{
  "schema_version": 1,
  "report_date": "2026-07-05",
  "title": "AI 日报 2026-07-05",
  "summary": "今日重点关注三类变化：阿里云继续把 Qoder 和 Quest Mode 推向软件工程 agent 场景，DeepMind 与 A24 展开面向创作和模型研究的合作，开发者社区也在用成本可视化、信息推送和自动化项目探索更可落地的 AI 工作流。",
  "hero_highlights": [
    {
      "title": "DeepMind 与 A24 展开创作研究合作",
      "url": "https://deepmind.google/blog/google-deepmind-and-a24-announce-first-of-its-kind-research-partnership/",
      "reason": "可观察的是评测设置、能力边界和内部实验参照价值",
      "what_happened": "DeepMind 与 A24 宣布研究合作，把影视创作场景纳入模型研究和评估讨论。后续值得关注的是公开方法、实验边界、创作者参与方式以及是否会产生可复现的工具或案例。",
      "why_watch": "可观察的是评测设置、能力边界和内部实验参照价值",
      "category": "model_platform",
      "source_item_ref": "https://deepmind.google/blog/google-deepmind-and-a24-announce-first-of-its-kind-research-partnership/"
    },
    {
      "title": "Rauch 可视化模型 token 消耗",
      "url": "https://x.com/rauchg/status/2073563586270781674",
      "reason": "可观察的是 agent、开发工具和自动化工作流的接入成本",
      "what_happened": "Rauch 发布一段动画，把不同 AI 工具的 token 消耗速度放在同一条时间线上展示。它提醒团队在比较 agent 或聊天产品时，同时关注调用量、成本提示、速度感知和用户体验。",
      "why_watch": "可观察的是 agent、开发工具和自动化工作流的接入成本",
      "category": "product_tool",
      "source_item_ref": "https://x.com/rauchg/status/2073563586270781674"
    },
    {
      "title": "Alibaba Cloud发布面向软件团队的 agent 平台",
      "url": "https://www.alibabacloud.com/blog/qoderwake-your-always-on-ai-employee_603327",
      "reason": "可观察的是产品入口、目标用户、上线范围和采购节奏",
      "what_happened": "Alibaba Cloud发布面向软件团队的 agent 平台，重点包括代码仓库上下文、工作流编排、IDE 集成、企业控制和评估钩子，使用前提是工程落地取决于仓库权限、上下文质量、评估回放和团队治理",
      "why_watch": "可观察的是产品入口、目标用户、上线范围和采购节奏",
      "category": "china_open_source_community",
      "source_item_ref": "https://www.alibabacloud.com/blog/qoderwake-your-always-on-ai-employee_603327"
    }
  ],
  "stories": [
    {
      "story_id": "story-content-alibaba-cloud-blog-qoderwake-your-always-on-ai-employee",
      "title": "Alibaba Cloud 发布面向软件团队的 Qoder",
      "importance": "general",
      "trend": "AI products and developer workflow",
      "event_date": "2026-07-03",
      "primary_entity": "Alibaba Cloud Blog",
      "event_type": "update",
      "object": "Alibaba Cloud发布面向软件团队的 agent 平台",
      "what_happened": "阿里云把 Qoder 描述成可常驻的软件工程 agent，目标是让它在仓库上下文中处理开发任务、生成变更并配合团队评审。团队试点时需要重点看权限、代码审查、回滚和日志。",
      "why_it_matters": "可观察的是产品入口、目标用户、上线范围和采购节奏",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Alibaba Cloud Blog",
          "url": "https://www.alibabacloud.com/blog/qoderwake-your-always-on-ai-employee_603327",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-content-google-deepmind-rss-google-deepmind-and-a24-announce-first-of-its-kind-r",
      "title": "DeepMind 与 A24 展开创作研究合作",
      "importance": "general",
      "trend": "AI industry",
      "event_date": "2026-07-03",
      "primary_entity": "Google DeepMind RSS",
      "event_type": "research",
      "object": "DeepMind说明模型评估和研究结果",
      "what_happened": "DeepMind 与 A24 宣布围绕创作场景展开研究合作，影视制作流程将成为观察模型评估、人机协作和专业创作需求的真实样本。",
      "why_it_matters": "可观察的是评测设置、能力边界和内部实验参照价值",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Google DeepMind RSS",
          "url": "https://deepmind.google/blog/google-deepmind-and-a24-announce-first-of-its-kind-research-partnership/",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-content-alibaba-cloud-blog-quest-mode-task-delegation-to-agents",
      "title": "Alibaba Cloud 介绍 Quest Mode 的任务委派流程",
      "importance": "general",
      "trend": "AI products and developer workflow",
      "event_date": "2026-07-03",
      "primary_entity": "Alibaba Cloud Blog",
      "event_type": "signal",
      "object": "Alibaba Cloud说明 agent 与开发者工具能力",
      "what_happened": "Alibaba Cloud 的 Quest Mode 博客展示了如何把复杂开发任务拆给 agent 执行，涉及任务描述、上下文交接、执行记录和人工确认。",
      "why_it_matters": "可观察的是 agent、开发工具和自动化工作流的接入成本",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Alibaba Cloud Blog",
          "url": "https://www.alibabacloud.com/blog/quest-mode-task-delegation-to-agents_603328",
          "type": "official"
        }
      ]
    },
    {
      "story_id": "story-follow-builders-x-guillermo-rauch-i-animated-the-token-spend-race-from-lifetime",
      "title": "Rauch 可视化模型 token 消耗",
      "importance": "general",
      "trend": "AI products and developer workflow",
      "event_date": "2026-07-05",
      "primary_entity": "follow-builders X feed",
      "event_type": "signal",
      "object": "follow-builders X说明 agent 与开发者工具能力",
      "what_happened": "Rauch 发布一段动画，把不同 AI 工具的 token 消耗速度放在同一条时间线上展示，让模型调用量、成本和用户体验可以一起讨论。",
      "why_it_matters": "可观察的是 agent、开发工具和自动化工作流的接入成本",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "follow-builders X feed",
          "url": "https://x.com/rauchg/status/2073563586270781674",
          "type": "primary"
        }
      ]
    },
    {
      "story_id": "story-content-salvatorera-ml-news-week-prima-mente-announces-pleiades-epigenetic-found",
      "title": "Pleiades 论文探索表观遗传基础模型",
      "importance": "general",
      "trend": "AI industry",
      "event_date": "2026-07-05",
      "primary_entity": "ML & AI News of the Week",
      "event_type": "signal",
      "object": "ML & AI News of the Week说明模型能力和推理入口变化",
      "what_happened": "bioRxiv 论文介绍 Pleiades，一组面向表观遗传数据的基础模型，关注 DNA 调控任务、训练数据和下游预测。",
      "why_it_matters": "可观察的是 AI 产品、模型或平台策略的实际变化",
      "evidence_level": "multi_source",
      "sources": [
        {
          "label": "ML & AI News of the Week",
          "url": "https://www.biorxiv.org/content/10.1101/2025.07.16.665231v1",
          "type": "primary"
        },
        {
          "label": "ML News of the Week README",
          "url": "https://www.biorxiv.org/content/10.1101/2025.07.16.665231v1",
          "type": "github"
        }
      ]
    },
    {
      "story_id": "story-content-awesome-ai-news-trendradar",
      "title": "TrendRadar 强调企业信息推送和 MCP 分析",
      "importance": "general",
      "trend": "open source AI",
      "event_date": "2026-07-05",
      "primary_entity": "sansan0/TrendRadar",
      "event_type": "update",
      "object": "这篇教程讲的是如何在阿里云 ECS 上部署 OpenClaw，并通过 Telegram 把自建 coding agent 接到日常协作入口",
      "what_happened": "TrendRadar 项目强调 MCP 分析、多渠道通知和统一时间线调度，可用于搭建 AI 信息监控或内部情报分发流程。",
      "why_it_matters": "可观察的是代码、权重、示例、许可证和生态复用条件",
      "evidence_level": "primary",
      "sources": [
        {
          "label": "Awesome AI News",
          "url": "https://github.com/sansan0/TrendRadar",
          "type": "github"
        }
      ]
    }
  ],
  "main_items": [
    {
      "title": "Alibaba Cloud 发布面向软件团队的 Qoder",
      "editorial_category": "product_radar",
      "event_date": "2026-07-03",
      "url": "https://www.alibabacloud.com/blog/qoderwake-your-always-on-ai-employee_603327",
      "source": "Alibaba Cloud Blog",
      "tier": "T0",
      "entities": [
        "Alibaba Cloud Blog"
      ],
      "summary": "阿里云把 Qoder 描述成可常驻的软件工程 agent，目标是让它在仓库上下文中处理开发任务、生成变更并配合团队评审。真正的评估重点在权限、代码审查、回滚、日志和与现有研发流程的衔接。",
      "bullets": [
        "**Qoder 的定位是常驻式工程 agent**：官方介绍强调仓库上下文、任务执行、代码变更和团队协作，而不只是一个问答式编程助手。",
        "团队试点时应选择低风险仓库，观察它能否把需求拆成可审阅的提交，并在失败时保留足够的日志和人工接管入口。",
        "采购和平台负责人需要同步评估权限边界、数据留存、评审责任和与 IDE / CI 的整合成本。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "DeepMind 与 A24 展开创作研究合作",
      "editorial_category": "ai_industry",
      "event_date": "2026-07-03",
      "url": "https://deepmind.google/blog/google-deepmind-and-a24-announce-first-of-its-kind-research-partnership/",
      "source": "Google DeepMind RSS",
      "tier": "T0",
      "entities": [
        "Google DeepMind RSS"
      ],
      "summary": "DeepMind 与 A24 宣布一项围绕创作场景的研究合作，重点不在短期产品发布，而在影视制作流程如何为模型研究、评估和人机协作提供真实样本。",
      "bullets": [
        "**DeepMind 与 A24 的合作把创作流程带入研究现场**：双方将围绕影视创作中的构思、制作和评估环节探索 AI 辅助方式。",
        "这类合作值得关注公开方法、创作者参与方式、实验边界和后续是否形成可复现案例，而不是只看品牌联名本身。",
        "对内容团队和模型团队来说，它提供了观察生成式 AI 进入专业创作流程的样本。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "Alibaba Cloud 介绍 Quest Mode 的任务委派流程",
      "editorial_category": "engineering_toolchain",
      "event_date": "2026-07-03",
      "url": "https://www.alibabacloud.com/blog/quest-mode-task-delegation-to-agents_603328",
      "source": "Alibaba Cloud Blog",
      "tier": "T0",
      "entities": [
        "Alibaba Cloud Blog"
      ],
      "summary": "Alibaba Cloud 的 Quest Mode 博客展示了如何把复杂开发任务拆给 agent 执行，涉及任务描述、上下文交接、执行记录和人工确认。团队评估这类能力时，需要提前设计权限、日志和失败回退。",
      "bullets": [
        "**Quest Mode 关注任务委派而非单轮补全**：文章围绕如何描述任务、交接上下文、跟踪执行过程和让人工确认结果展开。",
        "研发团队可以把它当作 agent 工作流样本，检查任务拆解质量、仓库权限、变更审查和异常回退是否足够清晰。",
        "如果要接入真实项目，建议先用小范围任务验证日志、可观测性和人工接管体验。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "Rauch 可视化模型 token 消耗",
      "editorial_category": "engineering_toolchain",
      "event_date": "2026-07-05",
      "url": "https://x.com/rauchg/status/2073563586270781674",
      "source": "follow-builders X feed",
      "tier": "T0",
      "entities": [
        "follow-builders X feed"
      ],
      "summary": "Rauch 发布的动画把不同 AI 工具的 token 消耗速度放到同一时间线上，直观呈现调用量和成本压力。它提醒团队在比较 agent 或聊天产品时，把功能、速度、成本提示和用户感知放在一起看。",
      "bullets": [
        "**token 消耗被做成了可视化体验指标**：动画把后台调用量变成产品、工程和财务团队都能理解的对比画面。",
        "这类展示有助于讨论模型使用成本、响应速度、上下文长度和用户是否能理解计费或额度变化。",
        "团队评估 AI 工具时，可以把 token 曲线和真实任务完成率、人工接管次数一起纳入观察。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "Pleiades 论文探索表观遗传基础模型",
      "editorial_category": "ai_industry",
      "event_date": "2026-07-05",
      "url": "https://www.biorxiv.org/content/10.1101/2025.07.16.665231v1",
      "source": "ML & AI News of the Week",
      "tier": "T0",
      "entities": [
        "ML & AI News of the Week"
      ],
      "summary": "来自 bioRxiv 的论文线索介绍了 Pleiades，一组面向表观遗传数据的基础模型，关注 DNA 调控任务、训练数据和下游预测。它展示了基础模型方法进入生命科学数据场景的一个方向。",
      "bullets": [
        "**Pleiades 将基础模型方法用于表观遗传数据**：论文关注 DNA 调控相关任务、训练数据组织和下游预测能力。",
        "研究团队可以重点阅读实验设置、数据范围、对比基线和复现条件，判断它对生命科学建模是否有可迁移价值。",
        "对 AI 平台团队来说，这类论文说明垂直领域基础模型仍需要数据治理、评测集和专业解释共同支撑。"
      ],
      "importance": "general",
      "image_urls": []
    },
    {
      "title": "TrendRadar 强调企业信息推送和 MCP 分析",
      "editorial_category": "open_source",
      "event_date": "2026-07-05",
      "url": "https://github.com/sansan0/TrendRadar",
      "source": "Awesome AI News",
      "tier": "T2",
      "entities": [
        "sansan0/TrendRadar"
      ],
      "summary": "TrendRadar 是一个企业级信息推送项目，强调 MCP 分析、多渠道通知和统一时间线调度。它适合搭建 AI 信息监控或内部情报分发流程，接入前要检查部署方式、消息渠道权限和维护成本。",
      "bullets": [
        "**TrendRadar 把多渠道通知放进同一条信息流**：项目覆盖企业微信、Telegram、钉钉、飞书和邮件等渠道，并加入 MCP 分析能力。",
        "它更适合用来做内部 AI 情报分发、主题监控和跨渠道提醒，而不是承担事实核验本身。",
        "落地前要确认消息渠道权限、去重策略、摘要质量和长期维护成本。"
      ],
      "importance": "general",
      "image_urls": []
    }
  ],
  "github_trending": [
    {
      "name": "usestrix/strix",
      "repo": "usestrix/strix",
      "description": "usestrix/strix 的公开仓库提供了可检查的代码、示例和配置入口，适合从 安全测试 agent 和自动化漏洞验证 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/usestrix/strix/main/unknown",
        "hit": true,
        "repo": "usestrix/strix",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/usestrix/strix/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/usestrix/strix",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 1,
      "source_rank": 1,
      "source_scope": "weekly:all",
      "previous_rank": 9,
      "rank_delta": 8,
      "trend": "up",
      "importance": "notable"
    },
    {
      "name": "xbtlin/ai-berkshire",
      "repo": "xbtlin/ai-berkshire",
      "description": "xbtlin/ai-berkshire 的公开仓库提供了可检查的代码、示例和配置入口，适合从 财报分析和投资研究 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/xbtlin/ai-berkshire/main/unknown",
        "hit": true,
        "repo": "xbtlin/ai-berkshire",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/xbtlin/ai-berkshire/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/xbtlin/ai-berkshire",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 2,
      "source_rank": 2,
      "source_scope": "weekly:all",
      "previous_rank": 1,
      "rank_delta": -1,
      "trend": "down",
      "importance": "general"
    },
    {
      "name": "diegosouzapw/OmniRoute",
      "repo": "diegosouzapw/OmniRoute",
      "description": "diegosouzapw/OmniRoute 的公开仓库提供了可检查的代码、示例和配置入口，适合从 多模型路由和请求分发 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/diegosouzapw/omniroute/main/unknown",
        "hit": true,
        "repo": "diegosouzapw/omniroute",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/diegosouzapw/OmniRoute",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 3,
      "source_rank": 3,
      "source_scope": "weekly:all",
      "previous_rank": 12,
      "rank_delta": 9,
      "trend": "up",
      "importance": "notable"
    },
    {
      "name": "simplex-chat/simplex-chat",
      "repo": "simplex-chat/simplex-chat",
