tiandytdd

README.md

@@ -28,6 +28,11 @@
 这是当前型号的控制方式，不是标定程序预先排了多个扫描点，也不能单凭这个现象判定电机故障。
 标定时应等待程序自己完成到位回读，不要同时在Web端控制云台。
 
+`interactive.sh`启动时会先执行`docker exec smart-cam smart-camctl control pause`，
+同时停止扫图、巡航和自动追踪对云台的新控制。向导正常完成、发生错误或用户
+按`Ctrl+C`退出时，Shell的`EXIT` trap都会执行`smart-camctl control resume`，
+恢复巡航和自动追踪。
+
 ## 目录结构
 
 ```text
@@ -295,8 +300,8 @@ zoom
 2. 只更新`scan`中的七个运动参数，保留定时时间、等待时间、容差和HTTP设置；
 3. 用`python3 -m json.tool`验证新JSON；
 4. 原子替换配置，不另外备份原配置；
-5. 执行`docker restart smart-cam`；
-6. 等待scan HTTP服务重新可用。
+5. 若宿主机存在`smart-cam.service`，通过systemd重启，避免systemd与`docker restart`同时管理容器；否则执行`docker restart smart-cam`；
+6. 等待scan HTTP服务连续稳定15秒后再进入试扫。
 
 回复`3`不会替换配置。
 

interactive.sh

@@ -2,4 +2,48 @@
 set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 export PYTHONDONTWRITEBYTECODE=1
-exec python3 "$SCRIPT_DIR/interactive_calibrator.py"
+
+control_paused=false
+wait_for_smart_cam() {
+    local deadline=$((SECONDS + 180))
+    local stable_checks=0
+    while (( SECONDS < deadline )); do
+        if docker inspect -f '{{.State.Running}}' smart-cam 2>/dev/null | grep -qx true \
+           && docker exec smart-cam curl -fsS --max-time 5 -o /dev/null \
+                http://127.0.0.1:18080/health 2>/dev/null; then
+            stable_checks=$((stable_checks + 1))
+            if (( stable_checks >= 8 )); then
+                return 0
+            fi
+        else
+            stable_checks=0
+        fi
+        sleep 2
+    done
+    return 1
+}
+
+resume_control() {
+    local exit_code=$?
+    trap - EXIT
+    if [[ "$control_paused" == true ]]; then
+        printf '\n正在恢复smart-cam巡航和自动追踪……\n'
+        if ! wait_for_smart_cam \
+           || ! docker exec smart-cam smart-camctl control resume; then
+            printf '错误：标定已结束，但自动恢复失败。请立即手动执行：\n' >&2
+            printf '  docker exec smart-cam smart-camctl control resume\n' >&2
+            exit_code=1
+        fi
+    fi
+    exit "$exit_code"
+}
+trap resume_control EXIT
+
+printf '正在暂停smart-cam的扫图、巡航和自动追踪，准备独占云台……\n'
+if ! docker exec smart-cam smart-camctl control pause; then
+    printf '错误：无法暂停smart-cam自动控制，本次不启动标定。\n' >&2
+    exit 1
+fi
+control_paused=true
+
+python3 "$SCRIPT_DIR/interactive_calibrator.py"

interactive_calibrator.py

@@ -10,6 +10,7 @@ from datetime import datetime
 import io
 import json
 import math
+import os
 from pathlib import Path
 import re
 import select
@@ -906,16 +907,33 @@ def deploy_config(scan: dict) -> None:
     finally:
         local_temp.unlink(missing_ok=True)
 
-    subprocess.run(["docker", "restart", "smart-cam"], check=True,
-                   stdout=subprocess.DEVNULL)
-    deadline = time.monotonic() + 90
-    while time.monotonic() < deadline:
-        try:
-            core.api("GET", "/api/v1/scan/status", timeout=5)
-            return
-        except (SystemExit, subprocess.SubprocessError):
-            time.sleep(2)
-    raise RuntimeError("smart-cam重启后90秒内scan HTTP服务未就绪")
+    unit = subprocess.run(
+        ["systemctl", "show", "-p", "LoadState", "--value", "smart-cam.service"],
+        text=True, capture_output=True,
+    )
+    if unit.returncode == 0 and unit.stdout.strip() == "loaded":
+        restart = ["systemctl", "restart", "smart-cam.service"]
+        if os.geteuid() != 0:
+            restart = ["sudo", "-n", *restart]
+        result = subprocess.run(restart, text=True, capture_output=True)
+        if result.returncode:
+            detail = result.stderr.strip() or result.stdout.strip()
+            raise RuntimeError(
+                "宿主机由smart-cam.service管理容器，但无法通过systemd重启。"
+                "请使用root执行本向导，或为systemctl restart smart-cam.service配置sudo权限。"
+                f"\n{detail}"
+            )
+    else:
+        subprocess.run(
+            ["docker", "restart", "smart-cam"], check=True,
+            stdout=subprocess.DEVNULL,
+        )
+
