fix: make llm provider async and add tool toggle

.living_spec/stories/04_ollama_model_detection.md

@@ -0,0 +1,17 @@
+# Story: Ollama Model Detection
+
+## User Story
+**As a** User
+**I want to** select my Ollama model from a dropdown list of installed models
+**So that** I don't have to manually type (and potentially mistype) the model names.
+
+## Acceptance Criteria
+*   [ ] Backend: Implement `get_ollama_models()` command.
+    *   [ ] Call `GET /api/tags` on the Ollama instance.
+    *   [ ] Parse the JSON response to extracting model names.
+*   [ ] Frontend: Replace the "Ollama Model" text input with a `<select>` dropdown.
+*   [ ] Frontend: Populate the dropdown on load.
+*   [ ] Frontend: Handle connection errors gracefully (if Ollama isn't running, show empty or error).
+
+## Out of Scope
+*   Downloading new models via the UI (pulling).

src-tauri/Cargo.lock

@@ -2056,6 +2056,7 @@ checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 name = "living-spec-standalone"
 version = "0.1.0"
 dependencies = [
+ "async-trait",
  "chrono",
  "ignore",
  "reqwest",

src-tauri/Cargo.toml

@@ -28,4 +28,5 @@ walkdir = "2.5.0"
 reqwest = { version = "0.12.28", features = ["json", "blocking"] }
 uuid = { version = "1.19.0", features = ["v4", "serde"] }
 chrono = { version = "0.4.42", features = ["serde"] }
+async-trait = "0.1.89"
 

src-tauri/src/commands/chat.rs

@@ -4,7 +4,7 @@ use crate::llm::types::{
     Message, ModelProvider, Role, ToolCall, ToolDefinition, ToolFunctionDefinition,
 };
 use crate::state::SessionState;
-use serde::{Deserialize, Serialize};
+use serde::Deserialize;
 use serde_json::json;
 use tauri::State;
 
@@ -13,6 +13,7 @@ pub struct ProviderConfig {
     pub provider: String, // "ollama"
     pub model: String,
     pub base_url: Option<String>,
+    pub enable_tools: Option<bool>,
 }
 
 const MAX_TURNS: usize = 10;
@@ -34,7 +35,12 @@ pub async fn chat(
     };
 
     // 2. Define Tools
-    let tools = get_tool_definitions();
+    let tool_defs = get_tool_definitions();
+    let tools = if config.enable_tools.unwrap_or(true) {
+        tool_defs.as_slice()
+    } else {
+        &[]
+    };
 
     // 3. Agent Loop
     let mut current_history = messages.clone();
@@ -49,7 +55,8 @@ pub async fn chat(
 
         // Call LLM
         let response = provider
-            .chat(&config.model, &current_history, &tools)
+            .chat(&config.model, &current_history, tools)
+            .await
             .map_err(|e| format!("LLM Error: {}", e))?;
 
         // Process Response

src-tauri/src/llm/ollama.rs

@@ -1,6 +1,7 @@
 use crate::llm::types::{
     CompletionResponse, FunctionCall, Message, ModelProvider, Role, ToolCall, ToolDefinition,
 };
+use async_trait::async_trait;
 use serde::{Deserialize, Serialize};
 use serde_json::Value;
 
@@ -76,14 +77,15 @@ struct OllamaResponseFunctionCall {
     arguments: Value, // Ollama returns Object, we convert to String for internal storage
 }
 
+#[async_trait]
 impl ModelProvider for OllamaProvider {
-    fn chat(
+    async fn chat(
         &self,
         model: &str,
         messages: &[Message],
         tools: &[ToolDefinition],
     ) -> Result<CompletionResponse, String> {
-        let client = reqwest::blocking::Client::new();
+        let client = reqwest::Client::new();
         let url = format!("{}/api/chat", self.base_url.trim_end_matches('/'));
 
