| Last active | User | First match | Questions | Cost | Feedback |
|---|---|---|---|---|---|
| 2026-08-17 09:57 | kathryn.buckley@dext.com | Using the same engagement definition as the Feature Adoption Omni dashboard (https://dext.omniapp.co/dashboards/feature-adoption), what is the percentage of Partner accounts and the percentage of Client accounts using Item Messaging, on average over the last 6 months? | 7 | $2.6593 | — |
| 2026-08-12 16:13 | kathryn.buckley@dext.com | Monthly revenue for the Precision add-on from January 2024 to June 2026, broken down by month | 21 | $8.1057 | — |
| 2026-08-06 09:28 | kathryn.buckley@dext.com | How many Dext client accounts that are attached to a Partner and currently active have only a basic Dext subscription with no add-ons — meaning no AI Assist, no Vault, no Data Health, no Dext Solo, and no e-invoicing in France? | 7 | $2.6051 | — |
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.