petal/internal/suggestions/stability_test.go

package suggestions

import (
	"encoding/json"
	"net/http"
	"strings"
	"testing"

	"gitea.parodia.dev/drwily/petal/internal/db"
	"gitea.parodia.dev/drwily/petal/internal/llm"
)

// byOriginal indexes a pending set by the text each card flags.
func byOriginal(in []db.Suggestion) map[string]db.Suggestion {
	out := map[string]db.Suggestion{}
	for _, s := range in {
		out[s.Original] = s
	}
	return out
}

// TestUntouchedSentencesKeepTheirCards is the heart of the stability work: she
// edits one sentence, and the cards on every other sentence stay exactly as they
// were — same id (so the rail keeps the card instead of remounting it), same
// explanation (the model re-words its reasoning every time it is asked, and one
// unchanged mistake used to carry three different explanations in a sitting).
// The model is only asked about the sentence that changed.
func TestUntouchedSentencesKeepTheirCards(t *testing.T) {
	client := &stubClient{response: `{"suggestions":[
		{"original":"I has two apple","replacement":"I have two apples","explanation":"first wording","type":"grammar"},
		{"original":"She go to market","replacement":"She goes to market","explanation":"agreement","type":"grammar"}
	]}`}
	srv, docID, h := newTestServer(t, client)
	h.Limit = llm.NewRateLimiter(0)
	setDocText(t, h, docID, "I has two apple. She go to market yesterday.")

	rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
	var first []db.Suggestion
	if err := json.Unmarshal(rec.Body.Bytes(), &first); err != nil {
		t.Fatalf("decode: %v", err)
	}
	if len(first) != 2 {
		t.Fatalf("first pass: want 2, got %d: %+v", len(first), first)
	}
	kept := byOriginal(first)["I has two apple"]

	// She fixes only the second sentence. The model, asked again, re-words its
	// reasoning about the first — which it must never get the chance to do.
	setDocText(t, h, docID, "I has two apple. She goes to market yesterday.")
	client.response = `{"suggestions":[
		{"original":"I has two apple","replacement":"I have two apples","explanation":"REWORDED","type":"grammar"}
	]}`
	rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
	var second []db.Suggestion
	if err := json.Unmarshal(rec.Body.Bytes(), &second); err != nil {
		t.Fatalf("decode: %v", err)
	}

	if strings.Contains(client.lastPrompt, "I has two apple") {
		t.Fatalf("untouched sentence was sent to the model:\n%s", client.lastPrompt)
	}
	if !strings.Contains(client.lastPrompt, "She goes to market") {
		t.Fatalf("edited sentence was not sent to the model:\n%s", client.lastPrompt)
	}

	now := byOriginal(second)["I has two apple"]
	if now.ID != kept.ID {
		t.Fatalf("card was remounted: id %q became %q", kept.ID, now.ID)
	}
	if now.Explanation != "first wording" {
		t.Fatalf("explanation drifted: %q", now.Explanation)
	}
	// The fixed sentence's card is gone, and the model's stray re-proposal for the
	// cached sentence did not become a second card.
	if len(second) != 1 {
		t.Fatalf("want exactly one card left, got %d: %+v", len(second), second)
	}
}

// TestUnchangedDocumentSkipsTheModel proves a check with nothing new to read
// costs nothing: no model call, and every card left standing untouched. This is
// the doc-open and tone-less re-check path.
func TestUnchangedDocumentSkipsTheModel(t *testing.T) {
	client := &stubClient{response: `{"suggestions":[
		{"original":"I has","replacement":"I have","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 first []db.Suggestion
	_ = json.Unmarshal(rec.Body.Bytes(), &first)
	if len(first) != 1 || client.calls != 1 {
		t.Fatalf("first pass: %d cards, %d calls", len(first), client.calls)
	}

	rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
	var second []db.Suggestion
	if err := json.Unmarshal(rec.Body.Bytes(), &second); err != nil {
		t.Fatalf("decode: %v", err)
	}
	if client.calls != 1 {
		t.Fatalf("re-checking an unedited document called the model %d times", client.calls)
	}
	if len(second) != 1 || second[0].ID != first[0].ID {
		t.Fatalf("card did not survive an idle re-check: %+v", second)
	}
}

