- Add core helpers to list, read, and write .fusion/agent-memory/{agentId} files with strict path validation and exports
- Add dashboard API routes and client methods for agent memory file listing and single-file read/write operations
- Expand AgentDetailView memory tab with file selection, editing, save states, and inline validation feedback
- Add route/backend coverage for agent memory file endpoints and include a @gsxdsm/fusion minor changeset
- Initialize AgentStore and ReflectionStore with taskStore.getFusionDir() in reflection APIs
- Prevent reflection endpoints from touching root-level fusion.db and agents artifacts
- Add regression coverage to ensure root project files are not created by reflection requests
- Add recursive markdown file discovery in file-service with excluded directories and sorted metadata output
- Expose GET /api/files/markdown and wire a frontend API client plus useProjectMarkdownFiles hook
- Redesign DocumentsView with project/task tabs, search, task grouping, and desktop/mobile file preview flows
- Add coverage for markdown scanning and DocumentsView behaviors, and update useDocuments tests for new API usage
- Remove legacy .fusion/memory.md fallback references and normalize prompts/docs to .fusion/memory/MEMORY.md
- Stop legacy mirror writes and fallback reads in core memory backend and project memory flows
- Update engine worktree boundary checks and tests for canonical memory file handling
- Align dashboard memory/settings surfaces and route tests with canonical memory behavior
- Add model-favorites persistence test coverage for mission interview and new agent dialogs
Anthropic now requires `anthropic-beta: oauth-2025-04-20` on /api/oauth/usage
for OAuth-scoped tokens; without it the endpoint returns 401 "OAuth
authentication is currently not supported" and the dashboard falls back to
a PTY-based CLI parser that times out at 75s. Mirrors the header the Claude
CLI (2.1.114) sends from `claude /usage`, and also aligns the refresh call
with the CLI's JSON body + `scope` field so token refresh keeps working.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Follow symlink entries that resolve to directories so linked markdown trees are discovered
- Add guarded scan diagnostics for non-ENOENT directory read failures without noisy missing-dir logs
- Expand markdown scanner regression tests for symlinks, empty roots, deep nesting, and .md-like directory names
- Clarify the Documents view empty-state copy to say no Markdown files were found in the project
- Trigger onError for unexpected AbortError failures in streamChatResponse while ignoring user-initiated closes
- Keep quick chat user messages on send errors, reset streaming state, and reload messages from the server
- Persist partial assistant output (including thinking-only fallbacks) when AI processing fails mid-stream
- Add regression coverage for stream abort handling, quick chat error UX, and partial-response persistence
- Move the core DocumentsView, document group, and document card styles to global scope so they apply on desktop and tablet
- Keep the max-width: 768px block focused on mobile-only agent and skills layout overrides
- Preserve existing design tokens and interaction states while restoring expected non-mobile DocumentsView styling
- Add backend Markdown scanner and /project-files/md endpoint with directory exclusions, depth/size limits, and search filtering
- Extend dashboard API and useDocuments hook to fetch task documents and project markdown files in parallel with resilient partial-failure handling
- Update Documents view with a collapsible Project Files section, inline metadata previews, and on-demand file content expansion from workspace API
- Add and refresh hook and file-service tests to cover markdown scanning, query propagation, project scoping, and fetch error behavior
- Add token-based styles for project file cards and responsive mobile adjustments in the documents panel
- Normalize GET /api/skills/:id/content handling by decoding encoded IDs and returning consistent invalid-id and not-found responses
- Update readSkillContent to use stat-based file vs directory detection, read SKILL.md robustly, and list non-SKILL.md entries
- Refine SkillsView interactions to ignore toggle clicks, support explicit retry of failed content fetches, and show a SKILL.md fallback placeholder
- Add/adjust dashboard route, component, and mobile CSS tests to cover content route behavior, retry flow, and touch-friendly detail panel styles
- Add defensive cleanup for in-memory task tracking when tasks move state or agents pause
- Improve stuck-detection and self-healing flow to reduce leaked state and missed recovery paths
- Add logging around previously swallowed errors and tighten executor cleanup behavior
- Expand restart and self-healing reliability tests to cover regression scenarios
- Split agent mailbox responses into inbox and outbox arrays while keeping messages as an inbox alias
