- Introduced caching mechanism with expiration for message feeds to improve performance.
- Added logging for cache expiration events to aid in debugging.
- Updated MessagesPanel to reopen search bar when participant filters are active.
- Added test cases for handling tmux server errors and message panel behavior with filters.
- Updated `getClaudeLogs` method to support asynchronous fetching of logs.
- Introduced new interfaces for retained logs and transcript cache entries.
- Added logic to retain and retrieve Claude logs even after cleanup of live runs.
- Implemented fallback mechanism to use persisted transcripts when no live run exists.
- Updated tests to cover new log retention and retrieval scenarios.
Remove the SessionDetail.messages stripping and related cache-size
change per maintainer feedback. The session-detail optimization will
follow separately after PR #58 lands with the right architectural
pattern (lightweight snapshot + separate endpoints).
This PR now contains only:
- progressPayload helpers (buildProgressLogsTail, buildProgressAssistantOutput)
- cap applied to emitLogsProgress, updateProgress, stall warning, retry error
- throttle raised 300ms -> 1000ms
- tests for the progress payload behavior
Autofix-only change. The OOM-fix commit inserted the progressPayload
import into the wrong position relative to AutoResumeService /
idleNotificationMainProcessSemantics, which failed the
simple-import-sort ESLint rule enforced by CI.
Users with long-running teams (37+ tasks, 10+ agents for an hour) were
hitting constant renderer crashes (issue #36). Two hot paths were
serializing unbounded histories across IPC on every tick:
- Provisioning progress: emitLogsProgress and updateProgress both
joined the full provisioningOutputParts array (~20 event-driven call
sites) plus the full CLI log tail, then fanned that out to the
renderer. After an hour, each tick shipped multi-megabyte payloads
and Zustand OOM'd on the immutable state clone.
- Session detail cache: SessionDetail.messages (the raw parsed JSONL)
was being cached and returned over IPC/HTTP even though the renderer
only reads session/chunks/processes/metrics. This roughly doubled
the per-entry cache footprint on large sessions.
Fixes:
- Add progressPayload helpers that cap the log tail to 200 lines and
assistant output to the last 20 parts; empty/whitespace joins
collapse to undefined so the noop guard is explicit rather than
coincidental.
- Apply the cap inside emitLogsProgress, updateProgress, and the two
inline emission paths (stall warning, retry error). Throttle the
log-progress tick 300ms -> 1000ms so Zustand can keep up.
- Add stripSessionDetailMessages and call it at every SessionDetail
production site that crosses IPC/HTTP (both sessions.ts routes,
both cache stores).
- Raise MAX_CACHE_SESSIONS 5 -> 20 now that the per-entry SessionDetail
footprint is bounded. Previously 5 forced constant re-parsing on
every session switch.
Tests: 15 new unit tests covering the helpers (tail slicing, empty
parts, whitespace-only parts, non-mutation of inputs).
- Added support for live runtime model metadata in team provisioning.
- Implemented functions to extract and manage CLI flag values for team members.
- Updated member specifications to include effective models based on provider defaults.
- Enhanced UI dialogs to check selected providers in parallel, improving responsiveness.
- Added tests for handling model unavailability during team bootstrap and launch processes.
- Introduced CLI_INSTALLER_VERIFY_PROVIDER_MODELS IPC channel for on-demand model verification.
- Implemented handler for verifying provider models in the CliInstallerService.
- Enhanced CLI installation status management with model verification state and availability.
- Updated related components to support model verification feedback in the UI.
- Updated components in the agent-graph renderer to utilize context hooks instead of the store for accessing team data.
- Introduced `useGraphActivityContext` and `useGraphMemberPopoverContext` hooks to streamline data management.
- Refactored `GraphBlockingEdgePopover`, `GraphNodePopover`, and `GraphTaskCard` components for improved performance and readability.
- Enhanced imports in `MemberDetailDialog` for better organization.
- Added stable slot layout support in various components, enhancing the layout and interaction of nodes.
- Updated TypeScript configuration to include new paths for the agent-graph package.
- Refactored layout logic in activity lanes and kanban to accommodate stable slot assignments.
- Enhanced GraphView and GraphControls to support sidebar visibility toggling and owner slot drop handling.
- Introduced new types for layout management in GraphDataPort and related files.
- Updated README to include stable slot layout documentation.
* fix(team): resolve stuck "reconciling" state and skip resume when teammates never spawned
Addresses #54.
When a team launch fails to bootstrap teammates, the team gets stuck showing
"Last launch is still reconciling" indefinitely, and retrying with --resume
reconnects the lead but does not re-spawn the dead teammates. The only
workaround was enabling "Clear context (fresh session)", which loses the
lead's prior conversation context.
Two root causes addressed:
1. createPersistedLaunchSnapshot counted members still in 'starting' state
(agentToolAccepted=false) as 'pending' regardless of launchPhase. When
launchPhase was 'finished' with never-spawned members, the aggregate
state stayed as 'partial_pending' forever, rendered as "still reconciling".
