* feat(voice): add voice input/output support with multiple providers
- Add BrowserVoiceButton component for Web Speech API voice input
- Add VoiceProvider context for managing voice state across the app
- Add TTS (Text-to-Speech) support with browser, macOS Say, and OpenAI providers
- Add message TTS buttons to read assistant messages aloud
- Add VoiceSettings page in OpenChamber settings
- Add server endpoints for TTS and summarization services
- Include slider component for voice rate/pitch/volume controls
- Add hidden session support for background voice operations
- Add Caddyfile for HTTPS support (required for microphone access)
* fix: Build errors fixed and removed outdated ElevenLabs test code.
* refactor(voice): use zen API with gpt-5-nano for TTS summarization
Replace the hidden session + OpenCode SDK approach with direct calls
to the opencode.ai zen API (same pattern used for commit message and
PR description generation).
- Rewrite summarization-service.js to call zen/v1/responses with gpt-5-nano
- Remove hidden session logic (hiddenSession.ts, sessionStore filtering)
- Remove summarizeModel setting and model selector from VoiceSettings
- Simplify client-side summarize.ts to no longer pass model params
- Clean up callers in useMessageTTS and useBrowserVoice
* fix(voice): remove false 'voice not supported' warning in settings
Mobile Safari does support voice but the isSupported check was
incorrectly flagging it. Remove the warning banner entirely.
* feat(voice): add configurable summary length limit for TTS output
Add a slider (50-2000 chars) in voice settings to control max summary
length. The limit is passed through the summarize endpoint and speak
endpoint to the zen API prompt, with token budget scaled accordingly.
* fix(voice): add diagnostic logging and sanitize TTS fallback
Add console logging throughout the summarization flow (client + server)
to trace why text may not be summarized. Fix silent error swallowing in
/api/tts/speak. Always apply sanitizeForTTS even when summarization is
disabled so raw markdown/code is never spoken verbatim.
* fix(voice): fix token budget starving model of output tokens
max_output_tokens includes both reasoning and output tokens. With
effort:'low', reasoning alone consumes ~128 tokens, so a budget of
100 left zero tokens for the actual summary text. Use a fixed 1000
token budget (matching commit message generation) and control output
length via the prompt's character limit instruction instead.
* chore(voice): remove diagnostic logging from summarization flow
* fix(voice): don't request mic permission on mobile page load
Remove the useEffect that pre-requested microphone permission when the
BrowserVoiceButton component mounted on mobile. This caused an unwanted
permission prompt immediately on page load before the user tapped the
mic icon. Permission is now only requested on explicit user interaction.
* fix(voice): remove unused BrowserVoiceButton binding
* fix(voice): desktop mic flow + non-continuous draft mode
* fix(voice): stabilize continuous loop and polish controls
* feat(settings): mark voice section experimental
---------
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
## What / Why
This PR finishes the desktop refactor: the Tauri app is now a thin shell that launches the web server as a sidecar and loads the UI from `http://127.0.0.1:<port>`. All real backend logic lives in `packages/web/server/index.js`; desktop Rust keeps only native integrations (menu/dialog/notifications/updater/deep-link + window chrome).
This unblocks:
- consistent behavior across web/desktop/vscode (single backend)
- simpler desktop maintenance (no duplicated Rust backend)
- host switching between Local + remote instances in desktop
- reliable cold-start behavior on slow machines (VSCode + desktop)
## Key changes
- Desktop sidecar runtime
- build pipeline to bundle web dist + `openchamber-server` sidecar (`packages/desktop/scripts/build-sidecar.mjs`)
- robust local port selection (prefer saved/default, fallback to random; persisted in `~/.config/openchamber/settings.json`)
- improved PATH handling so the sidecar can locate `opencode` CLI (incl `~/.opencode/bin`, overrides, common bins)
- disable native right-click context menu in production builds (dev keeps it)
- Desktop instance switcher (Tauri-only)
- header button + modal to add/edit/delete remote hosts, set default, probe status/ping, switch back to Local escape hatch
- auth gate includes host switcher so you can recover when a remote host is broken/auth-required
- host list stored desktop-locally (not tied to the currently selected remote server)
- Notifications
- decision logic moved server-side; desktop notifications emitted via sidecar stdout and shown natively by Tauri
- prevent double-notifications on desktop Local origin (UI ignores SSE notification when native path is active)
- restore macOS notification sound
- Updates
- Tauri updater used only when viewing Local instance in desktop shell (avoid “remote web update” triggering desktop restart)
- Settings persistence & UX polish
- persist model favorites/recents via `/api/config/settings` (works for web + desktop; not origin-dependent)
- persist per-project sidebar collapse state in `projects[].sidebarCollapsed` via `/api/config/settings` (with debounce on toggles)
- macOS header sizing/traffic-lights offsets fixed (marketing macOS major injected from desktop; MultiRun header aligned)
- VSCode cold-start: keep retrying provider/agent loads after connection to avoid empty UI on slow machines
- misc lint/type fixes + bun.lock sync
- Desktop bootstrap / resiliency
- show onboarding screen when OpenCode CLI is missing (desktop Local origin), with retry hook to restart OpenCode after install
## Testing notes
- Desktop (macOS): switch Local <-> remote, set default host, verify auth gate recovery, native notifications (with sound), updater gated to Local
- Web: favorites/recents + per-project collapsed state persist across reload/restart
