fix: allow env overrides to create missing config keys (#2064)

Previously, environment variable overrides (e.g. SYSTEM__INSTANCE_ID)
were silently skipped if the target key didn't already exist in
data/config.yaml. This caused SaaS pods running older LangBot images
(whose config template lacked system.instance_id) to ignore the
SYSTEM__INSTANCE_ID env var, falling back to a random UUID that
didn't match the pod UUID — breaking idle timeout tracking.

Now env overrides create missing keys (as strings) and missing
intermediate dicts, so they work regardless of template version.

Co-authored-by: rocksclawbot <rocksclawbot@users.noreply.github.com>

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.9.2"
+version = "4.9.3"
 description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -64,7 +64,7 @@ dependencies = [
     "chromadb>=1.0.0,<2.0.0",
     "qdrant-client (>=1.15.1,<2.0.0)",
     "pyseekdb==1.1.0.post3",
-    "langbot-plugin==0.3.1",
+    "langbot-plugin==0.3.2",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
     "tboxsdk>=0.0.10",

src/langbot/__init__.py

@@ -1,3 +1,3 @@
 """LangBot - Production-grade platform for building agentic IM bots"""
 
-__version__ = '4.9.2'
+__version__ = '4.9.3'

src/langbot/pkg/core/stages/load_config.py

@@ -74,20 +74,26 @@ def _apply_env_overrides_to_config(cfg: dict) -> dict:
         current = cfg
 
         for i, key in enumerate(keys):
-            if not isinstance(current, dict) or key not in current:
+            if not isinstance(current, dict):
                 break
 
             if i == len(keys) - 1:
-                # At the final key - check if it's a scalar value
-                if isinstance(current[key], (dict, list)):
-                    # Skip dict and list types
-                    pass
+                # At the final key
+                if key in current:
+                    if isinstance(current[key], (dict, list)):
+                        # Skip dict and list types
+                        pass
+                    else:
+                        # Valid scalar value - convert and set it
+                        converted_value = convert_value(env_value, current[key])
+                        current[key] = converted_value
                 else:
-                    # Valid scalar value - convert and set it
-                    converted_value = convert_value(env_value, current[key])
-                    current[key] = converted_value
+                    # Key doesn't exist yet - create it as string
+                    current[key] = env_value
             else:
-                # Navigate deeper
+                # Navigate deeper - create intermediate dict if needed
+                if key not in current:
+                    current[key] = {}
                 current = current[key]
 
     return cfg
@@ -146,16 +152,50 @@ class LoadConfigStage(stage.BootingStage):
         await ap.instance_config.dump_config()
 
         # load or generate instance id
-        ap.instance_id = await config.load_json_config(
-            'data/labels/instance_id.json',
-            template_data={
-                'instance_id': f'instance_{str(uuid.uuid4())}',
-                'instance_create_ts': int(time.time()),
-            },
-            completion=False,
-        )
+        # Priority:
+        # 1. system.instance_id from config.yaml (can be set via SYSTEM__INSTANCE_ID env var)
+        # 2. data/labels/instance_id.json (if file exists)
+        # 3. Generate new and save to file
+        config_instance_id = ap.instance_config.data.get('system', {}).get('instance_id', '')
 
-        constants.instance_id = ap.instance_id.data['instance_id']
+        if config_instance_id:
+            # Use the instance_id from config.yaml
+            constants.instance_id = config_instance_id
+            # Still load/create the file for backward compat, but don't use its value
+            ap.instance_id = await config.load_json_config(
+                'data/labels/instance_id.json',
+                template_data={
+                    'instance_id': f'instance_{str(uuid.uuid4())}',
+                    'instance_create_ts': int(time.time()),
+                },
+                completion=False,
+            )
+        else:
+            # Try loading file-based instance id
+            instance_id_path = os.path.join('data', 'labels', 'instance_id.json')
+            if os.path.exists(instance_id_path):
+                # File exists, read it
+                ap.instance_id = await config.load_json_config(
+                    'data/labels/instance_id.json',
+                    template_data={
+                        'instance_id': '',
+                        'instance_create_ts': 0,
+                    },
+                    completion=False,
+                )
+                constants.instance_id = ap.instance_id.data['instance_id']
+            else:
+                # Neither config nor file, generate new and save to file
+                new_id = f'instance_{str(uuid.uuid4())}'
+                ap.instance_id = await config.load_json_config(
+                    'data/labels/instance_id.json',
+                    template_data={
+                        'instance_id': new_id,
+                        'instance_create_ts': int(time.time()),
+                    },
+                    completion=False,
+                )
+                constants.instance_id = new_id
         constants.edition = ap.instance_config.data.get('system', {}).get('edition', 'community')
 
