fix: normalize claude system events and refresh tests

server/packages/agent-management/src/agents.rs

@@ -112,11 +112,13 @@ impl AgentManager {
 
     pub fn install(&self, agent: AgentId, options: InstallOptions) -> Result<InstallResult, AgentError> {
         let install_path = self.binary_path(agent);
-        if install_path.exists() && !options.reinstall {
-            return Ok(InstallResult {
-                path: install_path,
-                version: self.version(agent).unwrap_or(None),
-            });
+        if !options.reinstall {
+            if let Ok(existing_path) = self.resolve_binary(agent) {
+                return Ok(InstallResult {
+                    path: existing_path,
+                    version: self.version(agent).unwrap_or(None),
+                });
+            }
         }
 
         fs::create_dir_all(&self.install_dir)?;
@@ -135,7 +137,9 @@ impl AgentManager {
     }
 
     pub fn is_installed(&self, agent: AgentId) -> bool {
-        self.binary_path(agent).exists() || find_in_path(agent.binary_name()).is_some()
+        self.binary_path(agent).exists()
+            || find_in_path(agent.binary_name()).is_some()
+            || default_install_dir().join(agent.binary_name()).exists()
     }
 
     pub fn binary_path(&self, agent: AgentId) -> PathBuf {
@@ -368,6 +372,10 @@ impl AgentManager {
         if let Some(path) = find_in_path(agent.binary_name()) {
             return Ok(path);
         }
+        let fallback = default_install_dir().join(agent.binary_name());
+        if fallback.exists() {
+            return Ok(fallback);
+        }
         Err(AgentError::BinaryNotFound { agent })
     }
 }
@@ -780,6 +788,12 @@ fn find_in_path(binary_name: &str) -> Option<PathBuf> {
     None
 }
 
+fn default_install_dir() -> PathBuf {
+    dirs::data_dir()
+        .map(|dir| dir.join("sandbox-agent").join("bin"))
+        .unwrap_or_else(|| PathBuf::from(".").join(".sandbox-agent").join("bin"))
+}
+
 fn download_bytes(url: &Url) -> Result<Vec<u8>, AgentError> {
     let client = Client::builder().build()?;
     let mut response = client.get(url.clone()).send()?;

server/packages/sandbox-agent/tests/http_sse_snapshots.rs

@@ -19,7 +19,7 @@ use tower_http::cors::CorsLayer;
 const PROMPT: &str = "Reply with exactly the single word OK.";
 const PERMISSION_PROMPT: &str = "List files in the current directory using available tools.";
 const QUESTION_PROMPT: &str =
-    "Ask the user a multiple-choice question with options yes/no using any built-in AskUserQuestion tool, then wait.";
+    "Use the AskUserQuestion tool to ask exactly one yes/no question, then wait for a reply. Do not answer yourself.";
 
 struct TestApp {
     app: Router,
@@ -1022,7 +1022,7 @@ async fn approval_flow_snapshots() {
         }
 
         let question_reply_session = format!("question-reply-{}", config.agent.as_str());
-        create_session(&app.app, config.agent, &question_reply_session, test_permission_mode(config.agent)).await;
+        create_session(&app.app, config.agent, &question_reply_session, "plan").await;
         let status = send_status(
             &app.app,
             Method::POST,
@@ -1083,7 +1083,7 @@ async fn approval_flow_snapshots() {
         }
 
         let question_reject_session = format!("question-reject-{}", config.agent.as_str());
-        create_session(&app.app, config.agent, &question_reject_session, test_permission_mode(config.agent)).await;
+        create_session(&app.app, config.agent, &question_reject_session, "plan").await;
         let status = send_status(
             &app.app,
             Method::POST,

server/packages/sandbox-agent/tests/snapshots/http_sse_snapshots__approval_flow_snapshots@permission_events_claude.snap

@@ -1,6 +1,5 @@
 ---
 source: server/packages/sandbox-agent/tests/http_sse_snapshots.rs
-assertion_line: 978
 expression: normalize_events(&permission_events)
 ---
 - agent: claude
@@ -9,8 +8,10 @@ expression: normalize_events(&permission_events)
   started:
     message: session.created
 - agent: claude
-  kind: unknown
+  kind: started
   seq: 2
+  started:
+    message: system.init
 - agent: claude
   kind: message
   message:

server/packages/sandbox-agent/tests/snapshots/http_sse_snapshots__approval_flow_snapshots@question_reject_events_claude.snap

