 zhenyu.hu
|
f2ebc9932a
docs: plan benchmark ledger identity fixes
|
il y a 2 semaines |
|
zhenyu.hu
|
217db98974
fix: enforce benchmark visible ttft and call counts
|
il y a 2 semaines |
|
zhenyu.hu
|
58ede87cb6
docs: plan benchmark visible ttft call count fixes
|
il y a 2 semaines |
|
zhenyu.hu
|
11210a94bc
feat: run isolated agent benchmarks
|
il y a 2 semaines |
|
zhenyu.hu
|
9464c41c94
docs: close benchmark configuration follow-ups
|
il y a 2 semaines |
|
zhenyu.hu
|
f7fd343f74
refactor: unify benchmark case and mode ids
|
il y a 2 semaines |
|
zhenyu.hu
|
9ed4d56ceb
docs: plan benchmark case mode single source
|
il y a 2 semaines |
|
zhenyu.hu
|
a5569f70bc
fix: validate benchmark urls with httpx
|
il y a 2 semaines |
|
zhenyu.hu
|
5ceda5ddc1
docs: plan benchmark url transport validation
|
il y a 2 semaines |
|
zhenyu.hu
|
bd36806189
fix: reject benchmark url control characters
|
il y a 2 semaines |
|
zhenyu.hu
|
d903ccc054
docs: plan strict benchmark url validation
|
il y a 2 semaines |
|
zhenyu.hu
|
5735985a46
feat: add benchmark case catalog
|
il y a 2 semaines |
|
zhenyu.hu
|
ebebc5d6a7
docs: design agent benchmark runner
|
il y a 2 semaines |
|
zhenyu.hu
|
c13599b4b9
docs: close invocation comparison experiment
|
il y a 2 semaines |
|
zhenyu.hu
|
368d918f8e
test: enforce first reply and protocol parity
|
il y a 2 semaines |
|
zhenyu.hu
|
b8476ae05d
docs: plan first reply protocol matrix fixes
|
il y a 2 semaines |
|
zhenyu.hu
|
97a98a9e8b
test: add invocation mode comparison matrix
|
il y a 2 semaines |
|
zhenyu.hu
|
a51b2a7f21
docs: document invocation comparison experiment
|
il y a 2 semaines |
|
zhenyu.hu
|
0c62819b9c
docs: plan invocation comparison closeout
|
il y a 2 semaines |
|
zhenyu.hu
|
3f441335c4
docs: close comparable metrics todos
|
il y a 2 semaines |
|
zhenyu.hu
|
1d5f65f582
fix: deduplicate metric keys during migration
|
il y a 2 semaines |
|
zhenyu.hu
|
44256c611f
docs: plan metric key migration dedup
|
il y a 2 semaines |
|
zhenyu.hu
|
38d674ef48
feat: add comparable invocation metrics
|
il y a 2 semaines |
|
zhenyu.hu
|
9c15337c6b
docs: plan comparable invocation metrics
|
il y a 2 semaines |
|
zhenyu.hu
|
250387d468
docs: close tool mode session restore todos
|
il y a 2 semaines |
|
zhenyu.hu
|
ac526139d2
fix: reject stale replay before token advance
|
il y a 2 semaines |
|
zhenyu.hu
|
275dcae097
docs: plan stale replay token fix
|
il y a 2 semaines |
|
zhenyu.hu
|
792dcb5b29
fix: guard session replay restoration
|
il y a 2 semaines |
|
zhenyu.hu
|
9894aab5a2
docs: plan session restore race fixes
|
il y a 2 semaines |
|
zhenyu.hu
|
342a96c520
fix: make session transcript restoration atomic
|
il y a 2 semaines |
