[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XPD8MCSWJN3XZKPQ9DM28":3,"skill-same:01M78XPD8MCSWJN3XZKPQ9DM28":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78XPD8MCSWJN3XZKPQ9DM28","server-webui-and-protocols",null,"Operate gptme server, Web UI, REST\u002FSSE API, TUI, ACP, deployment, security, and protocol integration workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: server-webui-and-protocols\ndescription: \"Operate gptme server, Web UI, REST\u002FSSE API, TUI, ACP, deployment,\n  security, and protocol integration workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# server-webui-and-protocols\n\nUse this sub-skill for tasks about `gptme-server`, the REST\u002FSSE API, the bundled or Vite Web UI, `gptme-tui`, ACP editor integration, deployment hardening, reverse proxies, or desktop sidecar behavior.\n\nKeep this file as the router. Open the bundled references for details; do not depend on a target checkout's documentation when answering operational questions.\n\n## Route here for\n\n- starting or probing `gptme-server`, choosing server options, or checking server route availability\n- HTTP API, Server-Sent Events, auth cookies, bearer token handling, CORS, Host validation, or Local Network Access\n- Web UI connection setup, multi-server settings, message metadata, streaming state, markdown rendering, or frontend\u002Fbackend protocol mismatches\n- ACP shim\u002Fdirect\u002Fmodule launch, editor protocol lifecycle, stdout\u002Fstderr protocol failures, or server-side ACP step mode\n- `gptme-tui` install, options, key limitations, or switching between TUI and CLI conversations\n- Docker Compose self-hosting, nginx reverse proxy, systemd service shape, public exposure hardening, or parent-death sidecar cleanup\n\n## Route away\n\n- Generic terminal conversation usage, prompts, slash commands, log browsing, or `gptme-agent` CLI: route to `cli-and-conversations`.\n- Provider keys, model selection, credential storage, provider plugins, or local model config: route to `configuration-and-providers`.\n- Built-in tools, plugins, hooks, browser\u002Fcomputer tool internals, MCP, skills, or lessons: route to `tools-and-extensibility`.\n- Evaluation suites, benchmark runs, SWE-bench\u002FT-bench, Docker eval isolation, or leaderboards: route to `evals-and-benchmarks`.\n- Maintainer-only checkout work such as frontend test selection, package release checks, lint\u002Ftypecheck strategy, or code-review policy: route to `repo-development`.\n\n## Read first\n\n- [references\u002Fserver-api.md](references\u002Fserver-api.md) — install\u002Fserve options, safe help checks, auth\u002FCORS\u002FHost validation, route families, SSE events, message metadata, and `GptmeApiClient`.\n- [references\u002Fwebui-api.md](references\u002Fwebui-api.md) — bundled vs Vite Web UI, multi-backend behavior, frontend development gotchas, markdown paths, message metadata\u002FSSE flow, Step grouping, and `ChatInput` state.\n- [references\u002Facp-and-tui.md](references\u002Facp-and-tui.md) — ACP shim\u002Fdirect\u002Fmodule launch, protocol lifecycle, stdio failure modes, and TUI options\u002Flimitations.\n- [references\u002Fdeployment.md](references\u002Fdeployment.md) — Docker Compose, nginx reverse proxy, systemd service pattern, self-hosting security, and sidecar parent-death behavior.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) — concrete symptoms, causes, and recovery steps for connection, streaming, metadata, ACP, TUI, and deployment failures.\n\n## Safe helper scripts\n\n- [scripts\u002Fprobe_gptme_server.py](scripts\u002Fprobe_gptme_server.py) probes a running server's root page, `\u002Fapi\u002Fv2`, `\u002Fapi\u002Fv2\u002Fversion`, and `\u002Fapi\u002Fv2\u002Fserver\u002Fhealth` with an optional bearer token. It performs only read-only requests and supports `--help`.\n- [scripts\u002Fcheck_webui_message_metadata.py](scripts\u002Fcheck_webui_message_metadata.py) validates representative REST\u002FSSE message dictionaries and compares the metadata fields expected by the Web UI. It supports JSON, JSON lines, and `data: {...}` SSE samples and supports `--help`.\n\n## Fast operating checklist\n\n1. Identify the surface: local server, hosted Web UI, Vite frontend development, TUI, ACP, deployment, or sidecar cleanup.\n2. For browser connection failures, check token, exact CORS origin, and Local Network Access together; each is a separate gate.\n3. For message badge\u002Frendering problems, compare REST conversation payloads with SSE `message_added` and `generation_complete` payloads before changing frontend code.\n4. For ACP, treat stdout as JSON-RPC-only; logs and diagnostics must go to stderr.\n5. For persistent deployments, prefer a stable `GPTME_SERVER_TOKEN`, loopback bind plus reverse proxy, disabled proxy buffering for SSE, and explicit parent-death watching for sidecars.\n","# server-webui-and-protocols\n\nUse this sub-skill for tasks about `gptme-server`, the REST\u002FSSE API, the bundled or Vite Web UI, `gptme-tui`, ACP editor integration, deployment hardening, reverse proxies, or desktop sidecar behavior.\n\nKeep this file as the router. Open the bundled references for details; do not depend on a target checkout's documentation when answering operational questions.