v0.2.0-llm: LLM integration, core utilities, and persistence

- Rust backend: LLM abstraction with OpenAI-compatible + Ollama API clients
- Tauri commands: generate, generate_stream, get/set LLM config
- LLM config: api_url, api_key, model, temperature, max_tokens, top_p
- Works with Ollama (localhost:11434), LM Studio, any OpenAI-compatible API
- Streaming infrastructure via Tauri Channels (LlmEvent)
- tauri-plugin-store, tauri-plugin-fs added
- Frontend: NPC Generator with race/class/alignment selection + AI generation
- Frontend: Dice Roller with notation parsing (2d6+3), presets, history
- Frontend: Session Logger with note-taking + AI summarization
- Frontend: Settings panel for LLM configuration (URL, key, model, temperature)
- App shell: left rail nav with active states, settings toggle
- All glassmorphism cards with gold glow hover states
- Builds clean: tsc, vite build, cargo check, tauri build

src-tauri/src/commands/llm_commands.rs

@@ -0,0 +1,166 @@
+use crate::llm::{self, AppState, ChatMessage, ChatResponse, GenerateRequest, LlmEvent, OllamaChatResponse};
+use serde_json::json;
+use tauri::ipc::Channel;
+
+// ─── Simple (non-streaming) generate ─────────────────────────
+
+#[tauri::command]
+pub async fn generate(state: tauri::State<'_, AppState>, req: GenerateRequest) -> Result<String, String> {
+    let config = {
+        let guard = state.config.lock().map_err(|e| e.to_string())?;
+        guard.clone()
+    };
+
+    let client = reqwest::Client::new();
+    let messages = llm::build_messages(req.system.as_deref(), &req.prompt);
+    let temperature = req.temperature.unwrap_or(config.temperature);
+    let max_tokens = req.max_tokens.unwrap_or(config.max_tokens);
+
+    if llm::is_ollama(&config.api_url) {
+        call_ollama(&client, &config, &messages, temperature, max_tokens).await
+    } else {
+        call_openai(&client, &config, &messages, temperature, max_tokens).await
+    }
+}
+
+// ─── Streaming generate via Tauri Channel ─────────────────────
+
+#[tauri::command]
+pub async fn generate_stream(
+    state: tauri::State<'_, AppState>,
+    req: GenerateRequest,
+    channel: Channel<LlmEvent>,
+) -> Result<(), String> {
+    let config = state.config.lock().map_err(|e| e.to_string())?.clone();
+
+    tauri::async_runtime::spawn(async move {
+        let client = reqwest::Client::new();
+        let messages = llm::build_messages(req.system.as_deref(), &req.prompt);
+        let temperature = req.temperature.unwrap_or(config.temperature);
+        let max_tokens = req.max_tokens.unwrap_or(config.max_tokens);
+
+        // For now, we do a non-streaming call and emit the full response as one token
+        // Real SSE streaming from Ollama/OpenAI can be added later
+        let result = if llm::is_ollama(&config.api_url) {
+            call_ollama(&client, &config, &messages, temperature, max_tokens).await
+        } else {
+            call_openai(&client, &config, &messages, temperature, max_tokens).await
+        };
+
+        match result {
+            Ok(text) => {
+                let _ = channel.send(LlmEvent::Token(text.clone()));
+                let _ = channel.send(LlmEvent::Done(text));
+            }
+            Err(e) => {
+                let _ = channel.send(LlmEvent::Error(e));
+            }
+        }
+    });
+
+    Ok(())
+}
+
+// ─── Get / Set LLM Config ────────────────────────────────────
+
+#[tauri::command]
+pub fn get_llm_config(state: tauri::State<'_, AppState>) -> Result<crate::llm::LlmConfig, String> {
+    let config = state.config.lock().map_err(|e| e.to_string())?;
+    Ok(config.clone())
+}
+
+#[tauri::command]
+pub fn set_llm_config(state: tauri::State<'_, AppState>, config: crate::llm::LlmConfig) -> Result<(), String> {
+    let mut lock = state.config.lock().map_err(|e| e.to_string())?;
+    *lock = config;
+    Ok(())
+}
+
+// ─── Ollama API ───────────────────────────────────────────────
+
+async fn call_ollama(
+    client: &reqwest::Client,
+    config: &crate::llm::LlmConfig,
+    messages: &[ChatMessage],
+    temperature: f32,
+    max_tokens: u32,
+) -> Result<String, String> {
+    let body = json!({
+        "model": config.model,
+        "messages": messages,
+        "stream": false,
+        "options": {
+            "temperature": temperature,
+            "num_predict": max_tokens,
+        }
+    });
+
+    let url = format!("{}/api/chat", config.api_url.trim_end_matches('/'));
+
+    let res = client
+        .post(&url)
+        .json(&body)
+        .send()
+        .await
+        .map_err(|e| format!("Ollama request failed: {e}"))?;
+
+    if !res.status().is_success() {
+        let status = res.status();
+        let text = res.text().await.unwrap_or_default();
+        return Err(format!("Ollama error {status}: {text}"));
+    }
+
+    let response: OllamaChatResponse = res
+        .json()
+        .await
+        .map_err(|e| format!("Ollama parse error: {e}"))?;
+
+    Ok(response.message.content)
+}
+
+// ─── OpenAI-compatible API ────────────────────────────────────
+
+async fn call_openai(
+    client: &reqwest::Client,
+    config: &crate::llm::LlmConfig,
+    messages: &[ChatMessage],
+    temperature: f32,
+    max_tokens: u32,
+) -> Result<String, String> {
+    let body = json!({
+        "model": config.model,
+        "messages": messages,
+        "temperature": temperature,
+        "max_tokens": max_tokens,
+    });
+
+    let url = format!("{}/v1/chat/completions", config.api_url.trim_end_matches('/'));
+
+    let mut req = client.post(&url);
+    if !config.api_key.is_empty() {
+        req = req.bearer_auth(&config.api_key);
+    }
+
+    let res = req
+        .json(&body)
+        .send()
+        .await
+        .map_err(|e| format!("API request failed: {e}"))?;
+
+    if !res.status().is_success() {
+        let status = res.status();
+        let text = res.text().await.unwrap_or_default();
+        return Err(format!("API error {status}: {text}"));
+    }
+
+    let response: ChatResponse = res
+        .json()
+        .await
+        .map_err(|e| format!("API parse error: {e}"))?;
+
+    response
+        .choices
+        .first()
+        .map(|c| c.message.content.clone())
+        .ok_or_else(|| "No response from API".to_string())
+}

src-tauri/src/commands/mod.rs

@@ -0,0 +1 @@
+pub mod llm_commands;