refactor(realism): move emailgen LLM/personas/prompt into shared library
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).
This commit is contained in:
@@ -122,8 +122,8 @@ def register(app: typer.Typer) -> None:
|
||||
this command does not touch them.
|
||||
"""
|
||||
_require_master_mode("emailgen import-personas")
|
||||
from decnet.orchestrator.emailgen import global_pool
|
||||
from decnet.orchestrator.emailgen.personas import parse_personas
|
||||
from decnet.realism import personas_pool as global_pool
|
||||
from decnet.realism.personas import parse_personas
|
||||
|
||||
try:
|
||||
raw = path.read_text(encoding="utf-8")
|
||||
|
||||
@@ -5,9 +5,9 @@ configured emailgen spool directory (``/var/spool/decnet-emails/`` by
|
||||
default). The IMAP/POP3 service templates read that spool at request
|
||||
time so attackers see the generated mail in their MUA.
|
||||
|
||||
The LLM call goes through :mod:`decnet.orchestrator.emailgen.llm` —
|
||||
backend-agnostic by construction so swapping Ollama for the Anthropic
|
||||
API, vLLM, or llama.cpp is a config change, not a driver rewrite.
|
||||
The LLM call goes through :mod:`decnet.realism.llm` — backend-agnostic
|
||||
by construction so swapping Ollama for the Anthropic API, vLLM, or
|
||||
llama.cpp is a config change, not a driver rewrite.
|
||||
Output is parsed-and-repaired into a valid EML using
|
||||
:mod:`email.mime.*`; the worker then ``docker exec``\\s a ``tee`` to
|
||||
drop the file inside the target container, followed by a
|
||||
@@ -29,10 +29,10 @@ from typing import Any, Optional
|
||||
|
||||
from decnet.logging import get_logger
|
||||
from decnet.orchestrator.drivers.base import ActivityResult
|
||||
from decnet.orchestrator.emailgen.llm import LLMBackend, LLMTimeout, get_llm
|
||||
from decnet.orchestrator.emailgen.prompt import PromptInputs, build as build_prompt
|
||||
from decnet.orchestrator.emailgen.scheduler import EmailAction
|
||||
from decnet.orchestrator.emailgen.threads import new_message_id
|
||||
from decnet.realism.llm import LLMBackend, LLMTimeout, get_llm
|
||||
from decnet.realism.prompts.email import PromptInputs, build as build_prompt
|
||||
|
||||
log = get_logger("orchestrator.email")
|
||||
|
||||
|
||||
@@ -11,7 +11,7 @@ heartbeat / control-listener scaffolding via :mod:`decnet.bus.publish`.
|
||||
|
||||
Lazy worker re-export: :func:`emailgen_worker` is loaded on first
|
||||
attribute access so that submodules can import package-level names
|
||||
(``decnet.orchestrator.emailgen.prompt``) without triggering an eager
|
||||
(``decnet.orchestrator.emailgen.events``) without triggering an eager
|
||||
load of the worker — and through it, the email driver, which imports
|
||||
back into this package. Without lazy loading the package + driver +
|
||||
worker form a cycle.
|
||||
|
||||
@@ -1,22 +0,0 @@
|
||||
"""LLM backend for emailgen.
|
||||
|
||||
Pluggable from day one (per the provider-subpackages convention used by
|
||||
:mod:`decnet.web.db` and :mod:`decnet.bus`): the worker only depends on
|
||||
:class:`LLMBackend` from :mod:`base`; concrete transports live under
|
||||
:mod:`impl` and are selected by :func:`get_llm`.
|
||||
|
||||
This is the seam ANTI will pull on when swapping local Ollama for the
|
||||
Anthropic API, llama.cpp, vLLM, or any other inference server — change
|
||||
``DECNET_EMAILGEN_LLM`` (or pass ``llm=`` to the driver), no driver
|
||||
rewrite.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from decnet.orchestrator.emailgen.llm.base import (
|
||||
LLMBackend,
|
||||
LLMResult,
|
||||
LLMTimeout,
|
||||
)
|
||||
from decnet.orchestrator.emailgen.llm.factory import get_llm
|
||||
|
||||
__all__ = ["LLMBackend", "LLMResult", "LLMTimeout", "get_llm"]
|
||||
@@ -1,6 +0,0 @@
|
||||
"""Concrete LLM-backend implementations.
|
||||
|
||||
Importers go through :func:`decnet.orchestrator.emailgen.llm.get_llm`,
|
||||
not these modules directly — same convention as
|
||||
:mod:`decnet.web.db.sqlite` and :mod:`decnet.bus.unix_client`.
|
||||
"""
|
||||
@@ -1,119 +0,0 @@
|
||||
"""Persona schema for the emailgen worker.
|
||||
|
||||
Stored as a JSON list on :attr:`Topology.email_personas`. Each persona
|
||||
describes one fictional employee whose mailbox lives on the topology's
|
||||
IMAP/POP3 decky. The schema deliberately stays narrow: the LLM gets
|
||||
*enough* differentiation to write distinct voices, no more.
|
||||
|
||||
Invalid entries are dropped with a warning (returned alongside the
|
||||
parsed list) rather than raising — a single typo in one persona must
|
||||
not stall the entire emailgen tick.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Literal, Optional
|
||||
|
||||
from pydantic import BaseModel, Field, ValidationError, field_validator
|
||||
|
||||
from decnet.logging import get_logger
|
||||
|
||||
logger = get_logger("orchestrator.emailgen")
|
||||
|
||||
Tone = Literal["formal", "direct", "casual", "technical"]
|
||||
ReplyLatency = Literal["fast", "normal", "slow"]
|
||||
|
||||
|
||||
class EmailPersona(BaseModel):
|
||||
"""One fake mailbox owner.
|
||||
|
||||
``language`` is ISO 639-1 (``en``, ``es``, ``pt``…); when unset on the
|
||||
persona it falls back to the topology's ``language_default``.
|
||||
``uses_llms_heavily`` lifts the prompt-layer em-dash suppression for
|
||||
that persona — em-dashes are an LLM tell, but a persona explicitly
|
||||
pegged as a heavy LLM user should *naturally* produce them.
|
||||
"""
|
||||
name: str = Field(min_length=1, max_length=128)
|
||||
email: str = Field(min_length=3, max_length=255)
|
||||
role: str = Field(min_length=1, max_length=128)
|
||||
tone: Tone = "formal"
|
||||
mannerisms: list[str] = Field(default_factory=list, max_length=12)
|
||||
language: Optional[str] = Field(default=None, max_length=8)
|
||||
signature: Optional[str] = Field(default=None, max_length=512)
|
||||
active_hours: str = Field(default="09:00-18:00", max_length=32)
|
||||
reply_latency: ReplyLatency = "normal"
|
||||
uses_llms_heavily: bool = False
|
||||
|
||||
@field_validator("email")
|
||||
@classmethod
|
||||
def _email_shape(cls, v: str) -> str:
|
||||
# Cheap structural check — full RFC 5322 isn't worth the
|
||||
# dependency. We only need ``user@domain`` with non-empty parts
|
||||
# for the prompt builder + Message-ID generator.
|
||||
if "@" not in v:
|
||||
raise ValueError("email must contain '@'")
|
||||
local, _, domain = v.rpartition("@")
|
||||
if not local or not domain or "." not in domain:
|
||||
raise ValueError("email must look like user@domain.tld")
|
||||
return v
|
||||
|
||||
|
||||
def parse_personas(
|
||||
raw: str | list | None,
|
||||
*,
|
||||
language_default: str = "en",
|
||||
) -> list[EmailPersona]:
|
||||
"""Parse the JSON-or-list ``email_personas`` value into models.
|
||||
|
||||
Resolves ``language`` against *language_default* so downstream
|
||||
consumers (prompt builder, scheduler) never need to know about
|
||||
fallback semantics.
