UNIFIED CHAT — talk to one or more AI models. mode "chat" (default): 1..N models answer independently in parallel. mode "consensus": ≥2 models answer, then refine after seeing each other. mode "roundtable": models answer sequentially, each building on the running transcript. Supports files, images, and continuation_id for multi-turn threads (you may switch modes on resume). Use model "auto" for automatic selection. IMPORTANT: use the "files" parameter to share code/file content instead of pasting into the prompt.

Check the status and progress of async jobs. Query specific jobs by continuation_id or list the 10 most recent jobs. Returns job status with start time and progress information.

Cancel a running async job by its continuation_id.

Terminates queued or running jobs with graceful cleanup. Preserves partial results when available.

DECIDE — ask a decision model (OpenAI gpt-6-luna, TypeSafe Jev, Cloudflare Clef) typed questions about a state and get calibrated answers, not text. Question types: "noul" (yes/no → probability 0..1), "choice" (pick one of 2–255 named options → choice, per-option probabilities, confidence), "score" (ordered rubric of 2–10 levels → weighted position, per-level probabilities, confidence), "box" (where one target is in an image → left/top/right/bottom edges as 0..1 fractions of width/height, confidence; jev-1.14 / jev-preview only, needs an image, always returns a box, so pair it with a noul asking whether the target is there). Batch independent questions over the same state into one call: they are judged in parallel and in isolation, so none sees another's answer; each extra question adds its own input tokens. Best for fast semantic judgments (classify, route, select, verify, rank). Ask one narrow, coherent judgment per question, with its full meaning in the question; split independently useful dimensions, but a bounded action choice or contextual interpretation is a valid single question. Do counting, arithmetic, and date comparison in code. confidence measures how concentrated the distribution is, not permission to act: take the top option to pick a best, and treat a noul near 0.5 as "yes and no equally likely". No explanations are returned. Images work with gpt-6-luna (PNG/JPEG/WebP), Jev on TypeSafe (PNG/JPEG, 256–1568 px per side, upright pixels: EXIF rotation is ignored), and Clef (PNG/JPEG/WebP, up to 4, ~180 KB total); "auto" skips models that cannot take the images. gpt-6-luna may answer a question with type "refusal" instead of a value: treat it as unanswered, never as a no. Limits per model: Jev ~64k tokens per request (~32k for state plus the longest question), and on TypeSafe a request over that is resent once in long-context mode (262k, slower and less accurate; the result says "long context"); Clef ~64k tokens and at most 64 questions named with letters, digits, "_", ".", "-".