fix: enterprise-grade reliability — three changes

1. CI: restart system container instead of just systemctl restart botserver
   — ensures full env reload, Vault re-auth, DriveMonitor fresh state

2. Health endpoint: add 'commit' field with short git SHA
   — build.rs passes BOTSERVER_COMMIT from CI via rustc-env
   - Both /health and /api/health now report the running commit

3. WebSocket recv_task: spawn stream_response in separate tokio task
   - prevents one hung LLM from freezing all message processing
   - each WebSocket connection can now handle multiple messages
     concurrently regardless of LLM latency

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

.forgejo/workflows/botserver.yaml

@@ -84,8 +84,11 @@ jobs:
         run: |
           sccache --start-server 2>/dev/null || true
           BOTSERVER_BUILD_DATE="$(date -u '+%Y-%m-%dT%H:%M:%SZ')"
+          BOTSERVER_COMMIT="$(git -C /opt/gbo/data/botserver rev-parse --short HEAD)"
           export BOTSERVER_BUILD_DATE
+          export BOTSERVER_COMMIT
           echo "Build date: $BOTSERVER_BUILD_DATE"
+          echo "Commit: $BOTSERVER_COMMIT"
           cargo build -p botserver  -j 8 2>&1 | tee /tmp/build.log
           sccache --show-stats
           ls -lh target/debug/botserver
@@ -103,12 +106,12 @@ jobs:
           ls -lh /opt/gbo/data/botserver/target/debug/botserver
           echo "Step 2: Backing up old binary..."
           ssh $SSH_ARGS system "cp /opt/gbo/bin/botserver /tmp/botserver.bak"
-          echo "Step 3: Stopping botserver service..."
-          ssh $SSH_ARGS system "sudo systemctl stop botserver || true"
-          echo "Step 4: Transferring new binary..."
+          echo "Step 3: Transferring new binary..."
           tar cf - -C /opt/gbo/data/botserver/target/debug botserver | gzip -1 | ssh $SSH_ARGS system "gzip -d | tar xf - -C /opt/gbo/bin && chmod +x /opt/gbo/bin/botserver && chown gbuser:gbuser /opt/gbo/bin/botserver && echo 'Transfer complete'"
-          echo "Step 5: Starting botserver service..."
-          ssh $SSH_ARGS system "sudo systemctl start botserver && echo 'Botserver started'"
+          echo "Step 4: Restarting system container..."
+          ssh $SSH_ARGS system "sudo systemctl restart system" || ssh $SSH_ARGS system "sudo reboot"
+          echo "Step 5: Waiting for botserver to come back..."
+          ssh $SSH_ARGS system "for i in \$(seq 1 60); do pgrep -f botserver >/dev/null 2>&1 && curl -sf http://localhost:5858/health >/dev/null 2>&1 && break; sleep 2; done"
           echo "=== Deploy completed ==="
 
       - name: Verify botserver started

build.rs

@@ -4,4 +4,12 @@ fn main() {
     }
     println!("cargo:rerun-if-changed=3rdparty.toml");
     println!("cargo:rerun-if-changed=.env.embedded");
+
+    // Pass build metadata to the binary via option_env!
+    if let Ok(date) = std::env::var("BOTSERVER_BUILD_DATE") {
+        println!("cargo:rustc-env=BOTSERVER_BUILD_DATE={}", date);
+    }
+    if let Ok(commit) = std::env::var("BOTSERVER_COMMIT") {
+        println!("cargo:rustc-env=BOTSERVER_COMMIT={}", commit);
+    }
 }

src/main_module/health.rs

@@ -17,8 +17,8 @@ pub async fn health_check(State(state): State<Arc<AppState>>) -> (StatusCode, Js
         StatusCode::SERVICE_UNAVAILABLE
     };
 
-    // Build timestamp set by CI via BOTSERVER_BUILD_DATE env var
     let build_date = option_env!("BOTSERVER_BUILD_DATE").unwrap_or("unknown");
+    let commit = option_env!("BOTSERVER_COMMIT").unwrap_or("unknown");
 
     (
         code,
@@ -27,18 +27,21 @@ pub async fn health_check(State(state): State<Arc<AppState>>) -> (StatusCode, Js
             "service": "botserver",
             "version": env!("CARGO_PKG_VERSION"),
             "build_date": build_date,
+            "commit": commit,
             "database": db_ok
         })),
     )
 }
 
 pub async fn health_check_simple() -> (StatusCode, Json<serde_json::Value>) {
+    let commit = option_env!("BOTSERVER_COMMIT").unwrap_or("unknown");
     (
         StatusCode::OK,
         Json(serde_json::json!({
             "status": "ok",
             "service": "botserver",
-            "version": env!("CARGO_PKG_VERSION")
+            "version": env!("CARGO_PKG_VERSION"),
+            "commit": commit
         })),
     )
 }