feat(config): add typed resource schema

This commit is contained in:
2026-07-11 20:43:08 +02:00
parent fe8d70da47
commit 1e0911bb6a
5 changed files with 380 additions and 45 deletions
+105
View File
@@ -0,0 +1,105 @@
import json
import pytest
from typer.testing import CliRunner
from tht.cli import app
from tht.config import load_config
def _write_old_workspace(tmp_path):
path = tmp_path / "old.yaml"
path.write_text(
"""
database:
host: ignored-for-rest
database: analytics
schema: mart
user: legacy-user
password: legacy-password
transport: rest
rest:
base_url: https://dwh.example.test/
api_key: dwh-reader
vector_db:
host: vector-db
database: postgres
schema: vectors
user: vector-user
password: vector-password
vector_rest:
base_url: https://vectors.example.test/
api_key: vector-reader
vector_write_rest:
base_url: https://vectors.example.test/
api_key: vector-writer
paths:
artifacts: build/artifacts
indexes: build/indexes
sessions: build/sessions
"""
)
return path
def _write_new_workspace(tmp_path):
path = tmp_path / "new.yaml"
path.write_text(
"""
dwh:
type: thoth_rest
database:
database: analytics
schema: mart
endpoint:
base_url: https://dwh.example.test/
api_key: dwh-reader
vectors:
type: thoth_vector_http
reader:
base_url: https://vectors.example.test/
api_key: vector-reader
writer:
base_url: https://vectors.example.test/
api_key: vector-writer
direct:
host: vector-db
database: postgres
schema: vectors
user: vector-user
password: vector-password
roots:
artifacts: build/artifacts
indexes: build/indexes
sessions: build/sessions
"""
)
return path
def test_legacy_rest_workspace_equals_new_resource_schema(tmp_path, capsys):
with pytest.warns(FutureWarning, match="DEPRECATION") as warnings:
old = load_config(_write_old_workspace(tmp_path))
captured = capsys.readouterr()
new = load_config(_write_new_workspace(tmp_path))
assert old.dwh.model_dump() == new.dwh.model_dump()
assert old.vectors.model_dump() == new.vectors.model_dump()
assert old.roots.model_dump() == new.roots.model_dump()
assert captured.out == ""
assert captured.err == ""
assert len(warnings) == 1
def test_legacy_warning_does_not_contaminate_cli_json(tmp_path):
with pytest.warns(FutureWarning, match="DEPRECATION") as warnings:
result = CliRunner().invoke(
app,
["session", "list", "--json", "-c", str(_write_old_workspace(tmp_path))],
)
assert result.exit_code == 0
json.loads(result.stdout)
assert "DEPRECATION" not in result.stdout
assert result.stderr == ""
assert len(warnings) == 1
+71
View File
@@ -0,0 +1,71 @@
from tht.config import (
PgvectorDirectConfig,
PostgresDwhConfig,
ThothRestDwhConfig,
ThothVectorHttpConfig,
load_config,
)
def test_loads_discriminated_dwh_and_vector_resources(tmp_path):
workspace = tmp_path / "workspace.yaml"
workspace.write_text(
"""
dwh:
type: thoth_rest
database:
database: analytics
schema: mart
endpoint:
base_url: https://dwh.example.test/
api_key: dwh-reader
vectors:
type: thoth_vector_http
reader:
base_url: https://vectors.example.test/
api_key: vector-reader
writer:
base_url: https://vectors.example.test/
api_key: vector-writer
roots:
artifacts: build/artifacts
indexes: build/indexes
sessions: build/sessions
"""
)
cfg = load_config(workspace)
assert isinstance(cfg.dwh, ThothRestDwhConfig)
assert cfg.dwh.database.db_schema == "mart"
assert isinstance(cfg.vectors, ThothVectorHttpConfig)
assert cfg.vectors.writer.api_key == "vector-writer"
assert cfg.roots.sessions.as_posix() == "build/sessions"
def test_loads_direct_discriminated_resources(tmp_path):
workspace = tmp_path / "workspace.yaml"
workspace.write_text(
"""
dwh:
type: postgres_direct
connection: &database
host: db
database: analytics
schema: mart
user: reader
password: secret
vectors:
type: pgvector_direct
connection:
<<: *database
schema: vectors
"""
)
cfg = load_config(workspace)
assert isinstance(cfg.dwh, PostgresDwhConfig)
assert cfg.database.transport == "direct"
assert isinstance(cfg.vectors, PgvectorDirectConfig)
assert cfg.vector_db.db_schema == "vectors"
+102 -3
View File
@@ -1,10 +1,13 @@
import os
import re
import warnings
from pathlib import Path
from typing import Any, Literal
from typing import Annotated, Any, Literal
import yaml
from pydantic import BaseModel, Field, ValidationError
from pydantic import BaseModel, Field, model_validator, ValidationError
from tht.config_compat import translate_legacy_config
_ENV_RE = re.compile(r"\$\{([A-Za-z_][A-Za-z0-9_]*)\}")
@@ -56,12 +59,59 @@ class RestConfig(BaseModel):
ssl_ca: str | None = None # path al certificato CA (per server con CA interna)
class DatabaseIdentityConfig(BaseModel):
database: str
db_schema: str = Field(alias="schema")
model_config = {"populate_by_name": True}
class PostgresDwhConfig(BaseModel):
type: Literal["postgres_direct"]
connection: DatabaseConfig
class ThothRestDwhConfig(BaseModel):
type: Literal["thoth_rest"]
database: DatabaseIdentityConfig
endpoint: RestConfig
DwhResourceConfig = Annotated[
PostgresDwhConfig | ThothRestDwhConfig,
Field(discriminator="type"),
]
class PgvectorDirectConfig(BaseModel):
type: Literal["pgvector_direct"]
connection: DatabaseConfig
class ThothVectorHttpConfig(BaseModel):
type: Literal["thoth_vector_http"]
