modelbeast/server/runner.py

"""Job runner: executes operators as subprocesses across concurrency lanes.

Operator contract:
  <python> run.py --input <path> [--input <path> ...] --outdir <dir> --params '<json>'
  - inputs are passed in asset order (single-input ops get one --input)
  - stdout/stderr are streamed into the job log (secret values redacted)
  - operator writes outputs into outdir and (optionally) outdir/result.json:
      {"outputs": [{"path": "rel/or/abs", "name": "...", "meta": {...}}, ...],
       "summary": {...}}
  - if result.json is absent, every top-level file in outdir is registered
Concurrency lanes (from manifest "resources"): gpu=1 (Metal contention),
cpu=3, net=6. Env vars from settings are injected; "requires_env" gates a job.
"""
import asyncio
import json
import os
import signal
import sys
from pathlib import Path

from . import db, settings as settings_mod, store

JOBS_DIR = db.DATA / "jobs"
LANE_LIMITS = {"gpu": 1, "cpu": 3, "net": 6}


class Runner:
    def __init__(self):
        self.queue: asyncio.Queue[str] = asyncio.Queue()
        self.subscribers: set = set()
        self.operators: dict[str, dict] = {}
        self.lanes: dict[str, asyncio.Semaphore] = {}
        self.procs: dict = {}          # job_id -> subprocess
        self.cancelled: set[str] = set()
        self._tasks: set = set()
        self.get_settings = lambda: {}  # set by main.py

    # -- pubsub -------------------------------------------------------------
    async def broadcast(self, message: dict):
        dead = []
        for ws in self.subscribers:
            try:
                await ws.send_json(message)
            except Exception:
                dead.append(ws)
        for ws in dead:
            self.subscribers.discard(ws)

    def lane_of(self, operator: str) -> str:
        op = self.operators.get(operator, {})
        lane = op.get("resources", "cpu")
        return lane if lane in LANE_LIMITS else "cpu"

    # -- job lifecycle --------------------------------------------------------
    def create_job(self, con, operator: str, asset_ids: list[str], params: dict) -> dict:
        job_id = db.new_id()
        outdir = JOBS_DIR / job_id
        outdir.mkdir(parents=True, exist_ok=True)
        primary = asset_ids[0] if asset_ids else None
        con.execute(
            "INSERT INTO jobs (id, operator, status, asset_id, asset_ids, params, outdir, created_at) "
            "VALUES (?, ?, 'queued', ?, ?, ?, ?, ?)",
            (job_id, operator, primary, json.dumps(asset_ids),
             json.dumps(params), str(outdir), db.now()),
        )
        con.commit()
        self.queue.put_nowait(job_id)
        return self.get_job(con, job_id)

    def get_job(self, con, job_id: str) -> dict | None:
        row = con.execute("SELECT * FROM jobs WHERE id = ?", (job_id,)).fetchone()
        return db.row_to_dict(row) if row else None

    def list_jobs(self, con) -> list[dict]:
        rows = con.execute("SELECT * FROM jobs ORDER BY created_at DESC LIMIT 200").fetchall()
        return [db.row_to_dict(r) for r in rows]

    def input_paths(self, con, job: dict) -> list[str]:
        ids = job.get("asset_ids") or ([job["asset_id"]] if job.get("asset_id") else [])
        paths = []
        for aid in ids:
            asset = store.get_asset(con, aid)
            if asset:
                paths.append(asset["path"])
        return paths

    async def cancel(self, con, job_id: str) -> bool:
        job = self.get_job(con, job_id)
        if not job or job["status"] in ("done", "error", "cancelled"):
            return False
        self.cancelled.add(job_id)
        proc = self.procs.get(job_id)
        if proc and proc.returncode is None:
            try:
                os.killpg(os.getpgid(proc.pid), signal.SIGTERM)
            except (ProcessLookupError, PermissionError):
                pass
        else:  # queued but not yet started
            await self._update(con, job_id, status="cancelled", finished_at=db.now())
        return True

    def delete_job(self, con, job_id: str) -> bool:
        job = self.get_job(con, job_id)
        if not job or job_id in self.procs:
            return False
        import shutil
        if job.get("outdir"):
            shutil.rmtree(job["outdir"], ignore_errors=True)
        con.execute("DELETE FROM jobs WHERE id = ?", (job_id,))
        con.commit()
        return True

    async def _update(self, con, job_id: str, **fields):
        sets = ", ".join(f"{k} = ?" for k in fields)
        con.execute(f"UPDATE jobs SET {sets} WHERE id = ?", (*fields.values(), job_id))
        con.commit()
        job = self.get_job(con, job_id)
        await self.broadcast({"type": "job", "job": job})

