Closes#15
Add nullable tokens_in / tokens_out IntegerFields to PromptMetric so we
record real prompt/completion token counts per turn. Values come from the
LLM provider usage payload via a new extract_token_usage helper; when a
provider does not report usage the fields stay null (never estimated).
- consumers/consumers_graph create_prompt_metric + finish_prompt_metric
now accept and persist optional tokens_in / tokens_out.
- Admin: PromptMetric lists tokens_in/tokens_out (+ event/model filters);
Conversation admin shows summed tokens_in/out/total per conversation.
- Tests cover the model fields, extract_token_usage parsing, metric
lifecycle token persistence, and admin aggregation.
Follow-ups: #16 (frontend token display) and #17 (billing/quotas).
Co-authored-by: Cursor <cursoragent@cursor.com>
westfarnandCursor