i/Aether
1
0
Fork 0
mirror of https://github.com/fawney19/Aether.git synced 2026-10-07 01:47:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: unify user analytics and optimize overview aggregation

Browse Source 
Merge user accounts and usage reporting into one page with a combined ranking and account table, shared precise time ranges, and simpler range labels.

Parse overview metadata once through a schema-only view migration and disable JIT locally for bucket rebuilds. Preserve automatic backfills.

Add redacted OAuth refresh diagnostics, bucket failure context, and regression coverage. Resolve strict Clippy warnings.
This commit is contained in:
elky
2026-10-05 00:28:31 +08:00
parent 2075cd95de
commit cb7b9c9ecd
27 changed files with 1255 additions and 587 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/aether-data/runtime/schema/README.md
+8 -2
View File
@@ -33,12 +33,17 @@ The schema workspace has three normal source areas:
| `drivers/postgres/` | Current maintenance fragments for executable SQL. | Edit only for deployment compatibility, ordering, or generator gaps. |
| `bootstrap/postgres/` | Source fragments for the Postgres empty-database bootstrap snapshot. | Edit here when the bootstrap snapshot changes, then rebuild `aether-data` so `build.rs` regenerates the embedded snapshot. |
Everything else is output:
Generated schema and the composed baseline are outputs:
| Path | Role | Edit policy |
|---|---|---|
| `generated/postgres/` | Machine-written SQL emitted from `logical/*.toml` for audit and drift detection. | Do not edit; regenerate with `compose_schema.sh generate`. |
| `../../adapters/postgres/migrations/` | Runtime SQL artifacts embedded by each database adapter. | Regenerate through `compose_schema.sh compose`; do not edit independently. |
| `../../adapters/postgres/migrations/20260403000000_baseline.sql` | Composed PostgreSQL baseline embedded by the adapter. | Regenerate through `compose_schema.sh compose`; do not edit independently. |
Later incremental migrations are maintained directly under
`../../adapters/postgres/migrations/`; they have no compose target. Add a new
version for an upgrade and preserve the checksums of already-applied scripts.
Keep any corresponding maintained bootstrap definitions in sync.
`generated/**` is deliberately checked in so reviews and CI can see exactly
what the logical schema compiler emits for each driver. It is not a fourth SQL
@@ -131,6 +136,7 @@ cannot run them inside a transaction.
| `20260921020000` | Add the attribution-owner lookup index concurrently on existing databases. |
| `20260921020100` | Create the usage metadata actor index concurrently. |
| `20261001000000` | Remove deleted-user attribution from dashboard activity on future user deletion; schema-only upgrade without rewriting historical rows. |
| `20261004000000` | Parse request metadata once per overview fact; replace only the view definition without rewriting facts or statistics. |
Do not remove an applied migration after folding its changes into an earlier
schema definition. Existing databases retain its version in `_sqlx_migrations`
crates/aether-data/runtime/schema/bootstrap/postgres/190_overview_analytics.sql
+24 -21
View File
@@ -215,23 +215,23 @@ SELECT u.request_id, COALESCE(u.id, u.request_id) AS id, u.created_at,
u.status, u.status_code, u.error_category, u.failure_origin, u.failure_stage, u.failure_reason,
u.failure_schema_version, u.response_time_ms, u.first_byte_time_ms,
COALESCE(s.billing_status, u.billing_status) AS settlement_status,
COALESCE(u.request_metadata::jsonb->'usage_available', 'true'::jsonb) <> 'false'::jsonb AS usage_available,
COALESCE(u.request_metadata::jsonb->'usage_pricing_available', 'true'::jsonb) <> 'false'::jsonb
COALESCE(metadata.value->'usage_available', 'true'::jsonb) <> 'false'::jsonb AS usage_available,
COALESCE(metadata.value->'usage_pricing_available', 'true'::jsonb) <> 'false'::jsonb
AND (s.billing_total_cost_usd IS NOT NULL OR COALESCE(s.billing_status, u.billing_status) = 'settled') AS pricing_available,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available', 'true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_available', 'true'::jsonb) <> 'false'::jsonb
THEN b.input_tokens END AS input_tokens,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available', 'true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_available', 'true'::jsonb) <> 'false'::jsonb
THEN b.output_tokens END AS output_tokens,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available', 'true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_available', 'true'::jsonb) <> 'false'::jsonb
THEN b.total_tokens END AS total_tokens,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available', 'true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_available', 'true'::jsonb) <> 'false'::jsonb
