fleet-memory/hindsight-api/tests/test_mcp_endpoint_routing.py
DK09876 f641b30d83
feat: add mental model CRUD tools to MCP server (#337)
* Add mental model CRUD tools to MCP server

Expose mental models (pinned reflections) as 6 new MCP tools:
- list_mental_models: List with optional tag filtering
- get_mental_model: Get by ID
- create_mental_model: Create with async content generation
- update_mental_model: Update name/source_query/tags
- delete_mental_model: Delete by ID
- refresh_mental_model: Re-run source query to update content

Both multi-bank (bank_id param) and single-bank modes supported,
following the same patterns as existing retain/recall/reflect tools.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: include mental model tools in single-bank MCP mode and update tests

The single-bank mode tool set was hardcoded to only retain/recall/reflect,
excluding the new mental model tools. Updated all 3 test layers (unit,
routing, HTTP integration) to assert mental model tool exposure.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: update extension test tool count for mental model tools

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: move mental model usage metering into engine for MCP support

Mental model validation hooks (validate_mental_model_get, validate_mental_model_refresh)
were only called in REST HTTP handlers, not in the engine. MCP tools call engine methods
directly, so usage metering was skipped entirely for MCP mental model operations.

Moved pre-validation and post-completion hooks into memory_engine.py (matching the
retain/recall/reflect pattern) and removed the duplicate code from http.py.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: remove double validation from create_mental_model and add internal checks

- Remove pre-validation from create_mental_model since callers always call
  submit_async_refresh_mental_model next (which validates), preventing
  double credit checks
- Add is_internal checks to mental model metering validators (matching
  the existing pattern for recall/reflect) so background worker tasks
  skip billing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-10 22:40:43 +01:00

86 lines
4.7 KiB
Python

"""Integration test for MCP endpoint routing.
This test verifies that /mcp/ and /mcp/{bank_id}/ expose different tool sets.
"""
import httpx
import pytest
from mcp.client.session import ClientSession
from mcp.client.streamable_http import streamable_http_client
@pytest.mark.asyncio
async def test_mcp_endpoint_routing_integration(memory):
"""Test that multi-bank and single-bank endpoints expose different tools using StreamableHTTP.
This is a regression test for issue #317 where /mcp/{bank_id}/ was incorrectly
exposing all tools (including list_banks) and bank_id parameters.
"""
from hindsight_api.api import create_app
# Create app with MCP enabled
app = create_app(memory, mcp_api_enabled=True, initialize_memory=False)
# Use the app's lifespan context to properly initialize MCP servers
async with app.router.lifespan_context(app):
# Create an HTTPX client that routes to our ASGI app
from httpx import ASGITransport
async with httpx.AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as http_client:
# Test 1: Multi-bank endpoint /mcp/
async with streamable_http_client("http://test/mcp/", http_client=http_client) as (
read_stream,
write_stream,
_,
):
async with ClientSession(read_stream, write_stream) as session:
await session.initialize()
multi_result = await session.list_tools()
multi_tools = {t.name for t in multi_result.tools}
# Multi-bank should have all tools including bank management and mental models
assert "retain" in multi_tools
assert "recall" in multi_tools
assert "reflect" in multi_tools
assert "list_banks" in multi_tools, "Multi-bank should expose list_banks"
assert "create_bank" in multi_tools, "Multi-bank should expose create_bank"
assert "list_mental_models" in multi_tools, "Multi-bank should expose list_mental_models"
assert "create_mental_model" in multi_tools, "Multi-bank should expose create_mental_model"
assert "get_mental_model" in multi_tools, "Multi-bank should expose get_mental_model"
assert "update_mental_model" in multi_tools, "Multi-bank should expose update_mental_model"
assert "delete_mental_model" in multi_tools, "Multi-bank should expose delete_mental_model"
assert "refresh_mental_model" in multi_tools, "Multi-bank should expose refresh_mental_model"
# Multi-bank retain should have bank_id parameter
retain_tool = next((t for t in multi_result.tools if t.name == "retain"), None)
assert retain_tool is not None
multi_params = set(retain_tool.inputSchema.get("properties", {}).keys())
assert "bank_id" in multi_params, "Multi-bank retain should have bank_id parameter"
# Test 2: Single-bank endpoint /mcp/test-bank/
async with streamable_http_client("http://test/mcp/test-bank/", http_client=http_client) as (
read_stream,
write_stream,
_,
):
async with ClientSession(read_stream, write_stream) as session:
await session.initialize()
single_result = await session.list_tools()
single_tools = {t.name for t in single_result.tools}
# Single-bank should have scoped tools including mental models (no bank management)
assert "retain" in single_tools
assert "recall" in single_tools
assert "reflect" in single_tools
assert "list_mental_models" in single_tools, "Single-bank should expose list_mental_models"
assert "create_mental_model" in single_tools, "Single-bank should expose create_mental_model"
assert "list_banks" not in single_tools, "Single-bank should NOT expose list_banks"
assert "create_bank" not in single_tools, "Single-bank should NOT expose create_bank"
# Single-bank retain should NOT have bank_id parameter
retain_tool = next((t for t in single_result.tools if t.name == "retain"), None)
assert retain_tool is not None
single_params = set(retain_tool.inputSchema.get("properties", {}).keys())
assert "bank_id" not in single_params, "Single-bank retain should NOT have bank_id parameter"