Maycon Santos e814f12995 [e2e] allow zero input_tokens on cache-heavy providers in cost validation ...

Run 30061545790 validated 7/8 providers exactly; the kimi subtest failed
only on the test's own input_tokens>0 precondition. Moonshot's
Anthropic-compatible endpoint reports the whole prompt under the
cache-read bucket (input_tokens=0, 90 cache tokens riding total_tokens),
and the stored cost was exactly right: 64 out x $15/M + 90 cache-read x
$0.30/M = $0.000987. Require positive output/total tokens instead and let
the existing cache-aware bounds cover the zero-input shape.

2026-07-24 02:59:22 +00:00

..

agentnetwork

[e2e] allow zero input_tokens on cache-heavy providers in cost validation

2026-07-24 02:59:22 +00:00

harness

[management, proxy] add Kimi (Moonshot AI) provider to Agent Network (#6853)

2026-07-23 13:32:32 +02:00