Merge pull request 'dev to main: improvements and bug fixes' (#4) from dev into main

Reviewed-on: bvandeusen/FabledAssistant#4

frontend/src/api/client.ts

@@ -328,6 +328,8 @@ export interface BriefingConfig {
   work_days: number[];
   slots: BriefingSlots;
   notifications: boolean;
+  temp_unit: 'C' | 'F';
+  timezone: string;
 }
 
 export interface BriefingFeed {
@@ -360,6 +362,8 @@ const DEFAULT_BRIEFING_CONFIG: BriefingConfig = {
   work_days: [1, 2, 3, 4, 5],
   slots: { compilation: true, morning: true, midday: false, afternoon: false },
   notifications: true,
+  temp_unit: 'C',
+  timezone: '',
 };
 
 export async function getBriefingConfig(): Promise<BriefingConfig> {

frontend/src/components/BriefingSetupWizard.vue

@@ -19,6 +19,8 @@ const config = reactive<BriefingConfig>({
   work_days: [1, 2, 3, 4, 5],
   slots: { compilation: true, morning: true, midday: false, afternoon: false },
   notifications: true,
+  temp_unit: 'C',
+  timezone: '',
 })
 
 // Step 2 — locations

frontend/src/stores/chat.ts

@@ -109,6 +109,28 @@ export const useChatStore = defineStore("chat", () => {
     }
   }
 
+  // Drain the next queued message for a conversation, if conditions are met.
+  // Called both at stream-end and after fetchConversation, so orphaned queue
+  // messages (e.g. from a navigation away mid-stream) are picked up on return.
+  function _tryDrainQueue(convId: number) {
+    const queue = convQueues.value[convId];
+    if (!queue?.length) return;
+    if (isStreamingConv(convId)) return; // stream-end will drain naturally
+    if (currentConversation.value?.id !== convId) return; // not our conversation
+    const next = queue.shift()!;
+    _saveQueue(convId);
+    setTimeout(() => sendMessage(
+      next.content,
+      next.contextNoteId,
+      next.includeNoteIds,
+      next.think,
+      next.contextNoteTitle,
+      next.excludeNoteIds,
+      next.ragProjectId,
+      next.workspaceProjectId,
+    ), 0);
+  }
+
   function clearQueue() {
     const id = currentConversation.value?.id;
     if (id) {
@@ -158,6 +180,9 @@ export const useChatStore = defineStore("chat", () => {
         `/api/chat/conversations/${id}`
       );
       _loadQueue(id);
+      // Drain any messages that were queued but never sent because the user
+      // navigated away before the previous stream finished.
+      _tryDrainQueue(id);
     } catch (e) {
       useToastStore().show("Failed to load conversation", "error");
       throw e;
@@ -431,23 +456,9 @@ export const useChatStore = defineStore("chat", () => {
       s.pendingTool = null;
     }
 
-    // Process next queued message, if any.
-    // Use setTimeout so this frame resolves before the next send begins.
-    const queue = convQueues.value[convId];
-    if (queue?.length && currentConversation.value?.id === convId) {
-      const next = queue.shift()!;
-      _saveQueue(convId);
-      setTimeout(() => sendMessage(
-        next.content,
-        next.contextNoteId,
-        next.includeNoteIds,
-        next.think,
-        next.contextNoteTitle,
-        next.excludeNoteIds,
-        next.ragProjectId,
-        next.workspaceProjectId,
-      ), 0);
-    }
+    // Process next queued message if this is still the active conversation.
+    // If the user has navigated away, _tryDrainQueue will fire on fetchConversation.
+    _tryDrainQueue(convId);
   }
 
   async function reconnectIfGenerating(convId: number): Promise<void> {

frontend/src/views/SettingsView.vue

@@ -126,6 +126,8 @@ const briefingConfig = ref<BriefingConfig>({
   work_days: [1, 2, 3, 4, 5],
   slots: { compilation: true, morning: true, midday: false, afternoon: false },
   notifications: true,
+  temp_unit: 'C',
+  timezone: '',
 });
 const briefingFeeds = ref<BriefingFeed[]>([]);
 const briefingSaving = ref(false);
@@ -138,6 +140,10 @@ const addingFeed = ref(false);
 async function loadBriefingTab() {
   briefingConfig.value = await getBriefingConfig();
   briefingFeeds.value = await getBriefingFeeds();
+  // Auto-populate timezone from browser if not already stored.
+  if (!briefingConfig.value.timezone) {
+    briefingConfig.value.timezone = Intl.DateTimeFormat().resolvedOptions().timeZone;
+  }
 }
 
 async function geocodeLocation(key: 'home' | 'work') {
@@ -173,6 +179,7 @@ function toggleWorkDay(day: number) {
   days.sort();
 }
 
