setProvider() updated toolsOptions.provider but didn't reload tool
instances. The sessions_spawn tool captured the old provider in its
closure at creation time, causing subagents to inherit a stale provider.
Now calls resolveTools() + setTools() after updating toolsOptions so
sessions_spawn gets a fresh closure with the correct provider.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace tab navigation with collapsible sidebar
- Fix header scroll issue with proper flex container structure
- Add TooltipProvider at app root
- Simplify onboarding store by removing forceOnboarding flag
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace ring-[3px] with ring-3 in button and input
- Use data-horizontal/data-vertical in separator
- Fix sidebar data attributes and RTL support
- Simplify tooltip provider nesting
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Separate entrance animation from hover animation
- Use state to track entrance completion
- Hover spin only activates after entrance is done
- Shorten entrance animation to 0.6s
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add StepDots progress indicator to all steps
- Update animations for consistency
- Minor copy and layout adjustments
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add radio button style indicators for provider selection
- Add HoverCard component for provider setup help
- Add Link component for external URLs
- Add Popover component (dependency for HoverCard)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Single column centered layout matching other steps
- Improved copy: "Your agent, everywhere"
- Info box explaining direct connection to local agent
- Coming soon hint for Discord, Slack, Mobile app
- Simplified button logic: Skip (outline) + Continue
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create ProviderStore for global provider state management
- Refactor useProvider hook to use the store
- Data fetched once at startup, shared across components
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create ChannelsStore for global channel state management
- Refactor useChannels hook to use the store
- Initialize channels store at app startup
- Share state between onboarding and channels page
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add resolvedTheme state to expose actual applied theme
- Listen for system theme changes when in "system" mode
- Fix mode toggle to show correct icon based on selected theme
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add an `announce` parameter to sessions_spawn that controls when findings
are delivered to the parent agent:
- "immediate" (default): announce per-completion (existing behavior)
- "silent": defer until ALL silent runs from the same requester complete,
then deliver ONE coalesced announcement with all findings
This enables workflows like "spawn 10 parallel subagents to collect data,
then summarize everything at once" without intermediate results.
Changes:
- types.ts: add `announce` field to SubagentRunRecord & RegisterSubagentRunParams
- sessions-spawn.ts: add `announce` parameter to tool schema
- registry.ts: split checkAndAnnounce into immediate/silent groups,
extract announceGroup helper, use count-match guard for silent readiness
- sections.ts: add announce mode guidance to system prompt
- registry.test.ts: add silent mode tests (field storage, group isolation)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extract SILENT_REPLY_TOKEN and isSilentReplyText() into a shared
module. Detects NO_REPLY at the start or end of text (with optional
whitespace/punctuation) to filter out silent announcement responses
that should not be forwarded to the user.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Document the full subagent lifecycle: spawn, concurrency queue,
execution, completion handling, two-tier announcement delivery,
and record archival. Include provider inheritance chain and
error propagation diagrams.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add error reporting rule to subagent system prompt: subagents must
explicitly report tool failures and missing credentials in their
final message. Add timeout guidelines to parent system prompt with
recommended values by task complexity (10-30 min).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When subagents are still running, sessions_list now returns an
explicit instruction telling the LLM not to poll again and wait
for automatic result delivery. Normalizes status display to
uppercase ([RUNNING], [OK], [ERROR]).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pass parent's resolvedProvider through the tool chain (tools.ts →
sessions-spawn.ts → hub.createSubagent) so subagents use the same
LLM provider as the parent. Previously subagents fell back to the
hardcoded default provider, causing API key errors.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace immediate record deletion with archiveAtMs-based deferred
cleanup (60min retention). This keeps records queryable via
sessions_list after completion. Add sweeper to clean expired records.
Check childAgent.lastRunError after waitForIdle to detect failed runs
that resolve the promise without throwing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add isRunning flag to Agent (runner.ts) for detecting active runs.
Add lastRunError to AsyncAgent for propagating child run errors to
the registry. Fix duplicate message emission in writeInternal by
resetting forwardInternalAssistant before persistAssistantSummary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add announce-queue.ts for batching nearby subagent completions with
debounce (1s) and collect mode. Implement two-tier delivery in
announce.ts: queue when parent is busy, writeInternal when idle.