+    if not core.wait_for_scan_http_stable(timeout=180, stable_seconds=15):
+        raise RuntimeError(
+            "smart-cam重启后未能连续稳定运行15秒。请执行 "
+            "systemctl status smart-cam.service 和 docker logs --tail 100 smart-cam 查因。"
+        )
 
 
 def run_test_scan() -> dict:
@@ -1068,9 +1086,11 @@ def acquire_calibration_control() -> bool:
         say("已临时暂停巡航；标定结束或正常中断时会自动恢复。", color=YELLOW)
 
     try:
-        # This is a synchronization barrier: GET waits behind any PTZ command
-        # already in flight when patrol was paused, then claims manual control.
-        core.get_ptz()
+        # This synchronization barrier waits behind the one PTZ command that
+        # was already in flight when patrol was paused. Tiandy emulated
+        # absolute moves can legitimately take up to 135 seconds.
+        say("正在等待已暂停巡航的最后一条PTZ指令结束……")
+        core.get_ptz(timeout=160)
     except BaseException:
         if should_resume:
             try:

scan_calibrator.py

@@ -58,7 +58,7 @@ def transient_api_failure(result: subprocess.CompletedProcess[str]) -> bool:
     if result.returncode in TRANSIENT_CURL_EXIT_CODES:
         return True
     detail = f"{result.stdout}\n{result.stderr}".lower()
-    return any(marker in detail for marker in (
+    return bool(re.search(r"container(?:\s+[0-9a-f]+)?\s+is not running", detail)) or any(marker in detail for marker in (
         "container is not running",
         "container is restarting",
         "no such container",
@@ -138,6 +138,25 @@ def wait_for_scan_http(timeout: float = API_RECOVERY_TIMEOUT) -> bool:
     return False
 
 
+def wait_for_scan_http_stable(
+    timeout: float = 180.0, stable_seconds: float = 15.0
+) -> bool:
+    """Wait until scan HTTP stays healthy across the systemd restart window."""
+    deadline = time.monotonic() + timeout
+    ready_since: float | None = None
+    while time.monotonic() < deadline:
+        now = time.monotonic()
+        if scan_http_ready():
+            if ready_since is None:
+                ready_since = now
+            elif now - ready_since >= stable_seconds:
+                return True
+        else:
+            ready_since = None
+        time.sleep(API_RECOVERY_POLL_INTERVAL)
+    return False
+
+
 def api(method: str, path: str, body: dict | None = None, timeout: int = 60) -> dict:
     global _HELPER_READY
     command = api_command(method, path, body, timeout)
@@ -218,8 +237,10 @@ def parse_ptz_payload(payload: dict) -> dict[str, int]:
     return result
 
 
-def get_ptz() -> dict[str, int]:
-    payload = api("GET", "/api/v1/ptz?source=scan_calibrator", timeout=50)
+def get_ptz(timeout: int = 50) -> dict[str, int]:
+    payload = api(
+        "GET", "/api/v1/ptz?source=scan_calibrator", timeout=timeout
+    )
     return parse_ptz_payload(payload)
 
 

tests/test_scan_calibrator.py

@@ -51,6 +51,18 @@ class ApiRecoveryTests(unittest.TestCase):
         self.assertEqual(payload["scan"]["state"], "idle")
         wait_mock.assert_called_once_with()
 
+    def test_container_id_not_running_is_transient(self):
+        result = completed(
+            1,
+            stderr=(
+                "Error response from daemon: container "
+                "181a3df5ec75c1ed7183528c758078fee72b5f23505e18dd25b46789a01efac2 "
+                "is not running"
+            ),
+        )
+
+        self.assertTrue(core.transient_api_failure(result))
+
     def test_move_not_reached_error_is_explained_for_operator(self):
         result = completed(
             22,
@@ -230,7 +242,7 @@ class InteractiveWizardTests(unittest.TestCase):
             "POST", "/api/v1/patrol/stop",
             {"source": "scan_calibrator"}, timeout=15,
         )
-        get_ptz_mock.assert_called_once_with()
+        get_ptz_mock.assert_called_once_with(timeout=160)
 
     def test_manual_ptz_accepts_annotated_display_format(self):
         self.assertEqual(