+
 async function saveBriefingSettings() {
   briefingSaving.value = true;
   briefingSaved.value = false;
@@ -1316,6 +1323,22 @@ function formatUserDate(iso: string): string {
           </label>
           <p class="field-hint">Look up weather for locations in today's calendar events.</p>
         </div>
+
+        <div class="field" style="margin-top: 1rem">
+          <label class="field-label">Temperature unit</label>
+          <div class="briefing-unit-toggle">
+            <button
+              type="button"
+              :class="['briefing-unit-btn', { active: briefingConfig.temp_unit === 'C' }]"
+              @click="briefingConfig.temp_unit = 'C'"
+            >°C</button>
+            <button
+              type="button"
+              :class="['briefing-unit-btn', { active: briefingConfig.temp_unit === 'F' }]"
+              @click="briefingConfig.temp_unit = 'F'"
+            >°F</button>
+          </div>
+        </div>
       </section>
 
       <!-- Work schedule -->
@@ -1333,13 +1356,42 @@ function formatUserDate(iso: string): string {
         </div>
       </section>
 
+      <!-- Timezone -->
+      <section class="settings-section full-width">
+        <h2>Timezone</h2>
+        <p class="section-desc">
+          Briefing slots fire at the times below in this timezone.
+          Auto-detected from your browser — override if the server should use a different zone.
+        </p>
+        <div class="briefing-timezone-row">
+          <input
+            type="text"
+            class="input"
+            v-model="briefingConfig.timezone"
+            placeholder="e.g. America/New_York"
+            style="flex: 1"
+          />
+          <button
+            type="button"
+            class="btn-secondary"
+            @click="briefingConfig.timezone = Intl.DateTimeFormat().resolvedOptions().timeZone"
+          >Detect</button>
+        </div>
+        <p class="field-hint">
+          Use an
+          <a href="https://en.wikipedia.org/wiki/List_of_tz_database_time_zones" target="_blank" rel="noopener">IANA timezone name</a>
+          (e.g. <code>Europe/London</code>, <code>America/Chicago</code>).
+          Your browser reports: <strong>{{ Intl.DateTimeFormat().resolvedOptions().timeZone }}</strong>
+        </p>
+      </section>
+
       <!-- Slots -->
       <section class="settings-section full-width">
         <h2>Scheduled Slots</h2>
-        <p class="section-desc">Each active slot will post an update into your briefing conversation.</p>
+        <p class="section-desc">Each active slot posts an update into your briefing conversation at the listed local time.</p>
         <div class="briefing-slot-list">
           <div
-            v-for="[key, label, time] in ([
+            v-for="[key, label, localTime] in ([
               ['compilation', 'Morning briefing', '4:00 am'],
               ['morning', 'Office check-in', '8:00 am'],
               ['midday', 'Midday update', '12:00 pm'],
@@ -1350,13 +1402,16 @@ function formatUserDate(iso: string): string {
           >
             <div class="briefing-slot-info">
               <span class="briefing-slot-label">{{ label }}</span>
-              <span class="briefing-slot-time">{{ time }}</span>
+              <span class="briefing-slot-time">{{ localTime }}</span>
             </div>
             <label>
               <input type="checkbox" v-model="briefingConfig.slots[key]" />
             </label>
           </div>
         </div>
+        <p v-if="briefingConfig.timezone" class="field-hint" style="margin-top: 0.5rem">
+          Firing in timezone: <strong>{{ briefingConfig.timezone }}</strong>
+        </p>
       </section>
 
       <!-- RSS Feeds -->
@@ -2697,6 +2752,38 @@ function formatUserDate(iso: string): string {
   flex-wrap: wrap;
   margin-top: 0.5rem;
 }
+.briefing-timezone-row {
+  display: flex;
+  gap: 0.5rem;
+  align-items: center;
+  margin-bottom: 0.5rem;
+}
+.briefing-unit-toggle {
+  display: flex;
+  gap: 0;
+  border: 1px solid var(--color-border);
+  border-radius: 8px;
+  overflow: hidden;
+  width: fit-content;
+  margin-top: 0.25rem;
+}
+.briefing-unit-btn {
+  padding: 0.35rem 1rem;
+  background: var(--color-bg-card);
+  color: var(--color-text-muted);
+  font-size: 0.85rem;
+  cursor: pointer;
+  border: none;
+  font-family: inherit;
+  transition: all 0.15s;
+}
+.briefing-unit-btn:first-child {
+  border-right: 1px solid var(--color-border);
+}
+.briefing-unit-btn.active {
+  background: var(--color-primary);
+  color: #fff;
+}
 .briefing-day-btn {
   padding: 0.35rem 0.65rem;
   border: 1px solid var(--color-border);

