Files
petal/internal/llm/checkpoint_test.go
prosolis 08b801e752 Drop no-op suggestions where replacement equals original
The checkpoint model sometimes "flags" a correct sentence and echoes it
verbatim as the replacement, producing a card whose before/after are
identical and whose explanation says it's already fine — a suggestion
that suggests nothing. ParseCheckpoint already dropped empty-original
items; also drop these no-ops. Awareness-only families (voice) carry an
empty replacement, so the guard only fires on the edit families.

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd
2026-06-27 00:18:10 -07:00

143 lines
4.9 KiB
Go

package llm
import (
"testing"
"time"
)
func TestParseCheckpoint(t *testing.T) {
tests := []struct {
name string
raw string
want int
wantErr bool
}{
{
name: "clean json",
raw: `{"suggestions":[{"original":"I has","replacement":"I have","explanation":"subject-verb agreement","type":"grammar"}]}`,
want: 1,
},
{
name: "wrapped in markdown fence",
raw: "Here you go:\n```json\n{\"suggestions\":[{\"original\":\"a apple\",\"replacement\":\"an apple\",\"explanation\":\"use an before a vowel\",\"type\":\"grammar\"}]}\n```",
want: 1,
},
{
name: "empty suggestions",
raw: `{"suggestions":[]}`,
want: 0,
},
{
name: "drops items with empty original",
raw: `{"suggestions":[{"original":"","replacement":"x","explanation":"e","type":"grammar"},{"original":"teh","replacement":"the","explanation":"typo","type":"grammar"}]}`,
want: 1,
},
{
name: "no json at all",
raw: "I could not find any issues!",
wantErr: true,
},
{
// A correct sentence echoed verbatim as its own replacement is a card
// that suggests nothing — dropped. The second item is a real edit.
name: "drops no-op where replacement equals original",
raw: `{"suggestions":[{"original":"It wasn't the most graceful morning.","replacement":"It wasn't the most graceful morning.","explanation":"used correctly here","type":"idiom"},{"original":"teh","replacement":"the","explanation":"typo","type":"grammar"}]}`,
want: 1,
},
{
// Whitespace-only difference is still a no-op once both are trimmed.
name: "drops no-op after whitespace trim",
raw: `{"suggestions":[{"original":"the cat sat","replacement":" the cat sat ","explanation":"already fine","type":"grammar"}]}`,
want: 0,
},
{
// Awareness-only voice flags carry an empty replacement and must survive.
name: "keeps awareness-only flag with empty replacement",
raw: `{"suggestions":[{"original":"a long run-on passage","replacement":"","explanation":"this drifts from your voice","type":"voice"}]}`,
want: 1,
},
{
name: "braces inside string values",
raw: `{"suggestions":[{"original":"use {x}","replacement":"use x","explanation":"drop the braces","type":"clarity"}]}`,
want: 1,
},
{
// The bug that 502'd every long doc: the model hit num_predict and the
// JSON never closed. Two suggestions completed; the third is cut off.
// Salvage keeps the two that completed instead of failing outright.
name: "truncated mid-array salvages completed objects",
raw: `{"suggestions":[{"original":"I has","replacement":"I have","explanation":"subject-verb agreement","type":"grammar"},{"original":"a apple","replacement":"an apple","explanation":"use an before a vowel","type":"grammar"},{"original":"she relised","replacement":"she real`,
want: 2,
},
{
// A truncated array where even the first object is incomplete has
// nothing to salvage → still an error (the caller releases + retries).
name: "truncated before any object closes",
raw: `{"suggestions":[{"original":"It was a thursdy morning when Clara`,
wantErr: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got, err := ParseCheckpoint(tt.raw)
if tt.wantErr {
if err == nil {
t.Fatalf("expected error, got none")
}
return
}
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if len(got) != tt.want {
t.Fatalf("got %d suggestions, want %d", len(got), tt.want)
}
})
}
}
func TestRateLimiter(t *testing.T) {
rl := NewRateLimiter(30 * time.Second)
ok, _, at := rl.Allow("doc1")
if !ok {
t.Fatal("first call should be allowed")
}
if ok, retry, _ := rl.Allow("doc1"); ok || retry <= 0 {
t.Fatalf("immediate second call should be throttled, got ok=%v retry=%v", ok, retry)
}
// A different document is independent.
if ok, _, _ := rl.Allow("doc2"); !ok {
t.Fatal("different doc should be allowed")
}
// Releasing doc1's slot (as a failed pass does) lets the next check re-run
// immediately instead of waiting out the interval.
rl.Release("doc1", at)
if ok, _, _ := rl.Allow("doc1"); !ok {
t.Fatal("after Release the next call should be allowed again")
}
// Release only rolls back its own slot: a stale timestamp must not evict the
// slot a newer Allow holds (so a late failure can't cancel a fresh in-flight
// check). doc2 still holds its slot from above; a zero-time Release is a no-op.
rl.Release("doc2", time.Time{})
if ok, _, _ := rl.Allow("doc2"); ok {
t.Fatal("stale Release must not free doc2's current slot")
}
}
func TestTruncateDoc(t *testing.T) {
short := "hello"
if got := TruncateDoc(short); got != short {
t.Fatalf("short doc should be unchanged")
}
long := make([]byte, maxDocChars+500)
for i := range long {
long[i] = 'a'
}
got := TruncateDoc(string(long))
if len(got) != maxDocChars {
t.Fatalf("truncated length = %d, want %d", len(got), maxDocChars)
}
}