Commit Graph
7 Commits
Author SHA1 Message Date
Bohdan Triapitsyn bb45164ae8 feat: session goals - server-driven goal loop with independent small-model audit (#2148)
Arm the target button in the composer and the next prompt becomes a goal:
the server keeps the session working toward it (idle tick -> small-model
audit -> continuation) until the objective is verifiably complete, blocked,
or out of budget — even with the UI closed.

Server (packages/web/server/lib/session-goal):
- event-driven loop on the global SSE hub; goal state lives in
  session.metadata.openchamber.goal (merge-safe patches, stale-write guard
  by goal id), so it survives restarts and syncs to every client for free
- the small-model audit (objective + last assistant turn only, language
  pinned to the objective) is the sole termination authority; blocked needs
  3 consecutive verdicts, audit outages tolerate one unaudited continuation
  then stop the goal as resumable-blocked
- hard stops: optional token budget, auto-continuation cap (Resume grants a
  fresh allowance), turn errors; user abort pauses the goal instead of
  blocking it, and resuming over an aborted tail nudges immediately
- token accounting as a snapshot of the latest turn (input + cache.read +
  output), goal-relative via a creation baseline and segmented across
  compactions; a compaction summary skips the audit and continues
- continuations reuse the session's own provider/model/agent/variant

UI:
- three-mode target button (arm / disarm / manage dialog), informational
  goal strip with inline pause/resume and an Evaluating indicator, sidebar
  state glyph, objective length counter (2000-char server clamp),
  read-only completed goals
- goal entry points: composer (sessions and drafts), start-new-session-
  from-answer dialog, plan implement dialog (plan content becomes the
  objective), scheduled tasks (Run as goal + budget)
- Settings -> Chat -> Goal: feature toggle + default token budget with
  three-layer parity (web server, client persistence, VS Code bridge);
  VS Code renders goal state but hides the entry points (the loop runs in
  the web server only)

Notifications: per-turn "ready" notifications are suppressed while a goal
is active; settling sends one final notification (desktop, web-push, APNs
generic titles with the session name as body) honoring the completion
toggle. Error/question/permission notifications are untouched.

Docs: user guide (session-goals) in all 9 locales + sidebar entry,
scheduled-tasks cross-reference, server module DOCUMENTATION.md.
2026-07-12 01:23:22 +03:00
Bohdan Triapitsyn e192359da9 fix: improve startup readiness performance 2026-06-05 15:09:24 +03:00
Bohdan Triapitsyn 6a88cd09cc feat: add dialog for "Start new session from this answer" (#1501)
* feat: add dialog for "Start new session from this answer"

Replace the one-click fork action on assistant messages with a dialog
(ForkSessionDialog) that lets the user pick model, thinking level, and
agent, plus edit the instructions sent to the new session.

The instructions field is prefilled with the previous fixed fork prompt
and is mandatory. The composed message is now fully visible (no synthetic
preface): the user's instructions sit above a short fixed connective that
opens the assistant content. createSessionFromAssistantMessage takes the
chosen execution params instead of reading from config.

Also fix TodoSendDialog visuals: narrower vertical layout, model trigger
no longer stretches with centered text, and the agent/thinking dropdowns
portal to body so opening them no longer nudges the dialog height. Extract
the shared ThinkingPill into its own component.

* fix: address review feedback on fork session dialog

- Fix "bellow" -> "below" typo in the fork content preface (now user-visible
  since the message is no longer synthetic)
- Reset ForkSessionDialog state only on open transition, reading the config
  store snapshot via getState() so background store refreshes can't discard
  in-progress instruction edits
2026-06-02 12:53:30 +03:00
Robert HamiltonandBohdan Triapitsyn cc3d1bd63c fix: improve todo send dialog model picker (#1426)
* fix: improve todo send dialog model picker

* fix: truncate long model selector labels

---------

Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
2026-05-26 20:46:30 +03:00
Bohdan Triapitsyn 14357257ae perf(ui): migrate icons to SVG sprite system
Replace @remixicon/react with a shared Icon component that renders
via <use href> references to a single hidden SVG sprite. This reduces
DOM node count by replacing inline SVGs with lightweight references.

- Create Icon component with sprite injection (packages/ui/src/components/icon/)
- Migrate all 164 files from @remixicon/react to Icon component
- Auto-generate sprite data from remixicon bundle (scripts/generate-icon-sprite.mjs)
- Add bun run icons:generate to package.json
- Move @remixicon/react to devDependencies
- Add icon usage instructions to theme-system skill
2026-05-13 13:26:35 +03:00
Bohdan Triapitsyn 7d7285655d Add i18n foundation and translations (#1027)
* feat: add i18n foundation

* feat: localize sessions sidebar

* Localize multirun/scheduled tasks and fix dialog dropdown interactions

* localize git sidebar surface and add zh-CN keys

* feat(ui): localize context panel, diff/plan views, and context sidebar content

* fix(config): resolve user config home via fs/home before embedded home

* localize header/chat UI and complete model/worktree panel strings

* localize worktree + github issue/pr dialog flows

* localize settings sections and split settings i18n dictionaries

* localize additional settings sections and sidebars

* localize more settings pages and dialogs

* fix settings select trigger localization

* localize tunnel settings ui surface

* localize additional settings sections

* localize keyboard shortcuts labels in settings

* localize terminal and utility dialogs surfaces

* feat(i18n): localize remaining UI strings

* Add Ukrainian locale

* Add Spanish locale

* Add Brazilian Portuguese locale

* Polish locale translations
2026-04-26 14:03:39 +03:00
Bohdan Triapitsyn a7bc2a228c feat(todos): send todo to new session or worktree with model/agent/variant picker
Add a dedicated TodoSendDialog that lets the user pick provider/model,
reasoning variant and agent before opening a new session (or a fresh
worktree branch) pre-seeded with the todo text and a hidden instructions
prompt (plan.todo).
2026-04-18 13:47:11 +03:00