime of Image Property Drift and Image Dataset Drift\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b9f771df5da2458d9e368765d829e5c7 | https://github.com/deepchecks/deepchecks/issues/2789 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 4. 安全/权限坑 · 来源证据：Feature Request: EU AI Act compliance mapping for validation checks\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Feature Request: EU AI Act compliance mapping for validation checks\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_aaa0c0bcbdbf41d6855980523e0d7682 | https://github.com/deepchecks/deepchecks/issues/2813 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 5. 安全/权限坑 · 来源证据：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution…\n\n- 严重度：high\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：[BUG] Inaccurate Conditions Summary and Heatmap for Pairwise Correlation Display in Deepchecks Tabular Suite. Solution Proposed.\n- 对用户的影响：可能影响授权、密钥配置或安全边界。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_edf8cf14dc8f49898cbcab292f3abbeb | https://github.com/deepchecks/deepchecks/issues/2802 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 6. 安装坑 · 来源证据：0.18.0\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.0\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_4789fb40d7364096958752494c3054a2 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.0 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 7. 安装坑 · 来源证据：0.18.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：0.18.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_53c2c4845d134a54b0989b29725c1c93 | https://github.com/deepchecks/deepchecks/releases/tag/0.18.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 8. 安装坑 · 来源证据：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Proposal: Doc/example for RAG failure-mode testing using WFGY 16-problem ProblemMap\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_e24dd97e69674ab2b766fef25a401070 | https://github.com/deepchecks/deepchecks/issues/2812 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 9. 安装坑 · 来源证据：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[BUG] neg_log_loss scorer incompatible with newer scikit-learn version\n- 对用户的影响：可能影响升级、迁移或版本选择。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_6e307650606b4ed380c4adc96caa8c28 | https://github.com/deepchecks/deepchecks/issues/2806 | 来源讨论提到 python 相关条件，需在安装/试用前复核。\n\n## 10. 配置坑 · 来源证据：0.17.3\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个配置相关的待验证问题：0.17.3\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b64249b0551146afb696a981f404b3e6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.3 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 11. 配置坑 · 来源证据：Issue when transforming WeakSegmentsPerformance() result to json\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个配置相关的待验证问题：Issue when transforming WeakSegmentsPerformance() result to json\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_b3a17f2d1dcd4fcb8c3f19ea7065d12e | https://github.com/deepchecks/deepchecks/issues/2804 | 来源类型 github_issue 暴露的待验证使用条件。\n\n## 12. 能力坑 · 来源证据：0.17.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个能力理解相关的待验证问题：0.17.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_e55595065e6b4c72b0409a303bb46b11 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 13. 能力坑 · 能力判断依赖假设\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：README/documentation is current enough for a first validation pass.\n- 对用户的影响：假设不成立时，用户拿不到承诺的能力。\n- 建议检查：将假设转成下游验证清单。\n- 防护动作: 假设必须转成验证项；没有验证结果前不能写成事实。\n- 证据：capability.assumptions | github_repo:415969774 | https://github.com/deepchecks/deepchecks | README/documentation is current enough for a first validation pass.