scripts/release_check.py

from __future__ import annotations

import importlib
import re
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
README = (ROOT / "README.md").read_text()
SRC = ROOT / "src"
sys.path.insert(0, str(SRC))

inferscale = importlib.import_module("inferscale")
__version__ = inferscale.__version__
design_space_search = inferscale.design_space_search
run_simulation = inferscale.run_simulation

errors: list[str] = []

match = re.search(r"^short_description:\s*(.+)$", README, re.MULTILINE)
if not match:
    errors.append("README metadata is missing short_description")
    short = ""
else:
    short = match.group(1).strip().strip('"\'')
    if len(short) > 60:
        errors.append(f"short_description is {len(short)} chars; HF limit is 60")

if "sdk: static" not in README:
    errors.append("README metadata must use sdk: static")
if __version__ != "0.3.0":
    errors.append(f"package version is {__version__}; expected 0.3.0")

src_files = sorted((ROOT / "src" / "inferscale").glob("*.py"))
web_files = sorted((ROOT / "py" / "inferscale").glob("*.py"))
if [path.name for path in src_files] != [path.name for path in web_files]:
    errors.append("browser Python mirror is stale; run python scripts/sync_web_python.py")
else:
    for src, web in zip(src_files, web_files, strict=True):
        if src.read_bytes() != web.read_bytes():
            errors.append(f"browser mirror differs for {src.name}; run sync_web_python.py")

worker_text = (ROOT / "worker.mjs").read_text()
for src in src_files:
    if f'"{src.name}"' not in worker_text:
        errors.append(f"worker module list is missing {src.name}")

for ui_file in (ROOT / "index.html", ROOT / "app.js"):
    try:
        ui_file.read_text().encode("ascii")
    except UnicodeEncodeError:
        errors.append(f"{ui_file.name} contains non-ASCII UI glyphs; use text labels for reliable rendering")

index = (ROOT / "index.html").read_text()
app = (ROOT / "app.js").read_text()
if "<footer" in index.lower():
    errors.append("v0.3 UI should not include the old product-style footer")
if "Download PNG" not in index or ".chart-download" not in app:
    errors.append("chart PNG export controls are missing")
if "Worst repetition" not in index or "Target" not in index:
    errors.append("capacity evidence columns are missing")

smoke_cfg = {
    "model": "Qwen2.5-3B",
    "accelerator": "L4",
    "quantization": "int8",
    "duration_s": 4,
    "request_rate_rps": 1,
    "prompt_tokens_mean": 128,
    "output_tokens_mean": 8,
}
try:
    smoke = run_simulation(smoke_cfg)
    if smoke["summary"]["requests_completed"] <= 0:
        errors.append("simulation smoke test completed zero requests")
    if smoke["provenance"]["latency_profile_type"] != "analytical-reference":
        errors.append("profile provenance guard is missing")
    if smoke["diagnostics"].get("provenance") != "heuristic-simulator-diagnosis":
        errors.append("diagnosis provenance missing")
    if "prefix_cache_hit_rate" not in smoke["resource"]:
        errors.append("prefix-cache telemetry missing")
except Exception as exc:  # pragma: no cover
    errors.append(f"colocated smoke test raised: {exc}")

try:
    pd = run_simulation(smoke_cfg | {
        "topology": "disaggregated_pd",
        "scheduler": "continuous_slo",
        "prefill_accelerator": "L4",
        "decode_accelerator": "L4",
        "interconnect_gbps": 50,
    })
    if pd["provenance"].get("topology") != "disaggregated_pd":
        errors.append("P/D provenance missing")
    if pd["resource"].get("p95_transfer_ms", 0) <= 0:
        errors.append("P/D transfer telemetry missing")
except Exception as exc:  # pragma: no cover
    errors.append(f"P/D smoke test raised: {exc}")

try:
    design = design_space_search(smoke_cfg | {
        "shared_prefix_tokens": 64,
        "prefix_reuse_fraction": 0.5,
        "prefill_accelerator": "L4",
        "decode_accelerator": "L4",
    }, include_disaggregated=False)
    if design["candidate_count"] != 10 or design["pareto_count"] < 1 or design["efficiency_pareto_count"] < 1:
        errors.append("design-space smoke test did not return both expected Pareto frontiers")
except Exception as exc:  # pragma: no cover
    errors.append(f"design-space smoke test raised: {exc}")

if errors:
    print("InferScale release check: FAIL")
    for error in errors:
        print(f"- {error}")
    raise SystemExit(1)

print("InferScale release check: PASS")
print(f"Version: {__version__}")
print(f"HF short_description: {len(short)}/60 characters")
print(f"Python modules mirrored: {len(src_files)}")
print(f"Colocated smoke requests: {smoke['summary']['requests_completed']}")
print(f"P/D transfer p95: {pd['resource']['p95_transfer_ms']:.3f} ms")
print(
    f"Design candidates: {design['candidate_count']} "
    f"({design['pareto_count']} performance Pareto, {design['efficiency_pareto_count']} efficiency Pareto)"
)
print(f"Profile provenance: {smoke['provenance']['latency_profile_type']}")