anti
0b9873982d
Lift the format-agnostic pieces from decnet/orchestrator/emailgen/
into the new decnet/realism/ library so file-class content generation
(stage 3 of the realism migration) can reuse them. Email-specific
delivery (RFC 2822 EML, IMAP/POP3 spool, thread chains) stays in
orchestrator/.
Renames (history-preserving git mv):
emailgen/personas.py -> realism/personas.py
emailgen/prompt.py -> realism/prompts/email.py
emailgen/global_pool.py -> realism/personas_pool.py
emailgen/llm/ -> realism/llm/
Env-var clean break (pre-v1, no aliases):
DECNET_EMAILGEN_LLM -> DECNET_REALISM_LLM
DECNET_EMAILGEN_MODEL -> DECNET_REALISM_MODEL
DECNET_EMAILGEN_TIMEOUT -> DECNET_REALISM_TIMEOUT
DECNET_EMAILGEN_PERSONAS -> DECNET_REALISM_PERSONAS
DECNET_EMAILGEN_FAKE_OUTPUT -> DECNET_REALISM_FAKE_OUTPUT
Importers rewritten in: orchestrator/emailgen/scheduler.py,
orchestrator/drivers/email.py, web/router/{emailgen,topology}/
api_personas.py, cli/emailgen.py. Tests for moved modules relocated
to tests/realism/; tests for stay-put modules updated in place.
API URL `/api/v1/emailgen/personas` and CLI `decnet emailgen
import-personas` keep their public names until the service-collapse
commit (stage 5).
101 lines
3.4 KiB
Python
101 lines
3.4 KiB
Python
"""Ollama subprocess backend.
|
|
|
|
Shells out to ``ollama run <model>`` with the prompt fed via stdin.
|
|
|
|
Why subprocess and not the Ollama HTTP API:
|
|
* No new dependency (``ollama`` Python lib is optional).
|
|
* Works on hosts where Ollama is bound to a unix socket, an unusual TCP
|
|
port, or behind a remote-mount layer — `ollama run` resolves all that.
|
|
* Same path the operator uses by hand (``ollama run llama3.1``); easier
|
|
to debug discrepancies between worker output and a console session.
|
|
|
|
Cost: per-call process spawn (~50ms on a warm box). Acceptable for
|
|
realism tick rates (one body per ~5 minutes per persona by default).
|
|
When that cost matters, swap to an HTTP-API backend; the seam is in
|
|
:mod:`decnet.realism.llm.factory`.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import os
|
|
import time
|
|
from typing import Optional
|
|
|
|
from decnet.logging import get_logger
|
|
from decnet.realism.llm.base import LLMBackend, LLMResult, LLMTimeout
|
|
|
|
log = get_logger("realism.llm")
|
|
|
|
_OLLAMA = "ollama"
|
|
_DEFAULT_MODEL = os.environ.get("DECNET_REALISM_MODEL", "llama3.1")
|
|
_DEFAULT_TIMEOUT = float(os.environ.get("DECNET_REALISM_TIMEOUT", "60"))
|
|
|
|
|
|
class OllamaBackend(LLMBackend):
|
|
"""Concrete :class:`LLMBackend` that shells out to ``ollama run``."""
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
model: Optional[str] = None,
|
|
timeout: Optional[float] = None,
|
|
) -> None:
|
|
self.model = model or _DEFAULT_MODEL
|
|
self.timeout = timeout if timeout is not None else _DEFAULT_TIMEOUT
|
|
|
|
async def generate(self, prompt: str) -> LLMResult:
|
|
t0 = time.monotonic()
|
|
try:
|
|
proc = await asyncio.create_subprocess_exec(
|
|
_OLLAMA, "run", self.model,
|
|
stdin=asyncio.subprocess.PIPE,
|
|
stdout=asyncio.subprocess.PIPE,
|
|
stderr=asyncio.subprocess.PIPE,
|
|
)
|
|
except FileNotFoundError as exc:
|
|
latency_ms = int((time.monotonic() - t0) * 1000)
|
|
return LLMResult(
|
|
success=False,
|
|
text="",
|
|
model=self.model,
|
|
latency_ms=latency_ms,
|
|
extra={"rc": 127, "stderr": f"argv[0] not found: {exc}"},
|
|
)
|
|
try:
|
|
stdout, stderr = await asyncio.wait_for(
|
|
proc.communicate(prompt.encode("utf-8")),
|
|
timeout=self.timeout,
|
|
)
|
|
except asyncio.TimeoutError as exc:
|
|
try:
|
|
proc.kill()
|
|
except ProcessLookupError:
|
|
pass
|
|
raise LLMTimeout(
|
|
f"ollama run {self.model} exceeded {self.timeout}s"
|
|
) from exc
|
|
|
|
latency_ms = int((time.monotonic() - t0) * 1000)
|
|
rc = proc.returncode if proc.returncode is not None else -1
|
|
text = stdout.decode("utf-8", "replace")
|
|
stderr_s = stderr.decode("utf-8", "replace")
|
|
if rc != 0 or not text.strip():
|
|
log.warning(
|
|
"ollama backend non-zero / empty rc=%d model=%s stderr=%r",
|
|
rc, self.model, stderr_s[:200],
|
|
)
|
|
return LLMResult(
|
|
success=False,
|
|
text=text,
|
|
model=self.model,
|
|
latency_ms=latency_ms,
|
|
extra={"rc": rc, "stderr": stderr_s.strip()[:256]},
|
|
)
|
|
return LLMResult(
|
|
success=True,
|
|
text=text,
|
|
model=self.model,
|
|
latency_ms=latency_ms,
|
|
extra={"rc": rc},
|
|
)
|