// TestDeletedSentenceDropsItsCard covers the other half of the skip path: she
// removes a flagged sentence outright, so nothing changed that the model could
// be asked about — but its card must still go.
func TestDeletedSentenceDropsItsCard(t *testing.T) {
	client := &stubClient{response: `{"suggestions":[
		{"original":"I has","replacement":"I have","explanation":"agreement","type":"grammar"}
	]}`}
	srv, docID, h := newTestServer(t, client)
	h.Limit = llm.NewRateLimiter(0)

	do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
	setDocText(t, h, docID, "")

	rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
	var got []db.Suggestion
	if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
		t.Fatalf("decode: %v", err)
	}
	if len(got) != 0 {
		t.Fatalf("card outlived its sentence: %+v", got)
	}
}

// TestToneChangeReopensEverySentence: the checkpoint's advice is written for the
// document's tone, so switching from a journal to an academic essay has to
// re-read sentences that haven't changed a character.
func TestToneChangeReopensEverySentence(t *testing.T) {
	client := &stubClient{response: `{"suggestions":[
		{"original":"I has","replacement":"I have","explanation":"agreement","type":"grammar"}
	]}`}
	srv, docID, h := newTestServer(t, client)
	h.Limit = llm.NewRateLimiter(0)

	do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")
	if _, err := h.DB.Exec(`UPDATE documents SET tone = 'academic' WHERE id = ?`, docID); err != nil {
		t.Fatalf("set tone: %v", err)
	}
	do(t, srv, http.MethodPost, "/docs/"+docID+"/check", "")

	if client.calls != 2 {
		t.Fatalf("tone change did not re-read the document: %d model calls", client.calls)
	}
}

// TestMechanicsFindingsKeepTheirRows: the rule pack re-runs 250 ms after every
// keystroke. A finding it still reports must keep its row, or the rail would
// remount several times a sentence — collapsing a card she has open, and
// re-firing the arrival chime for advice she is already reading.
func TestMechanicsFindingsKeepTheirRows(t *testing.T) {
	srv, docID, _ := newTestServer(t, &stubClient{response: `{"suggestions":[]}`})
	body := `{"findings":[
		{"from":0,"to":5,"original":"I has","replacement":"I have","explanation":"agreement"},
		{"from":6,"to":15,"original":"two apple","replacement":"two apples","explanation":"plural"}
	]}`

	rec := do(t, srv, http.MethodPost, "/docs/"+docID+"/mechanics", body)
	var first []db.Suggestion
	if err := json.Unmarshal(rec.Body.Bytes(), &first); err != nil {
		t.Fatalf("decode: %v", err)
	}
	if len(first) != 2 {
		t.Fatalf("want 2 rows, got %d", len(first))
	}

	// She types elsewhere: same findings, shifted spans, one of them now fixed.
	rec = do(t, srv, http.MethodPost, "/docs/"+docID+"/mechanics", `{"findings":[
		{"from":20,"to":25,"original":"I has","replacement":"I have","explanation":"agreement"}
	]}`)
	var second []db.Suggestion
	if err := json.Unmarshal(rec.Body.Bytes(), &second); err != nil {
		t.Fatalf("decode: %v", err)
	}
	if len(second) != 1 {
		t.Fatalf("want 1 row, got %d: %+v", len(second), second)
	}
	if second[0].ID != byOriginal(first)["I has"].ID {
		t.Fatalf("surviving finding was given a new identity: %+v", second[0])
	}
	if second[0].FromPos != 20 {
		t.Fatalf("span did not follow the text: %+v", second[0])
	}
}