diff --git a/AGENTS.md b/AGENTS.md index 95ea8ff263..3e8b3543e8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -24,7 +24,7 @@ agentic architectures that range from simple tasks to complex workflows. interacts with various services like session management, artifact storage, and memory, and integrates with application-wide plugins. The runner provides different execution modes: `run_async` for asynchronous execution - in production, `run_live` for bi-directional streaming interaction, and + in production, `run_live` for bidirectional streaming interaction, and `run` for synchronous execution suitable for local testing and debugging. At the end of each invocation, it can perform event compaction to manage session history size. diff --git a/CHANGELOG.md b/CHANGELOG.md index fada470bb0..b17c9f351c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -531,7 +531,7 @@ * Set `max_output_tokens` for the agent builder ([2e2d61b](https://github.com/google/adk-python/commit/2e2d61b6fecb90cd474d6f51255678ff74b67a9b)) * Set default response modality to AUDIO in run_session ([68402bd](https://github.com/google/adk-python/commit/68402bda49083f2d56f8e8488fe13aa58b3bc18c)) * Update remote_a2a_agent to better handle streaming events and avoid duplicate responses ([8e5f361](https://github.com/google/adk-python/commit/8e5f36126498f751171bb2639c7f5a9e7dca2558)) -* Update the load_artifacts tool so that the model can reliably call it for follow up questions about the same artifact ([238472d](https://github.com/google/adk-python/commit/238472d083b5aa67551bde733fc47826ff062679)) +* Update the load_artifacts tool so that the model can reliably call it for follow-up questions about the same artifact ([238472d](https://github.com/google/adk-python/commit/238472d083b5aa67551bde733fc47826ff062679)) * Fix VertexAiSessionService base_url override to preserve initialized http_options ([8110e41](https://github.com/google/adk-python/commit/8110e41b36cceddb8b92ba17cffaacf701706b36), [c51ea0b](https://github.com/google/adk-python/commit/c51ea0b52e63de8e43d3dccb24f9d20987784aa5)) * Handle `App` instances returned by `agent_loader.load_agent` ([847df16](https://github.com/google/adk-python/commit/847df1638cbf1686aa43e8e094121d4e23e40245)) @@ -698,7 +698,7 @@ * AgentTool returns last content, instead of the content in the last event [bcf0dda](https://github.com/google/adk-python/commit/bcf0dda8bcc221974098f3077007c9e84c63021a) * Fix adk deploy docker file permission [ad81aa5](https://github.com/google/adk-python/commit/ad81aa54de1f38df580915b7f47834ea8e5f1004) * Updating BaseAgent.clone() and LlmAgent.clone() to properly clone fields that are lists [29bb75f](https://github.com/google/adk-python/commit/29bb75f975fe0c9c9d9a7e534a9c20158e1cbe1e) -* Make tool description for bigquery `execute_sql` for various write modes self contained [167182b](https://github.com/google/adk-python/commit/167182be0163117f814c70f453d5b2e19bf474df) +* Make tool description for bigquery `execute_sql` for various write modes self-contained [167182b](https://github.com/google/adk-python/commit/167182be0163117f814c70f453d5b2e19bf474df) * Set invocation_id and branch for event generated when both output_schema and tools are used [3f3aa7b](https://github.com/google/adk-python/commit/3f3aa7b32d63cae5750d71bc586c088427c979ea) * Rework parallel_agent.py to always aclose async generators [826f554](https://github.com/google/adk-python/commit/826f5547890dc02e707be33a3d6a58b527dac223) * Add table metadata info into Spanner tool `get_table_schema` and fix the key usage info [81a53b5](https://github.com/google/adk-python/commit/81a53b53d6336011187a50ae8f1544de9b2764a8) diff --git a/contributing/samples/bigquery_mcp/README.md b/contributing/samples/bigquery_mcp/README.md index bce19976ca..31fdb59895 100644 --- a/contributing/samples/bigquery_mcp/README.md +++ b/contributing/samples/bigquery_mcp/README.md @@ -4,7 +4,7 @@ This sample agent demonstrates using ADK's `McpToolset` to interact with BigQuery's official MCP endpoint, allowing an agent to access and execute -toole by leveraging the Model Context Protocol (MCP). These tools include: +tools by leveraging the Model Context Protocol (MCP). These tools include: 