fix: use ACP protocol stopReason for proper agent completion detection

Replace unreliable 2-second timeout heuristic with proper protocol-based completion detection using PromptResponse.stopReason from ACP SDK.

Changes:
- Capture and handle PromptResponse.stopReason in sendPrompt()
- Set agent status based on stop reason: end_turn → completed, refusal → failed, cancelled → ready
- Remove 2-second timeout completion heuristic (was causing drift)
- Update SessionStateMessageSchema to match AgentInfo null types

This ensures agent completion is detected via the protocol spec, not manual polling/timing.

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

packages/voice-assistant/src/server/acp/agent-manager.ts

@@ -225,7 +225,7 @@ export class AgentManager {
     this.notifySubscribers(agentId);
 
     try {
-      await agent.connection.prompt({
+      const response = await agent.connection.prompt({
         sessionId: agent.sessionId!,
         prompt: [
           {
@@ -234,6 +234,23 @@ export class AgentManager {
           },
         ],
       });
+
+      // Handle completion based on stopReason from the protocol
+      console.log(`[Agent ${agentId}] Prompt completed with stopReason: ${response.stopReason}`);
+
+      if (response.stopReason === "end_turn") {
+        agent.status = "completed";
+      } else if (response.stopReason === "refusal") {
+        agent.status = "failed";
+        agent.error = "Agent refused to process the prompt";
+      } else if (response.stopReason === "cancelled") {
+        agent.status = "ready";
+      } else {
+        // max_tokens, max_turn_requests - still completed but may be truncated
+        agent.status = "completed";
+      }
+
+      this.notifyStatusChange(agentId);
     } catch (error) {
       this.handleAgentError(
         agentId,
@@ -435,29 +452,8 @@ export class AgentManager {
       console.log(`[Agent ${agentId}] Mode changed to: ${agent.currentModeId}`);
     }
 
-    // Track completion based on final message state
-    // ACP protocol indicates completion when the last agent_message_chunk arrives
-    // We detect this by tracking a completion timer that fires if no more updates arrive
-    const updateType = update.update.sessionUpdate;
-
-    // Clear and reset completion timer on any update during processing
-    if (agent.status === "processing") {
-      if ((agent as any).completionTimer) {
-        clearTimeout((agent as any).completionTimer);
-      }
-
-      // Set a new timer to mark as completed if no more updates arrive
-      // This is a heuristic - if no updates for 2 seconds, consider complete
-      (agent as any).completionTimer = setTimeout(() => {
-        if (agent.status === "processing") {
-          console.log(`[Agent ${agentId}] No more updates, marking as completed`);
-          agent.status = "completed";
-          this.notifyStatusChange(agentId);
-        }
-      }, 2000);
-    }
-
     // Log update for debugging
+    const updateType = update.update.sessionUpdate;
     console.log(
       `[Agent ${agentId}] Session update:`,
       updateType

packages/voice-assistant/src/server/messages.ts

@@ -166,14 +166,14 @@ export const SessionStateMessageSchema = z.object({
         status: z.string(),
         createdAt: z.date(),
         type: z.literal("claude"),
-        sessionId: z.string().optional(),
+        sessionId: z.string().nullable(),
-        error: z.string().optional(),
+        error: z.string().nullable(),
-        currentModeId: z.string().optional(),
+        currentModeId: z.string().nullable(),
         availableModes: z.array(z.object({
           id: z.string(),
           name: z.string(),
           description: z.string().nullable().optional(),
-        })).optional(),
+        })).nullable(),
       })
     ),
     commands: z.array(