Add Grok orchestration group routing (#8058)

* docs: design Grok orchestration group

* docs: plan Grok orchestration group implementation

* fix: add Grok orchestration group

* test(orchestration): accept Windows skill newlines

* Fix @grok orchestration group matching and remove stale planning docs

- Reuse the shared buildAgentNameRe matcher in groups.ts instead of a
  divergent local regex, so orchestration groups honor the same
  Windows launcher-suffix rule (grok.exe/.cmd/.bat/.ps1) as the rest
  of Orca's agent-title detection.
- Add test coverage for real Grok OSC title shapes (spinner-collapsed,
  session titles) and Windows launcher-suffix titles.
- Delete the now-completed design and implementation-plan docs for
  the Grok orchestration group work.

---------

Co-authored-by: Jinjing <6427696+AmethystLiang@users.noreply.github.com>

src/shared/agent-hook-listener.test.ts

@@ -956,7 +956,10 @@ describe('shared agent-hook-listener', () => {
       'grok',
       {
         paneKey: PANE_KEY,
-        payload: { hookEventName: 'user_prompt_submit', prompt: '<user_query>fix the bug</user_query>' }
+        payload: {
+          hookEventName: 'user_prompt_submit',
+          prompt: '<user_query>fix the bug</user_query>'
+        }
       },
       'production'
     )

src/shared/agent-name-token-match.ts

@@ -33,7 +33,7 @@ export const AGENT_NAMES = [
 // `openclaude.exe`; still reject arbitrary dotted path fragments.
 const WINDOWS_EXECUTABLE_SUFFIX_RE = String.raw`(?:\.(?:exe|cmd|bat|ps1))`
 
-function buildAgentNameRe(name: string): RegExp {
+export function buildAgentNameRe(name: string): RegExp {
   return new RegExp(
     `(?<![\\w./\\\\-])${name}(?:${WINDOWS_EXECUTABLE_SUFFIX_RE})?(?![\\w./\\\\-])`,
     'i'

src/shared/harness-injected-user-turns.test.ts

@@ -38,7 +38,9 @@ describe('isKnownHarnessInjectedUserTurnText', () => {
       isKnownHarnessInjectedUserTurnText('A message arrived from teammate-b:\n<agent-message>hi')
     ).toBe(true)
     expect(
-      isKnownHarnessInjectedUserTurnText('Another Claude session sent a message:\n<agent-message>hi')
+      isKnownHarnessInjectedUserTurnText(
+        'Another Claude session sent a message:\n<agent-message>hi'
+      )
     ).toBe(true)
     expect(isKnownHarnessInjectedUserTurnText('No response requested.')).toBe(true)
     expect(isKnownHarnessInjectedUserTurnText('[Request interrupted by user]')).toBe(true)
@@ -78,7 +80,9 @@ describe('isKnownHarnessInjectedUserTurnText', () => {
     expect(
       isKnownHarnessInjectedUserTurnText('<script>alert(1)</script> — why is this flagged?')
     ).toBe(false)
-    expect(isKnownHarnessInjectedUserTurnText('<https://example.com/a-b> what is this?')).toBe(false)
+    expect(isKnownHarnessInjectedUserTurnText('<https://example.com/a-b> what is this?')).toBe(
+      false
+    )
     expect(isKnownHarnessInjectedUserTurnText('<foo-bar@example.com> sent me this')).toBe(false)
   })