lukasandClaude Opus 4.8
9dbc5ed998
- concurrency.loop_semaphore: per-event-loop semaphores (safe across pytest loops and process restarts via a WeakKeyDictionary keyed by the running loop). - provider: holds a per-account (≤4) and per-host (PER_HOST_CONN_CAP) slot for the whole lifetime of an IMAP socket, released on close; SMTP send takes a per-host slot for its duration. A worker can no longer open hundreds of sockets to one host/account. - indexer: parsing goes through a PARSE_CONCURRENCY semaphore, and a message over STREAM_PARSE_MB is parsed from its blob file (parse_message_file) instead of an in-memory tree, so peak RAM ~= PARSE_CONCURRENCY x STREAM_PARSE_MB regardless of mailbox sizes. Backfill parallelism stays bounded by the bulk queue only. - config: PER_HOST_CONN_CAP, PARSE_CONCURRENCY, STREAM_PARSE_MB. - tests: per-account cap blocks the 5th connection / distinct accounts independent; file-vs-bytes parse equivalence + large-message streaming routing. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
68 lines
3.3 KiB
Python
68 lines
3.3 KiB
Python
"""Application configuration.
|
|
|
|
SPEC §14: the complete env list is read exactly once here (pydantic-settings).
|
|
No ``os.environ`` access is permitted anywhere else in the codebase.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from functools import lru_cache
|
|
|
|
from pydantic import Field
|
|
from pydantic_settings import BaseSettings, SettingsConfigDict
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
"""All runtime configuration, sourced from the environment (SPEC §14)."""
|
|
|
|
model_config = SettingsConfigDict(env_file=None, extra="ignore")
|
|
|
|
app_domain: str = Field(alias="APP_DOMAIN")
|
|
database_url: str = Field(alias="DATABASE_URL")
|
|
redis_url: str = Field(alias="REDIS_URL")
|
|
master_key: str = Field(alias="MASTER_KEY") # 32 bytes, base64
|
|
|
|
blob_root: str = Field(default="./var/blobs", alias="BLOB_ROOT")
|
|
|
|
search_backend: str = Field(default="pg", alias="SEARCH_BACKEND")
|
|
meili_url: str = Field(default="http://127.0.0.1:7700", alias="MEILI_URL")
|
|
meili_key: str = Field(default="", alias="MEILI_KEY")
|
|
|
|
undo_seconds: int = Field(default=10, alias="UNDO_SECONDS")
|
|
session_ttl_days: int = Field(default=30, alias="SESSION_TTL_DAYS")
|
|
max_attachment_mb: int = Field(default=25, alias="MAX_ATTACHMENT_MB")
|
|
log_level: str = Field(default="INFO", alias="LOG_LEVEL")
|
|
|
|
# --- Sync engine v2 (workers layer) --------------------------------------
|
|
# Worker role: "sync" (lease-owned account runners) | "jobs" (arq consumer)
|
|
# | "all" (both, single-process dev default).
|
|
worker_role: str = Field(default="all", alias="WORKER_ROLE")
|
|
interactive_concurrency: int = Field(default=20, alias="INTERACTIVE_CONCURRENCY")
|
|
bulk_concurrency: int = Field(default=2, alias="BULK_CONCURRENCY")
|
|
# Lease protocol (§2): account ownership across sync workers.
|
|
max_accounts_per_worker: int = Field(default=400, alias="MAX_ACCOUNTS_PER_WORKER")
|
|
lease_ttl: int = Field(default=60, alias="LEASE_TTL")
|
|
lease_renew: int = Field(default=20, alias="LEASE_RENEW")
|
|
# Activity tiers (§5): hot = persistent IDLE, warm/cold = transient polls.
|
|
poll_warm: int = Field(default=180, alias="POLL_WARM")
|
|
poll_cold: int = Field(default=900, alias="POLL_COLD")
|
|
tier_hot_activity_h: int = Field(default=24, alias="TIER_HOT_ACTIVITY_H")
|
|
tier_session_grace_min: int = Field(default=30, alias="TIER_SESSION_GRACE_MIN")
|
|
tier_cold_after_d: int = Field(default=3, alias="TIER_COLD_AFTER_D")
|
|
hot_budget_per_worker: int = Field(default=250, alias="HOT_BUDGET_PER_WORKER")
|
|
# Memory/connection bounds (§7, §4): peak RAM ~= PARSE_CONCURRENCY x STREAM_PARSE_MB.
|
|
per_host_conn_cap: int = Field(default=50, alias="PER_HOST_CONN_CAP")
|
|
parse_concurrency: int = Field(default=4, alias="PARSE_CONCURRENCY")
|
|
stream_parse_mb: int = Field(default=8, alias="STREAM_PARSE_MB")
|
|
|
|
oauth_google_client_id: str = Field(default="", alias="OAUTH_GOOGLE_CLIENT_ID")
|
|
oauth_google_client_secret: str = Field(default="", alias="OAUTH_GOOGLE_CLIENT_SECRET")
|
|
oauth_ms_client_id: str = Field(default="", alias="OAUTH_MS_CLIENT_ID")
|
|
oauth_ms_client_secret: str = Field(default="", alias="OAUTH_MS_CLIENT_SECRET")
|
|
|
|
|
|
@lru_cache(maxsize=1)
|
|
def get_settings() -> Settings:
|
|
"""Return the process-wide settings singleton."""
|
|
return Settings() # values are sourced from the environment
|