\n\n## Route here for\n\n- starting or probing `gptme-server`, choosing server options, or checking server route availability\n- HTTP API, Server-Sent Events, auth cookies, bearer token handling, CORS, Host validation, or Local Network Access\n- Web UI connection setup, multi-server settings, message metadata, streaming state, markdown rendering, or frontend\u002Fbackend protocol mismatches\n- ACP shim\u002Fdirect\u002Fmodule launch, editor protocol lifecycle, stdout\u002Fstderr protocol failures, or server-side ACP step mode\n- `gptme-tui` install, options, key limitations, or switching between TUI and CLI conversations\n- Docker Compose self-hosting, nginx reverse proxy, systemd service shape, public exposure hardening, or parent-death sidecar cleanup\n\n## Route away\n\n- Generic terminal conversation usage, prompts, slash commands, log browsing, or `gptme-agent` CLI: route to `cli-and-conversations`.\n- Provider keys, model selection, credential storage, provider plugins, or local model config: route to `configuration-and-providers`.\n- Built-in tools, plugins, hooks, browser\u002Fcomputer tool internals, MCP, skills, or lessons: route to `tools-and-extensibility`.\n- Evaluation suites, benchmark runs, SWE-bench\u002FT-bench, Docker eval isolation, or leaderboards: route to `evals-and-benchmarks`.\n- Maintainer-only checkout work such as frontend test selection, package release checks, lint\u002Ftypecheck strategy, or code-review policy: route to `repo-development`.\n\n## Read first\n\n- [references\u002Fserver-api.md](references\u002Fserver-api.md) — install\u002Fserve options, safe help checks, auth\u002FCORS\u002FHost validation, route families, SSE events, message metadata, and `GptmeApiClient`.\n- [references\u002Fwebui-api.md](references\u002Fwebui-api.md) — bundled vs Vite Web UI, multi-backend behavior, frontend development gotchas, markdown paths, message metadata\u002FSSE flow, Step grouping, and `ChatInput` state.\n- [references\u002Facp-and-tui.md](references\u002Facp-and-tui.md) — ACP shim\u002Fdirect\u002Fmodule launch, protocol lifecycle, stdio failure modes, and TUI options\u002Flimitations.\n- [references\u002Fdeployment.md](references\u002Fdeployment.md) — Docker Compose, nginx reverse proxy, systemd service pattern, self-hosting security, and sidecar parent-death behavior.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) — concrete symptoms, causes, and recovery steps for connection, streaming, metadata, ACP, TUI, and deployment failures.\n\n## Safe helper scripts\n\n- [scripts\u002Fprobe_gptme_server.py](scripts\u002Fprobe_gptme_server.py) probes a running server's root page, `\u002Fapi\u002Fv2`, `\u002Fapi\u002Fv2\u002Fversion`, and `\u002Fapi\u002Fv2\u002Fserver\u002Fhealth` with an optional bearer token. It performs only read-only requests and supports `--help`.\n- [scripts\u002Fcheck_webui_message_metadata.py](scripts\u002Fcheck_webui_message_metadata.py) validates representative REST\u002FSSE message dictionaries and compares the metadata fields expected by the Web UI. It supports JSON, JSON lines, and `data: {...}` SSE samples and supports `--help`.\n\n## Fast operating checklist\n\n1. Identify the surface: local server, hosted Web UI, Vite frontend development, TUI, ACP, deployment, or sidecar cleanup.\n2. For browser connection failures, check token, exact CORS origin, and Local Network Access together; each is a separate gate.\n3. For message badge\u002Frendering problems, compare REST conversation payloads with SSE `message_added` and `generation_complete` payloads before changing frontend code.\n4. For ACP, treat stdout as JSON-RPC-only; logs and diagnostics must go to stderr.\n5. For persistent deployments, prefer a stable `GPTME_SERVER_TOKEN`, loopback bind plus reverse proxy, disabled proxy buffering for SSE, and explicit parent-death watching for sidecars.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill server-webui-and-protocols",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill server-webui-and-protocols",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill server-webui-and-protocols","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002FSKILL.md",[46,52,56,60,64,68,74],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Facp-and-tui.md","REFERENCE","参考文档",7415,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002Freferences\u002Facp-and-tui.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdeployment.md",2986,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002Freferences\u002Fdeployment.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fserver-api.md",16268,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002Freferences\u002Fserver-api.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",6273,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fwebui-api.md",9582,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002Freferences\u002Fwebui-api.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_webui_message_metadata.py","SCRIPT","脚本",13585,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002Fscripts\u002Fcheck_webui_message_metadata.py",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fprobe_gptme_server.py",8354,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgptme\u002Fsub-skills\u002Fserver-webui-and-protocols\u002Fscripts\u002Fprobe_gptme_server.py",[79,87,94,101,108,115],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]