    # -- worker -----------------------------------------------------------------
    async def worker(self):
        con = db.connect()
        for key in LANE_LIMITS:
            self.lanes[key] = asyncio.Semaphore(LANE_LIMITS[key])
        # re-queue jobs left running/queued by a previous process
        for row in con.execute("SELECT id FROM jobs WHERE status IN ('queued','running')"):
            con.execute("UPDATE jobs SET status='queued' WHERE id = ?", (row["id"],))
            self.queue.put_nowait(row["id"])
        con.commit()
        while True:
            job_id = await self.queue.get()
            task = asyncio.create_task(self._run_lane(con, job_id))
            self._tasks.add(task)
            task.add_done_callback(self._tasks.discard)

    async def _run_lane(self, con, job_id: str):
        if job_id in self.cancelled:
            self.cancelled.discard(job_id)
            await self._update(con, job_id, status="cancelled", finished_at=db.now())
            return
        lane = self.lane_of(self.get_job(con, job_id)["operator"])
        async with self.lanes[lane]:
            if job_id in self.cancelled:
                self.cancelled.discard(job_id)
                await self._update(con, job_id, status="cancelled", finished_at=db.now())
                return
            try:
                await self._run_job(con, job_id)
            except Exception as e:
                await self._update(con, job_id, status="error", error=str(e), finished_at=db.now())

    async def _run_job(self, con, job_id: str):
        job = self.get_job(con, job_id)
        if not job:
            return
        op = self.operators.get(job["operator"])
        if not op:
            await self._update(con, job_id, status="error",
                               error=f"unknown operator {job['operator']}", finished_at=db.now())
            return

        cur_settings = self.get_settings()
        env = os.environ.copy()
        env.update(settings_mod.env_from_settings(cur_settings))
        secrets = settings_mod.secret_values(cur_settings)

        missing = [e for e in op.get("requires_env", []) if not env.get(e)]
        if missing:
            keys = ", ".join(sorted({k for k, v in settings_mod.ENV_MAP.items() if v in missing}))
            await self._update(con, job_id, status="error",
                               error=f"missing setting(s): {keys} — add them in Settings",
                               finished_at=db.now())
            return

        outdir = Path(job["outdir"])
        entry = Path(op["dir"]) / op.get("entry", "run.py")
        python = op.get("python") or sys.executable
        if op.get("python") and not Path(python).exists():
            await self._update(con, job_id, status="error", finished_at=db.now(),
                               error=f"operator not installed — {python} missing. "
                                     f"Run its install script under scripts/.")
            return
        cmd = [python, str(entry), "--outdir", str(outdir), "--params", json.dumps(job["params"])]
        for p in self.input_paths(con, job):
            cmd += ["--input", p]

        await self._update(con, job_id, status="running", started_at=db.now())
        proc = await asyncio.create_subprocess_exec(
            *cmd, stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.STDOUT,
            start_new_session=True, env=env)
        self.procs[job_id] = proc
        log_lines: list[str] = []
        assert proc.stdout
        try:
            async for raw in proc.stdout:
                log_lines.append(raw.decode(errors="replace"))
                if len(log_lines) % 5 == 0:
                    log = settings_mod.redact("".join(log_lines)[-100_000:], secrets)
                    await self._update(con, job_id, log=log)
            code = await proc.wait()
        finally:
            self.procs.pop(job_id, None)
        log = settings_mod.redact("".join(log_lines)[-100_000:], secrets)

        if job_id in self.cancelled:
            self.cancelled.discard(job_id)
            await self._update(con, job_id, status="cancelled", log=log, finished_at=db.now())
            return
        if code != 0:
            await self._update(con, job_id, status="error", log=log,
                               error=f"exit code {code}", finished_at=db.now())
            return

        registered = self._register_outputs(con, outdir, job_id)
        await self._update(con, job_id, status="done", log=log, finished_at=db.now())
        await self.broadcast({"type": "assets_changed", "job_id": job_id, "assets": registered})

    def _register_outputs(self, con, outdir: Path, job_id: str) -> list[str]:
        result_path = outdir / "result.json"
        registered = []
        if result_path.exists():
            result = json.loads(result_path.read_text())
            for out in result.get("outputs", []):
                p = Path(out["path"])
                if not p.is_absolute():
                    p = outdir / p
                if p.exists():
                    a = store.register_file(con, p, name=out.get("name"),
                                            parent_job=job_id, move=True, meta=out.get("meta"))
                    registered.append(a["id"])
        else:
            for p in sorted(outdir.iterdir()):
                if p.name == "result.json" or p.name.startswith("."):
                    continue
                a = store.register_file(con, p, parent_job=job_id, move=True)
                registered.append(a["id"])
        return registered


runner = Runner()