|
||||
"""
|
||||
if not raw:
|
||||
return []
|
||||
if isinstance(raw, str):
|
||||
try:
|
||||
raw = json.loads(raw)
|
||||
except json.JSONDecodeError as exc:
|
||||
logger.warning("emailgen personas: invalid JSON, skipping: %s", exc)
|
||||
return []
|
||||
if not isinstance(raw, list):
|
||||
logger.warning(
|
||||
"emailgen personas: expected list, got %s", type(raw).__name__
|
||||
)
|
||||
return []
|
||||
out: list[EmailPersona] = []
|
||||
for i, entry in enumerate(raw):
|
||||
try:
|
||||
persona = EmailPersona.model_validate(entry)
|
||||
except ValidationError as exc:
|
||||
logger.warning(
|
||||
"emailgen personas: dropping invalid entry index=%d: %s",
|
||||
i, exc.errors(include_url=False),
|
||||
)
|
||||
continue
|
||||
if persona.language is None:
|
||||
persona = persona.model_copy(update={"language": language_default})
|
||||
out.append(persona)
|
||||
return out
|
||||
|
||||
|
||||
def in_active_hours(persona: EmailPersona, now_hour: int) -> bool:
|
||||
"""Return True if *now_hour* (0–23) falls in the persona's window.
|
||||
|
||||
Format: ``"HH:MM-HH:MM"``. Wrap-around windows (``"22:00-06:00"``)
|
||||
are supported. Invalid windows treat the persona as always-on so a
|
||||
config typo never silences the whole fleet.
|
||||
"""
|
||||
try:
|
||||
start_s, end_s = persona.active_hours.split("-")
|
||||
start_h = int(start_s.split(":")[0])
|
||||
end_h = int(end_s.split(":")[0])
|
||||
except (ValueError, IndexError):
|
||||
return True
|
||||
if start_h == end_h:
|
||||
return True
|
||||
if start_h < end_h:
|
||||
return start_h <= now_hour < end_h
|
||||
# Wrap-around (e.g. 22:00-06:00).
|
||||
return now_hour >= start_h or now_hour < end_h
|
||||
@@ -25,18 +25,18 @@ from datetime import datetime
|
||||
from typing import Any, Optional
|
||||
|
||||
from decnet.logging import get_logger
|
||||
from decnet.orchestrator.emailgen import global_pool
|
||||
from decnet.orchestrator.emailgen.personas import (
|
||||
EmailPersona,
|
||||
in_active_hours,
|
||||
parse_personas,
|
||||
)
|
||||
from decnet.orchestrator.emailgen.threads import (
|
||||
ThreadChain,
|
||||
new_thread_id,
|
||||
references_for_reply,
|
||||
reply_subject,
|
||||
)
|
||||
from decnet.realism import personas_pool as global_pool
|
||||
from decnet.realism.personas import (
|
||||
EmailPersona,
|
||||
in_active_hours,
|
||||
parse_personas,
|
||||
)
|
||||
|
||||
logger = get_logger("orchestrator.emailgen")
|
||||
|
||||
|
||||
@@ -13,8 +13,8 @@ import from here. This package owns:
|
||||
``mtime`` sampler so planted files don't all stamp at wall-clock-now.
|
||||
* :mod:`decnet.realism.planner` — picks ``(decky, persona, class,
|
||||
action, mtime)`` tuples for the orchestrator's tick loop.
|
||||
* :mod:`decnet.realism.personas` — persona schema (lifted from
|
||||
``orchestrator.emailgen.personas`` in stage 2 of the migration).
|
||||
* :mod:`decnet.realism.personas` — persona schema (the
|
||||
:class:`EmailPersona` record describing each fictional employee).
|
||||
* :mod:`decnet.realism.prompts` — prompt builders, one per content
|
||||
class, sharing an em-dash-suppression style helper.
|
||||
* :mod:`decnet.realism.llm` — :class:`LLMBackend` ABC + factory + impl
|
||||
|
||||
@@ -38,8 +38,7 @@ def _parse_window(window: str) -> tuple[int, int, int, int] | None:
|
||||
|
||||
Returns ``None`` for malformed input — callers treat that as
|
||||
"always-on" so a single config typo never silences the whole fleet
|
||||
(mirrors :func:`decnet.orchestrator.emailgen.personas.in_active_hours`
|
||||
semantics).
|
||||
(mirrors :func:`decnet.realism.personas.in_active_hours` semantics).
|
||||
"""
|
||||
try:
|
||||
start_s, end_s = window.split("-")
|
||||
|
||||
@@ -1,8 +1,17 @@
|
||||
"""LLM backend ABC + factory + impls.
|
||||
"""LLM backend for the realism library.
|
||||
|
||||
Populated in stage 2 of the realism migration: lifts the existing
|
||||
``orchestrator.emailgen.llm`` subpackage as-is (``base``, ``factory``,
|
||||
``impl/ollama``, ``impl/fake``). Stage 6 adds ``circuit.py`` for
|
||||
cross-call breaker behaviour.
|
||||
Pluggable per the provider-subpackages convention (mirrors
|
||||
:mod:`decnet.web.db` and :mod:`decnet.bus`): consumers depend on
|
||||
:class:`LLMBackend` from :mod:`base`; concrete transports live under
|
||||
:mod:`impl` and are selected by :func:`get_llm`.
|
||||
|
||||
This is the seam to pull on when swapping local Ollama for the
|
||||
Anthropic API, llama.cpp, vLLM, or any other inference server — change
|
||||
``DECNET_REALISM_LLM`` (or pass ``llm=`` directly), no caller rewrite.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from decnet.realism.llm.base import LLMBackend, LLMResult, LLMTimeout
|
||||
from decnet.realism.llm.factory import get_llm
|
||||
|
||||
__all__ = ["LLMBackend", "LLMResult", "LLMTimeout", "get_llm"]
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
"""Backend protocol shared by every LLM transport.
|
||||
|
||||
Deliberately narrow: emailgen needs one async ``generate`` call that
|
||||
takes a prompt string and returns the model's output text plus enough
|
||||
metadata for the worker to populate the orchestrator-email payload
|
||||
(model name, latency, success bit). Streaming, embeddings, multi-turn
|
||||
chat — all out of scope here; emailgen only ever does one-shot
|
||||
single-prompt generations.
|
||||
Deliberately narrow: realism consumers need one async ``generate``
|
||||
call that takes a prompt string and returns the model's output text
|
||||
plus enough metadata to populate per-event payloads (model name,
|
||||
latency, success bit). Streaming, embeddings, multi-turn chat — all
|
||||
out of scope here; realism only ever does one-shot single-prompt
|
||||
generations.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -39,7 +39,7 @@ class LLMResult:
|
||||
|
||||
|
||||
class LLMBackend(Protocol):
|
||||
"""Minimal contract for an emailgen LLM provider."""
|
||||
"""Minimal contract for a realism LLM provider."""
|
||||
|
||||
model: str
|
||||
timeout: float
|
||||
@@ -1,17 +1,17 @@
|
||||
"""Backend dispatch.
|
||||
|
||||
Reads ``DECNET_EMAILGEN_LLM`` to pick a concrete :class:`LLMBackend`.
|
||||
Reads ``DECNET_REALISM_LLM`` to pick a concrete :class:`LLMBackend`.
|
||||
Defaults to ``ollama`` because that's what the prototype proved out and
|
||||
what most dev boxes have on hand.
|
||||
|
||||
Supported keys:
|
||||
|
||||
* ``ollama`` — :class:`decnet.orchestrator.emailgen.llm.impl.ollama.OllamaBackend`
|
||||
* ``fake`` — :class:`decnet.orchestrator.emailgen.llm.impl.fake.FakeBackend`
|
||||
* ``ollama`` — :class:`decnet.realism.llm.impl.ollama.OllamaBackend`
|
||||
* ``fake`` — :class:`decnet.realism.llm.impl.fake.FakeBackend`
|
||||
(canned output, used by tests so they don't shell out)
|
||||
|
||||
Anthropic / vLLM / llama.cpp slots in here as a third branch when the
|
||||
need shows up. Per the provider-subpackages memory, do NOT collapse
|
||||
need shows up. Per the provider-subpackages convention, do NOT collapse
|
||||
factory dispatch into the impl modules — keeps the ``__init__`` import
|
||||
graph cycle-free and the env contract auditable in one place.
