- Add skippedSteps persistence to onboarding state with new markStepSkipped/getSkippedSteps helpers and legacy defaults
- Update onboarding navigation so skip actions mark steps as skipped, while completed actions clear skipped state
- Render skipped progress indicators as clickable steps with a dash marker and dedicated skipped styling
- Expand onboarding state/modal tests and update App test mocks for the new onboarding-state exports
- Add agent memory support to instruction resolution and introduce/export buildAgentChatPrompt for identity-aware prompt assembly with optional project memory
- Wire ChatManager to AgentStore so chat sessions can enrich system prompts per agent and include recent conversation context in prompt payloads
- Update server chat wiring to provide an AgentStore for prompt enrichment and keep graceful fallback behavior when agent context is unavailable
- Enrich HeartbeatMonitor system prompts with resolved agent instructions/ratings while preserving base-prompt fallback paths
- Expand dashboard and engine tests to cover prompt enrichment, fallback behavior, conversation context assembly, and AgentStore route mocks
- Rewrite the GitHub onboarding step to emphasize that task creation works without GitHub
- Add a feature availability callout that contrasts capabilities with and without GitHub connection
- Update first-task CTA cards to dim GitHub import and show a connection-required note when unauthenticated
- Expand ModelOnboardingModal tests to cover optional messaging, CTA state changes, and step-specific rendering
- Add provider-specific API key format rules, display names, and fallback validation hints
- Render inline format hints plus error/success feedback in the API key form
- Add styled input states for error/success and success message auto-clear timers
- Expand onboarding modal tests to cover validation, network/server errors, success lifecycle, and skip flow behavior
- Derive GitHub-specific onboarding status from auth state, login outcomes, and persisted skip metadata
- Replace static GitHub auth text with status badge variants and contextual success/error/info feedback blocks
- Add retry, skip, and connect-anyway actions, including persistence and reset of skipped state on successful auth
- Style new GitHub feedback UI and badge states using dashboard tokens with mobile touch-target adjustments
- Expand ModelOnboardingModal tests to cover connected, pending, failed, skipped, and recovery flows
- Replace generic GitHub copy with a clear benefits list for issue, PR, and code-link workflows
- Promote the unauthenticated connect experience into a dedicated CTA container with primary button, icon, and inline feedback states
- Keep connected users focused on status and disconnect actions while hiding the connect CTA when already authenticated
- Expand ModelOnboardingModal tests to cover fallback guidance, benefits rendering, CTA styling, and connected-state behavior
- Add provider metadata for API key labels, setup instructions, usage text, and dashboard links with safe fallback defaults
- Extract API key entry UI into a reusable form component with connected/saved state, remove-key action, and Enter-to-save support
- Improve onboarding card rendering to use provider-specific descriptions and API key guidance for supported providers
- Update dashboard styles for the new API key form layout, key icon spacing, focus states, and mobile-friendly controls
- Expand ModelOnboardingModal tests to cover provider-specific copy, dashboard link behavior, Enter submission, connected badge text, and fallback instructions
- Add local scope state in RoutineEditor and sync it when the incoming scope prop changes
- Wire scope toggle buttons to update local state and invoke optional onScopeChange callbacks
- Use the selected local scope for validation, submit payload scope resolution, and helper text rendering
- Expand RoutineEditor tests to cover scope toggle interactions, disabled states, callback calls, submission, and prop-sync behavior
- Emit fix-feature mission events and forward validator telemetry through mission execution
- Add core and dashboard API types plus a validation telemetry route in mission-routes
- Update SSE mission event handling so validation telemetry updates stream reliably to clients
- Add telemetry surfaces in MissionManager with corresponding mission-specific UI styling
- Expand MissionManager and mission e2e test coverage for validation telemetry flows
- Resolve merge conflicts in routine editor, routine editor tests, and dashboard routes
