breakdown folder tree for epic R01
This commit is contained in:
@@ -0,0 +1,5 @@
|
||||
"""Test doubles and offline fakes package for Cowork Local test pyramid."""
|
||||
from .fake_provider import FakeProvider
|
||||
from .fake_tool_executor import FakeToolExecutor
|
||||
|
||||
__all__ = ["FakeProvider", "FakeToolExecutor"]
|
||||
@@ -0,0 +1,113 @@
|
||||
"""Fake LLM Provider for offline unit, contract, and characterization testing.
|
||||
|
||||
Provides deterministic responses, stream simulation, tool-call dispatching,
|
||||
and fault injection without requiring any external network access or API keys.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Callable, Dict, List, Optional
|
||||
|
||||
from providers.base import CancelFn, Provider, ProviderError, TextCallback, ToolSpec
|
||||
|
||||
|
||||
class FakeProvider(Provider):
|
||||
"""Deterministic test double mimicking real LLM Providers (OpenAI, Anthropic, Ollama)."""
|
||||
|
||||
name = "fake"
|
||||
supports_vision = True
|
||||
|
||||
def __init__(self, conf: Optional[Dict[str, Any]] = None) -> None:
|
||||
# Initialize base provider with default configuration if none provided
|
||||
super().__init__(conf or {"model": "fake-model-v1"})
|
||||
# History of all message batches sent across all chat calls
|
||||
self.call_history: List[List[Dict[str, Any]]] = []
|
||||
# Queue of programmed assistant responses to return sequentially
|
||||
self.response_queue: List[Dict[str, Any]] = []
|
||||
# Queue of exceptions to raise on corresponding calls
|
||||
self.error_queue: List[Exception] = []
|
||||
# Default text returned when response queue is empty
|
||||
self.default_text: str = "Fake model response."
|
||||
# Total number of chat invocations
|
||||
self.call_count: int = 0
|
||||
# Recorded tool specs passed into each turn
|
||||
self.last_tools: Optional[List[ToolSpec]] = None
|
||||
|
||||
def queue_response(
|
||||
self,
|
||||
content: str = "",
|
||||
tool_calls: Optional[List[Dict[str, Any]]] = None,
|
||||
reasoning: Optional[str] = None,
|
||||
chunks: Optional[List[str]] = None,
|
||||
) -> FakeProvider:
|
||||
"""Enqueue a pre-configured response structure for upcoming chat turns."""
|
||||
self.response_queue.append({
|
||||
"content": content,
|
||||
"tool_calls": tool_calls or [],
|
||||
"reasoning": reasoning,
|
||||
"chunks": chunks or ([content] if content else []),
|
||||
})
|
||||
return self
|
||||
|
||||
def queue_error(self, exc: Exception) -> FakeProvider:
|
||||
"""Enqueue an exception to simulate network/API errors on the next turn."""
|
||||
self.error_queue.append(exc)
|
||||
return self
|
||||
|
||||
def chat(
|
||||
self,
|
||||
messages: List[Dict[str, Any]],
|
||||
tools: Optional[List[ToolSpec]] = None,
|
||||
on_text: Optional[TextCallback] = None,
|
||||
cancel: Optional[CancelFn] = None,
|
||||
on_reasoning: Optional[TextCallback] = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""Simulate single LLM turn with full streaming and tool-call support."""
|
||||
self.call_count += 1
|
||||
self.call_history.append([dict(m) for m in messages])
|
||||
self.last_tools = tools
|
||||
|
||||
# 1. Check for injected errors
|
||||
if self.error_queue:
|
||||
raise self.error_queue.pop(0)
|
||||
|
||||
# 2. Check early cancellation before processing
|
||||
if cancel and cancel():
|
||||
raise ProviderError("Execution aborted by user cancel signal before response generation.")
|
||||
|
||||
# 3. Retrieve queued response or construct default response
|
||||
if self.response_queue:
|
||||
resp_spec = self.response_queue.pop(0)
|
||||
content = resp_spec.get("content", "")
|
||||
tool_calls = resp_spec.get("tool_calls", [])
|
||||
reasoning = resp_spec.get("reasoning")
|
||||
chunks = resp_spec.get("chunks", [content] if content else [])
|
||||
else:
|
||||
content = self.default_text
|
||||
tool_calls = []
|
||||
reasoning = None
|
||||
chunks = [content]
|
||||
|
||||
# 4. Stream reasoning chunks if provided
|
||||
if reasoning and on_reasoning:
|
||||
on_reasoning(reasoning)
|
||||
|
||||
# 5. Stream text chunks, checking cancellation between fragments
|
||||
for chunk in chunks:
|
||||
if cancel and cancel():
|
||||
raise ProviderError("Execution cancelled during text chunk streaming.")
