Merge branch 'main' into feat/function-tools-enum-support

Author: SOORAJTS2001

README.md

@@ -155,6 +155,10 @@ We welcome contributions from the community! Whether it's bug reports, feature r
 
 If you are to develop agent via vibe coding the [llms.txt](./llms.txt) and the [llms-full.txt](./llms-full.txt) can be used as context to LLM. While the former one is a summarized one and the later one has the full information in case your LLM has big enough context window.
 
+## Community Events
+
+- [Completed] ADK's 1st community meeting on Wednesday, October 15, 2025. Remember to [join our group](https://groups.google.com/g/adk-community) to get access to the [recording](https://drive.google.com/file/d/1rpXDq5NSH8-MyMeYI6_5pZ3Lhn0X9BQf/view), and [deck](https://docs.google.com/presentation/d/1_b8LG4xaiadbUUDzyNiapSFyxanc9ZgFdw7JQ6zmZ9Q/edit?slide=id.g384e60cdaca_0_658&resourcekey=0-tjFFv0VBQhpXBPCkZr0NOg#slide=id.g384e60cdaca_0_658).
+
 ## 📄 License
 
 This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.

contributing/samples/adk_agent_builder_assistant/instruction_embedded.template

@@ -120,6 +120,12 @@ Always reference this schema when creating configurations to ensure compliance.
 - **`agent_class` field**:
   * Always declare `agent_class` explicitly for every agent block (the loader defaults to `LlmAgent`, but we require clarity)
   * Use `agent_class: LlmAgent` when the agent talks directly to an LLM
+- **🚫 Workflow agent field ban**: Workflow orchestrators (`SequentialAgent`,
+  `ParallelAgent`, `LoopAgent`, etc.) must NEVER include `model`, `instruction`,
+  or `tools`. Only `LlmAgent` definitions—whether they are root agents or
+  sub-agents—may declare those fields
+- **Root agent requirement**: The root configuration must always remain an
+  `LlmAgent`. Never convert the root agent into a workflow agent.
 - **Workflow agent tool rule**: See **ADK Agent Types and Model Field Rules** for tool restrictions on workflow orchestrators; attach tools to their `LlmAgent` sub-agents.
 - **Sub-agent placement**: Place ALL sub-agent YAML files in the main project folder, NOT in `sub_agents/` subfolder
 - Tool paths use format: `project_name.tools.module.function_name` (must start with project folder name, no `.py` extension, all dots)
@@ -236,44 +242,25 @@ tools:
 
 ### ADK Knowledge and Research Tools
 
-#### Remote Semantic Search
-- **adk_knowledge_agent**: Search ADK knowledge base for ADK examples, patterns, and documentation
-
-#### Web-based Research
-- **google_search_agent**: Search web for ADK examples, patterns, and documentation (returns full page content as results)
-- **url_context_agent**: Fetch content from specific URLs when mentioned in search results or user queries (use only when specific URLs need additional fetching)
-
-#### Local ADK Source Search
-- **search_adk_source**: Search ADK source code using regex patterns for precise code lookups
-  * Use for finding class definitions: `"class FunctionTool"`
-  * Use for constructor signatures: `"def __init__.*FunctionTool"`
-  * Use for method definitions: `"def method_name"`
-  * Returns matches with file paths, line numbers, and context
-  * Follow up with **read_files** to get complete file contents
-
-**Research Workflow for ADK Questions:**
-Mainly rely on **adk_knowledge_agent** for ADK questions. Use other tools only when the knowledge agent doesn't have enough information.
-
-1. **search_adk_source** - Find specific code patterns with regex
-2. **read_files** - Read complete source files for detailed analysis
-3. **google_search_agent** - Find external examples and documentation
-4. **url_context_agent** - Fetch specific GitHub files or documentation pages
-
-### When to Use Research Tools
-**ALWAYS use research tools when:**
-1. **User asks ADK questions**: Any questions about ADK concepts, APIs, usage patterns, or troubleshooting
-2. **Unfamiliar ADK features**: When user requests features you're not certain about
-3. **Agent type clarification**: When unsure about agent types, their capabilities, or configuration
-4. **Best practices**: When user asks for examples or best practices
-5. **Error troubleshooting**: When helping debug ADK-related issues
-6. **Agent building uncertainty**: When unsure how to create agents or what's the best practice
-7. **Architecture decisions**: When evaluating different approaches or patterns for agent design
-
-**Research Tool Usage Patterns:**
-
-**Default Research Tool:**
-Use **adk_knowledge_agent** as the primary research tool for ADK questions.
-Use other tools only when the knowledge agent doesn't have enough information.
+**Default research tool**: Use `adk_knowledge_agent` first for ADK concepts, APIs,
+examples, and troubleshooting. Switch to the tools below only when the
+knowledge agent lacks the needed information.
+
+- `search_adk_source`: Regex search across ADK source for classes, methods, and
+  signatures; follow up with `read_files` for full context.
+- `google_search_agent`: Broader web search for ADK-related examples or docs.
+- `url_context_agent`: Fetch content from specific URLs returned by search
+  results.
+
+**Trigger research when** users ask ADK questions, request unfamiliar features,
+need agent-type clarification, want best practices, hit errors, express
+uncertainty about architecture, or you otherwise need authoritative guidance.
+
+**Recommended research sequence** (stop once you have enough information):
+1. `adk_knowledge_agent`
+2. `search_adk_source` → `read_files`
+3. `google_search_agent`
+4. `url_context_agent`
 
