confluence_web/backend/settings.py

"""Validated deployment configuration and URL validation for Confluence Web."""

from __future__ import annotations

import os
import math
import posixpath
import tempfile
import urllib.parse
import uuid
from pathlib import Path
from typing import List, Optional
from pydantic import BaseModel, Field, field_validator


class Settings(BaseModel):
    """Explicit validated deployment configuration for backend service."""

    # Confluence remote access policy
    approved_confluence_origins: List[str] = Field(
        default_factory=lambda: ["https://approved.example.com"]
    )
    corporate_ca_path: Optional[str] = None
    # Optional explicit outbound proxy for Confluence only (socks5://, socks5h://, http://, https://).
    # Model provider traffic never uses it. Environment proxy variables are ignored.
    confluence_proxy: Optional[str] = None

    # Model provider configuration
    model_provider: str = "fake"  # Explicit fake adapter or openai; unknown values fail app creation.
    model_name: str = "fake-model"
    model_api_key: Optional[str] = None
    model_endpoint: Optional[str] = None
    model_context_window_tokens: int = 128_000
    model_max_output_tokens: int = 4096
    model_timeout_seconds: float = 60.0  # per model call HTTP timeout

    # Container & Docker configuration
    runtime_image: str = "confluence-agent:latest"
    docker_host: Optional[str] = None
    container_label_key: str = "com.confluence_web.app"
    container_label_value: str = "query-runner"
    container_instance_id: str = Field(default_factory=lambda: uuid.uuid4().hex)

    # Artifact storage
    artifact_storage_dir: Path = Field(
        default_factory=lambda: Path(tempfile.gettempdir()) / "confluence_web_artifacts"
    )
    artifact_max_files_per_query: int = 20
    artifact_max_bytes_per_file: int = 10 * 1024 * 1024  # 10 MiB
    artifact_max_bytes_per_query: int = 50 * 1024 * 1024  # 50 MiB
    artifact_global_storage_limit: int = 500 * 1024 * 1024  # 500 MiB
    artifact_ttl_seconds: int = 900  # 15 minutes

    # Server & frontend
    bind_host: str = "127.0.0.1"
    bind_port: int = 8000
    frontend_dist_dir: Optional[Path] = None

    # Runtime deadlines and concurrency
    query_timeout_seconds: float = 180.0
    cleanup_timeout_seconds: float = 10.0
    max_inflight_remote_calls: int = 4
    max_confluence_calls: int = 100
    max_model_calls: int = 50

    # Development mode (explicit opt-in)
    dev_mode: bool = False

    @field_validator("approved_confluence_origins")
    @classmethod
    def validate_origins(cls, v: List[str]) -> List[str]:
        for origin in v:
            try:
                parsed = urllib.parse.urlsplit(origin)
                if parsed.scheme == "http" and parsed.hostname not in ("localhost", "127.0.0.1", "::1"):
                    raise ValueError(f"Approved origin '{origin}' uses HTTP but is not loopback. HTTPS is required.")
            except Exception as e:
                if isinstance(e, ValueError):
                    raise
                raise ValueError(f"Invalid approved origin: {origin}") from e
        return v

    @field_validator("confluence_proxy")
    @classmethod
    def validate_proxy(cls, v: Optional[str]) -> Optional[str]:
        if v is None:
            return None
        v = v.strip()
        if not v:
            return None
        parsed = urllib.parse.urlsplit(v)
        if parsed.scheme not in ("socks5", "socks5h", "http", "https") or not parsed.hostname:
            raise ValueError("confluence_proxy must be a socks5://, socks5h://, http:// or https:// URL")
        return v

    @field_validator("query_timeout_seconds", "cleanup_timeout_seconds", "model_timeout_seconds")
    @classmethod
    def validate_deadline(cls, value):
        if not math.isfinite(value) or value <= 0:
            raise ValueError("Deadlines must be finite and positive")
        return value

    @field_validator("model_context_window_tokens", "model_max_output_tokens", "artifact_ttl_seconds")
    @classmethod
    def validate_positive(cls, value):
        if value <= 0:
            raise ValueError("Resource limits must be positive")
        return value