reader: RestConfig | None = None
writer: RestConfig | None = None
# Transitional direct loading path used by the server profile.
direct: DatabaseConfig | None = None
VectorResourceConfig = Annotated[
PgvectorDirectConfig | ThothVectorHttpConfig,
Field(discriminator="type"),
]
class PathsConfig(BaseModel):
artifacts: Path = Path("artifacts")
indexes: Path = Path("indexes")
sessions: Path = Path("sessions")
class WorkspaceRoots(PathsConfig):
pass
class ExamplesConfig(BaseModel):
max_per_column: int = 10
@@ -138,6 +188,10 @@ class ExecutionConfig(BaseModel):
class Config(BaseModel):
dwh: DwhResourceConfig
vectors: VectorResourceConfig | None = None
roots: WorkspaceRoots = WorkspaceRoots()
# Compatibility views retained until all call sites consume typed resources.
database: DatabaseConfig
# Profilo dell'installazione, letto da THT_PROFILE (.env), non dallo yaml versionato.
# server: ricostruisce i derivati (artefatti, LSH, vettori schema nel vectordb).
@@ -166,6 +220,15 @@ class Config(BaseModel):
# una API key separata dalla lettura; espone solo upsert/hash via RPC allowlist.
vector_write_rest: RestConfig | None = None
@model_validator(mode="before")
@classmethod
def accept_legacy_constructor_fields(cls, value: Any) -> Any:
if not isinstance(value, dict) or "dwh" in value:
return value
translated, _ = translate_legacy_config(value)
_populate_legacy_views(translated)
return translated
def load_config(path: Path) -> Config:
if not path.exists():
@@ -173,8 +236,11 @@ def load_config(path: Path) -> Config:
raw = yaml.safe_load(path.read_text())
if not isinstance(raw, dict):
raise ConfigError(f"Configurazione non valida (atteso un mapping YAML): {path}")
expanded = _expand_env(raw)
translated, used_legacy = translate_legacy_config(expanded)
_populate_legacy_views(translated)
try:
cfg = Config.model_validate(_expand_env(raw))
cfg = Config.model_validate(translated)
except ValidationError as e:
raise ConfigError(f"Configurazione non valida in {path}:\n{e}") from e
env_profile = os.environ.get("THT_PROFILE")
@@ -188,4 +254,37 @@ def load_config(path: Path) -> Config:
raise ConfigError(
f"transport: rest richiede la sezione `rest` (base_url, api_key) in {path}."
)
if used_legacy:
warnings.warn(
"DEPRECATION: legacy workspace resource keys are deprecated; "
"use dwh, vectors, and roots.",
FutureWarning,
stacklevel=2,
)
return cfg
def _populate_legacy_views(raw: dict[str, Any]) -> None:
"""Populate old Config attributes for command compatibility during migration."""
dwh = raw.get("dwh")
if "database" not in raw and isinstance(dwh, dict):
if dwh.get("type") == "postgres_direct":
raw["database"] = {**dwh["connection"], "transport": "direct"}
elif dwh.get("type") == "thoth_rest":
raw["database"] = {
**dwh["database"],
"user": "rest",
"password": "",
"transport": "rest",
}
raw["rest"] = dwh["endpoint"]
vectors = raw.get("vectors")
if isinstance(vectors, dict):
if vectors.get("type") == "pgvector_direct":
raw.setdefault("vector_db", vectors["connection"])
elif vectors.get("type") == "thoth_vector_http":
raw.setdefault("vector_rest", vectors.get("reader"))
raw.setdefault("vector_write_rest", vectors.get("writer"))
raw.setdefault("vector_db", vectors.get("direct"))
raw.setdefault("paths", raw.get("roots", {}))
+74
View File
@@ -0,0 +1,74 @@
from __future__ import annotations
from copy import deepcopy
from typing import Any
_LEGACY_RESOURCE_KEYS = {
"database",
"rest",
"vector_db",
"vector_rest",
"vector_write_rest",
"paths",
}
def _as_mapping(value: Any) -> dict[str, Any] | None:
if isinstance(value, dict):
return deepcopy(value)
model_dump = getattr(value, "model_dump", None)
if callable(model_dump):
return model_dump(by_alias=True)
return None
def translate_legacy_config(raw: dict[str, Any]) -> tuple[dict[str, Any], bool]:
"""Translate the legacy flat resource keys without validating their contents."""