      "description": "simplex-chat/simplex-chat 的公开仓库提供了可检查的代码、示例和配置入口，适合从 私密通信和协作应用 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/simplex-chat/simplex-chat/master/unknown",
        "hit": true,
        "repo": "simplex-chat/simplex-chat",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/simplex-chat/simplex-chat/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/simplex-chat/simplex-chat",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 4,
      "source_rank": 4,
      "source_scope": "weekly:all",
      "previous_rank": 2,
      "rank_delta": -2,
      "trend": "down",
      "importance": "general"
    },
    {
      "name": "Robbyant/lingbot-map",
      "repo": "Robbyant/lingbot-map",
      "description": "Robbyant/lingbot-map 的公开仓库提供了可检查的代码、示例和配置入口，适合从 语言学习材料整理 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/robbyant/lingbot-map/main/unknown",
        "hit": true,
        "repo": "robbyant/lingbot-map",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/Robbyant/lingbot-map/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/Robbyant/lingbot-map",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 5,
      "source_rank": 5,
      "source_scope": "weekly:all",
      "previous_rank": 8,
      "rank_delta": 3,
      "trend": "up",
      "importance": "general"
    },
    {
      "name": "ogulcancelik/herdr",
      "repo": "ogulcancelik/herdr",
      "description": "ogulcancelik/herdr 的公开仓库提供了可检查的代码、示例和配置入口，适合从 个人知识采集和检索 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/ogulcancelik/herdr/master/unknown",
        "hit": true,
        "repo": "ogulcancelik/herdr",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/ogulcancelik/herdr/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/ogulcancelik/herdr",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 6,
      "source_rank": 6,
      "source_scope": "weekly:all",
      "previous_rank": 18,
      "rank_delta": 12,
      "trend": "up",
      "importance": "general"
    },
    {
      "name": "logto-io/logto",
      "repo": "logto-io/logto",
      "description": "logto-io/logto 的公开仓库提供了可检查的代码、示例和配置入口，适合从 身份认证和多租户接入 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/logto-io/logto/master/unknown",
        "hit": true,
        "repo": "logto-io/logto",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/logto-io/logto/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/logto-io/logto",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 7,
      "source_rank": 7,
      "source_scope": "weekly:all",
      "previous_rank": 13,
      "rank_delta": 6,
      "trend": "up",
      "importance": "general"
    },
    {
      "name": "Zackriya-Solutions/meetily",
      "repo": "Zackriya-Solutions/meetily",
      "description": "Zackriya-Solutions/meetily 的公开仓库提供了可检查的代码、示例和配置入口，适合从 会议记录和本地协作 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/zackriya-solutions/meetily/main/unknown",
        "hit": true,
        "repo": "zackriya-solutions/meetily",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/Zackriya-Solutions/meetily/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/Zackriya-Solutions/meetily",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 8,
      "source_rank": 8,
      "source_scope": "weekly:all",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general"
    },
    {
      "name": "browser-use/video-use",
      "repo": "browser-use/video-use",
      "description": "browser-use/video-use 的公开仓库提供了可检查的代码、示例和配置入口，适合从 视频理解和浏览器自动化 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/browser-use/video-use/main/unknown",
        "hit": true,
        "repo": "browser-use/video-use",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/browser-use/video-use/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/browser-use/video-use",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 9,
      "source_rank": 9,
      "source_scope": "weekly:all",
      "previous_rank": 11,
      "rank_delta": 2,
      "trend": "up",
      "importance": "general"
    },
    {
      "name": "alibaba/page-agent",
      "repo": "alibaba/page-agent",
      "description": "alibaba/page-agent 的公开仓库提供了可检查的代码、示例和配置入口，适合从 网页操作 agent 和页面理解 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/alibaba/page-agent/main/unknown",
        "hit": true,
        "repo": "alibaba/page-agent",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/alibaba/page-agent/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/alibaba/page-agent",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "language": "all",
      "window": "weekly",
      "rank": 10,
      "source_rank": 10,
      "source_scope": "weekly:all",
      "previous_rank": 10,
      "rank_delta": 0,
      "trend": "same",
      "importance": "general"
    },
    {
      "name": "interviewstreet/hiring-agent",
      "repo": "interviewstreet/hiring-agent",
      "description": "interviewstreet/hiring-agent 的公开仓库提供了可检查的代码、示例和配置入口，适合从 招聘流程自动化 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/interviewstreet/hiring-agent/main/unknown",
        "hit": true,
        "repo": "interviewstreet/hiring-agent",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/interviewstreet/hiring-agent/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/interviewstreet/hiring-agent",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Python weekly",
      "language": "python",
      "window": "weekly",
      "rank": 11,
      "source_rank": 9,
      "source_scope": "weekly:python",
      "previous_rank": 7,
      "rank_delta": -2,
      "trend": "down",
      "importance": "general"
    },
    {
      "name": "ChromeDevTools/chrome-devtools-mcp",
      "repo": "ChromeDevTools/chrome-devtools-mcp",
      "description": "ChromeDevTools/chrome-devtools-mcp 的公开仓库提供了可检查的代码、示例和配置入口，适合从 Chrome DevTools 与 MCP 工具链 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/chromedevtools/chrome-devtools-mcp/main/unknown",
        "hit": true,
        "repo": "chromedevtools/chrome-devtools-mcp",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/ChromeDevTools/chrome-devtools-mcp/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/ChromeDevTools/chrome-devtools-mcp",
      "event_date": "2026-07-05",
      "source": "GitHub Trending TypeScript weekly",
      "language": "typescript",
      "window": "weekly",
      "rank": 12,
      "source_rank": 6,
      "source_scope": "weekly:typescript",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general"
    },
    {
      "name": "TencentCloud/CubeSandbox",
      "repo": "TencentCloud/CubeSandbox",
      "description": "TencentCloud/CubeSandbox 的公开仓库提供了可检查的代码、示例和配置入口，适合从 云端沙箱和隔离执行 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/tencentcloud/cubesandbox/master/unknown",
        "hit": true,
        "repo": "tencentcloud/cubesandbox",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/TencentCloud/CubeSandbox/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/TencentCloud/CubeSandbox",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Rust weekly",
      "language": "rust",
      "window": "weekly",
      "rank": 13,
      "source_rank": 3,
      "source_scope": "weekly:rust",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general"
    },
    {
      "name": "hashicorp/terraform",
      "repo": "hashicorp/terraform",
      "description": "hashicorp/terraform 的公开仓库提供了可检查的代码、示例和配置入口，适合从 基础设施编排 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/hashicorp/terraform/main/unknown",
        "hit": true,
        "repo": "hashicorp/terraform",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/hashicorp/terraform/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/hashicorp/terraform",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Go weekly",
      "language": "go",
      "window": "weekly",
      "rank": 14,
      "source_rank": 1,
      "source_scope": "weekly:go",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general"
    },
    {
      "name": "elastic/elasticsearch",
      "repo": "elastic/elasticsearch",
      "readme_fetch_status": "failed",
      "readme_error": "HTTP 404",
      "url": "https://github.com/elastic/elasticsearch",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Java weekly",
      "language": "java",
      "window": "weekly",
      "rank": 15,
      "source_rank": 2,
      "source_scope": "weekly:java",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general",
      "description": "README拉取失败；此条仅展示仓库排名、语言、星标变化和趋势方向，不补写项目能力说明。 它把相关能力沉淀为代码、示例和集成入口，方便和同类方案做功能与工程成本比较。"
    },
    {
      "name": "cupy/cupy",
      "repo": "cupy/cupy",
      "description": "cupy/cupy 的公开仓库提供了可检查的代码、示例和配置入口，适合从 GPU 数组计算 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/cupy/cupy/main/unknown",
        "hit": true,
        "repo": "cupy/cupy",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/cupy/cupy/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/cupy/cupy",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Python weekly",
      "language": "python",
      "window": "weekly",
      "rank": 16,
      "source_rank": 10,
      "source_scope": "weekly:python",
      "previous_rank": 16,
      "rank_delta": 6,
      "trend": "up",
      "importance": "general"
    },
    {
      "name": "every-app/open-seo",
      "repo": "every-app/open-seo",
      "description": "every-app/open-seo 的公开仓库提供了可检查的代码、示例和配置入口，适合从 SEO 检查和内容站点自动化 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/every-app/open-seo/main/unknown",
        "hit": true,
        "repo": "every-app/open-seo",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/every-app/open-seo/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/every-app/open-seo",
      "event_date": "2026-07-05",
      "source": "GitHub Trending TypeScript weekly",
      "language": "typescript",
      "window": "weekly",
      "rank": 17,
      "source_rank": 7,
      "source_scope": "weekly:typescript",
      "previous_rank": 12,
      "rank_delta": 5,
      "trend": "up",
      "importance": "general"
    },
    {
      "name": "denoland/deno",
      "repo": "denoland/deno",
      "description": "denoland/deno 的公开仓库提供了可检查的代码、示例和配置入口，适合从 JavaScript 与 TypeScript 运行时 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/denoland/deno/main/unknown",
        "hit": true,
        "repo": "denoland/deno",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/denoland/deno/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/denoland/deno",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Rust weekly",
      "language": "rust",
      "window": "weekly",
      "rank": 18,
      "source_rank": 4,
      "source_scope": "weekly:rust",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general"
    },
    {
      "name": "prometheus/prometheus",
      "repo": "prometheus/prometheus",
      "description": "prometheus/prometheus 的公开仓库提供了可检查的代码、示例和配置入口，适合从 监控指标和告警 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/prometheus/prometheus/main/unknown",
        "hit": true,
        "repo": "prometheus/prometheus",
        "sha": "unknown",
        "default_branch": "main",
        "source_url": "https://raw.githubusercontent.com/prometheus/prometheus/main/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/prometheus/prometheus",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Go weekly",
      "language": "go",
      "window": "weekly",
      "rank": 19,
      "source_rank": 2,
      "source_scope": "weekly:go",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general"
    },
    {
      "name": "jenkinsci/jenkins",
      "repo": "jenkinsci/jenkins",
      "description": "jenkinsci/jenkins 的公开仓库提供了可检查的代码、示例和配置入口，适合从 CI/CD 和自动化交付 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_cache": {
        "key": "github-readme/jenkinsci/jenkins/master/unknown",
        "hit": true,
        "repo": "jenkinsci/jenkins",
        "sha": "unknown",
        "default_branch": "master",
        "source_url": "https://raw.githubusercontent.com/jenkinsci/jenkins/master/README.md"
      },
      "readme_fetch_status": "ok",
      "url": "https://github.com/jenkinsci/jenkins",
      "event_date": "2026-07-05",
      "source": "GitHub Trending Java weekly",
      "language": "java",
      "window": "weekly",
      "rank": 20,
      "source_rank": 3,
      "source_scope": "weekly:java",
      "previous_rank": null,
      "rank_delta": null,
      "trend": "new",
      "importance": "general"
    }
  ],
  "huggingface_trending": [
    {
      "name": "black-forest-labs/FLUX.1-dev",
      "repo": "black-forest-labs/FLUX.1-dev",
      "description": "FLUX.1-dev 面向高质量图像生成，适合关注开源图像模型的画质、提示词控制和授权边界。评估时应结合模型卡、推理成本和内容安全策略。",
      "url": "https://huggingface.co/black-forest-labs/FLUX.1-dev",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-to-image",
