Files
Maven/internal/phraser/grammar_test.go
kami d7cdcb63bd Stop shipping half-written JSON as a reply
Two bugs, one symptom. A run of the talk eval produced replies that were
literally "{" and "{\n  \"" — those strings went out as things Maven said.

First bug: the parser could not tell "the model answered in plain prose"
from "the model started a JSON object and got cut off". Both came back as
empty, and every caller then shipped the raw text. Now an unfinished object
returns an error and each caller uses its own fallback instead. Bare prose
with no JSON in it still passes through, because small models do sometimes
answer that way and the reply is fine.

Second bug, and the actual cause: the grammar capped the response field at
400 characters. I measured it against Qwen3.5-0.8B at three different token
caps — 256, 768 and 2048 — and the reply came back exactly 400 characters
every time, cut mid-word. So the token limit was never what stopped it.
The bound is 1000 now, about six Russian sentences, still low enough to cut
off a repetition loop.

Token caps go from 256 to 768 on the chat and query paths so 1000
characters of Russian actually fits. The nudge path keeps its own cap; a
nudge is meant to be one sentence.

Note: cmd/mavend/replier_llm.go has its own copy of this parser with the
same bug. Left alone here so this commit stays small — that duplicate is
Vikunja #396.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
2026-07-31 17:56:55 +04:00

128 lines
4.1 KiB
Go

package phraser
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"strings"
"testing"
"github.com/kami/maven/internal/loop"
)
// grammarSpy stands in for llama-server: it records the grammar field of every
// request and always answers with a contract-shaped reply.
type grammarSpy struct {
srv *httptest.Server
grammars []string
}
func newGrammarSpy(t *testing.T) *grammarSpy {
t.Helper()
s := &grammarSpy{}
s.srv = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
var req chatReq
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
t.Errorf("spy: decode request: %v", err)
}
s.grammars = append(s.grammars, req.Grammar)
w.Header().Set("Content-Type", "application/json")
w.Write([]byte(`{"choices":[{"message":{"content":"{\"response\": \"ага\", \"mood\": \"neutral\"}"}}]}`))
}))
t.Cleanup(s.srv.Close)
return s
}
// callAllPhrasingPaths hits every path that expects the JSON contract.
func callAllPhrasingPaths(t *testing.T, p *LLMPhraser) {
t.Helper()
ctx := context.Background()
if _, err := p.PhraseNudge(ctx, loop.Candidate{Rule: loop.WaterRule(), Severity: loop.Sev1}); err != nil {
t.Fatalf("PhraseNudge: %v", err)
}
if _, err := p.PhraseChat(ctx, "привет", nil); err != nil {
t.Fatalf("PhraseChat: %v", err)
}
// Both branches: no notes (general knowledge) and with notes (grounded).
if _, err := p.PhraseQuery(ctx, "сколько воды я выпил", nil); err != nil {
t.Fatalf("PhraseQuery (no notes): %v", err)
}
if _, err := p.PhraseQuery(ctx, "сколько воды я выпил", []string{"два литра"}); err != nil {
t.Fatalf("PhraseQuery (notes): %v", err)
}
}
func TestGrammarIsAttachedToEveryPhrasingRequest(t *testing.T) {
if strings.TrimSpace(responseGrammar) == "" {
t.Fatal("responseGrammar is empty")
}
spy := newGrammarSpy(t)
p := NewLLMPhraserAt(spy.srv.URL, Config{})
callAllPhrasingPaths(t, p)
if len(spy.grammars) != 4 {
t.Fatalf("expected 4 requests, got %d", len(spy.grammars))
}
for i, g := range spy.grammars {
if g != responseGrammar {
t.Errorf("request %d carries grammar %q, want responseGrammar", i, g)
}
}
}
func TestNoGrammarConfigDisablesIt(t *testing.T) {
spy := newGrammarSpy(t)
p := NewLLMPhraserAt(spy.srv.URL, Config{NoGrammar: true})
callAllPhrasingPaths(t, p)
for i, g := range spy.grammars {
if g != "" {
t.Errorf("request %d still carries a grammar with NoGrammar set: %q", i, g)
}
}
}
// The grammar's string rule must accept any codepoint, not just ASCII. Replies
// are Russian: an ASCII-only class would constrain the model into empty replies.
func TestGrammarStringRuleIsNotASCIIOnly(t *testing.T) {
if !strings.Contains(responseGrammar, `([^"\\] | "\\" ["\\/bfnrt])`) {
t.Error("string rule is not the any-codepoint-except-quote-and-backslash class; Cyrillic replies would be impossible")
}
}
// What the grammar describes must survive the parser that reads it back — a
// 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)
}
if want := "он сказал \"привет\" и ушёл.\nвот так."; text != want {
t.Errorf("response = %q, want %q", text, want)
}
if mood != "confused" {
t.Errorf("mood = %q, want confused", mood)
}
}
// Every mood the grammar permits is one the contract knows, and all five are there.
func TestGrammarMoodEnumMatchesTheContract(t *testing.T) {
for _, m := range []string{"neutral", "happy", "thinking", "tired", "confused"} {
if !strings.Contains(responseGrammar, `"\"`+m+`\""`) {
t.Errorf("mood %q missing from the grammar", m)
}
}
// No sixth mood: the enum line lists exactly five alternatives.
for _, line := range strings.Split(responseGrammar, "\n") {
if strings.HasPrefix(line, "mood") {
if n := strings.Count(line, "|") + 1; n != 5 {
t.Errorf("mood rule lists %d alternatives, want 5: %s", n, line)
}
}
}
}