| .. |
|
ab-adoption.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
vor 2 Monaten |
|
ab-hook.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
vor 2 Monaten |
|
ab-impl.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
vor 2 Monaten |
|
ab-new-vs-baseline.sh
|
3e8922dfad
test(agent-eval): report all three feedback metrics per arm, side by side (CG-11)
|
vor 1 Monat |
|
ab-sufficiency.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
vor 2 Monaten |
|
allocation-fixtures.json
|
eed16447c3
fix(explore): shrink a later cluster into the remainder instead of dropping it (CG-36)
|
vor 4 Wochen |
|
arms-F.sh
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
arms-matrix.sh
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
audit.sh
|
7fe64b32be
feat(eval): add agent-eval harness and /audit + /publish Claude skills
|
vor 3 Monaten |
|
bench-readme.sh
|
257a7b7327
test(agent-eval): RUN_FROM, to extend a pass without redoing finished runs (CG-7)
|
vor 1 Monat |
|
bench-why-repo.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
vor 2 Monaten |
|
block-read-hook.sh
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
compare-arms.mjs
|
3e8922dfad
test(agent-eval): report all three feedback metrics per arm, side by side (CG-11)
|
vor 1 Monat |
|
diff-index-drift.mjs
|
2cf63fd114
CG-33: record index-drift measurement and add a drift diff tool
|
vor 1 Monat |
|
hook-settings.json
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
itrun.sh
|
f58de8a391
feat(resolution): gin middleware-chain synthesizer + Opus 4.8 benchmark refresh (#547)
|
vor 3 Monaten |
|
no-cli-shim.sh
|
3e8922dfad
test(agent-eval): report all three feedback metrics per arm, side by side (CG-11)
|
vor 1 Monat |
|
offload-eval-3arm.sh
|
4f8782cbe5
test(agent-eval): add output-style A/B harness, cost/token analyzer, and DISALLOW/REP_START controls
|
vor 2 Monaten |
|
offload-eval-cost.mjs
|
4f8782cbe5
test(agent-eval): add output-style A/B harness, cost/token analyzer, and DISALLOW/REP_START controls
|
vor 2 Monaten |
|
offload-eval-effort.mjs
|
f82a662ddb
feat(mcp): pare default tool surface to codegraph_explore alone + redux-thunk synthesizer
|
vor 2 Monaten |
|
offload-eval-frontload-matrix.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval-frontload.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval-ground-truth.json
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval-hook.mjs
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval-judge.mjs
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval-matrix.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval-metrics.mjs
|
3e1547bbe1
fix(mcp): bold labels instead of ATX headings in tool results (#778) (#951)
|
vor 2 Monaten |
|
offload-eval-refs1.sh
|
f82a662ddb
feat(mcp): pare default tool surface to codegraph_explore alone + redux-thunk synthesizer
|
vor 2 Monaten |
|
offload-eval-setup.sh
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval-styles.sh
|
4f8782cbe5
test(agent-eval): add output-style A/B harness, cost/token analyzer, and DISALLOW/REP_START controls
|
vor 2 Monaten |
|
offload-eval-summarize.mjs
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
offload-eval.md
|
7ddd3fa7eb
test(agent-eval): persist offload accuracy/adoption eval harness + front-load hook
|
vor 2 Monaten |
|
parse-arms.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
parse-bench-readme.mjs
|
520ed9d933
test(agent-eval): report residual direction by sign, not by hope (CG-13)
|
vor 1 Monat |
|
parse-run.mjs
|
04c0f8eab5
test(agent-eval): sum tokens per turn — result.usage stopped being cumulative
|
vor 1 Monat |
|
parse-session.mjs
|
db3b8d2a1e
test(agent-eval): report what share of explore's bytes the answer used (CG-9)
|
vor 1 Monat |
|
probe-allocation.mjs
|
eed16447c3
fix(explore): shrink a later cluster into the remainder instead of dropping it (CG-36)
|
vor 4 Wochen |
|
probe-context.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
probe-decl-only.mjs
|
9efae0f8f2
fix(explore): damp ambient declaration files on flow queries (CG-28)
|
vor 4 Wochen |
|
probe-explore.mjs
|
3e1547bbe1
fix(mcp): bold labels instead of ATX headings in tool results (#778) (#951)
|
vor 2 Monaten |
|
probe-factory-closure.mjs
|
91cb5b4317
measure(explore): the factory-closure envelope premise does not hold (CG-27)
|
vor 4 Wochen |
|
probe-file-spend.mjs
|
eed16447c3
fix(explore): shrink a later cluster into the remainder instead of dropping it (CG-36)
|
vor 4 Wochen |
|
probe-named-symbol.mjs
|
89c53ddf24
fix(explore): guarantee an agent-named symbol renders, wherever it sits (CG-38)
|
vor 4 Wochen |
|
probe-node.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
probe-suite-envelope.mjs
|
7cbde95ce2
fix(explore): pay every admitted file on every render path (CG-26)
|
vor 1 Monat |
|
probe-sweep.mjs
|
71935e37c2
feat(mcp): multi-module Go trace-quality + small-repo retrieval tuning (#494)
|
vor 3 Monaten |
|
probe-trace.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
|
redirect-read-hook.sh
|
1983590533
feat(mcp): codegraph_node reads files like the Read tool — offset/limit, byte-parity (#738)
|
vor 2 Monaten |
|
repro-concurrent-explore.mjs
|
dfe13b03c8
feat(mcp): off-load read-tool dispatch to a worker pool to fix concurrent-call timeouts (#1002)
|
vor 2 Monaten |
|
repro-daemon-clients.mjs
|
dfe13b03c8
feat(mcp): off-load read-tool dispatch to a worker pool to fix concurrent-call timeouts (#1002)
|
vor 2 Monaten |
|
run-agent.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
vor 2 Monaten |
|
run-all.sh
|
3e8922dfad
test(agent-eval): report all three feedback metrics per arm, side by side (CG-11)
|
vor 1 Monat |
|
run-arms.sh
|
0682681175
chore(agent-eval): standing A/B model policy — sonnet + high effort, never Opus/Fable (#816)
|
vor 2 Monaten |
|
seq-matrix.mjs
|
025ebc88d6
Release 0.9.4: framework-aware routing + dynamic-dispatch coverage + retrieval improvements (#365)
|
vor 3 Monaten |
Colby Mchenry