Fix provider context limits and AWS authentication routing

2026-09-11 11:15:48 -05:00
parent 73d6839ee9
commit 5d2a0ea2de
8 changed files with 270 additions and 41 deletions
@@ -857,13 +857,19 @@ pub struct OpenAIModelConfig {
        default = "default_context_size",
        alias = "token_size",
        alias = "max_model_len",
-        alias = "context_window"
+        alias = "context_window",
+        alias = "max_context_window"
    )]
    #[schemars(description = "Maximum context window size in tokens.")]
    pub context_size: u32,
    #[serde(default, skip_serializing_if = "Option::is_none")]
    #[schemars(description = "Optional maximum input tokens supported by this model.")]
    pub max_input_tokens: Option<u32>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    #[schemars(
+        description = "Optional default context budget, distinct from the hard input limit."
+    )]
+    pub default_context_size: Option<u32>,
    #[serde(
        default,
        alias = "output_token_limit",