|
||||
"""
|
||||
@@ -20,27 +20,27 @@ from __future__ import annotations
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
from decnet.orchestrator.emailgen.llm.base import LLMBackend
|
||||
from decnet.realism.llm.base import LLMBackend
|
||||
|
||||
|
||||
def get_llm(*, model: str | None = None, **kwargs: Any) -> LLMBackend:
|
||||
"""Instantiate the LLM backend selected by environment.
|
||||
|
||||
*model* (when provided) overrides whatever the backend's own default
|
||||
is — e.g. for OllamaBackend that's ``llama3.1`` unless
|
||||
``DECNET_EMAILGEN_MODEL`` says otherwise. Lets the worker honour
|
||||
``decnet emailgen run --model gpt-oss`` without each backend having
|
||||
is — e.g. for :class:`OllamaBackend` that's ``llama3.1`` unless
|
||||
``DECNET_REALISM_MODEL`` says otherwise. Lets the worker honour
|
||||
``decnet orchestrate --model gpt-oss`` without each backend having
|
||||
to know about CLI flags.
|
||||
"""
|
||||
backend_key = os.environ.get("DECNET_EMAILGEN_LLM", "ollama").lower()
|
||||
backend_key = os.environ.get("DECNET_REALISM_LLM", "ollama").lower()
|
||||
|
||||
if backend_key == "ollama":
|
||||
from decnet.orchestrator.emailgen.llm.impl.ollama import OllamaBackend
|
||||
from decnet.realism.llm.impl.ollama import OllamaBackend
|
||||
return OllamaBackend(model=model, **kwargs)
|
||||
if backend_key == "fake":
|
||||
from decnet.orchestrator.emailgen.llm.impl.fake import FakeBackend
|
||||
from decnet.realism.llm.impl.fake import FakeBackend
|
||||
return FakeBackend(model=model or "fake-model", **kwargs)
|
||||
raise ValueError(
|
||||
f"Unsupported DECNET_EMAILGEN_LLM={backend_key!r}; "
|
||||
f"Unsupported DECNET_REALISM_LLM={backend_key!r}; "
|
||||
"expected one of: ollama, fake"
|
||||
)
|
||||
6
decnet/realism/llm/impl/__init__.py
Normal file
6
decnet/realism/llm/impl/__init__.py
Normal file
@@ -0,0 +1,6 @@
|
||||
"""Concrete LLM-backend implementations.
|
||||
|
||||
Importers go through :func:`decnet.realism.llm.get_llm`, not these
|
||||
modules directly — same convention as :mod:`decnet.web.db.sqlite` and
|
||||
:mod:`decnet.bus.unix_client`.
|
||||
"""
|
||||
@@ -1,9 +1,9 @@
|
||||
"""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.
|
||||
Returns a canned string so the driver path can be exercised without an
|
||||
Ollama install. Configurable via ``DECNET_REALISM_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
|
||||
|
||||
@@ -11,7 +11,7 @@ import os
|
||||
import time
|
||||
from typing import Optional
|
||||
|
||||
from decnet.orchestrator.emailgen.llm.base import LLMBackend, LLMResult
|
||||
from decnet.realism.llm.base import LLMBackend, LLMResult
|
||||
|
||||
|
||||
_DEFAULT_OUTPUT = (
|
||||
@@ -34,7 +34,7 @@ class FakeBackend(LLMBackend):
|
||||
self._output = (
|
||||
output
|
||||
if output is not None
|
||||
else os.environ.get("DECNET_EMAILGEN_FAKE_OUTPUT", _DEFAULT_OUTPUT)
|
||||
else os.environ.get("DECNET_REALISM_FAKE_OUTPUT", _DEFAULT_OUTPUT)
|
||||
)
|
||||
self._success = success
|
||||
|
||||
@@ -1,9 +1,6 @@
|
||||
"""Ollama subprocess backend.
|
||||
|
||||
Shells out to ``ollama run <model>`` with the prompt fed via stdin.
|
||||
Mirrors what the original prototype at ``DECNET-EMAILs/main.py`` did,
|
||||
but lifted out of the driver so the rest of emailgen never imports a
|
||||
specific transport.
|
||||
|
||||
Why subprocess and not the Ollama HTTP API:
|
||||
* No new dependency (``ollama`` Python lib is optional).
|
||||
@@ -13,9 +10,9 @@ Why subprocess and not the Ollama HTTP API:
|
||||
to debug discrepancies between worker output and a console session.
|
||||
|
||||
Cost: per-call process spawn (~50ms on a warm box). Acceptable for
|
||||
emailgen's tick rate (one email every 5 minutes by default). When that
|
||||
cost matters, swap to an HTTP-API backend; the seam is in
|
||||
:mod:`decnet.orchestrator.emailgen.llm.factory`.
|
||||
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
|
||||
|
||||
@@ -25,17 +22,13 @@ import time
|
||||
from typing import Optional
|
||||
|
||||
from decnet.logging import get_logger
|
||||
from decnet.orchestrator.emailgen.llm.base import (
|
||||
LLMBackend,
|
||||
LLMResult,
|
||||
LLMTimeout,
|
||||
)
|
||||
from decnet.realism.llm.base import LLMBackend, LLMResult, LLMTimeout
|
||||
|
||||
log = get_logger("orchestrator.emailgen.llm")
|
||||
log = get_logger("realism.llm")
|
||||
|
||||
_OLLAMA = "ollama"
|
||||
_DEFAULT_MODEL = os.environ.get("DECNET_EMAILGEN_MODEL", "llama3.1")
|
||||
_DEFAULT_TIMEOUT = float(os.environ.get("DECNET_EMAILGEN_TIMEOUT", "60"))
|
||||
_DEFAULT_MODEL = os.environ.get("DECNET_REALISM_MODEL", "llama3.1")
|
||||
_DEFAULT_TIMEOUT = float(os.environ.get("DECNET_REALISM_TIMEOUT", "60"))
|
||||
|
||||
|
||||
class OllamaBackend(LLMBackend):
|
||||
@@ -1,9 +1,138 @@
|
||||
"""Persona schema — placeholder for stage 2.
|
||||
"""Persona schema for realism content generation.
|
||||
|
||||
In stage 2 of the realism migration, this module receives the real
|
||||
persona schema currently living at
|
||||
``decnet.orchestrator.emailgen.personas`` (``EmailPersona``,
|
||||
``parse_personas``, ``in_active_hours``). Stage 1 keeps it empty so
|
||||
the import path is reserved without behaviour.
|
||||
Stored as a JSON list on :attr:`Topology.email_personas`. Each persona
|
||||
describes one fictional employee — sender of email *and* author of
|
||||
files (notes, TODOs, drafts, scripts) on the deckies they're sampled
|
||||
onto. The schema deliberately stays narrow: the LLM gets *enough*
|
||||
differentiation to write distinct voices, no more.
|
||||
|
||||
The class is still named :class:`EmailPersona` because every persona
|
||||
in the pool today carries a mandatory email address (used for IMAP/
|
||||
POP3 spool delivery). Future per-decky personas without mailboxes
|
||||
would justify a rename / superclass; not in scope for the realism
|
||||
migration.
|
||||
|
||||
Invalid entries are dropped with a warning (returned alongside the
|
||||
parsed list) rather than raising — a single typo in one persona must
|
||||
not stall the entire realism tick.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Literal, Optional
|
||||
|
||||
from pydantic import BaseModel, Field, ValidationError, field_validator, model_validator
|
||||
|
||||
from decnet.logging import get_logger
|
||||
|
||||
logger = get_logger("realism.personas")
|
||||
|
||||
Tone = Literal["formal", "direct", "casual", "technical", "custom"]
|
||||
ReplyLatency = Literal["fast", "normal", "slow"]
|
||||
|
||||
|
||||
class EmailPersona(BaseModel):
|
||||
"""One fake mailbox owner.
|
||||
|
||||
``language`` is ISO 639-1 (``en``, ``es``, ``pt``…); when unset on the
|
||||
persona it falls back to the topology's ``language_default``.
|
||||
``uses_llms_heavily`` lifts the prompt-layer em-dash suppression for
|
||||
that persona — em-dashes are an LLM tell, but a persona explicitly
|
||||
pegged as a heavy LLM user should *naturally* produce them.
