Fix precommit check after moving to ruff (#927)

Lint check in main branch is failing. This fixes the lint check after we
moved to ruff in https://github.com/meta-llama/llama-stack/pull/921. We
need to move to a `ruff.toml` file as well as fixing and ignoring some
additional checks.

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>

docs/source/building_applications/agent_execution_loop.md

@@ -77,7 +77,7 @@ agent_config = AgentConfig(
     instructions="You are a helpful assistant",
     # Enable both RAG and tool usage
     toolgroups=[
-        {"name": "builtin::rag", "args": {"vector_db_ids": ["my_docs"]}}.
+        {"name": "builtin::rag", "args": {"vector_db_ids": ["my_docs"]}},
         "builtin::code_interpreter",
     ],
     # Configure safety
@@ -86,13 +86,9 @@ agent_config = AgentConfig(
     # Control the inference loop
     max_infer_iters=5,
     sampling_params={
-        "strategy": {
-            "type": "top_p",
-            "temperature": 0.7,
-            "top_p": 0.95
-        },
-        "max_tokens": 2048
-    }
+        "strategy": {"type": "top_p", "temperature": 0.7, "top_p": 0.95},
+        "max_tokens": 2048,
+    },
 )
 
 agent = Agent(client, agent_config)
@@ -101,11 +97,13 @@ session_id = agent.create_session("monitored_session")
 # Stream the agent's execution steps
 response = agent.create_turn(
     messages=[{"role": "user", "content": "Analyze this code and run it"}],
-    attachments=[{
-        "content": "https://raw.githubusercontent.com/example/code.py",
-        "mime_type": "text/plain"
-    }],
-    session_id=session_id
+    attachments=[
+        {
+            "content": "https://raw.githubusercontent.com/example/code.py",
+            "mime_type": "text/plain",
+        }
+    ],
+    session_id=session_id,
 )
 
 # Monitor each step of execution

docs/source/building_applications/evals.md

@@ -15,6 +15,7 @@ This first example walks you through how to evaluate a model candidate served by
 
 ```python
 import datasets
+
 ds = datasets.load_dataset(path="llamastack/mmmu", name="Agriculture", split="dev")
 ds = ds.select_columns(["chat_completion_input", "input_query", "expected_answer"])
 eval_rows = ds.to_pandas().to_dict(orient="records")
@@ -43,7 +44,7 @@ system_message = {
 client.eval_tasks.register(
     eval_task_id="meta-reference::mmmu",
     dataset_id=f"mmmu-{subset}-{split}",
-    scoring_functions=["basic::regex_parser_multiple_choice_answer"]
+    scoring_functions=["basic::regex_parser_multiple_choice_answer"],
 )
 
 response = client.eval.evaluate_rows(
@@ -62,9 +63,9 @@ response = client.eval.evaluate_rows(
                 "max_tokens": 4096,
                 "repeat_penalty": 1.0,
             },
-            "system_message": system_message
-        }
-    }
+            "system_message": system_message,
+        },
+    },
 )
 ```
 
@@ -88,7 +89,7 @@ _ = client.datasets.register(
         "input_query": {"type": "string"},
         "expected_answer": {"type": "string"},
         "chat_completion_input": {"type": "chat_completion_input"},
-    }
+    },
 )
 
 eval_rows = client.datasetio.get_rows_paginated(
@@ -101,7 +102,7 @@ eval_rows = client.datasetio.get_rows_paginated(
 client.eval_tasks.register(
     eval_task_id="meta-reference::simpleqa",
     dataset_id=simpleqa_dataset_id,
-    scoring_functions=["llm-as-judge::405b-simpleqa"]
+    scoring_functions=["llm-as-judge::405b-simpleqa"],
 )
 
