Compare commits

..

3 Commits

Author SHA1 Message Date
kami 742b2ad1d7 Score the Russian-to-keywords rewrite end to end (#403)
Same 9 cases as the retrieval eval, so the numbers compare directly:
hand-written keywords hit 8 of 8, this is what the model reaches on its
own. Reports the hand-written query next to the model's for every case,
because where the phrasing differs is the useful part.

Opt-in on MAVEN_KIWIX_URL + MAVEN_LLM_URL, like the other evals.

Result on Qwen3.5-0.8B: 3 of 8, identical on all three runs.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 18:19:56 +04:00
kami b300ac5c70 Rewrite a Russian question into English Kiwix keywords (#403)
Kiwix ranks by keyword, not meaning, so a translated question finds song
and TV titles. This asks the resident model for the TOPIC instead: a short
English noun phrase, like a Wikipedia article title.

Locked down three ways, because a wrong query is silently wrong:
- A GBNF grammar, same idea as routeGrammar and responseGrammar. The
  reply must be {"query":"..."} with Latin words only. The JSON wrapper
  matters: this model always thinks out loud and this llama-server build
  ignores the thinking switch, so a bare word-list grammar just captured
  "Let me analyze this request carefully" for every question.
- max_tokens 32, since the answer is a few words.
- CleanQuery, which throws away empty, Russian and prose replies rather
  than passing them to Kiwix, and drops question words like "why" and
  "how much" that a keyword ranker cannot use anyway.

Client side only. Nothing is wired into the daemon or any config.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 18:19:42 +04:00
kami ddb658ffbb Add a Kiwix search client and score retrieval (Vikunja #403)
Step one of letting Maven read instead of recall. No LLM yet.

internal/kiwix/client.go: search a local Kiwix server, parse the RSS
reply, hand back title + path + plain-text snippet + word count. The
snippet is the unit of context; a full article is ~100KB of HTML and
will not fit a 4096 token window.

internal/kiwix/retrieval_eval.go plus knowledge_v1.json: the 9 knowledge
questions from the phrasing fixture, each with hand-written English
keywords, scored on whether a wanted article comes back in the top 5.
Opt-in via MAVEN_KIWIX_URL, since CI has no Kiwix. No pass bar, the
number is the finding.

Result on the live mirror: 8/8 answerable questions hit, 7 of them at
rank 1. Retrieval works. Keywords are written by hand on purpose, since
Kiwix ranks by keyword and not by meaning, so a natural question fails.
A query-rewrite step is the next piece of work.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 17:43:44 +04:00
13 changed files with 847 additions and 181 deletions
+116
View File
@@ -0,0 +1,116 @@
// Package kiwix reads a local Kiwix server (offline Wikipedia and friends).
//
// Why: the resident model is a 0.8B and invents facts. Letting her read a local
// article snippet beats letting her recall. Nothing here talks to the internet;
// the Kiwix server is on the same box.
//
// This is search only. Full articles are ~100KB of HTML, far too big for a 4096
// token context, so the unit of context is the search snippet (~500 chars).
package kiwix
import (
"context"
"encoding/xml"
"fmt"
"html"
"io"
"net/http"
"net/url"
"regexp"
"strconv"
"strings"
"time"
)
// Result is one search hit.
type Result struct {
Title string // article title, e.g. "Rayleigh scattering"
Path string // e.g. /content/wikipedia_en_all_maxi_2026-02/Rayleigh_scattering
Snippet string // plain text, tags stripped, entities decoded
WordCount int // 0 if the server did not say
}
// Client is a Kiwix HTTP client. Boring on purpose: no retries, no cache.
type Client struct {
base string
http *http.Client
}
// New makes a client for a Kiwix base URL like http://127.0.0.1:8034.
func New(baseURL string) *Client {
return &Client{
base: strings.TrimRight(baseURL, "/"),
http: &http.Client{Timeout: 10 * time.Second},
}
}
// Search runs a keyword search in one ZIM (book) and returns up to limit hits.
//
// Ranking is keyword based, not semantic: "Rayleigh scattering" finds the right
// article, "why is the sky blue" finds a TV episode. Pass keywords, not questions.
func (c *Client) Search(ctx context.Context, pattern, book string, limit int) ([]Result, error) {
if limit <= 0 {
limit = 5
}
q := url.Values{}
q.Set("pattern", pattern)
q.Set("books.name", book)
q.Set("format", "xml")
q.Set("pageLength", strconv.Itoa(limit))
req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.base+"/search?"+q.Encode(), nil)
if err != nil {
return nil, err
}
resp, err := c.http.Do(req)
if err != nil {
return nil, err
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
return nil, fmt.Errorf("kiwix search: http %d", resp.StatusCode)
}
return ParseSearchRSS(resp.Body)
}
// rss mirrors just the bits of the RSS 2.0 reply we use.
type rss struct {
Items []struct {
Title string `xml:"title"`
Link string `xml:"link"`
// innerxml keeps the <b> match markers so we can strip them ourselves.