frontend/src/views/WorkspaceView.vue

@@ -80,7 +80,7 @@ watch(
         activeNoteId.value = tc.result.data.id as number;
       }
       if (
-        ["create_task", "update_task"].includes(tc.function) &&
+        ["create_task", "update_task", "create_milestone", "update_milestone"].includes(tc.function) &&
         tc.status === "success"
       ) {
         taskPanelRef.value?.reload();
@@ -115,6 +115,7 @@ function scrollToBottom() {
 }
 
 watch(() => chatStore.streamingContent, scrollToBottom);
+watch(() => chatStore.currentConversation?.messages.length, scrollToBottom);
 
 function togglePanel(panel: keyof typeof panelOpen.value) {
   const open = panelOpen.value;

src/fabledassistant/routes/briefing.py

@@ -44,6 +44,9 @@ async def get_config():
 async def put_config():
     data = await request.get_json()
     await set_settings_batch(g.user.id, {"briefing_config": json.dumps(data)})
+    # Live-patch the scheduler so the new timezone takes effect immediately.
+    from fabledassistant.services.briefing_scheduler import update_user_schedule
+    update_user_schedule(g.user.id, data)
     return jsonify({"ok": True})
 
 

src/fabledassistant/services/briefing_pipeline.py

@@ -80,7 +80,7 @@ async def _gather_internal(user_id: int) -> dict:
     # Calendar events today
     calendar_events = []
     try:
-        if is_caldav_configured():
+        if is_caldav_configured(user_id):
             events = await list_events(user_id, start=today, end=today)
             calendar_events = [
                 f"{e.get('summary', 'Event')} at {e.get('dtstart', 'unknown time')}"
@@ -94,7 +94,7 @@ async def _gather_internal(user_id: int) -> dict:
     try:
         projects = await list_projects(user_id)
         for p in projects[:5]:
-            projects_summary.append(p.get("title", "Untitled project"))
+            projects_summary.append(p.title or "Untitled project")
     except Exception:
         logger.warning("Failed to gather projects for briefing", exc_info=True)
 
@@ -192,16 +192,26 @@ def _internal_user_prompt(data: dict, slot: str) -> str:
     return "\n".join(lines)
 
 
-def _external_user_prompt(data: dict, slot: str) -> str:
+def _format_temp(value: float, unit: str) -> str:
+    """Convert Celsius to the requested unit and format as an integer string."""
+    if unit == "F":
+        return f"{value * 9 / 5 + 32:.0f}"
+    return f"{value:.0f}"
+
+
+def _external_user_prompt(data: dict, slot: str, temp_unit: str = "C") -> str:
+    unit_sym = f"°{temp_unit}"
     lines = [f"Briefing slot: {slot}", ""]
     if data["weather"]:
         lines.append("WEATHER:")
         for loc in data["weather"]:
             lines.append(f"  {loc['location_label']}:")
             for day in loc["days"][:3]:
+                t_min = _format_temp(day["temp_min"], temp_unit)
+                t_max = _format_temp(day["temp_max"], temp_unit)
                 lines.append(
                     f"    {day['date']}: {day['description']}, "
-                    f"{day['temp_min']}–{day['temp_max']}°C, {day['precip_mm']}mm rain"
+                    f"{t_min}–{t_max}{unit_sym}, {day['precip_mm']}mm rain"
                 )
             if loc["changes_since_last_fetch"]:
                 lines.append("  FORECAST CHANGES:")
@@ -218,6 +228,18 @@ def _external_user_prompt(data: dict, slot: str) -> str:
 
 # ── Main entry point ───────────────────────────────────────────────────────────
 
+async def _get_temp_unit(user_id: int) -> str:
+    """Read the user's preferred temperature unit from briefing_config ('C' or 'F')."""
+    import json
+    raw = await get_setting(user_id, "briefing_config", "{}")
+    try:
+        config = json.loads(raw) if isinstance(raw, str) else (raw or {})
+        unit = config.get("temp_unit", "C")
+        return unit if unit in ("C", "F") else "C"
+    except Exception:
+        return "C"
+
+
 async def run_compilation(user_id: int, slot: str, model: str | None = None) -> str:
     """
     Run the full two-lane briefing pipeline for a user and slot.
@@ -227,7 +249,10 @@ async def run_compilation(user_id: int, slot: str, model: str | None = None) ->
         model = await get_setting(user_id, "default_model", Config.OLLAMA_MODEL)
 
     from fabledassistant.services.briefing_profile import get_profile_body
-    profile_body = await get_profile_body(user_id)
+    profile_body, temp_unit = await asyncio.gather(
+        get_profile_body(user_id),
+        _get_temp_unit(user_id),
+    )
 
