kami
a788ca3915
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
71 lines
2.3 KiB
Go
71 lines
2.3 KiB
Go
package llm
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// UnknownModel is the label to print when the server would not say what it has
|
|
// loaded. Deliberately ugly: an honest "unknown" is fine, a plausible-looking
|
|
// but wrong model name is the bug this whole file exists to prevent.
|
|
const UnknownModel = "unknown-model"
|
|
|
|
// llama-server is local, so never send this through a proxy: this box's
|
|
// http_proxy answers 503 for loopback, which would look like "server won't say
|
|
// which model it has" when the server is right there and fine.
|
|
// A Transport with no Proxy set bypasses http_proxy entirely.
|
|
var modelHTTP = &http.Client{Timeout: 10 * time.Second, Transport: &http.Transport{}}
|
|
|
|
// 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 := modelHTTP.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")
|
|
}
|
|
short := shortModelID(out.Data[0].ID)
|
|
if short == "" {
|
|
// Server answered but the id field was missing or blank. Say so
|
|
// instead of handing back an empty label that reads as a real name.
|
|
return "", fmt.Errorf("models: no id in response")
|
|
}
|
|
return short, 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 {
|
|
id = strings.TrimSpace(id)
|
|
if i := strings.LastIndexAny(id, "/\\"); i >= 0 {
|
|
id = id[i+1:]
|
|
}
|
|
return strings.TrimSpace(strings.TrimSuffix(id, ".gguf"))
|
|
}
|