sift/internal/api/search_test.go

package api

import (
	"bytes"
	"encoding/json"
	"log/slog"
	"net/http"
	"net/http/httptest"
	"os"
	"path/filepath"
	"strings"
	"testing"
	"time"

	"git.wntrmute.dev/kyle/sift/internal/auth"
	"git.wntrmute.dev/kyle/sift/internal/dcache"
	"git.wntrmute.dev/kyle/sift/internal/fetch"
	"git.wntrmute.dev/kyle/sift/internal/guard"
	"git.wntrmute.dev/kyle/sift/internal/search"
	"git.wntrmute.dev/kyle/sift/internal/search/dial"
)

func searchServer(t *testing.T) (*Server, string, string, *recHandler, *httptest.Server) {
	t.Helper()
	dir := t.TempDir()
	keys := filepath.Join(dir, "keys.toml")
	fleetOut := filepath.Join(dir, "fleet")
	gsOut := filepath.Join(dir, "gs")
	if err := auth.Add(keys, "test", "hermes-fleet", fleetOut); err != nil {
		t.Fatal(err)
	}
	if err := auth.Add(keys, "straylight-gs", "guardian-star", gsOut); err != nil {
		t.Fatal(err)
	}
	fleetKey, _ := os.ReadFile(fleetOut)
	gsKey, _ := os.ReadFile(gsOut)
	store, err := auth.Load(keys)
	if err != nil {
		t.Fatal(err)
	}
	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		if strings.Contains(r.URL.Path, "search") {
			_, _ = w.Write([]byte(`{"results":[{"url":"https://example.com/hit","title":"Hit","content":"snippet about q","score":1}]}`))
			return
		}
		w.WriteHeader(404)
	}))
	t.Cleanup(ts.Close)
	c, err := dial.New(ts.URL, dial.Options{Loopback: true, Timeout: time.Second})
	if err != nil {
		t.Fatal(err)
	}
	db, err := dcache.Open(filepath.Join(dir, "c.db"), 1<<20, nil)
	if err != nil {
		t.Fatal(err)
	}
	t.Cleanup(func() { _ = db.Close() })
	h := &recHandler{}
	s := New("test", &guard.Guard{}, &fetch.Fetcher{Guard: &guard.Guard{}, UA: "sift-test"}, store, slog.New(h))
	s.PermitRestricted = []string{"straylight-gs"}
	s.Search = &search.Engine{
		Sources:  []search.Source{&search.SearxNG{Client: c}},
		DefaultK: 8,
		RerankOn: false,
		Cache:    db,
	}
	return s, strings.TrimSpace(string(fleetKey)), strings.TrimSpace(string(gsKey)), h, ts
}

func TestV2SearchGolden(t *testing.T) {
	s, key, _, _, _ := searchServer(t)
	rec := postJSON(t, s, "/v2/search", key, map[string]any{"query": "contract", "limit": 3, "url": "http://127.0.0.1:11434"})
	if rec.Code != 200 {
		t.Fatalf("%d %s", rec.Code, rec.Body.String())
	}
	var env map[string]any
	if err := json.Unmarshal(rec.Body.Bytes(), &env); err != nil {
		t.Fatal(err)
	}
	if env["success"] != true {
		t.Fatalf("%v", env)
	}
	data, _ := env["data"].(map[string]any)
	web, _ := data["web"].([]any)
	if len(web) < 1 {
		t.Fatalf("web %v", env)
	}
	row, _ := web[0].(map[string]any)
	if row["url"] == "" || row["title"] == "" || row["description"] == nil {
		t.Fatalf("%v", row)
	}
}

func TestSearchCachePartitionAndRestrictedLogs(t *testing.T) {
	s, fleet, gs, h, _ := searchServer(t)
	rec := postJSON(t, s, "/v1/search", gs, map[string]any{"query": "secret topic", "k": 5, "rerank": false})
	if rec.Code != 200 {
		t.Fatalf("gs %d %s", rec.Code, rec.Body.String())
	}
	rec = postJSON(t, s, "/v1/search", fleet, map[string]any{"query": "secret topic", "k": 5, "rerank": false})
	if rec.Code != 200 {
		t.Fatalf("fleet %d %s", rec.Code, rec.Body.String())
	}
	var env map[string]any
	if err := json.Unmarshal(rec.Body.Bytes(), &env); err != nil {
		t.Fatal(err)
	}
	if env["cached"] == true {
		t.Fatal("fleet observed restricted cache")
	}
	dump := h.dump()
	if strings.Contains(dump, "secret topic") || strings.Contains(dump, "example.com") || strings.Contains(dump, "127.0.0.1") {
		t.Fatalf("restricted log leak:\n%s", dump)
	}
}

func TestSearchInvalidQuery(t *testing.T) {
	s, key, _, _, _ := searchServer(t)
	rec := postJSON(t, s, "/v1/search", key, map[string]any{"query": ""})
	if rec.Code != 400 {
		t.Fatalf("%d", rec.Code)
	}
}

func TestHealthzMissingKey(t *testing.T) {
	s, _ := setupAPI(t, nil)
	s.Search = &search.Engine{Degraded: []string{"search.tavily: missing key"}}
	req := httptest.NewRequest(http.MethodGet, "/healthz", nil)
	rec := httptest.NewRecorder()
	s.ServeHTTP(rec, req)
	if rec.Code != 200 || !strings.Contains(rec.Body.String(), "missing key") {
		t.Fatalf("%s", rec.Body.String())
	}
}

func TestNoSearchResults422(t *testing.T) {
	s, key := setupAPI(t, nil)
	s.Search = &search.Engine{DefaultK: 8}
	rec := postJSON(t, s, "/v1/search", key, map[string]any{"query": "none"})
	if rec.Code != 422 {
		t.Fatalf("%d %s", rec.Code, rec.Body.String())
	}
}

func (h *recHandler) dump() string {
	h.mu.Lock()
	defer h.mu.Unlock()
	var b bytes.Buffer
	for _, r := range h.recs {
		b.WriteString(recMsg(r))
		r.Attrs(func(a slog.Attr) bool {
			b.WriteByte(' ')
			b.WriteString(a.Key)
			b.WriteByte('=')
			b.WriteString(a.Value.String())
			return true
		})
		b.WriteByte('\n')
	}
	return b.String()
}