      "downloads": 875870,
      "likes": 13496,
      "rank": 1,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "notable"
    },
    {
      "name": "deepseek-ai/DeepSeek-R1",
      "repo": "deepseek-ai/DeepSeek-R1",
      "description": "DeepSeek-R1 面向推理和文本生成任务，适合关注开源推理模型的团队继续观察部署成本、长上下文表现和许可证约束。",
      "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-generation",
      "downloads": 8338210,
      "likes": 13436,
      "rank": 2,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "notable"
    },
    {
      "name": "stabilityai/stable-diffusion-xl-base-1.0",
      "repo": "stabilityai/stable-diffusion-xl-base-1.0",
      "description": "Stable Diffusion XL 仍是图像生成选型中的常见基线，适合对比画质、生态兼容性、推理资源和商用条款。",
      "url": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-to-image",
      "downloads": 1349715,
      "likes": 7890,
      "rank": 3,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "notable"
    },
    {
      "name": "CompVis/stable-diffusion-v1-4",
      "repo": "CompVis/stable-diffusion-v1-4",
      "description": "Stable Diffusion v1-4 代表较成熟的图像生成基线，适合用于兼容性测试、插件生态验证和历史项目维护。",
      "url": "https://huggingface.co/CompVis/stable-diffusion-v1-4",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-to-image",
      "downloads": 420764,
      "likes": 7033,
      "rank": 4,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "general"
    },
    {
      "name": "meta-llama/Meta-Llama-3-8B",
      "repo": "meta-llama/Meta-Llama-3-8B",
      "description": "Meta Llama 3 8B 适合关注轻量文本生成和本地部署的团队，评估时要同时看许可证、微调成本和推理延迟。",
      "url": "https://huggingface.co/meta-llama/Meta-Llama-3-8B",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-generation",
      "downloads": 1289733,
      "likes": 6586,
      "rank": 5,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "general"
    },
    {
      "name": "hexgrad/Kokoro-82M",
      "repo": "hexgrad/Kokoro-82M",
      "description": "Kokoro-82M 面向文本转语音场景，关注点在音色质量、语种覆盖、推理速度和实际集成成本。",
      "url": "https://huggingface.co/hexgrad/Kokoro-82M",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-to-speech",
      "downloads": 13685663,
      "likes": 6445,
      "rank": 6,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "general"
    },
    {
      "name": "meta-llama/Llama-3.1-8B-Instruct",
      "repo": "meta-llama/Llama-3.1-8B-Instruct",
      "description": "Llama 3.1 8B Instruct 面向对话和指令跟随任务，适合做轻量应用原型、边缘部署和成本敏感场景的基线。",
      "url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-generation",
      "downloads": 9024304,
      "likes": 6229,
      "rank": 7,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "general"
    },
    {
      "name": "openai/whisper-large-v3",
      "repo": "openai/whisper-large-v3",
      "description": "Whisper large-v3 面向语音识别与转写，关注点在多语言表现、长音频稳定性、硬件消耗和数据处理合规。",
      "url": "https://huggingface.co/openai/whisper-large-v3",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "automatic-speech-recognition",
      "downloads": 5799742,
      "likes": 5910,
      "rank": 8,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "general"
    },
    {
      "name": "black-forest-labs/FLUX.1-schnell",
      "repo": "black-forest-labs/FLUX.1-schnell",
      "description": "FLUX.1-schnell 面向快速图像生成，适合观察速度、质量、推理资源和输出内容审核之间的取舍。",
      "url": "https://huggingface.co/black-forest-labs/FLUX.1-schnell",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-to-image",
      "downloads": 241669,
      "likes": 5283,
      "rank": 9,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "general"
    },
    {
      "name": "deepseek-ai/DeepSeek-V4-Pro",
      "repo": "deepseek-ai/DeepSeek-V4-Pro",
      "description": "DeepSeek V4 Pro 面向文本生成和推理场景，适合继续观察模型卡、评测样本、许可证、部署成本和安全限制。",
      "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro",
      "event_date": "2026-07-05",
      "source": "Hugging Face Trending Models",
      "task": "text-generation",
      "downloads": 1232675,
      "likes": 5155,
      "rank": 10,
      "trend": "trending",
      "editorial_category": "open_source",
      "importance": "general"
    }
  ],
  "model_releases": [],
  "hot_blogs": [
    {
      "title": "QbitAI 关注 Meta Compute 算力服务传闻",
      "editorial_category": "viewpoint_analysis",
      "url": "https://www.qbitai.com/2026/07/443339.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-07-05",
      "topic": "中文 AI 媒体动态",
      "summary": "QbitAI 报道 Meta 正考虑推出 Meta Compute，把自家 GPU 资源包装成面向外部客户的云服务。文章把这个动作放在模型公司商业化背景下解读：当训练和推理成本持续上升，拥有算力的一方可能把基础设施本身变成新产品。读者后续应关注 Meta 官方公告、定价、可用区域、企业支持能力和是否开放给第三方开发者。",
      "content_type": "blog",
      "importance": "notable",
      "image_urls": []
    }
  ],
  "chinese_media_dynamics": [
    {
      "title": "Meta也来卖铲子了！小扎：模型可以慢，GPU必须赚",
      "url": "https://www.qbitai.com/2026/07/443339.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-07-05",
      "topic": "中文 AI 媒体动态",
      "summary": "Meta也来卖铲子了！小扎：模型可以慢，GPU必须赚：正考虑推出Meta Compute。",
      "key_points": [
        "Meta也来卖铲子了",
        "小扎：模型可以慢，GPU必须赚：正考虑推出Meta Compute",
        "这条内容来自中文媒体订阅源，可作为社区关注度参考；正式采用前仍应查对应机构、论文或厂商发布。"
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "李飞飞署名具身新论文：Sim2Real烧不起，Real2Sim量大管饱",
      "url": "https://www.qbitai.com/2026/07/443066.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-07-05",
      "topic": "中文 AI 媒体动态",
      "summary": "李飞飞署名具身新论文：Sim2Real烧不起，Real2Sim量大管饱：一段视频，生成无限训练场景。",
      "key_points": [
        "李飞飞署名具身新论文：Sim2Real烧不起，Real2Sim量大管饱：一段视频，生成无限训练场景",
        "这条内容来自中文媒体订阅源，可作为社区关注度参考；正式采用前仍应查对应机构、论文或厂商发布。"
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "刚刚，LeCun团队让世界模型学会持续学习！",
      "url": "https://www.qbitai.com/2026/07/442964.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-07-05",
      "topic": "中文 AI 媒体动态",
      "summary": "刚刚，LeCun团队让世界模型学会持续学习！：迈向持续学习的世界模型。",
      "key_points": [
        "刚刚，LeCun团队让世界模型学会持续学习",
        "：迈向持续学习的世界模型",
        "这条内容来自中文媒体订阅源，可作为社区关注度参考；正式采用前仍应查对应机构、论文或厂商发布。"
      ],
      "importance": "notable",
      "image_urls": []
    },
    {
      "title": "别争了！香农老婆，才是世界上第一个大语言模型",
      "url": "https://www.qbitai.com/2026/07/443241.html",
      "publisher": "QbitAI",
      "author": "QbitAI",
      "event_date": "2026-07-05",
      "topic": "中文 AI 媒体动态",
      "summary": "别争了！香农老婆，才是世界上第一个大语言模型：70年前，香农就拥有了端侧私人定制大语言模型。",
      "key_points": [
        "别争了",
        "香农老婆，才是世界上第一个大语言模型：70年前，香农就拥有了端侧私人定制大语言模型",
        "这条内容来自中文媒体订阅源，可作为社区关注度参考；正式采用前仍应查对应机构、论文或厂商发布。"
      ],
      "importance": "notable",
      "image_urls": []
    }
  ],
  "daily_tracking": [
    {
      "id": "openrouter-rankings",
      "name": "OpenRouter",
      "url": "https://openrouter.ai/rankings",
      "event_date": "2026-07-05",
      "source": "OpenRouter Rankings",
      "category": "model_usage",
      "importance": "notable",
      "change_status": "changed",
      "change_summary": "OpenRouter 本周 Top 10 已解析：#1 DeepSeek V4 Flash 5.34T tokens；#2 MiMo-V2.5 4.38T tokens；#3 MiniMax M3 4.11T tokens；GLM 5.2 周变化 22%。",
      "summary": "OpenRouter 公开榜单显示，本周调用热度第一是 DeepSeek V4 Flash（deepseek，5.34T tokens，周变化 15%）。 Top 10 供应商分布为 anthropic 3、deepseek 2、minimax 1、stepfun 1、tencent 1、xiaomi 1、z-ai 1，可用来观察开发者在 OpenRouter 平台内的真实调用偏好。 该快照只说明 OpenRouter 平台内使用热度，不能替代能力榜单或全市场份额判断。",
      "watch_points": [
        "GLM 5.2 的周变化为 22%，需要结合发布、价格、免费额度和上下文窗口变化判断原因。",
        "若没有新进榜，重点看榜首和供应商份额是否迁移。",
        "OpenRouter 用量是平台内需求信号；生产选型仍需回到延迟、价格、上下文长度和自有任务复测。"
      ],
      "metrics": [
        {
          "label": "榜单范围",
          "value": "This Week Top 10",
          "trend": "same"
        },
        {
          "label": "供应商分布",
          "value": "anthropic 3、deepseek 2、minimax 1、stepfun 1、tencent 1、xiaomi 1、z-ai 1",
          "trend": "unknown"
        },
        {
          "label": "#1",
          "value": "DeepSeek V4 Flash（deepseek）：5.34T tokens，周变化 15%",
          "trend": "up"
        },
        {
          "label": "#2",
          "value": "MiMo-V2.5（xiaomi）：4.38T tokens，周变化 2%",
          "trend": "up"
        },
        {
          "label": "#3",
          "value": "MiniMax M3（minimax）：4.11T tokens，周变化 10%",
          "trend": "up"
        },
        {
          "label": "#4",
          "value": "Hy3 preview（tencent）：3.13T tokens，周变化 7%",
          "trend": "up"
        },
        {
          "label": "#5",
          "value": "GLM 5.2（z-ai）：2.58T tokens，周变化 22%",
          "trend": "up"
        },
        {
          "label": "#6",
          "value": "DeepSeek V4 Pro（deepseek）：2.36T tokens，周变化 16%",
          "trend": "up"
        },
        {
          "label": "#7",
          "value": "Claude Opus 4.7（anthropic）：2.19T tokens，周变化 6%",
          "trend": "up"
        },
        {
          "label": "#8",
          "value": "Claude Opus 4.8（anthropic）：2.09T tokens，周变化 10%",
          "trend": "up"
        },
        {
          "label": "#9",
          "value": "Step 3.7 Flash（stepfun）：1.55T tokens，周变化 2%",
          "trend": "up"
        },
        {
          "label": "#10",
          "value": "Claude Sonnet 4.6（anthropic）：1.43T tokens，周变化 7%",
          "trend": "up"
        }
      ],
      "snapshot": {
        "type": "openrouter_rankings_public_page",
        "collection_method": "public_page_playwright",
        "snapshot_status": "complete",
        "snapshot_as_of": "2026-07-06T07:10:37.402Z",
        "source_url": "https://openrouter.ai/rankings",
        "top_entries": [
          {
            "rank": 1,
            "model": "DeepSeek V4 Flash",
            "provider": "deepseek",
            "tokens": "5.34T tokens",
            "change": "15%"
          },
          {
            "rank": 2,
            "model": "MiMo-V2.5",
            "provider": "xiaomi",
            "tokens": "4.38T tokens",
            "change": "2%"
          },
          {
            "rank": 3,
            "model": "MiniMax M3",
            "provider": "minimax",
            "tokens": "4.11T tokens",
            "change": "10%"
          },
          {
            "rank": 4,
            "model": "Hy3 preview",
            "provider": "tencent",
            "tokens": "3.13T tokens",
            "change": "7%"
          },
          {
            "rank": 5,
            "model": "GLM 5.2",
            "provider": "z-ai",
            "tokens": "2.58T tokens",
            "change": "22%"
          },
          {
            "rank": 6,
            "model": "DeepSeek V4 Pro",
            "provider": "deepseek",
            "tokens": "2.36T tokens",
            "change": "16%"
          },
          {
            "rank": 7,
            "model": "Claude Opus 4.7",
            "provider": "anthropic",
            "tokens": "2.19T tokens",
            "change": "6%"
          },
          {
            "rank": 8,
            "model": "Claude Opus 4.8",
            "provider": "anthropic",
            "tokens": "2.09T tokens",
            "change": "10%"
          },
          {
            "rank": 9,
            "model": "Step 3.7 Flash",
            "provider": "stepfun",
            "tokens": "1.55T tokens",
            "change": "2%"
          },
          {
            "rank": 10,
            "model": "Claude Sonnet 4.6",
            "provider": "anthropic",
            "tokens": "1.43T tokens",
            "change": "7%"
          }
        ],
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "openrouter_rankings",
          "source_url": "https://openrouter.ai/rankings",
          "captured_at": "2026-07-06T07:10:37.402Z",
          "selector_version": "openrouter-rankings-v1",
          "source_selector": "[data-openrouter-rankings]",
          "sanitized_html": "<section class=\"openrouter-rankings-card\" data-openrouter-rankings>\n        <header>\n          <p>OpenRouter Top Models</p>\n          <span>This Week usage ranking</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model</th><th>Provider</th><th>Tokens</th><th>Change</th></tr></thead>\n          <tbody>\n        <tr><td>#1</td><td>DeepSeek V4 Flash</td><td>deepseek</td><td>5.34T tokens</td><td>15%</td></tr>\n        <tr><td>#2</td><td>MiMo-V2.5</td><td>xiaomi</td><td>4.38T tokens</td><td>2%</td></tr>\n        <tr><td>#3</td><td>MiniMax M3</td><td>minimax</td><td>4.11T tokens</td><td>10%</td></tr>\n        <tr><td>#4</td><td>Hy3 preview</td><td>tencent</td><td>3.13T tokens</td><td>7%</td></tr>\n        <tr><td>#5</td><td>GLM 5.2</td><td>z-ai</td><td>2.58T tokens</td><td>22%</td></tr>\n        <tr><td>#6</td><td>DeepSeek V4 Pro</td><td>deepseek</td><td>2.36T tokens</td><td>16%</td></tr>\n        <tr><td>#7</td><td>Claude Opus 4.7</td><td>anthropic</td><td>2.19T tokens</td><td>6%</td></tr>\n        <tr><td>#8</td><td>Claude Opus 4.8</td><td>anthropic</td><td>2.09T tokens</td><td>10%</td></tr>\n        <tr><td>#9</td><td>Step 3.7 Flash</td><td>stepfun</td><td>1.55T tokens</td><td>2%</td></tr>\n        <tr><td>#10</td><td>Claude Sonnet 4.6</td><td>anthropic</td><td>1.43T tokens</td><td>7%</td></tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".openrouter-rankings-card { border: 1px solid currentColor; padding: 16px; }\n      .openrouter-rankings-card table { width: 100%; border-collapse: collapse; }\n      .openrouter-rankings-card th, .openrouter-rankings-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:1edf3689d84b515dedcacdf5577afc414d3771363830a70d5ea577102cae287e",
