* fix: resolve Windows CLI module loading on absolute paths
* fix: improve chat tool rows layout and timestamp readability
* fix: make web update restart more reliable
* fix: make web self-update detect package manager correctly
* feat(chat): add shared activity timestamp formatter
* feat(chat): pass assistant created timestamp to message body
* feat(chat): render footer timestamp beside elapsed time
* feat(chat): pass timing metadata in reasoning text blocks
* feat(chat): propagate justification timing to timeline block
* feat(chat): show thinking duration with hover end time
* feat(chat): reveal tool end time on activity hover
Display the actual subagent type (e.g., 'general', 'build') instead of hardcoded
'subAgent' in the task tool button. Changes 'session' to 'subtask' for consistency.
- Add input prop to TaskToolSummary component
- Extract subagent_type from task input
- Capitalize agent type and update button text format
* feat: add project actions in header with reliable terminal run flow
- Add per-project Actions settings with icons, platform filters, and default action
- Run/stop actions from header using terminal tabs, including Ctrl+C then force-kill fallback
- Improve terminal UX with stable selection, resize handling, and smarter URL auto-open for localhost ports
* feat: add project actions UI with refined header dropdown behavior
* feat: add parent-session back button in chat
* fix: make web and desktop dev modes reliable and conflict-free
- Separate desktop and web dev ports to avoid collisions
- Add robust process-tree shutdown so Ctrl+C cleans sidecars
- Add true web HMR mode and keep service worker out of dev
* fix: linux safe scripts for dev
* feat: run project actions on web and add desktop SSH forward URL opening
* feat: add mobile project actions button with terminal tabs and tighter tab UI
* revert: remove experimental mobile terminal selection UI
* feat: show Add action button in header when empty
* fix: make retry countdown human-readable in status row
* fix: prevent nav rail actions from firing through overlays
- Use active session prompts for commit/PR generation and drop backend git generation routes.
- Improve tool activity UX with Structured Output rendering, description styling tweaks, and detailed-mode expansion fixes.
* feat(chat): add mermaid preview popups and fullscreen diagram viewer
Enable opening Mermaid diagrams from markdown and file attachments with a dedicated fullscreen dialog, while tightening preview loading behavior and sizing for more reliable interaction.
* refactor(chat): extract shared preview overlay hooks
Centralize fullscreen preview transition and viewport lifecycle logic so image and Mermaid dialogs stay behaviorally aligned while reducing maintenance overhead.
* fix(security): enforce workspace boundaries for fs read endpoints
Validate /api/fs/read and /api/fs/raw paths against active workspace roots and canonical realpaths to block traversal and symlink escapes before serving file contents.
* fix(chat): remove dead Mermaid copy component
Drop an unused merge-leftover component in MarkdownRenderer to keep lint clean without changing Mermaid preview behavior.
* fix: stale model variants in chat controls in draft session
* fix: attention indicator for project tabs
* fix: use part index and type for consistent IDs
* fix question card navigation for unanswered questions
* feat: reload interface after skills operations
- Adds configurable delay before interface reload after skills changes
- Introduces polling to wait for application health after reload
- Updates UI to show reload message when installing or modifying skills
* feat: distinguish skills from commands in UI
- Displays skill badge for commands that are registered skills
- Prevents editing skills through command management interface
- Triggers interface reload after skill operations to reflect changes
* feat(chat): align command and subtask UX with opencode parity
Route commands/shell via parity paths, render delegated subtasks cleanly, and surface child-session permission/question prompts in parent chat.
* fix(ProjectEditDialog): improve layout consistency
* fix: update task icon and session handling in ToolPart
* feat(chat): add shell-mode input and collapse shell bridge output
Switch leading ! to shell mode UX and fold synthetic shell bridge assistant messages into the user shell bubble with inline output actions.
* fix: remove AI agent icon from file mention autocomplete
* fix: remove unused icon import from file mention component
* feat: show current branch in empty chat state
* fix: display current git branch for worktrees and update them with branch change
* refactor: improve read tool output parsing with structured data
* feat: add support for message part delta events
* fix(chat): improve streaming rendering, scroll behavior, and assistant action visibility
* feat: Add mermaid diagram support to chat markdown rendering
* fix: update table download functionality to include success notification and remove unused MarkdownRenderer import
* refactor: streamline Streamdown component props for improved readability
* fix: preserve Streamdown code-block markers and use native Tauri cache clearing
* feat: add context overview panel to view conversation details
* hive(01-add-mobile-autocorrect-to-commit-message-input): Added mobile autocorrect to commit message input.
* hive(02-add-mobile-autocorrect-to-pr-title-inputs): Added mobile autocorrect to PR title inputs in Pul
* hive(03-add-mobile-autocorrect-to-pr-description-textareas): Added mobile autocorrect to PR description textare
* Fix chat last message overlap
* feat(BottomTerminalDock): add close button next to the fullscreen toggle in the dock
* style: replace hardcoded gradient with theme value in shine text variant
* fix(header): adapt instance button for desktop only
* refactor(chat): polish sticky turn UX and message action rows for better readability
Switch to stable sticky-only turn behavior and redesign user/assistant action controls (placement, hover rules, ordering, spacing, selection-safe clamp) to reduce visual noise and improve interaction flow.
