Files
petal/internal/suggestions/handlers_test.go
prosolis 9d2501a625 Suppress fickle re-edits of sentences the user already settled
Suppression keyed on the exact original->replacement pair, which the
model routinely sidestepped: it reverses an accepted edit (reverse
pair), re-polishes its own accepted output (new original == accepted
replacement), and the editor's smart-quote churn ("..." -> '...')
defeated even a byte-exact match. Result: a few sentences got nudged
back and forth pass after pass.

Replace the exact-pair actionedKeys with a suppressor that compares
under a normalization folding all quote variants and collapsing
whitespace, and drops a fresh suggestion when it re-touches an
already-settled span: same edit re-proposed, an original the user
already accepted/dismissed, the model re-touching its own accepted
output, or a multi-word sub-clause contained in an accepted span.

Tradeoff: once a sentence is accepted/dismissed it won't be re-flagged
until its text changes — stability over marginal improvement, the right
call for the calm ESL persona.

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd
2026-06-27 00:18:23 -07:00

474 lines
18 KiB
Go

package suggestions
import (
"bytes"
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"path/filepath"
"testing"
"github.com/go-chi/chi/v5"
"gitea.parodia.dev/drwily/petal/internal/db"
"gitea.parodia.dev/drwily/petal/internal/llm"
)
// stubClient returns a canned checkpoint response; it never touches the network.
type stubClient struct {
response string
calls int
}
func (s *stubClient) Complete(_ context.Context, _ llm.CompletionRequest) (string, error) {
s.calls++
return s.response, nil
}
func (s *stubClient) Stream(_ context.Context, _ llm.CompletionRequest) (<-chan string, error) {
ch := make(chan string)
close(ch)
return ch, nil
}
// newTestServer wires a real DB, a seeded document, and the suggestion routes
// (both the doc-scoped and the per-suggestion mounts) onto one router.
func newTestServer(t *testing.T, client llm.LLMClient) (http.Handler, string, *Handler) {
t.Helper()
database, err := db.Open(filepath.Join(t.TempDir(), "test.db"))
if err != nil {
t.Fatalf("open db: %v", err)
}
t.Cleanup(func() { database.Close() })
// Seed a document with some content to check.
var docID string
err = database.QueryRow(
`INSERT INTO documents (user_id, content_text) VALUES (?, ?) RETURNING id`,
db.LocalUserID, "I has two apple.",
).Scan(&docID)
if err != nil {
t.Fatalf("seed doc: %v", err)
}
h := New(database, client)
r := chi.NewRouter()
r.Route("/docs", func(dr chi.Router) { h.RegisterDocRoutes(dr) })
r.Mount("/suggestions", h.Routes())
return r, docID, h
}
func do(t *testing.T, srv http.Handler, method, path, body string) *httptest.ResponseRecorder {
t.Helper()
var r *http.Request
if body != "" {
r = httptest.NewRequest(method, path, bytes.NewBufferString(body))
} else {
r = httptest.NewRequest(method, path, nil)
}
rec := httptest.NewRecorder()
srv.ServeHTTP(rec, r)
return rec
}
func TestCheckpointFlow(t *testing.T) {
client := &stubClient{response: `{"suggestions":[
{"original":"I has","replacement":"I have","explanation":"subject-verb agreement","type":"grammar"},
{"original":"two apple","replacement":"two apples","explanation":"plural noun","type":"grammar"}
]}`}
srv, docID, _ := newTestServer(t, client)
// Run a checkpoint → two pending suggestions, with positions located.