- VSCode: slow startup no longer results in missing providers/agents/models
Remove commitMessageModel from persisted settings and defaults
Eliminate UI controls and state for commitMessageModel in GitSettings and config store
Update backend and persistence layers to stop reading or writing commitMessageModel
Add gitmoji toggle in Git settings to enable emoji support
Show Add gitmoji button in commit section when feature is enabled
Display gitmoji picker dialog with searchable emoji list
* types: add commitMessageModel to DesktopSettings
* store: add commitMessageModel state and fetch logic
* lib: implement persistence for commitMessageModel setting
* ui: create GitSettings component for model selection
* ui: add Git section to OpenChamber settings sidebar
* ui: register GitSectionContent in OpenChamberPage
* server: use commitMessageModel setting for AI generation
* tauri: sanitize commitMessageModel in settings commands
* tauri: use commitMessageModel for desktop message generation
* build: update lockfile and package configuration
* refactor(openchamber): improve default model parsing with fallback logic
* feat(openchamber): improve model selection fallback logic
* refactor: move worktree settings into git section
* refactor(openchamber): merge worktree into git section
* refactor[worktree]: simplify empty state layout
* revert: rollback bun.lock and package.json to main
* feat(git): restrict model selection to OpenCode provider
* feat: Implement project management store with project path validation and synchronization
- Added `useProjectsStore` for managing projects, including adding, removing, renaming, and validating project paths.
- Implemented persistence for projects and active project ID using safe storage.
- Introduced synchronization from desktop settings to keep project data consistent.
- Enhanced session store to manage sessions by directory and added new methods for session management.
- Updated todo store to fetch session todos based on the directory context.
- Refactored server code to validate and resolve project directories for various API endpoints.
- Added project entry validation and sanitization to ensure data integrity.
* feat(settings): migrate legacy project settings and update settings loading logic
* feat: enhance project management with directory-aware settings and improved agent/command source handling
* feat: enhance session and project management with directory-aware settings and improved configuration refresh logic
* feat: enhance project management with worktree manager integration and project directory resolution
* feat: enhance agent groups store with project directory resolution and loading logic
* feat: add heartbeat management and global wrapping for SSE blocks in agent and chat providers
* feat: refactor command and project handling in useCommandsStore
- Replaced useDirectoryStore with useProjectsStore to manage project paths.
- Introduced getRequestDirectory function to determine the active project directory.
- Updated command fetching to respect project-level scoping.
- Enhanced error handling and logging for command configuration fetching.
- Improved command configuration saving and updating to utilize project directory context.
feat: enhance project path normalization in useProjectsStore
- Added resolveTildePath function to expand paths starting with ~.
- Updated normalizeProjectPath to utilize home directory for path expansion.
fix: update permission handling in useSessionStore
- Changed Permission type to PermissionRequest for clarity.
- Updated respondToPermission method to use requestId instead of permissionId.
refactor: improve permission utilities
- Introduced types for PermissionAction and PermissionRule.
- Enhanced getAgentDefinition and resolveConfigStore functions for better type safety.
- Added resolvePermissionAction to streamline permission resolution logic.
feat: add agent configuration retrieval endpoint
- Implemented new API endpoint to fetch agent configuration based on project directory.
- Enhanced getAgentPermissionSource to prioritize project-level permissions.
chore: update SDK version in package.json files
- Bumped @opencode-ai/sdk version to ^1.1.1 across all relevant package.json files.
refactor: streamline bridge message handling
- Updated handleBridgeMessage to accept directory parameter for agent and command requests.
- Improved local API request handling to extract directory from query parameters and headers.
feat: enhance project configuration management
- Added functions to retrieve and merge project configuration paths.
- Improved handling of existing project configuration files for agents and commands.
* feat: enhance VSCode integration and session management
- Added support for a sticky sidebar header background in light and dark themes.
- Introduced functions to read VSCode workspace directory and check if running in VSCode.
- Implemented detailed logging for session loading and creation processes.
- Enhanced session filtering based on directory structure and canonical paths.
- Added a new method to reorder projects and prevent modifications in VSCode workspace.
- Improved error handling and logging for app initialization and markdown file parsing.
- Updated API checks and health checks to ensure readiness before proceeding.
- Refactored code for better readability and maintainability across various modules.
* feat: improve agent and branch selection logic, enhance session management, and update multi-run creation response
* feat: add worktree management actions in agent group detail and sidebar, including delete and keep only options
* fix(ui): share IME guard and cover multi-run
* fix(session): reduce maximum visible sessions in group from 7 to 5
Update all import statements to use @opencode-ai/sdk/v2
Modify Vite configurations to alias new SDK path
Update API client method signatures for SDK v2 compatibility
Bohdan Triapitsyn