[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CTB43221ABW9S023D73XMF":3,"skill-same:01M7CTB43221ABW9S023D73XMF":44},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7CTB43221ABW9S023D73XMF","run-load-test",null,"Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test \u002F stress-test \u002F benchmark Omnigent under concurrency (\"load test omnigent\", \"stress test the server\", \"how many hosts\u002Fsessions\u002Fturns can it handle\", \"load test real agent turns \u002F conversations\", \"run a load test\"). The test makes each simulated user a real omnigent host that creates host-bound sessions and drives real multi-turn conversations with a mocked LLM; it boots its own local stack (dev\u002Floadtest\u002Frun.py). Gather inputs, run it, then read the generated summary.md and explain the latency distribution (avg\u002Fmedian\u002Fp95\u002Fp99, throughput, failures). NOT for single-request latency micro-benchmarks (that is dev\u002Fbenchmarks\u002F).","roland-id-au\u002Fomniagent","roland-id-au","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2590653?v=4","01M7CT4DEBVK4R185WFWCWN4JD","Buck Chancey","01M7CT4DFGWX49CGE347EF4V6T",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002F.claude\u002Fskills\u002Frun-load-test\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: run-load-test\ndescription: Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test \u002F stress-test \u002F benchmark Omnigent under concurrency (\"load test omnigent\", \"stress test the server\", \"how many hosts\u002Fsessions\u002Fturns can it handle\", \"load test real agent turns \u002F conversations\", \"run a load test\"). The test makes each simulated user a real omnigent host that creates host-bound sessions and drives real multi-turn conversations with a mocked LLM; it boots its own local stack (dev\u002Floadtest\u002Frun.py). Gather inputs, run it, then read the generated summary.md and explain the latency distribution (avg\u002Fmedian\u002Fp95\u002Fp99, throughput, failures). NOT for single-request latency micro-benchmarks (that is dev\u002Fbenchmarks\u002F).\n---\n\n# Run the Omnigent load test\n\nDrives `dev\u002Floadtest\u002F` end to end: collect inputs → run → read `summary.md` →\nexplain the latencies. **Each Locust user is a real `omnigent host`** that\nregisters over the host tunnel, creates host-bound sessions, and drives **real\nmulti-turn conversations** — every turn is a genuine post→idle loop through the\nhost's runner, with the **LLM mocked** (zero latency) so the numbers are\nOmnigent's own overhead. `-u N` scales the number of hosts.\n\nIt **boots its own local stack** (server + mock LLM), so there is no server to\npoint at, and it runs **from a repo checkout** only. For single-request latency\nmicro-benchmarks (not concurrency), that is a different tool: `dev\u002Fbenchmarks\u002F`.\n\n## 1. Ensure deps (repo checkout)\n\n```bash\nuv sync --extra loadtest --extra agents-sdk\n```\n\nRun with that same interpreter (e.g. `.venv\u002Fbin\u002Fpython`), from the repo root.\n\n## 2. Gather inputs\n\nAsk the user (AskUserQuestion when several are unknown); all have defaults.\n\n| Input | Flag | Default | Notes |\n|---|---|---|---|\n| Hosts | `--users` | 4 | Concurrent hosts (N) — the main scale knob. |\n| Spawn rate | `--spawn-rate` | 1 | Hosts started per second. |\n| Run time | `--run-time` | 120s | `40s` \u002F `5m` \u002F `1h`. |\n| Sessions\u002Fhost | `--sessions-per-user` | 2 | Host-bound sessions each host drives. |\n| Turns\u002Fsession | `--turns-per-session` | 4 | Turns per session — history grows across them. |\n| Reply length | `--reply-words` | 60 | Words in the mocked (streamed) reply per turn. |\n\n**Capacity caveat — say this to the user if they ask for large N:** turns run on\nreal host + runner subprocesses, so N hosts × M sessions = N×M runner processes\non *this* box. It is capacity-limited by design (real turns, not faked). Start at\n`--users 2 --sessions-per-user 1 --turns-per-session 2 --run-time 40s` to confirm\nthe stack boots (~10-30s), then ramp to a few dozen hosts at most. At high N the\nload box saturates before the server (Locust warns about CPU).