Add Google Imagen and Google Cloud TTS provider tools

Two new provider tools following the BaseTool pattern with auto-discovery:
- google_imagen: Imagen 4 image generation via Generative Language REST API
- google_tts: Google Cloud TTS with 700+ voices across 50+ languages

Both share GOOGLE_API_KEY env var. Selectors auto-discover them — no
selector code changes needed. Docs and contract tests updated.

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

PROJECT_CONTEXT.md

@@ -46,7 +46,7 @@ Each tool's `agent_skills[]` field bridges Layer 1 → Layer 3. See `skills/INDE
 - **Instruction-driven stages:** Each stage has a director skill (MD) that teaches the agent HOW
 - **Pipeline manifests:** Declarative YAML defining stages, skills, tools, review focus, approval gates
 - **Capability-first tool design:** Each major family should expose a selector tool plus explicit provider tools
-  - Example: `tts_selector` + `elevenlabs_tts` / `openai_tts` / `piper_tts`
+  - Example: `tts_selector` + `elevenlabs_tts` / `google_tts` / `openai_tts` / `piper_tts`
   - Example: `video_selector` + `heygen_video` / `wan_video` / `hunyuan_video` / `ltx_video_local` / `ltx_video_modal` / `cogvideo_video`
 - **Style playbooks:** YAML defining visual language, typography, motion, audio, asset generation constraints
 - **Artifacts are canonical:** `brief`, `script`, `scene_plan`, `asset_manifest`, `edit_decisions`, `render_report`, `publish_log`