- docs/api-reference.md: complete REST API endpoint reference (~60+ routes)
- docs/android-app.md: Flutter companion app stack, architecture, feature status
- docs/architecture.md: detailed file-by-file reference for all backend services and frontend components
- docs/features.md: LLM pipeline internals (intent routing, tool loop, duplicate guards, image search, research pipeline), roadmap
- docs/development.md: full migration chain (0001–0026) with naming and caveats
- README.md: link to new api-reference and android-app docs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Backend:
- Enrich GET /api/chat/models to also hit /api/ps and return loaded:bool
and modified_at alongside name/size, using parallel gather
Frontend (Settings → General):
- Model list: each row shows name (monospace), size (GB/MB), 'in VRAM' badge
if currently loaded, 'default' badge if it's the configured default
- Delete button per row; disabled while deletion in progress
- Pull form: text input (Enter submits) + Pull button
- Suggestion chips for qwen3:7b/14b/4b, llama3.1:8b, nomic-embed-text;
disabled if already installed
- Progress display during pull: status text + determinate bar when
Ollama reports total/completed, indeterminate animation otherwise
- Refresh button reloads the list; list auto-refreshes after pull/delete
- Link to ollama.com/library for model discovery
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
start_briefing_scheduler was called from before_serving (event loop thread)
and used run_coroutine_threadsafe(...).result() which blocks the calling
thread waiting for the coroutine to complete — but since the calling thread
IS the event loop, the coroutine could never run, causing a 10s timeout and
zero jobs scheduled.
Fix: make start_briefing_scheduler async and await _get_briefing_enabled_users()
directly. Also use asyncio.create_task for the catch-up rather than
run_coroutine_threadsafe. The background thread jobs (_run_user_slot_sync)
continue to use run_coroutine_threadsafe correctly since they run on the
APScheduler thread, not the event loop thread.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Register the Esc keydown listener in capture phase (useCapture=true) and
call stopPropagation() so App.vue's document-level handler never fires.
Without this, both handlers ran: App.vue pushed "/" and the component
pushed "/projects/:id", with non-deterministic winner. Also fixes the
blur-then-navigate issue where App.vue blurring an input caused the
component's handler to see body as the active element and navigate
immediately instead of stopping at the blur step.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Project view:
- Add inline status advance buttons on kanban task cards (todo→in_progress,
in_progress→done); buttons reveal on hover, stop link navigation
Task viewer:
- Back button navigates to task's project instead of /tasks when project_id set
- Esc key navigates to project (or /tasks); blurs focused element first
Quick capture:
- Use user's configured model instead of hardcoded Config.OLLAMA_MODEL
- Remove create_project from classifier prompt (tool not offered, caused
task-shaped inputs to silently fall through to note fallback)
Briefing scheduler:
- Fix get_event_loop() → get_running_loop() so background thread uses the
correct hypercorn event loop (jobs were scheduling but never executing)
- Suppress bare greeting when both LLM synthesis lanes return empty
RSS feed UI (SettingsView):
- Show last-fetched age, category badge, and feed URL per row
- Category input field when adding a feed
- Refresh all button: fetches latest items, reloads list, toasts with count
- Enter key submits add-feed form; better empty-state hint with example feeds
Weather tool:
- Accept any city/region name in addition to 'home'/'work'/'all'
- Geocodes via Nominatim + fetches live from Open-Meteo for arbitrary queries
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Accepted main's semantic duplicate threshold (>= 80 chars) over dev's
(>= 200 chars) for both note and task body checks.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
All code goes through dev first where CI runs on push. PR runs
(dev→main) were duplicating already-validated checks and causing
queue contention. Build job was already gated to push-only events.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
navigator.clipboard.writeText() requires a secure context (HTTPS) and
silently fails on http://. Add an execCommand fallback so the API key
copy button works on non-secure dev instances.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
After creating a key, two download buttons appear:
- 'Download .env' — pre-filled FABLE_URL + FABLE_API_KEY
- 'Download Claude config' — ready-to-paste mcpServers JSON block
Also adds Future Task A (in-app install instructions) and Future Task B
(Forgejo MCP) to the implementation plan.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
pyproject.toml with mcp[cli]/httpx/python-dotenv deps, entry point
fable-mcp=fable_mcp.server:main, dev deps for testing.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
