feat: initial Sol virtual librarian implementation

Matrix bot with E2EE (matrix-sdk 0.9) that passively archives all messages to OpenSearch and responds to queries via Mistral AI with function calling tools. Core systems: - Archive: bulk OpenSearch indexer with batch/flush, edit/redaction handling, embedding pipeline passthrough - Brain: rule-based engagement evaluator (mentions, DMs, name invocations), LLM-powered spontaneous engagement, per-room conversation context windows, response delay simulation - Tools: search_archive, get_room_context, list_rooms, get_room_members registered as Mistral function calling tools with iterative tool loop - Personality: templated system prompt with Sol's librarian persona 47 unit tests covering config, evaluator, conversation windowing, personality templates, schema serialization, and search query building.
2026-03-20 21:40:13 +00:00
commit 4dc20bee23
21 changed files with 6934 additions and 0 deletions
--- a/src/tools/mod.rs
+++ b/src/tools/mod.rs
@@ -0,0 +1,151 @@
+pub mod room_history;
+pub mod room_info;
+pub mod search;
+
+use std::sync::Arc;
+
+use matrix_sdk::Client as MatrixClient;
+use mistralai_client::v1::tool::Tool;
+use opensearch::OpenSearch;
+use serde_json::json;
+
+use crate::config::Config;
+
+pub struct ToolRegistry {
+    opensearch: OpenSearch,
+    matrix: MatrixClient,
+    config: Arc<Config>,
+}
+
+impl ToolRegistry {
+    pub fn new(opensearch: OpenSearch, matrix: MatrixClient, config: Arc<Config>) -> Self {
+        Self {
+            opensearch,
+            matrix,
+            config,
+        }
+    }
+
+    pub fn tool_definitions() -> Vec<Tool> {
+        vec![
+            Tool::new(
+                "search_archive".into(),
+                "Search the message archive. Use this to find past conversations, \
+                 messages from specific people, or about specific topics."
+                    .into(),
+                json!({
+                    "type": "object",
+                    "properties": {
+                        "query": {
+                            "type": "string",
+                            "description": "Search query for message content"
+                        },
+                        "room": {
+                            "type": "string",
+                            "description": "Filter by room name (optional)"
+                        },
+                        "sender": {
+                            "type": "string",
+                            "description": "Filter by sender display name (optional)"
+                        },
+                        "after": {
+                            "type": "string",
+                            "description": "Unix timestamp in ms — only messages after this time (optional)"
+                        },
+                        "before": {
+                            "type": "string",
+                            "description": "Unix timestamp in ms — only messages before this time (optional)"
+                        },
+                        "limit": {
+                            "type": "integer",
+                            "description": "Max results to return (default 10)"
+                        },
+                        "semantic": {
+                            "type": "boolean",
+                            "description": "Use semantic search instead of keyword (optional)"
+                        }
+                    },
+                    "required": ["query"]
+                }),
+            ),
+            Tool::new(
+                "get_room_context".into(),
+                "Get messages around a specific point in time or event in a room. \
+                 Useful for understanding the context of a conversation."
+                    .into(),
+                json!({
+                    "type": "object",
+                    "properties": {
+                        "room_id": {
+                            "type": "string",
+                            "description": "The Matrix room ID"
+                        },
+                        "around_timestamp": {
+                            "type": "integer",
+                            "description": "Unix timestamp in ms to center the context around"
+                        },
+                        "around_event_id": {
+                            "type": "string",
+                            "description": "Event ID to center the context around"
+                        },
+                        "before_count": {
+                            "type": "integer",
+                            "description": "Number of messages before the pivot (default 10)"
+                        },
+                        "after_count": {
+                            "type": "integer",
+                            "description": "Number of messages after the pivot (default 10)"
+                        }
+                    },
+                    "required": ["room_id"]
+                }),
+            ),
+            Tool::new(
+                "list_rooms".into(),
+                "List all rooms Sol is currently in, with names and member counts.".into(),
+                json!({
+                    "type": "object",
+                    "properties": {}
+                }),
+            ),
+            Tool::new(
+                "get_room_members".into(),
+                "Get the list of members in a specific room.".into(),
+                json!({
+                    "type": "object",
+                    "properties": {
+                        "room_id": {
+                            "type": "string",
+                            "description": "The Matrix room ID"
+                        }
+                    },
+                    "required": ["room_id"]
+                }),
+            ),
+        ]
+    }
+
+    pub async fn execute(&self, name: &str, arguments: &str) -> anyhow::Result<String> {
+        match name {
+            "search_archive" => {
+                search::search_archive(
+                    &self.opensearch,
+                    &self.config.opensearch.index,
+                    arguments,
+                )
+                .await
+            }
+            "get_room_context" => {
+                room_history::get_room_context(
+                    &self.opensearch,
+                    &self.config.opensearch.index,
+                    arguments,
+                )
+                .await
+            }
+            "list_rooms" => room_info::list_rooms(&self.matrix).await,
+            "get_room_members" => room_info::get_room_members(&self.matrix, arguments).await,
+            _ => anyhow::bail!("Unknown tool: {name}"),
+        }
+    }
+}