- Add Inbox/Outbox sub-tabs in MailboxView and MailboxModal with unread badge and agent-switch reset behavior
- Render tab-specific empty states and sent-message metadata in the outbox list
- Add dashboard styles and mobile overrides for agent mailbox sub-tabs
- Expand MailboxModal and MailboxView tests to cover sub-tab visibility, switching, reset, and unread badge behavior
- Add file search API wiring in dashboard client/server with route coverage for /api/files/search
- Introduce useFileMention hook and FileMentionPopup component, integrated into ChatView and QuickChatFAB
- Resolve @file references in chat messages so referenced file content is included in AI context
- Add styling, mobile responsiveness, and focused tests for popup UI, hook behavior, chat resolution, and file services
- Add dashboard backend routes for Pi settings management with comprehensive route tests
- Add API client functions and tests for fetching and updating Pi settings endpoints
- Replace PiExtensionsManager with package management UI and add supporting dashboard styles
- Rewrite and fix PiExtensionsManager tests and include a changeset for @gsxdsm/fusion
- Add optional keyHint field to the auth provider client interface
- Return masked API key hints from /api/auth/status for API-key providers
- Render key hints in both Settings and onboarding provider cards when authenticated
- Add auth-key-hint styling using existing dashboard design tokens
- Add a new Memory view with Working, Insights, and Engines tabs for editing, extraction, audit visibility, and backend status
- Introduce useMemoryData and API client wrappers for insights read/write, extraction triggers, audit reports, and quick memory stats
- Implement dashboard memory routes for /memory/insights, /memory/extract, /memory/audit, and /memory/stats including AI-powered extraction orchestration
- Wire the Memory view into desktop and mobile navigation and persist it in task view state
- Add comprehensive route, API wrapper, and hook tests covering happy paths and validation/error handling
- Add /api/skills/:id/content support in dashboard API routes and client exports for skill content types
- Extend the skills adapter with readSkillContent() to read SKILL.md and list supplementary files while handling invalid and missing skills
- Update SkillsView with expandable skill detail panels, lazy content loading, and loading/error/empty states without interfering with enable toggles
- Add comprehensive SkillsView, mobile CSS, and skills-adapter tests covering interaction flows and content parsing
- Add /api/projects/across-nodes to merge local projects with online remote node project lists
- Expose fetchProjectsAcrossNodes and ProjectInfoWithSource, and switch useProjects to consume cross-node data
- Update ProjectOverview and ProjectCard with node badges, node count stats, and a node filter dropdown plus responsive styles
- Add server and dashboard test coverage for cross-node aggregation, filtering, and hook behavior changes
- Include a changeset for @gsxdsm/fusion minor release and preserve stale-channel SSE reconnect guards during merge
- Emit chat:session:updated from ChatStore when message deletion mutates a session and cover deleteMessage false returns
- Pass ChatStore into SSE setup and forward chat session update events to connected clients
- Update useChat to consume SSE updates in real time with safer EnrichedChatSession typing
- Add core and dashboard tests for chat-store emissions, SSE forwarding, route wiring, and hook behavior
- Add a reusable .btn-secondary style (including light-theme hover/focus states) for reflections tab actions
- Initialize ReflectionStore in reflection API routes before reading or writing reflections
- Create AgentStore and ReflectionStore during in-process runtime startup and wire AgentReflectionService into TaskExecutor
- Reuse the initialized AgentStore for HeartbeatMonitor and trigger scheduler setup with non-fatal guards
- Move the shared skills search input to the top of SkillsView so it applies to discovered skills and catalog results
- Add client-side discovered skills filtering by name/path with a dedicated filtered-empty-state message
- Extend skills adapter fallback logic to use unauthenticated catalog search when authenticated requests return 400, 401, or 403
- Add dashboard component and adapter tests covering discovered filtering behavior and authenticated-endpoint fallback scenarios
- Add Memory section controls for enabling auto-summarize with threshold and cron schedule inputs
- Wire ProjectEngine to sync auto-summarize automation on startup and when related settings change
- Reuse a single startup settings snapshot when syncing insight extraction and auto-summarize automations
- Add SettingsModal and ProjectEngine tests covering auto-summarize UI persistence and automation re-sync behavior
- 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
- 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
