 Colby McHenry
|
04c0f8eab5
test(agent-eval): sum tokens per turn — result.usage stopped being cumulative
|
пре 1 месец |
|
Colby McHenry
|
3e8922dfad
test(agent-eval): report all three feedback metrics per arm, side by side (CG-11)
|
пре 1 месец |
|
Colby McHenry
|
db3b8d2a1e
test(agent-eval): report what share of explore's bytes the answer used (CG-9)
|
пре 1 месец |
|
Colby McHenry
|
a2a916e1a5
test(agent-eval): bucket every explore by what the agent did next (CG-8)
|
пре 1 месец |
|
Colby McHenry
|
52b194a6be
merge main into CG-3: keep the envelope view alongside occupancy
|
пре 1 месец |
|
Colby McHenry
|
1d333017a8
test(agent-eval): count blocked CLI attempts apart from real contamination (CG-7)
|
пре 1 месец |
|
Colby McHenry
|
e35d4861e0
test(agent-eval): block the codegraph CLI outright — hiding it from PATH was not enough (CG-7)
|
пре 1 месец |
|
Colby McHenry
|
d3c01ce8ed
test(agent-eval): stop the arms reaching codegraph through the shell (CG-7)
|
пре 1 месец |
|
Colby McHenry
|
b93c8d2b6c
test(agent-eval): self-test the occupancy math, and fix ratio calibration under shedding (CG-7)
|
пре 1 месец |
|
Colby McHenry
|
4d5f8d371a
test(agent-eval): report the occupancy metric's own error bar (CG-7)
|
пре 1 месец |
|
Colby McHenry
|
9b4df2133b
test(agent-eval): price codegraph's fixed context cost alongside its residual (CG-7)
|
пре 1 месец |
|
Colby McHenry
|
4080b7501e
test(agent-eval): measure residual context occupancy, over multi-turn sessions (CG-7)
|
пре 1 месец |
|
Colby McHenry
|
48a2309b92
test(agent-eval): RUNS knob + explore envelope-share view for new-vs-baseline A/B (CG-15)
|
пре 1 месец |
|
Colby McHenry
|
7fe64b32be
feat(eval): add agent-eval harness and /audit + /publish Claude skills
|
пре 3 месеци |