Fix: when launchPhase != 'active', promote such members to
'failed_to_start' so the aggregate becomes 'partial_failure'
("Launch failed partway"), which correctly signals a terminal state.
2. TeamProvisioningService._launchTeamInner always used --resume when a
previous leadSessionId existed, even if the previous launch had no
teammates successfully spawned. The CLI's deterministic reconnect path
restores lead context but does not re-spawn dead teammates, so the team
stays broken across relaunches. Fix: before adding --resume, read the
persisted launch state. If every expected teammate is 'starting' (never
spawned) or 'failed_to_start', skip --resume so the CLI performs a full
fresh bootstrap that spawns all teammates.
Verified manually on Linux: a team stuck in "still reconciling" correctly
transitions to "failed partway" after the first fix, and the next Launch
(without "Clear context") fully bootstraps and brings teammates online.
* fix(team): narrow skip resume to never-spawned teammates
---------
Co-authored-by: 777genius <quantjumppro@gmail.com>
P1: Poller no longer overwrites nextCursor/hasMore — those belong
to the "Load older" flow. Both poller and loadOlder now dedup
messages by messageId or timestamp+from fingerprint.
P1: Cursor is now compound (timestamp|messageId) with stable
tie-breaking sort. Messages sharing the same timestamp at page
boundaries are no longer lost.
P2: getMessagesPage now applies the same enrichment as getTeamData:
leadSessionId propagation and slash-command-result annotation.
P3: Added 3 tests for getMessagesPage covering pagination, cursor
stability with same-timestamp messages, and slash command annotation.
Two different interval sets with the same length would produce
the same cache key, returning stale results. Serialize each
interval's startedAt~completedAt into the key.
Returning messages: [] broke the slash command annotation test and
any code relying on getTeamData.messages (notifications, dedup).
Keep a small batch (50 newest) in getTeamData for compatibility.
Full message history is available via getMessagesPage() API.
New cursor-based IPC endpoint for the messages timeline panel:
- team:getMessagesPage(teamName, { beforeTimestamp?, limit? })
returns { messages, nextCursor, hasMore }
- Cursor is timestamp-based — stable under live message insertion
- Default page size 50, max 200
getTeamData no longer includes messages in its response, eliminating
the ~1MB messages payload from every team refresh. Messages are now
fetched independently by MessagesPanel.
MessagesPanel changes:
- Fetches initial page on mount via getMessagesPage API
- Auto-refreshes newest page every 5s when team is alive
- "Load older messages" button for pagination
- Falls back to prop messages if API fails (graceful degradation)
The TeamDataWorkerClient logged console.warn when the worker file
was not found, which is expected during tests (no build output).
The test setup treats unexpected warnings as failures.
Downgrade to logger.debug for the "not found" message and remove
the eager warning from resolveWorkerPath().
Critical:
- findLogsForTask: call worker directly instead of wrapping in
wrapTeamHandler, so failures propagate to catch and trigger the
main-thread fallback correctly.
- TeamDataWorkerClient: scope error/exit handlers to the specific
worker instance to prevent a stale worker's exit event from
rejecting pending requests on a replacement worker (race condition).
Major:
- TeamDataWorkerClient: validate teamName and taskId before forwarding
to worker thread (input sanitization).
- team-data-worker: include status, since, and intervals length in
cache key to prevent stale results after filter changes.
- team-data-worker: move logsInFlight.delete() into .finally() so
rejected lookups don't poison the in-flight map permanently.
- MemberLogsTab: reset refreshCountRef and refreshing state in effect
cleanup to prevent the refresh indicator from latching on permanently
when the effect tears down mid-refresh (e.g. on tab switch).
The user inbox (user.json) contains real teammate-to-user messages
generated by Claude Code CLI. Filtering it as a system inbox was
incorrect — it broke message aggregation for user-directed messages.
Only the broadcast inbox (*.json) needs to be excluded since '*'
is not a valid member name and causes a phantom member in the UI.
The broadcast inbox file (inboxes/*.json) was being parsed by
listInboxNames() as a member named "*", which appeared in the UI
as a phantom team member. Since "*" fails the MEMBER_NAME_PATTERN
validation, it could not be removed through the UI.
Filter system inbox names (*, user) from listInboxNames() so they
are not treated as real team members.
Main process — worker thread for team data:
- New team-data-worker thread handles getTeamData and findLogsForTask,
isolating heavy file I/O (scanning 300+ subagent JSONL files) from
Electron's main event loop. getTeamData dropped from ~2000ms on the
main thread to ~110ms via the worker.
- Worker-side dedup and 10s result cache for findLogsForTask prevents
redundant scans when the same task is queried multiple times.
- Discovery cache TTL raised from 5s to 30s — avoids re-scanning the
entire project directory on every call.
- Message cap at 200 in TeamDataService to keep IPC payloads under 1MB
(was sending 2200+ messages / ~3MB, stalling Chromium IPC serialization).