17-task TDD plan covering Phase 1 (API key auth, search endpoint,
conversation type wiring, Settings UI) and Phase 2 (fable-mcp Python
package with all tool modules, tests, and Claude Code registration).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Design for two sub-projects: API key auth support in fabledassistant
(bearer tokens, read/write scope, Settings UI) and a standalone Python
MCP server at fable-mcp/ exposing notes, tasks, projects, milestones,
semantic search, and chat tools to Claude Code.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- _resolve_project now uses reverse-substring + SequenceMatcher (≥0.55)
so partial names like "Famous Supply" match "Famous Supply Co." reliably
- create_project runs similar-project checks before the confirmed gate so
confirmed=true can't bypass them; threshold lowered to 0.55 to catch
abbreviated names
- Error messages on project-not-found no longer suggest create_project,
directing the model to list_projects first
- Tool description updated to explicitly prohibit calling create_project
in response to a lookup failure
- tasks.py: fire-and-forget embedding update on create/update
- briefing_pipeline.py: await is_caldav_configured (was sync call)
- notes.py: remove erroneous duplicate count_query filter
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The watch(activeTab) only fires on changes, not the initial value.
When localStorage had settings_tab="briefing", onMounted skipped
loadBriefingTab() so the form always showed default empty values.
Follows the same pattern already used for the groups panel (line 338).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
BriefingSetupWizard and SettingsView had hardcoded initial objects that
predated the new fields, causing TS2345 type errors.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Previously the queue drain guard (currentConversation.id === convId) meant
that if the user navigated to ChatView while a workspace stream was running,
the workspace's queued messages were silently abandoned — they sat in
localStorage indefinitely with no code path to resume them.
- Extract _tryDrainQueue(convId) with the same guard logic
- Call it at stream-end (replaces the inline block)
- Call it in fetchConversation after _loadQueue, so returning to a
conversation with orphaned queue messages drains them automatically
- Order is now preserved: messages drain in the order they were queued,
even across navigation events
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Watch currentConversation.messages.length so the chat panel scrolls to
the bottom when user messages are appended or assistant messages land,
not only while streaming content is updating.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add update_milestone LLM tool: accepts project + milestone title to
look up, then applies any of title/description/status changes
- WorkspaceView SSE watcher now triggers taskPanelRef.reload() on
create_milestone and update_milestone success, so milestone groups
appear immediately without a manual refresh
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Briefing slots (4am/8am/12pm/4pm) now fire in each user's local timezone
rather than UTC, so the schedule matches the user's actual day.
Backend:
- briefing_scheduler: replaced 4 global UTC cron jobs with per-user
CronTrigger jobs keyed to the user's IANA timezone; update_user_schedule()
live-patches the scheduler when config is saved (no restart needed)
- Catchup logic evaluates missed slots in the user's local timezone
- put_config route calls update_user_schedule() after saving
Frontend:
- New Timezone section in Briefing settings: text input pre-filled from
browser (Intl.DateTimeFormat) with a Detect button for re-detection
- Slot times shown as fixed local times (4:00 am etc.) with the configured
timezone displayed beneath, replacing the old UTC-conversion display
- timezone field added to BriefingConfig type and default
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add °C/°F toggle in briefing settings; persisted in briefing_config.temp_unit
- briefing_pipeline reads temp_unit and converts Open-Meteo Celsius values
before passing them to the LLM (both full compilation and slot injection)
- Scheduled Slots section now shows each UTC slot time converted to the
user's browser local time, plus a line confirming which timezone the
browser is using
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Merging to main now runs CI checks only. The release tag (v*) is the
sole trigger for a production :latest image, eliminating the redundant
double-build that previously occurred on every PR merge + tag pair.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Dockerfile: ARG BUILD_VERSION=dev → ENV APP_VERSION baked into image
- ci.yml: BUILD_VERSION passed as build-arg; set to git tag name on v*
tag builds, "dev" on branch builds
- routes/api.py: GET /api/version returns {"version": APP_VERSION}
- SettingsView: fetches /api/version on mount, displays in About section
under General tab
Version source of truth is the git tag (YY.MM.DD.N CalVer).
