mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
Fixes #1310. ## Description On Windows, `headroom` startup crashes a subprocess reader thread: ``` UnicodeDecodeError: 'charmap' codec can't decode byte 0x8d in position 7894: character maps to <undefined> ... subprocess.py _readerthread -> buffer.append(fh.read()) ... encodings/cp1252.py ``` Text-mode `subprocess` calls omit `encoding=`, so Python decodes child output with the locale codec (**cp1252** on Windows). Children that emit UTF-8 ??? `cbm index_repository` (indexing sources with chars like `???`/`???`), `claude mcp get/add`, the memory-sync process ??? produce bytes invalid in cp1252 and kill the reader thread. Linux/macOS default to UTF-8, so it's invisible there. ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - Add `encoding="utf-8", errors="replace"` to every text-mode (`text=True` / `universal_newlines=True`) subprocess call in the `headroom/` package (~50 call sites; several already had it). - `errors="replace"` (not `ignore`) so corrupt bytes surface as `???` rather than vanishing from parsed output. - Add `tests/test_cli/test_subprocess_utf8_encoding.py`: an AST guard asserting every text-mode subprocess call pins `encoding=`. The runtime crash can't reproduce on UTF-8 CI, so the invariant is enforced at the source level instead. ## Testing - [x] Unit tests pass (`pytest`) - New guard test passes (validates 51 call sites). - `tests/test_install`, `tests/test_cli/test_mcp.py`, `tests/test_mcp_registry` pass. (`test_runtime_start_lock_blocks_another_process` fails on this Windows box, but it fails identically on unmodified `main` ??? a pre-existing `msvcrt` lock flake, unrelated.) ### Test Output ```text > python -m pytest tests/test_cli/test_subprocess_utf8_encoding.py -q 1 passed in 0.12s > python -m pytest tests/test_install/ tests/test_cli/test_mcp.py tests/test_mcp_registry/ -q 133 passed, 2 skipped in 15.34s ``` ## Real Behavior Proof - Environment: Windows 11, Python 3.13.13. - Exact command / steps: Started `headroom` without `PYTHONUTF8=1` on a repo with UTF-8 chars in indexable files. Observed the `UnicodeDecodeError` crash. Applied the fix (pinning `encoding="utf-8"` on all text-mode subprocess calls). Re-ran. No crash. The AST guard enforces the invariant on CI (which runs UTF-8 locales and cannot reproduce the cp1252 crash natively). - Observed result: Subprocess reader threads no longer crash on UTF-8 output under cp1252 locale. - Not tested: All third-party tools that `headroom` shells out to; each was given `errors="replace"` as a safety net. ## Workaround for affected users (before fix is deployed) `PYTHONUTF8=1` (PowerShell: `$env:PYTHONUTF8=1; headroom ...`). ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
205 lines
6.8 KiB
Python
205 lines
6.8 KiB
Python
"""Download and install rtk binary from GitHub releases."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import io
|
|
import logging
|
|
import os
|
|
import platform
|
|
import stat
|
|
import subprocess
|
|
import tarfile
|
|
import zipfile
|
|
from pathlib import Path
|
|
from urllib.request import urlopen
|
|
|
|
from headroom._subprocess import run
|
|
|
|
from . import RTK_BIN_DIR, RTK_BIN_PATH, RTK_VERSION
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
GITHUB_RELEASE_URL = "https://github.com/rtk-ai/rtk/releases/download"
|
|
|
|
|
|
def _detect_runtime_target_triple() -> str:
|
|
"""Detect platform and return the rtk release target triple."""
|
|
system = platform.system()
|
|
machine = platform.machine()
|
|
|
|
if system == "Darwin":
|
|
arch = "aarch64" if machine == "arm64" else "x86_64"
|
|
return f"{arch}-apple-darwin"
|
|
elif system == "Linux":
|
|
arch = "aarch64" if machine == "aarch64" else "x86_64"
|
|
suffix = "unknown-linux-gnu" if arch == "aarch64" else "unknown-linux-musl"
|
|
return f"{arch}-{suffix}"
|
|
elif system == "Windows":
|
|
return "x86_64-pc-windows-msvc"
|
|
|
|
raise RuntimeError(f"Unsupported platform: {system} {machine}")
|
|
|
|
|
|
def _get_target_triple() -> str:
|
|
"""Return the requested rtk target triple, honoring explicit overrides."""
|
|
return os.environ.get("HEADROOM_RTK_TARGET", "").strip() or _detect_runtime_target_triple()
|
|
|
|
|
|
def _binary_name_for_target(target: str) -> str:
|
|
"""Return the expected binary name for a target triple."""
|
|
return "rtk.exe" if "windows" in target else "rtk"
|
|
|
|
|
|
def _should_verify_target(target: str) -> bool:
|
|
"""Verify only when the requested target matches the current runtime."""
|
|
return target == _detect_runtime_target_triple()
|
|
|
|
|
|
def _get_download_url(version: str) -> tuple[str, str]:
|
|
"""Get download URL and extension for this platform.
|
|
|
|
Returns (url, extension) where extension is 'tar.gz' or 'zip'.
|
|
"""
|
|
target = _get_target_triple()
|
|
|
|
if "windows" in target:
|
|
ext = "zip"
|
|
else:
|
|
ext = "tar.gz"
|
|
|
|
url = f"{GITHUB_RELEASE_URL}/{version}/rtk-{target}.{ext}"
|
|
return url, ext
|
|
|
|
|
|
def download_rtk(version: str | None = None) -> Path:
|
|
"""Download rtk binary from GitHub releases.