@@ -1,6 +1,5 @@
 ---
 source: server/packages/sandbox-agent/tests/http_sse_snapshots.rs
-assertion_line: 1100
 expression: normalize_events(&reject_events)
 ---
 - agent: claude
@@ -9,8 +8,10 @@ expression: normalize_events(&reject_events)
   started:
     message: session.created
 - agent: claude
-  kind: unknown
+  kind: started
   seq: 2
+  started:
+    message: system.init
 - agent: claude
   kind: message
   message:

server/packages/sandbox-agent/tests/snapshots/http_sse_snapshots__approval_flow_snapshots@question_reply_events_claude.snap

@@ -8,8 +8,10 @@ expression: normalize_events(&question_events)
   started:
     message: session.created
 - agent: claude
-  kind: unknown
+  kind: started
   seq: 2
+  started:
+    message: system.init
 - agent: claude
   kind: message
   message:

server/packages/sandbox-agent/tests/snapshots/http_sse_snapshots__run_concurrency_snapshot@concurrency_events_claude.snap

@@ -1,6 +1,5 @@
 ---
 source: server/packages/sandbox-agent/tests/http_sse_snapshots.rs
-assertion_line: 1232
 expression: snapshot
 ---
 session_a:
@@ -10,8 +9,10 @@ session_a:
     started:
       message: session.created
   - agent: claude
-    kind: unknown
+    kind: started
     seq: 2
+    started:
+      message: system.init
   - agent: claude
     kind: message
     message:
@@ -27,8 +28,10 @@ session_b:
     started:
       message: session.created
   - agent: claude
-    kind: unknown
+    kind: started
     seq: 2
+    started:
+      message: system.init
   - agent: claude
     kind: message
     message:

server/packages/sandbox-agent/tests/snapshots/http_sse_snapshots__run_http_events_snapshot@http_events_claude.snap

@@ -1,6 +1,5 @@
 ---
 source: server/packages/sandbox-agent/tests/http_sse_snapshots.rs
-assertion_line: 721
 expression: normalized
 ---
 - agent: claude
@@ -9,8 +8,10 @@ expression: normalized
   started:
     message: session.created
 - agent: claude
-  kind: unknown
+  kind: started
   seq: 2
+  started:
+    message: system.init
 - agent: claude
   kind: message
   message:

server/packages/sandbox-agent/tests/snapshots/http_sse_snapshots__run_sse_events_snapshot@sse_events_claude.snap

@@ -1,6 +1,5 @@
 ---
 source: server/packages/sandbox-agent/tests/http_sse_snapshots.rs
-assertion_line: 729
 expression: normalized
 ---
 - agent: claude
@@ -9,8 +8,10 @@ expression: normalized
   started:
     message: session.created
 - agent: claude
-  kind: unknown
+  kind: started
   seq: 2
+  started:
+    message: system.init
 - agent: claude
   kind: message
   message:

server/packages/universal-agent-schema/src/agents/claude.rs

@@ -7,6 +7,7 @@ use crate::{
     QuestionInfo,
     QuestionOption,
     QuestionRequest,
+    Started,
     UniversalEventData,
     UniversalMessage,
     UniversalMessageParsed,
@@ -20,6 +21,7 @@ pub fn event_to_universal_with_session(
 ) -> EventConversion {
     let event_type = event.get("type").and_then(Value::as_str).unwrap_or("");
     match event_type {
+        "system" => system_event_to_universal(event),
         "assistant" => assistant_event_to_universal(event),
         "tool_use" => tool_use_event_to_universal(event, session_id),
         "tool_result" => tool_result_event_to_universal(event),
@@ -114,6 +116,18 @@ fn assistant_event_to_universal(event: &Value) -> EventConversion {
     EventConversion::new(UniversalEventData::Message { message })
 }
 
+fn system_event_to_universal(event: &Value) -> EventConversion {
+    let subtype = event
+        .get("subtype")
+        .and_then(Value::as_str)
+        .unwrap_or("system");
+    let started = Started {
+        message: Some(format!("system.{subtype}")),
+        details: Some(event.clone()),
+    };
+    EventConversion::new(UniversalEventData::Started { started })
+}
+
 fn tool_use_event_to_universal(event: &Value, session_id: String) -> EventConversion {
     let tool_use = event.get("tool_use");
     let name = tool_use