fix(tools): tell the model the retrieval query is required - #7678

Link to Issue or Description of Change

1. Link to an existing issue (if applicable):

• Closes: Retrieval tools declare query as optional, and a call without it fails the run #7677

Problem:
BaseRetrievalTool declared its only parameter, query, without listing it in required, in both the JSON schema and the types.Schema form. Every tool built on it told the model the query was optional: LlamaIndexRetrieval and FilesRetrieval with any model, and VertexAiRagRetrieval with non-Gemini models. None of them can run without one. LlamaIndexRetrieval raises KeyError, VertexAiRagRetrieval raises ValueError, and the exception fails the run.

Solution:
List query in required in both forms, as load_memory already does for its own query parameter. The model then knows it has to send a query, and the Gemini API's VALIDATED function calling mode, which keeps calls to the declared schema, no longer allows a call without one. What the tools do with a call that still leaves the query out is unchanged.

Testing Plan

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

test_get_declaration_with_json_schema_feature_disabled and test_get_declaration_with_json_schema_feature_enabled in tests/unittests/tools/retrieval/test_base_retrieval_tool.py now check required in each form. Both fail on main and pass with the fix.

$ pytest tests/unittests/tools/retrieval
31 passed, 5 warnings in 72.49s

Full suite on Windows 11, Python 3.11 (pytest tests/unittests -n 4): 71 failed, 20782 passed, 107 skipped. Every one of the 71 also fails on unmodified main in this environment, and none of them is in tools/retrieval/.

Manual End-to-End (E2E) Tests:

An Agent with a LlamaIndexRetrieval tool, run through InMemoryRunner with a model that records each request. The run prints the tool parameters ADK sends, and the same declaration converted by LiteLlm:

# main
Gemini request:  {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The query to retrieve.'}}}
LiteLlm request: {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The query to retrieve.'}}}

# this change
Gemini request:  {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The query to retrieve.'}}, 'required': ['query']}
LiteLlm request: {'type': 'object', 'properties': {'query': {'type': 'string', 'description': 'The query to retrieve.'}}, 'required': ['query']}

Checklist

• I have read the CONTRIBUTING.md document.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.

Additional context

The formatters, linters and repository checks from .pre-commit-config.yaml pass on both files, and mypy reports no errors in base_retrieval_tool.py. The change does not overlap with #7675, which touches llama_index_retrieval.py.