openpencil/tests/engine/app
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
..
ai feat(ai): choose a thinking level per message (#809) 2026-10-03 13:30:05 +04:00
automation feat(settings): configure tool access, MCP failures, and step limits 2026-09-17 23:55:58 +03:00
chat feat(ai): choose a thinking level per message (#809) 2026-10-03 13:30:05 +04:00
clipboard fix(clipboard): preserve component dependency references 2026-09-13 12:46:31 +03:00
code feat(code): add live JSX and HTML/CSS editing (#525) 2026-08-15 09:48:42 +03:00
demo feat: assemble an editable demo document 2026-09-14 00:36:53 +03:00
diagnostics feat(settings): configure tool access, MCP failures, and step limits 2026-09-17 23:55:58 +03:00
document feat: export components as Storybook stories (#751) 2026-09-30 03:16:47 +04:00
editor feat: export components as Storybook stories (#751) 2026-09-30 03:16:47 +04:00
integrations fix: restore engine test coverage and isolation (#653) 2026-09-06 23:29:45 +03:00
recent-files refactor(app): polish files workspace and New tabs 2026-08-20 17:20:33 +03:00
runtime perf(canvas): rebuild navigation rendering (#591) 2026-08-31 13:39:40 +03:00
settings feat(settings): configure tool access, MCP failures, and step limits 2026-09-17 23:55:58 +03:00
shell feat(updater): show download progress while installing an update 2026-09-25 23:15:14 +04:00
storage fix(storage): harden workspace previews 2026-08-10 20:02:58 +03:00
tabs feat(app): prepare documents atomically per tab (#592) 2026-08-30 12:21:49 +03:00
tauri fix(tauri): preserve request and abort semantics 2026-07-18 05:02:51 +03:00
usage feat(diagnostics): add local usage and diagnostics foundation 2026-08-24 16:56:40 +03:00
cache.test.ts refactor(app): polish files workspace and New tabs 2026-08-20 17:20:33 +03:00
demo.test.ts feat(demo): rebuild the first page as a component library with staged loading (#717) 2026-09-18 08:18:21 +03:00
external-link.test.ts test: move tauri helpers into domain folder 2026-05-06 16:16:08 +03:00
font-loading.test.ts fix(tauri): prevent Windows font loading crashes (#497) 2026-08-12 20:09:04 +03:00
vector-edit-transforms.test.ts fix(editor): commit vector drags on pointer release (#586) 2026-08-24 16:02:27 +03:00