feat(gemini-web): squash all features and fixes for gemini-web

config.example.yaml

@@ -65,3 +65,23 @@ openai-compatibility:
     models: # The models supported by the provider.
       - name: "moonshotai/kimi-k2:free" # The actual model name.
         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