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
if rec.Code != http.StatusOK {
t.Fatalf("check: code=%d body=%s", rec.Code, rec.Body)
}
var got []db.Suggestion
if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
t.Fatalf("decode: %v", err)
}
if len(got) != 2 {
t.Fatalf("want 2 suggestions, got %d: %+v", len(got), got)
}
if got[0].Original != "I has" || got[0].FromPos != 0 {
t.Fatalf("first suggestion anchoring wrong: %+v", got[0])
}
if got[0].Status != db.SuggestionStatusPending {
t.Fatalf("new suggestion should be pending: %+v", got[0])
}
// Listing returns the same pending set.
rec = do(t, srv, http.MethodGet, "/docs/"+docID+"/suggestions", "")
var listed []db.Suggestion
_ = json.Unmarshal(rec.Body.Bytes(), &listed)
if len(listed) != 2 {
t.Fatalf("list pending: want 2, got %d", len(listed))
}
// Accept the first, dismiss the second.
if rec = do(t, srv, http.MethodPost, "/suggestions/"+got[0].ID+"/accept", ""); rec.Code != http.StatusNoContent {
t.Fatalf("accept: code=%d body=%s", rec.Code, rec.Body)
}
if rec = do(t, srv, http.MethodPost, "/suggestions/"+got[1].ID+"/dismiss", ""); rec.Code != http.StatusNoContent {
t.Fatalf("dismiss: code=%d body=%s", rec.Code, rec.Body)
}
// Pending list is now empty (accepted/dismissed are excluded).
rec = do(t, srv, http.MethodGet, "/docs/"+docID+"/suggestions", "")
_ = json.Unmarshal(rec.Body.Bytes(), &listed)
if len(listed) != 0 {
t.Fatalf("pending after resolve: want 0, got %d", len(listed))
}
// Re-accepting an already-resolved suggestion 404s.
if rec = do(t, srv, http.MethodPost, "/suggestions/"+got[0].ID+"/accept", ""); rec.Code != http.StatusNotFound {
t.Fatalf("re-accept: want 404, got %d", rec.Code)
}
}
// TestResolvedSuggestionsNotReproposed proves a checkpoint won't re-nag a
// sentence the user already accepted or dismissed: the model returns the same
// raw batch on the next pass (it has no memory), but the resolved edits are
// suppressed. This is the "accept it, then it nags again moments later" bug.
func TestResolvedSuggestionsNotReproposed(t *testing.T) {
client := &stubClient{response: `{"suggestions":[
{"original":"I has","replacement":"I have","explanation":"subject-verb agreement","type":"grammar"},
{"original":"two apple","replacement":"two apples","explanation":"plural noun","type":"grammar"}
]}`}
srv, docID, h := newTestServer(t, client)
// Zero the checkpoint floor so the second pass runs instead of being throttled.
h.Limit = llm.NewRateLimiter(0)
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
var got []db.Suggestion
_ = json.Unmarshal(rec.Body.Bytes(), &got)
if len(got) != 2 {
t.Fatalf("first pass: want 2, got %d", len(got))
}
// Accept one, dismiss the other.
do(t, srv, http.MethodPost, "/suggestions/"+got[0].ID+"/accept", "")
do(t, srv, http.MethodPost, "/suggestions/"+got[1].ID+"/dismiss", "")
// Second checkpoint returns the identical raw batch — both must be suppressed.
rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
if rec.Code != http.StatusOK {
t.Fatalf("second check: code=%d body=%s", rec.Code, rec.Body)
}
var again []db.Suggestion
if err := json.Unmarshal(rec.Body.Bytes(), &again); err != nil {
t.Fatalf("decode: %v", err)
}
if len(again) != 0 {
t.Fatalf("resolved suggestions should not be re-proposed, got %d: %+v", len(again), again)
}
}
// TestFickleEditsSuppressed proves the suppressor kills the "keeps going back and
// forth on a few sentences" behavior seen live on the Missing Key doc: a later
// pass that (a) reverses an edit the user just accepted — even with the editor's
// double→single quote churn that defeats a byte-exact match — or (b) re-polishes
// the model's own accepted output. A genuinely new edit on a fresh sentence still
// survives.
