Merge fix/suggestion-renag-anchoring: stop re-nagging resolved suggestions + typographic anchoring

Claude-Session: https://claude.ai/code/session_016Yr6jELuRc7hyzYLccQKZd

internal/suggestions/handlers.go

@@ -154,6 +154,14 @@ var (
 // 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.
+//
+// Suggestions the user already accepted or dismissed are suppressed from the
+// fresh batch: the model has no memory between passes, so without this it would
+// re-propose the identical edit on the very next checkpoint — re-nagging a
+// sentence the user already resolved. This matters most when an accept silently
+// no-ops (the `original` text couldn't be anchored in the editor, so the doc
+// never changed): the sentence is unaltered, yet the user shouldn't see the same
+// card again.
 func (h *Handler) replacePending(docID, contentText string, raw []llm.RawSuggestion, scope pendingScope) error {
 	tx, err := h.DB.Begin()
 	if err != nil {
@@ -168,7 +176,15 @@ func (h *Handler) replacePending(docID, contentText string, raw []llm.RawSuggest
 		return err
 	}
 
+	actioned, err := actionedKeys(tx, docID)
+	if err != nil {
+		return err
+	}
+
 	for _, s := range raw {
+		if _, seen := actioned[suggestionKey(s.Original, s.Replacement)]; seen {
+			continue
+		}
 		typ := scope.forceType
 		if typ == "" {
 			typ = normalizeType(s.Type)
@@ -186,6 +202,39 @@ func (h *Handler) replacePending(docID, contentText string, raw []llm.RawSuggest
 	return tx.Commit()
 }
 
+// actionedKeys returns the set of original→replacement keys the user has already
+// accepted or rejected for this document, so a fresh checkpoint can skip
+// re-proposing them. Keyed on the trimmed original+replacement pair, matching the
+// normalization ParseCheckpoint applies, so a genuinely different edit on the same
+// sentence is not suppressed.
+func actionedKeys(tx *sql.Tx, docID string) (map[string]struct{}, error) {
+	rows, err := tx.Query(
+		`SELECT original, replacement FROM suggestions
+		  WHERE doc_id = ? AND status IN (?, ?)`,
+		docID, db.SuggestionStatusAccepted, db.SuggestionStatusRejected,
+	)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	keys := make(map[string]struct{})
+	for rows.Next() {
+		var original, replacement string
+		if err := rows.Scan(&original, &replacement); err != nil {
+			return nil, err
+		}
+		keys[suggestionKey(original, replacement)] = struct{}{}
+	}
+	return keys, rows.Err()
+}
+
+// suggestionKey is the dedup identity for a suggestion: its trimmed original and
+// replacement text. Two suggestions with the same key are "the same edit."
+func suggestionKey(original, replacement string) string {
+	return strings.TrimSpace(original) + "\x00" + strings.TrimSpace(replacement)
+}
+
 // 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) {

internal/suggestions/handlers_test.go

@@ -127,6 +127,44 @@ func TestCheckpointFlow(t *testing.T) {
 	}
 }
 
+// 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.

web/src/components/Editor/SuggestionHighlight.test.ts

@@ -0,0 +1,54 @@
+import { describe, it, expect } from 'vitest'
+import { foldTypography, findRange } from './SuggestionHighlight'
+import { Schema, type Node as PMNode } from '@tiptap/pm/model'
+
+// A minimal doc/paragraph/text schema, enough to exercise findRange's textblock
+// walk without pulling in the full editor.
+const schema = new Schema({
+  nodes: {
+    doc: { content: 'block+' },
+    paragraph: { group: 'block', content: 'inline*', toDOM: () => ['p', 0] },
+    text: { group: 'inline' },
+  },
+})
+
+// Build a single-paragraph doc with the given plaintext.
+const para = (text: string): PMNode => schema.node('doc', null, [schema.node('paragraph', null, text ? [schema.text(text)] : [])])
+
+describe('foldTypography', () => {
+  it('folds curly quotes back to straight ASCII', () => {
+    expect(foldTypography('“He’s here,” she said').folded).toBe('"He\'s here," she said')
+  })
+
+  it('folds dashes and ellipsis, keeping a source-index map across length changes', () => {
+    const { folded, map } = foldTypography('wait—really...')
+    expect(folded).toBe('wait—really…')
+    // The em dash is already one glyph; the `...` collapsed 3 source chars to 1,
+    // so the trailing sentinel still points just past the last source char.
+    expect(map[map.length - 1]).toBe('wait—really...'.length)
+  })
+
+  it('treats `--` and `...` typed-but-unconverted as their canonical glyphs', () => {
+    expect(foldTypography('a--b...c').folded).toBe('a—b…c')
+  })
+})
+
+describe('findRange typographic anchoring', () => {
+  it('anchors a model echo with straight quotes onto curly-quote document text', () => {
+    const doc = para('She said “hello” to me')
+    const range = findRange(doc, '“hello”'.replace(/[“”]/g, '"')) // model echoed "hello"
+    expect(range).not.toBeNull()
+    // The matched span must cover the curly-quoted region in the real document.
+    expect(doc.textBetween(range!.from - 1, range!.to - 1)).toContain('hello')
+  })
+
+  it('anchors an ASCII `--` echo onto an em-dash in the document', () => {
+    const doc = para('I waited—forever')
+    const range = findRange(doc, 'waited--forever')
+    expect(range).not.toBeNull()
+  })
+
+  it('still returns null when the text genuinely is not present', () => {
+    expect(findRange(para('nothing to see'), 'absent phrase')).toBeNull()
+  })
+})