         print(f'LangBot instance id: {constants.instance_id}')

src/langbot/pkg/pipeline/preproc/preproc.py

@@ -176,6 +176,16 @@ class PreProcessor(stage.PipelineStage):
         query.variables['user_message_text'] = plain_text
 
         query.user_message = provider_message.Message(role='user', content=content_list)
+
+        # Extract knowledge base UUIDs into query variables so plugins can modify them
+        # during PromptPreProcessing before the runner performs retrieval.
+        kb_uuids = query.pipeline_config['ai']['local-agent'].get('knowledge-bases', [])
+        if not kb_uuids:
+            old_kb_uuid = query.pipeline_config['ai']['local-agent'].get('knowledge-base', '')
+            if old_kb_uuid and old_kb_uuid != '__none__':
+                kb_uuids = [old_kb_uuid]
+        query.variables['_knowledge_base_uuids'] = list(kb_uuids)
+
         # =========== 触发事件 PromptPreProcessing
 
         event = events.PromptPreProcessing(

src/langbot/pkg/plugin/handler.py

@@ -675,11 +675,15 @@ class RuntimeConnectionHandler(handler.Handler):
                 )
 
             try:
+                session_name = f'{query.session.launcher_type.value}_{query.session.launcher_id}'
                 entries = await kb.retrieve(
                     query_text,
                     settings={
                         'top_k': top_k,
                         'filters': filters,
+                        'session_name': session_name,
+                        'bot_uuid': query.bot_uuid or '',
+                        'sender_id': str(query.sender_id),
                     },
                 )
                 results = [entry.model_dump(mode='json') for entry in entries]

src/langbot/pkg/provider/runners/localagent.py

@@ -132,14 +132,9 @@ class LocalAgentRunner(runner.RequestRunner):
         """Run request"""
         pending_tool_calls = []
 
-        # Get knowledge bases list (new field)
-        kb_uuids = query.pipeline_config['ai']['local-agent'].get('knowledge-bases', [])
-
-        # Fallback to old field for backward compatibility
-        if not kb_uuids:
-            old_kb_uuid = query.pipeline_config['ai']['local-agent'].get('knowledge-base', '')
-            if old_kb_uuid and old_kb_uuid != '__none__':
-                kb_uuids = [old_kb_uuid]
+        # Get knowledge bases list from query variables (set by PreProcessor,
+        # may have been modified by plugins during PromptPreProcessing)
+        kb_uuids = query.variables.get('_knowledge_base_uuids', [])
 
         user_message = copy.deepcopy(query.user_message)
 

src/langbot/templates/config.yaml

@@ -16,6 +16,7 @@ proxy:
     http: ''
     https: ''
 system:
+    instance_id: ''
     edition: community
     recovery_key: ''
     allow_modify_login_info: true

uv.lock

@@ -1832,7 +1832,7 @@ wheels = [
 
 [[package]]
 name = "langbot"
-version = "4.9.2"
+version = "4.9.3"
 source = { editable = "." }
 dependencies = [
     { name = "aiocqhttp" },
@@ -1937,7 +1937,7 @@ requires-dist = [
     { name = "ebooklib", specifier = ">=0.18" },
     { name = "gewechat-client", specifier = ">=0.1.5" },
     { name = "html2text", specifier = ">=2024.2.26" },
-    { name = "langbot-plugin", specifier = "==0.3.1" },
+    { name = "langbot-plugin", specifier = "==0.3.2" },
     { name = "langchain", specifier = ">=0.2.0" },
     { name = "langchain-text-splitters", specifier = ">=0.0.1" },
     { name = "lark-oapi", specifier = ">=1.4.15" },
@@ -1993,7 +1993,7 @@ dev = [
 