\n\n## 3. Run\n\n```bash\npython dev\u002Floadtest\u002Frun.py \\\n    --users \u003CN> --spawn-rate \u003CR> --run-time \u003CT> \\\n    --sessions-per-user \u003CS> --turns-per-session \u003CTU>\n```\n\nIt boots the stack, prints the server URL + registered agent, runs Locust, and\nwrites `dev\u002Floadtest\u002Fresults\u002Fomnigent_load_test-\u003Ctimestamp>\u002F`.\n\n## 4. Read and explain\n\n`Read` the `summary.md` and relay it. Focus on:\n\n- **Outcome \u002F failures** first. Exit 0 + 0 failures = PASS. Non-zero failures are\n  the headline — check `console.log` and, for a host that failed to register,\n  the per-host `results\u002F...\u002Fhost-workspaces\u002F\u003Cname>\u002Fhost.log`. At high N, failures\n  usually mean the *load box* saturated, not the server.\n- **turn** — the headline latency: one full post→idle agent turn on a host's\n  runner (mocked LLM), so it is Omnigent's per-turn overhead. It **grows across a\n  conversation** as history accumulates, so a rising p95\u002Fp99 with larger\n  `--turns-per-session` is expected and is the interesting signal.\n- **host online** — host tunnel registration cost; **session create** — the\n  host-bound create; **Ops\u002Fs** — aggregate throughput at this concurrency.\n\nIf failures appeared or the tail looks high, suggest a concrete next step (lower\nN if the load box is saturated, raise `--turns-per-session` to study history\ngrowth, lengthen `--run-time` for steady state, or check server logs\u002Fmetrics).\n\n## Notes\n\n- Scenario file: `dev\u002Floadtest\u002Fomnigent_load_test.py`; driver + report:\n  `dev\u002Floadtest\u002Frun.py`. Full reference: `dev\u002Floadtest\u002FREADME.md`.\n","# Run the Omnigent load test\n\nDrives `dev\u002Floadtest\u002F` end to end: collect inputs → run → read `summary.md` →\nexplain the latencies. **Each Locust user is a real `omnigent host`** that\nregisters over the host tunnel, creates host-bound sessions, and drives **real\nmulti-turn conversations** — every turn is a genuine post→idle loop through the\nhost's runner, with the **LLM mocked** (zero latency) so the numbers are\nOmnigent's own overhead. `-u N` scales the number of hosts.\n\nIt **boots its own local stack** (server + mock LLM), so there is no server to\npoint at, and it runs **from a repo checkout** only. For single-request latency\nmicro-benchmarks (not concurrency), that is a different tool: `dev\u002Fbenchmarks\u002F`.\n\n## 1. Ensure deps (repo checkout)\n\n```bash\nuv sync --extra loadtest --extra agents-sdk\n```\n\nRun with that same interpreter (e.g. `.venv\u002Fbin\u002Fpython`), from the repo root.\n\n## 2. Gather inputs\n\nAsk the user (AskUserQuestion when several are unknown); all have defaults.\n\n| Input | Flag | Default | Notes |\n|---|---|---|---|\n| Hosts | `--users` | 4 | Concurrent hosts (N) — the main scale knob. |\n| Spawn rate | `--spawn-rate` | 1 | Hosts started per second. |\n| Run time | `--run-time` | 120s | `40s` \u002F `5m` \u002F `1h`. |\n| Sessions\u002Fhost | `--sessions-per-user` | 2 | Host-bound sessions each host drives. |\n| Turns\u002Fsession | `--turns-per-session` | 4 | Turns per session — history grows across them. |\n| Reply length | `--reply-words` | 60 | Words in the mocked (streamed) reply per turn. |\n\n**Capacity caveat — say this to the user if they ask for large N:** turns run on\nreal host + runner subprocesses, so N hosts × M sessions = N×M runner processes\non *this* box. It is capacity-limited by design (real turns, not faked). Start at\n`--users 2 --sessions-per-user 1 --turns-per-session 2 --run-time 40s` to confirm\nthe stack boots (~10-30s), then ramp to a few dozen hosts at most. At high N the\nload box saturates before the server (Locust warns about CPU).\n\n## 3. Run\n\n```bash\npython dev\u002Floadtest\u002Frun.py \\\n    --users \u003CN> --spawn-rate \u003CR> --run-time \u003CT> \\\n    --sessions-per-user \u003CS> --turns-per-session \u003CTU>\n```\n\nIt boots the stack, prints the server URL + registered agent, runs Locust, and\nwrites `dev\u002Floadtest\u002Fresults\u002Fomnigent_load_test-\u003Ctimestamp>\u002F`.