feat: listen mode + volume knob in chat; briefing discuss auto-send; fix LLM proactive note search

- ChatView: listen mode toggle (auto-reads new responses via TTS), volume popup
  with range slider persisted per-device in localStorage via GainNode
- useVoiceAudio: shared module-level _volume ref with localStorage persistence,
  GainNode for volume control, exported setVoiceVolume()
- tts.py: pre-warm all Kokoro voices at pipeline load to eliminate HuggingFace
  HEAD requests at synthesis time (reduces TTS latency)
- BriefingView: discuss article button now auto-sends instead of just filling input;
  prompt capped to 15 sentences; send() accepts optional overrideText
- llm.py: instruct LLM not to proactively search notes or comment on note absence

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

src/fabledassistant/services/llm.py

@@ -507,7 +507,8 @@ async def build_context(
         "Use search_notes for conceptual/semantic queries — e.g. 'what notes do I have about X' or "
         "'find notes related to Y' — it uses semantic understanding to find thematically related content "
         "even when exact words don't match. Pass project= to scope the search to a specific project. "
-        "Use delete_note / delete_task only when explicitly asked to delete — these require confirmation."
+        "Use delete_note / delete_task only when explicitly asked to delete — these require confirmation. "
+        "Never proactively search notes or comment on the absence of notes/context unless the user explicitly asks about their notes."
     )
     tool_guidance = "\n".join(tool_lines)
 

src/fabledassistant/services/tts.py

@@ -46,11 +46,18 @@ async def load_tts_model() -> None:
 
             logger.info("Loading Kokoro TTS pipeline...")
             loop = asyncio.get_running_loop()
-            _pipeline = await loop.run_in_executor(
-                None,
-                lambda: KPipeline(lang_code="a"),  # "a" = American English
-            )
-            logger.info("Kokoro TTS pipeline loaded")
+            def _load_and_warm():
+                p = KPipeline(lang_code="a")  # "a" = American English
+                # Pre-load all voice tensors so synthesis never hits HuggingFace at request time
+                for v in _VOICES:
+                    try:
+                        p.load_voice(v["id"])
+                    except Exception:
+                        pass
+                return p
+
+            _pipeline = await loop.run_in_executor(None, _load_and_warm)
+            logger.info("Kokoro TTS pipeline loaded and voices pre-warmed")
         except Exception:
             _load_error = "Failed to load Kokoro TTS pipeline"
             logger.exception(_load_error)