feat(cya): T01-T07 core console-native MVP slice (CYA-WP-0001)

- T01: Python + Typer/rich + pyproject.toml + full src/ layout + working `cya` CLI entrypoint
- T02: Bounded transparent context collector (top-level only, provenance, ignores) + --explain-context
- T03: Genuine rule-based risk classifier (primary) + mandatory terminal confirmation, no auto-execute
- T04: LLMAdapter Protocol + deterministic FakeLLMAdapter seam (llm-connect boundary, zero bypass)
- T05: Strictly minimal phase-memory no-op ports (loud markers, per operator direction 2026-05-26)
- T06: Orchestrator coordinating the full flow; CLI is thin delegation
- T07: pytest harness + safety-focused tests (risk invariants + collector)

All changes verified by running the installed `cya` binary and `pytest tests/`.

Workplan updated with status. State Hub progress event logged (workstream 0a1233fd...).

Refs: CYA-WP-0001, Decision a644364b-11c4-49a9-bf17-99063382e27b

src/cya/llm/__init__.py

@@ -0,0 +1,27 @@
+"""llm-connect adapter boundary — the integration seam (T04).
+
+can-you-assist owns orchestration + CLI experience.
+llm-connect owns provider access, config, token counting, and structured I/O.
+
+This package defines the small stable Protocol / interface that all model
+interaction must flow through. A deterministic fake lives here for tests.
+Real delegation to llm-connect is a small localized change once the contract
+is stable.
+
+See workplan CYA-WP-0001-T04 for the full contract and acceptance criteria.
+"""
+
+from .adapter import (
+    AssistanceRequest,
+    AssistanceResponse,
+    LLMAdapter,
+    FakeLLMAdapter,
+)
+
+__all__ = [
+    "AssistanceRequest",
+    "AssistanceResponse",
+    "LLMAdapter",
+    "FakeLLMAdapter",
+]
+