Files
mcp-server/spark_executor/tools/connections.py
T
ClaudeandClaude Fable 5 6d7387b022 feat: simplify fetch_url allowlist + add update_connection tool
Part 1 — fetch_url validation simplification
  Now that Connection.allowed_url_hosts exists, it's the ONLY check.
  The old 2-label suffix-overlap rule against yarn_rm_url is gone.

  - Connection.allowed_url_hosts: list[str] = Field(default_factory=list)
    (was list[str] | None = None). Default empty list means the
    connection has no fetch access; the user must explicitly opt in
    via save_connection or update_connection.
  - _validate_url_host drops the yarn_rm_url parameter and the
    _host_suffix_overlap helper. Now: scheme/host/IP checks, then
    empty-reject, then glob match. Reject everything else.
  - fetch_url's error message now points the user at
    Connection.allowed_url_hosts as the fix.
  - The label-by-label glob check from the previous commit is kept
    (SSRF guard: 'ccam*' matches 'ccam50' but NOT 'ccam50.evil.com').

Part 2 — update_connection tool
  PATCH-style update for an existing Connection record. Only the
  fields the caller provides are changed. Same pattern as
  update_pending_job: req.model_dump(exclude_none=True), with
  'name' popped before passing to the store.

  To CLEAR a field (e.g. drop auth_password), use delete_connection
  + save_connection. This is YAGNI; the alternative (model_fields_set
  to distinguish 'omitted' from 'null') adds surface for bugs.

  - ConnectionStore.update(name, **fields): get, model_copy(update=...),
    save. Lock + atomic write. Re-validates the patched record.
  - update_connection tool function: passes fields through to the
    store, logs which fields were changed.
  - UpdateConnectionRequest Pydantic model: 12 mutable fields + name.
  - /update_connection route with operation_id='update_connection'.
  - 9 new unit tests in test_connection_tools.py (PATCH, dict/list
    replace-not-merge, unknown name 404, validation of patched record,
    disk persistence).
  - test_fetch_url.py: existing 21 tests updated; 3 new tests for
    the empty/None/missing allowed_url_hosts cases.
  - test_mcp_routes.py: assert 22 tool routes.
  - README: update_connection row added; fetch_url row updated.

Tests: 386 passed (up from 377, +9 net).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-09 11:46:07 +08:00

84 lines
2.7 KiB
Python

# coding=utf-8
"""
@Time :2026/6/24
@Author :tao.chen
"""
from common.logging import logger
from spark_executor.core.connection_store import ConnectionStore, store
from spark_executor.models import Connection
def save_connection(
*,
name: str,
master: str,
deploy_mode: str = "cluster",
yarn_rm_url: str | None = None,
spark_conf: dict[str, str] | None = None,
ssl_verify: bool | None = None,
ssl_ca_bundle: str | None = None,
auth_type: str = "none",
auth_user: str | None = None,
auth_password: str | None = None,
auth_principal: str | None = None,
auth_keytab: str | None = None,
allowed_url_hosts: list[str] | None = None,
) -> dict[str, str]:
logger.debug(
f"save_connection enter name={name} master={master} deploy_mode={deploy_mode} "
f"yarn_rm_url={yarn_rm_url} spark_conf_keys={list((spark_conf or {}).keys())}"
)
conn = Connection(
name=name,
master=master,
deploy_mode=deploy_mode,
yarn_rm_url=yarn_rm_url,
spark_conf=spark_conf or {},
ssl_verify=ssl_verify,
ssl_ca_bundle=ssl_ca_bundle,
auth_type=auth_type,
auth_user=auth_user,
auth_password=auth_password,
auth_principal=auth_principal,
auth_keytab=auth_keytab,
allowed_url_hosts=allowed_url_hosts or [],
)
store.save(conn)
return {"name": name, "status": "SAVED"}
def update_connection(name: str, **fields) -> dict[str, object]:
"""Update an existing Connection's mutable fields.
`name` is the identifier (immutable). PATCH semantics: only the fields
you pass are changed. To clear an optional field (e.g. `yarn_rm_url`),
use `delete_connection(name=...)` followed by `save_connection(...)`.
Mutable fields: master, deploy_mode, yarn_rm_url, spark_conf,
ssl_verify, ssl_ca_bundle, auth_type, auth_user, auth_password,
auth_principal, auth_keytab, allowed_url_hosts.
"""
logger.debug(f"update_connection enter name={name} fields={sorted(fields.keys())}")
return store.update(name, **fields).model_dump()
def list_connections() -> list[dict[str, object]]:
logger.debug("list_connections enter")
return [c.model_dump() for c in store.list_all()]
def get_connection(name: str) -> dict[str, object]:
logger.debug(f"get_connection enter name={name}")
conn = store.get(name)
if conn is None:
raise KeyError(f"Unknown connection: {name}")
return conn.model_dump()
def delete_connection(name: str) -> dict[str, str]:
logger.debug(f"delete_connection enter name={name}")
removed = store.delete(name)
if not removed:
raise KeyError(f"Unknown connection: {name}")
return {"name": name, "status": "DELETED"}