LongCat 2.5 Preview in OpenCode 1.18.32
skills off
The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. It starts in its auto-tour (T switches to play mode on a keyboard).
drawing unverified.
Wall time 42m 56sCost $0 reported
Generation timelapse
Generation timelapse (the agent's screen during the run, sped up). This is not the finished video. Download video (602 KB).
Review
No verdict yet.
The full review
Stopped by us. Stopped by us (box row cap reached (2862s); stopped by the box lane so the run ships as partial); not a model failure.
Scores
Not scored: only runs that finished on their own are scored.
Downloads
Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.
The exact prompt
as run, 725 characters. Every result for this prompt
Build a conceptual X-16 engine in 3D with Three.js: four cylinder banks, one crankshaft and exposed mechanics inspired by experimental multi-bank engine architectures. Make it animate (pistons, rods and crank moving in sync) with orbit controls. Everything is built in code from Three.js geometry, shaders and materials; no external models or textures. Build it as a single self-contained index.html in the current directory. Three.js may load from a CDN or be vendored. You may serve it locally and open it in headless chromium (/usr/bin/chromium, software WebGL, no GPU) to screenshot and inspect your own output, and iterate on your own before finishing. Close any browser you open as soon as you've taken your screenshot.
How it was made
Versions saved during the run
8 intermediate outputs, in the order the model wrote them.
Step by step
The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full transcript is 3.0 MB; it is published as a scrubbed, compressed download rather than shown on the page.
Show all 135 steps
Loading the timeline…
Download the full transcript OpenCode session export, 96 KB, gzip. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.
Cost breakdown
Headline cost $0, as reported by OpenCode (its own bill for the run).
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 100,424 | n/a | n/a |
| Cache write | 0 | n/a | n/a |
| Cache read | 3,326,208 | n/a | n/a |
| Output | 68,473 | n/a | n/a |
- Total computed from tokens
- unknown
- Total reported by the harness
- $0
OpenCode 1.18.32 reported its own total; token counts x list prices shown beside it. No list price for longcat-2.5-preview-free in config/prices.json; no estimate computed. The harness reports reasoning tokens separately from output; here output includes them (16,481 visible + 51,992 reasoning), and both bill at the output rate.
Run notes
- frozen prompt (written): engine/prompts_written/x16_engine.txt: a new test's prompt written by us from the project lead's brief (zero results)
- plain OpenCode config copy (providers only; no ECC instructions/agents)
- opencode export written to a file (not piped)
- Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
- Isolation audit: outside paths seen