All delivery uses writeInternal() to mark messages as internal,
preventing announcement bubbles from appearing in the UI.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Display the label (or truncated task) as subtitle for SpawnSession tool
calls, so users can see what each spawned session is working on.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add chart icon, smart subtitle (shows action + ticker, e.g. "price_snapshot AAPL"),
and running state label for the data tool in the tool call UI component.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Use credentialManager.getToolConfig("data") as the primary source for
the Financial Datasets API key, with FINANCIAL_DATASETS_API_KEY env var
as fallback. Also add data tool entry to the credentials template.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- finance-research: guides agent on financial data retrieval and analysis
workflows using the data tool
- dcf-valuation: 8-step DCF valuation workflow with sector WACC reference
data, sensitivity analysis, and validation checks
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduces a `data` tool that provides structured access to the Financial
Datasets API (financialdatasets.ai). Supports 18 finance actions covering
stock prices, financial statements, key metrics, SEC filings, analyst
estimates, insider trades, news, and crypto data.
Designed as a stable interface — the backend can be swapped from direct
API calls to a Multica Data Service without changing the tool schema.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Simplify permissions step to single centered column
- Replace per-item switches with single "I understand" checkbox
- Add capabilities info card with clean dividers
- Add trust note section for privacy messaging
- Rename step from "Permissions" to "Privacy" for clarity
- Add fade-in animation for step transitions
- Add shadcn checkbox component
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Major positioning change:
- Redefine from "distributed framework" to "personal AI agent"
- Primary focus: personal use, one user, one agent, local-first
- Secondary: remote access (optional power feature)
Value proposition restructure:
- Tier 1: Personal AI Agent, Capable, Local-First
- Tier 2: Your Keys, Safe Execution, Persistent Memory
- Tier 3: Extensible Skills, Remote Access (demoted)
Feature priority changes:
- QR code/remote access moved from P0 to P3
- Dashboard (agent capabilities) moved to P1
- Home page becomes Dashboard, not connection-focused
User model simplified:
- Single user "You" instead of Owner/Collaborator roles
- Remote access as optional power feature
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Font unification:
- Add @fontsource packages for Geist Sans, Geist Mono, Playfair Display
- Create fonts.ts for centralized font imports
- Import fonts in both web (layout.tsx) and desktop (main.tsx)
- Register --font-brand in Tailwind @theme inline block
- Fix font-brand class usage (replace arbitrary value syntax)
Design system documentation:
- Add comprehensive design philosophy comments to globals.css
- Document typography choices (why Geist, why Playfair for brand)
- Document color system approach (neutral grays, semantic colors only)
- Explain component library customizations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement one-click desktop auto-update with version checking, download progress, and automatic installation. Includes toast notification UI in bottom-right corner showing update status (checking, available, downloading, ready, or error).
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- Replace nested routes with single OnboardingPage component
- Simplify Stepper to use numeric index instead of StepId
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Welcome step before the 4-step onboarding flow
- Welcome page introduces Multica with brand title (Playfair Display font)
- Display three core principles: Your AI, Your Machine, Your Control
- Add entrance spin animation to MulticaIcon component
- Welcome page has no stepper, only shown after clicking "Start Exploring"
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add reset-user-data.sh script to clear ~/.super-multica/
- Add --reset CLI flag to clear localStorage on startup
- Add dev:reset npm script for development testing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add description, author, and homepage fields to package.json
required by electron-builder when building .deb packages on Linux CI.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change productName from "YourAppName" to "Multica"
- Change appId from "YourAppID" to "com.multica.app"
- Add app icons (icns, ico, png) for all platforms
- Disable hardenedRuntime to fix ad-hoc signing on ARM Macs
- Add build:desktop script to root package.json
- Simplify desktop .gitignore with !build/ exception
- Remove unused asarUnpack and entitlements config
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
completeOnboarding() only set completed=true but never cleared the
forceOnboarding flag, causing OnboardingGuard to redirect back to
onboarding in an infinite loop when --force-onboarding was used.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
setProvider() updated the resolved provider and model but did not
rebuild the system prompt, so the runtime info line still showed the
old provider/model (e.g. claude-code/claude-opus-4-6) after switching.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