\n\n## 4. Read and explain\n\n`Read` the `summary.md` and relay it. Focus on:\n\n- **Outcome \u002F failures** first. Exit 0 + 0 failures = PASS. Non-zero failures are\n  the headline — check `console.log` and, for a host that failed to register,\n  the per-host `results\u002F...\u002Fhost-workspaces\u002F\u003Cname>\u002Fhost.log`. At high N, failures\n  usually mean the *load box* saturated, not the server.\n- **turn** — the headline latency: one full post→idle agent turn on a host's\n  runner (mocked LLM), so it is Omnigent's per-turn overhead. It **grows across a\n  conversation** as history accumulates, so a rising p95\u002Fp99 with larger\n  `--turns-per-session` is expected and is the interesting signal.\n- **host online** — host tunnel registration cost; **session create** — the\n  host-bound create; **Ops\u002Fs** — aggregate throughput at this concurrency.\n\nIf failures appeared or the tail looks high, suggest a concrete next step (lower\nN if the load box is saturated, raise `--turns-per-session` to study history\ngrowth, lengthen `--run-time` for steady state, or check server logs\u002Fmetrics).\n\n## Notes\n\n- Scenario file: `dev\u002Floadtest\u002Fomnigent_load_test.py`; driver + report:\n  `dev\u002Floadtest\u002Frun.py`. Full reference: `dev\u002Floadtest\u002FREADME.md`.\n",{"name":5,"description":7},"deploy\u002Froland-id-au-omniagent","83ee3dcd78468bbe3baf4bb264a0c99a53aa0fec","work\u002Fomnigent-main\u002F.claude\u002Fskills\u002Frun-load-test","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent","https:\u002F\u002Fgithub.com\u002Froland-id-au","2026-09-16 03:15:34",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add roland-id-au\u002Fomniagent --skill run-load-test",{"tool":36,"command":37},"bunx","bunx skills add roland-id-au\u002Fomniagent --skill run-load-test",{"tool":39,"command":40},"pnpm","pnpm dlx skills add roland-id-au\u002Fomniagent --skill run-load-test","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002F.claude\u002Fskills\u002Frun-load-test\u002FSKILL.md",true,[],[45,52,59,66,71,76],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7CTDVNPM78AJ051GVDB44X5","deep-research","Research checklist and source-quality guidance for the archer e2e fixture.","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002Ftests\u002Fresources\u002Fexamples\u002Farcher\u002Fskills\u002Fdeep-research\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7CTDS8SPN8P5GK1Q4SCSY7K","pi-e2e-xyz-greet-c4a8d5","Test greeter — pi skills e2e. The unique suffix c4a8d5 appears in the skill name so a string match in the agent's output proves Pi loaded this skill.","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002Ftests\u002Fresources\u002Fagents\u002Fpi_skills_none\u002Fskills\u002Fpi-e2e-xyz-greet-c4a8d5\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7CTDP4R9F06966W78WNZS2Y","pi-e2e-xyz-count-d2f6e1","Test counter — pi skills e2e. The unique suffix d2f6e1 appears in the skill name so a string match in the agent's output proves Pi loaded this skill.","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002Ftests\u002Fresources\u002Fagents\u002Fpi_skills_none\u002Fskills\u002Fpi-e2e-xyz-count-d2f6e1\u002FSKILL.md",[],[],{"skillNo":67,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CTDKP4W1Q18ZCY0XANDSEG","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002Ftests\u002Fresources\u002Fagents\u002Fpi_skills_list\u002Fskills\u002Fpi-e2e-xyz-greet-c4a8d5\u002FSKILL.md",[],[],{"skillNo":72,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7CTDFBMA3EBZNV7J380THGP","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002Ftests\u002Fresources\u002Fagents\u002Fpi_skills_list\u002Fskills\u002Fpi-e2e-xyz-count-d2f6e1\u002FSKILL.md",[],[],{"skillNo":77,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7CTDCVTXTG72BKEV2HY7M6W","https:\u002F\u002Fgithub.com\u002Froland-id-au\u002Fomniagent\u002Fblob\u002Fdeploy\u002Froland-id-au-omniagent\u002Fwork\u002Fomnigent-main\u002Ftests\u002Fresources\u002Fagents\u002Fpi_skills_all\u002Fskills\u002Fpi-e2e-xyz-greet-c4a8d5\u002FSKILL.md",[],[]]