Merge pull request 'Release v26.04.14.3 — Live amplitude mic pulse' (#34) from dev into main

The mic button now scales and glows proportional to the silence
detector's RMS amplitude instead of sitting static. Gives obvious
feedback that audio is actually being picked up — silence still
breathes via a 0.1 floor, loud input caps at ~1.18x scale so it
doesn't punch through the input bar.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

frontend/src/components/ChatInputBar.vue

@@ -114,6 +114,18 @@ const transcribingVoice = ref(false)
 const recorder = useVoiceRecorder()
 const silenceDetector = useSilenceDetector()
 
+// Live mic pulse. `silenceDetector.amplitude` is 0..1 RMS; we floor at 0.1
+// so the button still breathes on silence and cap the scale growth so loud
+// input doesn't punch through the input bar.
+const micStyle = computed(() => {
+  if (!recorder.recording.value) return {}
+  const pulse = 0.1 + Math.min(silenceDetector.amplitude.value, 1) * 0.9
+  return {
+    transform: `scale(${1 + pulse * 0.18})`,
+    boxShadow: `0 0 ${6 + pulse * 14}px ${2 + pulse * 4}px rgba(239, 68, 68, ${0.2 + pulse * 0.3})`,
+  }
+})
+
 async function toggleVoice() {
   if (transcribingVoice.value) return
   if (recorder.recording.value) {
@@ -235,6 +247,7 @@ defineExpose({ focus, prefill })
         v-if="voiceEnabled"
         class="btn-icon btn-mic"
         :class="{ 'mic-recording': recorder.recording.value, 'mic-transcribing': transcribingVoice }"
+        :style="micStyle"
         @click.prevent="toggleVoice"
         :disabled="transcribingVoice || !store.chatReady"
         :title="recorder.recording.value ? 'Click to stop (or wait for silence)' : 'Click to speak'"
@@ -343,7 +356,14 @@ defineExpose({ focus, prefill })
 .btn-icon:hover { opacity: 1; }
 .btn-icon:disabled { opacity: 0.3; cursor: default; }
 
-.btn-mic.mic-recording { opacity: 1; color: #ef4444; }
+.btn-mic.mic-recording {
+  opacity: 1;
+  color: #ef4444;
+  border-radius: 50%;
+  /* Smooth between amplitude samples (~100ms) so the pulse feels continuous
+     rather than stepping. */
+  transition: transform 0.12s ease-out, box-shadow 0.12s ease-out;
+}
 .btn-mic.mic-transcribing { opacity: 0.5; }
 
 .note-picker-wrapper { position: relative; }

src/fabledassistant/routes/briefing.py

@@ -537,10 +537,16 @@ async def discuss_article(item_id: int):
     # exchange and the conversational seed user prompt into the conversation.
     # The /news from-article route calls the same helper so behavior stays
     # byte-identical across entry points.
-    from fabledassistant.services.article_context import seed_article_discussion
+    from fabledassistant.services.article_context import (
+        EmptyArticleError,
+        seed_article_discussion,
+    )
 
     model = await get_setting(uid, "default_model", "") or ""
-    discuss_prompt = await seed_article_discussion(conv_id, item, model)
+    try:
+        discuss_prompt = await seed_article_discussion(conv_id, item, model)
+    except EmptyArticleError as e:
+        return jsonify({"error": str(e)}), 422
 
     # Reload conversation with fresh messages to build history
     conv = await get_conversation(uid, conv_id)

src/fabledassistant/routes/chat.py

@@ -521,7 +521,10 @@ async def create_conversation_from_article(item_id: int):
     from sqlalchemy import select as _select
     from fabledassistant.models import async_session as _async_session
     from fabledassistant.models.rss_feed import RssItem, RssFeed
-    from fabledassistant.services.article_context import seed_article_discussion
+    from fabledassistant.services.article_context import (
+        EmptyArticleError,
+        seed_article_discussion,
+    )
 
     uid = get_current_user_id()
 
