| .. |
|
ab-adoption.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
ab-hook.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
ab-impl.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
ab-new-vs-baseline.sh
|
df6f4bec43
feat(explore): dynamic-dispatch boundary surfacing — announce where a flow ends instead of guessing edges (#687) (#835)
|
il y a 1 semaine |
|
ab-sufficiency.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
arms-F.sh
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
arms-matrix.sh
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
audit.sh
|
7fe64b32be
feat(eval): add agent-eval harness and /audit + /publish Claude skills
|
il y a 1 mois |
|
bench-readme.sh
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
bench-why-repo.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
block-read-hook.sh
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
hook-settings.json
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
itrun.sh
|
f58de8a391
feat(resolution): gin middleware-chain synthesizer + Opus 4.8 benchmark refresh (#547)
|
il y a 3 semaines |
|
offload-eval-3arm.sh
|
4f8782cbe5
test(agent-eval): add output-style A/B harness, cost/token analyzer, and DISALLOW/REP_START controls
|
il y a 3 jours |
|
offload-eval-cost.mjs
|
4f8782cbe5
test(agent-eval): add output-style A/B harness, cost/token analyzer, and DISALLOW/REP_START controls
|
il y a 3 jours |
|
offload-eval-effort.mjs
|
f82a662ddb
feat(mcp): pare default tool surface to codegraph_explore alone + redux-thunk synthesizer
|
il y a 4 jours |
|
offload-eval-frontload-matrix.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval-frontload.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval-ground-truth.json
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval-hook.mjs
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval-judge.mjs
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval-matrix.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval-metrics.mjs
|
f82a662ddb
feat(mcp): pare default tool surface to codegraph_explore alone + redux-thunk synthesizer
|
il y a 4 jours |
|
offload-eval-refs1.sh
|
f82a662ddb
feat(mcp): pare default tool surface to codegraph_explore alone + redux-thunk synthesizer
|
il y a 4 jours |
|
offload-eval-setup.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval-styles.sh
|
4f8782cbe5
test(agent-eval): add output-style A/B harness, cost/token analyzer, and DISALLOW/REP_START controls
|
il y a 3 jours |
|
offload-eval-summarize.mjs
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
offload-eval.md
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
il y a 4 jours |
|
parse-arms.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
parse-bench-readme.mjs
|
3a1ddf41cd
feat(mcp): trace relevance + closure-collection + god-file rendering + cold-start handshake (#580)
|
il y a 3 semaines |
|
parse-run.mjs
|
7fe64b32be
feat(eval): add agent-eval harness and /audit + /publish Claude skills
|
il y a 1 mois |
|
parse-session.mjs
|
7fe64b32be
feat(eval): add agent-eval harness and /audit + /publish Claude skills
|
il y a 1 mois |
|
probe-context.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
probe-explore.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
probe-node.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
probe-sweep.mjs
|
71935e37c2
feat(mcp): multi-module Go trace-quality + small-repo retrieval tuning (#494)
|
il y a 3 semaines |
|
probe-trace.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
|
redirect-read-hook.sh
|
1983590533
feat(mcp): codegraph_node reads files like the Read tool — offset/limit, byte-parity (#738)
|
il y a 2 semaines |
|
run-agent.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
run-all.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
run-arms.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
il y a 1 semaine |
|
seq-matrix.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
il y a 1 mois |
Colby McHenry
4f8782cbe5
test(agent-eval): add output-style A/B harness, cost/token analyzer, and DISALLOW/REP_START controls