feat: enhance API key normalization and improve Space OAuth callback handling

src/langbot/pkg/provider/modelmgr/requester.py

@@ -340,6 +340,7 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
     """Provider API请求器"""
 
     name: str = None
+    init_api_key: str = 'langbot-init-placeholder'
 
     ap: app.Application
 

src/langbot/pkg/provider/modelmgr/requesters/chatcmpl.py

@@ -17,7 +17,6 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
     """OpenAI ChatCompletion API 请求器"""
 
     client: openai.AsyncClient
-    init_api_key: str = 'langbot-init-placeholder'
 
     default_config: dict[str, typing.Any] = {
         'base_url': 'https://api.openai.com/v1',

src/langbot/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py

@@ -25,7 +25,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
 
     async def initialize(self):
         self.client = openai.AsyncClient(
-            api_key='',
+            api_key=self.init_api_key,
             base_url=self.requester_cfg['base_url'],
             timeout=self.requester_cfg['timeout'],
             http_client=httpx.AsyncClient(trust_env=True, timeout=self.requester_cfg['timeout']),

src/langbot/pkg/provider/modelmgr/token.py

@@ -14,7 +14,14 @@ class TokenManager:
 
     def __init__(self, name: str, tokens: list[str]):
         self.name = name
-        self.tokens = tokens
+        self.tokens = []
+        seen_tokens = set()
+        for token in tokens:
+            normalized_token = token.strip() if isinstance(token, str) else ''
+            if not normalized_token or normalized_token in seen_tokens:
+                continue
+            self.tokens.append(normalized_token)
+            seen_tokens.add(normalized_token)
         self.using_token_index = 0
 
     def get_token(self) -> str: