For account CRN 7371765911 (Global Infosys Ltd), what was its MRR on 2026-06-21 versus its current MRR?
Basis: Prepare MRR for a Corporate account, or Prepare Monthly ACV if this is an Accountant account, snapshots of 21 Jun 2026 and the latest available date. Governed filters applied. How did I do with this report?
Per-step detail — each LLM call, each Omni request, each rejected draft —
is traced to stdout only and is not stored, so it cannot be shown here.
Query attempts counts run_query executions, not model turns.
WITH booking_snapshot_grain AS (
SELECT DISTINCT
omni_dbt__eds_calendar_day."DATE_DAY" AS "Snapshot Date",
omni_dbt__eds_calendar_day."IS_LATEST_AVAILABLE_DATE" AS "Is Current Snapshot",
omni_dbt__eds_all_accounts."ACCOUNT_CRN" AS "Account CRN",
omni_dbt__eds_all_accounts."ACCOUNT_NAME" AS "Account Name",
omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE" AS "Finance Account Type",
omni_dbt__eds_bookings."PRIMARY_KEY" AS "Booking Primary Key",
CASE
WHEN omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE" = 'Accountant'
THEN omni_dbt__eds_bookings."PREPARE_BOOKINGS_MONTHLY_ACV"
WHEN omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE" = 'Corporate'
THEN omni_dbt__eds_bookings."PREPARE_BOOKINGS_MRR"
ELSE NULL
END AS "Revenue Value"
FROM PROD."EDS_ALL_ACCOUNTS" AS omni_dbt__eds_all_accounts
INNER JOIN PROD."EDS_CALENDAR_DAY" AS omni_dbt__eds_calendar_day
ON omni_dbt__eds_calendar_day."DATE_DAY" >= omni_dbt__eds_all_accounts."VALID_FROM" AND omni_dbt__eds_calendar_day."DATE_DAY" <= omni_dbt__eds_all_accounts."VALID_TO"
LEFT JOIN PROD."EDS_BOOKINGS" AS omni_dbt__eds_bookings
ON omni_dbt__eds_all_accounts."DERIVED_ACCOUNT_ID" = omni_dbt__eds_bookings."DERIVED_ACCOUNT_ID" AND omni_dbt__eds_calendar_day."DATE_DAY" >= omni_dbt__eds_bookings."VALID_FROM" AND omni_dbt__eds_calendar_day."DATE_DAY" <= omni_dbt__eds_bookings."VALID_TO"
WHERE TRY_TO_NUMBER(omni_dbt__eds_all_accounts."ACCOUNT_CRN") = 7371765911
AND (omni_dbt__eds_calendar_day."DATE_DAY" = DATE_FROM_PARTS(2026, 6, 21)
OR omni_dbt__eds_calendar_day."IS_LATEST_AVAILABLE_DATE" = TRUE)
AND omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE" IN ('Accountant', 'Corporate')
AND omni_dbt__eds_bookings."HAS_PAID_SUBSCRIPTION" = TRUE
AND COALESCE(omni_dbt__eds_all_accounts."IS_DEXT_DEMO", FALSE) = FALSE
AND omni_dbt__eds_all_accounts."FRANCHISE_NAME" IS NULL
AND (omni_dbt__eds_all_accounts."SALESFORCE_ACCOUNT_TYPE" != 'Reseller'
OR omni_dbt__eds_all_accounts."SALESFORCE_ACCOUNT_TYPE" IS NULL)
), snapshot_totals AS (
SELECT
"Snapshot Date" AS "Snapshot Date",
"Is Current Snapshot" AS "Is Current Snapshot",
"Account CRN" AS "Account CRN",
"Account Name" AS "Account Name",
"Finance Account Type" AS "Finance Account Type",
SUM("Revenue Value") AS "Revenue Value"
FROM booking_snapshot_grain
GROUP BY
"Snapshot Date",
"Is Current Snapshot",
"Account CRN",
"Account Name",
"Finance Account Type"
)
SELECT
MAX("Account CRN") AS "Account CRN",
MAX("Account Name") AS "Account Name",
MAX("Finance Account Type") AS "Finance Account Type",
MAX(CASE WHEN "Snapshot Date" = DATE_FROM_PARTS(2026, 6, 21) THEN "Revenue Value" END) AS "Value on 2026-06-21",
MAX(CASE WHEN "Is Current Snapshot" = TRUE THEN "Snapshot Date" END) AS "Current Snapshot Date",
MAX(CASE WHEN "Is Current Snapshot" = TRUE THEN "Revenue Value" END) AS "Current Value"
FROM snapshot_totals
LIMIT 1
No feedback linked to this request.
Cost is the LLM completion spend LiteLLM priced for each call, summed per
request.
Chandler is running on the Codex CLI, which draws ChatGPT plan quota
rather than per-token API billing, so this figure is not money paid —
it is what the same traffic would have cost on the API, priced from the
token counts Codex reports. Read it as the size of the bill avoided.
Two known limits: embedding spend is not recorded, so
retrieval and matching cost is missing, and because the figure is one sum
per request it cannot be split by model within a request — a
request's classifier and agent calls can use different models while
llm_model holds only one name.
Only authenticated calls are logged, USAGE_LOG_ENABLED can
switch logging off, and log writes are fail-soft — this is not a complete
record of traffic. Questions are grouped into sessions: a session is
exact when the caller echoed its id back to us and otherwise inferred from
a 30-minute gap in that user’s activity, so a grouping is only as
good as the source shown on the session itself. A call with no
attributable user gets no session at all; those questions are listed
separately rather than dropped.