imbajin commented on code in PR #355: URL: https://github.com/apache/hugegraph-ai/pull/355#discussion_r3340652618
########## tools/ai/hugegraph-ai-deepwiki-skill/plugins/hugegraph-ai-deepwiki-skill/skills/hugegraph-ai-deepwiki-skill/scripts/deepwiki_mcp.py: ########## @@ -0,0 +1,559 @@ +#!/usr/bin/env python3 Review Comment: ‼️ **Core script is omitted from source archives** Evidence: on current head `29aae41`, `git archive HEAD | tar -tf -` includes `tools/ai/hugegraph-ai-deepwiki-skill/plugins/hugegraph-ai-deepwiki-skill/tests/test_deepwiki_mcp.py` but not this `scripts/deepwiki_mcp.py` file. The existing root `.gitattributes` has `scripts/ export-ignore`, so archive-based installs and release source tarballs ship the tests/manifests without the executable client. Please either move/rename the plugin script directory or add an explicit archive rule so the skill package is complete in source archives. ########## tools/ai/hugegraph-ai-deepwiki-skill/plugins/hugegraph-ai-deepwiki-skill/skills/hugegraph-ai-deepwiki-skill/scripts/deepwiki_mcp.py: ########## @@ -0,0 +1,559 @@ +#!/usr/bin/env python3 +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +"""Small DeepWiki MCP client for repository-scoped Q&A.""" + +# ruff: noqa: T201 + +from __future__ import annotations + +import argparse +import json +import os +import re +import socket +import sys +import tempfile +import time +import urllib.error +import urllib.parse +import urllib.request +from pathlib import Path +from typing import Any + +DEFAULT_ENDPOINT = "https://mcp.deepwiki.com/mcp"; +CLIENT_NAME = "hugegraph-ai-deepwiki-skill" +SCRIPT_DIR = Path(__file__).resolve().parent +SKILL_DIR = SCRIPT_DIR.parent +PLUGIN_MANIFEST_PATH = SKILL_DIR.parent.parent / ".codex-plugin" / "plugin.json" +REPOS_PATH = SKILL_DIR / "references" / "repos.json" +CLIENT_VERSION_FALLBACK = "0.1.4" +CONTEXT_WINDOW_SIZE = 30 +CONTEXT_STRIDE = 10 +STOPWORDS = { + "a", + "an", + "and", + "apache", + "are", + "as", + "for", + "hugegraph", + "how", + "in", + "is", + "it", + "of", + "on", + "or", + "the", + "to", + "used", + "what", + "where", + "which", + "why", +} + + +class McpError(RuntimeError): + pass + + +def env_float(name: str, default: float) -> float: + raw_value = os.environ.get(name) + if raw_value is None: + return default + try: + return float(raw_value) + except ValueError as exc: + raise McpError(f"{name} must be a number, got {raw_value!r}.") from exc + + +def stream_timeout_seconds() -> float: + return max(1.0, env_float("DEEPWIKI_MCP_STREAM_TIMEOUT", 120.0)) + + +def load_client_version() -> str: + try: + parsed = json.loads(PLUGIN_MANIFEST_PATH.read_text(encoding="utf-8")) + except (OSError, json.JSONDecodeError): + return CLIENT_VERSION_FALLBACK + if isinstance(parsed, dict) and isinstance(parsed.get("version"), str): + return parsed["version"] + return CLIENT_VERSION_FALLBACK + + +CLIENT_VERSION = load_client_version() + + +def preview_text(text: str, limit: int = 500) -> str: + if len(text) <= limit: + return text + return f"{text[:limit]}..." + + +def positive_int(value: str) -> int: + try: + parsed = int(value) + except ValueError as exc: + raise argparse.ArgumentTypeError("--limit must be an integer") from exc + if parsed < 1: + raise argparse.ArgumentTypeError("--limit must be >= 1") + return parsed + + +def load_repos() -> dict[str, dict[str, Any]]: + try: + with REPOS_PATH.open("r", encoding="utf-8") as file: + repos = json.load(file) + except FileNotFoundError as exc: + raise McpError(f"Repository profile file is missing: {REPOS_PATH}") from exc + except UnicodeError as exc: + raise McpError(f"Repository profile file is not valid UTF-8: {REPOS_PATH}") from exc + except OSError as exc: + raise McpError(f"Repository profile file could not be read: {REPOS_PATH}") from exc + except json.JSONDecodeError as exc: + raise McpError(f"Repository profile file is not valid JSON: {REPOS_PATH}") from