     # Parallel gather
     internal_data, external_data = await asyncio.gather(
@@ -244,7 +269,7 @@ async def run_compilation(user_id: int, slot: str, model: str | None = None) ->
         ),
         _llm_synthesise(
             _external_system_prompt(),
-            _external_user_prompt(external_data, slot),
+            _external_user_prompt(external_data, slot, temp_unit),
             model,
         ),
     )
@@ -268,9 +293,10 @@ async def run_slot_injection(user_id: int, slot: str, model: str | None = None)
     if model is None:
         model = await get_setting(user_id, "default_model", Config.OLLAMA_MODEL)
 
-    internal_data, external_data = await asyncio.gather(
+    internal_data, external_data, temp_unit = await asyncio.gather(
         _gather_internal(user_id),
         _gather_external(user_id),
+        _get_temp_unit(user_id),
     )
 
     system = (
@@ -281,6 +307,6 @@ async def run_slot_injection(user_id: int, slot: str, model: str | None = None)
         f"Slot: {slot}\n\n"
         + _internal_user_prompt(internal_data, slot)
         + "\n\n"
-        + _external_user_prompt(external_data, slot)
+        + _external_user_prompt(external_data, slot, temp_unit)
     )
     return await _llm_synthesise(system, user_prompt, model)

src/fabledassistant/services/briefing_scheduler.py

@@ -1,14 +1,20 @@
 """
-APScheduler-based briefing scheduler.
+APScheduler-based briefing scheduler — per-user, timezone-aware.
+
+Each enabled user gets 4 individual CronTrigger jobs keyed to their IANA
+timezone (stored in briefing_config.timezone).  Changing the config via the
+settings UI calls update_user_schedule() which live-patches the scheduler
+without a restart.
 
 Uses a background thread scheduler (not async) because APScheduler 3.x's
-AsyncIOScheduler has known issues with Quart/hypercorn. Jobs are async functions
-wrapped with asyncio.run_coroutine_threadsafe().
+AsyncIOScheduler has known issues with Quart/hypercorn.  Jobs are async
+functions wrapped with asyncio.run_coroutine_threadsafe().
 """
 
 import asyncio
 import logging
-from datetime import date, datetime, time, timedelta, timezone
+from datetime import date, datetime, time, timedelta
+from zoneinfo import ZoneInfo, ZoneInfoNotFoundError
 
 from apscheduler.schedulers.background import BackgroundScheduler
 from apscheduler.triggers.cron import CronTrigger
@@ -20,8 +26,9 @@ from fabledassistant.models.setting import Setting
 logger = logging.getLogger(__name__)
 
 _scheduler: BackgroundScheduler | None = None
+_loop: asyncio.AbstractEventLoop | None = None
 
-# Slot definitions: (name, hour, minute)
+# Slot definitions: (name, hour, minute) — local time in the user's timezone
 SLOTS = [
     ("compilation", 4, 0),
     ("morning", 8, 0),
@@ -30,8 +37,22 @@ SLOTS = [
 ]
 
 
+# ── Helpers ───────────────────────────────────────────────────────────────────
+
+def _resolve_timezone(tz_str: str) -> str:
+    """Validate and return an IANA timezone string, falling back to UTC."""
+    if not tz_str:
+        return "UTC"
+    try:
+        ZoneInfo(tz_str)
+        return tz_str
+    except (ZoneInfoNotFoundError, KeyError):
+        logger.warning("Invalid timezone %r in briefing config, falling back to UTC", tz_str)
+        return "UTC"
+
+
 async def _get_briefing_enabled_users() -> list[tuple[int, str]]:
-    """Return [(user_id, model)] for users with briefing enabled."""
+    """Return [(user_id, iana_timezone)] for all users with briefing enabled."""
     import json
     async with async_session() as session:
         result = await session.execute(
@@ -44,12 +65,60 @@ async def _get_briefing_enabled_users() -> list[tuple[int, str]]:
         try:
             config = json.loads(row.value) if row.value else {}
             if config.get("enabled"):
-                enabled.append((row.user_id, ""))  # model resolved per-user at runtime
+                tz = _resolve_timezone(config.get("timezone", "UTC"))
+                enabled.append((row.user_id, tz))
         except Exception:
             pass
     return enabled
 
