hermes-agent/tests/tools/test_mcp_oauth_manager.py
Teknium 70768665a4
fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383)
* feat(mcp-oauth): scaffold MCPOAuthManager

Central manager for per-server MCP OAuth state. Provides
get_or_build_provider (cached), remove (evicts cache + deletes
disk), invalidate_if_disk_changed (mtime watch, core fix for
external-refresh workflow), and handle_401 (dedup'd recovery).

No behavior change yet — existing call sites still use
build_oauth_auth directly. Task 1 of 8 in the MCP OAuth
consolidation (fixes Cthulhu's BetterStack reliability issues).

* feat(mcp-oauth): add HermesMCPOAuthProvider with pre-flow disk watch

Subclasses the MCP SDK's OAuthClientProvider to inject a disk
mtime check before every async_auth_flow, via the central
manager. When a subclass instance is used, external token
refreshes (cron, another CLI instance) are picked up before
the next API call.

Still dead code: the manager's _build_provider still delegates
to build_oauth_auth and returns the plain OAuthClientProvider.
Task 4 wires this subclass in. Task 2 of 8.

* refactor(mcp-oauth): extract build_oauth_auth helpers

Decomposes build_oauth_auth into _configure_callback_port,
_build_client_metadata, _maybe_preregister_client, and
_parse_base_url. Public API preserved. These helpers let
MCPOAuthManager._build_provider reuse the same logic in Task 4
instead of duplicating the construction dance.

Also updates the SDK version hint in the warning from 1.10.0 to
1.26.0 (which is what we actually require for the OAuth types
used here). Task 3 of 8.

* feat(mcp-oauth): manager now builds HermesMCPOAuthProvider directly

_build_provider constructs the disk-watching subclass using the
helpers from Task 3, instead of delegating to the plain
build_oauth_auth factory. Any consumer using the manager now gets
pre-flow disk-freshness checks automatically.

build_oauth_auth is preserved as the public API for backwards
compatibility. The code path is now:

    MCPOAuthManager.get_or_build_provider  ->
      _build_provider  ->
        _configure_callback_port
        _build_client_metadata
        _maybe_preregister_client
        _parse_base_url
        HermesMCPOAuthProvider(...)

Task 4 of 8.

* feat(mcp): wire OAuth manager + add _reconnect_event

MCPServerTask gains _reconnect_event alongside _shutdown_event.
When set, _run_http / _run_stdio exit their async-with blocks
cleanly (no exception), and the outer run() loop re-enters the
transport to rebuild the MCP session with fresh credentials.
This is the recovery path for OAuth failures that the SDK's
in-place httpx.Auth cannot handle (e.g. cron externally consumed
the refresh_token, or server-side session invalidation).

_run_http now asks MCPOAuthManager for the OAuth provider
instead of calling build_oauth_auth directly. Config-time,
runtime, and reconnect paths all share one provider instance
with pre-flow disk-watch active.

shutdown() defensively sets both events so there is no race
between reconnect and shutdown signalling.

Task 5 of 8.

* feat(mcp): detect auth failures in tool handlers, trigger reconnect

All 5 MCP tool handlers (tool call, list_resources, read_resource,
list_prompts, get_prompt) now detect auth failures and route
through MCPOAuthManager.handle_401:

  1. If the manager says recovery is viable (disk has fresh tokens,
     or SDK can refresh in-place), signal MCPServerTask._reconnect_event
     to tear down and rebuild the MCP session with fresh credentials,
     then retry the tool call once.

  2. If no recovery path exists, return a structured needs_reauth
     JSON error so the model stops hallucinating manual refresh
     attempts (the 'let me curl the token endpoint' loop Cthulhu
     pasted from Discord).

_is_auth_error catches OAuthFlowError, OAuthTokenError,
OAuthNonInteractiveError, and httpx.HTTPStatusError(401). Non-auth
exceptions still surface via the generic error path unchanged.

Task 6 of 8.

* feat(mcp-cli): route add/remove through manager, add 'hermes mcp login'

cmd_mcp_add and cmd_mcp_remove now go through MCPOAuthManager
instead of calling build_oauth_auth / remove_oauth_tokens
directly. This means CLI config-time state and runtime MCP
session state are backed by the same provider cache — removing
a server evicts the live provider, adding a server populates
the same cache the MCP session will read from.

New 'hermes mcp login <name>' command:
  - Wipes both the on-disk tokens file and the in-memory
    MCPOAuthManager cache
  - Triggers a fresh OAuth browser flow via the existing probe
    path
  - Intended target for the needs_reauth error Task 6 returns
    to the model

Task 7 of 8.

* test(mcp-oauth): end-to-end integration tests

Five new tests exercising the full consolidation with real file
I/O and real imports (no transport mocks):

  1. external_refresh_picked_up_without_restart — Cthulhu's cron
     workflow. External process writes fresh tokens to disk;
     on the next auth flow the manager's mtime-watch flips
     _initialized and the SDK re-reads from storage.

  2. handle_401_deduplicates_concurrent_callers — 10 concurrent
     handlers for the same failed token fire exactly ONE recovery
     attempt (thundering-herd protection).

  3. handle_401_returns_false_when_no_provider — defensive path
     for unknown servers.

  4. invalidate_if_disk_changed_handles_missing_file — pre-auth
     state returns False cleanly.