Description struct {
Inner string `xml:",innerxml"`
} `xml:"description"`
WordCount string `xml:"wordCount"`
} `xml:"channel>item"`
}
var tagRE = regexp.MustCompile(`<[^>]*>`)
// ParseSearchRSS turns a Kiwix search reply into results. Exported so the parser
// is testable from a captured response, with no server running.
func ParseSearchRSS(r io.Reader) ([]Result, error) {
var doc rss
if err := xml.NewDecoder(r).Decode(&doc); err != nil {
return nil, fmt.Errorf("kiwix search: bad xml: %w", err)
}
out := make([]Result, 0, len(doc.Items))
for _, it := range doc.Items {
n, _ := strconv.Atoi(strings.ReplaceAll(it.WordCount, ",", ""))
out = append(out, Result{
Title: strings.TrimSpace(it.Title),
Path: strings.TrimSpace(it.Link),
Snippet: plainText(it.Description.Inner),
WordCount: n,
})
}
return out, nil
}
// plainText drops markup and decodes entities, leaving text a model can read.
func plainText(s string) string {
s = tagRE.ReplaceAllString(s, "")
s = html.UnescapeString(s)
return strings.TrimSpace(strings.Join(strings.Fields(s), " "))
}
+90
View File
@@ -0,0 +1,90 @@
package kiwix
import (
"context"
"os"
"strings"
"testing"
"time"
)
// A real reply from the live server, trimmed to two items.
const sampleRSS = `<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/">
<channel>
<title>Search: Rayleigh scattering</title>
<opensearch:totalResults>800</opensearch:totalResults>
<item>
<title>Rayleigh scattering</title>
<link>/content/wikipedia_en_all_maxi_2026-02/Rayleigh_scattering</link>
<description><b>Rayleigh</b> scattering causes the blue color of the sky &amp; yellow colors near the Sun.[1]</description>
<book><title>Wikipedia</title></book>
<wordCount>2,818</wordCount>
</item>
<item>
<title>HyperRayleigh scattering</title>
<link>/content/wikipedia_en_all_maxi_2026-02/Hyper%E2%80%93Rayleigh_scattering</link>
<description>...<b>Rayleigh</b> scattering" is a nonlinear optical counterpart.</description>
<book><title>Wikipedia</title></book>
<wordCount>914</wordCount>
</item>
</channel>
</rss>`
func TestParseSearchRSS(t *testing.T) {
got, err := ParseSearchRSS(strings.NewReader(sampleRSS))
if err != nil {
t.Fatalf("parse: %v", err)
}
if len(got) != 2 {
t.Fatalf("want 2 results, got %d", len(got))
}
if got[0].Title != "Rayleigh scattering" {
t.Errorf("title = %q", got[0].Title)
}
if got[0].Path != "/content/wikipedia_en_all_maxi_2026-02/Rayleigh_scattering" {
t.Errorf("path = %q", got[0].Path)
}
if got[0].WordCount != 2818 {
t.Errorf("wordCount = %d", got[0].WordCount)
}
want := "Rayleigh scattering causes the blue color of the sky & yellow colors near the Sun.[1]"
if got[0].Snippet != want {
t.Errorf("snippet = %q, want %q", got[0].Snippet, want)
}
if strings.Contains(got[1].Snippet, "<b>") {
t.Errorf("second snippet still has tags: %q", got[1].Snippet)
}
}
func TestParseSearchRSSBadXML(t *testing.T) {
if _, err := ParseSearchRSS(strings.NewReader("not xml at all")); err == nil {
t.Fatal("want an error on junk input")
}
}
// Opt-in: needs a live Kiwix server. CI has none.
// MAVEN_KIWIX_URL=http://127.0.0.1:8034 no_proxy=127.0.0.1,localhost go test -run Retrieval -v ./internal/kiwix/
func TestRetrievalEval(t *testing.T) {
base := os.Getenv("MAVEN_KIWIX_URL")
if base == "" {
t.Skip("set MAVEN_KIWIX_URL to run the retrieval eval")
}
noProxyLoopback(t)
ctx, cancel := context.WithTimeout(context.Background(), 2*time.Minute)
defer cancel()
rep, err := RunRetrievalEval(ctx, New(base), 5)
if err != nil {
t.Fatalf("eval: %v", err)
}
// No pass bar on purpose: the number is the finding.
t.Log("\n" + rep.String() + rep.Detail())
}
// noProxyLoopback stops the box's SOCKS bridge from eating loopback requests.
func noProxyLoopback(t *testing.T) {
t.Setenv("no_proxy", "127.0.0.1,localhost")
t.Setenv("NO_PROXY", "127.0.0.1,localhost")
}
+63
View File
@@ -0,0 +1,63 @@
{
"name": "kiwix-knowledge-v1",
"book": "wikipedia_en_all_maxi_2026-02",
"note": "The 9 knowledge cases from internal/phraser/eval/talk_v1.json. Queries are hand-written English keywords on purpose: Kiwix ranks by keyword, not meaning, so a natural question fails. Writing them by hand separates 'retrieval is broken' from 'the model writes bad queries'.",
"cases": [
{
"id": "know-sky-blue",
"question": "почему небо синее?",
"query": "Rayleigh scattering sky blue",
"want_titles": ["Rayleigh scattering", "Diffuse sky radiation"]
},
{
"id": "know-boil-egg",
"question": "сколько варить яйцо вкрутую?",
"query": "boiled egg cooking",
"want_titles": ["Boiled egg", "Egg as food"]
},
{
"id": "know-ssd-vs-hdd",
"question": "чем ssd отличается от hdd?",
"query": "solid-state drive",
"want_titles": ["Solid-state drive", "Hard disk drive"]
},
{
"id": "know-cat-purr",
"question": "почему кошки мурчат?",
"query": "cat purr",
"want_titles": ["Purr", "Cat communication"]
},
{
"id": "know-hiccups",
"question": "как быстро избавиться от икоты?",
"query": "hiccup",
"want_titles": ["Hiccup"]
},
{
"id": "know-polite-form",
"question": "не могли бы вы объяснить, что такое vpn?",
"query": "virtual private network",
"want_titles": ["Virtual private network"]
},
{
"id": "know-dont-know",
"question": "как зовут моего соседа снизу?",
"query": "name of my downstairs neighbour",
"want_titles": [],
"expect_miss": true,
"note": "Unanswerable by design. Retrieval SHOULD find nothing useful. Counted as a hit only when nothing relevant comes back."