 **For ADK Code Questions (NEW - Preferred Method):**
 1. **search_adk_source** - Find exact code patterns:

contributing/samples/adk_pr_triaging_agent/agent.py

@@ -27,18 +27,18 @@
 from google.adk import Agent
 import requests
 
-LABEL_TO_OWNER = {
-    "documentation": "polong-lin",
-    "services": "DeanChensj",
-    "tools": "seanzhou1023",
-    "mcp": "seanzhou1023",
-    "eval": "ankursharmas",
-    "live": "hangfei",
-    "models": "genquan9",
-    "tracing": "Jacksunwei",
-    "core": "Jacksunwei",
-    "web": "wyf7107",
-}
+ALLOWED_LABELS = [
+    "documentation",
+    "services",
+    "tools",
+    "mcp",
+    "eval",
+    "live",
+    "models",
+    "tracing",
+    "core",
+    "web",
+]
 
 CONTRIBUTING_MD = read_file(
     Path(__file__).resolve().parents[3] / "CONTRIBUTING.md"
@@ -158,19 +158,19 @@ def get_pull_request_details(pr_number: int) -> str:
     return error_response(str(e))
 
 
-def add_label_and_reviewer_to_pr(pr_number: int, label: str) -> dict[str, Any]:
-  """Adds a specified label and requests a review from a mapped reviewer on a PR.
+def add_label_to_pr(pr_number: int, label: str) -> dict[str, Any]:
+  """Adds a specified label on a pull request.
 
   Args:
       pr_number: the number of the Github pull request
       label: the label to add
 
   Returns:
-      The the status of this request, with the applied label and assigned
-      reviewer when successful.
+      The the status of this request, with the applied label and response when
+      successful.
   """
-  print(f"Attempting to add label '{label}' and a reviewer to PR #{pr_number}")
-  if label not in LABEL_TO_OWNER:
+  print(f"Attempting to add label '{label}' to PR #{pr_number}")
+  if label not in ALLOWED_LABELS:
     return error_response(
         f"Error: Label '{label}' is not an allowed label. Will not apply."
     )
@@ -186,31 +186,10 @@ def add_label_and_reviewer_to_pr(pr_number: int, label: str) -> dict[str, Any]:
   except requests.exceptions.RequestException as e:
     return error_response(f"Error: {e}")
 
-  owner = LABEL_TO_OWNER.get(label, None)
-  if not owner:
-    return {
-        "status": "warning",
-        "message": (
-            f"{response}\n\nLabel '{label}' does not have an owner. Will not"
-            " assign."
-        ),
-        "applied_label": label,
-    }
-  reviewer_url = f"{GITHUB_BASE_URL}/repos/{OWNER}/{REPO}/pulls/{pr_number}/requested_reviewers"
-  reviewer_payload = {"reviewers": [owner]}
-  try:
-    post_request(reviewer_url, reviewer_payload)
-  except requests.exceptions.RequestException as e:
-    return {
-        "status": "warning",
-        "message": f"Reviewer not assigned: {e}",
-        "applied_label": label,
-    }
-
   return {
       "status": "success",
       "applied_label": label,
-      "assigned_reviewer": owner,
+      "response": response,
   }
 
 
@@ -252,7 +231,6 @@ def add_comment_to_pr(pr_number: int, comment: str) -> dict[str, Any]:
       Your core responsibility includes:
       - Get the pull request details.
       - Add a label to the pull request.
-      - Assign a reviewer to the pull request.
       - Check if the pull request is following the contribution guidelines.
       - Add a comment to the pull request if it's not following the guidelines.
 
@@ -303,7 +281,7 @@ def add_comment_to_pr(pr_number: int, comment: str) -> dict[str, Any]:
       - Skip the PR (i.e. do not label or comment) if any of the following is true:
         - the PR is closed
         - the PR is labeled with "google-contributior"
-        - the PR is already labelled with the above labels (e.g. "documentation", "services", "tools", etc.) and has a reviewer assigned.
+        - the PR is already labelled with the above labels (e.g. "documentation", "services", "tools", etc.).
       - Check if the PR is following the contribution guidelines.
         - If it's not following the guidelines, recommend or add a comment to the PR that points to the contribution guidelines (https://github.com/google/adk-python/blob/main/CONTRIBUTING.md).
         - If it's following the guidelines, recommend or add a label to the PR.
@@ -312,12 +290,11 @@ def add_comment_to_pr(pr_number: int, comment: str) -> dict[str, Any]:
       Present the followings in an easy to read format highlighting PR number and your label.
       - The PR summary in a few sentence
       - The label you recommended or added with the justification
-      - The owner of the label if you assigned a reviewer to the PR
       - The comment you recommended or added to the PR with the justification
     """,
     tools=[
         get_pull_request_details,
-        add_label_and_reviewer_to_pr,
+        add_label_to_pr,
         add_comment_to_pr,
     ],
 )

src/google/adk/a2a/converters/request_converter.py

@@ -106,12 +106,16 @@ def convert_a2a_request_to_agent_run_request(
   if not request.message:
     raise ValueError('Request message cannot be None')
 