|
|
|
|
Args:
|
|
version: Version to download (e.g., "v0.28.2"). Defaults to pinned version.
|
|
|
|
Returns:
|
|
Path to the installed binary.
|
|
|
|
Raises:
|
|
RuntimeError: If download or extraction fails.
|
|
"""
|
|
version = version or RTK_VERSION
|
|
target = _get_target_triple()
|
|
url, ext = _get_download_url(version)
|
|
target_path = RTK_BIN_DIR / _binary_name_for_target(target)
|
|
|
|
RTK_BIN_DIR.mkdir(parents=True, exist_ok=True)
|
|
|
|
logger.info("Downloading rtk %s from %s ...", version, url)
|
|
|
|
try:
|
|
# Validate URL scheme to prevent B310 warning
|
|
if not url.startswith(("http://", "https://")):
|
|
raise ValueError(f"Invalid URL scheme in {url}")
|
|
|
|
# Fail closed on TLS errors rather than executing an unverifiable download.
|
|
try:
|
|
with urlopen(url, timeout=30) as response:
|
|
data = response.read()
|
|
except Exception as download_err:
|
|
if "CERTIFICATE_VERIFY_FAILED" in str(download_err):
|
|
raise RuntimeError(
|
|
"TLS verification failed downloading rtk; fix the local trust store and retry."
|
|
) from download_err
|
|
raise
|
|
except Exception as e:
|
|
raise RuntimeError(f"Failed to download rtk from {url}: {e}") from e
|
|
|
|
# Extract binary
|
|
try:
|
|
if ext == "tar.gz":
|
|
with tarfile.open(fileobj=io.BytesIO(data), mode="r:gz") as tar:
|
|
# Find the rtk binary inside the archive
|
|
for member in tar.getmembers():
|
|
if member.name.endswith("/rtk") or member.name == "rtk":
|
|
member.name = target_path.name # Flatten path
|
|
tar.extract(member, RTK_BIN_DIR)
|
|
break
|
|
else:
|
|
raise RuntimeError("rtk binary not found in archive")
|
|
elif ext == "zip":
|
|
with zipfile.ZipFile(io.BytesIO(data)) as zf:
|
|
for name in zf.namelist():
|
|
if name.endswith("rtk.exe") or name.endswith("/rtk"):
|
|
with zf.open(name) as src, open(target_path, "wb") as dst:
|
|
dst.write(src.read())
|
|
break
|
|
else:
|
|
raise RuntimeError("rtk binary not found in archive")
|
|
except (tarfile.TarError, zipfile.BadZipFile) as e:
|
|
raise RuntimeError(f"Failed to extract rtk archive: {e}") from e
|
|
|
|
# Make executable (skip on Windows — no Unix permissions)
|
|
if "windows" not in target:
|
|
target_path.chmod(target_path.stat().st_mode | stat.S_IEXEC | stat.S_IXGRP | stat.S_IXOTH)
|
|
|
|
if _should_verify_target(target):
|
|
try:
|
|
result = run(
|
|
[str(target_path), "--version"],
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=5,
|
|
)
|
|
if result.returncode != 0:
|
|
raise RuntimeError(f"rtk verification failed: {result.stderr}")
|
|
logger.info("rtk installed: %s", result.stdout.strip())
|
|
except FileNotFoundError as e:
|
|
raise RuntimeError("rtk binary not found after extraction") from e
|
|
except subprocess.TimeoutExpired as e:
|
|
raise RuntimeError("rtk verification timed out") from e
|
|
else:
|
|
logger.info("rtk installed for target %s at %s (verification skipped)", target, target_path)
|
|
|
|
return target_path
|
|
|
|
|
|
def register_claude_hooks(rtk_path: Path | None = None) -> bool:
|
|
"""Register rtk hooks in Claude Code settings.
|
|
|
|
Runs `rtk init --global` which adds a PreToolUse hook to
|
|
~/.claude/settings.json that rewrites Bash commands through rtk.
|
|
|
|
Returns True if hooks were registered successfully.
|
|
"""
|
|
rtk_path = rtk_path or RTK_BIN_PATH
|
|
|
|
try:
|
|
result = run(
|
|
[str(rtk_path), "init", "--global", "--auto-patch"],
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=10,
|
|
)
|
|
if result.returncode == 0:
|
|
logger.info("rtk hooks registered in Claude Code")
|
|
return True
|
|
else:
|
|
logger.warning("rtk init failed: %s", result.stderr)
|
|
return False
|
|
except Exception as e:
|
|
logger.warning("Failed to register rtk hooks: %s", e)
|
|
return False
|
|
|
|
|
|
def ensure_rtk(version: str | None = None) -> Path | None:
|
|
"""Ensure rtk is installed — download if needed.
|
|
|
|
Returns path to rtk binary, or None if installation failed.
|
|
"""
|
|
from . import get_rtk_path
|
|
|
|
existing = get_rtk_path()
|
|
if existing:
|
|
return existing
|
|
|
|
try:
|
|
return download_rtk(version)
|
|
except RuntimeError as e:
|
|
logger.warning("Could not install rtk: %s", e)
|
|
return None
|