 
+def _job_id(user_id: int, slot: str) -> str:
+    return f"briefing_{slot}_user_{user_id}"
+
+
+def _add_user_jobs(user_id: int, tz: str) -> None:
+    """Add (or replace) all 4 slot jobs for a user in their timezone."""
+    if _scheduler is None or _loop is None:
+        return
+    for slot_name, hour, minute in SLOTS:
+        _scheduler.add_job(
+            _run_user_slot_sync,
+            CronTrigger(hour=hour, minute=minute, timezone=tz),
+            args=[user_id, slot_name],
+            id=_job_id(user_id, slot_name),
+            replace_existing=True,
+            misfire_grace_time=3600,
+        )
+    logger.info("Scheduled briefing jobs for user %d in timezone %s", user_id, tz)
+
+
+def _remove_user_jobs(user_id: int) -> None:
+    """Remove all slot jobs for a user."""
+    if _scheduler is None:
+        return
+    for slot_name, _, _ in SLOTS:
+        jid = _job_id(user_id, slot_name)
+        if _scheduler.get_job(jid):
+            _scheduler.remove_job(jid)
+    logger.info("Removed briefing jobs for user %d", user_id)
+
+
+# ── Public API ────────────────────────────────────────────────────────────────
+
+def update_user_schedule(user_id: int, config: dict) -> None:
+    """
+    Called when a user saves their briefing config via the settings UI.
+    Live-patches the scheduler — no restart required.
+    """
+    if config.get("enabled"):
+        tz = _resolve_timezone(config.get("timezone", "UTC"))
+        _add_user_jobs(user_id, tz)
+    else:
+        _remove_user_jobs(user_id)
+
+
+# ── Job execution ─────────────────────────────────────────────────────────────
+
 async def _run_slot_for_user(user_id: int, slot: str) -> None:
     """Execute one slot job for one user."""
     from fabledassistant.services.briefing_conversations import (
@@ -64,12 +133,11 @@ async def _run_slot_for_user(user_id: int, slot: str) -> None:
     if slot == "compilation":
         # Refresh external data first
         try:
-            from fabledassistant.services.rss import refresh_all_feeds
             import json
+            from fabledassistant.services.rss import refresh_all_feeds
             config_raw = await get_setting(user_id, "briefing_config", "{}")
             config = json.loads(config_raw) if isinstance(config_raw, str) else {}
             await refresh_all_feeds(user_id)
-            # Refresh weather for configured locations
             from fabledassistant.services import weather as wx
             for key, loc in config.get("locations", {}).items():
                 if loc.get("lat") and loc.get("lon"):
@@ -83,25 +151,19 @@ async def _run_slot_for_user(user_id: int, slot: str) -> None:
         except Exception:
             logger.warning("Pre-compilation refresh failed for user %d", user_id, exc_info=True)
 
-        # Run previous day's profile close-out
         await _run_profile_closeout(user_id, model)
-
-        # Create today's conversation and post opening message
         conv = await get_or_create_today_conversation(user_id, model)
         text = await run_compilation(user_id, slot, model)
         if text:
             await post_message(conv.id, "assistant", text)
 
     else:
-        # Inject slot update into today's conversation
         conv = await get_or_create_today_conversation(user_id, model)
         text = await run_slot_injection(user_id, slot, model)
         if text:
-            # Post as a system-injected user prompt + assistant response pair
             await post_message(conv.id, "user", f"[{slot.title()} briefing update]")
             await post_message(conv.id, "assistant", text)
 
-    # Send push notification
     try:
         from fabledassistant.services.push import send_push_notification
         slot_labels = {
@@ -122,10 +184,22 @@ async def _run_slot_for_user(user_id: int, slot: str) -> None:
     logger.info("Briefing slot '%s' completed for user %d", slot, user_id)
 
 
+def _run_user_slot_sync(user_id: int, slot: str) -> None:
+    """Synchronous wrapper called by APScheduler's background thread."""
+    if _loop is None:
+        logger.error("No event loop available for briefing slot %s user %d", slot, user_id)
+        return
+    future = asyncio.run_coroutine_threadsafe(_run_slot_for_user(user_id, slot), _loop)
+    try:
+        future.result(timeout=600)
+    except Exception:
+        logger.exception("Briefing slot '%s' failed for user %d", slot, user_id)
+
+
 async def _run_profile_closeout(user_id: int, model: str) -> None:
     """
-    Read yesterday's briefing conversation, ask the LLM to extract preference
-    observations, and append them to the briefing profile note.
+    Read yesterday's briefing conversation, extract preference observations,
+    and append them to the briefing profile note.
     """
     from fabledassistant.services.briefing_profile import append_observations
     from fabledassistant.services.briefing_pipeline import _llm_synthesise
@@ -149,7 +223,7 @@ async def _run_profile_closeout(user_id: int, model: str) -> None:
         messages = list(msgs_result.scalars().all())
 
     if len(messages) < 2:
-        return  # Nothing interesting to learn from
+        return
 
     transcript = "\n".join(
         f"{m.role.upper()}: {m.content[:500]}" for m in messages[-20:]
@@ -166,100 +240,97 @@ async def _run_profile_closeout(user_id: int, model: str) -> None:
         await append_observations(user_id, observations)
 