|
||||
"""
|
||||
name: str = Field(min_length=1, max_length=128)
|
||||
email: str = Field(min_length=3, max_length=255)
|
||||
role: str = Field(min_length=1, max_length=128)
|
||||
tone: Tone = "formal"
|
||||
tone_custom: Optional[str] = Field(default=None, max_length=128)
|
||||
mannerisms: list[str] = Field(default_factory=list, max_length=12)
|
||||
language: Optional[str] = Field(default=None, max_length=8)
|
||||
signature: Optional[str] = Field(default=None, max_length=512)
|
||||
active_hours: str = Field(default="09:00-18:00", max_length=32)
|
||||
reply_latency: ReplyLatency = "normal"
|
||||
uses_llms_heavily: bool = False
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _custom_tone_requires_text(self) -> "EmailPersona":
|
||||
# ``tone="custom"`` lets operators describe a voice the four canned
|
||||
# tones don't capture (sarcastic, deadpan, terse, etc.). The free
|
||||
# text is interpolated into the prompt verbatim, so an empty
|
||||
# value would just leave the LLM with the literal word "custom" —
|
||||
# reject it loudly instead of silently producing a useless prompt.
|
||||
if self.tone == "custom" and not (self.tone_custom and self.tone_custom.strip()):
|
||||
raise ValueError("tone_custom is required when tone is 'custom'")
|
||||
return self
|
||||
|
||||
@field_validator("email")
|
||||
@classmethod
|
||||
def _email_shape(cls, v: str) -> str:
|
||||
# Cheap structural check — full RFC 5322 isn't worth the
|
||||
# dependency. We only need ``user@domain`` with non-empty parts
|
||||
# for the prompt builder + Message-ID generator.
|
||||
if "@" not in v:
|
||||
raise ValueError("email must contain '@'")
|
||||
local, _, domain = v.rpartition("@")
|
||||
if not local or not domain or "." not in domain:
|
||||
raise ValueError("email must look like user@domain.tld")
|
||||
return v
|
||||
|
||||
|
||||
def parse_personas(
|
||||
raw: str | list | None,
|
||||
*,
|
||||
language_default: str = "en",
|
||||
) -> list[EmailPersona]:
|
||||
"""Parse the JSON-or-list ``email_personas`` value into models.
|
||||
|
||||
Resolves ``language`` against *language_default* so downstream
|
||||
consumers (prompt builder, scheduler) never need to know about
|
||||
fallback semantics.
|
||||
"""
|
||||
if not raw:
|
||||
return []
|
||||
if isinstance(raw, str):
|
||||
try:
|
||||
raw = json.loads(raw)
|
||||
except json.JSONDecodeError as exc:
|
||||
logger.warning("realism personas: invalid JSON, skipping: %s", exc)
|
||||
return []
|
||||
if not isinstance(raw, list):
|
||||
logger.warning(
|
||||
"realism personas: expected list, got %s", type(raw).__name__
|
||||
)
|
||||
return []
|
||||
out: list[EmailPersona] = []
|
||||
for i, entry in enumerate(raw):
|
||||
try:
|
||||
persona = EmailPersona.model_validate(entry)
|
||||
except ValidationError as exc:
|
||||
logger.warning(
|
||||
"realism personas: dropping invalid entry index=%d: %s",
|
||||
i, exc.errors(include_url=False),
|
||||
)
|
||||
continue
|
||||
if persona.language is None:
|
||||
persona = persona.model_copy(update={"language": language_default})
|
||||
out.append(persona)
|
||||
return out
|
||||
|
||||
|
||||
def in_active_hours(persona: EmailPersona, now_hour: int) -> bool:
|
||||
"""Return True if *now_hour* (0–23) falls in the persona's window.
|
||||
|
||||
Format: ``"HH:MM-HH:MM"``. Wrap-around windows (``"22:00-06:00"``)
|
||||
are supported. Invalid windows treat the persona as always-on so a
|
||||
config typo never silences the whole fleet.
|
||||
"""
|
||||
try:
|
||||
start_s, end_s = persona.active_hours.split("-")
|
||||
start_h = int(start_s.split(":")[0])
|
||||
end_h = int(end_s.split(":")[0])
|
||||
except (ValueError, IndexError):
|
||||
return True
|
||||
if start_h == end_h:
|
||||
return True
|
||||
if start_h < end_h:
|
||||
return start_h <= now_hour < end_h
|
||||
# Wrap-around (e.g. 22:00-06:00).
|
||||
return now_hour >= start_h or now_hour < end_h
|
||||
|
||||
@@ -1,34 +1,36 @@
|
||||
"""Global persona pool — non-topology mail deckies.
|
||||
"""Global persona pool — non-topology deckies.
|
||||
|
||||
DECNET runs in three deployment shapes that emit running deckies:
|
||||
|
||||
* **MazeNET topologies** — each topology owns its own
|
||||
:attr:`Topology.email_personas` JSON list; the scheduler walks back
|
||||
from the mail decky to its parent topology row.
|
||||
:attr:`Topology.email_personas` JSON list; consumers walk from the
|
||||
decky back to its parent topology row.
|
||||
* **Unihost fleet** — MACVLAN/IPVLAN deckies that have no
|
||||
parent topology row at all. They share one host-wide pool.
|
||||
* **SWARM shards** — DeckyShard rows on enrolled workers.
|
||||
Same shape as fleet for emailgen purposes (no parent topology row),
|
||||
Same shape as fleet for realism purposes (no parent topology row),
|
||||
so they read the same global pool.
|
||||
|
||||
This module owns the global pool: a JSON file on disk that operators
|
||||
populate via ``decnet emailgen import-personas <file>`` (or by editing
|
||||
populate via ``decnet realism import-personas <file>`` (or by editing
|
||||
the file directly). The file is loaded lazily on first read and
|
||||
re-loaded on mtime change so a CLI import takes effect for the running
|
||||
worker without a restart.
|
||||
|
||||
Path resolution order:
|
||||
|
||||
1. ``DECNET_EMAILGEN_PERSONAS`` environment variable — explicit override.
|
||||
1. ``DECNET_REALISM_PERSONAS`` environment variable — explicit override.
|
||||
2. ``/etc/decnet/email_personas.json`` — canonical master path; this is
|
||||
what ``decnet init`` will eventually own.
|
||||
what ``decnet init`` will eventually own. Filename retained
|
||||
(``email_personas.json``) because the on-disk schema hasn't changed
|
||||
and operators may already have committed copies.
|
||||
3. ``~/.decnet/email_personas.json`` — dev fallback so a developer can
|
||||
exercise the worker without root or ``decnet init``.
|
||||
exercise consumers without root or ``decnet init``.
|
||||
|
||||
When the file is missing / empty / unparseable, the pool is empty and
|
||||
the scheduler skips fleet/shard mail deckies the same way it skips a
|
||||
topology with too few personas. No silent fallback to dummy personas;
|
||||
silence is correct when there's no opinion to convey.
|
||||
consumers skip fleet/shard deckies the same way they skip a topology
|
||||
with too few personas. No silent fallback to dummy personas; silence
|
||||
is correct when there's no opinion to convey.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -38,11 +40,11 @@ from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
from decnet.logging import get_logger
|
||||
from decnet.orchestrator.emailgen.personas import EmailPersona, parse_personas
|
||||
from decnet.realism.personas import EmailPersona, parse_personas
|
||||
|
||||
logger = get_logger("orchestrator.emailgen")
|
||||
logger = get_logger("realism.personas_pool")
|
||||
|
||||
_ENV_VAR = "DECNET_EMAILGEN_PERSONAS"
|
||||
_ENV_VAR = "DECNET_REALISM_PERSONAS"
|
||||
_SYSTEM_PATH = Path("/etc/decnet/email_personas.json")
|
||||
|
||||
|
||||
@@ -54,13 +56,20 @@ def resolve_path() -> Path:
|
||||
"""Return the path the global pool would load from right now.
|
||||
|
||||
The file may not exist; callers are expected to handle that. The
|
||||
function is pure (no I/O) so the ``decnet emailgen import-personas``
|
||||
function is pure (no I/O) so the ``decnet realism import-personas``
|
||||
CLI can ask "where would I write to?" without touching the disk.
