Add full Docker image defaults, fix actor deadlocks, and improve dev experience

- Add Dockerfile.full and --all flag to install-agent CLI for pre-built images
- Centralize Docker image constant (FULL_IMAGE) pinned to 0.3.1-full
- Remove examples/shared/Dockerfile{,.dev} and daytona snapshot example
- Expand Docker docs with full runnable Dockerfile
- Fix self-deadlock in createWorkbenchSession (fire-and-forget provisioning)
- Audit and convert 12 task actions from wait:true to wait:false
- Add bun --hot for dev backend hot reload
- Remove --force from pnpm install in dev Dockerfile for faster startup
- Add env_file support to compose.dev.yaml for automatic credential loading
- Add mock frontend compose config and dev panel
- Update CLAUDE.md with wait:true policy and dev environment setup

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

justfile

@@ -141,10 +141,24 @@ foundry-frontend-dev host='127.0.0.1' port='4173' backend='http://127.0.0.1:7741
 	VITE_HF_BACKEND_ENDPOINT="{{backend}}" pnpm --filter @sandbox-agent/foundry-frontend dev -- --host {{host}} --port {{port}}
 
 [group('foundry')]
-foundry-dev-mock host='127.0.0.1' port='4173':
+foundry-dev-mock host='127.0.0.1' port='4174':
 	pnpm install
 	FOUNDRY_FRONTEND_CLIENT_MODE=mock pnpm --filter @sandbox-agent/foundry-frontend dev -- --host {{host}} --port {{port}}
 
+[group('foundry')]
+foundry-mock:
+	pnpm install
+	mkdir -p foundry/.foundry/logs
+	docker compose -f foundry/compose.mock.yaml up --build --force-recreate -d
+
+[group('foundry')]
+foundry-mock-down:
+	docker compose -f foundry/compose.mock.yaml down
+
+[group('foundry')]
+foundry-mock-logs:
+	docker compose -f foundry/compose.mock.yaml logs -f --tail=200
+
 [group('foundry')]
 foundry-dev-turbo:
 	pnpm exec turbo run dev --parallel --filter=@sandbox-agent/foundry-*