* feat(chat/message): refactor buttons in messages footer
* feat: enhance image preview functionality in chat messages
- Added a new ImagePreviewDialog component to handle image previews with navigation support.
- Updated ToolOutputDialog to utilize the new ImagePreviewDialog for displaying images.
- Modified the ToolPopupContent type to include a gallery of images and an index for the current image.
- Removed the old inline image display logic from ToolOutputDialog.
- Improved file handling in the file store, including better MIME type guessing and handling of server paths.
- Introduced a new API endpoint for handling large session message payloads, allowing for better management of multi-file attachments.
- Updated the VSCode bridge to support session message requests with appropriate headers and body handling.
* feat(proxy): implement SSE forwarding and enhance generic API request handling
* feat(chat): support submitting only queued messages
* feat: add image preview transition state
* fix: default VSCode view to draft and fixed sessions list regression
* 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>
* feat: add unified dropdown with services content in header
* feat: add right Git sidebar with resizable panel
* feat: implement responsive panel auto-toggle and terminal rehydration
- Auto-close the right sidebar when width is below a threshold and auto-open it when space permits
- Auto-close the bottom terminal when height is below a threshold and auto-open it when enough space
- Apply a dedicated rehydrated streaming configuration for terminal sessions to optimize reconnect behavior
* feat: enhance PR view with status caching and annotations
* feat(ui): enable chat dispatch in PullRequestSection
* feat(TerminalView): adjust layout
* feat: refine chat input layout and text selection menu
* fix(ui): show empty state in GitView when no changes
* feat(git): update PR actions styling and create PR button
## 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
Add TextSelectionMenu component that appears when selecting text in messages.
Provides quick actions: Add to chat, New session, Copy.
- Add TextSelectionMenu.tsx component with desktop and mobile layouts
- Integrate menu into MessageBody with message-content-text ref
- Add mobile CSS for text selection behavior
* feat: added themes system
* feat: smart sidebar auto-hide for files/diff tabs + lower files sidebar threshold
* feat: added Checkbox component and update theming
- Add reusable Checkbox component for toggles across UI
- Replace several inputs with Checkbox in settings and commands panels
- Add DiffIcon and apply surface/border theming to key UI areas
* feat: Add convert-vscode-theme.cjs to convert VS Code themes to OpenChamber format
* refactor: remove unused permission logic from ChatInput
- Remove unused permission rules parsing logic from ChatInput
- Memoize renderTheme in DiffWorkerProvider to avoid unnecessary recalculations
- Remove forceOpaque helper in vscode theme adapter
* fix: guard VSCode theme loading in MarkdownRenderer
* feat: add custom user themes loading and reload
- Load user themes from ~/.config/openchamber/themes at runtime
- Expose /api/config/themes to fetch custom themes
- Allow theme reloading from Settings → Theme → Reload themes in the UI
Add a centralized useEffectiveDirectory hook to resolve the active directory
Use the hook across DiffView, FilesView, GitView, and TerminalView
Fix list styling by rendering ul/ol bullets outside
* feat: display provider logos for favorite/recent models
Show provider logo next to model name in favorites and recents
Render provider logos in ModelControls, ModelMultiSelect, and ModelSelector lists
Maintain zero-logo state for other sections to avoid clutter
* feat: render user message as markdown instead of plain text
Render agent mentions as markdown links in user text
Apply inside list style for chat content to fix list rendering
Rely on SimpleMarkdownRenderer for consistent rendering
* fix(openchamber): adjust layout and overscroll behavior
Enable overscroll-auto on overlay containers for smoother scrolling
Move page content to full-width wrapper and preserve section borders
Show AboutSettings inside its own bordered block when visible
* feat: integrate GitHub auth status store and UI
Introduce GitHubAuthStore to track connection status and polling
Show GitHub avatar in header when connected
Guard issue/pr dialogs behind GitHub auth status and show notices
* feat: add GitHub multi-account support
Add API and UI flow to activate a GitHub account
Show and switch between multiple GitHub accounts in header
Persist and normalize accounts list with current selection
* feat: add chat virtualization and turn grouping infrastructure
Implement VirtualMessageList with virtualization and overscan for smooth scrolling
Refactor MessageList to render only visible messages and pass scroll refs
Introduce TurnGroupingContext and provider to stabilize per-turn rendering and reduce re-renders
* feat: add web server session activity endpoint for visibility restore
Add /api/session-activity endpoint to expose tracked session activity
Use web server activity first when restoring visibility, with fallback to global status
Update server SSE to set session phase on activity events
* feat(chat): split TurnGroupingContext into UI/Streaming contexts
Add separate UI state and streaming contexts to reduce re-renders.
Skip animations for items visible in collapsed view when expanding.