|
||||
if on_text and chunk:
|
||||
on_text(chunk)
|
||||
|
||||
# 6. Return canonical assistant message payload
|
||||
assistant_msg: Dict[str, Any] = {
|
||||
"role": "assistant",
|
||||
"content": content,
|
||||
}
|
||||
if tool_calls:
|
||||
assistant_msg["tool_calls"] = tool_calls
|
||||
|
||||
return assistant_msg
|
||||
|
||||
def list_models(self) -> List[str]:
|
||||
"""Return available mock models for settings and validation tests."""
|
||||
return ["fake-model-v1", "fake-reasoner-pro", "fake-vision-plus"]
|
||||
@@ -0,0 +1,71 @@
|
||||
"""Fake Tool Executor for isolated, offline agent tool-call verification.
|
||||
|
||||
Allows tests to verify tool invocation arguments, mock tool return values,
|
||||
and simulate failures/delays without performing unsafe host disk or OS operations.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Callable, Dict, List, Optional
|
||||
|
||||
|
||||
class FakeToolExecutor:
|
||||
"""Mock execution engine for agent tool-call dispatching."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
# History of all executed tool invocations: List of {"name": str, "args": dict, "result": dict}
|
||||
self.call_log: List[Dict[str, Any]] = []
|
||||
# Custom handlers registered per tool name
|
||||
self.handlers: Dict[str, Callable[[Dict[str, Any]], Dict[str, Any]]] = {}
|
||||
# Pre-programmed fixed responses keyed by tool name
|
||||
self.mock_responses: Dict[str, Dict[str, Any]] = {}
|
||||
# Default response when no specific handler or response is found
|
||||
self.default_result: Dict[str, Any] = {"ok": True, "output": "Fake tool executed successfully."}
|
||||
|
||||
def register_handler(
|
||||
self,
|
||||
tool_name: str,
|
||||
handler: Callable[[Dict[str, Any]], Dict[str, Any]],
|
||||
) -> FakeToolExecutor:
|
||||
"""Register a dynamic handler function for a specific tool name."""
|
||||
self.handlers[tool_name] = handler
|
||||
return self
|
||||
|
||||
def set_mock_response(
|
||||
self,
|
||||
tool_name: str,
|
||||
result: Dict[str, Any],
|
||||
) -> FakeToolExecutor:
|
||||
"""Set a static return payload for a specific tool name."""
|
||||
self.mock_responses[tool_name] = result
|
||||
return self
|
||||
|
||||
def execute(self, tool_name: str, arguments: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Execute a tool call using registered mocks and record invocation details."""
|
||||
# 1. Resolve result from handler, preset response, or default fallback
|
||||
if tool_name in self.handlers:
|
||||
result = self.handlers[tool_name](arguments)
|
||||
elif tool_name in self.mock_responses:
|
||||
result = self.mock_responses[tool_name]
|
||||
else:
|
||||
result = dict(self.default_result)
|
||||
result["tool"] = tool_name
|
||||
result["received_args"] = arguments
|
||||
|
||||
# 2. Record execution trace for post-test assertions
|
||||
self.call_log.append({
|
||||
"name": tool_name,
|
||||
"args": dict(arguments),
|
||||
"result": dict(result),
|
||||
})
|
||||
|
||||
return result
|
||||
|
||||
def get_calls_for(self, tool_name: str) -> List[Dict[str, Any]]:
|
||||
"""Retrieve all recorded calls for a given tool name."""
|
||||
return [call for call in self.call_log if call["name"] == tool_name]
|
||||
|
||||
def reset(self) -> None:
|
||||
"""Clear recorded logs and registered mock responses."""
|
||||
self.call_log.clear()
|
||||
self.handlers.clear()
|
||||
self.mock_responses.clear()
|
||||
Reference in New Issue
Block a user