[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDFGJ7PCMENEWKDGSAD1DZ":3,"skill-same:01M7FDFGJ7PCMENEWKDGSAD1DZ":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7FDFGJ7PCMENEWKDGSAD1DZ","agent-runtime",null,"Implement\u002Fdebug Yuxi agent runtime, APIs, tools, skills, MCP, subagents, queue, streaming, and middleware behavior.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Fsub-skills\u002Fagent-runtime\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: agent-runtime\ndescription: \"Implement\u002Fdebug Yuxi agent runtime, APIs, tools, skills, MCP,\n  subagents, queue, streaming, and middleware behavior.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Yuxi Agent Runtime\n\nUse this sub-skill when the task touches Yuxi's LangGraph\u002FFastAPI agent execution path: agent configuration and context, run submission, request queue and steer behavior, worker\u002FSSE streaming, middleware, attachments, built-in tools, Skills, MCP, subagents, sandbox file boundaries, API-key access, or Langfuse\u002Fevaluation runtime hooks.\n\nDo not use it as the primary guide for deployment topology, knowledge-base ingestion internals, OCR engine selection, CLI usage, or general repo development; route those to the sibling sub-skills and use this one only for the agent-facing boundary.\n\n## First decisions\n\n1. **Classify the failing layer.** Use `references\u002Fagent-runtime-map.md` to decide whether the change belongs in context\u002Fconfig, request intake and queueing, run execution, stream serialization, middleware, sandbox\u002Ffiles, tools\u002FSkills\u002FMCP, or subagents.\n2. **Apply safety gates before probing.** API keys, provider keys, Langfuse keys, MCP endpoints, remote Skill sources, Tavily, non-local OCR, and live model calls are service\u002Fcredential gated. Do not print secrets or run side-effectful external calls without explicit approval.\n3. **Prefer CPU-safe unit proofs first.** Most runtime contracts are covered by backend unit tests. E2E stream\u002Fsubagent\u002Fpersonal-Skill checks require a running Docker Compose stack and sometimes admin credentials.\n4. **Keep HTTP routes thin.** Route code should validate request\u002Fauth\u002Fresponse shape and delegate stateful behavior to services\u002Frepositories.\n\n## Quick route map\n\n- **Agent definition\u002Fconfig:** inspect BaseAgent\u002FBaseContext\u002FChatBotContext\u002FSubAgentContext, Agent repository serialization, and `config_json.context` normalization.\n- **Run submission and queue:** start at `POST \u002Fapi\u002Fagent\u002Fruns`, `RunSubmissionCommand`, and the request queue service for `enqueue`, `reject`, and `steer` semantics.\n- **Worker execution and streaming:** follow AgentRun creation, ARQ enqueue, `stream_agent_chat`\u002Fresume, Redis stream events, and `\u002Fapi\u002Fagent\u002Fruns\u002F{run_id}\u002Fevents` SSE serialization.\n- **Middleware behavior:** inspect the built-in Chatbot\u002FSubAgent graph assembly, then the specific middleware in question: filesystem, attachments, Skills, subagent task tools, summary\u002Foffload, image-input compatibility, token usage, model retry, or tool approval.\n- **Tools, Skills, MCP, subagents:** use `references\u002Ftools-skills-mcp-subagents.md` for activation, gating, storage, async subagent lifecycle, and sandbox boundaries.\n- **Known failure modes:** use `references\u002Ftroubleshooting.md` before making broad changes.\n\n## Safe command entry points\n\nRun commands from the repository root. Docker Compose is the canonical development runtime.\n\n```bash\n# Non-mutating service\u002Flog probes\ndocker compose ps\ndocker logs api-dev --tail 100\ndocker logs worker-dev --tail 100\ndocker logs sandbox-provisioner --tail 100\ncurl -s http:\u002F\u002Flocalhost:5050\u002Fapi\u002Fsystem\u002Fhealth\ncurl -s http:\u002F\u002Flocalhost:8002\u002Fhealth\n\n# CPU-safe unit coverage for this sub-skill\ndocker compose exec api uv run --group test pytest \\\n  test\u002Funit\u002Frouters\u002Ftest_skill_router.py \\\n  test\u002Funit\u002Fservices\u002Ftest_skill_service.py \\\n  test\u002Funit\u002Fbackends\u002Ftest_sandbox_backends.py \\\n  test\u002Funit\u002Fservices\u002Ftest_agent_request_queue_service.py \\\n  test\u002Funit\u002Fmiddlewares\u002Ftest_steer_middleware.py \\\n  test\u002Funit\u002Fmiddlewares\u002Ftest_subagent_task_middleware.py \\\n  test\u002Funit\u002Fservices\u002Ftest_subagent_run_service.py \\\n  test\u002Funit\u002Frouters\u002Ftest_mcp_router.py \\\n  test\u002Funit\u002Fservices\u002Ftest_mcp_service.py \\\n  test\u002Funit\u002Ftoolkits\u002Ftest_install_skill.py\n```\n\nOnly run the E2E candidates when the stack is intentionally running and test credentials are available:\n\n```bash\ndocker compose exec api uv run --group test pytest -m e2e \\\n  test\u002Fe2e\u002Ftest_subagent_stream_e2e.py \\\n  test\u002Fe2e\u002Ftest_personal_skill_agent_e2e.py\n```\n\n## Native proof candidates\n\n- Required CPU\u002Fany: skill router, skill service, sandbox backend\u002Fpath rules, request queue\u002Fsteer service, subagent middleware\u002Fservice, MCP router\u002Fservice, and `install_skill` unit tests.\n- Optional service-required: subagent streaming E2E and personal Skill agent E2E. These require Docker Compose services and should not be treated as proof when services, admin user, worker, Redis\u002FPostgres, MinIO, or sandbox-provisioner are unavailable.\n- Optional external credentials: API-key\u002FSSE examples, live model provider calls, Langfuse\u002Fevaluation, Tavily search, remote MCP, and remote Skill installs.\n\n## Reference files\n\n- `references\u002Fagent-runtime-map.md` — execution architecture, layer ownership, APIs, middleware, streaming, tests, and backend gates.\n- `references\u002Ftools-skills-mcp-subagents.md` — tool registry, built-in\u002FKB tools, Skill install\u002Factivation\u002Fstorage, MCP integration, subagent lifecycle, and sandbox file semantics.\n- `references\u002Ftroubleshooting.md` — targeted symptoms, probes, fixes, safety boundaries, and test selection.\n","# Yuxi Agent Runtime\n\nUse this sub-skill when the task touches Yuxi's LangGraph\u002FFastAPI agent execution path: agent configuration and context, run submission, request queue and steer behavior, worker\u002FSSE streaming, middleware, attachments, built-in tools, Skills, MCP, subagents, sandbox file boundaries, API-key access, or Langfuse\u002Fevaluation runtime hooks.\n\nDo not use it as the primary guide for deployment topology, knowledge-base ingestion internals, OCR engine selection, CLI usage, or general repo development; route those to the sibling sub-skills and use this one only for the agent-facing boundary.\n\n## First decisions\n\n1. **Classify the failing layer.** Use `references\u002Fagent-runtime-map.md` to decide whether the change belongs in context\u002Fconfig, request intake and queueing, run execution, stream serialization, middleware, sandbox\u002Ffiles, tools\u002FSkills\u002FMCP, or subagents.\n2. **Apply safety gates before probing.** API keys, provider keys, Langfuse keys, MCP endpoints, remote Skill sources, Tavily, non-local OCR, and live model calls are service\u002Fcredential gated. Do not print secrets or run side-effectful external calls without explicit approval.\n3. **Prefer CPU-safe unit proofs first.** Most runtime contracts are covered by backend unit tests. E2E stream\u002Fsubagent\u002Fpersonal-Skill checks require a running Docker Compose stack and sometimes admin credentials.\n4. **Keep HTTP routes thin.** Route code should validate request\u002Fauth\u002Fresponse shape and delegate stateful behavior to services\u002Frepositories.\n\n## Quick route map\n\n- **Agent definition\u002Fconfig:** inspect BaseAgent\u002FBaseContext\u002FChatBotContext\u002FSubAgentContext, Agent repository serialization, and `config_json.context` normalization.\n- **Run submission and queue:** start at `POST \u002Fapi\u002Fagent\u002Fruns`, `RunSubmissionCommand`, and the request queue service for `enqueue`, `reject`, and `steer` semantics.\n- **Worker execution and streaming:** follow AgentRun creation, ARQ enqueue, `stream_agent_chat`\u002Fresume, Redis stream events, and `\u002Fapi\u002Fagent\u002Fruns\u002F{run_id}\u002Fevents` SSE serialization.\n- **Middleware behavior:** inspect the built-in Chatbot\u002FSubAgent graph assembly, then the specific middleware in question: filesystem, attachments, Skills, subagent task tools, summary\u002Foffload, image-input compatibility, token usage, model retry, or tool approval.