|
||||
"""
|
||||
override = os.environ.get(_ENV_VAR, "").strip()
|
||||
if override:
|
||||
return Path(override)
|
||||
if _SYSTEM_PATH.parent.exists() or _SYSTEM_PATH.exists():
|
||||
if _SYSTEM_PATH.exists():
|
||||
return _SYSTEM_PATH
|
||||
# ``/etc/decnet`` exists on a fully-provisioned host (post ``decnet
|
||||
# init``) but may be read-only for the API user on dev boxes — fall
|
||||
# back to the user path when the directory isn't writable so a fresh
|
||||
# PUT lands somewhere instead of erroring out. We only do this when
|
||||
# the system file doesn't exist yet; once it does, it's authoritative.
|
||||
if _SYSTEM_PATH.parent.exists() and os.access(_SYSTEM_PATH.parent, os.W_OK):
|
||||
return _SYSTEM_PATH
|
||||
return _user_path()
|
||||
|
||||
@@ -108,7 +117,7 @@ def load(*, language_default: str = "en") -> list[EmailPersona]:
|
||||
try:
|
||||
raw = path.read_text(encoding="utf-8")
|
||||
except OSError as exc:
|
||||
logger.warning("emailgen global pool: read failed path=%s: %s", path, exc)
|
||||
logger.warning("realism global pool: read failed path=%s: %s", path, exc)
|
||||
return []
|
||||
|
||||
parsed = parse_personas(raw, language_default=language_default)
|
||||
@@ -118,7 +127,7 @@ def load(*, language_default: str = "en") -> list[EmailPersona]:
|
||||
_cache_mtime = st.st_mtime
|
||||
if parsed:
|
||||
logger.info(
|
||||
"emailgen global pool: loaded %d personas from %s", len(parsed), path,
|
||||
"realism global pool: loaded %d personas from %s", len(parsed), path,
|
||||
)
|
||||
return parsed
|
||||
|
||||
@@ -1,7 +1,9 @@
|
||||
"""Prompt builders for LLM-enriched content.
|
||||
|
||||
Populated in stage 2 (``email.py`` lifted from
|
||||
``orchestrator.emailgen.prompt``) and stage 6 (``filebody.py``,
|
||||
``filename.py``, ``_style.py`` for em-dash suppression).
|
||||
* :mod:`decnet.realism.prompts.email` — corporate-email body builder.
|
||||
|
||||
Stage 6 of the realism migration adds ``filebody.py``, ``filename.py``,
|
||||
and a ``_style.py`` helper so em-dash suppression sits in one place
|
||||
across email + file-class prompts.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
"""Ollama prompt builder for emailgen.
|
||||
"""Prompt builder for the email content class.
|
||||
|
||||
The LLM gets a tightly-scoped instruction and a small handful of
|
||||
deterministic constraints. Persona mannerisms are *pre-selected* in
|
||||
@@ -9,7 +9,10 @@ ignore it, and the corpus collapses into one voice.
|
||||
**Em-dash suppression** is on by default; suppression is lifted only
|
||||
for personas that opt in via ``uses_llms_heavily``. Em-dashes are a
|
||||
strong stylometric tell for LLM-authored prose, and a honeypot mailbox
|
||||
where every author uses them is a tell.
|
||||
where every author uses them is a tell. Stage 6 of the realism
|
||||
migration extracts the suppression block into a shared
|
||||
``decnet.realism.prompts._style`` helper so file-class prompts pick
|
||||
it up too.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -17,7 +20,7 @@ import secrets
|
||||
from dataclasses import dataclass
|
||||
from typing import Optional
|
||||
|
||||
from decnet.orchestrator.emailgen.personas import EmailPersona
|
||||
from decnet.realism.personas import EmailPersona
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -128,7 +131,7 @@ def build(
|
||||
Persona — sender:
|
||||
- Name: {sender.name}
|
||||
- Role: {sender.role}
|
||||
- Tone: {sender.tone}
|
||||
- Tone: {sender.tone_custom if sender.tone == "custom" and sender.tone_custom else sender.tone}
|
||||
- Mannerisms (must show through):
|
||||
{mannerism_block}
|
||||
|
||||
@@ -113,7 +113,7 @@ api_router.include_router(orchestrator_events_router)
|
||||
|
||||
# Emailgen — global persona pool CRUD for the dashboard's
|
||||
# "Persona Generation" page. The worker reads from the same on-disk
|
||||
# JSON file directly (see decnet.orchestrator.emailgen.global_pool).
|
||||
# JSON file directly (see decnet.realism.personas_pool).
|
||||
api_router.include_router(emailgen_personas_router)
|
||||
|
||||
# Observability
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
"""GET/PUT ``/api/v1/emailgen/personas`` — global persona pool CRUD.
|
||||
|
||||
The "global pool" is a JSON file consumed by the emailgen worker for
|
||||
fleet (MACVLAN/IPVLAN) and SWARM-shard mail deckies — see
|
||||
:mod:`decnet.orchestrator.emailgen.global_pool`. MazeNET topology
|
||||
mail deckies use ``Topology.email_personas`` instead and are
|
||||
configured per-topology elsewhere.
|
||||
The "global pool" is a JSON file consumed by the realism content
|
||||
engine for fleet (MACVLAN/IPVLAN) and SWARM-shard deckies — see
|
||||
:mod:`decnet.realism.personas_pool`. MazeNET topology deckies use
|
||||
``Topology.email_personas`` instead and are configured per-topology
|
||||
elsewhere.
|
||||
|
||||
This endpoint is the API surface behind the dashboard's "Persona
|
||||
Generation" page. Reads accept admin or viewer; writes are admin-only
|
||||
@@ -22,8 +22,8 @@ from typing import Any
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
|
||||
from decnet.logging import get_logger
|
||||
from decnet.orchestrator.emailgen import global_pool
|
||||
from decnet.orchestrator.emailgen.personas import EmailPersona, parse_personas
|
||||
from decnet.realism import personas_pool as global_pool
|
||||
from decnet.realism.personas import EmailPersona, parse_personas
|
||||
from decnet.telemetry import traced as _traced
|
||||
from decnet.web.dependencies import require_admin, require_viewer
|
||||
from decnet.web.db.models.common import MessageResponse # noqa: F401 - response shape
|
||||
@@ -110,11 +110,28 @@ async def replace_personas(
|
||||
)
|
||||
|
||||
dest = global_pool.resolve_path()
|
||||
dest.parent.mkdir(parents=True, exist_ok=True)
|
||||
dest.write_text(
|
||||
json.dumps(_serialize(parsed), indent=2, ensure_ascii=False),
|
||||
encoding="utf-8",
|
||||
)
|
||||
try:
|
||||
dest.parent.mkdir(parents=True, exist_ok=True)
|
||||
dest.write_text(
|
||||
json.dumps(_serialize(parsed), indent=2, ensure_ascii=False),
|
||||
encoding="utf-8",
|
||||
)
|
||||
except OSError as exc:
|
||||
# Most common cause on dev boxes: ``/etc/decnet`` exists but is
|
||||
# not writable by the API process. Surface a 500 with the
|
||||
# actionable hint instead of leaking a traceback.
|
||||
log.warning(
|
||||
"api.emailgen.replace_personas write failed path=%s err=%s",
|
||||
dest, exc,
|
||||
)
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=(
|
||||
f"Could not write persona pool at {dest}: {exc.strerror or exc}. "
|
||||
f"Set DECNET_EMAILGEN_PERSONAS to a writable path "
|
||||
f"(e.g. ~/.decnet/email_personas.json) and restart the API."