exc + + if not isinstance(repos, dict): + raise McpError(f"Repository profile file must contain a JSON object: {REPOS_PATH}") + return repos + + +def resolve_repo(alias_or_name: str) -> str: + repos = load_repos() + profile = repos.get(alias_or_name) + if profile is None: + known = ", ".join(sorted(repos)) + raise McpError(f"Unknown repository alias '{alias_or_name}'. Known aliases: {known}.") + if not isinstance(profile, dict): + raise McpError(f"Repository profile for '{alias_or_name}' must be a JSON object.") + if not profile.get("enabled", False): + raise McpError( + f"Repository alias '{alias_or_name}' is reserved but not enabled yet ({profile.get('repoName')})." + ) + repo_name = profile.get("repoName") + if not isinstance(repo_name, str) or not repo_name: + raise McpError(f"Repository alias '{alias_or_name}' is missing a valid repoName.") + return repo_name + + +def cache_root() -> Path: + configured = os.environ.get("DEEPWIKI_MCP_CACHE_DIR") + if configured: + return Path(configured).expanduser() + xdg_cache = os.environ.get("XDG_CACHE_HOME") + if xdg_cache: + return Path(xdg_cache).expanduser() / "deepwiki-mcp" + try: + return Path.home() / ".cache" / "deepwiki-mcp" + except RuntimeError: + return Path(tempfile.gettempdir()) / "deepwiki-mcp" + + +def repo_cache_dir(repo_name: str) -> Path: + return cache_root() / repo_name.replace("/", "__") + + +def contents_cache_path(repo_name: str) -> Path: + return repo_cache_dir(repo_name) / "wiki-contents.md" + + +def write_text_atomic(path: Path, text: str) -> None: + path.parent.mkdir(parents=True, exist_ok=True) + tmp_path: Path | None = None + try: + with tempfile.NamedTemporaryFile( + "w", + encoding="utf-8", + dir=path.parent, + prefix=f"{path.name}.", + suffix=".tmp", + delete=False, + ) as tmp_file: + tmp_file.write(text) + tmp_path = Path(tmp_file.name) + tmp_path.replace(path) + finally: + if tmp_path is not None and tmp_path.exists(): + tmp_path.unlink() + + +def parse_json(data: str) -> dict[str, Any]: + try: + parsed = json.loads(data) + except json.JSONDecodeError as exc: + raise McpError(f"DeepWiki MCP returned non-JSON content: {preview_text(data)}") from exc + if not isinstance(parsed, dict): + raise McpError(f"DeepWiki MCP returned an unexpected JSON payload: {preview_text(data)}") + return parsed + + +def read_sse_response(response: Any, expected_id: int | None) -> dict[str, Any]: + data_lines: list[str] = [] + seen_payloads: list[str] = [] + max_seconds = stream_timeout_seconds() + deadline = time.monotonic() + max_seconds + timed_out = False + + while True: + if time.monotonic() > deadline: + timed_out = True + break + try: + raw_line = response.readline() + except (TimeoutError, socket.timeout): # noqa: UP041 + timed_out = True + break + if not raw_line: + break + + line = raw_line.decode("utf-8", errors="replace").rstrip("\r\n") + if line.startswith("data:"): + data_content = line[5:] + if data_content.startswith(" "): + data_content = data_content[1:] + data_lines.append(data_content) + continue + if line: + continue + + if not data_lines: + continue + + data = "\n".join(data_lines) + data_lines = [] + seen_payloads.append(data) + parsed = parse_json(data) + if expected_id is None or parsed.get("id") == expected_id: + return parsed + + if data_lines: Review Comment: ⚠️ **Partial SSE timeouts still surface as parse errors** Evidence: a fake response that first returns `b'data: {"jsonrpc":"2.0","id":7,\n'` and then raises `TimeoutError` makes `read_sse_response()` raise `McpError: DeepWiki MCP returned non-JSON content...` instead of the timeout error path added above. The new timeout test only covers an immediate timeout before any bytes are buffered. Please treat the buffered partial event as a timeout when `timed_out` is true before parsing the trailing `data_lines`, and add a regression test for that branch. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
