Commit Graph

10 Commits

Author SHA1 Message Date
bvandeusen ebc79b34f9 feat(rag): RAG scoping and context isolation controls
- Migration 0030: add conversations.rag_project_id (NULL=orphan-only,
  -1=all notes, positive=project), projects.auto_summary and
  projects.summary_updated_at
- Three-value scope semantics thread from build_context() → semantic
  search and keyword fallback via orphan_only + effective_project_id
- Project summarization background job (generate_project_summary,
  backfill_project_summaries) called via Ollama; triggered on project
  update and note saves (debounced 1h); runs at startup
- New LLM tools: search_projects (SequenceMatcher scoring on
  title+description+auto_summary) and set_rag_scope (persists to DB,
  workspace-guarded, emits new_rag_scope in SSE done event)
- execute_tool() accepts conv_id + workspace_project_id; generation_task
  passes both and captures scope changes for SSE done enrichment
- Frontend: Conversation type gets rag_project_id; chat store adds
  ragProjectId computed + updateRagScope(); SSE done handler syncs scope
- ChatView: replace sidebar ProjectSelector with a scope chip pill above
  the input bar, animated dropdown, pulse on model-driven scope change

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-25 17:44:39 -04:00
bvandeusen 47b4af281b feat: API key routes, search endpoint, conversation type wiring
- GET/POST/DELETE /api/api-keys blueprint registered
- GET /api/search?q=&content_type=&limit= semantic search endpoint
- create_conversation gains conversation_type param (default "chat")
- cleanup_old_conversations excludes mcp type from retention sweep
- POST /api/chat/conversations accepts conversation_type body field

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-23 21:01:04 -04:00
bvandeusen 42b0d8c4ac feat: filter chat conversations by type; add get_weather and get_rss_items LLM tools
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-11 19:46:08 -04:00
bvandeusen ef141f07f8 UI polish pass: word count, slash commands, task lists, graph peek, bulk delete, export
- WordCount component (toggle words/chars vs read time, persisted mode)
- TipTap: TaskList/TaskItem extensions, slash command menu (H1-H3, lists, code, quote, task)
- Markdown serializer: task list → `- [ ]` / `- [x]` roundtrip
- GraphView: slide-in peek panel for note/task nodes (body, tags, linked nodes); tag nodes still navigate
- ChatView: bulk-select conversations with two-click confirm delete + chat retention policy (default 90d)
- NoteEditorView: pill tab bar with animated edit/preview toggle + WordCount in toolbar
- WorkspaceNoteEditor: inline search with tag matching, inline new-note creation, WordCount
- WorkspaceTaskPanel: task body rendered in slide-over + Edit link
- Settings: data export (Markdown ZIP / JSON) via GET /api/export
- Accessibility: skip-to-content link, aria-labels on all icon-only buttons
- Fix: export route used non-existent fabledassistant.database — corrected to async_session()
- Fix: ToolCallRecord.status type now includes "running" (was causing TS build error)
- Dockerfile: upgrade npm to latest before install to suppress major-version notice
- npm audit fix: patched minimatch (ReDoS) and rollup (path traversal) — 0 vulnerabilities

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-07 23:15:01 -05:00
bvandeusen 953eaf2feb Add model selection, dashboard chat input, and model warming
- Add GET /api/chat/ps and POST /api/chat/warm endpoints for hot model
  visibility and pre-loading
- Extend PATCH /api/chat/conversations/:id to accept model in addition
  to title
- Add ModelSelector component with hot/cold indicators from Ollama /api/ps
- Add DashboardChatInput component (model selector + note picker + textarea)
  replacing the simple "New Chat" button on the dashboard
- Add model selector dropdown to ChatView header, persisted per-conversation
- Warm default model on dashboard mount via fire-and-forget background task
- Configure Ollama with OLLAMA_MAX_LOADED_MODELS=2 and OLLAMA_KEEP_ALIVE=30m
- Always-visible edit buttons on NoteCard/TaskCard (remove hover-only behavior)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-14 18:49:06 -05:00
bvandeusen 586026bff6 Add Tiptap inline-preview editor, layout improvements, and README
Replace plain textarea with Tiptap (ProseMirror) WYSIWYG editor for notes
and tasks. Headings, bold, lists, and code blocks now render inline while
editing. Tags and wikilinks get visual highlighting via decoration plugins,
and autocomplete uses @tiptap/suggestion with heading disambiguation.

