Files
petal/internal/suggestions/handlers.go
prosolis 0fa70979a0 Phase 5: voice consistency pass
Tier-1 voice-consistency pass: whole-document LLM review surfacing passages
that read tonally out of place (formal/over-polished/paraphrased-too-closely),
as honey-decorated `voice` flags with no correction (awareness-only).

- internal/llm/voice.go: RunVoice sends the whole document (no TruncateDoc),
  MaxTokens 2048, 20s per-doc floor (VoiceInterval). Standalone voice prompt
  in prompts.go (not bundled with the grammar checkpoint, per spec).
- internal/suggestions: POST /api/docs/:id/voice. replacePending is now
  family-scoped (pendingScope) so grammar and voice never clobber each other's
  pending flags; both passes return the unified pending set. check/voice share
  one runPass helper. TestVoicePassCoexists covers both directions.
- Frontend: api.voiceDoc, useCheckpoint voicing/runVoice, honey "Check my
  voice" toolbar pill, breathing honey dot in StatusBar.

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd
2026-06-25 21:16:53 -07:00

288 lines
9.3 KiB
Go

// Package suggestions implements the grammar-checkpoint endpoint and the
// accept/dismiss surface for LLM-proposed edits. Checkpoints run a single LLM
// pass over a document and persist the resulting pending suggestions; the
// frontend re-anchors each one by its `original` string at render time, so the
// stored positions are advisory only (spec Note #6).
package suggestions
import (
"context"
"database/sql"
"encoding/json"
"errors"
"net/http"
"strings"
"github.com/go-chi/chi/v5"
"gitea.parodia.dev/drwily/petal/internal/db"
"gitea.parodia.dev/drwily/petal/internal/llm"
)
// Handler holds the dependencies for the checkpoint + suggestion routes. The
// grammar checkpoint and the voice pass each get their own per-document rate
// limiter — they are independent passes with different cadences.
type Handler struct {
DB *db.DB
Client llm.LLMClient
Limit *llm.RateLimiter // grammar checkpoint floor
VoiceLimit *llm.RateLimiter // voice-consistency floor
}
// New constructs a Handler with per-document checkpoint and voice rate limiters.
func New(database *db.DB, client llm.LLMClient) *Handler {
return &Handler{
DB: database,
Client: client,
Limit: llm.NewRateLimiter(llm.CheckpointInterval),
VoiceLimit: llm.NewRateLimiter(llm.VoiceInterval),
}
}
// RegisterDocRoutes adds the document-scoped routes (check + voice + list) onto
// the existing /api/docs router so they share its base path.
func (h *Handler) RegisterDocRoutes(r chi.Router) {
r.Post("/{id}/check", h.check)
r.Post("/{id}/voice", h.voice)
r.Get("/{id}/suggestions", h.listForDoc)
}
// Routes returns the router mounted at /api/suggestions for per-suggestion
// actions.
func (h *Handler) Routes() chi.Router {
r := chi.NewRouter()
r.Post("/{id}/accept", h.accept)
r.Post("/{id}/dismiss", h.dismiss)
r.Post("/{id}/chat", h.chat)
return r
}
// check runs a grammar checkpoint over the document. Fast, typing-cadence pass.
func (h *Handler) check(w http.ResponseWriter, r *http.Request) {
h.runPass(w, r, h.Limit, llm.RunCheckpoint, grammarScope)
}
// voice runs a Tier-1 voice-consistency pass over the whole document. Slow,
// explicit-action pass; replaces only the pending voice flags.
func (h *Handler) voice(w http.ResponseWriter, r *http.Request) {
h.runPass(w, r, h.VoiceLimit, llm.RunVoice, voiceScope)
}
// pass is the signature shared by the grammar checkpoint and the voice pass:
// given the document text it returns the model's raw suggestions.
type pass func(ctx context.Context, client llm.LLMClient, contentText string) ([]llm.RawSuggestion, error)
// runPass is the shared body for both LLM passes. It loads the document text,
// enforces the pass's per-document rate limit, runs the model, swaps in the
// fresh batch scoped to this family, and returns the document's FULL pending set
// (both families) so the client always renders a unified picture.
func (h *Handler) runPass(w http.ResponseWriter, r *http.Request, limiter *llm.RateLimiter, run pass, scope pendingScope) {
docID := chi.URLParam(r, "id")
var contentText string
err := h.DB.QueryRow(
`SELECT content_text FROM documents WHERE id = ? AND user_id = ?`,
docID, db.LocalUserID,
).Scan(&contentText)
if errors.Is(err, sql.ErrNoRows) {
errorJSON(w, http.StatusNotFound, "document not found")
return
}
if err != nil {
serverError(w, err)
return
}
// Nothing to analyze on an empty document — skip the LLM round-trip.
if strings.TrimSpace(contentText) == "" {
writeJSON(w, http.StatusOK, []db.Suggestion{})
return
}
if ok, _ := limiter.Allow(docID); !ok {
// Throttled: return the existing pending set unchanged rather than an
// error, so the frontend keeps showing current suggestions.
existing, err := h.fetchPending(docID)
if err != nil {
serverError(w, err)
return
}
writeJSON(w, http.StatusOK, existing)
return
}
raw, err := run(r.Context(), h.Client, contentText)
if err != nil {
errorJSON(w, http.StatusBadGateway, "llm pass failed: "+err.Error())
return
}
if err := h.replacePending(docID, contentText, raw, scope); err != nil {
serverError(w, err)
return
}
// Return the unified pending set (grammar + voice), not just this batch, so
// a grammar check never drops the voice highlights from the client and the
// throttle path above stays consistent with the success path.
out, err := h.fetchPending(docID)
if err != nil {
serverError(w, err)
return
}
writeJSON(w, http.StatusOK, out)
}
// pendingScope describes how one LLM pass touches the shared suggestions table:
// which family of pending rows it replaces, and the type to stamp on the rows it
// inserts. The grammar checkpoint and voice pass each own a disjoint family, so
// running one never disturbs the other's pending flags.
type pendingScope struct {
deleteWhere string // extra WHERE clause scoping the DELETE to this family
forceType string // if set, every inserted row gets this type; else normalizeType
}
var (
// grammarScope owns the grammar/phrasing/idiom/clarity flags (everything but voice).
grammarScope = pendingScope{deleteWhere: "type != 'voice'", forceType: ""}
// voiceScope owns the voice flags only.
voiceScope = pendingScope{deleteWhere: "type = 'voice'", forceType: db.SuggestionTypeVoice}
)
// replacePending swaps a document's pending suggestions within one family for a
// fresh batch in a single transaction. Accepted/rejected suggestions and the
// other family's pending rows are left untouched.
func (h *Handler) replacePending(docID, contentText string, raw []llm.RawSuggestion, scope pendingScope) error {
tx, err := h.DB.Begin()
if err != nil {
return err
}
defer tx.Rollback()
if _, err := tx.Exec(
`DELETE FROM suggestions WHERE doc_id = ? AND status = ? AND `+scope.deleteWhere,
docID, db.SuggestionStatusPending,
); err != nil {
return err
}
for _, s := range raw {
typ := scope.forceType
if typ == "" {
typ = normalizeType(s.Type)
}
from, to := locate(contentText, s.Original)
if _, err := tx.Exec(
`INSERT INTO suggestions (doc_id, from_pos, to_pos, original, replacement, explanation, type)
VALUES (?, ?, ?, ?, ?, ?, ?)`,
docID, from, to, s.Original, s.Replacement, s.Explanation, typ,
); err != nil {
return err
}
}
return tx.Commit()
}
// listForDoc returns the document's current pending suggestions (used when the
// editor loads a document, before any new checkpoint fires).
func (h *Handler) listForDoc(w http.ResponseWriter, r *http.Request) {
out, err := h.fetchPending(chi.URLParam(r, "id"))
if err != nil {
serverError(w, err)
return
}
writeJSON(w, http.StatusOK, out)
}
func (h *Handler) fetchPending(docID string) ([]db.Suggestion, error) {
rows, err := h.DB.Query(
`SELECT id, doc_id, from_pos, to_pos, original, replacement, explanation, type, status, created_at
FROM suggestions
WHERE doc_id = ? AND status = ?
ORDER BY from_pos ASC, created_at ASC`,
docID, db.SuggestionStatusPending,
)
if err != nil {
return nil, err
}
defer rows.Close()
out := []db.Suggestion{}
for rows.Next() {
var s db.Suggestion
if err := rows.Scan(
&s.ID, &s.DocID, &s.FromPos, &s.ToPos, &s.Original, &s.Replacement,
&s.Explanation, &s.Type, &s.Status, &s.CreatedAt,
); err != nil {
return nil, err
}
out = append(out, s)
}
return out, rows.Err()
}
// accept marks a suggestion accepted (the client applies the replacement text).
func (h *Handler) accept(w http.ResponseWriter, r *http.Request) {
h.setStatus(w, r, db.SuggestionStatusAccepted)
}
// dismiss marks a suggestion rejected.
func (h *Handler) dismiss(w http.ResponseWriter, r *http.Request) {
h.setStatus(w, r, db.SuggestionStatusRejected)
}
func (h *Handler) setStatus(w http.ResponseWriter, r *http.Request, status string) {
res, err := h.DB.Exec(
`UPDATE suggestions SET status = ? WHERE id = ? AND status = ?`,
status, chi.URLParam(r, "id"), db.SuggestionStatusPending,
)
if err != nil {
serverError(w, err)
return
}
if n, _ := res.RowsAffected(); n == 0 {
errorJSON(w, http.StatusNotFound, "pending suggestion not found")
return
}
w.WriteHeader(http.StatusNoContent)
}
// locate finds the plaintext offsets of original within contentText. Returns
// (-1, -1) when not found; the frontend anchors by string regardless, so a miss
// here is non-fatal.
func locate(contentText, original string) (int, int) {
idx := strings.Index(contentText, original)
if idx < 0 {
return -1, -1
}
return idx, idx + len(original)
}
// normalizeType maps the model's type string onto a valid suggestion type,
// defaulting unknown values to grammar so a stray label never trips the CHECK.
func normalizeType(t string) string {
switch strings.ToLower(strings.TrimSpace(t)) {
case db.SuggestionTypeGrammar, db.SuggestionTypePhrasing, db.SuggestionTypeIdiom, db.SuggestionTypeClarity:
return strings.ToLower(strings.TrimSpace(t))
default:
return db.SuggestionTypeGrammar
}
}
// --- response helpers -------------------------------------------------------
func writeJSON(w http.ResponseWriter, status int, v any) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(status)
_ = json.NewEncoder(w).Encode(v)
}
func errorJSON(w http.ResponseWriter, status int, msg string) {
writeJSON(w, status, map[string]string{"error": msg})
}
func serverError(w http.ResponseWriter, err error) {
errorJSON(w, http.StatusInternalServerError, err.Error())
}