 
-def _run_slot_sync(slot: str, loop: asyncio.AbstractEventLoop) -> None:
-    """Synchronous wrapper called by APScheduler's background thread."""
-    async def _job():
-        users = await _get_briefing_enabled_users()
-        for user_id, _ in users:
-            try:
-                await _run_slot_for_user(user_id, slot)
-            except Exception:
-                logger.exception("Briefing slot '%s' failed for user %d", slot, user_id)
-
-    future = asyncio.run_coroutine_threadsafe(_job(), loop)
-    try:
-        future.result(timeout=600)  # 10 min max per slot run
-    except Exception:
-        logger.exception("Briefing slot '%s' job failed", slot)
-
+# ── Startup / catchup ─────────────────────────────────────────────────────────
 
 async def _catchup_missed_slots(loop: asyncio.AbstractEventLoop) -> None:
     """
-    On startup, check if any slot was missed within the last 24 hours.
-    Fire it once if so. Never backfill more than one slot per slot-name.
+    On startup, fire any slot that was missed in the last 24 hours
+    (one catch-up per slot per user, evaluated in the user's local timezone).
     """
-    now = datetime.now(timezone.utc)
-    today = now.date()
+    users = await _get_briefing_enabled_users()
+    for user_id, tz in users:
+        user_tz = ZoneInfo(tz)
+        now_local = datetime.now(user_tz)
+        today_local = now_local.date()
 
-    for slot_name, hour, minute in SLOTS:
-        slot_time = datetime.combine(today, time(hour, minute), tzinfo=timezone.utc)
-        if slot_time > now:
-            continue  # Hasn't happened yet today
-        age = (now - slot_time).total_seconds()
-        if age > 86400:
-            continue  # More than 24h ago — skip
-        # Check if we already have a message for this slot today
-        # Simple heuristic: if today's briefing conversation has messages posted
-        # after the slot time, consider it covered
-        users = await _get_briefing_enabled_users()
-        for user_id, _ in users:
+        for slot_name, hour, minute in SLOTS:
+            slot_local = datetime.combine(today_local, time(hour, minute), tzinfo=user_tz)
+            if slot_local > now_local:
+                continue  # Not yet due
+            age = (now_local - slot_local).total_seconds()
+            if age > 86400:
+                continue  # More than 24h ago — skip
+
+            # Check if today's conversation already has a message from after slot time
             async with async_session() as session:
                 from fabledassistant.models.conversation import Conversation, Message
                 result = await session.execute(
                     select(Conversation).where(
                         Conversation.user_id == user_id,
                         Conversation.conversation_type == "briefing",
-                        Conversation.briefing_date == today,
+                        Conversation.briefing_date == today_local,
                     )
                 )
                 conv = result.scalars().first()
                 if conv:
+                    # Convert slot_local to UTC for DB comparison (stored as UTC)
+                    slot_utc = slot_local.astimezone(ZoneInfo("UTC"))
                     msgs = await session.execute(
                         select(Message).where(
                             Message.conversation_id == conv.id,
-                            Message.created_at >= slot_time,
+                            Message.created_at >= slot_utc,
                         ).limit(1)
                     )
                     if msgs.scalars().first():
                         continue  # Already covered
-            # Fire the missed slot
-            logger.info("Catching up missed briefing slot '%s' for user %d", slot_name, user_id)
+
+            logger.info(
+                "Catching up missed briefing slot '%s' for user %d (tz: %s)",
+                slot_name, user_id, tz,
+            )
             try:
                 await _run_slot_for_user(user_id, slot_name)
             except Exception:
-                logger.exception("Catch-up for slot '%s' user %d failed", slot_name, user_id)
+                logger.exception(
+                    "Catch-up for slot '%s' user %d failed", slot_name, user_id
+                )
 
 
 def start_briefing_scheduler(loop: asyncio.AbstractEventLoop) -> None:
     """
-    Start the APScheduler background scheduler.
+    Start the APScheduler background scheduler with per-user timezone-aware jobs.
     Must be called from the app's before_serving hook with the running event loop.
     """
-    global _scheduler
+    global _scheduler, _loop
     if _scheduler is not None:
         return
 
+    _loop = loop
     _scheduler = BackgroundScheduler(timezone="UTC")
 
-    for slot_name, hour, minute in SLOTS:
-        _scheduler.add_job(
-            _run_slot_sync,
-            CronTrigger(hour=hour, minute=minute),
-            args=[slot_name, loop],
-            id=f"briefing_{slot_name}",
-            replace_existing=True,
-            misfire_grace_time=3600,  # Fire up to 1h late rather than skip
-        )
+    # Schedule jobs synchronously: run the async query in the provided loop
+    future = asyncio.run_coroutine_threadsafe(_get_briefing_enabled_users(), loop)
+    try:
+        users = future.result(timeout=10)
+    except Exception:
+        logger.exception("Failed to load briefing users at startup")
+        users = []
+
+    for user_id, tz in users:
+        _add_user_jobs(user_id, tz)
 
