petal/internal/suggestions/reconcile.go

package suggestions

import (
	"database/sql"

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

// Reconciliation replaces the old "delete the family, insert the new batch"
// shape of every pass. A suggestion the pass proposes again is the *same*
// suggestion: it keeps its row, and therefore its id, its created_at and — most
// visibly — the explanation it was first given. The model re-words its reasoning
// every time it is asked, so re-inserting meant one unchanged mistake carried
// three different explanations in a single sitting.
//
// The id is what the frontend keys its cards on, so a stable id is also what
// keeps the rail from emptying and refilling, a card from collapsing mid-read,
// and the arrival chime from re-firing for advice she has already seen.

// pendingRow is the part of an existing pending suggestion reconciliation cares
// about.
type pendingRow struct {
	id          string
	original    string
	replacement string
	chunkHash   string
	from        int
}

// loadPending reads the pending rows a pass owns. `where` is the pass's own
// scoping clause (by source, and for the model passes by family) — the same
// fragment that used to scope its DELETE.
func loadPending(tx *sql.Tx, docID, where string) ([]pendingRow, error) {
	rows, err := tx.Query(
		`SELECT id, original, replacement, chunk_hash, from_pos FROM suggestions
		  WHERE doc_id = ? AND status = ? AND `+where,
		docID, db.SuggestionStatusPending,
	)
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	var out []pendingRow
	for rows.Next() {
		var r pendingRow
		if err := rows.Scan(&r.id, &r.original, &r.replacement, &r.chunkHash, &r.from); err != nil {
			return nil, err
		}
		out = append(out, r)
	}
	return out, rows.Err()
}

// editKey identifies an edit by what it proposes, not where: "this exact change
// to this exact text". Normalized like the suppression comparisons, so the
// editor's quote rewriting and a reflowed paragraph don't read as a new edit.
func editKey(original, replacement string) string {
	return normalizeForDedup(original) + "\x00" + normalizeForDedup(replacement)
}

// editIndex matches freshly proposed edits against the rows already standing.
type editIndex struct {
	rows  []pendingRow
	used  []bool
	byKey map[string][]int
}

func indexByEdit(rows []pendingRow) *editIndex {
	idx := &editIndex{rows: rows, used: make([]bool, len(rows)), byKey: map[string][]int{}}
	for i, r := range rows {
		k := editKey(r.original, r.replacement)
		idx.byKey[k] = append(idx.byKey[k], i)
	}
	return idx
}

// take claims the standing row for this edit, if there is one. When a document
// repeats the same mistake, `near` (the fresh span's start) picks the closest
// standing row, so two identical cards keep their own identities instead of
// trading them whenever the text between them grows.
func (i *editIndex) take(original, replacement string, near int) (pendingRow, bool) {
	best, bestDist := -1, 0
	for _, n := range i.byKey[editKey(original, replacement)] {
		if i.used[n] {
			continue
		}
		d := i.rows[n].from - near
		if d < 0 {
			d = -d
		}
		if best < 0 || d < bestDist {
			best, bestDist = n, d
		}
	}
	if best < 0 {
		return pendingRow{}, false
	}
	i.used[best] = true
	return i.rows[best], true
}

// reposition updates the advisory offsets (and the sentence a row belongs to)
// without touching anything the writer can see. The frontend re-anchors by
// string at render time, so these only matter for the local-vs-model span
// arbitration in dedupeSpans.
func reposition(tx *sql.Tx, row pendingRow, from, to int, chunkHash string) error {
	if row.from == from && row.chunkHash == chunkHash {
		return nil
	}
	_, err := tx.Exec(
		`UPDATE suggestions SET from_pos = ?, to_pos = ?, chunk_hash = ? WHERE id = ?`,
		from, to, chunkHash, row.id,
	)
	return err
}

// reconcilePending brings a model pass's family in line with what it just
// proposed, sentence by sentence:
//
//   - A row on a sentence this pass didn't ask about is kept untouched — that
//     is the whole point of chunking. Only its offsets are refreshed.
//   - A row on a sentence that no longer exists in the document is dropped: she
//     rewrote or deleted it.
//   - A row on a sentence the pass *did* ask about survives only if the model
//     proposed the same edit again, in which case it keeps its identity.
//
// `fresh` names the sentences the model was asked about (nil when it wasn't
// called at all). inPlayAll marks the whole-document passes — voice and the
// collocation coach — where every row is up for re-proposal because the model
// just re-read everything.
//
// `pairLang` is the writer's own language, needed only to type a finding that
// turns out to be her language rendered into English (see language.go).
func (h *Handler) reconcilePending(
	docID, contentText, pairLang string,
	raw []llm.RawSuggestion,
	scope pendingScope,
	chunks, fresh []chunk,
	inPlayAll bool,
) error {
	tx, err := h.DB.Begin()
	if err != nil {
		return err
	}
	defer tx.Rollback()

	existing, err := loadPending(tx, docID, scope.deleteWhere)
	if err != nil {
		return err
	}

	present := hashSet(chunks)
	asked := hashSet(fresh)
	modelRan := inPlayAll || fresh != nil