pyproject.toml / package.json versions are no longer maintained.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Export now includes: projects, milestones, task_logs, note_drafts,
note_versions, push_subscriptions; full user fields (oauth_sub,
session_version); full message fields (status, tool_calls).
Restore v2 builds ID maps for all tables and patches FKs in dependency
order (users → projects → milestones → notes → child records). Notes
restored in two passes to handle self-referential parent_id correctly.
v1 backups still restore via _restore_v1 path (parent_id bug also fixed).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
TaskEditorView:
- Back button standardized to "← Tasks"
- Toolbar now on same row as Write/Preview tabs (flex-direction row)
- Save button and title input inherit gradient/Fraunces from editor-shared.css
TaskViewerView:
- Shimmer skeleton loader replaces plain "Loading..." text
- Task title uses Fraunces font at 2rem
- Edit button becomes primary gradient CTA
- Meta timestamps show clock/pencil SVG icons
- Backlinks section: card grid with colored type badges (note=indigo, task=amber)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
run_research_pipeline now accepts project_id; generation_task.py passes
workspace_project_id when the tool is called from a workspace context.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- WorkspaceNoteEditor: replace toggling list/editor views with always-visible
left rail (155px) showing note list alongside editor pane; persist last-open
note per project in localStorage (workspace_note_{projectId})
- WorkspaceTaskPanel: add priority dot + due date on task rows; replace full
overlay detail with bottom-split (44% list / 56% detail); close button
replaces back nav; active row highlighted; fade transition
- WorkspaceView: show project goal in header instead of 'Workspace'; non-equal
panel widths (0.8fr / 1.1fr / 1.1fr); empty chat quick-action chips (Project
status / New note / Add tasks); prefill() helper
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replaces the flat sorted list with date-aware sections that surface what
needs attention first. Completed tasks go into a collapsed section at the
bottom. Grouped-by-project mode is preserved as the second toggle option.
TaskCard compact restored to card hover/lift style.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Planning artifacts (specs/plans) generated by Claude Code sessions don't belong
in the repo. Removing existing files and ignoring the directory going forward.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- NotesListView: skeleton shimmer for grid and list modes; grid columns change from fixed 3 to auto-fill(260px)
- NoteCard compact: flat border-bottom row style instead of stacked mini-cards; gradient fade mask on grid preview text
- TaskCard compact: flat border-bottom row style; show up to 2 tags
- TasksListView: gradient + shadow on New Task button (matches NotesListView)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Ports UserManagementView logic (users list, invitations, registration
toggle) directly into SettingsView as a lazy-loaded 'users' admin tab.
