[remove import *][2/n] remove rest of import * in implementations (#690)

# What does this PR do?

- see https://github.com/meta-llama/llama-stack/pull/689
<img width="591" alt="image"
src="https://github.com/user-attachments/assets/76946a67-7373-43b5-8a03-0ad201aa543b"
/>

- leaving `tools/builtin.py` to avoid conflicts


## Test Plan

- see https://github.com/meta-llama/llama-stack/pull/689

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

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

@@ -13,19 +13,64 @@ import secrets
 import string
 import uuid
 from datetime import datetime
-from typing import AsyncGenerator, List, Tuple
+from typing import AsyncGenerator, Dict, List, Optional, Tuple
 from urllib.parse import urlparse
 
 import httpx
 
+from llama_models.llama3.api.datatypes import BuiltinTool
 
-from llama_stack.apis.agents import *  # noqa: F403
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.memory_banks import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentTool,
+    AgentTurnCreateRequest,
+    AgentTurnResponseEvent,
+    AgentTurnResponseEventType,
+    AgentTurnResponseStepCompletePayload,
+    AgentTurnResponseStepProgressPayload,
+    AgentTurnResponseStepStartPayload,
+    AgentTurnResponseStreamChunk,
+    AgentTurnResponseTurnCompletePayload,
+    AgentTurnResponseTurnStartPayload,
+    Attachment,
+    CodeInterpreterToolDefinition,
+    FunctionCallToolDefinition,
+    InferenceStep,
+    MemoryRetrievalStep,
+    MemoryToolDefinition,
+    PhotogenToolDefinition,
+    SearchToolDefinition,
+    ShieldCallStep,
+    StepType,
+    ToolExecutionStep,
+    Turn,
+    WolframAlphaToolDefinition,
+)
 
-from llama_stack.apis.common.content_types import InterleavedContent, TextContentItem
+from llama_stack.apis.common.content_types import (
+    InterleavedContent,
+    TextContentItem,
+    URL,
+)
+from llama_stack.apis.inference import (
+    ChatCompletionResponseEventType,
+    CompletionMessage,
+    Inference,
+    Message,
+    SamplingParams,
+    StopReason,
+    SystemMessage,
+    ToolCallDelta,
+    ToolCallParseStatus,
+    ToolChoice,
+    ToolDefinition,
+    ToolResponse,
+    ToolResponseMessage,
+    UserMessage,
+)
+from llama_stack.apis.memory import Memory, MemoryBankDocument, QueryDocumentsResponse
+from llama_stack.apis.memory_banks import MemoryBanks, VectorMemoryBankParams
+from llama_stack.apis.safety import Safety
 
 from llama_stack.providers.utils.kvstore import KVStore
 from llama_stack.providers.utils.memory.vector_store import concat_interleaved_content

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

@@ -9,15 +9,26 @@ import logging
 import shutil
 import tempfile
 import uuid
-from typing import AsyncGenerator
+from typing import AsyncGenerator, List, Optional, Union
 
 from termcolor import colored
 
-from llama_stack.apis.inference import Inference
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentCreateResponse,
+    Agents,
+    AgentSessionCreateResponse,
+    AgentStepResponse,
+    AgentTurnCreateRequest,
+    Attachment,
+    Session,
+    Turn,
+)
+
+from llama_stack.apis.inference import Inference, ToolResponseMessage, UserMessage
 from llama_stack.apis.memory import Memory
 from llama_stack.apis.memory_banks import MemoryBanks
 from llama_stack.apis.safety import Safety
-from llama_stack.apis.agents import *  # noqa: F403
 
 from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
 

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

@@ -10,9 +10,11 @@ import uuid
 from datetime import datetime
 
 from typing import List, Optional
-from llama_stack.apis.agents import *  # noqa: F403
+
 from pydantic import BaseModel
 
+from llama_stack.apis.agents import Turn
+
 from llama_stack.providers.utils.kvstore import KVStore
 
 log = logging.getLogger(__name__)

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

@@ -7,8 +7,6 @@
 from typing import List
 
 from jinja2 import Template
-from llama_models.llama3.api import *  # noqa: F403
-
 
 from llama_stack.apis.agents import (
     DefaultMemoryQueryGeneratorConfig,
@@ -16,7 +14,7 @@ from llama_stack.apis.agents import (
     MemoryQueryGenerator,
     MemoryQueryGeneratorConfig,
 )
-from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.apis.inference import Message, UserMessage
 from llama_stack.providers.utils.inference.prompt_adapter import (
     interleaved_content_as_str,
 )

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

@@ -9,7 +9,9 @@ import logging
 
 from typing import List
 
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.inference import Message
+
+from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel
 
 log = logging.getLogger(__name__)
 

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

@@ -8,10 +8,26 @@ from typing import AsyncIterator, List, Optional, Union
 
 import pytest
 
-from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.apis.memory import *  # noqa: F403
-from llama_stack.apis.safety import *  # noqa: F403
-from llama_stack.apis.agents import *  # noqa: F403
+from llama_stack.apis.agents import (
+    AgentConfig,
+    AgentTurnCreateRequest,
+    AgentTurnResponseTurnCompletePayload,
+)
+
+from llama_stack.apis.inference import (
+    ChatCompletionResponse,
+    ChatCompletionResponseEvent,
+    ChatCompletionResponseStreamChunk,
+    CompletionMessage,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    UserMessage,
+)
+from llama_stack.apis.memory import MemoryBank
+from llama_stack.apis.safety import RunShieldResponse
 
 from ..agents import (
     AGENT_INSTANCES_BY_ID,

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

@@ -7,7 +7,7 @@
 from typing import List
 
 from llama_stack.apis.inference import Message
-from llama_stack.apis.safety import *  # noqa: F403
+from llama_stack.apis.safety import Safety
 
 from ..safety import ShieldRunnerMixin
 from .builtin import BaseTool