Chandler usage · question

Prompt

For account CRN 8307087859, what was its MRR on 2026-04-25 versus its current MRR?

Outcome

success

Cost

$0.3440

excludes embeddings

Latency

24.7 s

Query attempts

Rows returned

Tokens

29,303 / 1,020

in / out

Request

request_id: bcbad573-537c-481b-9a51-0c29b84733ff
When: 2026-09-24 18:14
Tool: ask
User: chris.scott@dext.com · Chris Scott
Identity: google
Session: 67cf914d-9500-4868-80a9-322430d351e9
Model: not recorded

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.

Route taken

Topic

—

Omni model

—

Match method

cache_semantic

Nudge shown

—

Question shape

decision_shaped

Caveat raised

—

Sharper question offered

—

Shown to user

Basis: Prepare Monthly ACV for this Partner account, with Prepare MRR shown only to diagnose the missing hi, daily snapshots from 1 Apr through 31 May 2026, including 25 Apr. Governed filters applied.
Figures as of 18:13 UTC — reused from an earlier identical question, not recomputed just now.
Showing the top 10 of 18 rows.

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.

Feedback

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.