func TestFickleEditsSuppressed(t *testing.T) {
client := &stubClient{response: `{"suggestions":[
{"original":"He left \"early,\" because of the rain.","replacement":"He left \"early,\" due to the rain.","explanation":"smoother","type":"phrasing"},
{"original":"The cat always have a calm face.","replacement":"The cat always has a calm face.","explanation":"agreement","type":"grammar"}
]}`}
srv, docID, h := newTestServer(t, client)
h.Limit = llm.NewRateLimiter(0)
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
var got []db.Suggestion
_ = json.Unmarshal(rec.Body.Bytes(), &got)
if len(got) != 2 {
t.Fatalf("first pass: want 2, got %d", len(got))
}
for _, s := range got {
do(t, srv, http.MethodPost, "/suggestions/"+s.ID+"/accept", "")
}
// Reversal of the first accept (note the " → ' quote churn) and a re-polish of
// the second accept must both be dropped; only the unrelated edit survives.
client.response = `{"suggestions":[
{"original":"He left 'early,' due to the rain.","replacement":"He left 'early,' because of the rain.","explanation":"reverts the accepted edit","type":"phrasing"},
{"original":"The cat always has a calm face.","replacement":"The cat always seems to have a calm face.","explanation":"re-polishes accepted output","type":"phrasing"},
{"original":"due to the rain","replacement":"because of the rain","explanation":"sub-clause reversal of the accepted span","type":"phrasing"},
{"original":"She drived home.","replacement":"She drove home.","explanation":"past tense","type":"grammar"}
]}`
rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
var again []db.Suggestion
if err := json.Unmarshal(rec.Body.Bytes(), &again); err != nil {
t.Fatalf("decode: %v", err)
}
if len(again) != 1 || again[0].Original != "She drived home." {
t.Fatalf("want only the new edit to survive, got %d: %+v", len(again), again)
}
}
// TestVoicePassCoexists proves the voice pass and the grammar checkpoint own
// disjoint pending families: running one never wipes the other's flags, and
// each endpoint returns the unified pending set.
func TestVoicePassCoexists(t *testing.T) {
// One client serves both passes; the prompt distinguishes them but the stub
// just echoes whatever we set before each call.
client := &switchClient{}
srv, docID, h := newTestServer(t, client)
// Zero the voice floor so the test can re-run the pass without waiting out
// the real 20s interval; the family-scoping logic is what's under test here.
h.VoiceLimit = llm.NewRateLimiter(0)
// Grammar checkpoint first → one grammar flag.
client.response = `{"suggestions":[{"original":"I has","replacement":"I have","explanation":"agreement","type":"grammar"}]}`
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
if rec.Code != http.StatusOK {
t.Fatalf("check: code=%d body=%s", rec.Code, rec.Body)
}
// Voice pass next → one voice flag (null replacement). It must NOT remove the
// grammar flag; the response is the unified set of both.
client.response = `{"suggestions":[{"original":"two apple","replacement":null,"explanation":"sounds more formal","type":"voice"}]}`
rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/voice", "")
if rec.Code != http.StatusOK {
t.Fatalf("voice: code=%d body=%s", rec.Code, rec.Body)
}
var got []db.Suggestion
if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
t.Fatalf("decode: %v", err)
}
if len(got) != 2 {
t.Fatalf("voice response should carry both families, got %d: %+v", len(got), got)
}
var grammar, voice *db.Suggestion
for i := range got {
switch got[i].Type {
case db.SuggestionTypeGrammar:
grammar = &got[i]
case db.SuggestionTypeVoice:
voice = &got[i]
}
}
if grammar == nil || voice == nil {
t.Fatalf("want one grammar + one voice flag, got %+v", got)
}
if voice.Replacement != "" {
t.Fatalf("voice flag should have empty replacement, got %q", voice.Replacement)
}
// A fresh voice pass that finds nothing replaces only the voice flag; the
// grammar one survives.
client.response = `{"suggestions":[]}`
rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/voice", "")
if rec.Code != http.StatusOK {
t.Fatalf("second voice: code=%d body=%s", rec.Code, rec.Body)
}
_ = json.Unmarshal(rec.Body.Bytes(), &got)
if len(got) != 1 || got[0].Type != db.SuggestionTypeGrammar {
t.Fatalf("after clearing voice, only the grammar flag should remain, got %+v", got)
}
}
// TestCollocationPassCoexists proves the collocation coach is a third
// independent family: it never wipes grammar or voice pending flags, a grammar
// checkpoint never wipes its flags, and each endpoint returns the unified set.
