The Omni dashboard shows 11,046 paying partners, but you returned 11,172 (a difference of 126). What could explain the difference? Which snapshot date did you use, and how does your paying partner definition and filters compare to the governed Paying Partners metric in Omni?
Cost was recorded but no model name was. This happens when the answer came from an approved query — that path returns before the model name is stamped — so the cost figure is correct while the model behind it is not identified here. Cost was still priced per call at the right rate.
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.
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.