anti
6d520eaa6f
Lift the Ollama subprocess shell-out out of EmailDriver and into a
proper provider subpackage shape:
decnet/orchestrator/emailgen/llm/
base.py — LLMBackend Protocol + LLMResult + LLMTimeout
factory.py — get_llm() reads DECNET_EMAILGEN_LLM
impl/ollama.py — current 'ollama run' subprocess path
impl/fake.py — canned-output backend used by tests
Driver now takes an LLMBackend on construction (or inherits the
factory default). Tests inject FakeBackend instead of monkeypatching
the subprocess layer, which is cleaner and ~10x faster. Swapping
Ollama for the Anthropic API / vLLM / llama.cpp is now a third branch
in factory.py; no driver rewrite needed.
Mirrors the convention used by decnet.web.db.factory + decnet.bus.factory
per the provider-subpackages-from-day-one rule in memory.
51 lines
1.5 KiB
Python
51 lines
1.5 KiB
Python
"""In-process fake backend for tests.
|
|
|
|
Returns a canned ``Subject:\\n\\nbody`` string so the driver path can be
|
|
exercised without an Ollama install. Configurable via ``DECNET_EMAILGEN_FAKE_OUTPUT``
|
|
(env) or the ``output`` constructor arg — the env-var path lets
|
|
integration tests run the worker end-to-end with deterministic output.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import time
|
|
from typing import Optional
|
|
|
|
from decnet.orchestrator.emailgen.llm.base import LLMBackend, LLMResult
|
|
|
|
|
|
_DEFAULT_OUTPUT = (
|
|
"Subject: Quick update\n\n"
|
|
"Hi,\n\nFollowing up on the topic.\n\nBest regards,\nFake Persona\n"
|
|
)
|
|
|
|
|
|
class FakeBackend(LLMBackend):
|
|
def __init__(
|
|
self,
|
|
*,
|
|
model: str = "fake-model",
|
|
timeout: float = 1.0,
|
|
output: Optional[str] = None,
|
|
success: bool = True,
|
|
) -> None:
|
|
self.model = model
|
|
self.timeout = timeout
|
|
self._output = (
|
|
output
|
|
if output is not None
|
|
else os.environ.get("DECNET_EMAILGEN_FAKE_OUTPUT", _DEFAULT_OUTPUT)
|
|
)
|
|
self._success = success
|
|
|
|
async def generate(self, prompt: str) -> LLMResult: # noqa: ARG002
|
|
t0 = time.monotonic()
|
|
latency_ms = int((time.monotonic() - t0) * 1000)
|
|
return LLMResult(
|
|
success=self._success,
|
|
text=self._output if self._success else "",
|
|
model=self.model,
|
|
latency_ms=latency_ms,
|
|
extra={"rc": 0 if self._success else 1},
|
|
)
|