Adds loadLogsPanel stub for Task 4. Adds apiDelete import and User type
import at script top.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove the gear dropdown menu from AppHeader; cog icon is now a plain
router-link to /settings. Admin-only /admin/users and /admin/logs routes
are replaced with redirects to /settings. Mobile menu admin links removed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Hero card: last-active project (by most recent note/task updated_at),
prominent 'Open Workspace' button, milestone bars, 5 recent items,
highest-priority next-up todo task
- Projects grid: all other active projects with small workspace button,
urgency badges (in progress / todo count), milestone bars, hover lift
- Inbox section: collapsible strip of orphaned tasks + notes (no project)
- Skeleton shimmer replaces plain 'Loading...' text
- Chat widget + quick actions unchanged at top
Backend additions used: ?no_project=true on both /api/notes and
/api/tasks; ?project_id= on /api/tasks (committed separately)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
TaskViewerView:
- Add '→ In Progress' / '→ Done' advance button in toolbar (forward-only,
hidden when status is already done)
- Styled with primary indigo gradient to distinguish from secondary actions
TaskEditorView:
- showPreview now defaults false; set to true after load only when body
has content — empty tasks open directly in Write mode
- Save on an existing task now calls window.location.reload() so the
preview/edit mode re-evaluates from the freshly persisted body
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Nav padding: 0.5rem → 0.75rem vertical, 1.25rem → 1.5rem horizontal
- AppLogo size: 24px → 34px so the book detail is legible
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Previously the empty-conversation cleanup only fired when switching
between chats (convId watcher). Navigating to /notes, /tasks, etc.
left orphaned untitled empty conversations. onUnmounted now runs the
same check, deleting the current conversation if message_count === 0.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- theme.css: darken user bubble text (#3a3a4a light / #b0b0c8 dark) for better readability
- AppHeader: highlight Chat nav link when on any /chat/* route (was only active on exact /chat)
- summary.md: document workspace, graph, queue persistence, ToolCallCard direct-API, dedup scoping
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Matches the ChatView.vue update from the UI polish pass — queued bubbles
use linear-gradient(135deg, #6366f1, #4f46e5) and 18px border-radius
consistent with the Illuminated Transcript design language.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
create_note now only checks against existing notes (is_task=False);
create_task only checks against existing tasks (is_task=True). All three
checks (exact title, fuzzy title, semantic similarity) pass the type
filter through to list_notes and semantic_search_notes.
Adds is_task param to semantic_search_notes() so callers can restrict
results to notes or tasks independently.
Prevents a note titled "Design enemy AI" from blocking a task with the
same title, and vice versa.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The role-user justify-content and message-bubble shape styles are scoped
to ChatMessage.vue and don't reach the inline queued bubbles. Add them
directly in ChatView and WorkspaceView: right-aligned row, 16px border
radius with 4px bottom-right corner, same padding and font as user bubbles.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Raises body character limit from 80 → 200 (skips short/stub notes)
and threshold from 0.87 → 0.90 (only flags near-identical content).
Enemy design notes sharing a template will pass through cleanly;
accidentally duplicated notes with the same detailed content will
still trigger the confirmation prompt.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Queued message bubbles now match user bubble style (primary colour,
right-aligned, opacity 0.45) in both ChatView and WorkspaceView
- Queue persisted to localStorage (fa_conv_queue_<id>); survives page
refresh, restored on fetchConversation, cleared on delete
- ToolCallCard confirm/deny: buttons now inline in header row; "Create
anyway" calls POST /api/notes or /api/tasks directly (no LLM round-trip);
shows "✓ Created" / "Skipped" state; removed chatStore dependency
- POST /api/notes and POST /api/tasks now accept project (name string) and
resolve to project_id server-side, matching tools.py behaviour
- Remove semantic similarity duplicate check from create_note and
create_task — 0.87 threshold was too aggressive for topically-related
notes; title-based exact/fuzzy checks are sufficient
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Dashboard chat: allow typing/sending during streaming (queued in store)
placeholder updates to "Type to queue…" during generation
- ChatView/WorkspaceView: replace queued chip with actual pending message
bubbles — light grey, dashed border, "Queued" badge above content; clear
button below the stack
- ToolCallCard: when tool returns requires_confirmation=True, show
"Similar content found" label (not "Error"), link to the similar note,
