i/Aether
1
0
Fork 0
mirror of https://github.com/fawney19/Aether.git synced 2026-10-08 02:17:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: revamp analytics dashboards and harden database migrations

Browse Source 
Add dashboard and overview analytics, health monitoring, provider expense tracking, and announcement updates across the gateway and frontend.

Keep schema migrations free of historical backfills while preserving automatic backfill execution. Bound migration deadlines, run schema preparation before Compose replacement, and anonymize deleted dashboard users.

Include the current documentation cleanup and regression coverage.
This commit is contained in:
elky
2026-10-01 11:48:17 +08:00
parent 60b89cc840
commit 066ea87d72
327 changed files with 31728 additions and 20645 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/aether-gateway/src/execution_runtime/stream/execution.rs
+111 -5
View File
@@ -12,7 +12,7 @@ use std::time::{Duration, Instant};
use aether_ai_serving::{AiAttemptExecutionOutcome, AiAttemptRetryScope};
use aether_contracts::{
ExecutionPlan, ExecutionResponseObservation, ExecutionStreamTerminalSummary,
ExecutionTelemetry, StandardizedUsage, StreamFrame, StreamFramePayload,
ExecutionTelemetry, StandardizedUsage, StreamFrame, StreamFramePayload, UsageTokenSource,
};
use aether_data_contracts::repository::candidates::{
RequestCandidateStatus, UpsertRequestCandidateRecord,
@@ -445,11 +445,15 @@ fn build_sync_terminal_usage_seeds(
report_context: Option<&serde_json::Value>,
payload: &GatewaySyncReportRequest,
) -> (TerminalUsageContextSeed, SyncTerminalUsagePayloadSeed) {
let analytics_context =
crate::usage::reporting::failure::sync_analytics_context(report_context, payload);
let report_context_with_diagnostics =
attach_current_request_diagnostics_to_report_context(report_context);
attach_current_request_diagnostics_to_report_context(analytics_context.as_ref());
let context_seed = build_terminal_usage_context_seed(
plan,
report_context_with_diagnostics.as_ref().or(report_context),
report_context_with_diagnostics
.as_ref()
.or(analytics_context.as_ref()),
);
let payload_seed = build_sync_terminal_usage_payload_seed(payload);
(context_seed, payload_seed)
@@ -586,7 +590,12 @@ async fn record_stream_terminal_usage(
cancelled: bool,
) {
crate::execution_runtime::mark_stream_candidate_watchdog_terminal_started();
let context_seed = build_terminal_usage_context_seed(plan, report_context);
let analytics_context = crate::usage::reporting::failure::stream_analytics_context(
report_context,
payload,
cancelled,
);
let context_seed = build_terminal_usage_context_seed(plan, analytics_context.as_ref());
let payload_seed = build_stream_terminal_usage_payload_seed(payload);
state
.usage_runtime
@@ -976,6 +985,9 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
usage.cache_read_tokens = 0;
if usage.input_tokens <= 0 {
usage.input_tokens = estimated_input_tokens as i64;
if usage.input_tokens > 0 {
mark_kiro_stream_estimated_usage(usage, report_context, false);
}
}
return;
}
@@ -984,6 +996,10 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
usage.input_tokens = kiro_billed_input_tokens(estimated_input_tokens, cache_usage) as i64;
usage.cache_creation_tokens = cache_usage.cache_creation_input_tokens as i64;
usage.cache_read_tokens = cache_usage.cache_read_input_tokens as i64;
if usage.input_tokens > 0 || usage.cache_creation_tokens > 0 || usage.cache_read_tokens > 0
{
mark_kiro_stream_estimated_usage(usage, report_context, false);
}
return;
}
@@ -996,12 +1012,18 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
cache_read_input_tokens: usage.cache_read_tokens.max(0) as u64,
},
) as i64;
if usage.input_tokens > 0 {
mark_kiro_stream_estimated_usage(usage, report_context, true);
}
}
return;
}
if usage.input_tokens <= 0 {
usage.input_tokens = estimated_input_tokens as i64;
if usage.input_tokens > 0 {
mark_kiro_stream_estimated_usage(usage, report_context, true);
}
}
let Some(profile) =