translated = deepcopy(raw)
legacy = any(key in raw for key in _LEGACY_RESOURCE_KEYS)
if not legacy:
return translated, False
database = _as_mapping(raw.get("database"))
rest = raw.get("rest")
if "dwh" not in translated and database is not None:
if database.get("transport", "direct") == "rest":
identity = {
key: database[key]
for key in ("database", "schema")
if key in database
}
translated["dwh"] = {
"type": "thoth_rest",
"database": identity,
"endpoint": rest,
}
else:
connection = database
connection.pop("transport", None)
translated["dwh"] = {
"type": "postgres_direct",
"connection": connection,
}
if "vectors" not in translated:
vector_db = raw.get("vector_db")
reader = raw.get("vector_rest")
writer = raw.get("vector_write_rest")
if reader is not None or writer is not None:
translated["vectors"] = {
"type": "thoth_vector_http",
"reader": reader,
"writer": writer,
"direct": vector_db,
}
elif vector_db is not None:
translated["vectors"] = {
"type": "pgvector_direct",
"connection": vector_db,
}
if "roots" not in translated and "paths" in raw:
translated["roots"] = deepcopy(raw["paths"])
return translated, True
+28 -42
View File
@@ -1,26 +1,19 @@
# Workspace ThothII (esempio). I segreti vivono SOLO in .env (${THT_*}).
# La struttura rispecchia esattamente tht/config.py:
# database + rest per il DWH; vector_rest/vector_write_rest per il pgvector (doppia key);
# vector_db per il loading diretto (server-only); embeddings + evidence + execution.
# Ogni risorsa dichiara il proprio adapter tramite `type`.
language: it # descrizioni tabelle/colonne ed evidence sono in italiano (PSD)
database:
host: ${THT_DB_HOST}
port: ${THT_DB_PORT} # es. 5437 (Postgres diretto Supabase; 5432 = pooler)
database: ${THT_DB_NAME} # es. postgres (lo schema a stella vive in `datawarehouse`)
schema: datawarehouse
user: ${THT_DB_USER}
password: ${THT_DB_PASSWORD}
transport: rest # direct (Postgres) | rest (Supabase/PostgREST)
dwh:
type: thoth_rest # postgres_direct | thoth_rest
database:
database: ${THT_DB_NAME}
schema: datawarehouse
endpoint:
base_url: ${THT_DWH_REST_URL}
api_key: ${THT_DWH_API_KEY}
ssl_ca: ${THT_SSL_CA}
# Accesso al DWH via REST (richiesto se database.transport = rest).
rest:
base_url: ${THT_DWH_REST_URL} # es. https://supabase-aritmolab.policlinicosandonato.it/dwh/
api_key: ${THT_DWH_API_KEY} # header X-API-Key, ruolo dwh_reader (read-only)
ssl_ca: ${THT_SSL_CA} # path al certificato CA (per server con CA interna)
paths:
roots:
artifacts: artifacts
indexes: indexes
sessions: sessions
@@ -50,30 +43,23 @@ embeddings:
dim: 768
batch_size: 32
# LOADING del pgvector: connessione diretta, eseguita sul server (profilo server).
# Opzionale su postazione remota (lì la lettura passa da vector_rest).
vector_db:
host: ${THT_VEC_HOST} # Postgres locale del server
port: ${THT_VEC_PORT} # es. 5437
database: postgres
schema: vectors
user: ${THT_VEC_USER}
password: ${THT_VEC_PASSWORD}
# LETTURA (similarity search) del pgvector via REST remota: rpc search_similar.
vector_rest:
base_url: ${THT_VEC_REST_URL} # es. https://host/vector/v1/
api_key: ${THT_VEC_API_KEY} # header X-API-Key, ruolo vector_reader (read-only)
ssl_ca: ${THT_SSL_CA}
# SCRITTURA controllata del pgvector via REST remota: upsert/hash via RPC allowlist,
# niente delete/clear. Usa una API key SEPARATA dalla lettura (ruolo vector_writer).
# OPZIONALE: assente o key vuota = scrittura non abilitata (solo lettura).
# Abilita tht memory save-one / vector index-schema da postazione remota.
vector_write_rest:
base_url: ${THT_VEC_REST_URL}
api_key: ${THT_VEC_WRITE_API_KEY}
ssl_ca: ${THT_SSL_CA}
vectors:
type: thoth_vector_http # pgvector_direct | thoth_vector_http
reader:
base_url: ${THT_VEC_REST_URL}
api_key: ${THT_VEC_API_KEY}
ssl_ca: ${THT_SSL_CA}
writer: # opzionale: credenziale separata dalla lettura
base_url: ${THT_VEC_REST_URL}
api_key: ${THT_VEC_WRITE_API_KEY}
ssl_ca: ${THT_SSL_CA}
direct: # opzionale: loading server-side diretto
host: ${THT_VEC_HOST}
port: ${THT_VEC_PORT}
database: postgres
schema: vectors
user: ${THT_VEC_USER}
password: ${THT_VEC_PASSWORD}
vector:
max_chunk_chars: 4000