kami
14e98334ad
The offline encyclopedia was the only world source, and it reads what was true when the ZIM was built. A self-hosted SearXNG now asks first and Kiwix is the fallback for an empty result, an unreachable instance or no line out. Owner's ruling, 2026-08-02. internal/websearch is deliberately thin: no rewriter (SearXNG ranks through real engines, so the Russian question goes out as he asked it), no page fetch, no cache. It cannot read the store, so only the query string can leave the box. The personal boundary is unchanged and still sits above this source, so a question about him is never searched. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BFaeSbLMEVG5ey8tejU3y2
110 lines
3.7 KiB
Go
110 lines
3.7 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/kami/maven/internal/ipc"
|
|
"github.com/kami/maven/internal/router"
|
|
)
|
|
|
|
func TestIsPersonalQuery(t *testing.T) {
|
|
for _, s := range []string{
|
|
"во сколько у меня встреча",
|
|
"что у меня сегодня",
|
|
"когда мой следующий отпуск",
|
|
"где моя книга",
|
|
"сколько моих задач висит",
|
|
"when is my meeting",
|
|
"do i have anything today",
|
|
"did i take my vitamins",
|
|
} {
|
|
if !isPersonalQuery(s) {
|
|
t.Errorf("isPersonalQuery(%q) = false, want true", s)
|
|
}
|
|
}
|
|
for _, s := range []string{
|
|
// First person without possession. These are questions about the
|
|
// world that merely mention the asker, and refusing them would be the
|
|
// opposite mistake.
|
|
"как мне сварить борщ",
|
|
"что я могу посмотреть вечером",
|
|
"почему небо синее",
|
|
"столица франции",
|
|
"how do i boil an egg",
|
|
"",
|
|
} {
|
|
if isPersonalQuery(s) {
|
|
t.Errorf("isPersonalQuery(%q) = true, want false", s)
|
|
}
|
|
}
|
|
}
|
|
|
|
// kiwixTrapAPI stands in for the world. Nothing below the personal boundary
|
|
// should be consulted for a question about him, so the test asserts on the
|
|
// reply rather than on a call: reaching Kiwix or general knowledge produces a
|
|
// phrased answer, and refusing produces the honest one.
|
|
func personalHandler() *reactiveHandler {
|
|
return &reactiveHandler{
|
|
api: ipc.UnimplementedCoreAPI{},
|
|
now: func() time.Time { return contNow },
|
|
// No phraser and no kiwix wiring: if the walk gets past the personal
|
|
// source it reaches queryGeneral, which returns "не знаю." with a nil
|
|
// phraser — a different string from the one this guard produces, so
|
|
// the two cases stay distinguishable.
|
|
}
|
|
}
|
|
|
|
// The regression: "во сколько у меня встреча" reached Kiwix, Wikipedia matched
|
|
// an article on the 2015 CPISRA World Games, and the phraser reported it back
|
|
// as his meeting. Seen on the deployed daemon, 01-08-2026.
|
|
func TestPersonalQuestionIsNotSentToTheWorld(t *testing.T) {
|
|
h := personalHandler()
|
|
reply, ok := h.queryPersonal(context.Background(), &queryTurn{
|
|
dec: router.Decision{Intent: router.IntentQuery, Utterance: "во сколько у меня встреча"},
|
|
})
|
|
if !ok {
|
|
t.Fatal("queryPersonal passed on a question about him")
|
|
}
|
|
if reply == "" {
|
|
t.Fatal("empty reply")
|
|
}
|
|
}
|
|
|
|
func TestWorldQuestionsPassThroughTheBoundary(t *testing.T) {
|
|
h := personalHandler()
|
|
for _, u := range []string{"почему небо синее", "столица франции"} {
|
|
if _, ok := h.queryPersonal(context.Background(), &queryTurn{
|
|
dec: router.Decision{Intent: router.IntentQuery, Utterance: u},
|
|
}); ok {
|
|
t.Errorf("queryPersonal claimed %q, want it to pass to the encyclopedia", u)
|
|
}
|
|
}
|
|
}
|
|
|
|
// The boundary must sit above kiwix and general-knowledge and below every
|
|
// source that reads his own data. Asserted on the table itself: an ordering
|
|
// bug here is silent, because both arrangements answer, just from the wrong
|
|
// place.
|
|
func TestPersonalBoundarySitsBetweenHisDataAndTheWorld(t *testing.T) {
|
|
idx := map[string]int{}
|
|
for i, s := range querySources {
|
|
idx[s.name] = i
|
|
}
|
|
boundary, ok := idx["personal"]
|
|
if !ok {
|
|
t.Fatal("no personal source in the chain")
|
|
}
|
|
for _, his := range []string{"fact-by-key", "day-plan", "tasks", "calendar", "memory", "notes"} {
|
|
if i, ok := idx[his]; !ok || i > boundary {
|
|
t.Errorf("%q reads his own data and must run before the personal boundary", his)
|
|
}
|
|
}
|
|
for _, world := range []string{"search", "kiwix", "web", "general-knowledge"} {
|
|
if i, ok := idx[world]; !ok || i < boundary {
|
|
t.Errorf("%q reads the world and must run after the personal boundary", world)
|
|
}
|
|
}
|
|
}
|