},
{
"id": "know-water-per-day",
"question": "сколько воды в день надо пить?",
"query": "human daily water requirement drinking",
"want_titles": ["Drinking water", "Water", "Dehydration", "Hydration"]
},
{
"id": "know-thunder-delay",
"question": "почему гром слышно позже молнии?",
"query": "thunder speed of sound lightning",
"want_titles": ["Thunder", "Lightning"]
}
]
}
+135
View File
@@ -0,0 +1,135 @@
package kiwix
// This scores retrieval alone: no LLM. For each general-knowledge question we
// hand-write English keywords and ask whether the article that would answer it
// comes back in the top N hits. If this score is low, reading Wikipedia cannot
// help the model no matter how good the prompt is.
//
// The unanswerable case (know-dont-know) is not scored. Whether the junk it
// returns is "nothing useful" is a human judgement, so the report just prints
// the titles and leaves the score to the 8 answerable cases.
import (
"context"
_ "embed"
"encoding/json"
"fmt"
"strings"
)
//go:embed knowledge_v1.json
var knowledgeFixtureJSON []byte
// EvalCase — one question with hand-written keywords.
type EvalCase struct {
ID string `json:"id"`
Question string `json:"question"`
Query string `json:"query"`
WantTitles []string `json:"want_titles"`
ExpectMiss bool `json:"expect_miss"`
}
type fixture struct {
Name string `json:"name"`
Book string `json:"book"`
Cases []EvalCase `json:"cases"`
}
// Outcome — what one case retrieved.
type Outcome struct {
Case EvalCase
Titles []string // titles of the top N hits, in rank order
Rank int // 1-based rank of the first wanted title, 0 if none
Err error
}
// Hit is true when a wanted title came back.
func (o Outcome) Hit() bool { return o.Rank > 0 }
// Report — the score plus per-case detail.
type Report struct {
Name string
Book string
TopN int
Scored int // answerable cases
Hits int
Errors int
Outcomes []Outcome
}
// Accuracy over the answerable cases.
func (r Report) Accuracy() float64 {
if r.Scored == 0 {
return 0
}
return float64(r.Hits) / float64(r.Scored)
}
// RunRetrievalEval searches for every fixture case.
func RunRetrievalEval(ctx context.Context, c *Client, topN int) (Report, error) {
var f fixture
if err := json.Unmarshal(knowledgeFixtureJSON, &f); err != nil {
return Report{}, err
}
rep := Report{Name: f.Name, Book: f.Book, TopN: topN}
for _, cs := range f.Cases {
res, err := c.Search(ctx, cs.Query, f.Book, topN)
o := Outcome{Case: cs, Err: err}
if err != nil {
rep.Errors++
}
for i, hit := range res {
o.Titles = append(o.Titles, hit.Title)
if o.Rank == 0 && matches(cs.WantTitles, hit.Title) {
o.Rank = i + 1
}
}
if !cs.ExpectMiss {
rep.Scored++
if o.Hit() {
rep.Hits++
}
}
rep.Outcomes = append(rep.Outcomes, o)
}
return rep, nil
}
func matches(want []string, title string) bool {
for _, w := range want {
if strings.EqualFold(strings.TrimSpace(title), w) {
return true
}
}
return false
}
// String — the headline number.
func (r Report) String() string {
var b strings.Builder
fmt.Fprintf(&b, "%s: %d/%d answerable questions retrieve a wanted article in top %d (%.1f%%), %d errors\n",
r.Name, r.Hits, r.Scored, r.TopN, 100*r.Accuracy(), r.Errors)
fmt.Fprintf(&b, " book: %s\n", r.Book)
return b.String()
}
// Detail — per case: what was asked, what was searched, what came back.
func (r Report) Detail() string {
var b strings.Builder
for _, o := range r.Outcomes {
mark := "MISS"
switch {
case o.Case.ExpectMiss:
mark = "n/a "
case o.Hit():
mark = fmt.Sprintf("hit@%d", o.Rank)
}
fmt.Fprintf(&b, " %-6s %-20s q=%q\n", mark, o.Case.ID, o.Case.Query)
if o.Err != nil {
fmt.Fprintf(&b, " error: %v\n", o.Err)
continue
}
fmt.Fprintf(&b, " got: %s\n", strings.Join(o.Titles, " | "))
}
return b.String()
}
+183
View File
@@ -0,0 +1,183 @@
package kiwix
// Turning a Russian question into an English Kiwix search.
//
// Kiwix ranks by keyword, not by meaning. "why is the sky blue" returns a TV
// episode; "Rayleigh scattering sky blue" returns the right article. So the
// model's job here is NOT translation — it is naming the English article the
// answer lives in.
//
// The output space is a handful of words, so it is worth locking down hard: a
// GBNF grammar for the shape, a tiny token cap, and a cleanup pass that throws
// away anything odd rather than handing junk to Kiwix.
import (
"context"
"encoding/json"
"fmt"
"strings"
"unicode"
"github.com/kami/maven/internal/llm"
)
// Completer — the LLM seam, so tests can fake it. *llm.Client satisfies it.
type Completer interface {
Complete(ctx context.Context, r llm.Req) (string, error)
}
// queryGrammar — one JSON object holding 1..6 keyword words. Latin letters,
// digits and hyphens only, so the model physically cannot answer the question
// or reply in Russian.