and "Create Anyway" / "Don't Create" buttons that auto-send the reply
- tools.py: fuzzy title match now returns requires_confirmation=True with
similar_note data instead of a hard error, so numbered-series notes
(Lore: X 0, Lore: X 1) can be created with one button click; semantic
match responses also include similar_note for the link
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replaces the single long scrolling page with a tab bar. Active tab
persists to localStorage across navigation. Admin tab only visible to
admins. Push notifications description clarified to mention HTTPS requirement.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
deadsnakes python3.12 sees system python3.10's setuptools at
/usr/lib/python3/dist-packages and skips installation, leaving python3.12
without setuptools. A venv gets its own site-packages so pip/setuptools
are properly present for http-ece's legacy setup.py build.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
pip builds legacy setup.py packages in an isolated environment that doesn't
inherit the globally installed setuptools. Pre-building http-ece with
--no-build-isolation bypasses that isolation so setuptools is available.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
http-ece (pulled in by pywebpush) uses setup.py and requires setuptools,
which is not included in the deadsnakes Python 3.12 install.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- sw.js: suppress notification when the target chat tab is already focused
(clients.matchAll visibility check before showNotification)
- generation_task.py: provide meaningful body for tool-only responses
(lists tool names instead of sending an empty string that browsers discard);
promote scheduling failure from debug to warning
- push.py: promote send errors from warning to error with exc_info;
log successful sends at INFO so they're visible in normal operation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Chat store: when sendMessage() is called while streaming, push to a
per-conversation queue and return. When the stream ends the next queued
message fires automatically via setTimeout(0) to keep the call stack
clean. clearQueue() and queuedCount exposed for UI consumption.
Queue is cleaned up on conversation delete.
ChatView/WorkspaceView: remove the streaming guard from the local
sendMessage() functions and the :disabled on the textarea so users can
type and submit freely while streaming. Input placeholder changes to
"Type to queue next message…" during streaming. A small "⏳ N queued ×"
chip appears below the streaming bubble showing queue depth with a
cancel button.
DashboardChatInput: disable input, attach button, and send button
during streaming. The dashboard creates a fresh conversation per
message so in-conversation queuing doesn't apply — locking the input
is the correct UX here. Placeholder updates to "Generating response…"
during streaming.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
python:3.12-slim has no Node, causing actions/checkout@v4's post-step
to fail with 'exec: node not found'. Drop the container: declaration
so jobs run on the ubuntu-latest runner (which has Node). Install
Python 3.12 via deadsnakes PPA for the test job since the runner base
image (Ubuntu 22.04) ships with Python 3.10.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Merged ci.yml and build.yml into a single workflow. The build job now
declares needs: [typecheck, lint, test] so images are only pushed when
all checks are green. PRs run CI only; branch/tag pushes run CI then
build if successful.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The semantic similarity check was flagging unrelated short-title tasks
as duplicates (e.g. "Lore: Shell 0" matching "Lore: Reinitialization 0"
at 91%) because with no body, the embedding is purely title-based and
co-domain tasks in the same project share a tight embedding neighborhood.
Only run the semantic check when the body is ≥ 80 chars — enough
content to make a meaningful comparison. The fuzzy title check already
covers exact/near-exact title duplicates.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The 404 handler was unconditionally serving index.html (200) for all
non-API, non-static paths, including scanner probes for .php, .asp, .cgi
etc. Added _SPA_EXTENSIONS set so paths with unknown extensions get a
real 404 instead of a misleading 200.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The semantic similarity check was flagging unrelated short-title tasks
as duplicates (e.g. "Lore: Shell 0" matching "Lore: Reinitialization 0"
at 91%) because with no body, the embedding is purely title-based and
co-domain tasks in the same project share a tight embedding neighborhood.
Only run the semantic check when the body is ≥ 80 chars — enough
content to make a meaningful comparison. The fuzzy title check already
covers exact/near-exact title duplicates.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The 404 handler was unconditionally serving index.html (200) for all
non-API, non-static paths, including scanner probes for .php, .asp, .cgi
etc. Added _SPA_EXTENSIONS set so paths with unknown extensions get a
real 404 instead of a misleading 200.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