	// Sentences to hand back to the model next time, because a row we were
	// caching on them turned out to be unanchorable (see below).
	reopen := map[string]bool{}

	var inPlay []pendingRow
	for _, r := range existing {
		switch {
		// A row whose sentence we can't name is never cached — it is re-examined
		// whenever the model speaks, and left alone when it doesn't.
		case inPlayAll, r.chunkHash == "" && modelRan, asked[r.chunkHash]:
			inPlay = append(inPlay, r)
		case r.chunkHash != "" && !present[r.chunkHash]:
			if _, err := tx.Exec(`DELETE FROM suggestions WHERE id = ?`, r.id); err != nil {
				return err
			}
		default:
			// Untouched sentence: keep the card exactly as she last saw it.
			from, to := locate(contentText, r.original)
			if from < 0 {
				// The sentence is unchanged in substance but the quoted span no
				// longer matches byte for byte — a quote mark the editor rewrote
				// inside it, say. The frontend anchors by that string, so this card
				// can't be shown; drop it and let the sentence be read again rather
				// than cache advice nobody can see.
				reopen[r.chunkHash] = true
				if _, err := tx.Exec(`DELETE FROM suggestions WHERE id = ?`, r.id); err != nil {
					return err
				}
				continue
			}
			if err := reposition(tx, r, from, to, r.chunkHash); err != nil {
				return err
			}
		}
	}
	for h := range reopen {
		delete(present, h)
	}

	sup, err := buildSuppressor(tx, docID)
	if err != nil {
		return err
	}

	index := indexByEdit(inPlay)
	kept := make(map[string]bool, len(inPlay))
	for _, s := range raw {
		if sup.suppressed(s.Original, s.Replacement) {
			continue
		}
		from, to := locate(contentText, s.Original)
		// Attribute the finding to a sentence the model was actually shown before
		// falling back to the whole document: a short span ("the the") can occur in
		// two sentences, and crediting it to the cached one would drop it as advice
		// we already have.
		hash := chunkFor(s.Original, fresh)
		if hash == "" {
			hash = chunkFor(s.Original, chunks)
		}
		// A sentence we didn't ask about already has whatever advice it deserves.
		// The model can't normally quote one — it was only shown the delta — but if
		// it wanders there anyway, the cached card stands rather than gaining a
		// twin.
		if !inPlayAll && hash != "" && present[hash] && !asked[hash] {
			continue
		}
		if row, ok := index.take(s.Original, s.Replacement, from); ok {
			kept[row.id] = true
			if err := reposition(tx, row, from, to, hash); err != nil {
				return err
			}
			continue
		}
		// A pass with a forced type owns its family outright and is never asked
		// about translation: voice reads whole paragraphs for tone, and the
		// collocation coach is about English word pairings. Only the open-typed
		// grammar checkpoint can turn out to have been handed her own language.
		typ := scope.forceType
		if typ == "" {
			typ = normalizeType(s.Type)
			if isTranslation(s.Original, s.Replacement, pairLang) {
				typ = db.SuggestionTypeTranslate
			}
		}
		if _, err := tx.Exec(
			`INSERT INTO suggestions (doc_id, from_pos, to_pos, original, replacement, explanation, type, source, chunk_hash)
			 VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`,
			docID, from, to, s.Original, s.Replacement, s.Explanation, typ, db.SuggestionSourceLLM, hash,
		); err != nil {
			return err
		}
	}

	// Asked about and not proposed again: the model has changed its mind, or she
	// has fixed it.
	for _, r := range inPlay {
		if kept[r.id] {
			continue
		}
		if _, err := tx.Exec(`DELETE FROM suggestions WHERE id = ?`, r.id); err != nil {
			return err
		}
	}

	// Record the sentences this family has now read. Every sentence still in the
	// document has been read by *some* pass: the ones just asked about now, the
	// rest in an earlier round.
	if scope.chunked {
		if _, err := tx.Exec(
			`DELETE FROM checked_chunks WHERE doc_id = ? AND family = ?`, docID, scope.family,
		); err != nil {
			return err
		}
		for h := range present {
			if _, err := tx.Exec(
				`INSERT INTO checked_chunks (doc_id, family, hash) VALUES (?, ?, ?)`,
				docID, scope.family, h,
			); err != nil {
				return err
			}
		}
	}

	return tx.Commit()
}

// checkedChunks loads the sentences a family read on its last pass.
func (h *Handler) checkedChunks(docID, family string) (map[string]bool, error) {
	rows, err := h.DB.Query(
		`SELECT hash FROM checked_chunks WHERE doc_id = ? AND family = ?`, docID, family,
	)
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	out := map[string]bool{}
	for rows.Next() {
		var hash string
		if err := rows.Scan(&hash); err != nil {
			return nil, err
		}
		out[hash] = true
	}
	return out, rows.Err()
}