The boilerplate's rule: the deploy kit's Dockerfile, the APP_CONFIG, APP_PASSWORD and APP_DATA variables and its commands all assume a package called app, so a project renames its display title and nothing else. The console script is `app`, and the launch entry runs `uv run app serve --port 8790`. The domain noun stays `role`. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
101 lines
3.5 KiB
Python
101 lines
3.5 KiB
Python
"""Config loading: one YAML file, `roles.yaml`, validated into a model.
|
|
|
|
A typo in a key is an error naming the key, because `Section` forbids extras.
|
|
`sources` stays a dict: one block per plugin, whose keys only the plugin knows.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import yaml
|
|
from pydantic import Field, ValidationError
|
|
|
|
from desk.config import AgentConfig, ModelTaskConfig, Section, WorkersConfig
|
|
from app.models import Gate, Weights
|
|
|
|
DEFAULT_PATH = Path(os.environ.get("ROLEDESK_CONFIG", "roles.yaml"))
|
|
|
|
|
|
class ExtractConfig(ModelTaskConfig):
|
|
"""Turning a posting's title and text into the gate columns. See
|
|
app/jobs/extract.py. Off by default, so nobody is billed by surprise:
|
|
on the API backend every batch is a paid call."""
|
|
|
|
enabled: bool = False
|
|
model: str = "claude-haiku-4-5-20251001"
|
|
batch_size: int = Field(20, ge=1)
|
|
|
|
|
|
class EmbedConfig(Section):
|
|
"""Turning a role into a vector for `fit`. Needs sentence-transformers;
|
|
without it `embed` says so and does nothing, and `score` leaves fit out.
|
|
See app/jobs/embed.py."""
|
|
|
|
#: Recorded on every vector. Changing it drops the old vectors, which are
|
|
#: a different geometry and never comparable.
|
|
model: str = "sentence-transformers/all-MiniLM-L6-v2"
|
|
#: Roles embedded per run at most, newest first.
|
|
per_run: int = Field(50_000, ge=1)
|
|
|
|
|
|
class AgentSeed(Section):
|
|
"""A search agent as `roles.yaml` lists it. Imported into an empty
|
|
`agents` table once; after that the table is the answer."""
|
|
|
|
name: str
|
|
intent: str = ""
|
|
gates: list[Gate] = Field(default_factory=list)
|
|
weights: Weights = Field(default_factory=Weights)
|
|
enabled: bool = True
|
|
|
|
|
|
class Config(Section):
|
|
"""The whole file."""
|
|
|
|
database: str = "roledesk.db"
|
|
plugin_paths: list[str] = Field(default_factory=lambda: ["plugins"])
|
|
workers: WorkersConfig = Field(default_factory=WorkersConfig)
|
|
agent: AgentConfig = Field(default_factory=AgentConfig)
|
|
extract: ExtractConfig = Field(default_factory=ExtractConfig)
|
|
embed: EmbedConfig = Field(default_factory=EmbedConfig)
|
|
#: Starter agents, imported once into an empty table.
|
|
agents: list[AgentSeed] = Field(default_factory=list)
|
|
#: One block per plugin: `enabled`, and whatever that plugin reads.
|
|
sources: dict[str, Any] = Field(default_factory=dict)
|
|
#: Where this was loaded from. Never written back into the file.
|
|
path: str = Field("", exclude=True)
|
|
|
|
|
|
class ConfigError(FileNotFoundError):
|
|
"""A config that exists but does not validate. A FileNotFoundError so the
|
|
CLI reports both kinds of unusable config the same way: as a message."""
|
|
|
|
|
|
def load(path: str | Path | None = None) -> Config:
|
|
p = Path(path or DEFAULT_PATH).expanduser()
|
|
if not p.exists():
|
|
raise FileNotFoundError(
|
|
f"No config at {p}. Copy config.example.yaml to {p} and edit it.")
|
|
with p.open(encoding="utf-8") as fh:
|
|
raw = yaml.safe_load(fh) or {}
|
|
try:
|
|
config = Config(**raw, path=str(p))
|
|
except ValidationError as exc:
|
|
raise ConfigError(f"{p}:\n{_explain(exc)}") from None
|
|
config.agent.credentials_database = config.database
|
|
return config
|
|
|
|
|
|
def _explain(exc: ValidationError) -> str:
|
|
lines = []
|
|
for err in exc.errors():
|
|
where = ".".join(str(p) for p in err["loc"]) or "(top level)"
|
|
detail = err["msg"]
|
|
if err["type"] == "extra_forbidden":
|
|
detail = "unknown setting, check the spelling against config.example.yaml"
|
|
lines.append(f" {where}: {detail}")
|
|
return "\n".join(lines)
|