fix: Update import and version for k8s-agent-sandbox

Renames the imported module from `agentic_sandbox` to `k8s_agent_sandbox` in `gke_code_executor.py` and updates the required version in `pyproject.toml` to `>=0.1.1.post3`.

Closes #4883

Co-authored-by: Liang Wu <wuliang@google.com>
PiperOrigin-RevId: 885840142

Author: wuliang229

pyproject.toml

@@ -158,7 +158,7 @@ extensions = [
   "crewai[tools];python_version>='3.11' and python_version<'3.12'",       # For CrewaiTool; chromadb/pypika fail on 3.12+
   "docker>=7.0.0",                              # For ContainerCodeExecutor
   "kubernetes>=29.0.0",                         # For GkeCodeExecutor
-  "k8s-agent-sandbox>=0.1.1.post2",             # For GkeCodeExecutor sandbox mode
+  "k8s-agent-sandbox>=0.1.1.post3",             # For GkeCodeExecutor sandbox mode
   "langgraph>=0.2.60, <0.4.8",                  # For LangGraphAgent
   "litellm>=1.75.5, <2.0.0",                    # For LiteLlm class. Currently has OpenAI limitations. TODO: once LiteLlm fix it
   "llama-index-readers-file>=0.4.0",            # For retrieval using LlamaIndex.

src/google/adk/code_executors/gke_code_executor.py

@@ -30,12 +30,12 @@
 from .code_execution_utils import CodeExecutionResult
 
 try:
-  from agentic_sandbox import SandboxClient
+  from k8s_agent_sandbox import SandboxClient
 except ImportError:
   SandboxClient = None
 
 if TYPE_CHECKING:
-  from agentic_sandbox import SandboxClient
+  from k8s_agent_sandbox import SandboxClient
 
 # Expose these for tests to monkeypatch.
 client = k8s.client