Usage tracking
What it is
- Pulls provider usage/quota directly from their usage endpoints.
- No estimated costs; only the provider-reported windows.
Where it shows up
/statusin chats: emoji‑rich status card with session tokens + estimated cost (API key only). Provider usage shows for the current model provider when available./usage off|tokens|fullin chats: per-response usage footer (OAuth shows tokens only)./usage costin chats: local cost summary aggregated from the configured session store (JSONL transcripts or the sqlite/postgres store).- CLI:
wednesdayai status --usageprints a full per-provider breakdown. - CLI:
wednesdayai channels listprints the same usage snapshot alongside provider config (use--no-usageto skip). - macOS menu bar: “Usage” section under Context (only if available).
Per-model attribution
/usage cost and sessions.usage split the per-model rows by resolved model, not just the
configured alias:
modelis the configured alias (e.g.low);actualModelis the resolved backend model from the assistant entry’sresponseModel(e.g.zai-org/GLM-5.3-Flash).- byModel rows are keyed
provider::model::actualModel; the third segment is empty when the resolved model is unknown. One alias can therefore appear as several rows — one per resolved model — and per-row counts/tokens/cost always add back up to the session totals. - The Control UI usage view shows the resolved model per row, and its model filter matches against
actualModelas well.
Historical backfill
On the first startup after upgrading, the session store backfills the usage and model columns for historical entries once (markerusage-columns-v1), so older entries gain per-model rows and
actualModel too. The backfill runs after startup without blocking it; a failed run is logged
(startup backfill usage columns failed) and retried on the next start, because the marker is
written only after the last batch commits.
Providers + credentials
- Anthropic (Claude): OAuth tokens in auth profiles.
- GitHub Copilot: OAuth tokens in auth profiles.
- Gemini CLI: OAuth tokens in auth profiles.
- Antigravity: OAuth tokens in auth profiles.
- OpenAI Codex: OAuth tokens in auth profiles (accountId used when present).
- MiniMax: API key (coding plan key;
MINIMAX_CODE_PLAN_KEYorMINIMAX_API_KEY); uses the 5‑hour coding plan window. - z.ai: API key via env/config/auth store.