public/galaxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix provider context limits and AWS authentication routing

Browse Source
This commit is contained in:
rkw6086
2026-09-11 11:15:48 -05:00
parent 73d6839ee9
commit 5d2a0ea2de
8 changed files with 270 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/src/ai/llms.rs
+55 -25
View File
@@ -1046,7 +1046,9 @@ impl LLMPreferences {
configured_models
};
if !single_provider_models.is_empty() {
// The registry replaces legacy settings. Otherwise stale legacy credentials
// win duplicate model IDs before the configured provider is considered.
if settings.openai_providers.value().is_empty() && !single_provider_models.is_empty() {
let base_url = settings.openai_base_url.value().clone();
let api_key = {
let key = settings.openai_api_key.value().clone();
@@ -1170,7 +1172,7 @@ impl LLMPreferences {
location: provider_location.clone(),
model: Some(model.model_id.clone()),
reasoning_effort: reasoning_effort.clone(),
max_input_tokens: Some(openai_model_context_size(model)),
max_input_tokens: Some(openai_model_context_size(model, provider_kind)),
max_output_tokens: model.max_output_tokens,
supports_system_messages: model.supports_system_messages(),
};
@@ -1487,7 +1489,7 @@ impl LLMPreferences {
#[cfg(not(target_family = "wasm"))]
pub fn fetch_openai_models_from_endpoint(&mut self, ctx: &mut ModelContext<Self>) {
let settings = AISettings::as_ref(ctx);
if !settings.is_openai_provider_enabled() {
if !settings.is_openai_provider_enabled() || !settings.openai_providers.value().is_empty() {
return;
}
@@ -1833,6 +1835,7 @@ impl LLMPreferences {
vision_supported: true,
context_size: model.context_size.unwrap_or(128_000),
max_input_tokens: model.context_size,
default_context_size: None,
max_output_tokens: None,
provider: None,
supports_system_messages: Some(true),
@@ -2626,8 +2629,18 @@ fn get_new_agent_mode_choices(
}
#[cfg(not(target_family = "wasm"))]
fn openai_model_context_size(model: &OpenAIModelConfig) -> u32 {
model.max_input_tokens.unwrap_or(model.context_size)
fn openai_model_context_size(model: &OpenAIModelConfig, provider_kind: OpenAIProviderKind) -> u32 {
// Older saved ChatGPT catalogs stored the default window in max_input_tokens.
// Preserve their larger usable window until the catalog refresh separates them.
if provider_kind == OpenAIProviderKind::ChatGPTSubscription
&& model.default_context_size.is_none()
{
return model.context_size;
}
model
.max_input_tokens
.unwrap_or(model.context_size)
.min(model.context_size)
}
/// Merges endpoint metadata into a provider's configured models without
@@ -2721,25 +2734,24 @@ fn openai_model_context_window(
model: &OpenAIModelConfig,
provider_kind: OpenAIProviderKind,
) -> LLMContextWindow {
let default_context_size = openai_model_context_size(model);
let max_context_size = if provider_kind == OpenAIProviderKind::ChatGPTSubscription {
model.context_size.max(default_context_size)
} else {
default_context_size
};
let max_context_size = openai_model_context_size(model, provider_kind);
let default_context_size = model
.default_context_size
.or_else(|| {
// Compatibility with saved catalogs from before the fields were separated.
(provider_kind == OpenAIProviderKind::ChatGPTSubscription)
.then_some(model.max_input_tokens)
.flatten()
})
.unwrap_or(max_context_size)
.min(max_context_size);
LLMContextWindow {
is_configurable: max_context_size > default_context_size,
min: default_context_size,
max: max_context_size,
// ChatGPT's catalog exposes `context_window` as the effective window
// and `max_context_window` as the model's actual maximum. Use the
// latter as the default so model refreshes do not reset the profile
// to the smaller effective window (for example, 272k).
default_max: if provider_kind == OpenAIProviderKind::ChatGPTSubscription {
max_context_size
} else {
default_context_size
},
// Use the full usable window; the catalog default remains available as
// the smaller configurable budget, not as a hard input ceiling.
default_max: max_context_size,
}
}
@@ -2888,7 +2900,9 @@ fn chatgpt_models_from_codex_response(body: &serde_json::Value) -> Vec<OpenAIMod
u32::try_from(u64::from(context_size) * u64::from(effective_context_percent) / 100)
.unwrap_or(context_size)
};
let max_input_tokens = Some(effective_context_size(default_context_size));
let default_context_size = Some(effective_context_size(default_context_size));
let max_input_tokens =
u32_from_json_any(model, &["max_input_tokens"]).map(effective_context_size);
let context_size = effective_context_size(max_context_size);
let vision_supported = model["input_modalities"]
@@ -2921,6 +2935,7 @@ fn chatgpt_models_from_codex_response(body: &serde_json::Value) -> Vec<OpenAIMod
vision_supported,
context_size,
max_input_tokens,
default_context_size,
max_output_tokens: None,
provider: Some("openai".to_string()),
supports_system_messages: Some(true),
@@ -2991,7 +3006,12 @@ async fn fetch_from_litellm_model_info(
let max_output_tokens = model_info["max_output_tokens"]
.as_u64()
.and_then(|v| u32::try_from(v).ok());
let context_size = max_input_tokens.unwrap_or(200_000);
let context_size = u32_from_json_any(
model_info,
&["max_context_window", "context_window", "max_model_len"],
)
.or(max_input_tokens)
.unwrap_or(200_000);
let vision_supported = model_info["supports_vision"].as_bool().unwrap_or(true);
@@ -3042,6 +3062,7 @@ async fn fetch_from_litellm_model_info(
vision_supported,
context_size,
max_input_tokens,
default_context_size: None,
max_output_tokens,
provider,
supports_system_messages: if model_name.starts_with("codex-gpt-") {
@@ -3122,9 +3143,17 @@ async fn fetch_from_openai_models(
m,
&["max_input_tokens", "input_token_limit", "max_prompt_tokens"],
);
let context_size = u32_from_any(m, &["max_model_len", "context_window", "token_size"])
.or(max_input_tokens)
.unwrap_or(200_000);
let context_size = u32_from_any(
m,
&[
"max_context_window",
"max_model_len",
"context_window",
"token_size",
],
)
.or(max_input_tokens)
.unwrap_or(200_000);
let max_output_tokens = u32_from_any(
m,
&[
@@ -3171,6 +3200,7 @@ async fn fetch_from_openai_models(
.unwrap_or(true),
context_size,
max_input_tokens,
default_context_size: None,
max_output_tokens,
provider,
supports_system_messages: if id.starts_with("codex-gpt-") {