feat(CUST-WP-0001): implement Custodian Agent Runtime bootstrap

T2 complete: OODA loop skeleton with LLM integration, bounded actions,
and 32 offline unit tests.

Deliverables:
- runtime/agent.py     — CLI entry point (--domain/--all/--dry-run/--llm)
- runtime/context.py   — Observe: fetch_state + build_context
- runtime/actions.py   — Act: parse_plan + execute (3 sanctioned writes)
- runtime/README.md    — usage guide and architecture overview
- runtime/tests/       — 32 tests, fully offline
- runtime/pyproject.toml — standalone package with llm-connect dep
- canon/architecture/adr-002-custodian-agent-runtime-design.md

Key design decisions (ADR-002):
- Lives in runtime/ (not a new repo) — tight canon/state-hub coupling
- ClaudeCodeAdapter by default (local-first, no API key)
- Single-pass synchronous OODA for v0.1 simplicity
- Exactly 3 sanctioned write ops: add_progress_event, update_task_status, flag_for_human
- LLM returns JSON block in markdown for structured+auditable output

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

workplans/CUST-WP-0001-custodian-agent-runtime.md

@@ -3,12 +3,12 @@ id: CUST-WP-0001
 type: workplan
 title: "Custodian Agent Runtime — Bootstrap"
 domain: custodian
-status: active
+status: done
 owner: custodian
 topic_slug: custodian
 state_hub_workstream_id: a2d9919d-62ec-49e7-9533-ba650757e70a
 created: "2026-02-25"
-updated: "2026-03-11"
+updated: "2026-03-12"
 ---
 
 # Custodian Agent Runtime — Bootstrap
@@ -59,7 +59,7 @@ editable dependency; markitect llm-check smoke test green.
 ```task
 id: CUST-WP-0001-T02
 state_hub_task_id: 9a9297cd-bd3c-409c-8384-6f06cfc6faa2
-status: todo
+status: done
 priority: medium
 ```