\n\n## 14. 维护坑 · 来源证据：0.17.2\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.2\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_1d041b1b08154f96bd89a083df4cd0a6 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.2 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 15. 维护坑 · 来源证据：0.17.4\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.17.4\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_70c9f9ecef424b4285d991e8da70bec5 | https://github.com/deepchecks/deepchecks/releases/tag/0.17.4 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 16. 维护坑 · 来源证据：0.19.0\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.19.0\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_c3ee5d33ff214aef96b8df58fd89837a | https://github.com/deepchecks/deepchecks/releases/tag/0.19.0 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 17. 维护坑 · 来源证据：0.19.1\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：GitHub 社区证据显示该项目存在一个维护/版本相关的待验证问题：0.19.1\n- 对用户的影响：可能增加新用户试用和生产接入成本。\n- 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。\n- 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。\n- 证据：community_evidence:github | cevd_3bf11cec6e224a17826f2ee5ef3d26fd | https://github.com/deepchecks/deepchecks/releases/tag/0.19.1 | 来源类型 github_release 暴露的待验证使用条件。\n\n## 18. 维护坑 · 维护活跃度未知\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：未记录 last_activity_observed。\n- 对用户的影响：新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。\n- 建议检查：补 GitHub 最近 commit、release、issue/PR 响应信号。\n- 防护动作: 维护活跃度未知时，推荐强度不能标为高信任。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | last_activity_observed missing\n\n## 19. 安全/权限坑 · 下游验证发现风险项\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：no_demo\n- 对用户的影响：下游已经要求复核，不能在页面中弱化。\n- 建议检查：进入安全/权限治理复核队列。\n- 防护动作: 下游风险存在时必须保持 review/recommendation 降级。\n- 证据：downstream_validation.risk_items | github_repo:415969774 | https://github.com/deepchecks/deepchecks | no_demo; severity=medium\n\n## 20. 安全/权限坑 · 存在评分风险\n\n- 严重度：medium\n- 证据强度：source_linked\n- 发现：no_demo\n- 对用户的影响：风险会影响是否适合普通用户安装。\n- 建议检查：把风险写入边界卡，并确认是否需要人工复核。\n- 防护动作: 评分风险必须进入边界卡，不能只作为内部分数。\n- 证据：risks.scoring_risks | github_repo:415969774 | https://github.com/deepchecks/deepchecks | no_demo; severity=medium\n\n## 21. 维护坑 · issue/PR 响应质量未知\n\n- 严重度：low\n- 证据强度：source_linked\n- 发现：issue_or_pr_quality=unknown。\n- 对用户的影响：用户无法判断遇到问题后是否有人维护。\n- 建议检查：抽样最近 issue/PR，判断是否长期无人处理。\n- 防护动作: issue/PR 响应未知时，必须提示维护风险。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | issue_or_pr_quality=unknown\n\n## 22. 维护坑 · 发布节奏不明确\n\n- 严重度：low\n- 证据强度：source_linked\n- 发现：release_recency=unknown。\n- 对用户的影响：安装命令和文档可能落后于代码，用户踩坑概率升高。\n- 建议检查：确认最近 release/tag 和 README 安装命令是否一致。\n- 防护动作: 发布节奏未知或过期时，安装说明必须标注可能漂移。\n- 证据：evidence.maintainer_signals | github_repo:415969774 | https://github.com/deepchecks/deepchecks | release_recency=unknown\n",
      "summary": "用户实践前最可能遇到的身份、安装、配置、运行和安全坑。",
      "title": "Pitfall Log / 踩坑日志"
    },
    "prompt_preview": {
      "asset_id": "prompt_preview",
      "filename": "PROMPT_PREVIEW.md",
