feat: add auto-generated CI documentation pre-commit hook (#2890)

Our CI is entirely undocumented, this commit adds a README.md file with
a table of the current CI and what is does

---------

Signed-off-by: Nathan Weinberg <nweinber@redhat.com>

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -84,7 +84,7 @@ MEMORY_QUERY_TOOL = "knowledge_search"
 WEB_SEARCH_TOOL = "web_search"
 RAG_TOOL_GROUP = "builtin::rag"
 
-logger = get_logger(name=__name__, category="agents")
+log = get_logger(name=__name__, category="agents")
 
 
 class ChatAgent(ShieldRunnerMixin):
@@ -612,7 +612,7 @@ class ChatAgent(ShieldRunnerMixin):
             )
 
             if n_iter >= self.agent_config.max_infer_iters:
-                logger.info(f"done with MAX iterations ({n_iter}), exiting.")
+                log.info(f"done with MAX iterations ({n_iter}), exiting.")
                 # NOTE: mark end_of_turn to indicate to client that we are done with the turn
                 # Do not continue the tool call loop after this point
                 message.stop_reason = StopReason.end_of_turn
@@ -620,7 +620,7 @@ class ChatAgent(ShieldRunnerMixin):
                 break
 
             if stop_reason == StopReason.out_of_tokens:
-                logger.info("out of token budget, exiting.")
+                log.info("out of token budget, exiting.")
                 yield message
                 break
 
@@ -634,7 +634,7 @@ class ChatAgent(ShieldRunnerMixin):
                             message.content = [message.content] + output_attachments
                     yield message
                 else:
-                    logger.debug(f"completion message with EOM (iter: {n_iter}): {str(message)}")
+                    log.debug(f"completion message with EOM (iter: {n_iter}): {str(message)}")
                     input_messages = input_messages + [message]
             else:
                 input_messages = input_messages + [message]
@@ -889,7 +889,7 @@ class ChatAgent(ShieldRunnerMixin):
         else:
             tool_name_str = tool_name
 
-        logger.info(f"executing tool call: {tool_name_str} with args: {tool_call.arguments}")
+        log.info(f"executing tool call: {tool_name_str} with args: {tool_call.arguments}")
         result = await self.tool_runtime_api.invoke_tool(
             tool_name=tool_name_str,
             kwargs={
@@ -899,7 +899,7 @@ class ChatAgent(ShieldRunnerMixin):
                 **self.tool_name_to_args.get(tool_name_str, {}),
             },
         )
-        logger.debug(f"tool call {tool_name_str} completed with result: {result}")
+        log.debug(f"tool call {tool_name_str} completed with result: {result}")
         return result
 
 

llama_stack/providers/inline/agents/meta_reference/agents.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import uuid
 from collections.abc import AsyncGenerator
 from datetime import UTC, datetime
@@ -42,6 +41,7 @@ from llama_stack.apis.safety import Safety
 from llama_stack.apis.tools import ToolGroups, ToolRuntime
 from llama_stack.apis.vector_io import VectorIO
 from llama_stack.core.datatypes import AccessRule
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
 from llama_stack.providers.utils.pagination import paginate_records
 from llama_stack.providers.utils.responses.responses_store import ResponsesStore
@@ -51,7 +51,7 @@ from .config import MetaReferenceAgentsImplConfig
 from .openai_responses import OpenAIResponsesImpl
 from .persistence import AgentInfo
 
-logger = logging.getLogger()
+log = get_logger(name=__name__, category="agents")
 
 
 class MetaReferenceAgentsImpl(Agents):
@@ -268,7 +268,7 @@ class MetaReferenceAgentsImpl(Agents):
             # Get the agent info using the key
             agent_info_json = await self.persistence_store.get(agent_key)
             if not agent_info_json:
-                logger.error(f"Could not find agent info for key {agent_key}")
+                log.error(f"Could not find agent info for key {agent_key}")
                 continue
 
             try:
@@ -281,7 +281,7 @@ class MetaReferenceAgentsImpl(Agents):
                     )
                 )
             except Exception as e:
-                logger.error(f"Error parsing agent info for {agent_id}: {e}")
+                log.error(f"Error parsing agent info for {agent_id}: {e}")
                 continue
 
         # Convert Agent objects to dictionaries

llama_stack/providers/inline/agents/meta_reference/openai_responses.py

@@ -75,7 +75,7 @@ from llama_stack.models.llama.datatypes import ToolDefinition, ToolParamDefiniti
 from llama_stack.providers.utils.inference.openai_compat import convert_tooldef_to_openai_tool
 from llama_stack.providers.utils.responses.responses_store import ResponsesStore
 
-logger = get_logger(name=__name__, category="openai_responses")
+log = get_logger(name=__name__, category="openai_responses")
 
 OPENAI_RESPONSES_PREFIX = "openai_responses:"
 
@@ -544,12 +544,12 @@ class OpenAIResponsesImpl:
                 break
 
             if function_tool_calls:
-                logger.info("Exiting inference loop since there is a function (client-side) tool call")
+                log.info("Exiting inference loop since there is a function (client-side) tool call")
                 break
 
             n_iter += 1
             if n_iter >= max_infer_iters:
-                logger.info(f"Exiting inference loop since iteration count({n_iter}) exceeds {max_infer_iters=}")
+                log.info(f"Exiting inference loop since iteration count({n_iter}) exceeds {max_infer_iters=}")
                 break
 
             messages = next_turn_messages
@@ -698,7 +698,7 @@ class OpenAIResponsesImpl:
                 )
                 return search_response.data
             except Exception as e:
-                logger.warning(f"Failed to search vector store {vector_store_id}: {e}")
+                log.warning(f"Failed to search vector store {vector_store_id}: {e}")
                 return []
 
         # Run all searches in parallel using gather

llama_stack/providers/inline/agents/meta_reference/persistence.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 import json
-import logging
 import uuid
 from datetime import UTC, datetime
 
@@ -15,9 +14,10 @@ from llama_stack.core.access_control.access_control import AccessDeniedError, is
 from llama_stack.core.access_control.datatypes import AccessRule
 from llama_stack.core.datatypes import User
 from llama_stack.core.request_headers import get_authenticated_user
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import KVStore
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="agents")
 
 
 class AgentSessionInfo(Session):

llama_stack/providers/inline/agents/meta_reference/safety.py

@@ -5,13 +5,13 @@
 # the root directory of this source tree.
 
 import asyncio
-import logging
 
 from llama_stack.apis.inference import Message
 from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel
+from llama_stack.log import get_logger
 from llama_stack.providers.utils.telemetry import tracing
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="agents")
 
 
 class SafetyException(Exception):  # noqa: N818