- Add cortex/persona.py: ContextVar-based per-request routing with path traversal protection and persona validation - Migrate inara/ → personas/inara/ (git history preserved via git mv) - config.py: add personas_root(), inara_path() delegates to personas/inara - All 14 settings.inara_path() call sites replaced with persona_path() - ChatRequest + OrchestrateRequest: add persona field (default: "inara") with validation at request entry before any processing - memory_distiller: add optional persona param for future per-persona distill - cron_runner/tools/cron: stamp persona on jobs, prefix APScheduler IDs (persona:job_id) to prevent collisions across personas - scheduler: _load_user_crons() iterates all personas at startup Adding a new persona: create personas/<name>/ with IDENTITY.md + SOUL.md. Auth: handled at nginx level (inject X-Cortex-Persona header per subdomain). Future: persona maps to Aether account_id_random for full integration. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
140 lines
4.7 KiB
Python
140 lines
4.7 KiB
Python
"""
|
|
Auto memory distillation scheduler.
|
|
|
|
Default schedule (all overridable via .env flags):
|
|
short — daily at 03:00 (no LLM — fast)
|
|
mid — weekly Sun at 03:30 (LLM call)
|
|
long — monthly 1st at 04:00 (LLM call — off by default)
|
|
|
|
Set AUTO_DISTILL=false to disable entirely.
|
|
Set AUTO_DISTILL_LONG=true to enable monthly long-term integration.
|
|
"""
|
|
import logging
|
|
from zoneinfo import ZoneInfo
|
|
from apscheduler.schedulers.asyncio import AsyncIOScheduler
|
|
from config import settings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_scheduler: AsyncIOScheduler | None = None
|
|
|
|
|
|
async def _run_short() -> None:
|
|
from memory_distiller import distill_short
|
|
try:
|
|
result = distill_short()
|
|
logger.info("auto distill short: %d files, %d chars", result["files_included"], result["chars_written"])
|
|
except Exception as e:
|
|
logger.error("auto distill short failed: %s", e)
|
|
|
|
|
|
async def _run_mid() -> None:
|
|
from memory_distiller import distill_mid
|
|
try:
|
|
result = await distill_mid()
|
|
if "error" in result:
|
|
logger.warning("auto distill mid skipped: %s", result["error"])
|
|
else:
|
|
logger.info("auto distill mid: %d chars via %s", result["chars_written"], result["backend"])
|
|
except Exception as e:
|
|
logger.error("auto distill mid failed: %s", e)
|
|
|
|
|
|
async def _run_long() -> None:
|
|
from memory_distiller import distill_long
|
|
try:
|
|
result = await distill_long()
|
|
if "error" in result:
|
|
logger.warning("auto distill long skipped: %s", result["error"])
|
|
else:
|
|
logger.info("auto distill long: %d chars via %s", result["chars_written"], result["backend"])
|
|
except Exception as e:
|
|
logger.error("auto distill long failed: %s", e)
|
|
|
|
|
|
def get_scheduler() -> AsyncIOScheduler | None:
|
|
"""Return the running scheduler instance (used by cron tools for live add/remove)."""
|
|
return _scheduler
|
|
|
|
|
|
def start() -> None:
|
|
global _scheduler
|
|
_scheduler = AsyncIOScheduler(timezone=ZoneInfo(settings.scheduler_timezone))
|
|
|
|
if not settings.auto_distill:
|
|
logger.info("auto distillation disabled (AUTO_DISTILL=false)")
|
|
|
|
if settings.auto_distill_short:
|
|
_scheduler.add_job(_run_short, "cron", hour=3, minute=0, id="distill_short")
|
|
logger.info("scheduled: distill_short daily at 03:00")
|
|
|
|
if settings.auto_distill_mid:
|
|
_scheduler.add_job(_run_mid, "cron", day_of_week="sun", hour=3, minute=30, id="distill_mid")
|
|
logger.info("scheduled: distill_mid weekly Sun at 03:30")
|
|
|
|
if settings.auto_distill_long:
|
|
_scheduler.add_job(_run_long, "cron", day=1, hour=4, minute=0, id="distill_long")
|
|
logger.info("scheduled: distill_long monthly on 1st at 04:00")
|
|
|
|
# Load user-defined cron jobs from CRONS.json
|
|
_load_user_crons()
|
|
|
|
_scheduler.start()
|
|
logger.info("scheduler started (%d jobs)", len(_scheduler.get_jobs()))
|
|
|
|
|
|
def _load_user_crons() -> None:
|
|
"""Register all enabled user-defined cron jobs across all personas."""
|
|
import asyncio
|
|
try:
|
|
from cron_runner import load_crons, parse_schedule, run_job
|
|
from persona import list_personas
|
|
except ImportError as e:
|
|
logger.warning("could not import cron modules: %s", e)
|
|
return
|
|
|
|
total = 0
|
|
for persona_name in list_personas():
|
|
for job in load_crons(persona_name):
|
|
if not job.get("enabled", True):
|
|
continue
|
|
# Ensure persona is stamped on the job for run_job() to resolve paths
|
|
job.setdefault("persona", persona_name)
|
|
try:
|
|
kwargs = parse_schedule(job["schedule"])
|
|
sched_id = f"{persona_name}:{job['id']}"
|
|
_scheduler.add_job(
|
|
lambda j=job: asyncio.ensure_future(run_job(j)),
|
|
"cron",
|
|
id=sched_id,
|
|
replace_existing=True,
|
|
**kwargs,
|
|
)
|
|
total += 1
|
|
except Exception as e:
|
|
logger.warning("cron %s/%s skipped: %s", persona_name, job.get("id"), e)
|
|
|
|
if total:
|
|
logger.info("loaded %d user cron job(s) across %d persona(s)", total, len(list_personas()))
|
|
|
|
|
|
def stop() -> None:
|
|
global _scheduler
|
|
if _scheduler and _scheduler.running:
|
|
_scheduler.shutdown(wait=False)
|
|
logger.info("auto distillation scheduler stopped")
|
|
|
|
|
|
def status() -> list[dict]:
|
|
"""Return next-run info for all scheduled jobs."""
|
|
if not _scheduler or not _scheduler.running:
|
|
return []
|
|
jobs = []
|
|
for job in _scheduler.get_jobs():
|
|
next_run = job.next_run_time
|
|
jobs.append({
|
|
"id": job.id,
|
|
"next_run": next_run.isoformat() if next_run else None,
|
|
})
|
|
return jobs
|