 Colby McHenry
|
be7c968439
docs(benchmarks): record the CG-31 A/B — no regression, four repos stop truncating
|
vor 1 Monat |
|
Colby McHenry
|
f1fecb8232
fix(explore): fund the guard from room that exists, and cut the epilogue first (CG-31)
|
vor 1 Monat |
|
Colby McHenry
|
089dcc276f
fix(explore): hold back what is still owed below a clustered render (CG-31)
|
vor 1 Monat |
|
Colby McHenry
|
0d014a6582
docs(benchmarks): record the CG-30 A/B — deterministic win, no behavioural regression
|
vor 1 Monat |
|
Colby McHenry
|
cd1ea27ea8
fix(explore): restore the CG-30 bound d652c14 reverted
|
vor 1 Monat |
|
Colby McHenry
|
d652c148f6
docs(cg-30): changelog entry + record the self-query probe flip honestly
|
vor 1 Monat |
|
Colby McHenry
|
765c06aa40
fix(explore): bound how far an oversize cluster member may overshoot (CG-30)
|
vor 1 Monat |
|
Colby McHenry
|
d6d17288be
docs(benchmarks): re-derive the token figures the result.usage bug touched
|
vor 1 Monat |
|
Colby McHenry
|
da1f6121fd
docs(readme): benchmark table from the corrected 2026-08-05 re-measure
|
vor 1 Monat |
|
Colby McHenry
|
04c0f8eab5
test(agent-eval): sum tokens per turn — result.usage stopped being cumulative
|
vor 1 Monat |
|
Colby McHenry
|
a7db24d0c0
docs(readme): disclose the context-footprint side of the benchmark
|
vor 1 Monat |
|
Colby McHenry
|
48cbc21a17
merge: cross-call explore session dedup (CG-2, #1500)
|
vor 1 Monat |
|
Colby McHenry
|
2cfd321b23
docs: CG-20 — the dedup gate, three bars pass and the fourth cannot (CG-2)
|
vor 1 Monat |
|
Colby McHenry
|
7a7ea30cbd
docs: cross-call dedup — its gates, where the bytes go, and the all-pointer guard (CG-18)
|
vor 1 Monat |
|
Colby McHenry
|
ab38d1f090
feat(explore): point at source this session already sent, don't send it twice (CG-18)
|
vor 1 Monat |
|
Colby McHenry
|
4e94860f8f
docs: the session-state layer — its four constraints and which way to be wrong (CG-17)
|
vor 1 Monat |
|
Colby McHenry
|
fc31b1e2bf
feat(mcp): remember what explore already served this session (CG-17)
|
vor 1 Monat |
|
Colby McHenry
|
5dd4db68cd
docs: the occupancy baseline says our residual is higher — write that down (CG-13)
|
vor 1 Monat |
|
Colby McHenry
|
520ed9d933
test(agent-eval): report residual direction by sign, not by hope (CG-13)
|
vor 1 Monat |
|
Colby McHenry
|
382791f11e
docs: one entry point for the three feedback metrics, and how to run them (CG-11)
|
vor 1 Monat |
|
Colby McHenry
|
3e8922dfad
test(agent-eval): report all three feedback metrics per arm, side by side (CG-11)
|
vor 1 Monat |
|
Colby McHenry
|
fa15d1046a
docs: allocation efficiency — the metric, its guards, and the 103-run baseline (CG-9)
|
vor 1 Monat |
|
Colby McHenry
|
db3b8d2a1e
test(agent-eval): report what share of explore's bytes the answer used (CG-9)
|
vor 1 Monat |
|
Colby McHenry
|
254e573f11
docs: the 7-repo bucket baseline, and the recall case by hand (CG-8)
|
vor 1 Monat |
|
Colby McHenry
|
945e52f4ee
docs: explore sufficiency -- the metric, its rules, what it caught (CG-8)
|
vor 1 Monat |
|
Colby McHenry
|
a2a916e1a5
test(agent-eval): bucket every explore by what the agent did next (CG-8)
|
vor 1 Monat |
|
Colby McHenry
|
52b194a6be
merge main into CG-3: keep the envelope view alongside occupancy
|
vor 1 Monat |
|
Colby McHenry
|
1d333017a8
test(agent-eval): count blocked CLI attempts apart from real contamination (CG-7)
|
vor 1 Monat |
|
Colby McHenry
|
e35d4861e0
test(agent-eval): block the codegraph CLI outright — hiding it from PATH was not enough (CG-7)
|
vor 1 Monat |
|
Colby McHenry
|
d3c01ce8ed
test(agent-eval): stop the arms reaching codegraph through the shell (CG-7)
|
vor 1 Monat |