     _scheduler.start()
-    logger.info("Briefing scheduler started")
+    logger.info(
+        "Briefing scheduler started with %d user(s) across %d job(s)",
+        len(users), len(users) * len(SLOTS),
+    )
 
-    # Catch up missed slots in the background
     asyncio.run_coroutine_threadsafe(_catchup_missed_slots(loop), loop)
 
 
 def stop_briefing_scheduler() -> None:
-    global _scheduler
+    global _scheduler, _loop
     if _scheduler:
         _scheduler.shutdown(wait=False)
         _scheduler = None
+    _loop = None

src/fabledassistant/services/tools.py

@@ -436,6 +436,24 @@ _CORE_TOOLS = [
             },
         },
     },
+    {
+        "type": "function",
+        "function": {
+            "name": "update_milestone",
+            "description": "Update the title, description, or status of an existing milestone.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "project": {"type": "string", "description": "Project title the milestone belongs to"},
+                    "milestone": {"type": "string", "description": "Current milestone title to look up"},
+                    "title": {"type": "string", "description": "New title (omit to keep current)"},
+                    "description": {"type": "string", "description": "New description (omit to keep current)"},
+                    "status": {"type": "string", "enum": ["active", "completed", "cancelled"], "description": "New status (omit to keep current)"},
+                },
+                "required": ["project", "milestone"],
+            },
+        },
+    },
     {
         "type": "function",
         "function": {
@@ -1426,6 +1444,35 @@ async def execute_tool(user_id: int, tool_name: str, arguments: dict) -> dict:
             )
             return {"success": True, "type": "milestone", "data": ms.to_dict()}
 
+        elif tool_name == "update_milestone":
+            from fabledassistant.services.projects import get_project_by_title as _gpbt, list_projects as _lp
+            from fabledassistant.services.milestones import get_milestone_by_title as _gmbt, update_milestone as _um
+            project_name = arguments.get("project", "")
+            milestone_name = arguments.get("milestone", "")
+            if not project_name or not milestone_name:
+                return {"success": False, "error": "Both project and milestone are required"}
+            proj = await _gpbt(user_id, project_name)
+            if proj is None:
+                all_p = await _lp(user_id)
+                matches = [p for p in all_p if project_name.lower() in p.title.lower()]
+                proj = matches[0] if matches else None
+            if proj is None:
+                return {"success": False, "error": f"Project '{project_name}' not found"}
+            ms = await _gmbt(user_id, proj.id, milestone_name)
+            if ms is None:
+                return {"success": False, "error": f"Milestone '{milestone_name}' not found in project '{proj.title}'. Use list_milestones to see available milestones."}
+            fields: dict[str, object] = {}
+            if "title" in arguments:
+                fields["title"] = arguments["title"]
+            if "description" in arguments:
+                fields["description"] = arguments["description"]
+            if "status" in arguments:
+                fields["status"] = arguments["status"]
+            if not fields:
+                return {"success": False, "error": "No fields to update — provide at least one of: title, description, status"}
+            updated = await _um(user_id, ms.id, **fields)
+            return {"success": True, "type": "milestone", "data": updated.to_dict()}
+
         elif tool_name == "list_milestones":
             from fabledassistant.services.projects import get_project_by_title as _gpbt, list_projects as _lp
             from fabledassistant.services.milestones import get_project_milestone_summary

summary.md

@@ -12,7 +12,52 @@
 >    Include file-level details in the commit body when the change is non-trivial.
 