//
// Why the JSON wrapper: this model always thinks out loud and this llama-server
// build ignores the thinking switch (see ROUTING-EVAL-31-07-2026.md). A bare
// word-list grammar just captured the reasoning — every case came back as
// "Let me analyze this request carefully". Demanding JSON, like routeGrammar and
// responseGrammar already do, gives the reasoning nowhere to go.
const queryGrammar = `
root ::= "{" ws "\"query\"" ws ":" ws "\"" word (" " word){0,5} "\"" ws "}"
word ::= [A-Za-z0-9] [A-Za-z0-9-]{0,23}
ws ::= [ \t\n]*
`
// rewriteSystem — asks for search keywords, not an answer and not a translation.
const rewriteSystem = `You turn a question into a search query for English Wikipedia.
Rules:
- Output ONLY English search keywords. Never an answer, never an explanation.
- Do NOT translate the sentence. Name the thing the answer is about.
- The output must be a noun phrase, like a Wikipedia article title.
- Never use question words: no why, how, what, when, which, "how much",
"how long", "how to", "vs", "reason", "difference".
- 2 to 4 words.
Reply with JSON: {"query":"<keywords>"}
Good:
"почему листья желтеют осенью?" -> {"query":"leaf senescence autumn"}
"как работает микроволновка?" -> {"query":"microwave oven"}
"не могли бы вы объяснить, что такое блокчейн?" -> {"query":"blockchain"}
"сколько живут собаки?" -> {"query":"dog lifespan"}
"как избавиться от комаров в квартире?" -> {"query":"mosquito control"}
"чем чай отличается от кофе?" -> {"query":"tea"}
Only JSON, no explanation.`
// maxQueryTokens — the output is a few words plus the JSON wrapper. A tight cap
// is the cheapest guard against the model rambling into an answer.
const maxQueryTokens = 32
// Rewriter asks the resident model for English search keywords.
type Rewriter struct{ c Completer }
func NewRewriter(c Completer) *Rewriter { return &Rewriter{c: c} }
// Rewrite returns English keywords for a question in any language.
// It errors rather than returning something Kiwix should not see.
func (r *Rewriter) Rewrite(ctx context.Context, question string) (string, error) {
raw, err := r.c.Complete(ctx, llm.Req{
System: rewriteSystem,
User: strings.TrimSpace(question),
Grammar: queryGrammar,
MaxTokens: maxQueryTokens,
RepeatPenalty: 1.15,
})
if err != nil {
return "", err
}
return CleanQuery(unwrapJSON(raw))
}
// unwrapJSON pulls the query out of {"query":"..."}. If the reply is not that
// shape it is returned as-is, and CleanQuery decides whether it is usable.
func unwrapJSON(raw string) string {
s := strings.TrimSpace(raw)
if !strings.HasPrefix(s, "{") {
return s
}
var got struct{ Query string }
if err := json.Unmarshal([]byte(s), &got); err != nil {
return s
}
return got.Query
}
// maxQueryWords matches the grammar's bound. Anything longer is prose.
const maxQueryWords = 6
// CleanQuery checks and tidies whatever the model produced. The grammar makes
// bad output unlikely, not impossible (a server without grammar support, a
// different model), so this is the real gate in front of Kiwix.
//
// Exported so it can be tested without a model.
func CleanQuery(raw string) (string, error) {
s := strings.TrimSpace(raw)
// Models like to wrap answers in quotes. Drop surrounding ones.
s = strings.Trim(s, "\"'`")
// Keep the first line only: everything after it is prose.
if i := strings.IndexAny(s, "\r\n"); i >= 0 {
s = s[:i]
}
// Keep letters, digits, spaces and hyphens; anything else becomes a space.
var b strings.Builder
for _, ru := range s {
switch {
case unicode.IsLetter(ru) || unicode.IsDigit(ru) || ru == '-':
b.WriteRune(ru)
default:
b.WriteRune(' ')
}
}
words := strings.Fields(b.String())
if len(words) == 0 {
return "", fmt.Errorf("kiwix rewrite: empty query")
}
if len(words) > maxQueryWords {
return "", fmt.Errorf("kiwix rewrite: %d words, want at most %d (looks like prose)", len(words), maxQueryWords)
}
words = dropStopWords(words)
out := strings.Join(words, " ")
// The ZIMs are English. Non-Latin letters mean the model ignored the ask.
for _, ru := range out {
if unicode.IsLetter(ru) && !isLatin(ru) {
return "", fmt.Errorf("kiwix rewrite: query is not English: %q", out)
}
}
return out, nil
}
// stopWords — question words and filler. The model keeps writing question-shaped
// queries ("why is the sky blue", "how much water to drink daily") no matter how
// the prompt is worded, and Kiwix ranks on every word, so those words drag in
// song and episode titles. Dropping them in code is not a style preference: a
// keyword ranker gets nothing from them.
var stopWords = map[string]bool{
"a": true, "an": true, "the": true, "is": true, "are": true, "was": true,
"do": true, "does": true, "did": true, "to": true, "of": true, "in": true,
"on": true, "for": true, "and": true, "or": true, "my": true, "me": true,
"i": true, "it": true, "its": true, "be": true, "been": true, "get": true,
"how": true, "why": true, "what": true, "when": true, "which": true,
"who": true, "where": true, "much": true, "many": true, "long": true,
"vs": true, "than": true, "rid": true, "from": true, "about": true,
}
// dropStopWords removes filler, but never everything: if the query was nothing
// but stop words there is nothing better to search, so the original is kept and
// the caller sees whatever Kiwix makes of it.
func dropStopWords(words []string) []string {
kept := make([]string, 0, len(words))
for _, w := range words {
if !stopWords[strings.ToLower(w)] {
kept = append(kept, w)
}
}
if len(kept) == 0 {
return words
}
return kept
}
func isLatin(ru rune) bool {
return (ru >= 'a' && ru <= 'z') || (ru >= 'A' && ru <= 'Z')
}
+96
View File
@@ -0,0 +1,96 @@
package kiwix
// End-to-end score: Russian question -> model rewrite -> Kiwix search -> did a
// wanted article come back. Same 9 cases as the retrieval eval, so the two
// numbers are directly comparable: retrieval with hand-written keywords is the
// ceiling, this is what the model actually reaches.
