 Colby McHenry
|
a7db24d0c0
docs(readme): disclose the context-footprint side of the benchmark
|
1 månad sedan |
|
Colby McHenry
|
48cbc21a17
merge: cross-call explore session dedup (CG-2, #1500)
|
1 månad sedan |
|
Colby McHenry
|
2cfd321b23
docs: CG-20 — the dedup gate, three bars pass and the fourth cannot (CG-2)
|
1 månad sedan |
|
Colby McHenry
|
7a7ea30cbd
docs: cross-call dedup — its gates, where the bytes go, and the all-pointer guard (CG-18)
|
1 månad sedan |
|
Colby McHenry
|
ab38d1f090
feat(explore): point at source this session already sent, don't send it twice (CG-18)
|
1 månad sedan |
|
Colby McHenry
|
4e94860f8f
docs: the session-state layer — its four constraints and which way to be wrong (CG-17)
|
1 månad sedan |
|
Colby McHenry
|
fc31b1e2bf
feat(mcp): remember what explore already served this session (CG-17)
|
1 månad sedan |
|
Colby McHenry
|
5dd4db68cd
docs: the occupancy baseline says our residual is higher — write that down (CG-13)
|
1 månad sedan |
|
Colby McHenry
|
520ed9d933
test(agent-eval): report residual direction by sign, not by hope (CG-13)
|
1 månad sedan |
|
Colby McHenry
|
382791f11e
docs: one entry point for the three feedback metrics, and how to run them (CG-11)
|
1 månad sedan |
|
Colby McHenry
|
3e8922dfad
test(agent-eval): report all three feedback metrics per arm, side by side (CG-11)
|
1 månad sedan |
|
Colby McHenry
|
fa15d1046a
docs: allocation efficiency — the metric, its guards, and the 103-run baseline (CG-9)
|
1 månad sedan |
|
Colby McHenry
|
db3b8d2a1e
test(agent-eval): report what share of explore's bytes the answer used (CG-9)
|
1 månad sedan |
|
Colby McHenry
|
254e573f11
docs: the 7-repo bucket baseline, and the recall case by hand (CG-8)
|
1 månad sedan |
|
Colby McHenry
|
945e52f4ee
docs: explore sufficiency -- the metric, its rules, what it caught (CG-8)
|
1 månad sedan |
|
Colby McHenry
|
a2a916e1a5
test(agent-eval): bucket every explore by what the agent did next (CG-8)
|
1 månad sedan |
|
Colby McHenry
|
52b194a6be
merge main into CG-3: keep the envelope view alongside occupancy
|
1 månad sedan |
|
Colby McHenry
|
1d333017a8
test(agent-eval): count blocked CLI attempts apart from real contamination (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
e35d4861e0
test(agent-eval): block the codegraph CLI outright — hiding it from PATH was not enough (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
d3c01ce8ed
test(agent-eval): stop the arms reaching codegraph through the shell (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
257a7b7327
test(agent-eval): RUN_FROM, to extend a pass without redoing finished runs (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
af3ce390da
test(agent-eval): drop the duplicated fixed-overhead line (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
77845c747d
test(agent-eval): show every run's residual and tool mix, not just the median (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
b93c8d2b6c
test(agent-eval): self-test the occupancy math, and fix ratio calibration under shedding (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
4d5f8d371a
test(agent-eval): report the occupancy metric's own error bar (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
9b4df2133b
test(agent-eval): price codegraph's fixed context cost alongside its residual (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
4080b7501e
test(agent-eval): measure residual context occupancy, over multi-turn sessions (CG-7)
|
1 månad sedan |
|
Colby McHenry
|
c65d56ceba
docs: CG-22 — the epic's gate, re-run at CG-15's exact setup (#1500)
|
1 månad sedan |
|
Colby McHenry
|
abee46c5e4
docs: CG-21 A/B — the gate passes, all four bars (#1500)
|
1 månad sedan |
|
Colby McHenry
|
fca7d87047
fix(explore): a funded whole-file buy must also fit the render ceiling (CG-21)
|
1 månad sedan |
