kami
79893d646b
Two things that were each half-done. The prompts handed the model copyable examples. chatSystemPrompt lost its openers this morning and the "Я подумала, что" tic went with them, but "не забыл ли я" appeared in its place: the removed example had been suppressing the masculine self-reference by accident. Two predicatives are not enough signal, so the rule is now stated as morphology (-ла) rather than as a pair of words — a suffix rule generalises where an example only gets copied. querySystemPrompt had the same defect and gets the same treatment; its "вот что я нашла: " opener is deliberate and stays. internal/kiwix had no caller. actions_query.go said "once internal/kiwix is wired into this chain" and that never happened. It is wired now, between the notes pass and the web source: everything of his answers first, and only what is left over is looked up. Off unless a `kiwix` block names a server and a book. Reading the search snippet does not work. Kiwix builds it from wherever the keyword matched, which on Wikipedia is the navigation box at the foot of the page — the first version of this answered "что такое фотосинтез?" by reciting "Ecological economics Ecological footprint Ecological forecasting …". Client grows an Article method; the head of the article is the lead paragraph, which is the definition the snippet was meant to be. Verified on the box: the same question now answers correctly off the ZIM. Only the rewritten query leaves the process. A test asserts it: a turn carrying a stored note must not put that note in the search string. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX
188 lines
6.6 KiB
Go
188 lines
6.6 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/kami/maven/internal/config"
|
|
"github.com/kami/maven/internal/ipc"
|
|
"github.com/kami/maven/internal/kiwix"
|
|
"github.com/kami/maven/internal/phraser"
|
|
"github.com/kami/maven/internal/router"
|
|
"github.com/kami/maven/internal/voice"
|
|
)
|
|
|
|
// searchRSS is what kiwix-serve answers a /search with, trimmed to the fields
|
|
// ParseSearchRSS reads.
|
|
func searchRSS(items ...string) string {
|
|
return `<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel>` +
|
|
strings.Join(items, "") + `</channel></rss>`
|
|
}
|
|
|
|
func rssItem(title, snippet string) string {
|
|
return "<item><title>" + title + "</title><link>/x</link><description>" + snippet + "</description></item>"
|
|
}
|
|
|
|
// stubKiwixServer answers every search with the given body and records the
|
|
// pattern it was asked for, so a test can assert on what left the process.
|
|
type stubKiwixServer struct {
|
|
*httptest.Server
|
|
lastPattern string
|
|
lastBook string
|
|
}
|
|
|
|
func newStubKiwix(t *testing.T, body string, status int) *stubKiwixServer {
|
|
t.Helper()
|
|
s := &stubKiwixServer{}
|
|
s.Server = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
if status != 0 && status != http.StatusOK {
|
|
w.WriteHeader(status)
|
|
return
|
|
}
|
|
// Two endpoints on one server: /search answers the RSS, everything else
|
|
// is an article read. Only the search is recorded — an article fetch
|
|
// carries no query string and would blank the assertions.
|
|
if r.URL.Path != "/search" {
|
|
w.Header().Set("Content-Type", "text/html")
|
|
_, _ = w.Write([]byte("<html><title>Article</title><body><p>the lead paragraph</p></body></html>"))
|
|
return
|
|
}
|
|
s.lastPattern = r.URL.Query().Get("pattern")
|
|
s.lastBook = r.URL.Query().Get("books.name")
|
|
w.Header().Set("Content-Type", "application/xml")
|
|
_, _ = w.Write([]byte(body))
|
|
}))
|
|
t.Cleanup(s.Close)
|
|
return s
|
|
}
|
|
|
|
// buildKiwixHandler wires the source with no rewriter: the question is searched
|
|
// verbatim, which keeps the assertion about what was sent unambiguous.
|
|
func buildKiwixHandler(base string) *reactiveHandler {
|
|
return &reactiveHandler{
|
|
replier: voice.NewStubReplier(),
|
|
phraser: phraser.NewStub(),
|
|
kiwix: &kiwixWiring{
|
|
client: kiwix.New(base),
|
|
book: "wikipedia_en_all_maxi",
|
|
max: config.DefaultKiwixResults,
|
|
runes: config.DefaultKiwixSnippetRunes,
|
|
},
|
|
}
|
|
}
|
|
|
|
func askKiwix(h *reactiveHandler, q string) (string, bool) {
|
|
return h.queryKiwix(context.Background(), &queryTurn{
|
|
dec: router.Decision{Intent: router.IntentQuery, Utterance: q},
|
|
})
|
|
}
|
|
|
|
// The default daemon has no `kiwix` block, and a source that is off must not
|
|
// claim the turn — the model answers next, exactly as it did before.
|
|
func TestQueryKiwixOffPassesThrough(t *testing.T) {
|
|
h := &reactiveHandler{replier: voice.NewStubReplier(), phraser: phraser.NewStub()}
|
|
if reply, ok := askKiwix(h, "почему небо синее?"); ok {
|
|
t.Errorf("an unconfigured kiwix claimed the turn: %q", reply)
|
|
}
|
|
}
|
|
|
|
func TestQueryKiwixAnswersFromSnippets(t *testing.T) {
|
|
s := newStubKiwix(t, searchRSS(rssItem("Rayleigh scattering", "shorter wavelengths scatter more")), 0)
|
|
h := buildKiwixHandler(s.URL)
|
|
|
|
reply, ok := askKiwix(h, "почему небо синее?")
