Files
petal/internal/suggestions/handlers_test.go
prosolis 8aa437ec82 Phase 12 + 13: collocation coach + vocabulary garden
Phase 12 — collocation coach: a third suggestion family for gentle
"natives usually say…" hints on non-native word pairings, reusing the
existing runPass/pendingScope/rail machinery.
- llm/collocation.go (RunCollocation, 25s floor, reuses ParseCheckpoint)
  + collocationSystemPrompt/CollocationMessages (warm, Mandarin gloss,
  defers grammar/spelling to the grammar family)
- migration 0005 rebuilds the suggestions table to extend the type CHECK
  (SQLite can't ALTER a CHECK)
- collocationScope + CollocationLimit + POST /{id}/collocation
- fix: grammarScope was `type != 'voice'` and would wipe the new
  collocation flags; now `type NOT IN ('voice','collocation')`
- frontend: --color-blossom, "Make it sound natural 🌸" pill,
  collocating/runCollocation in useCheckpoint, StatusBar dot

Phase 13 — vocabulary garden: capture looked-up words and surface them
for gentle spaced repetition.
- new internal/vocab package: migration 0006 (vocab_words, SM-2-lite
  columns, doc_id ON DELETE SET NULL, UNIQUE(user_id,word)),
  scheduler.go (Leitner ladder 1/3/7/16/35 then geometric; gentle
  "again", no streak-shaming), handlers (capture-upsert/list/due/
  review/delete, owner-scoped, SQLite-side datetime math)
- auto-capture on word lookup (dictionary-known words only, captures
  the surrounding sentence + doc_id) + 🤍/💚 toggle on WordCard
- GardenPanel: blossom grid (bloom by reps), flashcard review (sentence
  blanked, flip, again/good/easy, recognition↔production), sleepy-kitten
  footer; opened from a global 🌷 header button

Tests: TestCollocationPassCoexists, vocab scheduler + handlers, db CHECK
extended. go build/vet/test + tsc + vite + vitest (51/51) clean;
migration verified against a copy of the live DB; live backend smoke
walked the full vocab lifecycle + the warm-502 collocation path.

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd
2026-06-26 15:50:25 -07:00

319 lines
12 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)
}
}
// 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)
}
}