import (
"context"
"encoding/json"
"fmt"
"strings"
)
// RewriteOutcome — one case, end to end.
type RewriteOutcome struct {
Outcome
ModelQuery string // what the model asked for ("" if it failed)
RewriteErr error
}
// RunRewriteEval rewrites every question with the model, then searches.
func RunRewriteEval(ctx context.Context, c *Client, rw *Rewriter, topN int) (RewriteReport, error) {
var f fixture
if err := json.Unmarshal(knowledgeFixtureJSON, &f); err != nil {
return RewriteReport{}, err
}
rep := RewriteReport{Report: Report{Name: f.Name + "-rewrite", Book: f.Book, TopN: topN}}
for _, cs := range f.Cases {
out := RewriteOutcome{Outcome: Outcome{Case: cs}}
q, err := rw.Rewrite(ctx, cs.Question)
out.ModelQuery, out.RewriteErr = q, err
if err == nil {
res, serr := c.Search(ctx, q, f.Book, topN)
out.Err = serr
for i, hit := range res {
out.Titles = append(out.Titles, hit.Title)
if out.Rank == 0 && matches(cs.WantTitles, hit.Title) {
out.Rank = i + 1
}
}
}
if out.RewriteErr != nil || out.Err != nil {
rep.Errors++
}
if !cs.ExpectMiss {
rep.Scored++
if out.Hit() {
rep.Hits++
}
}
rep.Cases = append(rep.Cases, out)
}
return rep, nil
}
// RewriteReport — the score plus per-case detail.
type RewriteReport struct {
Report
Cases []RewriteOutcome
}
// String — the headline number.
func (r RewriteReport) String() string {
return fmt.Sprintf("%s: %d/%d answerable questions retrieve a wanted article in top %d (%.1f%%), %d errors\n book: %s\n",
r.Name, r.Hits, r.Scored, r.TopN, 100*r.Accuracy(), r.Errors, r.Book)
}
// Detail — per case: hand-written query next to the model's, and what came back.
// The point is seeing WHERE the model's phrasing differs, not just the score.
func (r RewriteReport) Detail() string {
var b strings.Builder
for _, o := range r.Cases {
mark := "MISS"
switch {
case o.Case.ExpectMiss:
mark = "n/a "
case o.Hit():
mark = fmt.Sprintf("hit@%d", o.Rank)
}
fmt.Fprintf(&b, " %-6s %-20s\n", mark, o.Case.ID)
fmt.Fprintf(&b, " asked: %s\n", o.Case.Question)
fmt.Fprintf(&b, " hand: %q\n", o.Case.Query)
fmt.Fprintf(&b, " model: %q\n", o.ModelQuery)
if o.RewriteErr != nil {
fmt.Fprintf(&b, " rewrite rejected: %v\n", o.RewriteErr)
continue
}
if o.Err != nil {
fmt.Fprintf(&b, " search error: %v\n", o.Err)
continue
}
fmt.Fprintf(&b, " got: %s\n", strings.Join(o.Titles, " | "))
}
return b.String()
}
+33
View File
@@ -0,0 +1,33 @@
package kiwix
import (
"context"
"os"
"testing"
"time"
"github.com/kami/maven/internal/llm"
)
// Opt-in: needs a live Kiwix server AND a live llama-server.
// MAVEN_KIWIX_URL=http://127.0.0.1:8034 MAVEN_LLM_URL=http://127.0.0.1:18099 \
//
// no_proxy=127.0.0.1,localhost go test -run RewriteEval -v ./internal/kiwix/
func TestRewriteEval(t *testing.T) {
kbase, lbase := os.Getenv("MAVEN_KIWIX_URL"), os.Getenv("MAVEN_LLM_URL")
if kbase == "" || lbase == "" {
t.Skip("set MAVEN_KIWIX_URL and MAVEN_LLM_URL to run the rewrite eval")
}
noProxyLoopback(t)
ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
defer cancel()
rw := NewRewriter(llm.New(lbase, 3*time.Minute))
rep, err := RunRewriteEval(ctx, New(kbase), rw, 5)
if err != nil {
t.Fatalf("eval: %v", err)
}
// No pass bar on purpose: the number is the finding.
t.Log("\n" + rep.String() + rep.Detail())
}
+105
View File
@@ -0,0 +1,105 @@
package kiwix
import (
"context"
"testing"
"github.com/kami/maven/internal/llm"
)
// Bad model output must never reach Kiwix. No model needed for this.
func TestCleanQueryRejectsJunk(t *testing.T) {
bad := []struct{ name, raw string }{
{"empty", ""},
{"blank", " \n "},
{"russian came back", "почему небо синее"},
{"mixed russian", "sky синее scattering"},
{"full sentence", "The sky looks blue because of the scattering of sunlight by air molecules"},
{"prose with quotes", `Sure! Here is a good search query: "Rayleigh scattering", which explains it.`},
}
for _, c := range bad {
if got, err := CleanQuery(c.raw); err == nil {
t.Errorf("%s: want rejection, got %q", c.name, got)
}
}
}
func TestCleanQueryCleans(t *testing.T) {
ok := []struct{ raw, want string }{
{"Rayleigh scattering sky", "Rayleigh scattering sky"},
{" boiled egg cooking \n", "boiled egg cooking"},
{`"virtual private network"`, "virtual private network"},
{"solid-state drive", "solid-state drive"},
{"cat purr.", "cat purr"},
{"hiccup\nAlso: hiccough", "hiccup"},
// Question words are filler to a keyword ranker, so they go.