          "css_hash": "sha256:e5df3dc0e07de42f5c2ca4021bbf59258d47d1ef0fa569d55d98b09876618e43"
        },
        "history_entries": []
      },
      "tracking_component_snapshot": {
        "source": "OpenRouter",
        "component_kind": "openrouter_rankings",
        "source_url": "https://openrouter.ai/rankings",
        "collected_at": "2026-07-06T07:10:37.402Z",
        "selector_version": "openrouter-rankings-v1",
        "raw_dom_hash": "sha256:f744aaa64df3bba3e94e1e641ecbacfe4a19e66d6af29ea12da361143335dd7a",
        "data_hash": "sha256:fed7891c7aeeb3b7eaa0fc46e0a72c4612b8bc4dc853ac1b3638dbe683fc3b9f",
        "tabs": [
          {
            "id": "top-models",
            "label": "七日排名",
            "view": "line_multi",
            "fallback_reason": ""
          },
          {
            "id": "leaderboard",
            "label": "当前榜单",
            "view": "leaderboard",
            "fallback_reason": ""
          }
        ],
        "series": [
          {
            "id": "openrouter-top-models-weekly-usage",
            "tab_id": "top-models",
            "label": "OpenRouter Top models rank trend",
            "chart": "line_multi",
            "rows": [
              {
                "rank": 1,
                "model": "DeepSeek V4 Flash",
                "provider": "deepseek",
                "value": 5340000000000,
                "value_label": "5.34T tokens",
                "change": "15%",
                "metric": "2026-07-06"
              },
              {
                "rank": 2,
                "model": "MiMo-V2.5",
                "provider": "xiaomi",
                "value": 4380000000000,
                "value_label": "4.38T tokens",
                "change": "2%",
                "metric": "2026-07-06"
              },
              {
                "rank": 3,
                "model": "MiniMax M3",
                "provider": "minimax",
                "value": 4110000000000.0005,
                "value_label": "4.11T tokens",
                "change": "10%",
                "metric": "2026-07-06"
              },
              {
                "rank": 4,
                "model": "Hy3 preview",
                "provider": "tencent",
                "value": 3130000000000,
                "value_label": "3.13T tokens",
                "change": "7%",
                "metric": "2026-07-06"
              },
              {
                "rank": 5,
                "model": "GLM 5.2",
                "provider": "z-ai",
                "value": 2580000000000,
                "value_label": "2.58T tokens",
                "change": "22%",
                "metric": "2026-07-06"
              },
              {
                "rank": 6,
                "model": "DeepSeek V4 Pro",
                "provider": "deepseek",
                "value": 2360000000000,
                "value_label": "2.36T tokens",
                "change": "16%",
                "metric": "2026-07-06"
              },
              {
                "rank": 7,
                "model": "Claude Opus 4.7",
                "provider": "anthropic",
                "value": 2190000000000,
                "value_label": "2.19T tokens",
                "change": "6%",
                "metric": "2026-07-06"
              },
              {
                "rank": 8,
                "model": "Claude Opus 4.8",
                "provider": "anthropic",
                "value": 2089999999999.9998,
                "value_label": "2.09T tokens",
                "change": "10%",
                "metric": "2026-07-06"
              },
              {
                "rank": 9,
                "model": "Step 3.7 Flash",
                "provider": "stepfun",
                "value": 1550000000000,
                "value_label": "1.55T tokens",
                "change": "2%",
                "metric": "2026-07-06"
              },
              {
                "rank": 10,
                "model": "Claude Sonnet 4.6",
                "provider": "anthropic",
                "value": 1430000000000,
                "value_label": "1.43T tokens",
                "change": "7%",
                "metric": "2026-07-06"
              }
            ],
            "fallback_reason": ""
          },
          {
            "id": "openrouter-llm-leaderboard",
            "tab_id": "leaderboard",
            "label": "LLM Leaderboard",
            "chart": "leaderboard",
            "rows": [
              {
                "rank": 1,
                "model": "DeepSeek V4 Flash",
                "provider": "deepseek",
                "value": 5340000000000,
                "value_label": "5.34T tokens",
                "change": "15%"
              },
              {
                "rank": 2,
                "model": "MiMo-V2.5",
                "provider": "xiaomi",
                "value": 4380000000000,
                "value_label": "4.38T tokens",
                "change": "2%"
              },
              {
                "rank": 3,
                "model": "MiniMax M3",
                "provider": "minimax",
                "value": 4110000000000.0005,
                "value_label": "4.11T tokens",
                "change": "10%"
              },
              {
                "rank": 4,
                "model": "Hy3 preview",
                "provider": "tencent",
                "value": 3130000000000,
                "value_label": "3.13T tokens",
                "change": "7%"
              },
              {
                "rank": 5,
                "model": "GLM 5.2",
                "provider": "z-ai",
                "value": 2580000000000,
                "value_label": "2.58T tokens",
                "change": "22%"
              },
              {
                "rank": 6,
                "model": "DeepSeek V4 Pro",
                "provider": "deepseek",
                "value": 2360000000000,
                "value_label": "2.36T tokens",
                "change": "16%"
              },
              {
                "rank": 7,
                "model": "Claude Opus 4.7",
                "provider": "anthropic",
                "value": 2190000000000,
                "value_label": "2.19T tokens",
                "change": "6%"
              },
              {
                "rank": 8,
                "model": "Claude Opus 4.8",
                "provider": "anthropic",
                "value": 2089999999999.9998,
                "value_label": "2.09T tokens",
                "change": "10%"
              },
              {
                "rank": 9,
                "model": "Step 3.7 Flash",
                "provider": "stepfun",
                "value": 1550000000000,
                "value_label": "1.55T tokens",
                "change": "2%"
              },
              {
                "rank": 10,
                "model": "Claude Sonnet 4.6",
                "provider": "anthropic",
                "value": 1430000000000,
                "value_label": "1.43T tokens",
                "change": "7%"
              }
            ],
            "fallback_reason": ""
          }
        ],
        "rows": [
          {
            "rank": 1,
            "model": "DeepSeek V4 Flash",
            "provider": "deepseek",
            "value": 5340000000000,
            "value_label": "5.34T tokens",
            "change": "15%"
          },
          {
            "rank": 2,
            "model": "MiMo-V2.5",
            "provider": "xiaomi",
            "value": 4380000000000,
            "value_label": "4.38T tokens",
            "change": "2%"
          },
          {
            "rank": 3,
            "model": "MiniMax M3",
            "provider": "minimax",
            "value": 4110000000000.0005,
            "value_label": "4.11T tokens",
            "change": "10%"
          },
          {
            "rank": 4,
            "model": "Hy3 preview",
            "provider": "tencent",
            "value": 3130000000000,
            "value_label": "3.13T tokens",
            "change": "7%"
          },
          {
            "rank": 5,
            "model": "GLM 5.2",
            "provider": "z-ai",
            "value": 2580000000000,
            "value_label": "2.58T tokens",
            "change": "22%"
          },
          {
            "rank": 6,
            "model": "DeepSeek V4 Pro",
            "provider": "deepseek",
            "value": 2360000000000,
            "value_label": "2.36T tokens",
            "change": "16%"
          },
          {
            "rank": 7,
            "model": "Claude Opus 4.7",
            "provider": "anthropic",
            "value": 2190000000000,
            "value_label": "2.19T tokens",
            "change": "6%"
          },
          {
            "rank": 8,
            "model": "Claude Opus 4.8",
            "provider": "anthropic",
            "value": 2089999999999.9998,
            "value_label": "2.09T tokens",
            "change": "10%"
          },
          {
            "rank": 9,
            "model": "Step 3.7 Flash",
            "provider": "stepfun",
            "value": 1550000000000,
            "value_label": "1.55T tokens",
            "change": "2%"
          },
          {
            "rank": 10,
            "model": "Claude Sonnet 4.6",
            "provider": "anthropic",
            "value": 1430000000000,
            "value_label": "1.43T tokens",
            "change": "7%"
          }
        ],
        "previous_snapshot": null,
        "diff": {
          "summary": "本次是首次保存组件快照，暂无可比的上一版。",
          "changed_rows": [],
          "new_entries": [
            "DeepSeek V4 Flash",
            "MiMo-V2.5",
            "MiniMax M3",
            "Hy3 preview",
            "GLM 5.2",
            "DeepSeek V4 Pro",
            "Claude Opus 4.7",
            "Claude Opus 4.8",
            "Step 3.7 Flash",
            "Claude Sonnet 4.6"
          ]
        },
        "cache_path": "",
        "fallback_reason": "",
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "openrouter_rankings",
          "source_url": "https://openrouter.ai/rankings",
          "captured_at": "2026-07-06T07:10:37.402Z",
          "selector_version": "openrouter-rankings-v1",
          "source_selector": "[data-openrouter-rankings]",
          "sanitized_html": "<section class=\"openrouter-rankings-card\" data-openrouter-rankings>\n        <header>\n          <p>OpenRouter Top Models</p>\n          <span>This Week usage ranking</span>\n        </header>\n        <table>\n          <thead><tr><th>Rank</th><th>Model</th><th>Provider</th><th>Tokens</th><th>Change</th></tr></thead>\n          <tbody>\n        <tr><td>#1</td><td>DeepSeek V4 Flash</td><td>deepseek</td><td>5.34T tokens</td><td>15%</td></tr>\n        <tr><td>#2</td><td>MiMo-V2.5</td><td>xiaomi</td><td>4.38T tokens</td><td>2%</td></tr>\n        <tr><td>#3</td><td>MiniMax M3</td><td>minimax</td><td>4.11T tokens</td><td>10%</td></tr>\n        <tr><td>#4</td><td>Hy3 preview</td><td>tencent</td><td>3.13T tokens</td><td>7%</td></tr>\n        <tr><td>#5</td><td>GLM 5.2</td><td>z-ai</td><td>2.58T tokens</td><td>22%</td></tr>\n        <tr><td>#6</td><td>DeepSeek V4 Pro</td><td>deepseek</td><td>2.36T tokens</td><td>16%</td></tr>\n        <tr><td>#7</td><td>Claude Opus 4.7</td><td>anthropic</td><td>2.19T tokens</td><td>6%</td></tr>\n        <tr><td>#8</td><td>Claude Opus 4.8</td><td>anthropic</td><td>2.09T tokens</td><td>10%</td></tr>\n        <tr><td>#9</td><td>Step 3.7 Flash</td><td>stepfun</td><td>1.55T tokens</td><td>2%</td></tr>\n        <tr><td>#10</td><td>Claude Sonnet 4.6</td><td>anthropic</td><td>1.43T tokens</td><td>7%</td></tr></tbody>\n        </table>\n      </section>",
          "sanitized_css": ".openrouter-rankings-card { border: 1px solid currentColor; padding: 16px; }\n      .openrouter-rankings-card table { width: 100%; border-collapse: collapse; }\n      .openrouter-rankings-card th, .openrouter-rankings-card td { padding: 8px; border-top: 1px solid currentColor; text-align: left; }",
          "dom_hash": "sha256:1edf3689d84b515dedcacdf5577afc414d3771363830a70d5ea577102cae287e",
