179 lines
7.0 KiB
Python
179 lines
7.0 KiB
Python
#!/usr/bin/env python3
|
|
"""Configuration for the standalone ASR post-processing pipeline.
|
|
|
|
This program deliberately has **no dependency on Claude Code, opencode, or any
|
|
agent CLI**. It talks to the model provider over plain HTTPS and does its own file
|
|
and git handling, so it can run from systemd, cron, or a shell with nothing but
|
|
python3 and a network route.
|
|
|
|
Everything is overridable by environment variable so the systemd unit stays the
|
|
single place where deployment-specific values live. Credentials are read from the
|
|
same 600-perm env file the legacy unit uses, so token rotation remains a one-file
|
|
change.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from dataclasses import dataclass, field
|
|
from pathlib import Path
|
|
|
|
PKG = Path(__file__).resolve().parent
|
|
ROOT = PKG.parent # OBSIDIAN/asr-pipeline
|
|
OBSIDIAN = ROOT.parent # OBSIDIAN project dir
|
|
|
|
|
|
def _env(name: str, default: str) -> str:
|
|
v = os.environ.get(name)
|
|
return v if v not in (None, "") else default
|
|
|
|
|
|
def _envf(name: str, default: float) -> float:
|
|
try:
|
|
return float(os.environ["ASR_" + name])
|
|
except (KeyError, ValueError):
|
|
return default
|
|
|
|
|
|
def _envi(name: str, default: int) -> int:
|
|
try:
|
|
return int(os.environ["ASR_" + name])
|
|
except (KeyError, ValueError):
|
|
return default
|
|
|
|
|
|
@dataclass
|
|
class Config:
|
|
# ---- paths ----------------------------------------------------------
|
|
vault: Path = field(default_factory=lambda: Path(
|
|
_env("ASR_VAULT", str(Path.home() / "obsidian-vault"))))
|
|
obsidian: Path = OBSIDIAN
|
|
root: Path = ROOT
|
|
|
|
# ---- models ---------------------------------------------------------
|
|
# Cleaning: measured against claude-haiku-4.5 on a 118k-char English-mixed call,
|
|
# gemini-3.5-flash-lite tripped the fidelity gate 19/87 times vs haiku's 78/87
|
|
# (haiku's failures were 69x "over-compression" — it behaves like a summarizer
|
|
# and deleted terms such as AUTOIMMUNE/ADCS/CD), while being 2x faster and
|
|
# 2.9x cheaper. Hence flash-lite is the default cleaner.
|
|
clean_model: str = _env("ASR_CLEAN_MODEL", "google/gemini-3.5-flash-lite")
|
|
# Drafting: one call, needs judgement and structure. sonnet-5 replaces the
|
|
# legacy headless opus-4-8.
|
|
draft_model: str = _env("ASR_DRAFT_MODEL", "anthropic/claude-sonnet-5")
|
|
keyword_model: str = _env("ASR_KEYWORD_MODEL", "google/gemini-3.5-flash-lite")
|
|
|
|
endpoint: str = _env("ASR_ENDPOINT", "https://zenmux.ai/api/v1/chat/completions")
|
|
# ZenMux returned HTTP 429 at ~12 concurrent requests and was stable at 6.
|
|
concurrency: int = _envi("CONCURRENCY", 6)
|
|
http_timeout: float = _envf("HTTP_TIMEOUT", 420.0)
|
|
max_retries: int = _envi("MAX_RETRIES", 5)
|
|
|
|
# ---- chunking -------------------------------------------------------
|
|
chunk_budget: int = _envi("CHUNK_BUDGET", 1800)
|
|
chunk_overlap: int = _envi("CHUNK_OVERLAP", 200)
|
|
collapse_noise: bool = _env("ASR_COLLAPSE_NOISE", "1") != "0"
|
|
|
|
# ---- fidelity gate --------------------------------------------------
|
|
gate_enabled: bool = _env("ASR_GATE", "1") != "0"
|
|
gate_min_ratio: float = _envf("GATE_MIN_RATIO", 0.55)
|
|
gate_max_ratio: float = _envf("GATE_MAX_RATIO", 1.35)
|
|
|
|
# ---- knowledge sources ----------------------------------------------
|
|
use_termbank: bool = _env("ASR_TERMBANK", "1") != "0"
|
|
use_hindsight: bool = _env("ASR_HINDSIGHT", "1") != "0"