 [[package]]
 name = "langbot-plugin"
-version = "0.3.1"
+version = "0.3.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiofiles" },
@@ -2011,9 +2011,9 @@ dependencies = [
     { name = "watchdog" },
     { name = "websockets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/4e/ed/b440e26ebc40983abf00dd343338101ada3381065fb3347401ba75f873fe/langbot_plugin-0.3.1.tar.gz", hash = "sha256:0839dcb4cfe689fc670d0ded29b57e6a3f683d8f7326eaa771a5b753675459ac", size = 170285, upload-time = "2026-03-12T15:07:01.918Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/05/32/1b029961d718b5418d9d139687287193d4657914c467833176d9c060fb4c/langbot_plugin-0.3.2.tar.gz", hash = "sha256:2f7f16285600ec019a4e8cc8b40bc8f8d404e3bbc69c9d129620dc70b3bde2f8", size = 170431, upload-time = "2026-03-14T12:42:55.175Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/13/81/d3c4142911792838b90384a28f7dd1540d0862303293c53ba77e69fc0e15/langbot_plugin-0.3.1-py3-none-any.whl", hash = "sha256:8139796926fe8385b7b546ef865e29b1b8d8e28249e20f3b5417d42d3181ec62", size = 144813, upload-time = "2026-03-12T15:07:03.69Z" },
+    { url = "https://files.pythonhosted.org/packages/91/d7/a5dd6cff000a4f7fe88692689be276875b04485f48fc26e162f1ad2a341c/langbot_plugin-0.3.2-py3-none-any.whl", hash = "sha256:a1de527c4d651e6b6ba2458b6fac09a300e6b1ffdc5a25bbfad88d970cfd6cfd", size = 144906, upload-time = "2026-03-14T12:42:56.486Z" },
 ]
 
 [[package]]

web/src/app/login/page.tsx

@@ -23,7 +23,7 @@ import {
 import { useEffect, useState } from 'react';
 import { httpClient, initializeUserInfo } from '@/app/infra/http';
 import { useRouter } from 'next/navigation';
-import { Mail, Lock, Loader2 } from 'lucide-react';
+import { Mail, Lock, Loader2, AlertCircle, RefreshCw } from 'lucide-react';
 import langbotIcon from '@/app/assets/langbot-logo.webp';
 import { toast } from 'sonner';
 import { useTranslation } from 'react-i18next';
@@ -46,6 +46,8 @@ export default function Login() {
   const [accountType, setAccountType] = useState<AccountType | null>(null);
   const [hasPassword, setHasPassword] = useState(false);
   const [loading, setLoading] = useState(true);
+  const [loadError, setLoadError] = useState<string | null>(null);
+  const [retrying, setRetrying] = useState(false);
 
   const form = useForm<z.infer<ReturnType<typeof formSchema>>>({
     resolver: zodResolver(formSchema(t)),
@@ -61,6 +63,7 @@ export default function Login() {
 
   async function checkAccountInfo() {
     try {
+      setLoadError(null);
       const res = await httpClient.getAccountInfo();
       if (!res.initialized) {
         router.push('/register');
@@ -72,11 +75,22 @@ export default function Login() {
 
       // Also check if already logged in
       checkIfAlreadyLoggedIn();
-    } catch {
+    } catch (err) {
+      const errorMessage =
+        err instanceof Error ? err.message : t('common.loginLoadError');
+      setLoadError(errorMessage);
       setLoading(false);
     }
   }
 
+  async function handleRetry() {
+    setRetrying(true);
+    setLoading(true);
+    setLoadError(null);
+    await checkAccountInfo();
+    setRetrying(false);
+  }
+
   function checkIfAlreadyLoggedIn() {
     httpClient
       .checkUserToken()
@@ -129,6 +143,54 @@ export default function Login() {
     );
   }
 
