docs(guides): fix vendor_capabilities.py, mma_exec.py, audit_optional_returns drift

- Readme.md AI Client row: '5 providers' -> 8; added VendorCapabilities
  inlining note + Result[str] send() API note.
- guide_ai_client.md: src/vendor_capabilities.py refs -> src/ai_client.py
  #region: Vendor Capabilities (2 sites: the capabilities param
  comment + the V2 Capability Matrix section).
- docs/AGENTS.md: audit_optional_returns.py -> audit_optional_in_3_files.py
  (the live script; the successor is not yet built).
- guide_mma.md SubConversationRunner sketch: 'Reuses mma_exec.py' ->
  'Would reuse the WorkerPool internal subprocess template (NOT the
  deprecated mma_exec.py)'.
- guide_multi_agent_conductor.md: architecture diagram box
  'Workers call mma_exec.py' -> 'Workers run via the internal
  subprocess template (run_worker_lifecycle; NOT the deprecated
  meta-tooling mma_exec.py)'; the mma_exec.py box relabeled to
  run_worker_lifecycle; See Also 'scripts/mma_exec.py — sub-agent
  entry point' -> 'src/multi_agent_conductor.py:run_worker_lifecycle
  (NOT the deprecated meta-tooling mma_exec.py)'.

docs/guide_multi_agent_conductor.md

@@ -35,12 +35,14 @@ Together they implement a **non-blocking execution engine** with thread-safe sta
 │  WorkerPool                                       │
 │  - Configurable concurrency (default 4)          │
 │  - Threads pull ready tickets, spawn workers     │
-│  - Workers call mma_exec.py with sub-prompt       │
+│  - Workers run via the internal subprocess        │
+│    template (run_worker_lifecycle; NOT the        │
+│    deprecated meta-tooling mma_exec.py)           │
 └─────────────────┬───────────────────────────────┘
                   │ per ticket
                   ▼
 ┌─────────────────────────────────────────────────┐
-│  mma_exec.py (tier3-worker / tier4-qa)            │
+│  run_worker_lifecycle (tier3-worker / tier4-qa)  │
 │  - Stateless Tier 3 or Tier 4 sub-agent           │
 │  - TDD cycle: red → green → refactor             │
 │  - Commits per task                               │
@@ -457,7 +459,7 @@ Tests use `unittest.mock.patch` to mock `subprocess.Popen` and `ai_client.send`
 - **[guide_architecture.md](guide_architecture.md)** — Threading model
 - **[guide_mma.md](guide_mma.md)** — MMA concepts (4-Tier hierarchy, Token Firewall)
 - **[guide_app_controller.md](guide_app_controller.md)** — How the conductor is owned by the controller
-- **[guide_models.md](guide_models.md)** — `Ticket` and `Track` data structures
-- **`scripts/mma_exec.py`** — The sub-agent entry point
+- **[guide_models.md](guide_models.md)** — `Ticket` and `Track` data structures (now in `src/mma.py`; moved out of `src/models.py`)
+- **`src/multi_agent_conductor.py:run_worker_lifecycle`** — The WorkerPool's internal subprocess template (the application-domain worker entry point; NOT the deprecated meta-tooling `scripts/mma_exec.py` — see `docs/guide_meta_boundary.md`)
 - **`scripts/mma.ps1`** — PowerShell wrapper
 - **`conductor/workflow.md`**](../conductor/workflow.md) — Track execution protocol