pj b9cdf7a571 feat(llmclient): parse usage and the served model ...

An LLM-in-the-loop evaluation has to report tokens per action and cost per
defect, and the client discarded both counters. Served model is recorded
separately from the requested one because a router can substitute a
differently-priced variant.

Claude-Session: https://claude.ai/code/session_01A5KmftdEJ49A9z5mF5ESrX

2026-08-12 22:56:58 +05:30

..

_oracle

iOS simulator driver: Go-native companion-backed backend (#62)

2026-06-08 19:10:54 +05:30

android

WIP: Drive physical Android devices over USB (#67)

2026-06-11 10:10:05 +05:30

bundler

llm action-selection backend (#68)

2026-07-31 21:12:00 +05:30

driver

experiment instrumentation: step budgets, arm labels, campaign runner (#72)

2026-08-12 22:20:31 +05:30

hierarchy

llm action-selection backend (#68)

2026-07-31 21:12:00 +05:30

ios

Physical-device iOS support (#64) (#66)

2026-06-09 18:38:52 +05:30

llmclient

feat(llmclient): parse usage and the served model

2026-08-12 22:56:58 +05:30

ltl

experiment instrumentation: step budgets, arm labels, campaign runner (#72)

2026-08-12 22:20:31 +05:30

replay

iOS simulator driver: Go-native companion-backed backend (#62)

2026-06-08 19:10:54 +05:30

runner

experiment instrumentation: step budgets, arm labels, campaign runner (#72)

2026-08-12 22:20:31 +05:30

sidecarassets

experiment instrumentation: step budgets, arm labels, campaign runner (#72)

2026-08-12 22:20:31 +05:30

testrun

experiment instrumentation: step budgets, arm labels, campaign runner (#72)

2026-08-12 22:20:31 +05:30

trace

experiment instrumentation: step budgets, arm labels, campaign runner (#72)

2026-08-12 22:20:31 +05:30

verifier

fix ltl semantics and unify action enumeration (#71)

2026-08-12 18:06:04 +05:30