claude 80ac7579fb eval: score the reach fixture on both embedders (V-405) ...

TestReachDerivation pins the gate order the scorer depends on, so a change to
actions_act.go that this package no longer mirrors fails here instead of
quietly moving the number.

The hash baseline asserts overreach and nothing else. Accuracy on the hash
embedder measures the confidence gate, not reach. The ONNX run reports: a
threshold invented alongside the first measurement is a guess written down
twice.

2026-08-04 06:22:02 +04:00

..

eval_test.go

router: agenda questions belong to query, not to system

2026-08-01 22:53:01 +04:00

eval.go

Score the routing fixture with the ONNX embedder (Vikunja #319)

2026-07-31 00:34:29 +04:00

llmrouter_test.go

docs: tier the tree by lifetime, so staleness shows in the path (V-446)

2026-08-02 03:28:49 +04:00

reach_test.go

eval: score the reach fixture on both embedders (V-405)

2026-08-04 06:22:02 +04:00

reach.go

eval: derive and score which ecosystem service a turn reaches (V-405)

2026-08-04 06:22:02 +04:00

ru_ecosystem_v1.json

eval: add the held-out ecosystem reach fixture (V-405)

2026-08-04 06:21:40 +04:00

ru_routing_v1.json

router: stage 0 claims the task marker before the model renames it (V-467)

2026-08-04 03:12:47 +04:00