Failure recovery and operational runbooks

# Step 1: Create the local artifact helpers
"""Bounded local JAX subprocess supervisor and lifecycle verifier."""
from pathlib import Path
import hashlib
import json
import math
import os
import subprocess
import sys
import tempfile
import time


def digest(value):
    return hashlib.sha256(json.dumps(value, sort_keys=True, separators=(',', ':'), allow_nan=False).encode()).hexdigest()


def atomic_json(path, value):
    """Replace one local JSON file only after its bytes have been flushed."""
    path = Path(path)
    path.parent.mkdir(parents=True, exist_ok=True)
    fd, temporary = tempfile.mkstemp(prefix=path.name+'.', suffix='.tmp', dir=path.parent)
    # Run the boundary check and catch the expected exception:
    try:
        # Enter `os.fdopen(fd, 'w')` context block:
        with os.fdopen(fd, 'w') as stream:
            json.dump(value, stream, sort_keys=True, allow_nan=False)
            stream.flush()
            os.fsync(stream.fileno())
        os.replace(temporary, path)
    finally:
        if os.path.exists(temporary):
            os.unlink(temporary)

# This file is materialized only inside the caller-owned temporary run folder.
WORKER = r'''
import hashlib, json, os, sys, time
from pathlib import Path
import jax
import jax.numpy as jnp
import numpy as np
root = Path(sys.argv[1])
cfg = json.loads((root/'config.json').read_text())
worker_hash = hashlib.sha256(Path(__file__).read_bytes()).hexdigest()
def emit(event, **fields):
    print(json.dumps(dict(event=event, monotonic_s=time.monotonic(), **fields)), flush=True)
def digest(value):
    return hashlib.sha256(json.dumps(value,sort_keys=True,separators=(',', ':'),allow_nan=False).encode()).hexdigest()
def write_checkpoint(state):
    target = root/'checkpoint.json'
    temporary = root/'checkpoint.pending'
    with temporary.open('w') as stream:
        json.dump(dict(state,checksum=digest(state)),stream,sort_keys=True,allow_nan=False)
        stream.flush()
        os.fsync(stream.fileno())
    os.replace(temporary,target)
    emit('checkpoint',step=state['step'],state_hash=digest(state))
try:
    emit('started',pid=os.getpid(),backend=jax.default_backend(),device_count=jax.device_count())
    if jax.default_backend() != cfg['backend'] or jax.device_count() < cfg['min_devices']:
        raise ValueError('runtime backend/device contract failed')
    x = jnp.linspace(-1.,1.,64)
    y = 2*x+1
    data_hash = digest(dict(x=np.asarray(x).tolist(),y=np.asarray(y).tolist()))
    training = {name:cfg[name] for name in ('seed','learning_rate','momentum','batch_size')}
    config_hash = digest(training)
    if cfg['resume']:
        saved = json.loads((root/'checkpoint.json').read_text())
        checksum = saved.pop('checksum',None)
        if checksum != digest(saved) or saved.get('worker_hash') != worker_hash:
            raise ValueError('checkpoint checksum/source mismatch')
        if saved['schema_version'] != 1 or saved['config_hash'] != config_hash or saved['data_hash'] != data_hash:
            raise ValueError('checkpoint provenance mismatch')
        state = saved
        step = saved['step']
        params=jnp.array(saved['params'])
        velocity=jnp.array(saved['velocity'])
        key=jnp.array(saved['key'],dtype=jnp.uint32)
        if not isinstance(step,int) or isinstance(step,bool) or step < 0 or step > cfg['steps'] or params.shape != (2,) or velocity.shape != (2,) or key.shape != (2,):
            raise ValueError('invalid checkpoint state shape or step')
        if not bool(jnp.all(jnp.isfinite(params))) or not bool(jnp.all(jnp.isfinite(velocity))):
            raise ValueError('nonfinite checkpoint state')
        emit('restored',step=step,state_hash=digest(saved))
    else:
        step=0
        params=jnp.zeros(2)
        velocity=jnp.zeros(2)
        key=jax.random.PRNGKey(cfg['seed'])
    def update(params,velocity,key):
        key, sample = jax.random.split(key)
        indices=jax.random.choice(sample,64,(cfg['batch_size'],),replace=False)
        objective=lambda p:jnp.mean((p[0]*x[indices]+p[1]-y[indices])**2)
        loss, grad=jax.value_and_grad(objective)(params)
        velocity=cfg['momentum']*velocity+grad
        params=params-cfg['learning_rate']*velocity
        return params,velocity,key,loss
    compiled=jax.jit(update)
    # Compile and synchronize once without consuming actual training state.
    begin=time.perf_counter()
    warm=compiled(params,velocity,key)
    jax.block_until_ready(warm)
    emit('ready',compile_warmup_s=time.perf_counter()-begin,step=step)
    while step < cfg['steps']:
        if cfg.get('stall_at') == step:
            emit('stall_injected',step=step)
            time.sleep(cfg.get('stall_seconds',10.))
        begin=time.perf_counter()
        params,velocity,key,loss=compiled(params,velocity,key)
        jax.block_until_ready((params,velocity,key,loss))
        elapsed=time.perf_counter()-begin
        step+=1
        state=dict(schema_version=1,worker_hash=worker_hash,step=step,params=np.asarray(params).tolist(),velocity=np.asarray(velocity).tolist(),key=np.asarray(key).tolist(),config_hash=config_hash,data_hash=data_hash)
        emit('progress',step=step,loss=float(loss),examples=cfg['batch_size'],update_s=elapsed,state_hash=digest(state))
        if step % cfg['checkpoint_every'] == 0 or step == cfg['steps']:
            write_checkpoint(state)
        if cfg.get('fail_after') == step:
            raise RuntimeError('controlled failure after update')
    write_checkpoint(state)
    emit('completed',step=step,state_hash=digest(state))
except Exception as error:
    emit('failed',kind=type(error).__name__,message=str(error))
    raise SystemExit(23)
'''

