strix

forkless/strix

Fork 0

mirror of https://github.com/usestrix/strix.git synced 2026-08-23 11:22:37 +02:00

Commit Graph

Author	SHA1	Message	Date
Ahmed Allam	6c99829325	Simplify cost ledger to one bucket (#531 )	2026-06-08 15:56:28 -07:00
Ahmed Allam	1c9ab993bb	Use observed LiteLLM cost for LiteLLM-routed calls (#529 ) Register a litellm.success_callback that captures kwargs['response_cost'] into a new observed-cost bucket on LLMUsageLedger. record() skips the tokens-times-registry estimate for LiteLLM-routed models so we do not double-count with the callback; OpenAI direct routes keep estimating since LiteLLM is not invoked for them. Per-agent attribution for LiteLLM-routed calls is apportioned by token share at to_record() time.	2026-06-08 15:01:48 -07:00
0xallam	4791feb08e	Track SDK LLM usage	2026-04-26 15:38:41 -07:00

Author

SHA1

Message

Date

Ahmed Allam

6c99829325

Simplify cost ledger to one bucket (#531 )

2026-06-08 15:56:28 -07:00

Ahmed Allam

1c9ab993bb

Use observed LiteLLM cost for LiteLLM-routed calls (#529 )

Register a litellm.success_callback that captures kwargs['response_cost']
into a new observed-cost bucket on LLMUsageLedger. record() skips the
tokens-times-registry estimate for LiteLLM-routed models so we do not
double-count with the callback; OpenAI direct routes keep estimating
since LiteLLM is not invoked for them. Per-agent attribution for
LiteLLM-routed calls is apportioned by token share at to_record() time.

2026-06-08 15:01:48 -07:00

0xallam

4791feb08e

Track SDK LLM usage

2026-04-26 15:38:41 -07:00