 response = client.eval.evaluate_rows(
@@ -120,8 +121,8 @@ response = client.eval.evaluate_rows(
                 "max_tokens": 4096,
                 "repeat_penalty": 1.0,
             },
-        }
-    }
+        },
+    },
 )
 ```
 
@@ -144,14 +145,14 @@ agent_config = {
         {
             "type": "brave_search",
             "engine": "tavily",
-            "api_key": userdata.get("TAVILY_SEARCH_API_KEY")
+            "api_key": userdata.get("TAVILY_SEARCH_API_KEY"),
         }
     ],
     "tool_choice": "auto",
     "tool_prompt_format": "json",
     "input_shields": [],
     "output_shields": [],
-    "enable_session_persistence": False
+    "enable_session_persistence": False,
 }
 
 response = client.eval.evaluate_rows(
@@ -163,7 +164,7 @@ response = client.eval.evaluate_rows(
         "eval_candidate": {
             "type": "agent",
             "config": agent_config,
-        }
-    }
+        },
+    },
 )
 ```

docs/source/building_applications/evaluation.md

@@ -13,7 +13,7 @@ Here's how to set up basic evaluation:
 response = client.eval_tasks.register(
     eval_task_id="my_eval",
     dataset_id="my_dataset",
-    scoring_functions=["accuracy", "relevance"]
+    scoring_functions=["accuracy", "relevance"],
 )
 
 # Run evaluation
@@ -21,16 +21,10 @@ job = client.eval.run_eval(
     task_id="my_eval",
     task_config={
         "type": "app",
-        "eval_candidate": {
-            "type": "agent",
-            "config": agent_config
-        }
-    }
+        "eval_candidate": {"type": "agent", "config": agent_config},
+    },
 )
 
 # Get results
-result = client.eval.job_result(
-    task_id="my_eval",
-    job_id=job.job_id
-)
+result = client.eval.job_result(task_id="my_eval", job_id=job.job_id)
 ```

docs/source/building_applications/rag.md

@@ -34,15 +34,16 @@ chunks = [
     {
         "document_id": "doc1",
         "content": "Your document text here",
-        "mime_type": "text/plain"
+        "mime_type": "text/plain",
     },
-    ...
+    ...,
 ]
 client.vector_io.insert(vector_db_id, chunks)
 
 # You can then query for these chunks
-chunks_response = client.vector_io.query(vector_db_id, query="What do you know about...")
-
+chunks_response = client.vector_io.query(
+    vector_db_id, query="What do you know about..."
+)
 ```
 
 ### Using the RAG Tool
@@ -81,7 +82,6 @@ results = client.tool_runtime.rag_tool.query(
 One of the most powerful patterns is combining agents with RAG capabilities. Here's a complete example:
 
 ```python
-
 # Configure agent with memory
 agent_config = AgentConfig(
     model="Llama3.2-3B-Instruct",
@@ -91,9 +91,9 @@ agent_config = AgentConfig(
             "name": "builtin::rag",
             "args": {
                 "vector_db_ids": [vector_db_id],
-            }
+            },
         }
-    ]
+    ],
 )
 
 agent = Agent(client, agent_config)
@@ -101,25 +101,21 @@ session_id = agent.create_session("rag_session")
 
 # Initial document ingestion
 response = agent.create_turn(
-    messages=[{
-        "role": "user",
-        "content": "I am providing some documents for reference."
-    }],
+    messages=[
+        {"role": "user", "content": "I am providing some documents for reference."}
+    ],
     documents=[
         dict(
             content="https://raw.githubusercontent.com/example/doc.rst",
-            mime_type="text/plain"
+            mime_type="text/plain",
         )
     ],
-    session_id=session_id
+    session_id=session_id,
 )
 
 # Query with RAG
 response = agent.create_turn(
-    messages=[{
-        "role": "user",
-        "content": "What are the key topics in the documents?"
-    }],
-    session_id=session_id
+    messages=[{"role": "user", "content": "What are the key topics in the documents?"}],
+    session_id=session_id,
 )
 ```