func TestCollocationPassCoexists(t *testing.T) {
client := &switchClient{}
srv, docID, h := newTestServer(t, client)
// Zero the floors so the test can re-run passes without waiting them out.
h.Limit = llm.NewRateLimiter(0)
h.VoiceLimit = llm.NewRateLimiter(0)
h.CollocationLimit = llm.NewRateLimiter(0)
// Grammar + voice first, so all three families are exercised.
client.response = `{"suggestions":[{"original":"I has","replacement":"I have","explanation":"agreement","type":"grammar"}]}`
if rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", ""); rec.Code != http.StatusOK {
t.Fatalf("check: code=%d body=%s", rec.Code, rec.Body)
}
client.response = `{"suggestions":[{"original":"two apple","replacement":null,"explanation":"sounds formal","type":"voice"}]}`
if rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/voice", ""); rec.Code != http.StatusOK {
t.Fatalf("voice: code=%d body=%s", rec.Code, rec.Body)
}
// Collocation pass → a third flag (with a replacement). It must keep the
// grammar and voice flags; the response is the unified set of all three.
client.response = `{"suggestions":[{"original":"two apple","replacement":"two apples","explanation":"Natives usually say…","type":"collocation"}]}`
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/collocation", "")
if rec.Code != http.StatusOK {
t.Fatalf("collocation: code=%d body=%s", rec.Code, rec.Body)
}
var got []db.Suggestion
if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
t.Fatalf("decode: %v", err)
}
byType := map[string]bool{}
for _, s := range got {
byType[s.Type] = true
}
if !byType[db.SuggestionTypeGrammar] || !byType[db.SuggestionTypeVoice] || !byType[db.SuggestionTypeCollocation] {
t.Fatalf("collocation response should carry all three families, got %+v", got)
}
// A grammar checkpoint must NOT wipe the voice or collocation flags.
client.response = `{"suggestions":[]}`
rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
if rec.Code != http.StatusOK {
t.Fatalf("second check: code=%d body=%s", rec.Code, rec.Body)
}
_ = json.Unmarshal(rec.Body.Bytes(), &got)
byType = map[string]bool{}
for _, s := range got {
byType[s.Type] = true
}
if byType[db.SuggestionTypeGrammar] {
t.Fatalf("grammar flag should have cleared, got %+v", got)
}
if !byType[db.SuggestionTypeVoice] || !byType[db.SuggestionTypeCollocation] {
t.Fatalf("grammar checkpoint wiped a sibling family, got %+v", got)
}
}
// switchClient returns a response that can be swapped between calls.
type switchClient struct {
response string
calls int
}
func (s *switchClient) Complete(_ context.Context, _ llm.CompletionRequest) (string, error) {
s.calls++
return s.response, nil
}
func (s *switchClient) Stream(_ context.Context, _ llm.CompletionRequest) (<-chan string, error) {
ch := make(chan string)
close(ch)
return ch, nil
}
func TestCheckpointRateLimit(t *testing.T) {
client := &stubClient{response: `{"suggestions":[{"original":"I has","replacement":"I have","explanation":"x","type":"grammar"}]}`}
srv, docID, _ := newTestServer(t, client)
// First check runs the model.
do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
// Immediate second check is throttled — returns the existing set without
// hitting the model again.
do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
if client.calls != 1 {
t.Fatalf("rate limit should suppress the second model call, got %d calls", client.calls)
}
}
// postMechanics submits a deterministic-findings batch (as the client's prose
// detector would) and returns the unified pending set.
func postMechanics(t *testing.T, srv http.Handler, docID, findingsJSON string) []db.Suggestion {
t.Helper()
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/mechanics", `{"findings":`+findingsJSON+`}`)
if rec.Code != http.StatusOK {
t.Fatalf("mechanics: code=%d body=%s", rec.Code, rec.Body)
}
var got []db.Suggestion
if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
t.Fatalf("decode: %v", err)
}
return got
}
// TestMechanicsPersistsFindings proves the endpoint persists client-detected
// findings as a 'mechanics' family with the exact offsets the client supplied,
// and that a later grammar checkpoint leaves them untouched (own family).