- Keep the current routine editor implementation with cron preset selection and preset-to-cron autofill behavior
- Preserve existing command-validation test coverage and backup routine sync wiring in routes
- Wire MessageStore into the in-process executor runtime and project engine
- Forward MessageStore events through dashboard SSE infrastructure for mailbox updates
- Close mailbox pipeline gaps across API routes, server wiring, and mailbox UI components
- Add regression coverage for messaging routes, SSE forwarding, and agent tool behavior
- Document the MessageStore SSE wiring pattern in .fusion/memory.md
- Add SkillManifest support in core with parseSkillManifest and skills directory parsing/export wiring
- Extend /api/agents/import responses with dry-run skill previews and skillsCount metadata
- Show parsed package skills in AgentImportModal with dedicated preview UI and styles
- Add parser, API route, and modal tests covering skill manifest parsing and preview rendering
- Keep mission interview assertion generation explicit for milestone/slice fallbacks and update memory guidance for dashboard build resolution
- Route unauthenticated catalog requests to skills.sh /api/search with wildcard query support and normalized response mapping
- Keep authenticated v1 catalog fetch, but fall back to public search on 401/403 while preserving auth metadata
- Expand skills route tests for unauthenticated payload shape, query passthrough, and no-query wildcard behavior
- Stabilize onboarding reopen tests by awaiting Authentication section render before interaction
- Document dashboard dist build prerequisite for CLI test troubleshooting
- Add comprehensive review report for packages/engine/src under .fusion/tasks/FN-1960/findings-engine.md
- Document 8 total findings across scheduler, runtime, heartbeat, concurrency, and executor lifecycle areas
- Capture prioritized remediation recommendations focused on listener teardown, semaphore hardening, and lock cleanup
- Show the active model override in Agent Information, including support for legacy runtimeConfig.model values
- Add a Model section to agent settings with CustomModelDropdown and available model loading via fetchModels
- Persist model overrides as modelProvider/modelId/model and clear those fields when reverting to global default
- Expand AgentDetailView tests to cover model display, prefill behavior, save payloads, and clearing overrides
- Add a changeset for @gsxdsm/fusion describing the new agent model selection capability
- Surface companies.sh API errors to frontend instead of returning empty list
- Add 30s timeout to GitHub archive download to prevent hanging
- Prevent infinite retry loop in browse catalog useEffect
- Update retry handler to call fetch directly for better control
- Fix TypeScript error with Response type in timeout code
- Add comprehensive tests for error handling and retry behavior
- Add list_agents tool for discovering agents by role, state, or includeEphemeral filter
- Add delegate_task tool for assigning work to a specific agent by ID
- Add comprehensive test coverage for both delegation tools in agent-tools-delegation.test.ts
- Update executor.ts to wire up delegation tools when agentStore is configured
- Document both tools in AGENTS.md and docs/agents.md
- Fix overflow issues on roadmap screen on mobile devices
- Ensure roadmap cards are properly scrollable on small screens
- Resolve merge conflict in memory-compaction tests by keeping non-null assertions
- Import ReactNode type from react instead of JSX
- Update PluginSlot return type to ReactNode for proper null type inclusion
- This fixes type safety since the function returns null in error cases
- Add PluginSlot component for rendering plugin UI placeholders at designated dashboard locations
- Add usePluginUiSlots hook with 60-second TTL cache for slot definitions
- Add fetchPluginUiSlots API wrapper and PluginUiSlotEntry type
- Add UI slots documentation section to plugin authoring guide
- Add PluginSlot integration tests for TaskCard, Column, Header, SettingsModal, and TaskDetailModal
- Update CI Status example plugin to demonstrate uiSlots registration
- Fix JSX namespace import in PluginSlot.tsx for TypeScript compatibility
- Add fetchPluginUiSlots API wrapper with PluginUiSlotEntry type
- Add usePluginUiSlots hook with 30-second TTL cache for slot data
- Add PluginSlot component with error boundary and placeholder rendering
- Add comprehensive tests for hook (cache behavior, error handling, isolation)
- Add comprehensive tests for component (render states, error boundary)