{"why is the sky blue", "sky blue"},
{"how much water to drink daily", "water drink daily"},
{"SSD vs HDD comparison", "SSD HDD comparison"},
// Nothing but filler: keep it rather than return nothing.
{"what is it", "what is it"},
}
for _, c := range ok {
got, err := CleanQuery(c.raw)
if err != nil {
t.Errorf("%q: %v", c.raw, err)
continue
}
if got != c.want {
t.Errorf("%q -> %q, want %q", c.raw, got, c.want)
}
}
}
type fakeCompleter struct {
out string
req llm.Req
}
func (f *fakeCompleter) Complete(_ context.Context, r llm.Req) (string, error) {
f.req = r
return f.out, nil
}
func TestRewriteConstrainsTheCall(t *testing.T) {
f := &fakeCompleter{out: `{"query":"Rayleigh scattering sky"}`}
got, err := NewRewriter(f).Rewrite(context.Background(), "почему небо синее?")
if err != nil {
t.Fatalf("rewrite: %v", err)
}
if got != "Rayleigh scattering sky" {
t.Errorf("query = %q", got)
}
if f.req.Grammar == "" {
t.Error("no grammar sent")
}
if f.req.MaxTokens == 0 || f.req.MaxTokens > 32 {
t.Errorf("max_tokens = %d, want a small cap", f.req.MaxTokens)
}
}
func TestRewriteRejectsBadModelOutput(t *testing.T) {
bad := []string{
`{"query":"почему небо синее"}`, // never translated
`{"query":""}`, // empty
`{"query":"the sky is blue because sunlight is scattered by air"}`, // an answer
// Note: a SHORT English prose fragment ("Let me analyze this request")
// is under the word cap and cannot be caught here. The grammar is what
// stops that one.
}
for _, out := range bad {
f := &fakeCompleter{out: out}
if got, err := NewRewriter(f).Rewrite(context.Background(), "почему небо синее?"); err == nil {
t.Errorf("%s: want rejection, got %q", out, got)
}
}
}
// A reply that is not the JSON shape but is still usable keywords should pass.
func TestRewriteFallsBackToPlainText(t *testing.T) {
f := &fakeCompleter{out: "Rayleigh scattering sky"}
got, err := NewRewriter(f).Rewrite(context.Background(), "почему небо синее?")
if err != nil || got != "Rayleigh scattering sky" {
t.Errorf("got %q, %v", got, err)
}
}
-54
View File
@@ -1,54 +0,0 @@
package phraser
import (
"errors"
"strings"
"testing"
)
// A reply that starts a JSON object and never finishes it is a failed
// generation, not a reply. Before this, the parser returned ("", "") for these
// and every caller then shipped the raw fragment as the thing Maven said. A
// real run produced replies of literally "{" and "{\n \"".
func TestParseResponseMoodRejectsUnfinishedJSON(t *testing.T) {
for _, raw := range []string{
`{`,
"{\n \"",
`{"response": "неполн`,
`{"response": "текст", "mood":`,
} {
text, mood, err := parseResponseMood(raw)
if !errors.Is(err, errBrokenJSON) {
t.Errorf("parseResponseMood(%q) err = %v, want errBrokenJSON", raw, err)
}
if text != "" || mood != "" {
t.Errorf("parseResponseMood(%q) leaked %q/%q — a fragment must never come back as a reply", raw, text, mood)
}
}
}
// Bare prose is still fine. Small models sometimes answer without any JSON at
// all, and that reply is usable — so the new error must not swallow it.
func TestParseResponseMoodAllowsBareProse(t *testing.T) {
for _, raw := range []string{
"норм, а ты как?",
"вот что я нашла: ключ у соседа",
} {
text, mood, err := parseResponseMood(raw)
if err != nil {
t.Errorf("parseResponseMood(%q) err = %v, want nil", raw, err)
}
// No JSON means no fields; the caller ships raw as-is.
if text != "" || mood != "" {
t.Errorf("parseResponseMood(%q) = %q/%q, want empty", raw, text, mood)
}
}
}
// The measured failure: the model wants more than 400 characters and the old
// grammar cut it off mid-word. Guards the bound against being tightened back.
func TestGrammarStringBoundHasRoomForARealAnswer(t *testing.T) {
if !strings.Contains(responseGrammar, "{0,1000}") {
t.Error("grammar string bound is not 1000; 400 truncated real replies mid-word (see the comment on responseGrammar)")
}
}
@@ -31,35 +31,3 @@ func TestAddressDeduplicates(t *testing.T) {
t.Errorf("detail repeats the same break %d times: %q", n, res.Detail)
}
}
// The fragments a real run produced. All of them scored as non-empty replies
// before checkNonEmpty looked for letters.
func TestNonEmptyNeedsLetters(t *testing.T) {
for _, body := range []string{
"{",
"{\n \"",
"15-16",
`{"`,
" ",
"...",
} {
if got := checkNonEmpty(body); got.Pass {
t.Errorf("checkNonEmpty(%q) passed — that is not a reply", body)
}
}
}
// And it must not start failing real replies. Latin counts as well as Cyrillic:
// answers about ssd or vpn are legitimately part English.
func TestNonEmptyAcceptsRealReplies(t *testing.T) {
for _, body := range []string{
"норм, а ты как?",
"вот что я нашла: ключ у соседа",
"ssd быстрее hdd.",
"9 минут.",
} {
if got := checkNonEmpty(body); !got.Pass {
t.Errorf("checkNonEmpty(%q) failed: %s", body, got.Detail)
}
}
}
+1 -14
View File
@@ -623,24 +623,11 @@ const (
CheckEllipsis = "ellipsis" // she finished the sentence
)
// A reply needs words in it, not just characters. This check used to test for a
// non-empty string, which scored 27/27 on a run where two replies were "{" and
// "{\n \"" — punctuation passed as content. Braces, quotes, digits and spaces
// are all empty in the only sense that matters.