    @classmethod
    def from_env(cls) -> Settings:
        """Load settings from environment variables."""
        def _parse_int(name: str, default: int) -> int:
            val = os.getenv(name)
            if val is None:
                return default
            try:
                return int(val)
            except ValueError:
                raise ValueError(f"Invalid integer environment variable {name}")

        def _parse_float(name: str, default: float) -> float:
            val = os.getenv(name)
            if val is None:
                return default
            try:
                parsed = float(val)
                if not math.isfinite(parsed):
                    raise ValueError
                return parsed
            except ValueError:
                raise ValueError(f"Invalid float environment variable {name}")

        origins_raw = os.getenv("CONFLUENCE_WEB_APPROVED_ORIGINS")
        origins = (
            [o.strip() for o in origins_raw.split(",") if o.strip()]
            if origins_raw
            else ["https://approved.example.com"]
        )

        storage_dir_raw = os.getenv("CONFLUENCE_WEB_ARTIFACT_DIR")
        storage_dir = (
            Path(storage_dir_raw)
            if storage_dir_raw
            else Path(tempfile.gettempdir()) / "confluence_web_artifacts"
        )

        frontend_dist_raw = os.getenv("CONFLUENCE_WEB_FRONTEND_DIST_DIR")
        frontend_dist = Path(frontend_dist_raw) if frontend_dist_raw else None

        dev_mode = os.getenv("CONFLUENCE_WEB_DEV_MODE", "false").lower() in (
            "1",
            "true",
            "yes",
        )

        return cls(
            approved_confluence_origins=origins,
            corporate_ca_path=os.getenv("CONFLUENCE_WEB_CORPORATE_CA_PATH"),
            confluence_proxy=os.getenv("CONFLUENCE_WEB_CONFLUENCE_PROXY"),
            model_provider=os.getenv("CONFLUENCE_WEB_MODEL_PROVIDER", "fake"),
            model_name=os.getenv("CONFLUENCE_WEB_MODEL_NAME", "fake-model"),
            model_api_key=os.getenv("CONFLUENCE_WEB_MODEL_API_KEY"),
            model_endpoint=os.getenv("CONFLUENCE_WEB_MODEL_ENDPOINT"),
            model_context_window_tokens=_parse_int(
                "CONFLUENCE_WEB_MODEL_CONTEXT_WINDOW_TOKENS", 128000
            ),
            model_max_output_tokens=_parse_int(
                "CONFLUENCE_WEB_MODEL_MAX_OUTPUT_TOKENS", 4096
            ),
            model_timeout_seconds=_parse_float("CONFLUENCE_WEB_MODEL_TIMEOUT_SECONDS", 60.0),
            runtime_image=os.getenv(
                "CONFLUENCE_WEB_RUNTIME_IMAGE", "confluence-agent:latest"
            ),
            docker_host=os.getenv("CONFLUENCE_WEB_DOCKER_HOST"),
            container_label_key=os.getenv(
                "CONFLUENCE_WEB_CONTAINER_LABEL_KEY", "com.confluence_web.app"
            ),
            container_label_value=os.getenv(
                "CONFLUENCE_WEB_CONTAINER_LABEL_VALUE", "query-runner"
            ),
            container_instance_id=os.getenv(
                "CONFLUENCE_WEB_CONTAINER_INSTANCE_ID", uuid.uuid4().hex
            ),
            artifact_storage_dir=storage_dir,
            bind_host=os.getenv("CONFLUENCE_WEB_BIND_HOST", "127.0.0.1"),
            bind_port=_parse_int("CONFLUENCE_WEB_BIND_PORT", 8000),
            frontend_dist_dir=frontend_dist,
            dev_mode=dev_mode,
            query_timeout_seconds=_parse_float(
                "CONFLUENCE_WEB_QUERY_TIMEOUT_SECONDS", 180.0
            ),
            cleanup_timeout_seconds=_parse_float(
                "CONFLUENCE_WEB_CLEANUP_TIMEOUT_SECONDS", 10.0
            ),
        )


from backend.errors import DestinationDeniedError, InvalidInputError


def canonicalize_url(url_str: str) -> str:
    """Canonicalize a URL: scheme/host/port and context path.