- IPC handlers fall back to main-thread execution if the worker is
unavailable (graceful degradation).
Renderer — useShallow and memoization (55 files):
- Added useShallow to store selectors across 55 renderer files. Batched
individual useStore() calls (e.g. 17 calls in ExtensionStoreView,
10 in ConnectionSection) into single useShallow selectors, cutting
unnecessary re-render checks on every store update.
- MemberLogsTab: three 5-second polling intervals now pause when the
parent tab is hidden (display:none). Previously 5 hidden tabs × 3
intervals = 15 polling timers firing continuously.
- KanbanColumn wrapped in React.memo to skip re-renders when props
haven't changed.
- MemberList: memoized activeMembers/removedMembers/colorMap; replaced
O(n×m) per-member task scan with a pre-computed reviewer map.
- Bounded timer Maps in store initialization to prevent unbounded growth
of debounce/throttle tracking maps during long sessions.
- Eliminated the enrichMemberBranches method from TeamDataService to simplify member branch enrichment logic.
- Updated TeamDetailView to utilize live branch tracking for both lead and member worktrees, enhancing the accuracy of displayed member branches.
- Adjusted various references to ensure membersWithLiveBranches is used consistently across the component.
seedTeammateOperationalPermissionRules already pre-writes MCP tool
rules to settings.local.json before spawning the CLI. But standard
file tools (Write, Edit, NotebookEdit) were missing.
FACT: Teammates requesting Write get setMode: acceptEdits suggestion
but we can't change subprocess session mode. Pre-seeding these tools
as allow rules prevents the permission prompt entirely.
Belt-and-suspenders approach:
1. Settings file: handles all FUTURE calls (teammate finds rule on retry)
2. control_response via stdin: may unblock CURRENT waiting prompt
(now includes updatedInput: {} which was the previous ZodError fix)
Without #2, approved teammates stay stuck until team restart because
the CLI doesn't hot-reload settings.local.json for pending prompts.
FACT: Write/Edit permission_requests have permission_suggestions with
type "setMode" (not "addRules"): { type: "setMode", mode: "acceptEdits" }
Our code only handled "addRules", so Write/Edit approvals were no-ops.
Translate setMode suggestions to settings rules:
- acceptEdits → add Edit, Write, NotebookEdit to allow list
- bypassPermissions → add all common tools to allow list
- Replaced inline drawing logic for task comments with a new `drawCommentBubble` function to enhance readability and maintainability.
- The new function encapsulates the drawing of a speech-bubble icon, including the rounded rectangle body, tail, and inner dots to suggest text.
- Added mcpToolCatalog to the agent-teams-controller, exporting new types and constants for MCP tool groups and names.
- Updated tools registration to utilize AGENT_TEAMS_MCP_TOOL_GROUPS for streamlined tool management.
- Enhanced tests to validate the new operational permissions and ensure correct tool registration behavior.
When user approves any mcp__agent-teams__* tool, also add all other
agent-teams tools to settings.local.json preemptively. This prevents
teammates from getting stuck on subsequent tool calls (task_get,
task_start, task_complete, etc.) since each generates a separate
permission_request and the teammate blocks until resolved.
FACT: Settings file approach only prevents FUTURE blocks, not current
ones. Pre-adding all tools on first approval covers the common case.
- Added checks to ensure that only newer versions are installed during the update process.
- Updated the notification logic to suppress alerts for non-newer updates.
- Introduced a new method to compare version numbers, improving version management in the UpdaterService.
- Enhanced the release workflow by removing unnecessary file uploads and adding canonical updater metadata publishing for better asset management.
Claude Code CLI Zod schema requires updatedInput to be a record
when behavior is 'allow'. Without it, MCP tool approvals fail with
'Tool permission request failed: ZodError: expected record, received
undefined'.
Add empty updatedInput: {} to all allow responses (autoAllow,
timeout-allow, and manual allow).
Inbox files persist across team runs. Permission_request messages from
a previous run (e.g. when team was launched without auto-approve) were
being reprocessed on the next launch, showing false ToolApprovalSheet
popups even when the new run has bypassPermissions enabled.
Filter by timestamp: skip permission_request messages older than
run.startedAt.
Tool approval settings (autoAllowAll, autoAllowFileEdits, etc.) are
now stored per-team instead of globally. Clicking 'Allow all' in one
team no longer affects other teams.
- localStorage key: 'team:toolApprovalSettings:{teamName}'
- Settings loaded on team select, initialized on create/launch
- skipPermissions=false -> defaults (autoAllowAll:false)
- skipPermissions=true -> autoAllowAll:true for that team
- Main process: Map<teamName, settings> instead of single instance
- IPC: teamName parameter added to updateToolApprovalSettings
Split setTracking(enabled) into separate enableTracking/disableTracking
public methods per sonarjs/no-selector-parameter rule. Update all callers
and test mocks accordingly.