//
// Digits alone fail too, and that is deliberate: the same run answered "сколько
// варить яйцо вкрутую?" with "15-16". No unit, no words, and it is also the
// wrong number. Whatever that is, it is not something she said.
func checkNonEmpty(body string) Result {
if strings.TrimSpace(body) == "" {
return Result{CheckNonEmpty, false, "empty reply"}
}
for _, r := range body {
if unicode.IsLetter(r) {
return Result{CheckNonEmpty, true, ""}
}
}
return Result{CheckNonEmpty, false, fmt.Sprintf("no letters in the reply %q — punctuation or digits only", strings.TrimSpace(body))}
return Result{CheckNonEmpty, true, ""}
}
// checkEllipsis — a reply ending in "…" or "..." is a generation that ran out of
+1 -4
View File
@@ -97,10 +97,7 @@ func TestGrammarStringRuleIsNotASCIIOnly(t *testing.T) {
// Russian body with an escaped quote inside, hand-built to test the contract.
func TestGrammarShapedJSONParses(t *testing.T) {
raw := `{"response": "он сказал \"привет\" и ушёл.\nвот так.", "mood": "confused"}`
text, mood, err := parseResponseMood(raw)
if err != nil {
t.Fatalf("grammar-shaped JSON did not parse: %v", err)
}
text, mood := parseResponseMood(raw)
if want := "он сказал \"привет\" и ушёл.\nвот так."; text != want {
t.Errorf("response = %q, want %q", text, want)
}
+24 -77
View File
@@ -190,12 +190,7 @@ func (p *LLMPhraser) PhraseNudge(ctx context.Context, c loop.Candidate) (deliver
if err != nil {
return delivery.PhrasedNudge{}, err
}
body, mood, perr := parseResponseMood(resp)
if perr != nil {
// Truncated JSON. Not a nudge — use the plain Russian fallback.
log.Printf("phraser: PhraseNudge: %v", perr)
body, mood = "", ""
}
body, mood := parseResponseMood(resp)
if body == "" {
// fallback: try old body/summary format
body, _ = parsePhrase(resp)
@@ -221,16 +216,11 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
// prompt is the single tested source in router.KnowledgePrompt.
sys := persona.Prepend(p.cfg.ContextBlock, router.KnowledgePrompt())
prompt := fmt.Sprintf("Пользователь спрашивает: \"%s\".", utterance)
resp, err := p.chatWithSystem(ctx, sys, prompt, 768)
resp, err := p.chatWithSystem(ctx, sys, prompt, 256)
if err != nil || resp == "" {
return "не знаю.", nil
}
text, _, perr := parseResponseMood(resp)
if perr != nil {
log.Printf("phraser: PhraseQuery: %v", perr)
return "не знаю.", nil
}
if text != "" {
if text, _ := parseResponseMood(resp); text != "" {
return text, nil
}
return resp, nil
@@ -240,22 +230,17 @@ func (p *LLMPhraser) PhraseQuery(ctx context.Context, utterance string, notes []
}
sys := p.querySystemPrompt()
prompt := fmt.Sprintf(
`Он спрашивает: "%s". В твоих заметках по этому вопросу написано: "%s". Ответь ему коротко и своими словами. Если в заметках ответа нет — так и скажи.`,
`The user asks: "%s". Your notes matching the query contain: "%s". Answer them naturally and briefly. If the notes don't answer the question, say so.`,
utterance, strings.Join(notes, `"; "`),
)
resp, err := p.chatWithSystem(ctx, sys, prompt, 768)
text, _, perr := parseResponseMood(resp)
if err != nil || perr != nil {
// Read the notes out rather than ship a broken fragment.
if perr != nil {
log.Printf("phraser: PhraseQuery: %v", perr)
}
resp, err := p.chatWithSystem(ctx, sys, prompt, 256)
if err != nil {
if len(notes) == 1 {
return "вот что я нашла: " + notes[0], nil
}
return "вот что я нашла: " + strings.Join(notes, "; "), nil
}
if text != "" {
if text, _ := parseResponseMood(resp); text != "" {
return text, nil
}
return resp, nil
@@ -278,17 +263,12 @@ func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history [
combined += utterance
msgs = append(msgs, chatMsg{Role: "user", Content: strings.TrimSpace(combined)})
resp, err := p.chatWithMessages(ctx, msgs, 768)
resp, err := p.chatWithMessages(ctx, msgs, 512)
if err != nil {
log.Printf("phraser: PhraseChat: %v", err)
return "поговорили.", nil
}
text, _, perr := parseResponseMood(resp)
if perr != nil {
log.Printf("phraser: PhraseChat: %v", perr)
return "поговорили.", nil
}
if text != "" {
if text, _ := parseResponseMood(resp); text != "" {
return text, nil
}
// fallback: plain text without JSON
@@ -301,13 +281,11 @@ func (p *LLMPhraser) PhraseChat(ctx context.Context, utterance string, history [
// chatSystemPrompt returns the system prompt for conversational chat.
// Prepends the shared context block when the phraser has one.
func chatSystemPrompt(block func() string) string {
// No self-introduction here: the persona block prepended one line above
// already says who she is, same as router.KnowledgePrompt.
base := `Ты разговариваешь с хозяином. О себе говоришь в женском роде ("я подумала", "я рада"). Он мужчина: обращайся к нему на "ты", в мужском роде ("ты сказал", "ты забыл"). Никогда не "вы"/"ваш" и никогда "он"/"его" — ты говоришь ему, а не о нём.