|
|
if !ok {
|
|
t.Fatal("kiwix found a hit and did not claim the turn")
|
|
}
|
|
if reply == "" {
|
|
t.Error("claimed the turn with an empty reply")
|
|
}
|
|
if s.lastBook != "wikipedia_en_all_maxi" {
|
|
t.Errorf("books.name = %q, want the configured book", s.lastBook)
|
|
}
|
|
}
|
|
|
|
// No hit is not a failure worth announcing: the ZIM does not cover it, and the
|
|
// model answering next beats "ничего не нашла".
|
|
func TestQueryKiwixNoHitsPassesThrough(t *testing.T) {
|
|
s := newStubKiwix(t, searchRSS(), 0)
|
|
if reply, ok := askKiwix(buildKiwixHandler(s.URL), "почему небо синее?"); ok {
|
|
t.Errorf("an empty result set claimed the turn: %q", reply)
|
|
}
|
|
}
|
|
|
|
// A dead or misconfigured server must degrade to the model, not to an error
|
|
// spoken out loud. A turn never breaks on a capability.
|
|
func TestQueryKiwixServerErrorPassesThrough(t *testing.T) {
|
|
s := newStubKiwix(t, "", http.StatusBadRequest)
|
|
if reply, ok := askKiwix(buildKiwixHandler(s.URL), "почему небо синее?"); ok {
|
|
t.Errorf("a 400 claimed the turn: %q", reply)
|
|
}
|
|
}
|
|
|
|
// The privacy rule in CLAUDE.md, asserted rather than assumed: only the
|
|
// utterance is searched. No note, no fact, no persona block travels with it.
|
|
func TestQueryKiwixSendsOnlyTheQuestion(t *testing.T) {
|
|
s := newStubKiwix(t, searchRSS(rssItem("X", "y")), 0)
|
|
h := buildKiwixHandler(s.URL)
|
|
// A turn carrying notes an earlier source already pulled. They must not
|
|
// reach the query string.
|
|
_, _ = h.queryKiwix(context.Background(), &queryTurn{
|
|
dec: router.Decision{Intent: router.IntentQuery, Utterance: "почему небо синее?"},
|
|
notes: []ipc.Note{{Text: "пароль от роутера hunter2"}},
|
|
})
|
|
if strings.Contains(s.lastPattern, "hunter2") {
|
|
t.Fatalf("a stored note leaked into the search query: %q", s.lastPattern)
|
|
}
|
|
if s.lastPattern != "почему небо синее?" {
|
|
t.Errorf("pattern = %q, want the utterance verbatim", s.lastPattern)
|
|
}
|
|
}
|
|
|
|
func TestWireKiwixOffWithoutABlock(t *testing.T) {
|
|
if w := wireKiwix(&config.Config{}, nil); w != nil {
|
|
t.Error("wireKiwix built a source with no config block")
|
|
}
|
|
}
|
|
|
|
// No llama-server means no rewriter, but the source still works: searching the
|
|
// question verbatim is the honest degraded mode, not a reason to stay dark.
|
|
func TestWireKiwixWithoutAnLLMHasNoRewriter(t *testing.T) {
|
|
w := wireKiwix(&config.Config{Kiwix: &config.KiwixConfig{
|
|
URL: "http://kiwix:8080", Book: "b", MaxResults: 5, SnippetRunes: 1500,
|
|
}}, nil)
|
|
if w == nil {
|
|
t.Fatal("wireKiwix returned nil for a configured block")
|
|
}
|
|
if w.rewriter != nil {
|
|
t.Error("built a rewriter with no llm client")
|
|
}
|
|
if w.book != "b" {
|
|
t.Errorf("book = %q", w.book)
|
|
}
|
|
}
|
|
|
|
// The whole point of reading the article: kiwix's own snippet is usually the
|
|
// navigation box at the foot of the page, so the lead paragraph must be what
|
|
// reaches the phraser.
|
|
func TestQueryKiwixReadsTheArticleNotTheSnippet(t *testing.T) {
|
|
junk := "Ecological economics Ecological footprint Ecological forecasting"
|
|
s := newStubKiwix(t, searchRSS(rssItem("Photosynthesis", junk)), 0)
|
|
h := buildKiwixHandler(s.URL)
|
|
h.phraser = nil // no phraser ⇒ the fallback reads back what it was given
|
|
|
|
reply, ok := askKiwix(h, "что такое фотосинтез?")
|
|
if !ok {
|
|
t.Fatal("did not claim the turn")
|
|
}
|
|
if !strings.Contains(reply, "the lead paragraph") {
|
|
t.Errorf("reply did not come from the article: %q", reply)
|
|
}
|
|
if strings.Contains(reply, "Ecological economics") {
|
|
t.Errorf("recited the navigation-box snippet: %q", reply)
|
|
}
|
|
}
|