mirror of
https://github.com/fawney19/Aether.git
synced 2026-09-02 09:20:22 +08:00
Merge latest origin/main into codex/gemini-embedding-batch
# Conflicts: # apps/aether-gateway/src/ai_serving/planner/standard/openai/mod.rs # apps/aether-gateway/src/execution_runtime/fallback.rs
This commit is contained in:
@@ -136,7 +136,7 @@ fn lifecycle_status_and_billing(event_type: UsageEventType) -> (&'static str, &'
|
||||
UsageEventType::Streaming => ("streaming", "pending"),
|
||||
UsageEventType::Completed => ("completed", "pending"),
|
||||
UsageEventType::Failed => ("failed", "void"),
|
||||
UsageEventType::Cancelled => ("cancelled", "void"),
|
||||
UsageEventType::Cancelled => ("cancelled", "pending"),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -181,6 +181,38 @@ mod tests {
|
||||
assert_eq!(record.finalized_at_unix_secs, Some(1_700_000_000));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cancelled_terminal_record_stays_pending_for_settlement() {
|
||||
let record = build_upsert_usage_record_from_event(&UsageEvent {
|
||||
event_type: UsageEventType::Cancelled,
|
||||
request_id: "req-cancelled".to_string(),
|
||||
timestamp_ms: 1_700_000_000_000,
|
||||
data: UsageEventData {
|
||||
provider_name: "OpenAI".to_string(),
|
||||
model: "gpt-5".to_string(),
|
||||
input_tokens: Some(10),
|
||||
output_tokens: Some(20),
|
||||
total_tokens: Some(30),
|
||||
total_cost_usd: Some(0.03),
|
||||
actual_total_cost_usd: Some(0.02),
|
||||
status_code: Some(499),
|
||||
response_time_ms: Some(200),
|
||||
first_byte_time_ms: Some(50),
|
||||
..UsageEventData::default()
|
||||
},
|
||||
})
|
||||
.expect("record should build");
|
||||
|
||||
assert_eq!(record.status, "cancelled");
|
||||
assert_eq!(record.billing_status, "pending");
|
||||
assert_eq!(record.total_tokens, Some(30));
|
||||
assert_eq!(record.total_cost_usd, Some(0.03));
|
||||
assert_eq!(record.actual_total_cost_usd, Some(0.02));
|
||||
assert_eq!(record.status_code, Some(499));
|
||||
assert_eq!(record.response_time_ms, Some(200));
|
||||
assert_eq!(record.first_byte_time_ms, Some(50));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitizes_request_metadata_before_building_upsert_record() {
|
||||
let record = build_upsert_usage_record_from_event(&UsageEvent {
|
||||
|
||||
@@ -164,6 +164,29 @@ mod tests {
|
||||
assert!(!inputs[0].api_key_is_standalone);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn settles_pending_cancelled_usage() {
|
||||
let writer = TestSettlementWriter {
|
||||
has_writer: true,
|
||||
..Default::default()
|
||||
};
|
||||
let mut usage = sample_usage();
|
||||
usage.status = "cancelled".to_string();
|
||||
usage.status_code = Some(499);
|
||||
|
||||
settle_usage_if_needed(&writer, &usage)
|
||||
.await
|
||||
.expect("settlement should succeed");
|
||||
|
||||
let inputs = writer.inputs.lock().expect("settlement inputs lock");
|
||||
assert_eq!(inputs.len(), 1);
|
||||
assert_eq!(inputs[0].request_id, "req-1");
|
||||
assert_eq!(inputs[0].status, "cancelled");
|
||||
assert_eq!(inputs[0].billing_status, "pending");
|
||||
assert_eq!(inputs[0].total_cost_usd, 1.25);
|
||||
assert_eq!(inputs[0].actual_total_cost_usd, 0.75);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn propagates_standalone_key_flag_from_usage_metadata() {
|
||||
let writer = TestSettlementWriter {
|
||||
|
||||
@@ -27,15 +27,21 @@ impl UsageMapper {
|
||||
}
|
||||
|
||||
derive_missing_input_tokens(raw_usage, api_format, &mut usage);
|
||||
copy_explicit_total_tokens(raw_usage, api_format, &mut usage);
|
||||
usage.normalize_cache_creation_breakdown()
|
||||
}
|
||||
|
||||
pub fn map_from_response(response: &serde_json::Value, api_format: &str) -> StandardizedUsage {
|
||||
let family = api_family(api_format);
|
||||
let Some(usage_value) = resolve_usage_value(response, family.as_str()) else {
|
||||
return StandardizedUsage::new();
|
||||
let mut usage = if let Some(usage_value) = resolve_usage_value(response, family.as_str()) {
|
||||
Self::map(usage_value, api_format, None)
|
||||
} else {
|
||||
StandardizedUsage::new()
|
||||
};