@@ -1024,6 +1046,35 @@ async fn maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
usage.input_tokens = billed_input_tokens as i64;
usage.cache_creation_tokens = cache_usage.cache_creation_input_tokens as i64;
usage.cache_read_tokens = cache_usage.cache_read_input_tokens as i64;
mark_kiro_stream_estimated_usage(usage, report_context, false);
}
fn mark_kiro_stream_estimated_usage(
usage: &mut StandardizedUsage,
report_context: &Value,
retains_cache: bool,
) {
let retained_source = usage.token_source.unwrap_or_else(|| {
match report_context
.get("usage_token_source")
.and_then(Value::as_str)
{
Some("estimated") => UsageTokenSource::Estimated,
Some("mixed") => UsageTokenSource::Mixed,
_ => UsageTokenSource::Reported,
}
});
let retains_reported_tokens = retained_source != UsageTokenSource::Estimated
&& (usage.output_tokens > 0
|| usage.reasoning_tokens > 0
|| usage.cache_creation_ephemeral_5m_tokens > 0
|| usage.cache_creation_ephemeral_1h_tokens > 0
|| (retains_cache && (usage.cache_creation_tokens > 0 || usage.cache_read_tokens > 0)));
usage.token_source = Some(if retains_reported_tokens {
UsageTokenSource::Mixed
} else {
UsageTokenSource::Estimated
});
}
fn append_stream_capture_bytes(
@@ -3963,7 +4014,7 @@ async fn execute_execution_runtime_stream_inner(
let candidate_started_unix_secs = current_request_candidate_unix_ms();
let provider_in_flight_started_at = Instant::now();
let mut provider_pool_in_flight_guard =
match acquire_provider_pool_execution_guard(state, &plan).await? {
match acquire_provider_pool_execution_guard(state, &plan, report_context.as_ref()).await? {
ProviderPoolInFlightAdmission::Acquired(guard) => guard,
ProviderPoolInFlightAdmission::Saturated { limit } => {
record_local_runtime_candidate_skip_reason(
@@ -12293,6 +12344,10 @@ mod tests {
.expect("first usage should exist");
assert!(first_usage.cache_creation_tokens > 0);
assert_eq!(first_usage.cache_read_tokens, 0);
assert_eq!(
first_usage.token_source,
Some(aether_contracts::UsageTokenSource::Mixed)
);
let mut second_summary = Some(ExecutionStreamTerminalSummary {
standardized_usage: Some(StandardizedUsage {
@@ -12317,6 +12372,10 @@ mod tests {
assert_eq!(second_usage.cache_creation_tokens, 0);
assert!(second_usage.input_tokens < 6_000);
assert_eq!(second_usage.output_tokens, 19);
assert_eq!(
second_usage.token_source,
Some(aether_contracts::UsageTokenSource::Mixed)
);
}
#[tokio::test]
@@ -12512,6 +12571,49 @@ mod tests {
assert_eq!(usage.cache_creation_tokens, 0);
assert_eq!(usage.cache_read_tokens, 0);
assert_eq!(usage.output_tokens, 13);
assert_eq!(
usage.token_source,
Some(aether_contracts::UsageTokenSource::Mixed)
);
use aether_contracts::UsageTokenSource::{Estimated, Mixed};
for (hint, source, input, output, cache, expected) in [
(Some("estimated"), None, 0, 13, 0, Some(Estimated)),
(None, Some(Estimated), 0, 13, 0, Some(Estimated)),
(None, None, 0, 0, 200, Some(Mixed)),
(None, None, 0, 0, 0, Some(Estimated)),
(None, None, 50, 13, 0, None),
] {
let mut context = report_context.clone();
if let Some(hint) = hint {
context["usage_token_source"] = json!(hint);
}
let mut summary = Some(ExecutionStreamTerminalSummary {
standardized_usage: Some(StandardizedUsage {
token_source: source,
input_tokens: input,
output_tokens: output,
cache_read_tokens: cache,
..StandardizedUsage::new()
}),
..Default::default()
});
maybe_apply_kiro_prompt_cache_usage_to_stream_summary(
&state,
&plan,
Some(&context),
&mut summary,
)
.await;
let usage = summary.unwrap().standardized_usage.unwrap();
assert!(usage.input_tokens > 0);
assert_eq!(usage.output_tokens, output);
assert_eq!(usage.cache_read_tokens, cache);
assert_eq!(
usage.token_source, expected,
"hint={hint:?}, source={source:?}"
);
}
}
#[tokio::test]
@@ -12751,6 +12853,10 @@ mod tests {
assert_eq!(usage.cache_creation_tokens, 175);
assert_eq!(usage.cache_read_tokens, 24_463);
assert_eq!(usage.output_tokens, 167);
assert_eq!(
usage.token_source,
Some(aether_contracts::UsageTokenSource::Mixed)
);
}
#[tokio::test]