Tori: AI agent workflow manager - initial implementation

Rust (Axum) + Vue 3 + SQLite. Features:
- Project CRUD REST API with proper error handling
- Per-project agent loop (mpsc + broadcast channels)
- LLM-driven plan generation and replan on user feedback
- SSH command execution with status streaming
- WebSocket real-time updates to frontend
- Four-zone UI: requirement, plan (left), execution (right), comment

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

src/llm.rs

@@ -0,0 +1,56 @@
+use serde::{Deserialize, Serialize};
+use crate::LlmConfig;
+
+pub struct LlmClient {
+    client: reqwest::Client,
+    config: LlmConfig,
+}
+
+#[derive(Debug, Serialize)]
+struct ChatRequest {
+    model: String,
+    messages: Vec<ChatMessage>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ChatMessage {
+    pub role: String,
+    pub content: String,
+}
+
+#[derive(Debug, Deserialize)]
+struct ChatResponse {
+    choices: Vec<Choice>,
+}
+
+#[derive(Debug, Deserialize)]
+struct Choice {
+    message: ChatMessage,
+}
+
+impl LlmClient {
+    pub fn new(config: &LlmConfig) -> Self {
+        Self {
+            client: reqwest::Client::new(),
+            config: config.clone(),
+        }
+    }
+
+    pub async fn chat(&self, messages: Vec<ChatMessage>) -> anyhow::Result<String> {
+        let resp = self.client
+            .post(format!("{}/chat/completions", self.config.base_url))
+            .header("Authorization", format!("Bearer {}", self.config.api_key))
+            .json(&ChatRequest {
+                model: self.config.model.clone(),
+                messages,
+            })
+            .send()
+            .await?
+            .json::<ChatResponse>()
+            .await?;
+
+        Ok(resp.choices.first()
+            .map(|c| c.message.content.clone())
+            .unwrap_or_default())
+    }
+}