- Added logic to remove generated MCP config files when team creation or launch fails due to spawn errors.
- Updated tests to verify that MCP config files are correctly removed in failure scenarios, ensuring no leftover configurations persist.
- Enhanced error handling in the TeamProvisioningService to maintain clean state during provisioning operations.
MCP config files were stored in os.tmpdir() with no cleanup, and
the MCP server ran from the AppImage FUSE mount path which could
be inaccessible to Claude CLI subprocesses on Linux (fixes#31).
Changes:
- Store MCP configs in app.getPath('userData')/mcp-configs/ with
pid+timestamp filenames for safe multi-instance operation
- Copy MCP server to userData/mcp-server/<version>/ via atomic
temp-dir + rename (eliminates FUSE mount dependency)
- Add per-run cleanup in cleanupRun(), startup stale GC (7d TTL),
and shutdown own-pid GC
- Add --mcp-config recovery in respawnAfterAuthFailure()
- Add setAppDataBasePath(null) reset for test isolation
- Introduced 'task_comment_notification' message kind to enhance message handling in the team services.
- Updated TeamDataService, TeamInboxReader, and TeamSentMessagesStore to accommodate the new message kind.
- Modified filtering logic to exclude task comment notifications from the displayed messages.
- Added tests to ensure correct handling and filtering of task comment notifications.
- Added visual differentiation for 'task_comment' particles, adjusting size and glow effects.
- Updated drawing functions to handle new particle kind, ensuring proper rendering in the graph.
- Introduced a merge function for particles to prevent duplicates during state updates.
- Enhanced color constants for better visual representation of different particle types.
Restored markInboxMessagesRead for permission_request messages in the
early scan. Without this, processed permission_request messages stayed
read=false forever, potentially showing stale unread indicators in UI.
Root cause: handleTeammatePermissionRequest was called from 3 paths
(early inbox scan, Category 4 relay scan, stdout/native) but only
the early scan checked processedPermissionRequestIds, causing
duplicate ToolApprovalRequests and extra permission_responses.
Fix:
- Move processedPermissionRequestIds check INTO handleTeammatePermissionRequest
so ALL callers are protected by the same dedup gate
- Remove duplicate Category 4 scan that re-processed inbox messages
(early scan already covers all messages including read=true)
- Category 4 now only builds a filter Set to exclude permission_request
from relay to lead
Context window fix:
- Derive initial contextWindow from model selection (haiku=200K, else=1M)
- Use limitContext flag from request
- Updated to exact value from modelUsage on result.success
- Formula: input_tokens + cache_creation + cache_read (all three needed)
TokenUsageDisplay:
- New contextWindowSize prop → shows "X% of context" (not "X% of input")
Graph improvements:
- Pending approval: pulsing amber ring on member nodes
- Working spinner: spinning arc when member has active task
- Current task indicator in popover (Loader2 + "working on" + task name)
- GraphNode: added currentTaskId, currentTaskSubject, pendingApproval, activeTool fields
- Adapter: passes pendingApprovalAgents + currentTaskId from store
- Option keys now include question index prefix ("qi:label") to prevent
cross-question collisions when multiple questions share option labels
- Single-select clears only options from the same question, not all
- answersMessage built as per-question JSON map instead of flat join
- Backend parses JSON answers and maps to correct questions
- Fallback label "Option N" for options with undefined label
- Enter key now respects isAskQuestion selection requirement
- Selected option labels sent as message to respondToToolApproval
- control_response includes updatedInput with answers for AskUserQuestion
- useCallback/useEffect deps updated for selectedOptions and hasSelection
relayLeadInboxMessages only processes unread messages after
provisioningComplete, but CLI marks permission_request messages as
read after native delivery -- before our relay runs.
Move permission_request inbox scan BEFORE provisioningComplete check.
Scan ALL messages (including read=true), track processed IDs via
processedPermissionRequestIds Set on ProvisioningRun to prevent
re-emitting. Also look up both alive and provisioning runs so the
scan works during team bootstrap.
- Parse raw user text for permission_request in handleStreamJsonMessage
(covers case where permission_request arrives without <teammate-message> wrapper)
- Add [PERM-TRACE] logger.warn diagnostics to trace the exact flow:
where permission_request is detected, whether it reaches handleTeammatePermissionRequest,
and whether relay or stdout interception triggers
- These logs will help diagnose why ToolApprovalSheet may not appear
relayLeadInboxMessages only runs after provisioningComplete, but
teammate permission_request messages arrive during bootstrap (before
provisioning finishes). Claude Code delivers them natively via stdout
type:"user" messages, bypassing the relay entirely.
Add permission_request interception in handleNativeTeammateUserMessage
which processes stdout user messages at all times, including during
provisioning. This ensures ToolApprovalSheet appears immediately when
teammates need tool permission.
When Claude Code runtime natively delivers permission_request to the
lead via stdout, the message was excluded from interception by the
nativeMatchedMessageIds filter. This caused the ToolApprovalSheet to
not appear for teammate requests.