|
||||
Self::map(usage_value, api_format, None)
|
||||
if is_openai_image_api(api_format) {
|
||||
apply_openai_image_response_dimensions(response, &mut usage);
|
||||
}
|
||||
usage
|
||||
}
|
||||
}
|
||||
|
||||
@@ -59,6 +65,53 @@ fn api_family(api_format: &str) -> String {
|
||||
.to_ascii_lowercase()
|
||||
}
|
||||
|
||||
fn api_kind(api_format: &str) -> String {
|
||||
api_format
|
||||
.split(':')
|
||||
.nth(1)
|
||||
.unwrap_or_default()
|
||||
.trim()
|
||||
.to_ascii_lowercase()
|
||||
}
|
||||
|
||||
fn is_openai_image_api(api_format: &str) -> bool {
|
||||
api_family(api_format).as_str() == "openai" && api_kind(api_format).as_str() == "image"
|
||||
}
|
||||
|
||||
fn apply_openai_image_response_dimensions(
|
||||
response: &serde_json::Value,
|
||||
usage: &mut StandardizedUsage,
|
||||
) {
|
||||
let image_count = openai_image_response_image_count(response);
|
||||
if image_count <= 0 {
|
||||
return;
|
||||
}
|
||||
|
||||
usage.request_count = image_count;
|
||||
usage
|
||||
.dimensions
|
||||
.insert("image_count".to_string(), serde_json::json!(image_count));
|
||||
}
|
||||
|
||||
fn openai_image_response_image_count(response: &serde_json::Value) -> i64 {
|
||||
response
|
||||
.get("data")
|
||||
.and_then(serde_json::Value::as_array)
|
||||
.map(|items| items.len() as i64)
|
||||
.filter(|value| *value > 0)
|
||||
.or_else(|| image_result_count(response.get("result")))
|
||||
.unwrap_or(0)
|
||||
}
|
||||
|
||||
fn image_result_count(value: Option<&serde_json::Value>) -> Option<i64> {
|
||||
match value? {
|
||||
serde_json::Value::Array(items) => Some(items.len() as i64).filter(|count| *count > 0),
|
||||
serde_json::Value::Object(object) if !object.is_empty() => Some(1),
|
||||
serde_json::Value::String(text) if !text.trim().is_empty() => Some(1),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
fn base_mapping(api_format: &str) -> BTreeMap<String, String> {
|
||||
let mut mapping = BTreeMap::new();
|
||||
match api_family(api_format).as_str() {
|
||||
@@ -189,6 +242,22 @@ fn derive_missing_input_tokens(
|
||||
}
|
||||
}
|
||||
|
||||
fn copy_explicit_total_tokens(
|
||||
raw_usage: &serde_json::Value,
|
||||
api_format: &str,
|
||||
usage: &mut StandardizedUsage,
|
||||
) {
|
||||
let total_tokens = match api_family(api_format).as_str() {
|
||||
"gemini" => numeric_i64(raw_usage.get("totalTokenCount")),
|
||||
_ => numeric_i64(raw_usage.get("total_tokens")),
|
||||
};
|
||||
if let Some(total_tokens) = total_tokens.filter(|value| *value > 0) {
|
||||
usage
|
||||
.dimensions
|
||||
.insert("total_tokens".to_string(), serde_json::json!(total_tokens));
|
||||
}
|
||||
}
|
||||
|
||||
fn numeric_i64(value: Option<&serde_json::Value>) -> Option<i64> {
|
||||
value.and_then(|value| {
|
||||
value
|
||||
@@ -603,4 +672,47 @@ mod tests {
|
||||
assert_eq!(usage.output_tokens, 6);
|
||||
assert_eq!(usage.cache_read_tokens, 2);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn maps_openai_image_response_dimensions_without_usage() {
|
||||
let usage = map_usage_from_response(
|
||||
&serde_json::json!({
|
||||
"created": 1_700_000_000,
|
||||
"data": [
|
||||
{ "b64_json": "abc" },
|
||||
{ "url": "https://example.test/image.png" }
|
||||
]
|
||||
}),
|
||||
"openai:image",
|
||||
);
|
||||
|
||||
assert_eq!(usage.request_count, 2);
|
||||
assert_eq!(
|
||||
usage.dimensions.get("image_count"),
|
||||
Some(&serde_json::json!(2))
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn maps_openai_image_response_dimensions_with_native_usage() {
|
||||
let usage = map_usage_from_response(
|
||||
&serde_json::json!({
|
||||
"usage": {
|
||||
"input_tokens": 11,
|
||||
"output_tokens": 22,
|
||||
"total_tokens": 33
|
||||
},
|
||||
"data": [{ "b64_json": "abc" }]
|
||||
}),
|
||||
"openai:image",
|
||||
);
|
||||
|
||||
assert_eq!(usage.input_tokens, 11);
|
||||
assert_eq!(usage.output_tokens, 22);
|
||||
assert_eq!(usage.request_count, 1);
|
||||
assert_eq!(
|
||||
usage.dimensions.get("image_count"),
|
||||
Some(&serde_json::json!(1))
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user