Track shown parts in collapsed mode to fade in progressively
* feat(ui): cache turn groups with expand state and guard web activity
Add isExpanded to the turn cache key to trigger updates correctly
Expose isGroupExpanded from UI state so groups reflect expand/collapse
Limit web server session activity fetch to web runtime only
* feat: add plan/build mode switching and Plan view tab
Add PlanView view and integrate plan tab into main layout
Introduce plan_enter and plan_exit tools with icons and status strings
Persist per-session agent selections in context to reduce UI flicker during mode switches
* feat: enchanced plan discovery checks in header and plan view
* fix(ui): align PlanView and Header with sessionDirectory logic
Remove dependency on context store in header and compute sessionDirectory from session or currentDirectory
Compute display and repo paths using sessionDirectory for PlanView and update path resolution
Poll plan content every 3 seconds to reflect changes without heavy retries
* feat(ui): improve header tab switching and add copy buttons for plan
Switch header tab navigation to central UI store and auto-switch when plan is unavailable
Show checkmark icon after copying file contents or path with auto-hide timeout
Extend plan view path resolution to prefer session directory when present
* feat: add Apply Patch tool with patch input and diff view
Introduce Apply Patch tool with a patch input field and diff preview
Display target file path or file count for patch operations in tool UI
Update status label to show applying patch during execution
* fix: include apply_patch in editing tools detection
Add file management API and UI components
Implement directory listing, search and CRUD operations in desktop backend
Expose new Files API on frontend to list, search, and modify files
- Removed unused activeTurnAnchorId and activeTurnSpacerHeight from MemoryDebugPanel.
- Simplified useChatScrollManager by eliminating unnecessary state and functions related to active turn anchoring.
- Updated loadMessages function signatures to accept an optional limit parameter across message and session stores.
- Enhanced scroll behavior in useScrollEngine to support dynamic bottom tracking during animations.
- Improved event stream handling to allow for resyncing messages with a specified limit.
- Cleaned up session memory state to remove active turn properties, focusing on viewport anchoring.
* 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
* feat: add support for OpenCode permission.asked event
Implement UI handling for the new permission.asked event from OpenCode's
PermissionNext system, allowing tools configured with "ask" in opencode.json
to prompt user for approval.
Changes:
- Add permission.asked event handler in useEventStream
- Add patterns[] and always[] fields to Permission type
- Display patterns being requested in PermissionCard
- Show what "Always Allow" will auto-approve
This enables the permission asking feature where tools can require user
approval based on opencode.json configuration.
* feat: add button to open subAgent session from task tool
When an agent uses the task tool to create a subagent session,
a new "Open subAgent session" button is now displayed next to
the task tool output. Clicking this button navigates to the
child session in the chat view.
The button shows only when a sessionId is available in the task
metadata and uses the external link icon to indicate it opens
a separate session context.
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
* feat: add /undo, /redo, /timeline slash commands and fork button
- Add /undo command to revert to previous user message
- Add /redo command to redo previously undone messages
- Add /timeline command to show conversation history
- Add fork button on user messages (hover) to create new session
- Add TimelineDialog component for navigating conversation history
- Show undo/redo/timeline in autocomplete when session exists
- Fix fork to use SDK session.fork API
- Silent no-op behavior for undo/redo when no messages (matches OpenCode CLI)
* fix: correct fork session endpoint and session switching
- Add hybrid SDK approach using v1 for existing methods and v2 for fork only
- v2 SDK has correct endpoint /session/{sessionID}/fork instead of broken /session/{id}/fork
- Fix forkFromMessage to use setCurrentSession instead of direct set
- Ensures both useSessionStore and useSessionManagementStore are consistent
- Fixes issue where forked sessions appeared empty until sending a new message
* fix: use direct fetch for fork to avoid v2 SDK build errors
- Remove v2 SDK imports and hybrid SDK approach
- Use direct fetch() call to /api/session/{sessionID}/fork endpoint
- Avoids type conflicts between v1 and v2 SDK
- Bypasses broken v1 SDK fork endpoint (wrong path parameter)
- All codebase now uses v1 SDK consistently
* fix: use jsonc-parser for config file parsing
- Replace strip-json-comments + JSON.parse with jsonc-parser
- Handles comments, trailing commas, and unquoted keys
- Matches OpenCode CLI config parsing behavior
- Fixes SyntaxError when reading global opencode.json config
* feat: improve timeline dialog with loading state and search
- Add loading spinner on fork button during operation (~30s on big sessions)
- Refresh session list after fork so new session appears in sidebar immediately
- Add search bar to filter messages by prompt text content
- Show 'No messages found' when search has no results
- Disable fork button while forking to prevent duplicate operations
- Added skill scope helpers and CRUD operations for skills in opencodeConfig.ts.
- Introduced API endpoints for skill management in main.tsx and index.js.
- Enhanced server-side logic to support skill discovery, creation, updating, and deletion.
- Implemented supporting file operations for skills, including reading, writing, and deleting files.
- Updated package.json to use the latest version of @opencode-ai/sdk.
