kami a788ca3915 Label eval runs with the model the server actually loaded (#379) ...

The phrasing eval printed "llm (0.8B, ...)" no matter which gguf
llama-server had loaded, so two runs of two different models came out
named the same and were easy to mix up when comparing.

It now asks llama-server over /v1/models, same as the router eval
already did. The helper moved to internal/llm so both share it, and it
now errors instead of returning a blank name when the id field is
missing — an unreachable server gets labelled "unknown-model", never a
plausible-looking guess.

Both eval paths stay opt-in behind MAVEN_LLM_URL; no server needed for
go test.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ

2026-07-31 14:25:28 +04:00

..

eval_test.go

Swap the embedder to multilingual-e5-small (Vikunja #371, #372)

2026-07-31 11:38:18 +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

Label eval runs with the model the server actually loaded (#379)

2026-07-31 14:25:28 +04:00

ru_routing_v1.json

Give the router prompt a rule for clock and calendar questions (#374)

2026-07-31 13:52:00 +04:00