|
||||
),
|
||||
) from exc
|
||||
global_pool.reset_cache()
|
||||
log.info(
|
||||
"api.emailgen.replace_personas user=%s wrote=%d path=%s",
|
||||
|
||||
@@ -21,6 +21,7 @@ from .api_get_topology import router as _get_router
|
||||
from .api_lan_crud import router as _lan_router
|
||||
from .api_list_topologies import router as _list_router
|
||||
from .api_mutations import router as _mutations_router
|
||||
from .api_personas import router as _personas_router
|
||||
from .api_reap_orphans import router as _reap_router
|
||||
from .api_teardown_topology import router as _teardown_router
|
||||
|
||||
@@ -44,6 +45,10 @@ topology_router.include_router(_decky_router)
|
||||
topology_router.include_router(_edge_router)
|
||||
topology_router.include_router(_mutations_router)
|
||||
topology_router.include_router(_events_router)
|
||||
# Personas use a literal-suffix path (`/{id}/personas`) — register
|
||||
# before the bare `/{id}` getter so FastAPI's trie sees the literal
|
||||
# segment first.
|
||||
topology_router.include_router(_personas_router)
|
||||
topology_router.include_router(_get_router)
|
||||
|
||||
|
||||
|
||||
131
decnet/web/router/topology/api_personas.py
Normal file
131
decnet/web/router/topology/api_personas.py
Normal file
@@ -0,0 +1,131 @@
|
||||
"""GET/PUT ``/topologies/{id}/personas`` — per-topology email persona pool.
|
||||
|
||||
The global pool (``decnet/web/router/emailgen/api_personas.py``) drives
|
||||
non-MazeNET fleet/SWARM-shard mail deckies. MazeNET topology mail
|
||||
deckies use ``Topology.email_personas`` instead — one JSON-serialized
|
||||
list per topology, parsed by the emailgen scheduler each tick.
|
||||
|
||||
This endpoint is the API surface behind the dashboard's per-topology
|
||||
"Personas" editor. Reads accept admin or viewer; writes are admin-only.
|
||||
|
||||
Concurrency: last-write-wins. The list is operator-curated and small
|
||||
(typically <20 entries); no need for optimistic versioning here.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
|
||||
from decnet.logging import get_logger
|
||||
from decnet.realism.personas import EmailPersona, parse_personas
|
||||
from decnet.telemetry import traced as _traced
|
||||
from decnet.web.dependencies import repo, require_admin, require_viewer
|
||||
|
||||
router = APIRouter()
|
||||
log = get_logger("api.topology.personas")
|
||||
|
||||
|
||||
def _serialize(personas: list[EmailPersona]) -> list[dict[str, Any]]:
|
||||
return [p.model_dump(exclude_none=False) for p in personas]
|
||||
|
||||
|
||||
@router.get(
|
||||
"/{topology_id}/personas",
|
||||
tags=["MazeNET Topologies"],
|
||||
responses={
|
||||
401: {"description": "Could not validate credentials"},
|
||||
403: {"description": "Insufficient permissions"},
|
||||
404: {"description": "Topology not found"},
|
||||
},
|
||||
)
|
||||
@_traced("api.topology.list_personas")
|
||||
async def list_topology_personas(
|
||||
topology_id: str,
|
||||
_viewer: dict = Depends(require_viewer),
|
||||
) -> dict[str, Any]:
|
||||
"""Return the topology's persona list and its language default.
|
||||
|
||||
``language_default`` is included so the editor can show which
|
||||
language unset entries fall back to — same fallback the scheduler
|
||||
applies when building prompts.
|
||||
"""
|
||||
topo = await repo.get_topology(topology_id)
|
||||
if topo is None:
|
||||
raise HTTPException(status_code=404, detail="Topology not found")
|
||||
language_default = topo.get("language_default") or "en"
|
||||
personas = parse_personas(
|
||||
topo.get("email_personas"), language_default=language_default,
|
||||
)
|
||||
return {
|
||||
"topology_id": topology_id,
|
||||
"topology_name": topo.get("name", ""),
|
||||
"language_default": language_default,
|
||||
"personas": _serialize(personas),
|
||||
}
|
||||
|
||||
|
||||
@router.put(
|
||||
"/{topology_id}/personas",
|
||||
tags=["MazeNET Topologies"],
|
||||
responses={
|
||||
400: {"description": "Invalid persona payload"},
|
||||
401: {"description": "Could not validate credentials"},
|
||||
403: {"description": "Insufficient permissions"},
|
||||
404: {"description": "Topology not found"},
|
||||
},
|
||||
)
|
||||
@_traced("api.topology.replace_personas")
|
||||
async def replace_topology_personas(
|
||||
topology_id: str,
|
||||
body: dict[str, Any],
|
||||
user: dict = Depends(require_admin),
|
||||
) -> dict[str, Any]:
|
||||
"""Replace the topology's persona list.
|
||||
|
||||
Body shape: ``{"personas": [<EmailPersona>, ...]}``.
|
||||
|
||||
Drop-invalid semantics mirror the global-pool endpoint: bad entries
|
||||
are skipped with a warning rather than failing the whole request, but
|
||||
a wholly invalid payload returns 400 so a schema mistake doesn't
|
||||
silently wipe the list.
|
||||
"""
|
||||
raw = body.get("personas")
|
||||
if not isinstance(raw, list):
|
||||
raise HTTPException(
|
||||
status_code=400, detail="body.personas must be a list",
|
||||
)
|
||||
|
||||
topo = await repo.get_topology(topology_id)
|
||||
if topo is None:
|
||||
raise HTTPException(status_code=404, detail="Topology not found")
|
||||
language_default = topo.get("language_default") or "en"
|
||||
|
||||
parsed = parse_personas(raw, language_default=language_default)
|
||||
if raw and not parsed:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=(
|
||||
"All persona entries failed validation. Required fields: "
|
||||
"name, email (user@host.tld), role, tone, mannerisms."
|
||||
),
|
||||
)
|
||||
|
||||
serialized = _serialize(parsed)
|
||||
payload = json.dumps(serialized, ensure_ascii=False)
|
||||
updated = await repo.set_topology_email_personas(topology_id, payload)
|
||||
if not updated:
|
||||
# Race: row vanished between the get and the update.
|
||||
raise HTTPException(status_code=404, detail="Topology not found")
|
||||
|
||||
log.info(
|
||||
"api.topology.replace_personas user=%s topology=%s wrote=%d",
|
||||
user.get("username", user.get("uuid")), topology_id, len(parsed),
|
||||
)
|
||||
return {
|
||||
"topology_id": topology_id,
|
||||
"topology_name": topo.get("name", ""),
|
||||
"language_default": language_default,
|
||||
"personas": serialized,
|
||||
}
|
||||
@@ -5,7 +5,7 @@ import json
|
||||
|
||||
import pytest
|
||||
|
||||
from decnet.orchestrator.emailgen import global_pool
|
||||
from decnet.realism import personas_pool as global_pool
|
||||
from decnet.web.router.emailgen.api_personas import (
|
||||
list_personas,
|
||||
replace_personas,
|
||||
@@ -40,7 +40,7 @@ _VALID = [
|
||||
@pytest.mark.asyncio
|
||||
async def test_list_returns_empty_when_no_pool(tmp_path, monkeypatch):
|
||||
monkeypatch.setenv(
|
||||
"DECNET_EMAILGEN_PERSONAS", str(tmp_path / "missing.json"),
|
||||
"DECNET_REALISM_PERSONAS", str(tmp_path / "missing.json"),
|
||||
)
|
||||
result = await list_personas(user={"uuid": "u", "role": "viewer"})
|
||||
assert result["personas"] == []
|
||||
@@ -51,7 +51,7 @@ async def test_list_returns_empty_when_no_pool(tmp_path, monkeypatch):
|
||||
async def test_list_returns_existing_pool(tmp_path, monkeypatch):
|
||||
pool = tmp_path / "pool.json"
|
||||
pool.write_text(json.dumps(_VALID))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(pool))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(pool))
|
||||
|
||||
result = await list_personas(user={"uuid": "u", "role": "viewer"})
|
||||
assert len(result["personas"]) == 2
|
||||
@@ -63,7 +63,7 @@ async def test_list_returns_existing_pool(tmp_path, monkeypatch):
|
||||
@pytest.mark.asyncio
|
||||
async def test_replace_writes_canonical_file(tmp_path, monkeypatch):
|
||||
dest = tmp_path / "pool.json"
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(dest))
|
||||
|
||||
result = await replace_personas(
|
||||
body={"personas": _VALID},
|
||||
@@ -83,7 +83,7 @@ async def test_replace_with_empty_list_clears_pool(tmp_path, monkeypatch):
|
||||
valid and means "no fleet personas, skip fleet mail deckies"."""