  5. provider_is_reused_across_reconnects — cache stickiness so
     reconnects preserve the disk-watch baseline mtime.

Task 8 of 8 — consolidation complete.
2026-04-16 21:57:10 -07:00

141 lines
4.8 KiB
Python

"""Tests for the MCP OAuth manager (tools/mcp_oauth_manager.py).
The manager consolidates the eight scattered MCP-OAuth call sites into a
single object with disk-mtime watch, dedup'd 401 handling, and a provider
cache. See `tools/mcp_oauth_manager.py` for design rationale.
"""
import json
import os
import time
import pytest
pytest.importorskip(
"mcp.client.auth.oauth2",
reason="MCP SDK 1.26.0+ required for OAuth support",
)
def test_manager_is_singleton():
"""get_manager() returns the same instance across calls."""
from tools.mcp_oauth_manager import get_manager, reset_manager_for_tests
reset_manager_for_tests()
m1 = get_manager()
m2 = get_manager()
assert m1 is m2
def test_manager_get_or_build_provider_caches(tmp_path, monkeypatch):
"""Calling get_or_build_provider twice with same name returns same provider."""
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
from tools.mcp_oauth_manager import MCPOAuthManager
mgr = MCPOAuthManager()
p1 = mgr.get_or_build_provider("srv", "https://example.com/mcp", None)
p2 = mgr.get_or_build_provider("srv", "https://example.com/mcp", None)
assert p1 is p2
def test_manager_get_or_build_rebuilds_on_url_change(tmp_path, monkeypatch):
"""Changing the URL discards the cached provider."""
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
from tools.mcp_oauth_manager import MCPOAuthManager
mgr = MCPOAuthManager()
p1 = mgr.get_or_build_provider("srv", "https://a.example.com/mcp", None)
p2 = mgr.get_or_build_provider("srv", "https://b.example.com/mcp", None)
assert p1 is not p2
def test_manager_remove_evicts_cache(tmp_path, monkeypatch):
"""remove(name) evicts the provider from cache AND deletes disk files."""
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
from tools.mcp_oauth_manager import MCPOAuthManager
# Pre-seed tokens on disk
token_dir = tmp_path / "mcp-tokens"
token_dir.mkdir(parents=True)
(token_dir / "srv.json").write_text(json.dumps({
"access_token": "TOK",
"token_type": "Bearer",
}))
mgr = MCPOAuthManager()
p1 = mgr.get_or_build_provider("srv", "https://example.com/mcp", None)
assert p1 is not None
assert (token_dir / "srv.json").exists()
mgr.remove("srv")
assert not (token_dir / "srv.json").exists()
p2 = mgr.get_or_build_provider("srv", "https://example.com/mcp", None)
assert p1 is not p2
def test_hermes_provider_subclass_exists():
"""HermesMCPOAuthProvider is defined and subclasses OAuthClientProvider."""
from tools.mcp_oauth_manager import _HERMES_PROVIDER_CLS
from mcp.client.auth.oauth2 import OAuthClientProvider
assert _HERMES_PROVIDER_CLS is not None
assert issubclass(_HERMES_PROVIDER_CLS, OAuthClientProvider)
@pytest.mark.asyncio
async def test_disk_watch_invalidates_on_mtime_change(tmp_path, monkeypatch):
"""When the tokens file mtime changes, provider._initialized flips False.
This is the behaviour Claude Code ships as
invalidateOAuthCacheIfDiskChanged (CC-1096 / GH#24317) and is the core
fix for Cthulhu's external-cron refresh workflow.
"""
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
from tools.mcp_oauth_manager import MCPOAuthManager, reset_manager_for_tests
reset_manager_for_tests()
token_dir = tmp_path / "mcp-tokens"
token_dir.mkdir(parents=True)
tokens_file = token_dir / "srv.json"
tokens_file.write_text(json.dumps({
"access_token": "OLD",
"token_type": "Bearer",
}))
mgr = MCPOAuthManager()
provider = mgr.get_or_build_provider("srv", "https://example.com/mcp", None)
assert provider is not None
# First call: records mtime (zero -> real) -> returns True
changed1 = await mgr.invalidate_if_disk_changed("srv")
assert changed1 is True
# No file change -> False
changed2 = await mgr.invalidate_if_disk_changed("srv")
assert changed2 is False
# Touch file with a newer mtime
future_mtime = time.time() + 10
os.utime(tokens_file, (future_mtime, future_mtime))
changed3 = await mgr.invalidate_if_disk_changed("srv")
assert changed3 is True
# _initialized flipped — next async_auth_flow will re-read from disk
assert provider._initialized is False
def test_manager_builds_hermes_provider_subclass(tmp_path, monkeypatch):
"""get_or_build_provider returns HermesMCPOAuthProvider, not plain OAuthClientProvider."""
from tools.mcp_oauth_manager import (
MCPOAuthManager, _HERMES_PROVIDER_CLS, reset_manager_for_tests,
)
reset_manager_for_tests()
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
mgr = MCPOAuthManager()
provider = mgr.get_or_build_provider("srv", "https://example.com/mcp", None)
assert _HERMES_PROVIDER_CLS is not None
assert isinstance(provider, _HERMES_PROVIDER_CLS)
assert provider._hermes_server_name == "srv"