Files
petal/internal/llm/checkpoint_test.go
prosolis 46db0a3e16 Checkpoint: auto-retry after a failed pass; release rate-limit slot on failure
A paste fires exactly one grammar checkpoint, and a failed one never retried
until the next keystroke — stranding the writer on "Petal's helper is resting"
after a paste. Long docs make it worse: their 15-25s checks have a wide window
to catch a transient 502 from the shared Ollama (co-tenant apps load other
models and evict the 9B). A failed pass also burned the per-document rate-limit
slot, so a retry within 30s hit the throttle path and got an empty set back.

- llm.RateLimiter.Release rolls back a slot when its pass fails; Allow now
  returns the recorded timestamp so Release only frees its own slot.
- suggestions.runPass releases the slot on LLM failure before returning 502.
- useCheckpoint auto-retries a failed checkpoint with backoff (3/12/35s),
  keeping the breathing dot up and only flagging "resting" once retries exhaust.

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd
2026-06-26 13:09:12 -07:00

109 lines
3.0 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,
},
{
name: "braces inside string values",
raw: `{"suggestions":[{"original":"use {x}","replacement":"use x","explanation":"drop the braces","type":"clarity"}]}`,
want: 1,
},
}
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)
}
}