Ship the batch: undo, parallel subagents, lazy MCP, hot-reloaded skills; docs and CI/CD

Loop and ergonomics batch across Now/Next and Maintenance:
- /undo and /redo via pre-prompt file snapshots (snapshot.ts)
- task takes a tasks[] array and runs investigations concurrently (subagent.ts)
- lazy MCP tools: mcp_list/mcp_inspect/mcp_call meta-tools, eager opt-in (mcp.ts, config.ts)
- skill tool reads its list live so a mid-session install is callable next turn (skills.ts)
- tool-name lists (tool-kinds.ts) derived from a mutating() marker; gates previously ungated writes
- prune/session recovery path summarized, and step-back doom-loop primitive (step-back.ts)
- @file completion re-walks on a slow cooldown; estimateTokens and pricing labeled as estimates

Docs: README, CHANGELOG, docs/{mcp,architecture,development} updated to match.
CI/CD: bun install-store cache and concurrency gates on both workflows; release.yml now
composes file-based release notes via scripts/make-release-notes.ts and verifies every binary.

src/permission.ts

@@ -181,6 +181,11 @@ export const DEFAULT_PERMISSIONS: PermissionConfig = {
   apply_patch: 'ask',
   move_file: 'ask',
   delete_file: 'ask',
+  insert_lines: 'ask',
+  delete_lines: 'ask',
+  replace_lines: 'ask',
+  append_file: 'ask',
+  prepend_file: 'ask',
   bash: 'ask',
   web_fetch: 'ask',
 };
@@ -272,10 +277,6 @@ export class Permissions {
     this.granted.set(tool, set);
   }
 
-  granted_(tool: string): string[] {
-    return [...(this.granted.get(tool) ?? [])];
-  }
-
   /** The decision for one call, and which pattern decided it. */
   check(tool: string, input: unknown): Resolved {
     const resolved = resolve(entryFor(tool, this.config), tool, input);