          "css_hash": "sha256:e5df3dc0e07de42f5c2ca4021bbf59258d47d1ef0fa569d55d98b09876618e43"
        },
        "public_trace": {
          "source_url": "https://openrouter.ai/rankings",
          "collected_at": "2026-07-06T07:10:37.402Z",
          "selector_version": "openrouter-rankings-v1",
          "data_hash": "sha256:fed7891c7aeeb3b7eaa0fc46e0a72c4612b8bc4dc853ac1b3638dbe683fc3b9f",
          "top_rows": [
            {
              "rank": 1,
              "model": "DeepSeek V4 Flash",
              "provider": "deepseek",
              "value_label": "5.34T tokens",
              "change": "15%"
            },
            {
              "rank": 2,
              "model": "MiMo-V2.5",
              "provider": "xiaomi",
              "value_label": "4.38T tokens",
              "change": "2%"
            },
            {
              "rank": 3,
              "model": "MiniMax M3",
              "provider": "minimax",
              "value_label": "4.11T tokens",
              "change": "10%"
            },
            {
              "rank": 4,
              "model": "Hy3 preview",
              "provider": "tencent",
              "value_label": "3.13T tokens",
              "change": "7%"
            },
            {
              "rank": 5,
              "model": "GLM 5.2",
              "provider": "z-ai",
              "value_label": "2.58T tokens",
              "change": "22%"
            },
            {
              "rank": 6,
              "model": "DeepSeek V4 Pro",
              "provider": "deepseek",
              "value_label": "2.36T tokens",
              "change": "16%"
            },
            {
              "rank": 7,
              "model": "Claude Opus 4.7",
              "provider": "anthropic",
              "value_label": "2.19T tokens",
              "change": "6%"
            },
            {
              "rank": 8,
              "model": "Claude Opus 4.8",
              "provider": "anthropic",
              "value_label": "2.09T tokens",
              "change": "10%"
            },
            {
              "rank": 9,
              "model": "Step 3.7 Flash",
              "provider": "stepfun",
              "value_label": "1.55T tokens",
              "change": "2%"
            },
            {
              "rank": 10,
              "model": "Claude Sonnet 4.6",
              "provider": "anthropic",
              "value_label": "1.43T tokens",
              "change": "7%"
            }
          ],
          "diff": {
            "summary": "本次是首次保存组件快照，暂无可比的上一版。",
            "changed_rows": [],
            "new_entries": [
              "DeepSeek V4 Flash",
              "MiMo-V2.5",
              "MiniMax M3",
              "Hy3 preview",
              "GLM 5.2",
              "DeepSeek V4 Pro",
              "Claude Opus 4.7",
              "Claude Opus 4.8",
              "Step 3.7 Flash",
              "Claude Sonnet 4.6"
            ]
          },
          "cache_status": "live",
          "fallback_reason": ""
        }
      }
    },
    {
      "id": "swe-bench-pro-public",
      "name": "SWE-bench Pro",
      "url": "https://scaleapi.github.io/SWE-bench_Pro-os/",
      "event_date": "2026-07-05",
      "source": "Scale Labs SWE-Bench Pro",
      "category": "coding_benchmark",
      "importance": "major",
      "change_status": "changed",
      "change_summary": "SWE-bench Pro Public Dataset Top 10 已解析：#1 SWE-Agent + claude-4-5-Sonnet 43.72%，#2 SWE-Agent + claude-4-Sonnet 42.70%，#3 SWE-Agent + claude-4-5-haiku 39.45%。",
      "summary": "Scale Labs 公开榜单显示，SWE-bench Pro Public Dataset 当前第一是 SWE-Agent + claude-4-5-Sonnet（anthropic，Resolve Rate 43.72%）。 前三名为 SWE-Agent + claude-4-5-Sonnet 43.72%、SWE-Agent + claude-4-Sonnet 42.70%、SWE-Agent + claude-4-5-haiku 39.45%，Top 10 供应商分布为 anthropic 3、openai 2、moonshot 1、unknown 1。 这个榜单适合观察 coding agent 在长周期真实工程任务上的相对表现，但生产选型仍要结合 scaffold、成本上限、置信区间和团队自有仓库复测。",
      "watch_points": [
        "榜首 SWE-Agent + claude-4-5-Sonnet 的 Resolve Rate 为 43.72%，需要看它是否依赖特定 agent scaffold 或成本上限。",
        "如果 Top 10 没有新进榜，重点看相邻模型的置信区间是否重叠。",
        "把 SWE-bench Pro 与真实 IDE/CI 工作流分开看，避免把公开 benchmark 直接等同于团队仓库里的修复率。"
      ],
      "metrics": [
        {
          "label": "榜单范围",
          "value": "SWE-bench Pro Public Top 7",
          "trend": "same"
        },
        {
          "label": "供应商分布",
          "value": "anthropic 3、openai 2、moonshot 1、unknown 1",
          "trend": "unknown"
        },
        {
          "label": "#1",
          "value": "SWE-Agent + claude-4-5-Sonnet（anthropic）：Resolve Rate 43.72%",
          "trend": "unknown"
        },
        {
          "label": "#2",
          "value": "SWE-Agent + claude-4-Sonnet（anthropic）：Resolve Rate 42.70%",
          "trend": "unknown"
        },
        {
          "label": "#3",
          "value": "SWE-Agent + claude-4-5-haiku（anthropic）：Resolve Rate 39.45%",
          "trend": "unknown"
        },
        {
          "label": "#4",
          "value": "SWE-Agent + gpt-5-2025-08-07 (High)（openai）：Resolve Rate 36.30%",
          "trend": "unknown"
        },
        {
          "label": "#5",
          "value": "SWE-Agent + glm-4.5（unknown）：Resolve Rate 35.52%",
          "trend": "unknown"
        },
        {
          "label": "#6",
          "value": "SWE-Agent + kimi-k2-instruct（moonshot）：Resolve Rate 27.67%",
          "trend": "unknown"
        },
        {
          "label": "#7",
          "value": "SWE-Agent + gpt-oss-120b（openai）：Resolve Rate 16.20%",
          "trend": "unknown"
        }
      ],
      "snapshot": {
        "type": "swe_bench_pro_public_page",
        "collection_method": "public_page_playwright",
        "snapshot_status": "partial",
        "snapshot_as_of": "2026-07-06T07:10:37.402Z",
        "source_url": "https://scaleapi.github.io/SWE-bench_Pro-os/",
        "top_entries": [
          {
            "rank": 1,
            "model": "SWE-Agent + claude-4-5-Sonnet",
            "provider": "anthropic",
            "tokens": "43.72%",
            "change": "Resolve Rate"
          },
          {
            "rank": 2,
            "model": "SWE-Agent + claude-4-Sonnet",
            "provider": "anthropic",
            "tokens": "42.70%",
            "change": "Resolve Rate"
          },
          {
            "rank": 3,
            "model": "SWE-Agent + claude-4-5-haiku",
            "provider": "anthropic",
            "tokens": "39.45%",
            "change": "Resolve Rate"
          },
          {
            "rank": 4,
            "model": "SWE-Agent + gpt-5-2025-08-07 (High)",
            "provider": "openai",
            "tokens": "36.30%",
            "change": "Resolve Rate"
          },
          {
            "rank": 5,
            "model": "SWE-Agent + glm-4.5",
            "provider": "unknown",
            "tokens": "35.52%",
            "change": "Resolve Rate"
          },
          {
            "rank": 6,
            "model": "SWE-Agent + kimi-k2-instruct",
            "provider": "moonshot",
            "tokens": "27.67%",
            "change": "Resolve Rate"
          },
          {
            "rank": 7,
            "model": "SWE-Agent + gpt-oss-120b",
            "provider": "openai",
            "tokens": "16.20%",
            "change": "Resolve Rate"
          }
        ],
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "swe_bench_pro",
          "source_url": "https://scaleapi.github.io/SWE-bench_Pro-os/",
          "captured_at": "2026-07-06T07:10:37.402Z",
          "selector_version": "swe-bench-pro-v1",
          "source_selector": "[class*='leaderboard'] table",
          "sanitized_html": "<table id=\"leaderboardTable\">\n                <thead>\n                    <tr>\n                        <th>Model</th>\n                        <th>% Resolved</th>\n                        <th>(+/-)</th>\n                        <th>Link</th>\n                    </tr>\n                </thead>\n                <tbody>\n                    <tr data-score=\"43.72\">\n                        <td>\n                            <span class=\"model-icons\">🥇</span>\n                            <span class=\"model-name\">SWE-Agent + claude-4-5-Sonnet</span>\n                        </td>\n                        <td><span class=\"resolved-score\">43.72</span></td>\n                        <td><span class=\"z-score positive\">±3.60</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"42.70\">\n                        <td>\n                            <span class=\"model-icons\">🥈</span>\n                            <span class=\"model-name\">SWE-Agent + claude-4-Sonnet</span>\n                        </td>\n                        <td><span class=\"resolved-score\">42.70</span></td>\n                        <td><span class=\"z-score positive\">±3.59</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"39.45\">\n                        <td>\n                            <span class=\"model-icons\">🥉</span>\n                            <span class=\"model-name\">SWE-Agent + claude-4-5-haiku</span>\n                        </td>\n                        <td><span class=\"resolved-score\">39.45</span></td>\n                        <td><span class=\"z-score positive\">±3.55</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"36.30\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + gpt-5-2025-08-07 (High)</span>\n                        </td>\n                        <td><span class=\"resolved-score\">36.30</span></td>\n                        <td><span class=\"z-score positive\">±3.49</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"35.52\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + glm-4.5</span>\n                        </td>\n                        <td><span class=\"resolved-score\">35.52</span></td>\n                        <td><span class=\"z-score positive\">±3.47</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"27.67\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + kimi-k2-instruct</span>\n                        </td>\n                        <td><span class=\"resolved-score\">27.67</span></td>\n                        <td><span class=\"z-score positive\">±3.25</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"16.20\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + gpt-oss-120b</span>\n                        </td>\n                        <td><span class=\"resolved-score\">16.20</span></td>\n                        <td><span class=\"z-score positive\">±2.67</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                </tbody>\n            </table>",
          "sanitized_css": "* {\n            margin: 0;\n            padding: 0;\n            box-sizing: border-box;\n        }\n\n        body {\n            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, sans-serif;\n            background: linear-gradient(135deg, #667eea 0%, #764ba2 25%, #f093fb 50%, #4facfe 100%);\n            min-height: 100vh;\n            padding: 40px 20px;\n        }\n\n        .container {\n            max-width: 1200px;\n            margin: 0 auto;\n        }\n\n        .header {\n            text-align: center;\n            margin-bottom: 60px;\n        }\n\n        h1 {\n            font-size: 3.5rem;\n            font-weight: 800;\n            color: #ffffff;\n            text-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);\n        }\n\n        .subtitle {\n            font-size: 1.25rem;\n            color: #ffffff;\n            margin-top: 10px;\n            text-shadow: 0 1px 2px rgba(0, 0, 0, 0.1);\n        }\n\n        .buttons {\n            display: flex;\n            gap: 15px;\n            justify-content: center;\n            margin-top: 30px;\n            flex-wrap: wrap;\n        }\n\n        .btn {\n            padding: 12px 28px;\n            border: 2px solid #3b82f6;\n            background: white;\n            border-radius: 10px;\n            font-size: 1rem;\n            font-weight: 600;\n            color: #3b82f6;\n            cursor: pointer;\n            transition: all 0.3s ease;\n            text-decoration: none;\n            display: inline-flex;\n            align-items: center;\n            gap: 8px;\n        }\n\n        .btn:hover {\n            background: #3b82f6;\n            color: white;\n            transform: translateY(-2px);\n            box-shadow: 0 4px 12px rgba(59, 130, 246, 0.3);\n        }\n\n        .leaderboard-section {\n            background: white;\n            border-radius: 20px;\n            padding: 40px;\n            box-shadow: 0 10px 40px rgba(0, 0, 0, 0.1);\n        }\n\n        .leaderboard-title {\n            font-size: 2rem;\n            font-weight: 