Remove nativeMatchedMessageIds check from the permission_request
filter so interception works even for natively delivered messages.
When auto-approve is disabled, teammate tool requests arrived as
permission_request JSON via SendMessage and rendered as "Raw JSON"
with no way to approve/deny (#29).
- Intercept permission_request in lead inbox relay, convert to
ToolApprovalRequest and show in existing ToolApprovalSheet
- Respond via teammate inbox (permission_response) + control_response
via stdin as fallback
- Show teammate name in approval header (e.g. "bob — Bash")
- Compact noise label in Messages panel for permission_request/response
- Proper file locking, race condition protection, idempotency checks
- Added support for tracking task change presence with new IPC channels: TEAM_GET_TASK_CHANGE_PRESENCE and TEAM_SET_CHANGE_PRESENCE_TRACKING.
- Introduced JsonTaskChangePresenceRepository and TeamLogSourceTracker to manage task change presence data.
- Enhanced ChangeExtractorService to utilize task change presence services for improved task change detection.
- Updated TeamDataService to integrate task change presence tracking and resolve task change presence states.
- Modified UI components to reflect task change presence status in Kanban and task detail views.
This feature aims to provide real-time insights into task changes, enhancing user experience and task management capabilities.
HEAD-request the expected installer URL (DMG/EXE/AppImage) before
notifying the user about a new version. If CI hasn't finished
uploading the artifact for the current OS yet, the notification is
suppressed and retried on the next periodic check.
Extract sendUserTaskStartNotification as reusable private method.
When a task is created via UI directly in "In Progress" column
(startImmediately=true), the controller's maybeNotifyAssignedOwner
skips the lead. Now createTask sends the notification to the lead
with full description, prompt, and task_get instructions.
- Added a new IPC handler for starting tasks triggered by users, ensuring that the task owner is always notified.
- Introduced `startTaskByUser` method in `TeamDataService` to handle task initiation and notifications.
- Updated relevant components and API interfaces to support the new functionality, including changes in the UI to call `startTaskByUser` instead of the previous `startTask`.
- Documented agent block usage for internal instructions in CLAUDE.md.
This enhancement improves user interaction with task management by providing a clear mechanism for user-initiated task starts.
Manually ported from upstream:
- c239cda6: translateWslMountPath() converts /mnt/X/... → X:/... on Windows
- 7f5fbdab: normalizeDriveLetter() uppercases drive letter (c:/ → C:/)
Both are no-op on macOS/Linux. Fixes session fragmentation on Windows+WSL.
Manually ported from upstream:
- ef2e0868: deduplicate streaming JSONL entries by requestId
- 4f21f267: mark stale ongoing sessions as dead after 5min inactivity
- Changed references in messages to use the **Agent** tool instead of the Task tool for spawning teammates.
- Added warnings for missing team_name to ensure agents are persistent rather than ephemeral.
- Updated documentation within the code to reflect the new requirements for spawning teammates.
- Use buildEnrichedEnv() in PtyTerminalService so login terminal gets
full PATH (Homebrew, nvm, etc.) and USER for Keychain lookup
- Add cliInstaller:invalidateStatus IPC to clear cached auth status
after successful login, preventing stale "not logged in" responses
- Show "Verifying authentication..." spinner instead of flashing
the "Not logged in" banner between modal close and status refresh
Ref #27
On macOS, the Claude CLI uses a Keychain namespace derived from the
presence of CLAUDE_CONFIG_DIR env var. Setting it to the default
~/.claude creates a different Keychain key than when the var is absent,
causing "not logged in" errors even after successful `claude auth login`.
Only set CLAUDE_CONFIG_DIR when the user has configured a custom path
that differs from the auto-detected default.
Fixes#27
fs.rm() without { recursive: true } throws ERR_FS_EISDIR on directories,
unlike the deprecated fs.rmdir() which handled empty dirs. Also fix
broken roadmap bullet in README.
- Fix incorrect error message when attaching files to team lead while team is offline
- Kanban columns: color only on headers, body with 30% alpha tint per user preference
- Worktree projects now correctly detected on Dashboard via path-based detection
- Filter raw protocol messages (idle_notification, teammate-message) from lead thoughts
- Consistent text styles in Attachments section (From original message / From comments)
- Secondary sort for teams by lastActivity timestamp with alphabetical fallback
- Remove colored background from team cards, keep only left border
- Dynamic member color in Add Members dialog based on next available palette color
- Stylized @-mentions in task comments with colored MemberBadge
- Refactor CLI env resolution to shared utility
- Rearranged roadmap items in README.md for better organization, moving planning mode and visual workflow editor to the top.
- Updated the flag icon for English in LanguageSwitcher.vue from the US to the GB flag.
- Enhanced user environment setup in CliInstallerService.ts by adding user information retrieval.
- Improved timestamp handling in MemberLogsTab.tsx to better reflect recent activity.