\n- **Tools, Skills, MCP, subagents:** use `references\u002Ftools-skills-mcp-subagents.md` for activation, gating, storage, async subagent lifecycle, and sandbox boundaries.\n- **Known failure modes:** use `references\u002Ftroubleshooting.md` before making broad changes.\n\n## Safe command entry points\n\nRun commands from the repository root. Docker Compose is the canonical development runtime.\n\n```bash\n# Non-mutating service\u002Flog probes\ndocker compose ps\ndocker logs api-dev --tail 100\ndocker logs worker-dev --tail 100\ndocker logs sandbox-provisioner --tail 100\ncurl -s http:\u002F\u002Flocalhost:5050\u002Fapi\u002Fsystem\u002Fhealth\ncurl -s http:\u002F\u002Flocalhost:8002\u002Fhealth\n\n# CPU-safe unit coverage for this sub-skill\ndocker compose exec api uv run --group test pytest \\\n  test\u002Funit\u002Frouters\u002Ftest_skill_router.py \\\n  test\u002Funit\u002Fservices\u002Ftest_skill_service.py \\\n  test\u002Funit\u002Fbackends\u002Ftest_sandbox_backends.py \\\n  test\u002Funit\u002Fservices\u002Ftest_agent_request_queue_service.py \\\n  test\u002Funit\u002Fmiddlewares\u002Ftest_steer_middleware.py \\\n  test\u002Funit\u002Fmiddlewares\u002Ftest_subagent_task_middleware.py \\\n  test\u002Funit\u002Fservices\u002Ftest_subagent_run_service.py \\\n  test\u002Funit\u002Frouters\u002Ftest_mcp_router.py \\\n  test\u002Funit\u002Fservices\u002Ftest_mcp_service.py \\\n  test\u002Funit\u002Ftoolkits\u002Ftest_install_skill.py\n```\n\nOnly run the E2E candidates when the stack is intentionally running and test credentials are available:\n\n```bash\ndocker compose exec api uv run --group test pytest -m e2e \\\n  test\u002Fe2e\u002Ftest_subagent_stream_e2e.py \\\n  test\u002Fe2e\u002Ftest_personal_skill_agent_e2e.py\n```\n\n## Native proof candidates\n\n- Required CPU\u002Fany: skill router, skill service, sandbox backend\u002Fpath rules, request queue\u002Fsteer service, subagent middleware\u002Fservice, MCP router\u002Fservice, and `install_skill` unit tests.\n- Optional service-required: subagent streaming E2E and personal Skill agent E2E. These require Docker Compose services and should not be treated as proof when services, admin user, worker, Redis\u002FPostgres, MinIO, or sandbox-provisioner are unavailable.\n- Optional external credentials: API-key\u002FSSE examples, live model provider calls, Langfuse\u002Fevaluation, Tavily search, remote MCP, and remote Skill installs.\n\n## Reference files\n\n- `references\u002Fagent-runtime-map.md` — execution architecture, layer ownership, APIs, middleware, streaming, tests, and backend gates.\n- `references\u002Ftools-skills-mcp-subagents.md` — tool registry, built-in\u002FKB tools, Skill install\u002Factivation\u002Fstorage, MCP integration, subagent lifecycle, and sandbox file semantics.\n- `references\u002Ftroubleshooting.md` — targeted symptoms, probes, fixes, safety boundaries, and test selection.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fyuxi\u002Fsub-skills\u002Fagent-runtime",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill agent-runtime",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill agent-runtime",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill agent-runtime","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Fsub-skills\u002Fagent-runtime\u002FSKILL.md",[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fagent-runtime-map.md","REFERENCE","参考文档",16668,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Fsub-skills\u002Fagent-runtime\u002Freferences\u002Fagent-runtime-map.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Ftools-skills-mcp-subagents.md",15798,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Fsub-skills\u002Fagent-runtime\u002Freferences\u002Ftools-skills-mcp-subagents.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",19305,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fyuxi\u002Fsub-skills\u002Fagent-runtime\u002Freferences\u002Ftroubleshooting.md",[63,70,75,82,89,96],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":71,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]