Extension 0.6.0: next-edit, token healing, TS errors context, cursor-move, prewarm

- shared/nextedit.ts: next-edit prompt format (region rewrite or NO_EDIT, Qwen spare special tokens)
- shared/diagnostics.ts: TS errors near the cursor as context; symbols format 2 adds namespace imports
- shared/prompt.ts: token healing (cut the half-typed word, force it via grammar), errors header section
- daemon: model profiles carry contextFormat/errors/members/nextEdit; /v1/next-edit with edit-burst
  tracking; /v1/prewarm; /v1/debug/last; token healing on by default
- extension: next-edit decorations (Tab apply / Esc dismiss), suggest on cursor move, prewarm on focus,
  Show Last Prompt, update check against releases, diagnostics in the edit recorder
- models/README: training-data attribution; release script profiles for stage-d/stage-e
- .gitea/workflows/ci.yml: build + test, publish release on vscode-v* tags (needs a runner + RELEASE_TOKEN)

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

shared/prompt.ts

@@ -29,14 +29,14 @@ export function fimPrompt(order: FimOrder, prefix: number[], suffix: number[], i
 
 /**
  * Qwen2.5-Coder repo-level header placed before the FIM prompt:
- *   <repo_name>repo\n [<file_sep>dir/__symbols__.d.ts\n{context}\n] <file_sep>path\n
+ *   <repo_name>repo\n [<file_sep>dir/__symbols__.d.ts\n{context}\n] [<file_sep>dir/__errors__.txt\n{errors}\n] <file_sep>path\n
  */
-export function repoHeader(repo: string, filePath: string, context: string | undefined, encode: Encode, ids: HeaderTokenIds): number[] {
+export function repoHeader(repo: string, filePath: string, context: string | undefined, encode: Encode, ids: HeaderTokenIds, errors?: string): number[] {
   const out = [ids.repoName, ...encode(`${repo}\n`)]
-  if (context) {
-    const dir = filePath.includes('/') ? filePath.slice(0, filePath.lastIndexOf('/')) : '.'
-    out.push(ids.fileSep, ...encode(`${dir}/__symbols__.d.ts\n${context}\n`))
-  }
+  const dir = filePath.includes('/') ? filePath.slice(0, filePath.lastIndexOf('/')) : '.'
+  if (context) out.push(ids.fileSep, ...encode(`${dir}/__symbols__.d.ts\n${context}\n`))
+  // TS errors near the cursor (shared/diagnostics.ts), for models trained with them (Stage D+).
+  if (errors) out.push(ids.fileSep, ...encode(`${dir}/__errors__.txt\n${errors}\n`))
   out.push(ids.fileSep, ...encode(`${filePath}\n`))
   return out
 }
@@ -115,3 +115,22 @@ export function wantsSingleLine(suffix: string): boolean {
   const restOfLine = suffix.split('\n')[0]
   return /[^\s)\]}'"`;,]/.test(restOfLine)
 }
+
+/**
+ * Token healing for completions that start mid-identifier (`this.connections.del▮`).
+ *
+ * Suffix-first prompts end exactly at the cursor, so a half-typed word leaves an unnatural final token and the
+ * model tends to treat the word as finished (`(relayUrl)` instead of `ete(relayUrl)`). Instead, cut the partial
+ * word off the prompt and force the output to start with it (llama.cpp grammar); the caller strips it again.
+ * Bonus: while typing `d`, `de`, `del` the healed prompt is identical, so the KV cache is fully reused.
+ */
+export function healPrefix(prefix: string): { prefix: string; forced: string } | null {
+  const m = /(^|[^\w$])([\w$]{1,32})$/.exec(prefix)
+  if (!m) return null
+  return { prefix: prefix.slice(0, prefix.length - m[2].length), forced: m[2] }
+}
+
+/** GBNF grammar: output must start with `forced`, then anything. */
+export function forcedPrefixGrammar(forced: string): string {
+  return `root ::= "${forced.replace(/\\/g, '\\\\').replace(/"/g, '\\"')}" rest\nrest ::= [^\\x00]*`
+}