openpencil/tools/checks
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
..
architecture test(core): move the fig round-trip suite home, and stop test imports drilling 2026-10-01 14:11:53 +04:00
docs build(tools): group tools by role and gate them like the rest of the repo (#791) 2026-09-30 05:00:31 +04:00
i18n feat(ai): choose a thinking level per message (#809) 2026-10-03 13:30:05 +04:00
lint build(tools): group tools by role and gate them like the rest of the repo (#791) 2026-09-30 05:00:31 +04:00
package-quality refactor: print OpenPencil JSX export as syntax trees (#799) 2026-10-01 21:22:43 +04:00
secret-scan build(tools): group tools by role and gate them like the rest of the repo (#791) 2026-09-30 05:00:31 +04:00
test-homes test(core): move the fig round-trip suite home, and stop test imports drilling 2026-10-01 14:11:53 +04:00
type-shapes build(tools): group tools by role and gate them like the rest of the repo (#791) 2026-09-30 05:00:31 +04:00