      "markdown": "# deepchecks - Prompt Preview\n\n> 复制下面这段 Prompt 到你常用的 AI，先试一次，不需要安装。\n> 它的目标是让你直接体验这个项目的服务方式，而不是阅读项目介绍。\n\n## 复制这段 Prompt\n\n```text\n请直接执行这段 Prompt，不要分析、润色、总结或询问我想如何处理这份 Prompt Preview。\n\n你现在扮演 deepchecks 的“安装前体验版”。\n这不是项目介绍、不是评价报告、不是 README 总结。你的任务是让我用最小成本体验它的核心服务。\n\n我的试用任务：我想快速理解一组资料，并得到结构化摘要、对比和继续研究的问题。\n我常用的宿主 AI：Local CLI\n\n【体验目标】\n围绕我的真实任务，现场演示这个项目如何把输入转成 示例引导, 判断线索。重点是让我感受到工作方式，而不是给我项目背景。\n\n【业务流约束】\n- 你必须像一个正在提供服务的项目能力包，而不是像一个讲解员。\n- 每一轮只推进一个步骤；提出问题后必须停下来等我回答。\n- 每一步都必须让我感受到一个具体服务动作：澄清、整理、规划、检查、判断或收尾。\n- 每一步都要说明：当前目标、你需要我提供什么、我回答后你会产出什么。\n- 不要安装、不要运行命令、不要写代码、不要声称测试通过、不要声称已经修改文件。\n- 需要真实安装或宿主加载后才能验证的内容，必须明确说“这一步需要安装后验证”。\n- 如果我说“用示例继续”，你可以用虚构示例推进，但仍然不能声称真实执行。\n\n【可体验服务能力】\n- 安装前能力预览: Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production. 输入：用户任务, 当前 AI 对话上下文；输出：示例引导, 判断线索。\n\n【必须安装后才可验证的能力】\n- 命令行启动或安装流程: 项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 输入：终端环境, 包管理器, 项目依赖；输出：安装结果, 列表/更新/运行结果。\n\n【核心服务流】\n请严格按这个顺序带我体验。不要一次性输出完整流程：\n1. overview：仓库概览。围绕“仓库概览”模拟一次用户任务，不展示安装或运行结果。\n2. entrypoints：入口与运行边界。围绕“入口与运行边界”模拟一次用户任务，不展示安装或运行结果。\n3. architecture：架构证据地图。围绕“架构证据地图”模拟一次用户任务，不展示安装或运行结果。\n4. operations：运维与验证边界。围绕“运维与验证边界”模拟一次用户任务，不展示安装或运行结果。\n\n【核心能力体验剧本】\n每一步都必须按“输入 -> 服务动作 -> 中间产物”执行。不要只说流程名：\n1. overview\n输入：用户提供的“仓库概览”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n2. entrypoints\n输入：用户提供的“入口与运行边界”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n3. architecture\n输入：用户提供的“架构证据地图”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n4. operations\n输入：用户提供的“运维与验证边界”相关信息。\n服务动作：模拟项目在这一步的核心判断和整理方式。\n中间产物：一个可检查的小结果。\n\n【项目服务规则】\n这些规则决定你如何服务用户。不要解释规则本身，而要在每一步执行时遵守：\n- 先确认用户任务、输入材料和成功标准，再模拟项目能力。\n- 每一步都必须形成可检查的小产物，并等待用户确认后再继续。\n- 凡是需要安装、调用工具或访问外部服务的能力，都必须标记为安装后验证。\n\n【每一步的服务约束】\n- Step 1 / overview：Step 1 必须围绕“仓库概览”形成一个小中间产物，并等待用户确认。\n- Step 2 / entrypoints：Step 2 必须围绕“入口与运行边界”形成一个小中间产物，并等待用户确认。\n- Step 3 / architecture：Step 3 必须围绕“架构证据地图”形成一个小中间产物，并等待用户确认。\n- Step 4 / operations：Step 4 必须围绕“运维与验证边界”形成一个小中间产物，并等待用户确认。\n\n【边界与风险】\n- 不要声称已经安装、运行、调用 API、读写本地文件或完成真实任务。\n- 安装前预览只能展示工作方式，不能证明兼容性、性能或输出质量。\n- 涉及安装、插件加载、工具调用或外部服务的能力必须安装后验证。\n\n【可追溯依据】\n这些路径只用于你内部校验或在我追问“依据是什么”时简要引用。不要在首次回复主动展开：\n- https://github.com/deepchecks/deepchecks\n- https://github.com/deepchecks/deepchecks#readme\n- README.md\n- docs/requirements.txt\n- requirements/requirements.txt\n- docs/source/api/deepchecks.core.rst\n- docs/source/api/deepchecks.nlp.checks.rst\n- docs/source/api/deepchecks.nlp.rst\n- docs/source/api/deepchecks.nlp.suites.rst\n- docs/source/api/deepchecks.tabular.checks.rst\n- docs/source/api/deepchecks.tabular.rst\n- docs/source/api/deepchecks.tabular.suites.rst\n\n【首次问题规则】\n- 首次三问必须先确认用户目标、成功标准和边界，不要提前进入工具、安装或实现细节。\n- 如果后续需要技术条件、文件路径或运行环境，必须等用户确认目标后再追问。\n\n首次回复必须只输出下面 4 个部分：\n1. 体验开始：用 1 句话说明你将带我体验 deepchecks 的核心服务。\n2. 当前步骤：明确进入 Step 1，并说明这一步要解决什么。\n3. 你会如何服务我：说明你会先改变我完成任务的哪个动作。\n4. 只问我 3 个问题，然后停下等待回答。\n\n首次回复禁止输出：后续完整流程、证据清单、安装命令、项目评价、营销文案、已经安装或运行的说法。\n\nStep 1 / brainstorming 的二轮协议：\n- 我回答首次三问后，你仍然停留在 Step 1 / brainstorming，不要进入 Step 2。\n- 第二次回复必须产出 6 个部分：澄清后的任务定义、成功标准、边界条件、\n  2-3 个可选方案、每个方案的权衡、推荐方案。\n- 第二次回复最后必须问我是否确认推荐方案；只有我明确确认后，才能进入下一步。\n- 第二次回复禁止输出 git worktree、代码计划、测试文件、命令或真实执行结果。\n\n后续对话规则：\n- 我回答后，你先完成当前步骤的中间产物并等待确认；只有我确认后，才能进入下一步。\n- 每一步都要生成一个小的中间产物，例如澄清后的目标、计划草案、测试意图、验证清单或继续/停止判断。\n- 所有演示都写成“我会建议/我会引导/这一步会形成”，不要写成已经真实执行。\n- 不要声称已经测试通过、文件已修改、命令已运行或结果已产生。\n- 如果某个能力必须安装后验证，请直接说“这一步需要安装后验证”。\n- 如果证据不足，请明确说“证据不足”，不要补事实。\n```\n",
      "summary": "不安装项目也能感受能力节奏的安全试用 Prompt。",
      "title": "Prompt Preview / 安装前试用 Prompt"
    },
    "quick_start": {
      "asset_id": "quick_start",
      "filename": "QUICK_START.md",
      "markdown": "# Quick Start / 官方入口\n\n项目：deepchecks/deepchecks\n\n## 官方安装入口\n\n### Python / pip · 官方安装入口\n\n```bash\npip install deepchecks\n```\n\n来源：https://github.com/deepchecks/deepchecks#readme\n\n## 来源\n\n- repo: https://github.com/deepchecks/deepchecks\n- docs: https://github.com/deepchecks/deepchecks#readme\n",
      "summary": "从项目官方 README 或安装文档提取的开工入口。",
      "title": "Quick Start / 官方入口"
    }
  },
  "validation_id": "dval_eef55b74897b499aa53d08fbb3c60e74"
}