|
|
use_keyword_recall: bool = _env("ASR_KEYWORD_RECALL", "1") != "0"
|
|
use_lexicon: bool = _env("ASR_LEXICON", "1") != "0"
|
|
use_normalize: bool = _env("ASR_NORMALIZE", "1") != "0"
|
|
use_evidence: bool = _env("ASR_EVIDENCE", "1") != "0"
|
|
hindsight_api: str = _env("HINDSIGHT_API", "http://192.168.50.47:8888")
|
|
hindsight_bank: str = _env("HINDSIGHT_BANK", "personal-context")
|
|
hindsight_timeout: float = _envf("HINDSIGHT_TIMEOUT", 12.0)
|
|
flag_min_score: float = _envf("FLAG_MIN_SCORE", 0.86)
|
|
review_min_score: float = _envf("REVIEW_MIN_SCORE", 0.82)
|
|
review_max_score: float = _envf("REVIEW_MAX_SCORE", 0.96)
|
|
review_host: str = _env("ASR_REVIEW_HOST", "0.0.0.0")
|
|
review_public_host: str = _env("ASR_REVIEW_PUBLIC_HOST", "192.168.50.145")
|
|
review_port: int = _envi("REVIEW_PORT", 8765)
|
|
review_idle_seconds: int = _envi("REVIEW_IDLE_SECONDS", 2700)
|
|
review_max_seconds: int = _envi("REVIEW_MAX_SECONDS", 7200)
|
|
|
|
# ---- behaviour ------------------------------------------------------
|
|
git_sync: bool = _env("ASR_GIT_SYNC", "1") != "0"
|
|
notify: bool = _env("ASR_NOTIFY", "1") != "0"
|
|
cache_llm: bool = _env("ASR_CACHE", "0") != "0" # off in production
|
|
|
|
@property
|
|
def inbox(self) -> Path:
|
|
return self.vault / ".asr-inbox"
|
|
|
|
@property
|
|
def state(self) -> Path:
|
|
return self.inbox / ".state"
|
|
|
|
@property
|
|
def drafts(self) -> Path:
|
|
"""Private rough drafts. They are never part of the Obsidian repository."""
|
|
return Path(_env("ASR_DRAFTS_DIR", str(self.state_dir / "drafts")))
|
|
|
|
@property
|
|
def minutes(self) -> Path:
|
|
return Path(_env("ASR_RESULTS_DIR", str(self.vault / "minutes")))
|
|
|
|
@property
|
|
def pending_index(self) -> Path:
|
|
# Legacy compatibility only; the Web queue replaced the Vault draft index.
|
|
return self.vault / "minutes" / "_drafts" / "_待确认.md"
|
|
|
|
@property
|
|
def glossary(self) -> Path:
|
|
return self.vault / "minutes" / "_glossary.md"
|
|
|
|
@property
|
|
def termbank_dir(self) -> Path:
|
|
return Path(_env("ASR_TERMBANK_DIR", str(self.root / "termbank")))
|
|
|
|
@property
|
|
def cache_dir(self) -> Path:
|
|
return Path(_env("ASR_CACHE_DIR", str(self.root / "cache")))
|
|
|
|
@property
|
|
def state_dir(self) -> Path:
|
|
"""Program-owned persistent state. Never inside the vault."""
|
|
return Path(_env("ASR_STATE_DIR", str(self.root / "state")))
|
|
|
|
@property
|
|
def lexicon_db(self) -> Path:
|
|
return Path(_env("ASR_LEXICON_DB", str(self.state_dir / "lexicon.db")))
|
|
|
|
@property
|
|
def log_file(self) -> Path:
|
|
return Path(_env("ASR_LOG", str(self.obsidian / "logs" / "asr-pipeline.log")))
|
|
|
|
@property
|
|
def notifier(self) -> Path:
|
|
return self.obsidian / "bin" / "meeting-status-notify.py"
|
|
|
|
@property
|
|
def env_file(self) -> Path:
|
|
"""600-perm credentials file, shared with the legacy systemd unit."""
|
|
return Path(_env("ASR_ENV_FILE", str(self.obsidian / "bin" / ".asr-refine.env")))
|
|
|
|
def api_key(self) -> str:
|
|
for k in ("ZENMUX_API_KEY", "ANTHROPIC_AUTH_TOKEN"):
|
|
v = os.environ.get(k)
|
|
if v:
|
|
return v
|
|
p = self.env_file
|
|
if p.exists():
|
|
for line in p.read_text(errors="ignore").splitlines():
|
|
line = line.strip()
|
|
if line.startswith("ANTHROPIC_AUTH_TOKEN="):
|
|
val = line.split("=", 1)[1].strip().strip("'\"")
|
|
if val:
|
|
return val
|
|
raise RuntimeError(
|
|
"no API key: set ZENMUX_API_KEY/ANTHROPIC_AUTH_TOKEN or provide "
|
|
f"{p} with ANTHROPIC_AUTH_TOKEN=…")
|
|
|
|
|
|
CFG = Config()
|