feat: plan per-user memory integration

AGENTS.md

@@ -49,7 +49,7 @@ All config lives in `.env` (git-ignored). See `.env.example` for the full list.
 Key variables:
 - `AZURE_SPEECH_KEY` — Azure Speech resource key
 - `AZURE_SPEECH_REGION` — default `eastus`
-- `AZURE_TTS_VOICE` — default voice (e.g. `en-US-AvaNeural`)
+- `AZURE_TTS_VOICE` — default voice (`en-US-Ava:DragonHDOmniLatestNeural`)
 - `GEMMA_BASE_URL` — LLM endpoint (default `http://192.168.86.2:8023/v1`)
 - `GEMMA_MODEL` — model name (default `gemma-4-e4b`)
 
@@ -61,7 +61,7 @@ Supported voices: any Azure Neural voice. See https://learn.microsoft.com/en-us/
 
 ## SSML / Expressive Speech
 
-The TTS layer uses full SSML with `<mstts:express-as>` for style and `<prosody>` for rate/volume/pitch. The agent's system prompt instructs the LLM to write in a conversational, spoken style (short sentences, natural phrasing) so the output sounds like speech, not text.
+The TTS layer wraps output in SSML. The default Azure Dragon HD Omni voice recognizes inline style markers such as `[appreciative]`, `[whispering]`, and `[Neutral]`; the agent prompt allows these markers while keeping responses short and conversational.
 
 ## Agent Prompt
 
@@ -89,7 +89,7 @@ curl -s "https://eastus.tts.speech.microsoft.com/cognitiveservices/v1" \
   -H "Ocp-Apim-Subscription-Key: $AZURE_SPEECH_KEY" \
   -H "Content-Type: application/ssml+xml" \
   -H "X-Microsoft-OutputFormat: audio-24khz-48kbitrate-mono-mp3" \
-  --data-binary '<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="en-US"><voice name="en-US-AvaNeural">Test</voice></speak>' > /tmp/test.mp3
+  --data-binary '<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="en-US"><voice name="en-US-Ava:DragonHDOmniLatestNeural">[appreciative] Test complete.</voice></speak>' > /tmp/test.mp3
 ```
 
 ## File Layout