Adds read-only embedded chat mode without hiding permission prompts
Opens subagent sessions in the context panel instead of replacing the main chat
Fixes context panel message loading for embedded sessions
Adds a setting to show or hide OpenCode update notifications
Dismisses the active update toast when notifications are disabled
Adds localized settings labels
Auto-discovery no longer treats a single Project Action as a dev server
Only actions that look like dev, start, preview, or serve commands are used
Prevents lint or other unrelated actions from opening preview
Adds Run fusion for multi-run-like sessions
Combines sibling outputs into a new fusion session
Adds configurable Fusion prompts in Magic Prompts settings
Formats rate-limit reset timestamps in the client timezone
Keeps server-provided reset labels as fallbacks
Applies consistent reset labels across header, usage, and VS Code views
Adds Cycle Agent to shortcut settings with Tab as the default
Applies custom shortcut in chat input and model selector
Updates help dialog to show saved shortcut values
Creates non-Git multi-runs in the same project directory
Shows concise footer info when worktree isolation is unavailable
Displays default model variants with a friendly label
Replace server-enforced structured output with local JSON parsing for Git generation
Render generated commit and PR JSON responses as compact chat cards
Tighten generation prompts while preserving active session context
- Add local Whisper STT via Transformers.js with Web Worker (no UI freeze)
- Default sttProvider to 'local' in Electron (browser STT unavailable)
- Fix infinite toast loop: stop auto-restart on network errors
- Add retry limit with exponential backoff for transient STT errors
- Append voice transcript to input field (append-inline), not replace
- Add model catalog with download/load button in Voice Settings
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
* fix(terminal): clean up idle websocket
* fix(terminal): simplify active reconnect state
---------
Co-authored-by: Isaac Sanchez <isanchez-hawkins@arize.com>
Use existing local PR branches instead of blocking worktree creation
Only block PR branches already checked out in another worktree
Clarify local branch validation messages across locales
Add dedicated Electron Mini Chat windows for focused chat sessions without the full desktop shell. Mini Chat can open existing sessions or draft sessions, supports pinning above other windows, transfers sessions or drafts back to the main window, and deduplicates existing-session windows.
Expose Mini Chat entry points from the main header, session sidebar, command palette, and `mod+alt+n`. Add a dedicated Vite entry and React runtime so the compact surface can stay isolated from full-app chrome while still sharing chat, sync, theme, locale, model, agent, and worktree behavior.
Keep Mini Chat behavior scoped to the compact surface:
- limit assistant/user message actions to the appropriate Mini Chat set
- hide workspace changed-files UI in Mini Chat
- keep draft worktree selection and streaming directory state in sync
- mark sessions viewed while they are open in Mini Chat
- support Mini Chat-specific keyboard shortcuts for input focus, model selection, thinking variant cycling, favorite model cycling, and opening new Mini Chat drafts
Harden Electron integration by gating Mini Chat controls on desktop IPC availability, restricting pin/unpin IPC to Mini Chat windows, and only closing Mini Chat after the main window handoff succeeds.
Conflict resolution prompts now ask for an analysis-first strategy
Response style instructions are wrapped as system reminders
Prompt templates stay separate from reminder formatting
Replace placeholder conflict text with localized copy
Split in-progress operation details and actions into clearer rows
Keep merge and rebase status messages consistent
Add a Stashes dialog with create, apply, pop, and drop actions
Include untracked files automatically when stashing
Show file counts for current changes and stash entries
Combine fetch, pull with rebase, and push into one sync action
Keep remote dropdown focused on safe fetch actions
Block sync when uncommitted changes would conflict with rebase
* feat(chat): add active editor file context and related functionality
* feat(chat): improve active editor file context handling and update translations
* feat(i18n): standardize quotation marks in file attachment messages
* update Korean translation for image removal action in file attachment
* feat(chat): refine active editor file handling and optimize broadcast logic
* fix(chat): stabilize VS Code editor context chips
---------
Signed-off-by: David Saz <david.saz.g@gmail.com>
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
Polls every 2.5s and transitions automatically once the CLI is reachable
Advanced settings and troubleshooting moved into collapsible accordions
New i18n keys added for status indicator and section titles across 6 locales
* fix: add concurrency controls for multiple sessions using the same provider
Adds OS-inspired scheduling primitives (from HiveMind/AIMD research) to prevent
concurrent sessions from the same provider from experiencing slowdowns, random
stops, and cascading failures.
Server-side:
- Health check skips OpenCode restart when sessions are actively busy — a busy
server under concurrent load can fail the health check timeout without being
dead. Staleness guard forces restart if unhealthy+busy persists >2 minutes.
- Upstream SSE stall timeout scaled from 20s to 60s to avoid unnecessary
reconnections when multiple sessions are waiting for LLM responses.
Client-side (HiveMind primitives, arXiv:2604.17111):
- Transparent retry with exponential backoff (1s→2s→4s, max 32s) for
429/502/503/504 errors — the #1 most effective primitive from the paper.
- Circuit breaker: opens after 3 consecutive retryable errors, cooldown
doubles each trip (30s→60s→120s, capped 128s), matching TCP AIMD.
- Per-provider session tracking with TTL eviction (1h idle sweep).
- Fetch-level retry gated on AbortError/TypeError only (not DNS failures).
Refs github-code-review skill findings (all 8 issues resolved).
* fix: use definite assignment assertion for response variable
Fixes TS2454: Variable 'response' is used before being assigned
in strict mode. The for-loop body always assigns it on every path
that reaches the post-loop code, but TS can't prove that.
* fix: add cleanupSession to error paths and remove unreachable code
P1 fixes (Greptile review):
- cleanupSession called on fetch error throw path
- cleanupSession called on non-retryable HTTP error throw path
- Removed unreachable post-loop code (loop always terminates via return or throw)
Adds explicit post-loop throw to satisfy TypeScript strict return check.
* fix: address Greptile review feedback on concurrent session controls
Removes client-side session tracking that leaked on normal completion paths.
The session tracking was redundant — the server-side health check already reads from
sessionRuntime.getSessionActivitySnapshot() for busy-session detection.
Changes:
- Remove activeSessions Set and all session-tracking functions from provider-tracker
- Remove trackSessionStarted/cleanupSession calls from client.ts
- Remove unreachable (response as Response) block after retry loop
- Make upstreamStallTimeoutMs conditional: 60s when >1 sessions, 20s otherwise
Refs #1069
* fix: enforce dynamic concurrency safeguards
---------
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
Bohdan Triapitsyn