    Rejects userinfo, fragments, query strings, and path traversal.
    """
    if not isinstance(url_str, str):
        raise InvalidInputError("URL must be a string")

    stripped = url_str.strip()
    if not stripped:
        raise InvalidInputError("URL cannot be empty")

    if len(stripped.encode("utf-8")) > 8192:
        raise InvalidInputError("URL exceeds 8 KiB limit")

    if any(ord(c) < 32 or ord(c) == 127 for c in stripped) or "\\" in stripped:
        raise InvalidInputError("URL contains invalid characters")
    try:
        parsed = urllib.parse.urlsplit(stripped)
    except ValueError as exc:
        raise InvalidInputError("Malformed URL") from exc

    scheme = parsed.scheme.lower()
    if scheme not in ("http", "https"):
        raise InvalidInputError(f"Invalid URL scheme: {scheme}. Only http and https allowed.")

    if parsed.username or parsed.password or "@" in parsed.netloc:
        raise InvalidInputError("URL must not contain userinfo")

    if parsed.fragment or "#" in stripped:
        raise InvalidInputError("URL must not contain fragments")

    if parsed.query or "?" in stripped:
        raise InvalidInputError("URL must not contain query parameters")

    hostname = parsed.hostname
    if not hostname:
        raise InvalidInputError("URL must contain a valid hostname")
    hostname = hostname.lower()
    hostname = f"[{hostname}]" if ":" in hostname else hostname

    # Port canonicalization
    try:
        port = parsed.port
    except ValueError:
        raise InvalidInputError("URL contains invalid port")

    if port is not None:
        if not (1 <= port <= 65535):
            raise InvalidInputError(f"URL port {port} is out of range")
        if (scheme == "https" and port == 443) or (scheme == "http" and port == 80):
            netloc = hostname
        else:
            netloc = f"{hostname}:{port}"
    else:
        netloc = hostname

    # Check for traversal attempts in raw path
    raw_path = parsed.path
    if "%2e" in raw_path.lower() or "%2f" in raw_path.lower():
        raise InvalidInputError("URL contains encoded path traversal")

    # Reject raw traversal segments like /../ or /./
    path_segments = raw_path.split("/")
    if ".." in path_segments or "." in path_segments:
        raise InvalidInputError("URL contains path traversal or dot segments")

    # Normalize path
    normalized_path = posixpath.normpath(raw_path) if raw_path else ""
    if normalized_path.startswith("..") or "/../" in normalized_path or normalized_path == "..":
        raise InvalidInputError("URL contains directory traversal")

    if normalized_path == "/" or normalized_path == ".":
        normalized_path = ""
    elif normalized_path.endswith("/"):
        normalized_path = normalized_path.rstrip("/")

    return f"{scheme}://{netloc}{normalized_path}"


def validate_confluence_url(user_url: str, approved_origins: List[str]) -> str:
    """Canonicalize and validate user-supplied Confluence URL against approved origins.

    Rejects path-prefix lookalikes, non-matching origins, and invalid URLs.
    Returns canonical approved URL.
    """
    canonical_user = canonicalize_url(user_url)
    user_parsed = urllib.parse.urlsplit(canonical_user)

    if user_parsed.scheme == "http" and user_parsed.hostname not in ("localhost", "127.0.0.1", "::1"):
        raise DestinationDeniedError(
            f"Confluence destination denied: HTTP is only allowed for loopback development; HTTPS required for '{user_url}'"
        )

    for approved in approved_origins:
        try:
            canonical_approved = canonicalize_url(approved)
        except Exception:
            continue
        approved_parsed = urllib.parse.urlsplit(canonical_approved)

        # Scheme and netloc must match exactly
        if (user_parsed.scheme, user_parsed.netloc) != (approved_parsed.scheme, approved_parsed.netloc):
            continue

        approved_path = approved_parsed.path.rstrip("/")
        user_path = user_parsed.path.rstrip("/")

        # Context path matching: must match exactly or be an approved subpath
        if user_path == approved_path:
            return canonical_user
        # If approved has no context path (root), user must match root or subpath
        if not approved_path and (not user_path or user_path.startswith("/")):
            return canonical_user
        # If approved has context path like /wiki, user_path must start with /wiki/
        if user_path.startswith(approved_path + "/"):
            return canonical_user

    raise DestinationDeniedError(f"Confluence destination denied by policy: '{user_url}' is not in approved origins")