         // Convert domain Messages to Ollama Messages (handling String -> Object args mismatch)
@@ -129,16 +131,18 @@ impl ModelProvider for OllamaProvider {
             .post(&url)
             .json(&request_body)
             .send()
+            .await
             .map_err(|e| format!("Request failed: {}", e))?;
 
         if !res.status().is_success() {
             let status = res.status();
-            let text = res.text().unwrap_or_default();
+            let text = res.text().await.unwrap_or_default();
             return Err(format!("Ollama API error {}: {}", status, text));
         }
 
         let response_body: OllamaResponse = res
             .json()
+            .await
             .map_err(|e| format!("Failed to parse response: {}", e))?;
 
         // Convert Response back to Domain types

src-tauri/src/llm/types.rs

@@ -1,3 +1,4 @@
+use async_trait::async_trait;
 use serde::{Deserialize, Serialize};
 use std::fmt::Debug;
 
@@ -62,8 +63,9 @@ pub struct CompletionResponse {
 }
 
 /// The abstraction for different LLM providers (Ollama, Anthropic, etc.)
+#[async_trait]
 pub trait ModelProvider: Send + Sync {
-    fn chat(
+    async fn chat(
         &self,
         model: &str,
         messages: &[Message],

src/components/Chat.tsx

@@ -8,6 +8,7 @@ export function Chat() {
   const [input, setInput] = useState("");
   const [loading, setLoading] = useState(false);
   const [model, setModel] = useState("llama3.1"); // Default local model
+  const [enableTools, setEnableTools] = useState(true);
   const messagesEndRef = useRef<HTMLDivElement>(null);
 
   const scrollToBottom = () => {
@@ -21,7 +22,7 @@ export function Chat() {
 
     const userMsg: Message = { role: "user", content: input };
     const newHistory = [...messages, userMsg];
-    
+
     setMessages(newHistory);
     setInput("");
     setLoading(true);
@@ -31,6 +32,7 @@ export function Chat() {
         provider: "ollama",
         model: model,
         base_url: "http://localhost:11434",
+        enable_tools: enableTools,
       };
 
       // Invoke backend chat command
@@ -53,71 +55,157 @@ export function Chat() {
   };
 
   return (
-    <div className="chat-container" style={{ display: "flex", flexDirection: "column", height: "100%", maxWidth: "800px", margin: "0 auto" }}>
+    <div
+      className="chat-container"
+      style={{
+        display: "flex",
+        flexDirection: "column",
+        height: "100%",
+        maxWidth: "800px",
+        margin: "0 auto",
+      }}
+    >
       {/* Settings Bar */}
-      <div style={{ padding: "10px", borderBottom: "1px solid #ddd", display: "flex", gap: "10px", alignItems: "center" }}>
+      <div
+        style={{
+          padding: "10px",
+          borderBottom: "1px solid #ddd",
+          display: "flex",
+          gap: "10px",
+          alignItems: "center",
+        }}
+      >
         <label>Ollama Model:</label>
-        <input 
+        <input
-          value={model} 
+          value={model}
-          onChange={(e) => setModel(e.target.value)} 
+          onChange={(e) => setModel(e.target.value)}
           placeholder="e.g. llama3, mistral"
           style={{ padding: "5px" }}
         />
+        <label
+          style={{
+            display: "flex",
+            alignItems: "center",
+            gap: "5px",
+            marginLeft: "10px",
+          }}
+        >
+          <input
+            type="checkbox"
+            checked={enableTools}
+            onChange={(e) => setEnableTools(e.target.checked)}
+          />
+          Enable Tools
+        </label>
       </div>
 
