feat(hub): usage fact ledger for run-scoped cost attribution (ADR-0026) (#4)

Co-authored-by: Hong Jiarong <me@jrhim.com> Co-committed-by: Hong Jiarong <me@jrhim.com>
2026-07-18 14:46:41 +08:00
parent 97f7972cc5
commit aaa098bb8b
11 changed files with 760 additions and 46 deletions
@@ -0,0 +1,64 @@
+-- ADR-0026: append-only UsageFact ledger. AgentRun.costUsd/inputTokens/
+-- outputTokens become a derived rollup cache; the truth is in UsageFact.
+
+CREATE TABLE "UsageFact" (
+    "id"            TEXT                   NOT NULL,
+    "runId"         TEXT                   NOT NULL,
+    "occurredAt"    TIMESTAMP(3)           NOT NULL,
+    "kind"          TEXT                   NOT NULL,
+    "provider"      TEXT                   NOT NULL,
+    "model"         TEXT,
+    "inputTokens"   INTEGER,
+    "outputTokens"  INTEGER,
+    "quantity"      DECIMAL(18, 6),
+    "unit"          TEXT,
+    "costUsd"       DECIMAL(18, 8),
+    "costSource"    TEXT                   NOT NULL,
+    "capabilityId"  TEXT,
+    "correlationId" TEXT,
+    "metadata"      JSONB                  NOT NULL,
+    "createdAt"     TIMESTAMP(3)           NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    CONSTRAINT "UsageFact_pkey" PRIMARY KEY ("id")
+);
+
+CREATE INDEX "UsageFact_runId_occurredAt_idx" ON "UsageFact"("runId", "occurredAt");
+CREATE INDEX "UsageFact_runId_kind_idx"       ON "UsageFact"("runId", "kind");
+CREATE INDEX "UsageFact_provider_model_occurredAt_idx"
+  ON "UsageFact"("provider", "model", "occurredAt");
+CREATE INDEX "UsageFact_capabilityId_occurredAt_idx"
+  ON "UsageFact"("capabilityId", "occurredAt");
+
+ALTER TABLE "UsageFact"
+  ADD CONSTRAINT "UsageFact_runId_fkey"
+  FOREIGN KEY ("runId") REFERENCES "AgentRun"("id")
+  ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- Backfill: one synthetic model_completion fact per AgentRun that has any
+-- recorded usage (cost or tokens). correlationId = run id marks these as
+-- backfill artefacts (real facts use an external correlation id or null).
+-- Runs with no recorded usage stay fact-less and remain runsWithoutCost,
+-- matching ADR-0022's "missing cost ≠ zero" rule and the pre-existing
+-- migration 20260709143000_agent_run_cost_tracking's "no backfill for the
+-- truly unrecorded" stance.
+INSERT INTO "UsageFact" (
+  "id", "runId", "occurredAt", "kind", "provider", "model",
+  "inputTokens", "outputTokens", "costUsd", "costSource",
+  "correlationId", "metadata"
+)
+SELECT
+  'usagefact_backfill_' || "AgentRun"."id",
+  "AgentRun"."id",
+  COALESCE("AgentRun"."finishedAt", "AgentRun"."startedAt", CURRENT_TIMESTAMP),
+  'model_completion',
+  "AgentRun"."provider",
+  "AgentRun"."model",
+  "AgentRun"."inputTokens",
+  "AgentRun"."outputTokens",
+  "AgentRun"."costUsd",
+  COALESCE("AgentRun"."costSource", 'unknown'),
+  "AgentRun"."id",
+  '{}'::jsonb
+FROM "AgentRun"
+WHERE "AgentRun"."costUsd" IS NOT NULL
+   OR "AgentRun"."inputTokens" IS NOT NULL
+   OR "AgentRun"."outputTokens" IS NOT NULL;