openpencil/tests
Danila Poyarkov 0ff6b414e3
feat(ai): choose a thinking level per message (#809)
Reasoning effort was a free-text profile field that only reached OpenAI
and OpenRouter, so Anthropic, Google, and DeepSeek models never thought
in direct chat. AI SDK 7 standardizes a `reasoning` call option that
those providers map to their own thinking settings, so profiles now
store one typed thinking level, shared with Pi, and requests pass it
through that option. OpenRouter's provider ignores the standard option
and receives its own reasoning option instead.

The composer offers the level next to the Design profile and reads it
per request, so a change applies to the next message without
rebuilding the transport. Saved profiles migrate from the Pi level or
the old effort string. Finished reasoning shows how long the model
thought while the block streamed.
2026-10-03 13:30:05 +04:00
..
app feat(ai): choose a thinking level per message (#809) 2026-10-03 13:30:05 +04:00
e2e feat(ai): choose a thinking level per message (#809) 2026-10-03 13:30:05 +04:00
engine feat(ai): choose a thinking level per message (#809) 2026-10-03 13:30:05 +04:00
figma
fixtures fix(tests): let the app Playwright suite load every spec (#842) 2026-10-03 12:39:53 +04:00
helpers feat(ai): choose a thinking level per message (#809) 2026-10-03 13:30:05 +04:00
integration feat(fig): occurrence-scoped instance interpretation as the single .fig reader 2026-10-01 11:20:27 +04:00
AGENTS.md test(core): move the fig round-trip suite home, and stop test imports drilling 2026-10-01 14:11:53 +04:00