700;\n            color: #1f2937;\n            margin-bottom: 30px;\n        }\n\n        table {\n            width: 100%;\n            border-collapse: collapse;\n        }\n\n        thead {\n            background: #f3f4f6;\n        }\n\n        th {\n            padding: 16px;\n            text-align: left;\n            font-weight: 600;\n            color: #374151;\n            border-bottom: 2px solid #e5e7eb;\n        }\n\n        th:nth-child(2), th:nth-child(3) {\n            text-align: center;\n        }\n\n        th:last-child {\n            text-align: center;\n        }\n\n        tbody tr {\n            border-bottom: 1px solid #e5e7eb;\n            transition: background 0.2s ease;\n        }\n\n        tbody tr:hover {\n            background: #f9fafb;\n        }\n\n        td {\n            padding: 16px;\n            color: #1f2937;\n        }\n\n        td:nth-child(2), td:nth-child(3) {\n            text-align: center;\n        }\n\n        td:last-child {\n            text-align: center;\n        }\n\n        .model-name {\n            font-weight: 500;\n        }\n\n        .model-icons {\n            display: inline-flex;\n            gap: 4px;\n            margin-right: 8px;\n            font-size: 1.2rem;\n        }\n\n        .resolved-score {\n            font-size: 1.25rem;\n            font-weight: 700;\n            color: #059669;\n        }\n\n        .z-score {\n            font-size: 1.1rem;\n            font-weight: 600;\n        }\n\n        .z-score.positive {\n            color: #059669;\n        }\n\n        .z-score.negative {\n            color: #dc2626;\n        }\n\n        .link-icon {\n            color: #3b82f6;\n            text-decoration: none;\n            font-size: 1.2rem;\n            transition: transform 0.2s ease;\n            display: inline-block;\n        }\n\n        .link-icon:hover {\n            transform: scale(1.2);\n        }\n\n        .about-section {\n            background: white;\n            border-radius: 20px;\n            padding: 40px;\n            margin-top: 40px;\n            box-shadow: 0 10px 40px rgba(0, 0, 0, 0.1);\n        }\n\n        .about-section h2 {\n            font-size: 1.75rem;\n            font-weight: 700;\n            color: #1f2937;\n            margin-top: 30px;\n            margin-bottom: 15px;\n        }\n\n        .about-section h2:first-child {\n            margin-top: 0;\n        }\n\n        .about-section p {\n            color: #4b5563;\n            line-height: 1.7;\n            margin-bottom: 15px;\n        }\n\n        .about-section a {\n            color: #3b82f6;\n            text-decoration: none;\n        }\n\n        .about-section a:hover {\n            text-decoration: underline;\n        }\n\n        .citation-box {\n            background: #f9fafb;\n            border: 1px solid #e5e7eb;\n            border-radius: 8px;\n            padding: 20px;\n            margin: 20px 0;\n            font-family: 'Courier New', monospace;\n            font-size: 0.9rem;\n            overflow-x: auto;\n            white-space: pre-wrap;\n            color: #1f2937;\n        }\n\n        .disclaimer {\n            margin-top: 30px;\n            padding-top: 20px;\n            border-top: 1px solid #e5e7eb;\n            color: #6b7280;\n            font-size: 0.9rem;\n        }\n\n        @media (max-width: 768px) {\n            h1 {\n                font-size: 2.5rem;\n            }\n\n            .leaderboard-section {\n                padding: 20px;\n                overflow-x: auto;\n            }\n\n            .about-section {\n                padding: 20px;\n            }\n\n            table {\n                font-size: 0.9rem;\n            }\n\n            th, td {\n                padding: 12px 8px;\n            }\n        }\n    \n* { margin: 0px; padding: 0px; box-sizing: border-box; }\nbody { font-family: -apple-system, BlinkMacSystemFont, \"Segoe UI\", Roboto, Oxygen, Ubuntu, Cantarell, sans-serif; background: linear-gradient(135deg, rgb(102, 126, 234) 0%, rgb(118, 75, 162) 25%, rgb(240, 147, 251) 50%, rgb(79, 172, 254) 100%); min-height: 100vh; padding: 40px 20px; }\n.container { max-width: 1200px; margin: 0px auto; }\n.header { text-align: center; margin-bottom: 60px; }\nh1 { font-size: 3.5rem; font-weight: 800; color: rgb(255, 255, 255); text-shadow: rgba(0, 0, 0, 0.1) 0px 2px 4px; }\n.subtitle { font-size: 1.25rem; color: rgb(255, 255, 255); margin-top: 10px; text-shadow: rgba(0, 0, 0, 0.1) 0px 1px 2px; }\n.buttons { display: flex; gap: 15px; justify-content: center; margin-top: 30px; flex-wrap: wrap; }\n.btn { padding: 12px 28px; border: 2px solid rgb(59, 130, 246); background: white; border-radius: 10px; font-size: 1rem; font-weight: 600; color: rgb(59, 130, 246); cursor: pointer; transition: 0.3s; text-decoration: none; display: inline-flex; align-items: center; gap: 8px; }\n.btn:hover { background: rgb(59, 130, 246); color: white; transform: translateY(-2px); box-shadow: rgba(59, 130, 246, 0.3) 0px 4px 12px; }\n.leaderboard-section { background: white; border-radius: 20px; padding: 40px; box-shadow: rgba(0, 0, 0, 0.1) 0px 10px 40px; }\n.leaderboard-title { font-size: 2rem; font-weight: 700; color: rgb(31, 41, 55); margin-bottom: 30px; }\ntable { width: 100%; border-collapse: collapse; }\nthead { background: rgb(243, 244, 246); }\nth { padding: 16px; text-align: left; font-weight: 600; color: rgb(55, 65, 81); border-bottom: 2px solid rgb(229, 231, 235); }\nth:nth-child(2), th:nth-child(3) { text-align: center; }\nth:last-child { text-align: center; }\ntbody tr { border-bottom: 1px solid rgb(229, 231, 235); transition: background 0.2s; }\ntbody tr:hover { background: rgb(249, 250, 251); }\ntd { padding: 16px; color: rgb(31, 41, 55); }\ntd:nth-child(2), td:nth-child(3) { text-align: center; }\ntd:last-child { text-align: center; }\n.model-name { font-weight: 500; }\n.model-icons { display: inline-flex; gap: 4px; margin-right: 8px; font-size: 1.2rem; }\n.resolved-score { font-size: 1.25rem; font-weight: 700; color: rgb(5, 150, 105); }\n.z-score { font-size: 1.1rem; font-weight: 600; }\n.z-score.positive { color: rgb(5, 150, 105); }\n.z-score.negative { color: rgb(220, 38, 38); }\n.link-icon { color: rgb(59, 130, 246); text-decoration: none; font-size: 1.2rem; transition: transform 0.2s; display: inline-block; }\n.link-icon:hover { transform: scale(1.2); }\n.about-section { background: white; border-radius: 20px; padding: 40px; margin-top: 40px; box-shadow: rgba(0, 0, 0, 0.1) 0px 10px 40px; }\n.about-section h2 { font-size: 1.75rem; font-weight: 700; color: rgb(31, 41, 55); margin-top: 30px; margin-bottom: 15px; }\n.about-section h2:first-child { margin-top: 0px; }\n.about-section p { color: rgb(75, 85, 99); line-height: 1.7; margin-bottom: 15px; }\n.about-section a { color: rgb(59, 130, 246); text-decoration: none; }\n.about-section a:hover { text-decoration: underline; }\n.citation-box { background: rgb(249, 250, 251); border: 1px solid rgb(229, 231, 235); border-radius: 8px; padding: 20px; margin: 20px 0px; font-family: \"Courier New\", monospace; font-size: 0.9rem; overflow-x: auto; white-space: pre-wrap; color: rgb(31, 41, 55); }\n.disclaimer { margin-top: 30px; padding-top: 20px; border-top: 1px solid rgb(229, 231, 235); color: rgb(107, 114, 128); font-size: 0.9rem; }\n@media (max-width: 768px) {\n  h1 { font-size: 2.5rem; }\n  .leaderboard-section { padding: 20px; overflow-x: auto; }\n  .about-section { padding: 20px; }\n  table { font-size: 0.9rem; }\n  th, td { padding: 12px 8px; }\n}",
          "dom_hash": "sha256:1f59c1095c9588133cb14ee70c786c9fac692efe965f0037ac37af011dc9b8e0",
          "css_hash": "sha256:e8faaa62a35f8c29907c95bf2a3426552315a1b98e25418654fb403e5c98c8a9"
        },
        "history_entries": []
      },
      "tracking_component_snapshot": {
        "source": "Scale Labs SWE-Bench Pro",
        "component_kind": "swe_bench_pro",
        "source_url": "https://scaleapi.github.io/SWE-bench_Pro-os/",
        "collected_at": "2026-07-06T07:10:37.402Z",
        "selector_version": "swe-bench-pro-v1",
        "raw_dom_hash": "sha256:057bc1637ef3ae8c8b543f87c930e575de79e7272761bb098f5986a60bf81dcb",
        "data_hash": "sha256:8a4d1031bcf6f5b85c8480e97e3a422beed4c578cdecf63016f8e16fde45b0f1",
        "tabs": [
          {
            "id": "leaderboard",
            "label": "Public Leaderboard",
            "view": "leaderboard",
            "fallback_reason": ""
          }
        ],
        "series": [
          {
            "id": "swe-bench-pro-public-leaderboard",
            "tab_id": "leaderboard",
            "label": "SWE-Bench Pro Public Dataset",
            "chart": "leaderboard",
            "rows": [
              {
                "rank": 1,
                "model": "SWE-Agent + claude-4-5-Sonnet",
                "provider": "anthropic",
                "value": 43.72,
                "value_label": "43.72%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 2,
                "model": "SWE-Agent + claude-4-Sonnet",
                "provider": "anthropic",
                "value": 42.7,
                "value_label": "42.70%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 3,
                "model": "SWE-Agent + claude-4-5-haiku",
                "provider": "anthropic",
                "value": 39.45,
                "value_label": "39.45%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 4,
                "model": "SWE-Agent + gpt-5-2025-08-07 (High)",
                "provider": "openai",
                "value": 36.3,
                "value_label": "36.30%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 5,
                "model": "SWE-Agent + glm-4.5",
                "provider": "unknown",
                "value": 35.52,
                "value_label": "35.52%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 6,
                "model": "SWE-Agent + kimi-k2-instruct",
                "provider": "moonshot",
                "value": 27.67,
                "value_label": "27.67%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              },
              {
                "rank": 7,
                "model": "SWE-Agent + gpt-oss-120b",
                "provider": "openai",
                "value": 16.2,
                "value_label": "16.20%",
                "change": "Resolve Rate",
                "metric": "Resolve Rate"
              }
            ],
            "fallback_reason": ""
          }
        ],
        "rows": [
          {
            "rank": 1,
            "model": "SWE-Agent + claude-4-5-Sonnet",
            "provider": "anthropic",
            "value": 43.72,
            "value_label": "43.72%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 2,
            "model": "SWE-Agent + claude-4-Sonnet",
            "provider": "anthropic",
            "value": 42.7,
            "value_label": "42.70%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 3,
            "model": "SWE-Agent + claude-4-5-haiku",
            "provider": "anthropic",
            "value": 39.45,
            "value_label": "39.45%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 4,
            "model": "SWE-Agent + gpt-5-2025-08-07 (High)",
            "provider": "openai",
            "value": 36.3,
            "value_label": "36.30%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 5,
            "model": "SWE-Agent + glm-4.5",
            "provider": "unknown",
            "value": 35.52,
            "value_label": "35.52%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 6,
            "model": "SWE-Agent + kimi-k2-instruct",
            "provider": "moonshot",
            "value": 27.67,
            "value_label": "27.67%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          },
          {
            "rank": 7,
            "model": "SWE-Agent + gpt-oss-120b",
            "provider": "openai",
            "value": 16.2,
            "value_label": "16.20%",
            "change": "Resolve Rate",
            "metric": "Resolve Rate"
          }
        ],
        "previous_snapshot": null,
        "diff": {
          "summary": "本次是首次保存组件快照，暂无可比的上一版。",
          "changed_rows": [],
          "new_entries": [
            "SWE-Agent + claude-4-5-Sonnet",
            "SWE-Agent + claude-4-Sonnet",
            "SWE-Agent + claude-4-5-haiku",
            "SWE-Agent + gpt-5-2025-08-07 (High)",
            "SWE-Agent + glm-4.5",
            "SWE-Agent + kimi-k2-instruct",
            "SWE-Agent + gpt-oss-120b"
          ]
        },
        "cache_path": "",
        "fallback_reason": "",
        "official_component_snapshot": {
          "source": "official_dom",
          "component_kind": "swe_bench_pro",
