kyle
d7873403ff
POST /v1/search and /v2/search fan in SearXNG, Brave LLM Context, and Tavily from config-fixed endpoints. Public sources refuse private A records; SearXNG is a loopback-only client, not the fetch guard. Cache keys include caller class. Restricted callers search like the fleet; logs omit query, hosts, URLs, and upstream errors. Degraded results are not stored. Tavily sends search_depth=basic and drops answer. Missing keys surface in /healthz. Default-on sources stay off until the bake-off. Query harvest is not in this commit.
98 lines
3.0 KiB
Go
98 lines
3.0 KiB
Go
package search
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
|
|
"git.wntrmute.dev/kyle/sift/internal/search/dial"
|
|
)
|
|
|
|
func TestTavilyOutboundAndDropsAnswer(t *testing.T) {
|
|
var gotBody []byte
|
|
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
if r.Method != http.MethodPost {
|
|
t.Errorf("method %s", r.Method)
|
|
}
|
|
if !strings.HasPrefix(r.Header.Get("Authorization"), "Bearer ") {
|
|
t.Error("missing bearer")
|
|
}
|
|
gotBody, _ = io.ReadAll(r.Body)
|
|
_, _ = w.Write([]byte(`{"answer":"SECRET","results":[{"url":"https://ex.com/a","title":"A","content":"snip","score":0.9}],"usage":{"credits":1}}`))
|
|
}))
|
|
defer ts.Close()
|
|
c, err := dial.New(ts.URL, dial.Options{Loopback: true, Timeout: time.Second})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
out := (&Tavily{Client: c, Key: "test-key"}).Search(context.Background(), "q", 5)
|
|
if out.Warn != "" {
|
|
t.Fatal(out.Warn)
|
|
}
|
|
var req tavilyReq
|
|
if err := json.Unmarshal(gotBody, &req); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if req.IncludeAnswer || req.IncludeRawContent || req.IncludeImages || req.SearchDepth != "basic" {
|
|
t.Fatalf("%+v", req)
|
|
}
|
|
if strings.Contains(string(gotBody), "extract") || strings.Contains(string(gotBody), "crawl") {
|
|
t.Fatal(string(gotBody))
|
|
}
|
|
if len(out.Hits) != 1 || out.Hits[0].URL != "https://ex.com/a" {
|
|
t.Fatalf("%+v", out.Hits)
|
|
}
|
|
for _, h := range out.Hits {
|
|
if strings.Contains(h.Snippet, "SECRET") || strings.Contains(h.Title, "SECRET") {
|
|
t.Fatal("answer leaked into hit")
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestSearxNGMapsAndSorts(t *testing.T) {
|
|
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
if r.URL.Path != "/search" || r.URL.Query().Get("format") != "json" {
|
|
t.Errorf("path %s", r.URL.String())
|
|
}
|
|
_, _ = w.Write([]byte(`{"results":[
|
|
{"url":"https://b.example/","title":"b","content":"bb","score":0.1},
|
|
{"url":"https://a.example/","title":"a","content":"aa","score":0.9}
|
|
]}`))
|
|
}))
|
|
defer ts.Close()
|
|
c, err := dial.New(ts.URL, dial.Options{Loopback: true, Timeout: time.Second})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
out := (&SearxNG{Client: c}).Search(context.Background(), "q", 8)
|
|
if out.Warn != "" || len(out.Hits) != 2 || out.Hits[0].Title != "a" {
|
|
t.Fatalf("%+v", out)
|
|
}
|
|
}
|
|
|
|
func TestBraveMapsSources(t *testing.T) {
|
|
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
if r.Header.Get("X-Subscription-Token") == "" {
|
|
t.Error("token")
|
|
}
|
|
_, _ = w.Write([]byte(`{"grounding":"ignore me","sources":[{"url":"https://s.example/x","title":"S","snippet":"hello"}]}`))
|
|
}))
|
|
defer ts.Close()
|
|
c, err := dial.New(ts.URL, dial.Options{Loopback: true, Timeout: time.Second})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
out := (&BraveLLM{Client: c, Key: "k"}).Search(context.Background(), "q", 5)
|
|
if len(out.Hits) != 1 || out.Hits[0].URL != "https://s.example/x" {
|
|
t.Fatalf("%+v", out)
|
|
}
|
|
if strings.Contains(out.Hits[0].Snippet, "ignore") {
|
|
t.Fatal("grounding used as snippet")
|
|
}
|
|
}
|