PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

from praisonaiagents.tools.mentions import MentionsParser

parser = MentionsParser(workspace_path=os.getcwd())

if parser.has_mentions(prompt):
    mention_context, prompt = parser.process(prompt)

if mention_context:
    prompt = f"{mention_context}# Task:\n{prompt}"

PATTERNS = {
    "file": re.compile(r'@file:([^\s]+)'),
    "web": re.compile(r'@web:([^\s]+(?:\s+[^\s@]+)*)'),
    "doc": re.compile(r'@doc:([^\s]+)'),
    "rule": re.compile(r'@rule:([^\s]+)'),
    "url": re.compile(r'@url:(https?://[^\s]+)'),
}

req = urllib.request.Request(
    url,
    headers={'User-Agent': 'Mozilla/5.0 (compatible; PraisonAI/1.0)'}
)

with urllib.request.urlopen(req, timeout=10) as response:
    content = response.read().decode('utf-8', errors='ignore')

#!/usr/bin/env python3
"""Self-contained local replay for PraisonAI CLI @url mention loopback fetch."""

from __future__ import annotations

import sys
import threading
from http.server import BaseHTTPRequestHandler, HTTPServer
from pathlib import Path


REPO_ROOT = Path(__file__).resolve().parents[3] / "repos" / "praisonai"
PRAISON_ROOT = REPO_ROOT / "src" / "praisonai"
AGENTS_ROOT = REPO_ROOT / "src" / "praisonai-agents"
CLI_MAIN = PRAISON_ROOT / "praisonai/cli/main.py"
MENTIONS = AGENTS_ROOT / "praisonaiagents/tools/mentions.py"


def verify_source() -> None:
    expected = {
        CLI_MAIN: [
            "from praisonaiagents.tools.mentions import MentionsParser",
            "if parser.has_mentions(prompt):",
            "mention_context, prompt = parser.process(prompt)",
            'prompt = f"{mention_context}# Task:\\n{prompt}"',
        ],
        MENTIONS: [
            '"url": re.compile(r\'@url:(https?://[^\\s]+)\')',
            "def _process_url_mention(self, url: str) -> Optional[str]:",
            "with urllib.request.urlopen(req, timeout=10) as response:",
        ],
    }

    for path, needles in expected.items():
        text = path.read_text(encoding="utf-8")
        for needle in needles:
            if needle not in text:
                raise RuntimeError(f"source verification failed: {needle!r} not found in {path}")


class _Handler(BaseHTTPRequestHandler):
    hits: list[tuple[str, str | None]] = []
    body = b"<html><body>secret-local-page</body></html>"

    def do_GET(self) -> None:  # noqa: N802
        self.__class__.hits.append((self.path, self.headers.get("Host")))
        self.send_response(200)
        self.send_header("Content-Type", "text/html; charset=utf-8")
        self.send_header("Content-Length", str(len(self.body)))
        self.end_headers()
        self.wfile.write(self.body)

    def log_message(self, format: str, *args) -> None:  # noqa: A003
        return


def main() -> int:
    if not CLI_MAIN.exists() or not MENTIONS.exists():
        raise SystemExit("missing local PraisonAI source tree")

    verify_source()

    sys.path.insert(0, str(AGENTS_ROOT))
    from praisonaiagents.tools.mentions import MentionsParser

    _Handler.hits.clear()

    server = HTTPServer(("127.0.0.1", 8766), _Handler)
    thread = threading.Thread(target=server.serve_forever, daemon=True)
    thread.start()

    try:
        parser = MentionsParser(workspace_path="/tmp")
        context, cleaned = parser.process("@url:http://localhost.:8766/ summarize this")
    finally:
        server.shutdown()
        server.server_close()
        thread.join(timeout=1)

    print("[poc] cli_path_verified=yes")
    print("[poc] mention_impl_verified=yes")
    print(f"[poc] cleaned_prompt={cleaned}")
    print(f"[poc] loopback_hit_count={len(_Handler.hits)}")

    if _Handler.hits:
        print(f"[poc] loopback_host={_Handler.hits[0][1]}")

    print(f"[poc] context_contains_secret={'secret-local-page' in context}")

    if cleaned != "summarize this":
        raise SystemExit(f"[poc] MISS: unexpected cleaned prompt {cleaned!r}")

    if not _Handler.hits:
        raise SystemExit("[poc] MISS: no loopback HTTP request observed")

    if "secret-local-page" not in context:
        raise SystemExit("[poc] MISS: local response body was not injected into prompt context")

    print("[poc] HIT: @url mention fetched loopback content and injected it into prompt context")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())