|
||||
dest = tmp_path / "pool.json"
|
||||
dest.write_text(json.dumps(_VALID))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(dest))
|
||||
|
||||
result = await replace_personas(
|
||||
body={"personas": []},
|
||||
@@ -98,7 +98,7 @@ async def test_replace_rejects_non_list_payload(tmp_path, monkeypatch):
|
||||
from fastapi import HTTPException
|
||||
|
||||
monkeypatch.setenv(
|
||||
"DECNET_EMAILGEN_PERSONAS", str(tmp_path / "pool.json"),
|
||||
"DECNET_REALISM_PERSONAS", str(tmp_path / "pool.json"),
|
||||
)
|
||||
with pytest.raises(HTTPException) as exc:
|
||||
await replace_personas(
|
||||
@@ -116,7 +116,7 @@ async def test_replace_rejects_all_invalid_payload(tmp_path, monkeypatch):
|
||||
from fastapi import HTTPException
|
||||
|
||||
monkeypatch.setenv(
|
||||
"DECNET_EMAILGEN_PERSONAS", str(tmp_path / "pool.json"),
|
||||
"DECNET_REALISM_PERSONAS", str(tmp_path / "pool.json"),
|
||||
)
|
||||
with pytest.raises(HTTPException) as exc:
|
||||
await replace_personas(
|
||||
@@ -132,7 +132,7 @@ async def test_replace_drops_partially_invalid_entries(tmp_path, monkeypatch):
|
||||
"""One bad apple doesn't kill the request — invalid entries get
|
||||
dropped, valid ones land, response shows what stuck."""
|
||||
dest = tmp_path / "pool.json"
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(dest))
|
||||
|
||||
result = await replace_personas(
|
||||
body={"personas": [
|
||||
@@ -153,7 +153,7 @@ async def test_get_then_put_round_trips_through_pool(tmp_path, monkeypatch):
|
||||
"""The worker reads the same file the API writes — verify the
|
||||
write-then-read cycle leaves the pool in the expected state."""
|
||||
dest = tmp_path / "pool.json"
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(dest))
|
||||
|
||||
await replace_personas(
|
||||
body={"personas": _VALID},
|
||||
|
||||
@@ -7,7 +7,7 @@ import pytest
|
||||
from typer.testing import CliRunner
|
||||
|
||||
from decnet.cli import app
|
||||
from decnet.orchestrator.emailgen import global_pool
|
||||
from decnet.realism import personas_pool as global_pool
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
@@ -39,7 +39,7 @@ def test_import_personas_writes_canonical_file(tmp_path, monkeypatch):
|
||||
src = tmp_path / "src.json"
|
||||
src.write_text(json.dumps(_TWO))
|
||||
dest = tmp_path / "global_pool.json"
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(dest))
|
||||
|
||||
result = CliRunner().invoke(
|
||||
app, ["emailgen", "import-personas", str(src)]
|
||||
@@ -55,7 +55,7 @@ def test_import_personas_explicit_output_overrides_env(tmp_path, monkeypatch):
|
||||
src.write_text(json.dumps(_TWO))
|
||||
env_dest = tmp_path / "env.json"
|
||||
explicit = tmp_path / "explicit.json"
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(env_dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(env_dest))
|
||||
|
||||
result = CliRunner().invoke(
|
||||
app,
|
||||
@@ -79,7 +79,7 @@ def test_import_personas_rejects_invalid_json(tmp_path):
|
||||
def test_import_personas_rejects_non_list(tmp_path, monkeypatch):
|
||||
src = tmp_path / "src.json"
|
||||
src.write_text(json.dumps({"not": "a list"}))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(tmp_path / "out.json"))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(tmp_path / "out.json"))
|
||||
result = CliRunner().invoke(
|
||||
app, ["emailgen", "import-personas", str(src)]
|
||||
)
|
||||
@@ -92,7 +92,7 @@ def test_import_personas_rejects_all_invalid_entries(tmp_path, monkeypatch):
|
||||
src.write_text(json.dumps([
|
||||
{"name": "broken", "email": "no-at-symbol"},
|
||||
]))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(tmp_path / "out.json"))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(tmp_path / "out.json"))
|
||||
result = CliRunner().invoke(
|
||||
app, ["emailgen", "import-personas", str(src)]
|
||||
)
|
||||
@@ -104,7 +104,7 @@ def test_import_personas_warns_on_single_persona(tmp_path, monkeypatch):
|
||||
src = tmp_path / "src.json"
|
||||
src.write_text(json.dumps(_TWO[:1]))
|
||||
dest = tmp_path / "out.json"
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(dest))
|
||||
result = CliRunner().invoke(
|
||||
app, ["emailgen", "import-personas", str(src)]
|
||||
)
|
||||
@@ -117,7 +117,7 @@ def test_imported_personas_load_via_global_pool(tmp_path, monkeypatch):
|
||||
src = tmp_path / "src.json"
|
||||
src.write_text(json.dumps(_TWO))
|
||||
dest = tmp_path / "out.json"
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(dest))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(dest))
|
||||
|
||||
result = CliRunner().invoke(
|
||||
app, ["emailgen", "import-personas", str(src)]
|
||||
|
||||
@@ -5,10 +5,10 @@ from __future__ import annotations
|
||||
import pytest
|
||||
|
||||
from decnet.orchestrator.drivers import email as email_driver
|
||||
from decnet.orchestrator.emailgen.llm.base import LLMResult, LLMTimeout
|
||||
from decnet.orchestrator.emailgen.llm.impl.fake import FakeBackend
|
||||
from decnet.orchestrator.emailgen.personas import EmailPersona
|
||||
from decnet.orchestrator.emailgen.scheduler import EmailAction
|
||||
from decnet.realism.llm.base import LLMResult, LLMTimeout
|
||||
from decnet.realism.llm.impl.fake import FakeBackend
|
||||
from decnet.realism.personas import EmailPersona
|
||||
|
||||
|
||||
class _RaisingBackend:
|
||||
|
||||
@@ -4,7 +4,7 @@ from __future__ import annotations
|
||||
from decnet.bus import topics as _topics
|
||||
from decnet.orchestrator.drivers.base import ActivityResult
|
||||
from decnet.orchestrator.emailgen import events
|
||||
from decnet.orchestrator.emailgen.personas import EmailPersona
|
||||
from decnet.realism.personas import EmailPersona
|
||||
from decnet.orchestrator.emailgen.scheduler import EmailAction
|
||||
|
||||
|
||||
|
||||
@@ -7,7 +7,8 @@ from typing import Any
|
||||
|
||||
import pytest
|
||||
|
||||
from decnet.orchestrator.emailgen import global_pool, scheduler
|
||||
from decnet.orchestrator.emailgen import scheduler
|
||||
from decnet.realism import personas_pool as global_pool
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
@@ -147,7 +148,7 @@ async def test_pick_for_fleet_source_uses_global_pool(tmp_path, monkeypatch):
|
||||
personas come from the host-wide JSON file."""
|
||||
pool_file = tmp_path / "personas.json"
|
||||
pool_file.write_text(json.dumps(_PERSONAS_TWO))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(pool_file))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(pool_file))
|
||||
|
||||
repo = _FakeRepo(
|
||||
deckies=[_decky(source="fleet", topology_id=None)],
|
||||
@@ -163,7 +164,7 @@ async def test_pick_for_shard_source_uses_global_pool(tmp_path, monkeypatch):
|
||||
"""SWARM shards are non-topology too — same path as fleet."""