docs/source/building_applications/safety.md

@@ -5,15 +5,11 @@ Safety is a critical component of any AI application. Llama Stack provides a Shi
 ```python
 # Register a safety shield
 shield_id = "content_safety"
-client.shields.register(
-    shield_id=shield_id,
-    provider_shield_id="llama-guard-basic"
-)
+client.shields.register(shield_id=shield_id, provider_shield_id="llama-guard-basic")
 
 # Run content through shield
 response = client.safety.run_shield(
-    shield_id=shield_id,
-    messages=[{"role": "user", "content": "User message here"}]
+    shield_id=shield_id, messages=[{"role": "user", "content": "User message here"}]
 )
 
 if response.violation:

docs/source/building_applications/telemetry.md

@@ -8,24 +8,16 @@ The telemetry system supports three main types of events:
 - **Unstructured Log Events**: Free-form log messages with severity levels
 ```python
 unstructured_log_event = UnstructuredLogEvent(
-    message="This is a log message",
-    severity=LogSeverity.INFO
+    message="This is a log message", severity=LogSeverity.INFO
 )
 ```
 - **Metric Events**: Numerical measurements with units
 ```python
-metric_event = MetricEvent(
-    metric="my_metric",
-    value=10,
-    unit="count"
-)
+metric_event = MetricEvent(metric="my_metric", value=10, unit="count")
 ```
 - **Structured Log Events**: System events like span start/end. Extensible to add more structured log types.
 ```python
-structured_log_event = SpanStartPayload(
-    name="my_span",
-    parent_span_id="parent_span_id"
-)
+structured_log_event = SpanStartPayload(name="my_span", parent_span_id="parent_span_id")
 ```
 
 ### Spans and Traces

docs/source/building_applications/tools.md

@@ -35,7 +35,7 @@ Example client SDK call to register a "websearch" toolgroup that is provided by
 client.toolgroups.register(
     toolgroup_id="builtin::websearch",
     provider_id="brave-search",
-    args={"max_results": 5}
+    args={"max_results": 5},
 )
 ```
 
@@ -50,8 +50,7 @@ The Code Interpreter allows execution of Python code within a controlled environ
 ```python
 # Register Code Interpreter tool group
 client.toolgroups.register(
-    toolgroup_id="builtin::code_interpreter",
-    provider_id="code_interpreter"
+    toolgroup_id="builtin::code_interpreter", provider_id="code_interpreter"
 )
 ```
 
@@ -68,16 +67,14 @@ The WolframAlpha tool provides access to computational knowledge through the Wol
 ```python
 # Register WolframAlpha tool group
 client.toolgroups.register(
-    toolgroup_id="builtin::wolfram_alpha",
-    provider_id="wolfram-alpha"
+    toolgroup_id="builtin::wolfram_alpha", provider_id="wolfram-alpha"
 )
 ```
 
 Example usage:
 ```python
 result = client.tool_runtime.invoke_tool(
-    tool_name="wolfram_alpha",
-    args={"query": "solve x^2 + 2x + 1 = 0"}
+    tool_name="wolfram_alpha", args={"query": "solve x^2 + 2x + 1 = 0"}
 )
 ```
 
@@ -90,10 +87,7 @@ The Memory tool enables retrieval of context from various types of memory banks
 client.toolgroups.register(
     toolgroup_id="builtin::memory",
     provider_id="memory",
-    args={
-        "max_chunks": 5,
-        "max_tokens_in_context": 4096
-    }
+    args={"max_chunks": 5, "max_tokens_in_context": 4096},
 )
 ```
 
@@ -136,9 +130,7 @@ config = AgentConfig(
     toolgroups=[
         "builtin::websearch",
     ],
-    client_tools=[
-        ToolDef(name="client_tool", description="Client provided tool")
-    ]
+    client_tools=[ToolDef(name="client_tool", description="Client provided tool")],
 )
 ```
 
@@ -167,9 +159,9 @@ Example tool definition:
             "name": "query",
             "parameter_type": "string",
             "description": "The query to search for",
-            "required": True
+            "required": True,
         }
-    ]
+    ],
 }
 ```
 
@@ -179,8 +171,7 @@ Tools can be invoked using the `invoke_tool` method:
 
 ```python
 result = client.tool_runtime.invoke_tool(
-    tool_name="web_search",
-    kwargs={"query": "What is the capital of France?"}
+    tool_name="web_search", kwargs={"query": "What is the capital of France?"}
 )
 ```