feat: multi-agent architecture with Conversations API and persistent state

Mistral Agents + Conversations API integration:
- Orchestrator agent created on startup with Sol's personality + tools
- ConversationRegistry routes messages through persistent conversations
- Per-room conversation state (room_id → conversation_id + token counts)
- Function call handling within conversation responses
- Configurable via [agents] section in sol.toml (use_conversations_api flag)

Multimodal support:
- m.image detection and Matrix media download (mxc:// → base64 data URI)
- ContentPart-based messages sent to Mistral vision models
- Archive stores media_urls for image messages

System prompt rewrite:
- 687 → 150 lines — dense, few-shot examples, hard rules
- {room_context_rules} placeholder for group vs DM behavior
- Sender prefixing (<@user:server>) for multi-user turns in group rooms

SQLite persistence (/data/sol.db):
- Conversation mappings and agent IDs survive reboots
- WAL mode for concurrent reads
- Falls back to in-memory on failure (sneezes into all rooms to signal)
- PVC already mounted at /data alongside Matrix SDK state store

New modules:
- src/persistence.rs — SQLite state store
- src/conversations.rs — ConversationRegistry + message merging
- src/agents/{mod,definitions,registry}.rs — agent lifecycle
- src/agent_ux.rs — reaction + thread progress UX
- src/tools/bridge.rs — tool dispatch for domain agents

102 tests passing.

src/brain/evaluator.rs

@@ -210,14 +210,14 @@ impl Evaluator {
 
         match result {
             Ok(response) => {
-                let text = &response.choices[0].message.content;
+                let text = response.choices[0].message.content.text();
                 info!(
                     raw_response = text.as_str(),
                     model = self.config.mistral.evaluation_model.as_str(),
                     "LLM evaluation raw response"
                 );
 
-                match serde_json::from_str::<serde_json::Value>(text) {
+                match serde_json::from_str::<serde_json::Value>(&text) {
                     Ok(val) => {
                         let relevance = val["relevance"].as_f64().unwrap_or(0.0) as f32;
                         let hook = val["hook"].as_str().unwrap_or("").to_string();