1. `list_dataset_ids` diff --git a/contributing/samples/context_offloading_with_artifact/README.md b/contributing/samples/context_offloading_with_artifact/README.md index 93f391107e..741552bc33 100644 --- a/contributing/samples/context_offloading_with_artifact/README.md +++ b/contributing/samples/context_offloading_with_artifact/README.md @@ -32,7 +32,7 @@ response. This keeps the turn events small, saving context space. the *next* request to the LLM. This makes the report data available immediately, allowing the agent to summarize it or answer questions in the same turn, as seen in the logs. This artifact is only appended for that - round and not saved to session. For furtuer rounds of conversation, it will + round and not saved to session. For future rounds of conversation, it will be removed from context. 3. **Loading on Demand**: The `CustomLoadArtifactsTool` enhances the default `load_artifacts` behavior. diff --git a/contributing/samples/mcp_stdio_notion_agent/README.md b/contributing/samples/mcp_stdio_notion_agent/README.md index d40df313f2..9d8a8922f2 100644 --- a/contributing/samples/mcp_stdio_notion_agent/README.md +++ b/contributing/samples/mcp_stdio_notion_agent/README.md @@ -1,6 +1,6 @@ # Notion MCP Agent -This is an agent that is using Notion MCP tool to call Notion API. And it demonstrate how to pass in the Notion API key. +This is an agent that is using Notion MCP tool to call Notion API. And it demonstrates how to pass in the Notion API key. Follow below instruction to use it: diff --git a/contributing/samples/oauth_calendar_agent/README.md b/contributing/samples/oauth_calendar_agent/README.md index 381bb7902b..1a580ec8ff 100644 --- a/contributing/samples/oauth_calendar_agent/README.md +++ b/contributing/samples/oauth_calendar_agent/README.md @@ -7,7 +7,7 @@ This sample tests and demos the OAuth support in ADK via two tools: * 1. list_calendar_events This is a customized tool that calls Google Calendar API to list calendar - events. It pass in the client id and client secrete to ADK and then get back + events. It passes in the client id and client secret to ADK and then get back the access token from ADK. And then it uses the access token to call calendar api. diff --git a/src/google/adk/apps/app.py b/src/google/adk/apps/app.py index 5382eb5a05..5b0194e577 100644 --- a/src/google/adk/apps/app.py +++ b/src/google/adk/apps/app.py @@ -43,7 +43,7 @@ class ResumabilityConfig(BaseModel): """The config of the resumability for an application. The "resumability" in ADK refers to the ability to: - 1. pause an invocation upon a long running function call. + 1. pause an invocation upon a long-running function call. 2. resume an invocation from the last event, if it's paused or failed midway through. diff --git a/src/google/adk/cli/adk_web_server.py b/src/google/adk/cli/adk_web_server.py index 752af89c34..5230e9c83b 100644 --- a/src/google/adk/cli/adk_web_server.py +++ b/src/google/adk/cli/adk_web_server.py @@ -205,7 +205,7 @@ class RunAgentRequest(common.BaseModel): new_message: types.Content streaming: bool = False state_delta: Optional[dict[str, Any]] = None - # for resume long running functions + # for resume long-running functions invocation_id: Optional[str] = None diff --git a/src/google/adk/flows/llm_flows/base_llm_flow.py b/src/google/adk/flows/llm_flows/base_llm_flow.py index 91b57cb873..6d9bdc5788 100644 --- a/src/google/adk/flows/llm_flows/base_llm_flow.py +++ b/src/google/adk/flows/llm_flows/base_llm_flow.py @@ -73,7 +73,7 @@ class BaseLlmFlow(ABC): """A basic flow that calls the LLM in a loop until a final response is generated. - This flow ends when it transfer to another agent. + This flow ends when it transfers to another agent. """ def __init__(self): @@ -393,8 +393,8 @@ async def _run_one_step_async( current_invocation=True, current_branch=True ) - # Long running tool calls should have been handled before this point. - # If there are still long running tool calls, it means the agent is paused + # Long-running tool calls should have been handled before this point. + # If there are still long-running tool calls, it means the agent is paused # before, and its branch hasn't been resumed yet. if ( invocation_context.is_resumable