refactor(gemini-web): Remove auto-refresh, auto-close, and caching

This commit simplifies the Gemini web client by removing several complex, stateful features. The previous implementation for auto-refreshing cookies and auto-closing the client involved background goroutines, timers, and file system caching, which made the client's lifecycle difficult to manage.

The following features have been removed:
- The cookie auto-refresh mechanism, including the background goroutine (`rotateCookies`) and related configuration fields.
- The file-based caching for the `__Secure-1PSIDTS` token. The `rotate1PSIDTS` function now fetches a new token on every call.
- The auto-close functionality, which used timers to close the client after a period of inactivity.
- Associated configuration options and methods (`WithAccountLabel`, `WithOnCookiesRefreshed`, `Close`, etc.).

By removing this logic, the client becomes more stateless and predictable. The responsibility for managing the client's lifecycle and handling token expiration is now shifted to the caller, leading to a simpler and more robust integration.

config.example.yaml

@@ -71,21 +71,19 @@ openai-compatibility:
         alias: "kimi-k2" # The alias used in the API.
 
 # Gemini Web settings
-# gemini-web:
-#     # Conversation reuse: set to true to enable (default), false to disable.
-#     context: true
-#     # Maximum characters per single request to Gemini Web. Requests exceeding this
-#     # size split into chunks. Only the last chunk carries files and yields the final answer.
-#     max-chars-per-request: 1000000
-#     # Disable the short continuation hint appended to intermediate chunks
-#     # when splitting long prompts. Default is false (hint enabled by default).
-#     disable-continuation-hint: false
-#     # Background token auto-refresh interval seconds (defaults to 540 if unset or <= 0)
-#     token-refresh-seconds: 540
-#     # Code mode:
-#     #   - true: enable XML wrapping hint and attach the coding-partner Gem.
-#     #           Thought merging (<think> into visible content) applies to STREAMING only;
-#     #           non-stream responses keep reasoning/thought parts separate for clients
-#     #           that expect explicit reasoning fields.
-#     #   - false: disable XML hint and keep <think> separate
-#     code-mode: false
+gemini-web:
+    # Conversation reuse: set to true to enable (default), false to disable.
+    context: true
+    # Maximum characters per single request to Gemini Web. Requests exceeding this
+    # size split into chunks. Only the last chunk carries files and yields the final answer.
+    max-chars-per-request: 1000000
+    # Disable the short continuation hint appended to intermediate chunks
+    # when splitting long prompts. Default is false (hint enabled by default).
+    disable-continuation-hint: false
+    # Code mode:
+    #   - true: enable XML wrapping hint and attach the coding-partner Gem.
+    #           Thought merging (<think> into visible content) applies to STREAMING only;
+    #           non-stream responses keep reasoning/thought parts separate for clients
+    #           that expect explicit reasoning fields.
+    #   - false: disable XML hint and keep <think> separate
+    code-mode: false