web/src/components/Editor/SuggestionHighlight.ts

@@ -42,21 +42,87 @@ export function mapOffset(block: PMNode, blockPos: number, targetOffset: number)
   return result
 }
 
+// foldTypography canonicalizes the typographic variants that the editor's
+// Typography input rules introduce (curly quotes, em/en dashes, single-glyph
+// ellipsis) and the unicode spaces a paste can carry. The model echoes a
+// suggestion's `original` from the same text but often normalizes these back to
+// plain ASCII — straight quotes, `--`, `...` — so an exact match would miss and
+// the suggestion could be neither highlighted nor applied.
+//
+// It returns the folded string plus `map`, where map[k] is the source index at
+// which folded character k begins. A multi-character source run (`...`, `--`)
+// folds to one glyph, so lengths differ; map projects a match in folded space
+// back onto real document offsets. map has a trailing sentinel (= source length)
+// so map[start + folded.length] yields the offset just past the match.
+export function foldTypography(text: string): { folded: string; map: number[] } {
+  let folded = ''
+  const map: number[] = []
+  let i = 0
+  while (i < text.length) {
+    // Multi-character ASCII sequences the Typography rules would have replaced.
+    if (text.startsWith('...', i)) {
+      folded += '…'
+      map.push(i)
+      i += 3
+      continue
+    }
+    if (text[i] === '-' && text[i + 1] === '-') {
+      folded += '—'
+      map.push(i)
+      i += 2
+      continue
+    }
+    folded += foldChar(text[i])
+    map.push(i)
+    i++
+  }
+  map.push(text.length)
+  return { folded, map }
+}
+
+// foldChar maps a single character onto its canonical form (length-preserving).
+function foldChar(c: string): string {
+  switch (c) {
+    case '‘':
+    case '’':
+    case '‚':
+    case '‛':
+      return "'"
+    case '“':
+    case '”':
+    case '„':
+    case '‟':
+      return '"'
+    case '–': // en dash → em dash, the canonical form `--` also folds to
+      return '—'
+    case ' ': // non-breaking space
+    case ' ': // thin space
+    case ' ': // narrow no-break space
+      return ' '
+    default:
+      return c
+  }
+}
+
 // findRange locates the first occurrence of `search` within a single textblock
 // and returns its ProseMirror range, or null if the string isn't present (the
-// user may have edited or removed it since the checkpoint ran). Exported so the
-// accept flow can resolve the same span to replace.
+// user may have edited or removed it since the checkpoint ran). Matching is done
+// in canonical typographic space (see foldTypography) so curly-quote/dash/ellipsis
+// differences between the model's echo and the live document don't strand the
+// anchor. Exported so the accept flow can resolve the same span to replace.
 export function findRange(doc: PMNode, search: string): { from: number; to: number } | null {
-  if (!search) return null
+  const needle = foldTypography(search).folded
+  if (!needle) return null
   let result: { from: number; to: number } | null = null
   doc.descendants((node, pos) => {
     if (result) return false
     if (!node.isTextblock) return true // keep descending to the textblock
-    const idx = node.textContent.indexOf(search)
+    const { folded, map } = foldTypography(node.textContent)
+    const idx = folded.indexOf(needle)
     if (idx >= 0) {
       result = {
-        from: mapOffset(node, pos, idx),
-        to: mapOffset(node, pos, idx + search.length),
+        from: mapOffset(node, pos, map[idx]),
+        to: mapOffset(node, pos, map[idx + needle.length]),
       }
     }
     return false // never descend into a textblock's inline children