# Step 3 — Add bounded launch and result collection: The supervisor owns the child handle, captures its output and...
def default_config(**changes):
    cfg=dict(seed=3,learning_rate=.04,momentum=.8,batch_size=8,steps=8,
             checkpoint_every=2,backend='cpu',min_devices=1,resume=False,
             fail_after=None,stall_at=None,stall_seconds=10.)
    # Update state in place with the new values.
    cfg.update(changes)
    for name in ('steps','checkpoint_every','batch_size','min_devices'):
        # Guard input contract (`not isinstance(cfg[name], int) or isinstance(cfg[name], bool) or cfg[name] < 1`) and fail fast if violated.
        if not isinstance(cfg[name],int) or isinstance(cfg[name],bool) or cfg[name] < 1:
            raise ValueError(name+' must be a positive integer')
    # Guard input contract (`cfg['batch_size'] > 64 or not 0 <= cfg['momentum'] < 1 or (not 0 < cfg['learning_rate'] < 1)`) and fail fast if violated.
    if cfg['batch_size'] > 64 or not 0 <= cfg['momentum'] < 1 or not 0 < cfg['learning_rate'] < 1:
        raise ValueError('invalid training configuration')
    return cfg


def launch(root, config=None, timeout=10.):
    root=Path(root)
    root.mkdir(parents=True,exist_ok=True)
    cfg=default_config(**(config or {}))
    # Guard input contract (`timeout <= 0`) and fail fast if violated.
    if timeout <= 0:
        raise ValueError('timeout must be positive')
    atomic_json(root/'config.json',cfg)
    worker=root/'worker.py'
    worker.write_text(WORKER)
    # Configure environment variable before initializing the runtime.
    env=dict(os.environ,JAX_PLATFORMS=cfg['backend'],PYTHONUNBUFFERED='1')
    started=time.perf_counter()
    process=subprocess.Popen([sys.executable,str(worker),str(root)],stdout=subprocess.PIPE,stderr=subprocess.PIPE,text=True,env=env)
    timed_out=False
    try:
        stdout,stderr=process.communicate(timeout=timeout)
    except subprocess.TimeoutExpired:
        timed_out=True
        process.terminate()
        try:
            stdout,stderr=process.communicate(timeout=1.)
        except subprocess.TimeoutExpired:
            process.kill()
            stdout,stderr=process.communicate(timeout=1.)
    wall=time.perf_counter()-started
    events=[]
    malformed=[]
    for line in stdout.splitlines():
        if not line.strip():
            continue
        try:
            event=json.loads(line)
            if not isinstance(event,dict) or 'event' not in event:
                raise ValueError('not an event')
            events.append(event)
        except (ValueError,TypeError):
            malformed.append(line)
    status='timed_out' if timed_out else 'completed' if process.returncode == 0 and not malformed and events and events[-1]['event']=='completed' else 'failed'
    # Compute deterministic cryptographic digest `result` for provenance verification.
    result=dict(status=status,returncode=process.returncode,wall_s=wall,events=events,stderr=stderr,
                worker_hash=hashlib.sha256(WORKER.encode()).hexdigest(),config=cfg,malformed_stdout=malformed)
    atomic_json(root/'run.json',result)
    return result

# Step 4 — Rehearse a failure and verify every resumed update: All files stay inside one temporary drill directory; the two runs...
# Create an isolated temporary directory to run and inspect artifacts safely:
with tempfile.TemporaryDirectory(prefix='ops-recovery-') as folder:
    base=Path(folder)
    uninterrupted=launch(base/'full')
    failed=launch(base/'resume',dict(fail_after=3))
    committed=json.loads((base/'resume'/'checkpoint.json').read_text())
    assert committed['step']==2
    resumed=launch(base/'resume',dict(resume=True))
    final_full=json.loads((base/'full'/'checkpoint.json').read_text())
    final_resumed=json.loads((base/'resume'/'checkpoint.json').read_text())
assert failed['status']=='failed' and resumed['status']=='completed'
assert final_full==final_resumed
full_events={e['step']:e for e in uninterrupted['events'] if e['event']=='progress'}
resume_events=[e for e in resumed['events'] if e['event']=='progress']
assert [e['step'] for e in resume_events]==[3,4,5,6,7,8]
assert all(e['state_hash']==full_events[e['step']]['state_hash'] for e in resume_events)
print('restored step:',committed['step'],'replayed updates:',[e['step'] for e in resume_events])
print('all next-update state hashes match:',final_full==final_resumed)