|
||||
pool_file = tmp_path / "personas.json"
|
||||
pool_file.write_text(json.dumps(_PERSONAS_TWO))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(pool_file))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(pool_file))
|
||||
|
||||
repo = _FakeRepo(
|
||||
deckies=[_decky(source="shard", topology_id=None)],
|
||||
@@ -174,7 +175,7 @@ async def test_pick_for_shard_source_uses_global_pool(tmp_path, monkeypatch):
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_pick_fleet_with_empty_global_pool_returns_none(tmp_path, monkeypatch):
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(tmp_path / "missing.json"))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(tmp_path / "missing.json"))
|
||||
repo = _FakeRepo(deckies=[_decky(source="fleet", topology_id=None)])
|
||||
assert await scheduler.pick(repo, now=datetime(2026, 4, 26, 12, 0, 0)) is None
|
||||
|
||||
@@ -191,7 +192,7 @@ async def test_topology_personas_isolated_from_global_pool(tmp_path, monkeypatch
|
||||
"tone": "casual",
|
||||
"mannerisms": [],
|
||||
}]))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(pool_file))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(pool_file))
|
||||
|
||||
repo = _FakeRepo(
|
||||
deckies=[_decky()],
|
||||
|
||||
@@ -10,8 +10,8 @@ import pytest_asyncio
|
||||
from decnet.bus.fake import FakeBus
|
||||
from decnet.orchestrator.drivers import email as email_driver
|
||||
from decnet.orchestrator.emailgen import worker as eg_worker
|
||||
from decnet.orchestrator.emailgen.llm.impl.fake import FakeBackend
|
||||
from decnet.orchestrator.emailgen.scheduler import EmailAction # noqa: F401
|
||||
from decnet.realism.llm.impl.fake import FakeBackend
|
||||
from decnet.web.db.models import Topology, TopologyDecky
|
||||
from decnet.web.db.sqlite.repository import SQLiteRepository
|
||||
|
||||
|
||||
@@ -58,7 +58,7 @@ def test_in_work_hours_equal_start_end_means_always_on() -> None:
|
||||
)
|
||||
def test_malformed_window_fails_open(garbage: str) -> None:
|
||||
# The fleet must not silence on a typo — same fail-open semantics
|
||||
# as decnet.orchestrator.emailgen.personas.in_active_hours.
|
||||
# as decnet.realism.personas.in_active_hours.
|
||||
assert in_work_hours(garbage, _NOW) is True
|
||||
|
||||
|
||||
|
||||
@@ -4,8 +4,8 @@ from __future__ import annotations
|
||||
|
||||
import random
|
||||
|
||||
from decnet.orchestrator.emailgen.personas import EmailPersona
|
||||
from decnet.orchestrator.emailgen.prompt import (
|
||||
from decnet.realism.personas import EmailPersona
|
||||
from decnet.realism.prompts.email import (
|
||||
PromptInputs,
|
||||
build,
|
||||
select_mannerisms,
|
||||
@@ -5,34 +5,34 @@ import asyncio
|
||||
|
||||
import pytest
|
||||
|
||||
from decnet.orchestrator.emailgen.llm import LLMTimeout, get_llm
|
||||
from decnet.orchestrator.emailgen.llm.impl.fake import FakeBackend
|
||||
from decnet.orchestrator.emailgen.llm.impl.ollama import OllamaBackend
|
||||
from decnet.realism.llm import LLMTimeout, get_llm
|
||||
from decnet.realism.llm.impl.fake import FakeBackend
|
||||
from decnet.realism.llm.impl.ollama import OllamaBackend
|
||||
|
||||
|
||||
# ── factory dispatch ─────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
def test_factory_default_is_ollama(monkeypatch):
|
||||
monkeypatch.delenv("DECNET_EMAILGEN_LLM", raising=False)
|
||||
monkeypatch.delenv("DECNET_REALISM_LLM", raising=False)
|
||||
backend = get_llm()
|
||||
assert isinstance(backend, OllamaBackend)
|
||||
|
||||
|
||||
def test_factory_selects_fake(monkeypatch):
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_LLM", "fake")
|
||||
monkeypatch.setenv("DECNET_REALISM_LLM", "fake")
|
||||
backend = get_llm()
|
||||
assert isinstance(backend, FakeBackend)
|
||||
|
||||
|
||||
def test_factory_unknown_raises(monkeypatch):
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_LLM", "vllm-someday")
|
||||
monkeypatch.setenv("DECNET_REALISM_LLM", "vllm-someday")
|
||||
with pytest.raises(ValueError, match="Unsupported"):
|
||||
get_llm()
|
||||
|
||||
|
||||
def test_factory_passes_model_through(monkeypatch):
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_LLM", "ollama")
|
||||
monkeypatch.setenv("DECNET_REALISM_LLM", "ollama")
|
||||
backend = get_llm(model="qwen2:7b")
|
||||
assert backend.model == "qwen2:7b"
|
||||
|
||||
@@ -3,7 +3,7 @@ from __future__ import annotations
|
||||
|
||||
import json
|
||||
|
||||
from decnet.orchestrator.emailgen.personas import (
|
||||
from decnet.realism.personas import (
|
||||
EmailPersona,
|
||||
in_active_hours,
|
||||
parse_personas,
|
||||
@@ -5,7 +5,7 @@ import json
|
||||
|
||||
import pytest
|
||||
|
||||
from decnet.orchestrator.emailgen import global_pool
|
||||
from decnet.realism import personas_pool as global_pool
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
@@ -35,7 +35,7 @@ _TWO = [
|
||||
|
||||
def test_load_returns_empty_when_file_missing(tmp_path, monkeypatch):
|
||||
monkeypatch.setenv(
|
||||
"DECNET_EMAILGEN_PERSONAS", str(tmp_path / "does-not-exist.json")
|
||||
"DECNET_REALISM_PERSONAS", str(tmp_path / "does-not-exist.json")
|
||||
)
|
||||
assert global_pool.load() == []
|
||||
|
||||
@@ -43,7 +43,7 @@ def test_load_returns_empty_when_file_missing(tmp_path, monkeypatch):
|
||||
def test_load_returns_parsed_personas(tmp_path, monkeypatch):
|
||||
f = tmp_path / "personas.json"
|
||||
f.write_text(json.dumps(_TWO))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(f))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(f))
|
||||
personas = global_pool.load()
|
||||
assert len(personas) == 2
|
||||
assert {p.email for p in personas} == {"john@corp.com", "sarah@corp.com"}
|
||||
@@ -52,7 +52,7 @@ def test_load_returns_parsed_personas(tmp_path, monkeypatch):
|
||||
def test_load_resolves_language_default(tmp_path, monkeypatch):
|
||||
f = tmp_path / "personas.json"
|
||||
f.write_text(json.dumps(_TWO))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(f))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(f))
|
||||
personas = global_pool.load(language_default="es")
|
||||
assert all(p.language == "es" for p in personas)
|
||||
|
||||
@@ -60,14 +60,14 @@ def test_load_resolves_language_default(tmp_path, monkeypatch):
|
||||
def test_load_invalid_json_returns_empty(tmp_path, monkeypatch):
|
||||
f = tmp_path / "personas.json"
|
||||
f.write_text("{not valid")
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(f))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(f))
|
||||
assert global_pool.load() == []
|
||||
|
||||
|
||||
def test_load_caches_until_mtime_changes(tmp_path, monkeypatch):
|
||||
f = tmp_path / "personas.json"
|
||||
f.write_text(json.dumps(_TWO))
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(f))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(f))
|
||||
|
||||
first = global_pool.load()
|
||||
assert len(first) == 2
|
||||
@@ -84,12 +84,12 @@ def test_load_caches_until_mtime_changes(tmp_path, monkeypatch):
|
||||
|
||||
|
||||
def test_resolve_path_honours_env_override(tmp_path, monkeypatch):
|
||||
monkeypatch.setenv("DECNET_EMAILGEN_PERSONAS", str(tmp_path / "x.json"))
|
||||
monkeypatch.setenv("DECNET_REALISM_PERSONAS", str(tmp_path / "x.json"))
|
||||
assert global_pool.resolve_path() == tmp_path / "x.json"
|
||||
|
||||
|
||||
def test_resolve_path_falls_back_to_user_path_when_system_missing(monkeypatch):
|
||||
monkeypatch.delenv("DECNET_EMAILGEN_PERSONAS", raising=False)
|
||||
monkeypatch.delenv("DECNET_REALISM_PERSONAS", raising=False)
|
||||
# In a typical dev box /etc/decnet/ doesn't exist; the resolver
|
||||
# should pick ~/.decnet/email_personas.json.
|
||||
p = global_pool.resolve_path()
|
||||
Reference in New Issue
Block a user