          "source_url": "https://scaleapi.github.io/SWE-bench_Pro-os/",
          "captured_at": "2026-07-06T07:10:37.402Z",
          "selector_version": "swe-bench-pro-v1",
          "source_selector": "[class*='leaderboard'] table",
          "sanitized_html": "<table id=\"leaderboardTable\">\n                <thead>\n                    <tr>\n                        <th>Model</th>\n                        <th>% Resolved</th>\n                        <th>(+/-)</th>\n                        <th>Link</th>\n                    </tr>\n                </thead>\n                <tbody>\n                    <tr data-score=\"43.72\">\n                        <td>\n                            <span class=\"model-icons\">🥇</span>\n                            <span class=\"model-name\">SWE-Agent + claude-4-5-Sonnet</span>\n                        </td>\n                        <td><span class=\"resolved-score\">43.72</span></td>\n                        <td><span class=\"z-score positive\">±3.60</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"42.70\">\n                        <td>\n                            <span class=\"model-icons\">🥈</span>\n                            <span class=\"model-name\">SWE-Agent + claude-4-Sonnet</span>\n                        </td>\n                        <td><span class=\"resolved-score\">42.70</span></td>\n                        <td><span class=\"z-score positive\">±3.59</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"39.45\">\n                        <td>\n                            <span class=\"model-icons\">🥉</span>\n                            <span class=\"model-name\">SWE-Agent + claude-4-5-haiku</span>\n                        </td>\n                        <td><span class=\"resolved-score\">39.45</span></td>\n                        <td><span class=\"z-score positive\">±3.55</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"36.30\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + gpt-5-2025-08-07 (High)</span>\n                        </td>\n                        <td><span class=\"resolved-score\">36.30</span></td>\n                        <td><span class=\"z-score positive\">±3.49</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"35.52\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + glm-4.5</span>\n                        </td>\n                        <td><span class=\"resolved-score\">35.52</span></td>\n                        <td><span class=\"z-score positive\">±3.47</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"27.67\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + kimi-k2-instruct</span>\n                        </td>\n                        <td><span class=\"resolved-score\">27.67</span></td>\n                        <td><span class=\"z-score positive\">±3.25</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                    <tr data-score=\"16.20\">\n                        <td>\n                            <span class=\"model-name\">SWE-Agent + gpt-oss-120b</span>\n                        </td>\n                        <td><span class=\"resolved-score\">16.20</span></td>\n                        <td><span class=\"z-score positive\">±2.67</span></td>\n                        <td><a class=\"link-icon\" target=\"_blank\">🔗</a></td>\n                    </tr>\n                </tbody>\n            </table>",
          "sanitized_css": "* {\n            margin: 0;\n            padding: 0;\n            box-sizing: border-box;\n        }\n\n        body {\n            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, sans-serif;\n            background: linear-gradient(135deg, #667eea 0%, #764ba2 25%, #f093fb 50%, #4facfe 100%);\n            min-height: 100vh;\n            padding: 40px 20px;\n        }\n\n        .container {\n            max-width: 1200px;\n            margin: 0 auto;\n        }\n\n        .header {\n            text-align: center;\n            margin-bottom: 60px;\n        }\n\n        h1 {\n            font-size: 3.5rem;\n            font-weight: 800;\n            color: #ffffff;\n            text-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);\n        }\n\n        .subtitle {\n            font-size: 1.25rem;\n            color: #ffffff;\n            margin-top: 10px;\n            text-shadow: 0 1px 2px rgba(0, 0, 0, 0.1);\n        }\n\n        .buttons {\n            display: flex;\n            gap: 15px;\n            justify-content: center;\n            margin-top: 30px;\n            flex-wrap: wrap;\n        }\n\n        .btn {\n            padding: 12px 28px;\n            border: 2px solid #3b82f6;\n            background: white;\n            border-radius: 10px;\n            font-size: 1rem;\n            font-weight: 600;\n            color: #3b82f6;\n            cursor: pointer;\n            transition: all 0.3s ease;\n            text-decoration: none;\n            display: inline-flex;\n            align-items: center;\n            gap: 8px;\n        }\n\n        .btn:hover {\n            background: #3b82f6;\n            color: white;\n            transform: translateY(-2px);\n            box-shadow: 0 4px 12px rgba(59, 130, 246, 0.3);\n        }\n\n        .leaderboard-section {\n            background: white;\n            border-radius: 20px;\n            padding: 40px;\n            box-shadow: 0 10px 40px rgba(0, 0, 0, 0.1);\n        }\n\n        .leaderboard-title {\n            font-size: 2rem;\n            font-weight: 700;\n            color: #1f2937;\n            margin-bottom: 30px;\n        }\n\n        table {\n            width: 100%;\n            border-collapse: collapse;\n        }\n\n        thead {\n            background: #f3f4f6;\n        }\n\n        th {\n            padding: 16px;\n            text-align: left;\n            font-weight: 600;\n            color: #374151;\n            border-bottom: 2px solid #e5e7eb;\n        }\n\n        th:nth-child(2), th:nth-child(3) {\n            text-align: center;\n        }\n\n        th:last-child {\n            text-align: center;\n        }\n\n        tbody tr {\n            border-bottom: 1px solid #e5e7eb;\n            transition: background 0.2s ease;\n        }\n\n        tbody tr:hover {\n            background: #f9fafb;\n        }\n\n        td {\n            padding: 16px;\n            color: #1f2937;\n        }\n\n        td:nth-child(2), td:nth-child(3) {\n            text-align: center;\n        }\n\n        td:last-child {\n            text-align: center;\n        }\n\n        .model-name {\n            font-weight: 500;\n        }\n\n        .model-icons {\n            display: inline-flex;\n            gap: 4px;\n            margin-right: 8px;\n            font-size: 1.2rem;\n        }\n\n        .resolved-score {\n            font-size: 1.25rem;\n            font-weight: 700;\n            color: #059669;\n        }\n\n        .z-score {\n            font-size: 1.1rem;\n            font-weight: 600;\n        }\n\n        .z-score.positive {\n            color: #059669;\n        }\n\n        .z-score.negative {\n            color: #dc2626;\n        }\n\n        .link-icon {\n            color: #3b82f6;\n            text-decoration: none;\n            font-size: 1.2rem;\n            transition: transform 0.2s ease;\n            display: inline-block;\n        }\n\n        .link-icon:hover {\n            transform: scale(1.2);\n        }\n\n        .about-section {\n            background: white;\n            border-radius: 20px;\n            padding: 40px;\n            margin-top: 40px;\n            box-shadow: 0 10px 40px rgba(0, 0, 0, 0.1);\n        }\n\n        .about-section h2 {\n            font-size: 1.75rem;\n            font-weight: 700;\n            color: #1f2937;\n            margin-top: 30px;\n            margin-bottom: 15px;\n        }\n\n        .about-section h2:first-child {\n            margin-top: 0;\n        }\n\n        .about-section p {\n            color: #4b5563;\n            line-height: 1.7;\n            margin-bottom: 15px;\n        }\n\n        .about-section a {\n            color: #3b82f6;\n            text-decoration: none;\n        }\n\n        .about-section a:hover {\n            text-decoration: underline;\n        }\n\n        .citation-box {\n            background: #f9fafb;\n            border: 1px solid #e5e7eb;\n            border-radius: 8px;\n            padding: 20px;\n            margin: 20px 0;\n            font-family: 'Courier New', monospace;\n            font-size: 0.9rem;\n            overflow-x: auto;\n            white-space: pre-wrap;\n            color: #1f2937;\n        }\n\n        .disclaimer {\n            margin-top: 30px;\n            padding-top: 20px;\n            border-top: 1px solid #e5e7eb;\n            color: #6b7280;\n            font-size: 0.9rem;\n        }\n\n        @media (max-width: 768px) {\n            h1 {\n                font-size: 2.5rem;\n            }\n\n            .leaderboard-section {\n                padding: 20px;\n                overflow-x: auto;\n            }\n\n            .about-section {\n                padding: 20px;\n            }\n\n            table {\n                font-size: 0.9rem;\n            }\n\n            th, td {\n                padding: 12px 8px;\n            }\n        }\n    \n* { margin: 0px; padding: 0px; box-sizing: border-box; }\nbody { font-family: -apple-system, BlinkMacSystemFont, \"Segoe UI\", Roboto, Oxygen, Ubuntu, Cantarell, sans-serif; background: linear-gradient(135deg, rgb(102, 126, 234) 0%, rgb(118, 75, 162) 25%, rgb(240, 147, 251) 50%, rgb(79, 172, 254) 100%); min-height: 100vh; padding: 40px 20px; }\n.container { max-width: 1200px; margin: 0px auto; }\n.header { text-align: center; margin-bottom: 60px; }\nh1 { font-size: 3.5rem; font-weight: 800; color: rgb(255, 255, 255); text-shadow: rgba(0, 0, 0, 0.1) 0px 2px 4px; }\n.subtitle { font-size: 1.25rem; color: rgb(255, 255, 255); margin-top: 10px; text-shadow: rgba(0, 0, 0, 0.1) 0px 1px 2px; }\n.buttons { display: flex; gap: 15px; justify-content: center; margin-top: 30px; flex-wrap: wrap; }\n.btn { padding: 12px 28px; border: 2px solid rgb(59, 130, 246); background: white; border-radius: 10px; font-size: 1rem; font-weight: 600; color: rgb(59, 130, 246); cursor: pointer; transition: 0.3s; text-decoration: none; display: inline-flex; align-items: center; gap: 8px; }\n.btn:hover { background: rgb(59, 130, 246); color: white; transform: translateY(-2px); box-shadow: rgba(59, 130, 246, 0.3) 0px 4px 12px; }\n.leaderboard-section { background: white; border-radius: 20px; padding: 40px; box-shadow: rgba(0, 0, 0, 0.1) 0px 10px 40px; }\n.leaderboard-title { font-size: 2rem; font-weight: 700; color: rgb(31, 41, 55); margin-bottom: 30px; }\ntable { width: 100%; border-collapse: collapse; }\nthead { background: rgb(243, 244, 246); }\nth { padding: 16px; text-align: left; font-weight: 600; color: rgb(55, 65, 81); border-bottom: 2px solid rgb(229, 231, 235); }\nth:nth-child(2), th:nth-child(3) { text-align: center; }\nth:last-child { text-align: center; }\ntbody tr { border-bottom: 1px solid rgb(229, 231, 235); transition: background 0.2s; }\ntbody tr:hover { background: rgb(249, 250, 251); }\ntd { padding: 16px; color: rgb(31, 41, 55); }\ntd:nth-child(2), td:nth-child(3) { text-align: center; }\ntd:last-child { text-align: center; }\n.model-name { font-weight: 500; }\n.model-icons { display: inline-flex; gap: 4px; margin-right: 8px; font-size: 1.2rem; }\n.resolved-score { font-size: 1.25rem; font-weight: 700; color: rgb(5, 150, 105); }\n.z-score { font-size: 1.1rem; font-weight: 600; }\n.z-score.positive { color: rgb(5, 150, 105); }\n.z-score.negative { color: rgb(220, 38, 38); }\n.link-icon { color: rgb(59, 130, 246); text-decoration: none; font-size: 1.2rem; transition: transform 0.2s; display: inline-block; }\n.link-icon:hover { transform: scale(1.2); }\n.about-section { background: white; border-radius: 20px; padding: 40px; margin-top: 40px; box-shadow: rgba(0, 0, 0, 0.1) 0px 10px 40px; }\n.about-section h2 { font-size: 1.75rem; font-weight: 700; color: rgb(31, 41, 55); margin-top: 30px; margin-bottom: 15px; }\n.about-section h2:first-child { margin-top: 0px; }\n.about-section p { color: rgb(75, 85, 99); line-height: 1.7; margin-bottom: 15px; }\n.about-section a { color: rgb(59, 130, 246); text-decoration: none; }\n.about-section a:hover { text-decoration: underline; }\n.citation-box { background: rgb(249, 250, 251); border: 1px solid rgb(229, 231, 235); border-radius: 8px; padding: 20px; margin: 20px 0px; font-family: \"Courier New\", monospace; font-size: 0.9rem; overflow-x: auto; white-space: pre-wrap; color: rgb(31, 41, 55); }\n.disclaimer { margin-top: 30px; padding-top: 20px; border-top: 1px solid rgb(229, 231, 235); color: rgb(107, 114, 128); font-size: 0.9rem; }\n@media (max-width: 768px) {\n  h1 { font-size: 2.5rem; }\n  .leaderboard-section { padding: 20px; overflow-x: auto; }\n  .about-section { padding: 20px; }\n  table { font-size: 0.9rem; }\n  th, td { padding: 12px 8px; }\n}",