+  custom_metadata = {}
+  if request.metadata:
+    custom_metadata['a2a_metadata'] = request.metadata
+
   return AgentRunRequest(
       user_id=_get_user_id(request),
       session_id=request.context_id,
       new_message=genai_types.Content(
           role='user',
           parts=[part_converter(part) for part in request.message.parts],
       ),
-      run_config=RunConfig(),
+      run_config=RunConfig(custom_metadata=custom_metadata),
   )

src/google/adk/agents/run_config.py

@@ -17,6 +17,7 @@
 from enum import Enum
 import logging
 import sys
+from typing import Any
 from typing import Optional
 
 from google.genai import types
@@ -118,6 +119,9 @@ class RunConfig(BaseModel):
     - Less than or equal to 0: This allows for unbounded number of llm calls.
   """
 
+  custom_metadata: Optional[dict[str, Any]] = None
+  """Custom metadata for the current invocation."""
+
   @field_validator('max_llm_calls', mode='after')
   @classmethod
   def validate_max_llm_calls(cls, value: int) -> int:

src/google/adk/evaluation/local_eval_service.py

@@ -184,10 +184,10 @@ async def run_evaluation(inference_result):
   async def _evaluate_single_inference_result(
       self, inference_result: InferenceResult, evaluate_config: EvaluateConfig
   ) -> tuple[InferenceResult, EvalCaseResult]:
-    """Returns EvalCaseResult for the given inference result.
+    """Returns the inference result and its corresponding EvalCaseResult.
 
     A single inference result can have multiple invocations. For each
-    invocaiton, this method evaluates the metrics present in evaluate config.
+    invocation, this method evaluates the metrics present in evaluate config.
 
     The EvalCaseResult contains scores for each metric per invocation and the
     overall score.
@@ -432,9 +432,10 @@ async def _perform_inference_sigle_eval_item(
       # We intentionally catch the Exception as we don't failures to affect
       # other inferences.
       logger.error(
-          'Inference failed for eval case `%s` with error %s',
+          'Inference failed for eval case `%s` with error %s.',
           eval_case.eval_id,
           e,
+          exc_info=True,
       )
       inference_result.status = InferenceStatus.FAILURE
       inference_result.error_message = str(e)

tests/unittests/a2a/converters/test_request_converter.py

@@ -165,6 +165,7 @@ def test_convert_a2a_request_basic(self):
     request.message = mock_message
     request.context_id = "test_context_123"
     request.call_context = mock_call_context
+    request.metadata = {"test_key": "test_value"}
 
     # Create proper genai_types.Part objects instead of mocks
     mock_genai_part1 = genai_types.Part(text="test part 1")
@@ -185,6 +186,9 @@ def test_convert_a2a_request_basic(self):
     assert result.new_message.role == "user"
     assert result.new_message.parts == [mock_genai_part1, mock_genai_part2]
     assert isinstance(result.run_config, RunConfig)
+    assert result.run_config.custom_metadata == {
+        "a2a_metadata": {"test_key": "test_value"}
+    }
 
     # Verify calls
     assert mock_convert_part.call_count == 2
@@ -212,6 +216,7 @@ def test_convert_a2a_request_empty_parts(self):
     request.message = mock_message
     request.context_id = "test_context_123"
     request.call_context = None
+    request.metadata = {}
 
     # Act
     result = convert_a2a_request_to_agent_run_request(
@@ -241,6 +246,7 @@ def test_convert_a2a_request_none_context_id(self):
     request.message = mock_message
     request.context_id = None
     request.call_context = None
+    request.metadata = {}
 
     # Create proper genai_types.Part object instead of mock
     mock_genai_part = genai_types.Part(text="test part")
@@ -272,6 +278,7 @@ def test_convert_a2a_request_no_auth(self):
     request.message = mock_message
     request.context_id = "session_123"
     request.call_context = None
+    request.metadata = {}
 
     # Create proper genai_types.Part object instead of mock
     mock_genai_part = genai_types.Part(text="test part")
@@ -313,6 +320,7 @@ def test_end_to_end_conversion_with_auth_user(self):
     request.call_context = mock_call_context
     request.message = mock_message
     request.context_id = "mysession"
+    request.metadata = {}
 
     # Create proper genai_types.Part object instead of mock
     mock_genai_part = genai_types.Part(text="test part")
@@ -344,6 +352,7 @@ def test_end_to_end_conversion_with_fallback_user(self):
     request.call_context = None
     request.message = mock_message
     request.context_id = "test_session_456"
+    request.metadata = {}
 
     # Create proper genai_types.Part object instead of mock
     mock_genai_part = genai_types.Part(text="test part")