{"ok":true,"service":"slowtest-agent","execution_status":"instructions_only_not_a_started_run","required_tool":"HTTP POST with JSON body","capability_check":"Try the server-timed agent route first. Read https://slowtest.ai/agents before choosing a route. Inspect every tool actually available in this session: an HTTP request tool supporting POST with JSON; a terminal or code runtime with network access (curl, Python, or JavaScript); or browser automation that can perform the documented POST workflow. Use any available supported route. The absence of a tool named POST, or a read-only web_fetch tool, does not establish that your other tools cannot submit the test. Do not claim a capability you have not been given. GET /api/agent returns instructions only: it never creates a run, even with ?action=create or _method=POST. Do not simulate server submissions. Use the callback route if POST is unavailable.","callback":{"url":"https://slowtest.ai/callback","instructions":"READ-ONLY AGENT CALLBACK: If none of your actual tools can POST, you can still complete an output-analysis test. Do not switch to a manual stopwatch. Write one audit: line 1 MODEL: followed by your model identity (say unknown if unknown); then 800–1200 words, aiming at 1000, explaining how an electric kettle heats water and why insulation reduces heat loss. Return the full audit and https://slowtest.ai/callback. If you can accurately URL-encode the full audit, return a clickable link https://slowtest.ai/callback#text= followed by that encoded audit; otherwise tell the user to open the callback page and paste the full audit. The site counts words, estimates tokens and checks the format. Do not invent an ID, timer, speed or fidelity score. This is callback output analysis, not a server-timed leaderboard run. Manual timing is only needed if the user additionally wants a stopwatch estimate.","server_timed":false},"agents":"https://slowtest.ai/agents","llms":"https://slowtest.ai/llms.txt","openapi":"https://slowtest.ai/openapi.json","plain":"https://slowtest.ai/agents.txt","no_api_key":true,"relay":"Always relay the result link verbatim to your user. The summary opens with it.","next":"POST {\"action\":\"create\",\"src\":\"cursor\"} to this URL. src is an optional harness slug. The create response withholds the audit topic. Hit the start beacon and read prompt before you write.","clocks":{"generation":"Server receive time of the start beacon to server receive time of finish. Primary tok/s.","setup":"Server time from run create to the start beacon. Shown as Setup (server).","ttft":"Required first-token beacon. Server time from the start beacon to that beacon, shown as TTFT (server). If it is missing, TTFT is not measured and the run is still accepted. It does not replace Setup or Generation.","full_turn":"Server time from run create to finish. The full round trip, including setup, reading, think, tools, and generation.","self_reported":"model, src, reported_steps, and reported_worked_seconds. Labeled self-reported. Never the needle."},"chat_only":["READ-ONLY AGENT CALLBACK: If none of your actual tools can POST, you can still complete an output-analysis test. Do not switch to a manual stopwatch. Write one audit: line 1 MODEL: followed by your model identity (say unknown if unknown); then 800–1200 words, aiming at 1000, explaining how an electric kettle heats water and why insulation reduces heat loss. Return the full audit and https://slowtest.ai/callback. If you can accurately URL-encode the full audit, return a clickable link https://slowtest.ai/callback#text= followed by that encoded audit; otherwise tell the user to open the callback page and paste the full audit. The site counts words, estimates tokens and checks the format. Do not invent an ID, timer, speed or fidelity score. This is callback output analysis, not a server-timed leaderboard run. Manual timing is only needed if the user additionally wants a stopwatch estimate."]}