Replace old model gemini-2.0 references by 2.5

[morganroux]

Link to Issue or Description of Change

• Closes: Gemini-2.0 model is still used in integration tests, but deprecated #4666

Problem:
Gemini-2.0-flash model is still used in integration tests, but disabled for new users

Solution:
Replace all occurrences of Gemini-2.0-flash by Gemini-2.5-flash, in integration tests and docstrings.
Because gemini-2.0 is still enabled for some users, this PR doesn't clean the model from unit tests.

Testing Plan

Run already existing unittests and integration tests

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.

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request systematically updates all references to the 'gemini-2.0-flash' model to 'gemini-2.5-flash' throughout the project. This ensures that the codebase aligns with the latest available model, addressing a discrepancy where an older, deprecated model was still being referenced in various configurations and tests. The change impacts agent definitions, configuration schemas, utility functions, and a comprehensive suite of tests, promoting better model utilization and consistency.

Highlights

• Model Upgrade: The default and test model references have been upgraded from 'gemini-2.0-flash' to 'gemini-2.5-flash' across the codebase.
• Issue Resolution: This change resolves issue Gemini-2.0 model is still used in integration tests, but deprecated #4666, which noted that the older 'gemini-2.0-flash' model was still in use in integration tests despite being disabled for new users.
• Configuration and Examples: Updated model names in agent configurations, JSON schemas, and code examples to reflect the new 'gemini-2.5-flash' model.
• Test Suite Alignment: All relevant unit and integration tests have been updated to use the 'gemini-2.5-flash' model, ensuring consistency with the latest model version.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• src/google/adk/agents/common_configs.py
  • Updated the example model name from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• src/google/adk/agents/config_schemas/AgentConfig.json
  • Updated the model name example in the description from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• src/google/adk/agents/llm_agent_config.py
  • Updated the model name example in the description from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• src/google/adk/tools/mcp_tool/mcp_toolset.py
  • Updated the model used in the LlmAgent definition from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• src/google/adk/utils/instructions_utils.py
  • Updated the model used in the Agent definition from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• src/google/adk/utils/model_name_utils.py
  • Updated the example path-based model name from 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/integration/fixture/ecommerce_customer_service_agent/agent.py
  • Updated the model used in the root_agent definition from 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/integration/fixture/hello_world_agent/agent.py
  • Updated the model used in the root_agent definition from 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/integration/fixture/hello_world_agent_async/agent.py
  • Updated the model used in the root_agent definition from 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/integration/fixture/home_automation_agent/agent.py
  • Updated the model used in the root_agent definition from 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/integration/fixture/trip_planner_agent/agent.py
  • Updated the model used in the root_agent definition from 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/integration/test_vertex_ai_search_grounding_streaming.py
  • Updated the default model constant from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/agents/test_agent_config.py
  • Updated model names in YAML content for various agent configuration tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/agents/test_gemini_context_cache_manager.py
  • Updated model names in LlmRequest instances within cache manager tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/agents/test_llm_agent_error_messages.py
  • Updated model names in LlmAgent definitions for error message tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/agents/test_llm_agent_fields.py
  • Updated model names in test parameters and agent definitions from 'gemini-2.0-flash' to 'gemini-2.5-flash' and 'gemini-2.0-flash-exp' to 'gemini-2.5-flash-exp'.
• tests/unittests/cli/utils/test_agent_loader.py
  • Updated model names in YAML content and assertions for agent loader tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/cli/utils/test_cli_create.py
  • Updated model names in _generate_files and run_cmd calls, and YAML content for CLI agent creation tests from 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/unittests/code_executors/test_built_in_code_executor.py
  • Updated model names in LlmRequest instances for built-in code executor tests from 'gemini-2.0-flash' to 'gemini-2.5-flash' and 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/unittests/flows/llm_flows/test_context_cache_processor.py
  • Updated model names in LlmRequest instances for context cache processor tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/models/test_litellm.py
  • Updated model names in _get_completion_inputs and _to_litellm_response_format calls for LiteLLM tests from 'gemini/gemini-2.0-flash' to 'gemini/gemini-2.5-flash' and 'vertex_ai/gemini-2.0-flash' to 'vertex_ai/gemini-2.5-flash'.
• tests/unittests/models/test_llm_response.py
  • Updated the model_version in GenerateContentResponse for LLM response tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/models/test_models.py
  • Updated model names in test parameters for model family matching from 'gemini-2.0-flash-exp' to 'gemini-2.5-flash-exp' and 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/plugins/test_debug_logging_plugin.py
  • Updated model names in LlmRequest instances and assertions for debug logging plugin tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/streaming/test_streaming_audio_storage.py
  • Updated commented-out mock model names from 'gemini-2.0-flash-exp' to 'gemini-2.5-flash-exp'.
• tests/unittests/test_runners.py
  • Updated the model used in the MyAgent definition from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/tools/retrieval/test_vertex_ai_rag_retrieval.py
  • Updated the mock model name from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/tools/test_google_search_tool.py
  • Updated model names in LlmRequest instances and test parameters for Google Search tool tests from 'gemini-2.0-flash' to 'gemini-2.5-flash' and 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/unittests/tools/test_url_context_tool.py
  • Updated model names in LlmRequest instances for URL context tool tests from 'gemini-2.0-flash' to 'gemini-2.5-flash' and 'gemini-2.0-flash-001' to 'gemini-2.5-flash'.
• tests/unittests/tools/test_vertex_ai_search_tool.py
  • Updated model names in test parameters and assertions for Vertex AI Search tool tests from 'gemini-2.0-flash-001' to 'gemini-2.5-flash' and 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/utils/test_instructions_utils.py
  • Updated the model used in the Agent definition from 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/utils/test_model_name_utils.py
  • Updated model names in test parameters and assertions for model name utility tests from 'gemini-2.0-flash-001' to 'gemini-2.5-flash' and 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• tests/unittests/utils/test_output_schema_utils.py
  • Updated model names in test parameters for output schema utility tests from 'gemini-2.0-flash' to 'gemini-2.5-flash'.

Activity

• The pull request was created to address issue Gemini-2.0 model is still used in integration tests, but deprecated #4666, which identified the continued use of the 'gemini-2.0-flash' model in integration tests despite its deprecation for new users.
• The author, morganroux, implemented changes across numerous files to update all instances of 'gemini-2.0-flash' to 'gemini-2.5-flash'.
• The author performed a self-review and confirmed that new and existing unit tests pass locally.
• The author manually tested the changes end-to-end to ensure functionality.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the model name from gemini-2.0-flash to gemini-2.5-flash across the codebase, including documentation, configuration files, and tests. The changes are mostly straightforward replacements. I've found one minor issue in a test file where this change introduces a duplicate entry in a list, which I've commented on. Otherwise, the changes look good and align with the goal of phasing out the older model.

_{Note: Security Review did not run due to the size of the PR.}

I am having trouble creating individual review comments. Click here to see my feedback.

tests/unittests/tools/test_google_search_tool.py (421)

This change introduces a duplicate entry for 'gemini-2.5-flash' in the gemini_2_models list, as it's already present on line 423. While this doesn't break the test, it's redundant. For better code clarity, you could remove the duplicate entry. The list could be simplified to ['gemini-2.0-pro', 'gemini-2.5-flash', 'gemini-2.5-pro'].

[rohityan]

Hi @morganroux , Thank you for your contribution! We appreciate you taking the time to submit this pull request. Your PR has been received by the team and is currently under review. We will provide feedback as soon as we have an update to share.

[rohityan]

Hi @ankursharmas , can you please review this.