@@ -540,7 +543,16 @@ async def create_conversation_from_article(item_id: int):
     conv = await create_conversation(uid, title=conv_title, conversation_type="chat")
 
     model = await get_setting(uid, "default_model", "") or Config.OLLAMA_MODEL
-    discuss_prompt = await seed_article_discussion(conv.id, item, model)
+    try:
+        discuss_prompt = await seed_article_discussion(conv.id, item, model)
+    except EmptyArticleError as e:
+        # Roll back the empty conversation so the user doesn't end up with a
+        # phantom entry in their chat list.
+        try:
+            await delete_conversation(uid, conv.id)
+        except Exception:
+            logger.warning("Failed to clean up empty article conversation %s", conv.id)
+        return jsonify({"error": str(e)}), 422
 
     # Reload conversation so we see the two messages the helper just added.
     conv = await get_conversation(uid, conv.id)

src/fabledassistant/services/article_context.py

@@ -182,6 +182,15 @@ ARTICLE_DISCUSS_SEED = (
 )
 
 
+class EmptyArticleError(Exception):
+    """Raised when an article has no extractable body text.
+
+    Callers (the briefing and /news discuss routes) map this to a 422 so the
+    user sees a clear error instead of a hallucinated summary built from an
+    empty synthetic tool result.
+    """
+
+
 async def seed_article_discussion(
     conv_id: int,
     item: RssItem,
@@ -213,15 +222,30 @@ async def seed_article_discussion(
         article_content = item.context_prepared
     else:
         raw_body = await get_or_fetch_full_article(item) or item.content or ""
+        if not raw_body.strip():
+            # Hard-fail rather than stage an empty synthetic tool result.
+            # An empty `content` field silently tells the model "the article
+            # has nothing in it" and it confabulates from RAG/history. Better
+            # to surface a clean error to the user.
+            logger.warning(
+                "Article discussion aborted: empty body for rss_item %s (%s)",
+                item.id, item.url,
+            )
+            raise EmptyArticleError(
+                "Couldn't extract any readable text from this article."
+            )
         article_content = await prepare_article_context(
             item.title or "", item.url, raw_body, model,
         )
-        if article_content:
-            async with async_session() as session:
-                fresh = await session.get(RssItem, item.id)
-                if fresh is not None:
-                    fresh.context_prepared = article_content
-                    await session.commit()
+        if not article_content.strip():
+            raise EmptyArticleError(
+                "Couldn't extract any readable text from this article."
+            )
+        async with async_session() as session:
+            fresh = await session.get(RssItem, item.id)
+            if fresh is not None:
+                fresh.context_prepared = article_content
+                await session.commit()
 
     synthetic_tool_calls = [{
         "function": "read_article",

src/fabledassistant/services/llm.py

@@ -724,18 +724,27 @@ async def build_context(
     orphan_only = rag_project_id is None
     effective_project_id = rag_project_id if (rag_project_id is not None and rag_project_id != -1) else None
 
-    try:
-        from fabledassistant.services.embeddings import semantic_search_notes
-        for score, note in await semantic_search_notes(
-            user_id, user_message, exclude_ids=search_exclude or None, limit=8,
-            project_id=effective_project_id,
-            orphan_only=orphan_only,
-        ):
-            found_scored.append((score, note))
-    except Exception:
-        logger.warning("Semantic note search failed, falling back to keyword search", exc_info=True)
+    # Skip RAG auto-injection on the first turn of a seeded article discussion.
+    # The article body is already the sole context the user wants — pulling in
+    # unrelated orphan notes tricks the model into summarizing those instead.
+    # Follow-up turns keep RAG on because by then the user's own messages drive
+    # the query rather than the generic seed prompt.
+    from fabledassistant.services.article_context import ARTICLE_DISCUSS_SEED
+    _skip_rag_for_article_seed = user_message.strip() == ARTICLE_DISCUSS_SEED
 
-    if not found_scored:
+    if not _skip_rag_for_article_seed:
+        try:
+            from fabledassistant.services.embeddings import semantic_search_notes
+            for score, note in await semantic_search_notes(
+                user_id, user_message, exclude_ids=search_exclude or None, limit=8,
+                project_id=effective_project_id,
+                orphan_only=orphan_only,
+            ):
+                found_scored.append((score, note))
+        except Exception:
+            logger.warning("Semantic note search failed, falling back to keyword search", exc_info=True)
+
+    if not found_scored and not _skip_rag_for_article_seed:
         keywords = _extract_keywords(user_message)
         if keywords:
             try: