Files
Maven/internal/router/eval/modelid.go
T
kami 94eb92fb15 Label LLM eval runs with the model llama-server has loaded
The bake-off in #278/#250 needs two models' scores side by side, and the
report names only carried the config, so the rows were indistinguishable.
ModelID reads /v1/models instead of taking a string that goes stale.
New target: make eval-models MAVEN_LLM_URL=...

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 02:17:20 +04:00

52 lines
1.4 KiB
Go

package eval
import (
"context"
"encoding/json"
"fmt"
"net/http"
"strings"
)
// ModelID asks llama-server which model it has loaded, so a scoring run can
// label itself. Without this a bake-off between two models produces two tables
// that look identical, and the operator has to remember which server was up.
//
// Read from the server rather than passed in on purpose: a hand-typed label
// goes stale the moment someone restarts the server with a different -m.
func ModelID(ctx context.Context, base string) (string, error) {
req, err := http.NewRequestWithContext(ctx, "GET", strings.TrimSuffix(base, "/")+"/v1/models", nil)
if err != nil {
return "", err
}
resp, err := http.DefaultClient.Do(req)
if err != nil {
return "", err
}
defer resp.Body.Close()
if resp.StatusCode != 200 {
return "", fmt.Errorf("models: status %d", resp.StatusCode)
}
var out struct {
Data []struct {
ID string `json:"id"`
} `json:"data"`
}
if err := json.NewDecoder(resp.Body).Decode(&out); err != nil {
return "", err
}
if len(out.Data) == 0 {
return "", fmt.Errorf("models: empty list")
}
return shortModelID(out.Data[0].ID), nil
}
// shortModelID trims the path and the .gguf suffix — llama-server reports the
// file name it was started with, which is too long for a table header.
func shortModelID(id string) string {
if i := strings.LastIndexAny(id, "/\\"); i >= 0 {
id = id[i+1:]
}
return strings.TrimSuffix(id, ".gguf")
}