func TestMechanicsPersistsFindings(t *testing.T) {
client := &stubClient{response: `{"suggestions":[]}`}
srv, docID, _ := newTestServer(t, client)
got := postMechanics(t, srv, docID, `[
{"from":0,"to":1,"original":"i","replacement":"I","explanation":"capitalize I"},
{"from":6,"to":13,"original":"the the","replacement":"the","explanation":"doubled word"}
]`)
var mech []db.Suggestion
for _, s := range got {
if s.Type == db.SuggestionTypeMechanics {
mech = append(mech, s)
}
}
if len(mech) != 2 {
t.Fatalf("want 2 mechanics findings, got %d: %+v", len(mech), got)
}
// The client's exact offsets are preserved verbatim.
for _, s := range mech {
if s.Original == "the the" && (s.FromPos != 6 || s.ToPos != 13) {
t.Errorf("offsets not preserved: %+v", s)
}
}
// A grammar checkpoint must not wipe the mechanics family.
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
if rec.Code != http.StatusOK {
t.Fatalf("check: code=%d body=%s", rec.Code, rec.Body)
}
var after []db.Suggestion
_ = json.Unmarshal(rec.Body.Bytes(), &after)
count := 0
for _, s := range after {
if s.Type == db.SuggestionTypeMechanics {
count++
}
}
if count != 2 {
t.Fatalf("grammar checkpoint disturbed the mechanics family: got %d, want 2", count)
}
}
// TestMechanicsWinsSpanCollision proves that when a mechanics finding and an LLM
// grammar suggestion claim overlapping characters, the LLM card is dropped from
// the response and the exact mechanics fix owns the span.
func TestMechanicsWinsSpanCollision(t *testing.T) {
// LLM grammar suggestion covers "the the cat", overlapping the mechanics
// "the the" finding at [0,7].
client := &stubClient{response: `{"suggestions":[
{"original":"the the cat","replacement":"the cat","explanation":"wordy","type":"grammar"}
]}`}
srv, docID, h := newTestServer(t, client)
if _, err := h.DB.Exec(`UPDATE documents SET content_text = ? WHERE id = ?`, "the the cat sat", docID); err != nil {
t.Fatalf("set content: %v", err)
}
// Persist the mechanics finding, then run the grammar pass.
postMechanics(t, srv, docID, `[{"from":0,"to":7,"original":"the the","replacement":"the","explanation":"doubled word"}]`)
rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
if rec.Code != http.StatusOK {
t.Fatalf("check: code=%d body=%s", rec.Code, rec.Body)
}
var got []db.Suggestion
if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
t.Fatalf("decode: %v", err)
}
for _, s := range got {
if s.Type == db.SuggestionTypeGrammar {
t.Fatalf("overlapping grammar card should have been dropped in favor of mechanics, got %+v", got)
}
}
if len(got) != 1 || got[0].Type != db.SuggestionTypeMechanics {
t.Fatalf("want sole mechanics finding, got %+v", got)
}
}
// TestMechanicsActionedSuppression proves a dismissed mechanics fix is not
// re-proposed on the next submission of the same finding.
func TestMechanicsActionedSuppression(t *testing.T) {
client := &stubClient{response: `{"suggestions":[]}`}
srv, docID, _ := newTestServer(t, client)
findings := `[{"from":6,"to":13,"original":"the the","replacement":"the","explanation":"doubled word"}]`
got := postMechanics(t, srv, docID, findings)
if len(got) != 1 {
t.Fatalf("want 1 finding, got %+v", got)
}
// Dismiss it, then resubmit the same finding — it must stay suppressed.
do(t, srv, http.MethodPost, "/suggestions/"+got[0].ID+"/dismiss", "")
again := postMechanics(t, srv, docID, findings)
if len(again) != 0 {
t.Fatalf("dismissed mechanics fix should not reappear, got %+v", again)
}
}