 ## Last Updated
-2026-03-11 — Multi-user sharing & collaboration, in-app notifications, groups management, backup rewrite.
+2026-03-12 — Daily Briefing feature (full stack), CI release process fix, CalVer version tracking, content deduplication, task history improvements.
+
+**CI release process (2026-03-12):**
+- `.forgejo/workflows/ci.yml`: removed `main` from `branches` push trigger. CI now fires only on `dev` pushes, `v*` tags, and pull requests. Main branch merges no longer trigger a run — the PR check covers pre-merge safety. Production release process: create a release via Forgejo UI on `main` with a `v*` tag → tag push event fires CI → build job pushes `:latest` + `:<version>` Docker images to registry. Branch protection is not an obstacle because the UI release creates the tag through the API.
+
+---
+
+**Daily Briefing — full feature (2026-03-11):**
+
+Backend:
+- Migration `0026_add_briefing_tables.py`: `rss_feeds` (url, name, user_id), `rss_items` (feed_id FK, guid, title, url, summary, pub_date), `weather_cache` (user_id UNIQUE, lat, lon, location_name, forecast_json, fetched_at); added `conversation_type` TEXT and `briefing_date` DATE to `conversations`.
+- `models/rss_feed.py`, `models/rss_item.py`, `models/weather_cache.py`: SQLAlchemy models with `to_dict()`.
+- `services/weather.py`: geocoding via Nominatim (Open-Meteo), forecast fetch via Open-Meteo API, per-user DB cache with change detection. `get_weather(user_id)` returns structured dict with location, current, and 5-day forecast.
+- `services/rss.py`: feedparser-based fetch, per-feed DB cache with prune-to-100. `get_rss_items(user_id, limit)` returns recent items across all user feeds.
+- `services/briefing_profile.py`: service that reads user briefing config (CalDAV, weather, RSS, office days, tasks) and composes a profile note used as context for generation.
+- `services/briefing_pipeline.py`: two-lane parallel gather (async `asyncio.gather` over weather, RSS, tasks, calendar) → LLM synthesis. Streams result into a `GenerationBuffer` using the same SSE infrastructure as chat.
+- `routes/briefing.py`: RSS CRUD at `/api/briefing/feeds`, weather config at `/api/briefing/weather`, briefing config at `/api/briefing/config`, `POST /api/briefing/trigger` to manually fire a slot. Registered as `briefing_bp` in `app.py`.
+- `routes/chat.py`: `GET /api/briefing/conversations/today` — creates the day's briefing conversation if absent (type=`briefing`, `briefing_date=today`); `GET /api/briefing/conversations` — lists all past briefing conversations.
+- `services/generation_task.py` / `routes/chat.py`: `conversation_type` filter support so briefing conversations are excluded from the main chat list and vice versa.
+- APScheduler integration: `services/scheduler.py` runs briefing slots (morning, midday, evening) on schedule with catch-up logic — if a slot was missed while the server was down, it runs immediately on next startup.
+- LLM tools: `get_weather` and `get_rss_items` added to `_CORE_TOOLS` in `services/tools.py`.
+
+Frontend:
+- `frontend/src/views/BriefingView.vue` (new): primary briefing page. Soft chat-style layout. Top section shows the digest card (expandable) followed by the conversation thread. Reply bar at bottom — sends via standard chat endpoints and streams via SSE. Manual "Refresh" button triggers a new briefing generation. Conversation history dropdown (past briefing dates) in header.
+- `frontend/src/components/BriefingSetupWizard.vue` (new): 4-step setup wizard shown on first visit when briefing is not configured (welcome → location → office days → RSS feeds). Completes by enabling briefing in settings.
+- `frontend/src/views/SettingsView.vue`: Briefing tab added (`briefing` in `VALID_TABS`): enable toggle, location geocoding input (live preview), office days checkboxes, time slot toggles (morning/midday/evening), RSS feed CRUD (add URL + name, list, delete), push notification toggle for briefing completion.
+- `frontend/src/router/index.ts`: `/briefing` route added → `BriefingView`.
+- `frontend/src/components/AppHeader.vue`: "Briefing" nav link added.
+
+---
+
+**Previous session (2026-03-11):**
+
+**Version footer + CalVer tracking:**
+- `4636c9a` Add CalVer build-time version tracking: `Dockerfile` injects `BUILD_VERSION` ARG as `VITE_APP_VERSION` env var during frontend build. Frontend reads `import.meta.env.VITE_APP_VERSION` and displays it in the Settings footer. Docker image tags include `:<version>` on release builds.
+- `2cb4e6d` Version footer, task history UI, note version retention policy: Settings page shows `v<version>` in footer. Task history now displays inline in a sidebar within the task editor (previously required navigation). Note version retention policy configurable (max versions per note, default 20 — enforced at write time in `services/note_versions.py`).
+
+**Content deduplication + history sidebar:**
+- `6d593a0` Move history to sidebar, simplify task assist, add content deduplication: `HistoryPanel` moved to a collapsible right sidebar in `NoteEditorView` (previously a modal overlay). Writing assist panel simplified — removed multi-step UX, direct instruction input. `build_context()` in `services/llm.py` deduplicates injected content (RAG-found notes, sidebar includes, context notes) by ID so the same note cannot appear in multiple context blocks.
+
+**ShareDialog CSS fix:**
+- `a63f067` Fix ShareDialog transparent background — replaced undefined CSS custom property references with explicit values.
+
+---
+
+**Previous session (2026-03-11 — Multi-user & backup):** Multi-user sharing & collaboration, in-app notifications, groups management, backup rewrite.
 
 **Multi-user sharing & collaboration:**
 - `alembic/versions/0025_add_sharing_and_notifications.py` (new): creates `groups`, `group_memberships`, `project_shares`, `note_shares`, `notifications` tables. Partial unique indexes via raw SQL. CHECK constraint enforces exclusive user/group target on share rows.