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
88 lines
3.0 KiB
Go
88 lines
3.0 KiB
Go
package eval
|
|
|
|
import (
|
|
"context"
|
|
"os"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/kami/maven/internal/llm"
|
|
"github.com/kami/maven/internal/phraser"
|
|
)
|
|
|
|
// TestLLMPhrasingBaseline — the resident model wording real nudges. Opt-in,
|
|
// same shape as internal/router/eval's MAVEN_LLM_URL gate, because CI has no
|
|
// model and a phrasing run costs minutes on the CPU target.
|
|
//
|
|
// llama-server -m /mnt/hdd1/llms/qwen3.5/Qwen3.5-0.8B.Q4_K_M.gguf \
|
|
// --host 127.0.0.1 --port 18099 -c 2048 -ngl 99
|
|
// MAVEN_LLM_URL=http://127.0.0.1:18099 make eval-phrasing
|
|
//
|
|
// It reports and does not assert a quality bar. The numbers are the input to
|
|
// tuning the persona prompt; an assertion here would be the test inventing the
|
|
// bar rather than measuring against it. The one thing worth failing on is a
|
|
// harness fault — every case erroring means the run measured infrastructure.
|
|
func TestLLMPhrasingBaseline(t *testing.T) {
|
|
base := os.Getenv("MAVEN_LLM_URL")
|
|
if base == "" {
|
|
t.Skip("MAVEN_LLM_URL unset — point it at a running llama-server (see doc comment)")
|
|
}
|
|
// A local llama-server must not go through an HTTP proxy. This box proxies
|
|
// loopback through a SOCKS bridge that answers 503, which would score every
|
|
// case as a phrasing error and read as "the model cannot phrase".
|
|
noProxyLoopback(t)
|
|
|
|
ctx := context.Background()
|
|
f, err := Load()
|
|
if err != nil {
|
|
t.Fatalf("Load: %v", err)
|
|
}
|
|
|
|
cfg := phraser.DefaultConfig("")
|
|
// Generous: an unconstrained 0.8B can spend a minute thinking before it
|
|
// writes a word, and a timeout would be scored as a model failure.
|
|
cfg.Timeout = 5 * time.Minute
|
|
p := phraser.NewLLMPhraserAt(base, cfg)
|
|
defer p.Close()
|
|
|
|
// Label the run with whatever gguf the server actually has loaded. It used
|
|
// to say "0.8B" no matter what, so two runs of two different models came
|
|
// out named the same and were easy to mix up when comparing.
|
|
model, err := llm.ModelID(ctx, base)
|
|
if err != nil {
|
|
// An unlabelled score is still a score, but say so loudly — a made-up
|
|
// name in a bake-off table is worse than no name.
|
|
t.Logf("could not read model id from %s: %v — report will say %q", base, err, llm.UnknownModel)
|
|
model = llm.UnknownModel
|
|
}
|
|
t.Logf("scoring model %s at %s", model, base)
|
|
|
|
rep, err := Score(ctx, "llm ("+model+", built-in persona)", p, f)
|
|
if err != nil {
|
|
t.Fatalf("Score: %v", err)
|
|
}
|
|
t.Log("\n" + rep.String() + "\nmessages:\n" + rep.Messages() + "\nfailures:\n" + rep.Failures())
|
|
|
|
if rep.Errors == rep.Total {
|
|
t.Errorf("all %d cases errored — harness fault, not a measurement", rep.Total)
|
|
}
|
|
}
|
|
|
|
// noProxyLoopback appends the loopback host to no_proxy before any request, so
|
|
// http.ProxyFromEnvironment (which caches the environment on first use) sees it.
|
|
func noProxyLoopback(t *testing.T) {
|
|
t.Helper()
|
|
for _, key := range []string{"no_proxy", "NO_PROXY"} {
|
|
cur := os.Getenv(key)
|
|
if strings.Contains(cur, "127.0.0.1") {
|
|
continue
|
|
}
|
|
if cur == "" {
|
|
t.Setenv(key, "127.0.0.1,localhost")
|
|
continue
|
|
}
|
|
t.Setenv(key, cur+",127.0.0.1,localhost")
|
|
}
|
|
}
|