Improve agent provider resilience

This commit is contained in:
Ryan Ward
2026-09-02 17:09:08 -05:00
parent b115946534
commit 7a33cc7e56
72 changed files with 997 additions and 320 deletions
+210
View File
@@ -0,0 +1,210 @@
//! AWS Bedrock control-plane discovery.
//!
//! The foundation-model catalog is only a candidate list. Every candidate is
//! checked with `GetFoundationModelAvailability` before it is offered to the
//! user or persisted in Galaxy settings.
use aws_config::BehaviorVersion;
use aws_sdk_bedrock::Client;
use aws_sdk_bedrockruntime::config::Region;
use futures::{stream, StreamExt};
use galaxy_bedrock_model_catalog::model_metadata;
use super::client::{BedrockClientConfig, BedrockError};
use crate::settings::ai::BedrockModelConfig;
const AVAILABILITY_CHECK_CONCURRENCY: usize = 8;
pub async fn discover_available_models(
config: BedrockClientConfig,
) -> Result<Vec<BedrockModelConfig>, String> {
let aws_config = load_aws_config(&config)
.await
.map_err(|error| error.to_string())?;
let client = Client::new(&aws_config);
let catalog = client
.list_foundation_models()
.send()
.await
.map_err(|error| format!("Could not list AWS Bedrock foundation models: {error}"))?;
// AWS exposes agreement/authorization state only through an individual
// GetFoundationModelAvailability call. Keep using that control-plane API,
// but bound the independent checks so a large catalog does not serialize
// startup discovery one model at a time.
let checks = catalog.model_summaries().iter().cloned().map(|summary| {
let client = client.clone();
async move {
let model_id = summary.model_id();
let availability = match client
.get_foundation_model_availability()
.model_id(model_id)
.send()
.await
{
Ok(availability) => availability,
Err(error) => {
log::debug!(
"[bedrock] Availability check failed for {model_id}; excluding model: {error}"
);
return None;
}
};
if !model_availability_is_usable(
availability
.agreement_availability()
.map(|agreement| agreement.status().as_str()),
availability.authorization_status().as_str(),
availability.entitlement_availability().as_str(),
availability.region_availability().as_str(),
) {
log::debug!(
"[bedrock] Excluding {model_id}: agreement={}, authorization={}, entitlement={}, region={}",
availability
.agreement_availability()
.map(|agreement| agreement.status().as_str())
.unwrap_or("MISSING"),
availability.authorization_status().as_str(),
availability.entitlement_availability().as_str(),
availability.region_availability().as_str(),
);
return None;
}
let metadata = model_metadata(model_id);
let display_name = summary.model_name().map(str::to_owned).unwrap_or_else(|| {
metadata
.map(|metadata| metadata.model_name.clone())
.unwrap_or_else(|| prettify_model_id(model_id))
});
let vision_supported = summary
.input_modalities()
.iter()
.any(|modality| modality.as_str() == "IMAGE")
|| metadata.is_some_and(|metadata| metadata.supports_vision_input());
Some(BedrockModelConfig {
model_id: model_id.to_owned(),
display_name,
vision_supported,
})
}
});
let mut models = stream::iter(checks)
.buffer_unordered(AVAILABILITY_CHECK_CONCURRENCY)
.filter_map(futures::future::ready)
.collect::<Vec<_>>()
.await;
models.sort_by(|left, right| left.display_name.cmp(&right.display_name));
if models.is_empty() {
return Err(
"AWS returned no Bedrock models that are authorized and available in this region."
.to_string(),
);
}
Ok(models)
}
fn model_availability_is_usable(
agreement_status: Option<&str>,
authorization_status: &str,
entitlement_status: &str,
region_status: &str,
) -> bool {
agreement_status == Some("AVAILABLE")
&& authorization_status == "AUTHORIZED"
&& entitlement_status == "AVAILABLE"
&& region_status == "AVAILABLE"
}
async fn load_aws_config(
config: &BedrockClientConfig,
) -> Result<aws_config::SdkConfig, BedrockError> {
let sdk_config = match config.auth_method {
crate::settings::ai::BedrockAuthMethod::Profile
| crate::settings::ai::BedrockAuthMethod::Sso => {
let mut loader = aws_config::defaults(BehaviorVersion::latest());
if !config.profile.is_empty() && config.profile != "default" {
loader = loader.profile_name(&config.profile);
}
if !config.region.is_empty() {
loader = loader.region(Region::new(config.region.clone()));
}
loader.load().await
}
crate::settings::ai::BedrockAuthMethod::StaticKeys => {
if config.access_key_id.is_empty() || config.secret_access_key.is_empty() {
return Err(BedrockError::CredentialsNotConfigured);
}
let credentials = aws_credential_types::Credentials::new(
&config.access_key_id,
&config.secret_access_key,
config.session_token.clone(),
None,
"galaxy-bedrock-discovery",
);
let mut loader =
aws_config::defaults(BehaviorVersion::latest()).credentials_provider(credentials);
loader = loader.region(Region::new(if config.region.is_empty() {
"us-east-1".to_string()
} else {
config.region.clone()
}));
loader.load().await
}
};
if sdk_config.region().is_none() {
return Err(BedrockError::RegionNotConfigured);
}
Ok(sdk_config)
}
fn prettify_model_id(model_id: &str) -> String {
model_id
.rsplit('.')
.next()
.unwrap_or(model_id)
.replace(['-', ':'], " ")
}
#[cfg(test)]
mod tests {
use super::model_availability_is_usable;
#[test]
fn requires_every_availability_status() {
assert!(model_availability_is_usable(
Some("AVAILABLE"),
"AUTHORIZED",
"AVAILABLE",
"AVAILABLE",
));
assert!(!model_availability_is_usable(
None,
"AUTHORIZED",
"AVAILABLE",
"AVAILABLE",
));
assert!(!model_availability_is_usable(
Some("AVAILABLE"),
"NOT_AUTHORIZED",
"AVAILABLE",
"AVAILABLE",
));
assert!(!model_availability_is_usable(
Some("AVAILABLE"),
"AUTHORIZED",
"NOT_AVAILABLE",
"AVAILABLE",
));
assert!(!model_availability_is_usable(
Some("AVAILABLE"),
"AUTHORIZED",
"AVAILABLE",
"NOT_AVAILABLE",
));
}
}