Layout: pin navbar with app-shell flex column (100dvh), sticky editor
toolbar above scrolling content, AI Assist panel fixed at bottom 1/3 with
full-height section selector and prompt. Increase max-width to 960px
across all views. Hide assist controls during streaming/review.

Other fixes: markdown paste handling, auto-syncing assist sections via
body watcher, trailing newline on AI accept, ChatView height fix.

Add README.md describing the app, usage guide, and technical overview.
Update summary.md with Phase 5.2 roadmap and current status.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-11 21:24:35 -05:00
bvandeusen cbfdf5289e Add multi-user auth, background generation, and chat UX improvements
Phase 5: Multi-user authentication with session cookies, bcrypt passwords,
first-user-is-admin pattern, per-user data isolation, backup/restore,
Docker Swarm production stack with secrets and network isolation.

Phase 5.1: Chat UX improvements:
- Background generation architecture (GenerationBuffer + asyncio task)
  with SSE fan-out, reconnect support, and periodic DB flushes
- LLM-generated conversation titles (first exchange + every 10th message)
- Stop generation button with cancel_event and partial content preservation
- Relative timestamps in sidebar (5m ago, 3h ago, then dates)
- Empty chat auto-cleanup on navigation away
- Save-as-note uses LLM for title generation, tags notes with "chat"
- Summarize-as-note also tags with "chat"

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-11 14:36:30 -05:00
bvandeusen db01106714 Backend efficiency & consistency pass
- Rewrite get_all_tags() with SQL unnest instead of loading all notes
- Consolidate convert_note_to_task/convert_task_to_note to single-session ops
- Add search_notes_for_context() with single OR-keyword query for build_context()
- Drop selectinload from list_conversations(), use correlated subquery for message_count
- Add set_settings_batch() for single-transaction multi-setting upserts
- Extract get_installed_models() shared helper into services/llm.py
- Delete services/tasks.py pass-through wrapper; routes/tasks.py imports from services.notes
- Add B-tree indexes on notes.title and conversations.updated_at (migration 0007)
- Add logging to services/notes.py, services/chat.py, services/settings.py
- Safe Conversation.to_dict() when messages relationship is not loaded

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-11 08:27:11 -05:00
bvandeusen fb18d2c41d Add note context visibility in chat and standardize UI design tokens
Improve chat context: build_context() now returns metadata about auto-found
notes, emitted as an SSE event so the frontend can display context pills
showing which notes influenced the response. Users can promote notes for
deeper context (+) or exclude irrelevant ones (x). A note picker lets users
manually attach notes. Multi-word search uses per-term AND matching, and
auto-search iterates keywords individually for broader OR-style coverage.

Standardize styling: introduce CSS design tokens (--radius-sm/md/lg/pill,
--color-success/warning/overlay, --focus-ring) and migrate all components
to use them. Fix header alignment to full-width, add active nav link state,
replace hardcoded colors with CSS variables, and normalize button padding.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-11 06:49:12 -05:00
bvandeusen d2b8ab8fe8 Add LLM chat integration with streaming responses via Ollama
Phase 4: Full chat system with SSE streaming, note-aware context, and
conversation persistence.

Backend:
- Migration 0005: conversations + messages tables with FKs and indexes
- Conversation/Message SQLAlchemy models with relationships
- LLM service: ensure_model (auto-pull on startup), stream_chat (NDJSON),
  generate_completion, fetch_url_content (HTML stripping), build_context
  (keyword extraction, related note search, URL content injection)
- Chat service: conversation CRUD, save_response_as_note,
  summarize_conversation_as_note
- Chat routes blueprint: 9 endpoints including SSE streaming for messages,
  save/summarize as note, Ollama model listing
- Auto-pull llama3.1 model on app startup (non-blocking)

Frontend:
- apiStreamPost: SSE client using fetch + ReadableStream
- Chat Pinia store with streaming state management
- ChatView: dedicated /chat page with conversation sidebar + message thread
- ChatPanel: slide-out panel with contextNoteId from current route
- ChatMessage: markdown-rendered message bubble with "Save as Note" action
- Updated AppHeader with Chat nav link + panel toggle button
- Updated App.vue to mount ChatPanel with route-derived context
- Added /chat and /chat/:id routes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-10 18:45:22 -05:00