          "dom_hash": "sha256:1f59c1095c9588133cb14ee70c786c9fac692efe965f0037ac37af011dc9b8e0",
          "css_hash": "sha256:e8faaa62a35f8c29907c95bf2a3426552315a1b98e25418654fb403e5c98c8a9"
        },
        "public_trace": {
          "source_url": "https://scaleapi.github.io/SWE-bench_Pro-os/",
          "collected_at": "2026-07-06T07:10:37.402Z",
          "selector_version": "swe-bench-pro-v1",
          "data_hash": "sha256:8a4d1031bcf6f5b85c8480e97e3a422beed4c578cdecf63016f8e16fde45b0f1",
          "top_rows": [
            {
              "rank": 1,
              "model": "SWE-Agent + claude-4-5-Sonnet",
              "provider": "anthropic",
              "value_label": "43.72%",
              "change": "Resolve Rate"
            },
            {
              "rank": 2,
              "model": "SWE-Agent + claude-4-Sonnet",
              "provider": "anthropic",
              "value_label": "42.70%",
              "change": "Resolve Rate"
            },
            {
              "rank": 3,
              "model": "SWE-Agent + claude-4-5-haiku",
              "provider": "anthropic",
              "value_label": "39.45%",
              "change": "Resolve Rate"
            },
            {
              "rank": 4,
              "model": "SWE-Agent + gpt-5-2025-08-07 (High)",
              "provider": "openai",
              "value_label": "36.30%",
              "change": "Resolve Rate"
            },
            {
              "rank": 5,
              "model": "SWE-Agent + glm-4.5",
              "provider": "unknown",
              "value_label": "35.52%",
              "change": "Resolve Rate"
            },
            {
              "rank": 6,
              "model": "SWE-Agent + kimi-k2-instruct",
              "provider": "moonshot",
              "value_label": "27.67%",
              "change": "Resolve Rate"
            },
            {
              "rank": 7,
              "model": "SWE-Agent + gpt-oss-120b",
              "provider": "openai",
              "value_label": "16.20%",
              "change": "Resolve Rate"
            }
          ],
          "diff": {
            "summary": "本次是首次保存组件快照，暂无可比的上一版。",
            "changed_rows": [],
            "new_entries": [
              "SWE-Agent + claude-4-5-Sonnet",
              "SWE-Agent + claude-4-Sonnet",
              "SWE-Agent + claude-4-5-haiku",
              "SWE-Agent + gpt-5-2025-08-07 (High)",
              "SWE-Agent + glm-4.5",
              "SWE-Agent + kimi-k2-instruct",
              "SWE-Agent + gpt-oss-120b"
            ]
          },
          "cache_status": "live",
          "fallback_reason": ""
        }
      }
    }
  ],
  "projects": [
    {
      "name": "usestrix/strix",
      "editorial_category": "open_source",
      "description": "usestrix/strix 的公开仓库提供了可检查的代码、示例和配置入口，适合从 安全测试 agent 和自动化漏洞验证 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "usestrix/strix 的公开仓库提供了可检查的代码、示例和配置入口，适合从 安全测试 agent 和自动化漏洞验证 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "agent"
      ],
      "use_case": "适合把 usestrix/strix 放入安全测试 agent 和自动化漏洞验证的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/usestrix/strix",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "xbtlin/ai-berkshire",
      "editorial_category": "open_source",
      "description": "xbtlin/ai-berkshire 的公开仓库提供了可检查的代码、示例和配置入口，适合从 财报分析和投资研究 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "xbtlin/ai-berkshire 的公开仓库提供了可检查的代码、示例和配置入口，适合从 财报分析和投资研究 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "agent"
      ],
      "use_case": "适合把 xbtlin/ai-berkshire 放入财报分析和投资研究的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/xbtlin/ai-berkshire",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "diegosouzapw/OmniRoute",
      "editorial_category": "open_source",
      "description": "diegosouzapw/OmniRoute 的公开仓库提供了可检查的代码、示例和配置入口，适合从 多模型路由和请求分发 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "diegosouzapw/OmniRoute 的公开仓库提供了可检查的代码、示例和配置入口，适合从 多模型路由和请求分发 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "AI tooling"
      ],
      "use_case": "适合把 diegosouzapw/OmniRoute 放入多模型路由和请求分发的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/diegosouzapw/OmniRoute",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "simplex-chat/simplex-chat",
      "editorial_category": "open_source",
      "description": "simplex-chat/simplex-chat 的公开仓库提供了可检查的代码、示例和配置入口，适合从 私密通信和协作应用 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "simplex-chat/simplex-chat 的公开仓库提供了可检查的代码、示例和配置入口，适合从 私密通信和协作应用 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "AI tooling"
      ],
      "use_case": "适合把 simplex-chat/simplex-chat 放入私密通信和协作应用的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/simplex-chat/simplex-chat",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "Robbyant/lingbot-map",
      "editorial_category": "open_source",
      "description": "Robbyant/lingbot-map 的公开仓库提供了可检查的代码、示例和配置入口，适合从 语言学习材料整理 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "Robbyant/lingbot-map 的公开仓库提供了可检查的代码、示例和配置入口，适合从 语言学习材料整理 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "AI tooling"
      ],
      "use_case": "适合把 Robbyant/lingbot-map 放入语言学习材料整理的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/Robbyant/lingbot-map",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "ogulcancelik/herdr",
      "editorial_category": "open_source",
      "description": "ogulcancelik/herdr 的公开仓库提供了可检查的代码、示例和配置入口，适合从 个人知识采集和检索 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "ogulcancelik/herdr 的公开仓库提供了可检查的代码、示例和配置入口，适合从 个人知识采集和检索 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "agent"
      ],
      "use_case": "适合把 ogulcancelik/herdr 放入个人知识采集和检索的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/ogulcancelik/herdr",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "logto-io/logto",
      "editorial_category": "open_source",
      "description": "logto-io/logto 的公开仓库提供了可检查的代码、示例和配置入口，适合从 身份认证和多租户接入 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "logto-io/logto 的公开仓库提供了可检查的代码、示例和配置入口，适合从 身份认证和多租户接入 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "agent"
      ],
      "use_case": "适合把 logto-io/logto 放入身份认证和多租户接入的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/logto-io/logto",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "Zackriya-Solutions/meetily",
      "editorial_category": "open_source",
      "description": "Zackriya-Solutions/meetily 的公开仓库提供了可检查的代码、示例和配置入口，适合从 会议记录和本地协作 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "Zackriya-Solutions/meetily 的公开仓库提供了可检查的代码、示例和配置入口，适合从 会议记录和本地协作 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "agent"
      ],
      "use_case": "适合把 Zackriya-Solutions/meetily 放入会议记录和本地协作的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/Zackriya-Solutions/meetily",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "browser-use/video-use",
      "editorial_category": "open_source",
      "description": "browser-use/video-use 的公开仓库提供了可检查的代码、示例和配置入口，适合从 视频理解和浏览器自动化 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "browser-use/video-use 的公开仓库提供了可检查的代码、示例和配置入口，适合从 视频理解和浏览器自动化 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "agent",
        "AIGC"
      ],
      "use_case": "适合把 browser-use/video-use 放入视频理解和浏览器自动化的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/browser-use/video-use",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    },
    {
      "name": "alibaba/page-agent",
      "editorial_category": "open_source",
      "description": "alibaba/page-agent 的公开仓库提供了可检查的代码、示例和配置入口，适合从 网页操作 agent 和页面理解 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "readme_summary": "alibaba/page-agent 的公开仓库提供了可检查的代码、示例和配置入口，适合从 网页操作 agent 和页面理解 角度做小范围试验。使用前还应关注安装路径、默认配置、安全权限、近期提交、issue 讨论和维护节奏，避免把短期热度误认为生产可用性。",
      "domains": [
        "agent"
      ],
      "use_case": "适合把 alibaba/page-agent 放入网页操作 agent 和页面理解的初筛清单：先跑最小示例，再核对依赖、权限、数据处理方式和维护节奏。",
      "url": "https://github.com/alibaba/page-agent",
      "event_date": "2026-07-05",
      "source": "GitHub Trending weekly",
      "signal": "trending",
      "importance": "notable"
    }
  ],
  "builder_observations": [
    {
      "author": "Thibault Sottiaux",
      "handle": "thsottiaux",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "What is something that you feel is surprising that Codex still can't do well and we should have gotten right a while ago?",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条产品判断线索，重点是文件入口、版本历史，以及它怎样接进现有 AI 工具链；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/thsottiaux",
      "url": "https://x.com/thsottiaux/status/2073551549494596079",
      "role": "builder",
      "event_date": "2026-07-04",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Peter Yang",
      "handle": "petergyang",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 生态变化给出一条产品判断线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "Wow AI agrees with me 🤣 https://t.co/yCfCAupLMF",
      "translation": "原帖围绕AI 生态变化给出一条产品判断线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/petergyang",
      "url": "https://x.com/petergyang/status/2073492785991438426",
      "role": "builder",
      "event_date": "2026-07-04",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Nan Yu",
      "handle": "thenanyu",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "If you drop every production table does the model get fired or do you get fired. https://t.co/tvhupo3nh3",
      "translation": "原帖围绕AI 工具和 agent 实践给出一条工程落地线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/thenanyu",
      "url": "https://x.com/thenanyu/status/2073410944969932877",
      "role": "builder",
      "event_date": "2026-07-04",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Cat Wu",
      "handle": "_catwu",
      "editorial_category": "x_discussion",
      "content": "原帖围绕模型产品和能力变化给出一条产品判断线索，重点是成本、容灾、可观测性和网关这一层到底能替团队省多少事；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "One of the things I love about Claude Fable 5 is that it knew to use propensity score matching (matching users on activity so you compare like with like) in my retention analysis without me asking. It’s exciting to see Fable 5’s improved judgment across all of its work, from writing emails and docs in Cowork to debugging complex errors in Claude Code",
      "translation": "原帖围绕模型产品和能力变化给出一条产品判断线索，重点是成本、容灾、可观测性和网关这一层到底能替团队省多少事；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/_catwu",
      "url": "https://x.com/_catwu/status/2073439890482794966",
      "role": "builder",
      "event_date": "2026-07-04",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    },
    {
      "author": "Nan Yu",
      "handle": "thenanyu",
      "editorial_category": "x_discussion",
      "content": "原帖围绕AI 生态变化给出一条产品判断线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "original_text": "When I wrote code by hand I would utter a constant stream of profanities while in flow state. So this is basically AGI https://t.co/qaKVedlm6I",
      "translation": "原帖围绕AI 生态变化给出一条产品判断线索，重点是真实场景、落地边界和哪些做法可以直接复用；读者可把它作为 Builder/X 讨论信号，继续核对官方入口、可复现做法和失败边界。",
      "avatar_url": "https://unavatar.io/x/thenanyu",
      "url": "https://x.com/thenanyu/status/2073412466436878666",
      "role": "builder",
      "event_date": "2026-07-04",
      "source": "follow-builders X feed",
      "importance": "notable",
      "image_urls": []
    }
  ],
  "official_org_updates": [],
  "evidence_assets": [],
  "generated_at": "2026-07-06T07:16:26.939Z",
  "report_status": "normal",
  "canonical_url": "https://jasonxzwen.github.io/ai-daily-cn/reports/2026/07/2026-07-05.html",
  "html_path": "reports/2026/07/2026-07-05.html",
  "quality_status": {
    "status": "degraded",
    "public_note": "Some discovery coverage is degraded; this report may be incomplete.",
    "affected_sections": [
      "hot_blogs",
      "builder_observations",
      "daily_tracking"
    ],
    "degraded_events": [
      {
        "section": "hot_blogs",
        "message": "hot_blogs coverage is degraded and should be disclosed in the public report.",
        "severity": "degraded"
      },
      {
        "section": "builder_observations",
        "message": "builder_observations coverage is degraded and should be disclosed in the public report.",
        "severity": "degraded"
      },
      {
        "section": "daily_tracking",
        "message": "每日追踪固定源部分不可用；受影响榜单只保留抓取状态，不进入公开正文。",
        "severity": "degraded"
      }
    ]
  }
}