Next-edit: treat empty model output as no-edit

llama-server leaves special tokens out of content, so the NO_EDIT token arrives as an
empty string. The daemon treated that as a rewrite of the region to nothing (Tab would
have deleted the region). shared/nextedit.ts parseNextEditOutput() is now used by the
daemon and the eval.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J39imRDT8L7xYbWzsVWd8A

daemon/src/main.ts

@@ -31,7 +31,7 @@ import { symbolLang } from '../../shared/symbol-lang.ts'
 import { SymbolService, mightNeedThis } from './symbols.ts'
 import { EditTracker } from './edits.ts'
 import { locateFile, modeFromModel, parseFimPrompt } from './openai-shim.ts'
-import { NEXT_EDIT_TOKENS } from '../../shared/nextedit.ts'
+import { NEXT_EDIT_TOKENS, parseNextEditOutput } from '../../shared/nextedit.ts'
 
 const { values: args } = parseArgs({ options: { config: { type: 'string', default: 'acd.config.json' } } })
 const config = loadConfig(args.config!)
@@ -272,8 +272,8 @@ async function handleNextEdit(body: NextEditRequest, res: http.ServerResponse, c
 
   const oldText = lines.slice(startLine, endLine).join('\n') + (endLine < lines.length ? '\n' : '')
   const raw = result.text
-  const newText = raw.startsWith(NEXT_EDIT_TOKENS.noEdit) ? null : raw
-  const noEdit = newText === null || newText === oldText || result.stoppedBy === 'limit'
+  const newText = parseNextEditOutput(raw, oldText)
+  const noEdit = newText === null || result.stoppedBy === 'limit'
   const response = {
     requestId: body.requestId, noEdit, startLine, endLine, oldText, newText: noEdit ? null : newText,
     recentEdits, errors: errors ?? null, model: state.model,

shared/nextedit.ts

@@ -154,3 +154,12 @@ export function buildNextEditPrompt(input: NextEditInput, encode: Encode, ids: N
 export function nextEditTarget(newRegion: string | null, encode: Encode, ids: NextEditTokenIds): number[] {
   return newRegion === null ? [ids.noEdit, ids.outputEnd] : [...encode(newRegion), ids.outputEnd]
 }
+
+/**
+ * Model output → rewritten region, or null for "no edit". llama-server leaves special tokens out of `content`, so the
+ * NO_EDIT token usually arrives as an empty string; never treat empty output as "replace the region with nothing".
+ */
+export function parseNextEditOutput(raw: string, oldText: string): string | null {
+  if (raw.startsWith(NEXT_EDIT_TOKENS.noEdit) || raw.trim() === '' || raw === oldText) return null
+  return raw
+}