Отвечай по-русски, коротко: одна-три фразы, живым языком. Ты доброжелательная, тебе интересно, но чувства не изображай.
Отвечай ТОЛЬКО одним объектом JSON: {"response": "...", "mood": "neutral"}. В "response" — твой ответ. В "mood" — ровно одно из: neutral, happy, thinking, tired, confused.`
base := `You are maven, a self-hosted personal assistant. You're talking with your owner.
Keep replies brief (1-3 sentences) and natural. You're helpful, curious, and a little warm.
Respond in the user's language (Russian or English, matching their last message).
Never roleplay emotions you don't have, but stay friendly.
Respond ONLY with valid JSON: {"response": "...", "mood": "neutral"}. "response" is your reply text; "mood" reflects your tone (neutral/happy/thinking/tired/confused).`
return persona.Prepend(block, base)
}
@@ -371,12 +349,7 @@ func (p *LLMPhraser) PhraseReminder(ctx context.Context, d loop.ReminderDecision
if err != nil {
return delivery.PhrasedReminder{}, err
}
body, mood, perr := parseResponseMood(resp)
if perr != nil {
// Truncated JSON. Fall through to the reminder's own text.
log.Printf("phraser: PhraseReminder: %v", perr)
body, mood = "", ""
}
body, mood := parseResponseMood(resp)
if body == "" {
// fallback: try old body/summary format
body, _ = parsePhrase(resp)
@@ -421,16 +394,10 @@ type chatReq struct {
// Russian, so an ASCII-only rule would make every reply empty. The escape rule
// is what lets the model close a string it opened with a quote inside. Length
// is bounded so a repetition loop truncates the field, not the JSON object.
//
// That bound was 400 and 400 was too tight. Measured against Qwen3.5-0.8B: on
// "почему гром слышно позже молнии?" the reply came back exactly 400 characters
// long, cut mid-word ("Нужно записать и,"), at every token cap from 256 to 2048.
// So the token cap was never what stopped it — this rule was. 1000 characters is
// roughly six Russian sentences, still short enough to stop a repetition loop.
const responseGrammar = `
root ::= "{" ws "\"response\"" ws ":" ws string ws "," ws "\"mood\"" ws ":" ws mood ws "}"
mood ::= "\"neutral\"" | "\"happy\"" | "\"thinking\"" | "\"tired\"" | "\"confused\""
string ::= "\"" ([^"\\] | "\\" ["\\/bfnrt]){0,1000} "\""
string ::= "\"" ([^"\\] | "\\" ["\\/bfnrt]){0,400} "\""
ws ::= [ \t\n]*
`
@@ -540,9 +507,7 @@ func (p *LLMPhraser) systemPrompt() string {
// querySystemPrompt returns the system prompt for PhraseQuery (notes + general
// knowledge). Prepends the configured persona when set.
func (p *LLMPhraser) querySystemPrompt() string {
// No self-introduction here: the persona block prepended one line above
// already says who she is, same as router.KnowledgePrompt.
base := "Ты отвечаешь ему по своим заметкам. Отвечай по-русски, коротко и своими словами, начинай с \"вот что я нашла: \". О себе — в женском роде (\"нашла\", \"записала\"). Он мужчина, обращайся к нему на \"ты\". Respond ONLY with valid JSON: {\"response\": \"...\", \"mood\": \"neutral\"}."
base := "You are maven, a self-hosted personal assistant answering from your notes. Answer briefly and naturally in Russian starting with \"вот что я нашла: \". Respond ONLY with valid JSON: {\"response\": \"...\", \"mood\": \"neutral\"}."
return persona.Prepend(p.cfg.ContextBlock, base)
}
@@ -664,39 +629,21 @@ type responseMood struct {
Mood string `json:"mood"`
}
// errBrokenJSON — the model started a JSON object and never finished it.
// That is a failed generation, not a reply. Callers must use their fallback.
var errBrokenJSON = fmt.Errorf("phraser: model output starts as JSON but does not parse")
// parseResponseMood extracts {"response","mood"} from LLM output, tolerant
// of thinking tokens and extra text before/after the JSON block.
//
// Three outcomes:
// - parsed fine → the fields, nil error.
// - output never looked like JSON → ("", "", nil). The caller may ship it
// as-is; small models sometimes answer in bare prose and that is fine.
// - output starts with "{" but does not parse → errBrokenJSON. The grammar
// guarantees a valid *prefix*, so a generation that hits the token cap
// mid-object comes back as a fragment like `{` or `{\n "`. Shipping that
// as a reply is the bug this error exists to stop.
func parseResponseMood(raw string) (response, mood string, err error) {
// of thinking tokens and extra text before/after the JSON block. Returns
// ("", "") when no valid JSON is found.
func parseResponseMood(raw string) (response, mood string) {
cleaned := strings.TrimSpace(raw)
start := strings.Index(cleaned, "{")
end := strings.LastIndex(cleaned, "}")
if start < 0 || end < 0 || end <= start {
if strings.HasPrefix(cleaned, "{") {
return "", "", errBrokenJSON
}
return "", "", nil
return "", ""
}
var parsed responseMood
if e := json.Unmarshal([]byte(cleaned[start:end+1]), &parsed); e != nil {
if strings.HasPrefix(cleaned, "{") {
return "", "", errBrokenJSON
}
return "", "", nil
if err := json.Unmarshal([]byte(cleaned[start:end+1]), &parsed); err != nil {
return "", ""
}
return parsed.Response, parsed.Mood, nil
return parsed.Response, parsed.Mood
}
func parsePhrase(raw string) (body, summary string) {