THEN b.cache_read_input_tokens END AS cache_read_input_tokens,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available', 'true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_available', 'true'::jsonb) <> 'false'::jsonb
THEN b.cache_creation_input_tokens END AS cache_creation_input_tokens,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_pricing_available', 'true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_pricing_available', 'true'::jsonb) <> 'false'::jsonb
AND (s.billing_total_cost_usd IS NOT NULL OR COALESCE(s.billing_status, u.billing_status) = 'settled')
THEN round(COALESCE(s.billing_total_cost_usd::numeric, u.total_cost_usd::numeric), 8) END AS rated_amount,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_pricing_available', 'true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_pricing_available', 'true'::jsonb) <> 'false'::jsonb
AND (s.billing_actual_total_cost_usd IS NOT NULL OR COALESCE(s.billing_status, u.billing_status) = 'settled')
THEN round(COALESCE(s.billing_actual_total_cost_usd::numeric, u.actual_total_cost_usd::numeric), 8) END AS billable_amount,
s.quota_covered_amount_usd AS quota_covered_amount,
@@ -243,21 +243,24 @@ SELECT u.request_id, COALESCE(u.id, u.request_id) AS id, u.created_at,
s.allocation_status, s.finalized_at AS settled_at,
CASE WHEN s.billing_total_cost_usd IS NOT NULL THEN 'settlement_snapshot' ELSE 'legacy_float' END AS amount_source,
b.upstream_is_stream,
CASE WHEN u.request_metadata #>> '{analytics_measurement,source}' IN ('reported','estimated','mixed')
THEN u.request_metadata #>> '{analytics_measurement,source}' ELSE 'unknown' END AS token_source,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available','true'::jsonb) <> 'false'::jsonb
AND COALESCE(u.request_metadata::jsonb->'usage_pricing_available','true'::jsonb) <> 'false'::jsonb
CASE WHEN metadata.value #>> '{analytics_measurement,source}' IN ('reported','estimated','mixed')
THEN metadata.value #>> '{analytics_measurement,source}' ELSE 'unknown' END AS token_source,
CASE WHEN COALESCE(metadata.value->'usage_available','true'::jsonb) <> 'false'::jsonb
AND COALESCE(metadata.value->'usage_pricing_available','true'::jsonb) <> 'false'::jsonb
AND s.input_price_per_1m IS NOT NULL AND s.billing_cache_read_cost_usd IS NOT NULL
THEN round(s.input_price_per_1m::numeric * b.cache_read_input_tokens::numeric / 1000000,8) END AS cache_estimated_full_cost_amount,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available','true'::jsonb) <> 'false'::jsonb
AND COALESCE(u.request_metadata::jsonb->'usage_pricing_available','true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_available','true'::jsonb) <> 'false'::jsonb
AND COALESCE(metadata.value->'usage_pricing_available','true'::jsonb) <> 'false'::jsonb
AND s.input_price_per_1m IS NOT NULL AND s.billing_cache_read_cost_usd IS NOT NULL
THEN round(s.billing_cache_read_cost_usd::numeric,8) END AS cache_read_cost_amount,
CASE WHEN COALESCE(u.request_metadata::jsonb->'usage_available','true'::jsonb) <> 'false'::jsonb
AND COALESCE(u.request_metadata::jsonb->'usage_pricing_available','true'::jsonb) <> 'false'::jsonb
CASE WHEN COALESCE(metadata.value->'usage_available','true'::jsonb) <> 'false'::jsonb
AND COALESCE(metadata.value->'usage_pricing_available','true'::jsonb) <> 'false'::jsonb
AND s.input_price_per_1m IS NOT NULL AND s.billing_cache_creation_cost_usd IS NOT NULL
THEN round(s.billing_cache_creation_cost_usd::numeric,8) END AS cache_creation_cost_amount
FROM public.usage u
-- OFFSET 0 keeps this projection from being flattened: large metadata is
-- detoasted and parsed once per request, rather than once per metric expression.
CROSS JOIN LATERAL (SELECT u.request_metadata::jsonb AS value OFFSET 0) metadata
LEFT JOIN public.usage_settlement_snapshots s USING (request_id)
LEFT JOIN public.usage_attribution_snapshots a USING (request_id)
JOIN public.usage_billing_facts b USING (request_id)
@@ -266,10 +269,10 @@ CROSS JOIN LATERAL (
SELECT CASE WHEN a.request_id IS NOT NULL THEN a.credential_owner_id
WHEN EXISTS (SELECT 1 FROM public.users WHERE id=u.user_id AND NOT is_deleted) THEN u.user_id END AS owner_id,
COALESCE(k.is_standalone,
CASE WHEN jsonb_typeof(u.request_metadata::jsonb #> '{analytics_attribution,is_standalone}')='boolean'
THEN (u.request_metadata #>> '{analytics_attribution,is_standalone}')::boolean END,
CASE WHEN jsonb_typeof(u.request_metadata::jsonb->'api_key_is_standalone')='boolean'
THEN (u.request_metadata->>'api_key_is_standalone')::boolean END,
CASE WHEN jsonb_typeof(metadata.value #> '{analytics_attribution,is_standalone}')='boolean'
THEN (metadata.value #>> '{analytics_attribution,is_standalone}')::boolean END,
CASE WHEN jsonb_typeof(metadata.value->'api_key_is_standalone')='boolean'
THEN (metadata.value->>'api_key_is_standalone')::boolean END,
CASE WHEN a.attribution_source='user_account' THEN false
WHEN a.attribution_source='standalone_key' THEN true END,
CASE WHEN u.api_key_id IS NULL THEN false END) AS is_standalone