- Adjusted button class names in ProvisioningProgressBlock.tsx for consistency.
Three issues prevented standalone (non-Electron) mode from working:
1. sentry.ts used a top-level `import * from '@sentry/electron/main'`
which crashes in plain Node.js. Changed to a try/catch require()
so the module is safe to import in both environments.
2. vite.standalone.config.ts resolved all paths relative to __dirname
(docker/) but is invoked from the repo root. Fixed to resolve
relative to the repo root via a ROOT constant.
3. The electron stub was missing `safeStorage` and `screen` exports
that newer code imports. Added them, and externalized
agent-teams-controller (plain CJS with relative requires that
break when bundled by Vite).
- Introduced baseURL configuration to dynamically set asset paths in the landing components.
- Updated AppLogo and HeroSection components to use baseURL for logo image sources.
- Refactored ScreenshotsSection to utilize a publicPath function for consistent image path handling.
- Improved LanguageSwitcher to synchronize the i18n locale with the store on mount.
- Enhanced TaskCommentInput to handle file uploads more robustly, including validation for empty files and improved error handling.
- Adjusted MessageComposer to conditionally support attachments based on team status.
- Upgraded TypeScript target and library to ES2023 for improved language features.
- Enhanced TeamProvisioningService to better handle plain text attachments with UTF-8 validation.
- Improved TaskCommentInput to differentiate between image and non-image file previews, including a new FileIcon for non-image files.
- Refactored attachment handling in useAttachments and useComposerDraft hooks to simplify file processing.
- Added validation for empty files in attachmentUtils to improve user feedback on unsupported uploads.
- Added support for additional attachment types: PDF and plain text.
- Updated the TeamProvisioningService to handle new attachment types with appropriate content blocks.
- Enhanced AttachmentDisplay and AttachmentPreview components to differentiate between image and non-image files.
- Modified DropZoneOverlay and SendMessageDialog to reflect changes in file handling and messaging.
- Improved user experience by allowing file previews for non-image attachments and updating error messages accordingly.
- Refactored attachment validation logic to categorize unsupported files and handle them gracefully.
- Added logic to merge "lead" alias into "team-lead" to prevent phantom member entries in the inbox.
- Updated provisioning instructions to emphasize the importance of using the exact name for the team lead in messages, avoiding abbreviations.
- Modified default role for 'tom' from 'reviewer' to 'researcher' with updated workflow description.
- Improved UI in MemberDraftRow to indicate workflow status with a visual cue when expanded.
- Add content-based dedup in handleGetData merge: when two directed messages
have identical from+to+text within a 5-second window, keep only the first.
Fixes duplicate display caused by both CLI and our persistInboxMessage
writing to the same inbox file.
- Reorder checks in getMemberDotClass/getPresenceLabel: check leadActivity
before isTeamProvisioning so the lead shows green dot when its process
is already running during team setup.
- Changed image format for agent comments screenshot in README.
- Improved table of contents in README for better navigation.
- Refactored imports in IPC config and discovery services for consistency.
- Added shimmer effect for waiting members in CSS.
- Enhanced dashboard view to display active teams with online indicators.
- Updated team provisioning components to support message severity.
- Improved task detail dialog layout for related tasks and dependencies.
- Adjusted team model selector default value and refined member status handling.
- Fixed minor styling issues in messages panel and tab bar.
These changes aim to improve user experience and maintainability across the application.
Teammates are independent Claude Code processes that read their own inbox
files via fs.watch. Relaying DMs through the lead caused three bugs:
lead responding instead of the teammate, duplicate messages from relay
loops, and teammates not responding to user due to conflicting prompts.
- Disable relayMemberInboxMessages for teammate DMs (teams.ts, index.ts)
- Add SendMessage(to="user") filter in captureSendMessages as safety net
- Generate deterministic messageId for inbox entries lacking one (sha256)
- Wrap notification instructions in agent block, italic task subject
- Style system comments in task view with blue background, hide avatar
- Update CLAUDE.md, research docs, and code comments with architecture
- Integrate @sentry/electron and @sentry/react for crash reporting
- Add Sentry Vite plugin for source maps
- Add error tracking to main process, renderer, and IPC layer
- Exclude source maps from packaged builds
- Update README with new screenshots
- Add Sentry opt-out toggle in settings
- Update release workflow with Sentry config
Add explicit constraint in lead prompt forbidding SendMessage with
recipient "*". The broadcast address is not supported by the runtime
and creates a phantom team member named "*" in the UI.
- Add green "Update app" / "Restart to update" button in header (TabBarActions)
- Enhance UpdateDialog: larger, dynamic buttons, scrollable release notes,
version badge, "View on GitHub" link
- Add DashboardUpdateBanner: compact dismissible banner keyed by version
- Add periodic hourly update checks in UpdaterService with unref() timer
- Add dismissed version tracking in updateSlice (localStorage persistence)
- Add state transition guards in store listener: prevent periodic re-checks
from resetting downloading/downloaded status back to available/checking
- Guard error events from overriding downloaded state (transient check failures)
When a team was permanently deleted and a new team created with the
same name, the backup service still treated it as deleted. The old
registry entry blocked periodic backups, FileWatcher-triggered backups,
shutdown backups, and auto-restore on startup.