+  // Show error state when account info failed to load
+  if (loadError) {
+    return (
+      <div className="min-h-screen flex items-center justify-center bg-gray-50 dark:bg-neutral-900">
+        <Card className="w-[375px] shadow-lg dark:shadow-white/10">
+          <CardHeader>
+            <div className="flex justify-between items-center mb-6">
+              <ThemeToggle />
+              <LanguageSelector />
+            </div>
+            <img
+              src={langbotIcon.src}
+              alt="LangBot"
+              className="w-16 h-16 mb-4 mx-auto"
+            />
+            <CardTitle className="text-2xl text-center">
+              {t('common.welcome')}
+            </CardTitle>
+          </CardHeader>
+          <CardContent className="space-y-4">
+            <div className="flex flex-col items-center gap-3 py-4">
+              <AlertCircle className="h-10 w-10 text-destructive" />
+              <p className="text-sm text-center text-muted-foreground">
+                {t('common.loginLoadErrorDesc')}
+              </p>
+              <code className="text-xs bg-muted px-3 py-2 rounded max-w-full overflow-x-auto block text-center text-muted-foreground">
+                {loadError}
+              </code>
+              <Button
+                onClick={handleRetry}
+                disabled={retrying}
+                variant="outline"
+                className="mt-2 cursor-pointer"
+              >
+                {retrying ? (
+                  <Loader2 className="mr-2 h-4 w-4 animate-spin" />
+                ) : (
+                  <RefreshCw className="mr-2 h-4 w-4" />
+                )}
+                {t('common.retry')}
+              </Button>
+            </div>
+          </CardContent>
+        </Card>
+      </div>
+    );
+  }
+
   // Determine what to show based on account type
   const showLocalLogin =
     accountType === 'local' || (accountType === 'space' && hasPassword);

web/src/i18n/locales/en-US.ts

@@ -11,6 +11,10 @@ const enUS = {
     continueToLogin: 'Login to continue',
     loginSuccess: 'Login successful',
     loginFailed: 'Login failed, please check your email and password',
+    loginLoadError: 'Unable to connect to server',
+    loginLoadErrorDesc:
+      'Unable to connect to the LangBot backend. Please make sure the service is running and try again.',
+    retry: 'Retry',
     enterEmail: 'Enter email address',
     enterPassword: 'Enter password',
     invalidEmail: 'Please enter a valid email address',

web/src/i18n/locales/ja-JP.ts

@@ -12,6 +12,10 @@
     loginSuccess: 'ログインに成功しました',
     loginFailed:
       'ログインに失敗しました。メールアドレスまたはパスワードをご確認ください',
+    loginLoadError: 'サーバーに接続できません',
+    loginLoadErrorDesc:
+      'LangBot バックエンドに接続できません。サービスが起動していることを確認してから再試行してください。',
+    retry: '再試行',
     enterEmail: 'メールアドレスを入力',
     enterPassword: 'パスワードを入力',
     invalidEmail: '有効なメールアドレスを入力してください',

web/src/i18n/locales/zh-Hans.ts

@@ -11,6 +11,9 @@ const zhHans = {
     continueToLogin: '登录以继续',
     loginSuccess: '登录成功',
     loginFailed: '登录失败，请检查邮箱和密码是否正确',
+    loginLoadError: '无法连接到服务器',
+    loginLoadErrorDesc: '无法连接到 LangBot 后端服务，请确认服务已启动后重试。',
+    retry: '重试',
     enterEmail: '输入邮箱地址',
     enterPassword: '输入密码',
     invalidEmail: '请输入有效的邮箱地址',

web/src/i18n/locales/zh-Hant.ts

@@ -11,6 +11,9 @@ const zhHant = {
     continueToLogin: '登入以繼續',
     loginSuccess: '登入成功',
     loginFailed: '登入失敗，請檢查電子郵件和密碼是否正確',
+    loginLoadError: '無法連線到伺服器',
+    loginLoadErrorDesc: '無法連線到 LangBot 後端服務，請確認服務已啟動後重試。',
+    retry: '重試',
     enterEmail: '輸入電子郵件地址',
     enterPassword: '輸入密碼',
     invalidEmail: '請輸入有效的電子郵件地址',