       {/* Messages Area */}
-      <div style={{ flex: 1, overflowY: "auto", padding: "20px", display: "flex", flexDirection: "column", gap: "15px" }}>
+      <div
+        style={{
+          flex: 1,
+          overflowY: "auto",
+          padding: "20px",
+          display: "flex",
+          flexDirection: "column",
+          gap: "15px",
+        }}
+      >
         {messages.map((msg, idx) => (
-          <div 
+          <div
-            key={idx} 
+            key={idx}
             className={`message ${msg.role}`}
             style={{
               alignSelf: msg.role === "user" ? "flex-end" : "flex-start",
               maxWidth: "80%",
               padding: "10px 15px",
               borderRadius: "10px",
-              background: msg.role === "user" ? "#007AFF" : msg.role === "tool" ? "#f0f0f0" : "#E5E5EA",
+              background:
+                msg.role === "user"
+                  ? "#007AFF"
+                  : msg.role === "tool"
+                    ? "#f0f0f0"
+                    : "#E5E5EA",
               color: msg.role === "user" ? "white" : "black",
               border: msg.role === "tool" ? "1px solid #ccc" : "none",
               fontFamily: msg.role === "tool" ? "monospace" : "inherit",
               fontSize: msg.role === "tool" ? "0.9em" : "1em",
-              whiteSpace: msg.role === "tool" ? "pre-wrap" : "normal"
+              whiteSpace: msg.role === "tool" ? "pre-wrap" : "normal",
             }}
           >
-            <strong>{msg.role === "user" ? "You" : msg.role === "tool" ? "Tool Output" : "Agent"}</strong>
+            <strong>
+              {msg.role === "user"
+                ? "You"
+                : msg.role === "tool"
+                  ? "Tool Output"
+                  : "Agent"}
+            </strong>
             {msg.role === "tool" ? (
-               <div style={{maxHeight: "200px", overflow: "auto"}}>{msg.content}</div>
+              <div style={{ maxHeight: "200px", overflow: "auto" }}>
+                {msg.content}
+              </div>
             ) : (
               <Markdown>{msg.content}</Markdown>
             )}
-            
+
             {/* Show Tool Calls if present */}
             {msg.tool_calls && (
-              <div style={{ marginTop: "10px", fontSize: "0.85em", color: "#666" }}>
+              <div
+                style={{ marginTop: "10px", fontSize: "0.85em", color: "#666" }}
+              >
                 {msg.tool_calls.map((tc, i) => (
-                  <div key={i} style={{ background: "rgba(0,0,0,0.05)", padding: "5px", borderRadius: "4px" }}>
+                  <div
-                    🛠 <code>{tc.function.name}({tc.function.arguments})</code>
+                    key={i}
+                    style={{
+                      background: "rgba(0,0,0,0.05)",
+                      padding: "5px",
+                      borderRadius: "4px",
+                    }}
+                  >
+                    🛠{" "}
+                    <code>
+                      {tc.function.name}({tc.function.arguments})
+                    </code>
                   </div>
                 ))}
               </div>
             )}
           </div>
         ))}
-        {loading && <div style={{ alignSelf: "flex-start", color: "#888" }}>Thinking...</div>}
+        {loading && (
+          <div style={{ alignSelf: "flex-start", color: "#888" }}>
+            Thinking...
+          </div>
+        )}
         <div ref={messagesEndRef} />
       </div>
 
       {/* Input Area */}
-      <div style={{ padding: "20px", borderTop: "1px solid #ddd", display: "flex", gap: "10px" }}>
+      <div
+        style={{
+          padding: "20px",
+          borderTop: "1px solid #ddd",
+          display: "flex",
+          gap: "10px",
+        }}
+      >
         <input
           value={input}
           onChange={(e) => setInput(e.target.value)}
           onKeyDown={(e) => e.key === "Enter" && sendMessage()}
           placeholder="Ask the agent to do something..."
-          style={{ flex: 1, padding: "10px", borderRadius: "4px", border: "1px solid #ccc" }}
+          style={{
+            flex: 1,
+            padding: "10px",
+            borderRadius: "4px",
+            border: "1px solid #ccc",
+          }}
           disabled={loading}
         />
-        <button onClick={sendMessage} disabled={loading} style={{ padding: "10px 20px" }}>
+        <button
+          onClick={sendMessage}
+          disabled={loading}
+          style={{ padding: "10px 20px" }}
+        >
           Send
         </button>
       </div>

src/types.ts

@@ -36,4 +36,5 @@ export interface ProviderConfig {
   provider: string;
   model: string;
   base_url?: string;
+  enable_tools?: boolean;
 }