- discoverActiveTeams: re-activate deleted entries when valid config exists
- doBackupTeam: reset stale deleted manifest, always ensure identity marker
- doBackupTeam guard: allow resurrected teams through with config check
- doBackupTeamSync: reset deleted manifest to prevent status writeback
- reconcileResurrectedTeams: detect post-deletion backup data on init
- reconcileResurrectedTeamsSync: sync reconciliation before shutdown backup
Use ClaudeBinaryResolver instead of null binary path in extension services
(McpHealthDiagnosticsService, PluginInstallService, McpInstallService).
Packaged Electron on macOS has minimal PATH — bare `claude` lookup fails
with ENOENT. Now all CLI calls resolve the binary via ClaudeBinaryResolver
which checks PATH, NVM, standard install dirs and login shell env.
- Add buildEnrichedEnv() helper for child process env (PATH, HOME, USERPROFILE)
- Add stale cache re-verification with 30s TTL in ClaudeBinaryResolver
- Guard execCli() against null binaryPath with explicit error
- Replace projectPath.startsWith('/') with path.isAbsolute() for Windows
- Extract CLI_NOT_FOUND_MARKER/MESSAGE constants for consistent error detection
- Show amber info banner instead of red error when CLI not installed
- Revised the TeamProvisioningService to change event handling from 'Task' to 'Agent' for improved accuracy.
- Enhanced the StepProgressBar component to include error indicators and animations for better user feedback during provisioning.
- Updated the TeamProvisioningBanner to track and display the last active step in case of errors.
- Improved CSS styles for step indicators, adding new animations and error states.
- Refined the sidebar task item styling based on light/dark themes for better visual consistency.
- Adjusted the README to reflect changes in installation instructions and feature comparisons.
- Updated the TeamProvisioningService to advance the provisioning state to "assembling" when the first member spawn is detected.
- Improved the clarity of team setup progress tracking by refining the conditions for state transitions.
- Adjusted the README to include a new section on installation and a detailed comparison of features against other multi-agent orchestration tools.
- Updated provisioning states to include 'configuring', 'assembling', and 'finalizing' for better tracking of team setup progress.
- Refactored the provisioning progress block to utilize a new display step system, improving clarity in the UI.
- Adjusted the README to include a comprehensive table of contents and updated comparison metrics for multi-agent orchestration tools.
- Enhanced team management UI to reflect new provisioning states and improve user experience during team setup.
- Replaced instances of isLeadAgentType with isLeadMember for improved clarity in team member role checks.
- Updated README to include a new built-in review workflow feature for agent task reviews.
- Enhanced team detail and list views to accurately reflect current team members and their roles.
- Improved CSS for step progress indicators, adding new styles for a circular stepper.
- Refactored provisioning progress block to utilize a new StepProgressBar component for better visual representation of steps.
- Changed task assignment message to use italic formatting for task subject for better emphasis.
- Updated the task instruction message to utilize a wrapping function for improved readability.
- Enhanced splash screen background with an animated gradient for a more dynamic visual experience.
- Improved team detail view messaging to clarify provisioning status.
- Adjusted member list sorting logic to utilize a new lead member detection function.
Electron's 'action' event fires on both macOS and Windows per docs.
Removed isMac guard — now Allow/Deny buttons appear on Windows too.
Linux excluded (libnotify doesn't fire the 'action' event).
- Click handler reads this.mainWindowRef instead of captured closure ref,
so window recreation is handled correctly
- reEvaluatePendingApprovals now calls dismissApprovalNotification when
auto-allowing via settings change (was missing — stale notification stayed)
- Add teamProvisioningService.setMainWindow(null) in window close handler
- Add teamProvisioningService.setMainWindow(mainWindow) in window recreate
Without this, notification click focused destroyed window instead of new one
- Remove unused dismissAllApprovalNotifications (cleanupRun uses per-requestId dismiss)
- Track notifications by requestId (Map instead of Set) so they can
be dismissed individually when the approval is resolved
- Dismiss OS notification in respondToToolApproval (via UI or action)
- Dismiss OS notification on timeout auto-resolve
- Dismiss all OS notifications on cleanupRun (team stop/exit)
- Respect snoozedUntil — skip notification if user snoozed all
When a tool needs approval and the app is not focused, show a native
OS notification with clear description (tool name + file/command).
On macOS: notification includes Allow and Deny action buttons that
respond directly without switching to the app.
On all platforms: clicking the notification focuses the app window.
New setting: notifyOnToolApproval (default: true) in notification
settings with ShieldQuestion icon toggle.
- Added functionality to read draft team summaries from team.meta.json when config.json is missing.
- Introduced methods to save team-level metadata to team.meta.json during team creation.
- Updated UI components to handle draft teams, including launch and delete options.
- Enhanced error handling for draft teams in various components.
- Add autoAllowAll setting: overrides all individual auto-allow rules,
instantly approves every tool call without user interaction
- Settings panel: "Auto-allow all tools" checkbox at top, individual
checkboxes greyed out when all-allow is active
- Fix team color badge: use getTeamColorSet(teamName) as fallback
instead of getMemberColorByName which uses a different palette
and produced wrong colors (yellow instead of pink)
syntheticRequest for team launch was missing color and displayName
fields — they only existed in TeamCreateRequest (create flow).
Now reads color and name from config.json when building
syntheticRequest, so ToolApprovalRequest always has team color.
- Add diff preview for Write/Edit tools: reads current file via new IPC
(TEAM_TOOL_APPROVAL_READ_FILE), shows unified diff using existing DiffViewer
- Fix Allow button doing nothing: re-throw errors from store instead of
silently swallowing, show error message in UI, add 10s safety timeout
- Fix "No active process" during provisioning: use getTrackedRunId() to
find process in both provisioning and alive maps
- Add 5s stdin.write timeout to prevent hanging when process dies
- Add syntax highlighting for tool input preview (JSON, bash, etc.)
- Add team color/name badge from ToolApprovalRequest (works during provisioning)
- Conditionally show team badge only when user is on a different team page
- Format elapsed time as Xm Ys when over 60 seconds
- Replace native <select> with Radix UI Select in settings panel
- Enhanced the HttpServer class to prevent multiple concurrent calls to the start() method by introducing a startingPromise that ensures subsequent calls await the same promise.
- Added a private doStart method to encapsulate the server startup logic.
- Updated documentation to reflect the new behavior of the start method.
- Adjusted the ActivityTimeline component to improve padding in the "No messages" state for better visual alignment.
- Updated error handling in both registerUtilityRoutes and handleReadMentionedFile functions to return null for expected ENOENT errors, indicating that the file simply does not exist. This improves robustness in scenarios with stale or misdetected file references.
- Enhanced the isValidFileRef function to require either 3+ segments or a file extension to avoid false positives for npm scoped packages, ensuring more accurate file reference validation.
- Changed the development partitioning strategy to use a fixed name ('persist:dev') instead of a per-PID approach. This allows renderer-side storage (localStorage, IndexedDB) to survive app restarts, improving data stability during development.
- Updated the TeamProvisioningService to pre-create team configuration and member metadata before spawning the CLI, ensuring persistence even in case of failures.
- Modified return messages to reflect the new provisioning flow, indicating that the team configuration has been pre-created.
- Adjusted the steps in the provisioning process to streamline the creation and provisioning of teams, improving overall user experience.
Teammates must now post full results as a task comment (via task_add_comment)
before calling task_complete, then send a brief summary to the lead with
a pointer to the comment (first 8 chars of comment.id). This ensures results
are visible on the task board, not buried in ephemeral direct messages.
- Add task_get_comment MCP tool for fetching a single comment by id/prefix
- Add "save comment.id → use it in SendMessage" flow with concrete examples
- Update all teammate prompts: spawn, reconnect, assignment, briefing, task protocol
- Add task_get_comment to lead's MCP tools list with usage hint
- Optimize resolveTaskRef: fast-path for UUID (skip full dir scan)
- Updated task management guidelines to emphasize the importance of posting task comments before marking tasks as complete, ensuring visibility of results on the task board.
- Introduced a new notification system for team leads after task completion, summarizing key findings and linking to detailed comments.
- Improved UI components, including a new CLI checking spinner with a delayed hint and enhanced task filters to support unread/read task states.
- Refactored sidebar task item styles to visually indicate unread tasks and adjusted task sorting options to include 'unread' as a criterion.
- Enhanced settings tabs with tooltips for better user guidance and improved layout for advanced settings options.
In packaged Electron apps process.cwd() does not point to the app
directory so the mcp-server bundle was never found. Additionally the
mcp-server dist was not included in the package at all.
Changes:
- Bundle mcp-server into a single self-contained ESM file (tsup
noExternal + createRequire banner for CJS compat)
- Ship mcp-server/dist/index.js and package.json via extraResources
- Resolve entry via process.resourcesPath when app.isPackaged is true
- Build controller + mcp-server in prebuild so dist exists before
electron-builder runs
- Add mcp-server/dist/index.js to CI verify steps on all platforms
- Improve error message to list checked paths for easier debugging
- Added a pre-warming mechanism for the interactive shell environment at app startup to improve PATH resolution for CLI services.
- Introduced getCachedShellEnv function to retrieve the cached shell environment synchronously, aiding in non-blocking PATH enrichment.
- Updated buildChildEnv function to incorporate enriched PATH from the cached shell environment, ensuring reliable access to user-installed binaries.
- Refactored CLI process environment setup to utilize the binary path for more accurate environment configuration.
