15ea23d5d6
* feat: introduce hindsight-api-slim and hindsight-all-slim packages Closes #552 - Move all source code from hindsight-api/ to new hindsight-api-slim/ - hindsight-api-slim has heavy ML deps (torch, sentence-transformers, transformers, einops, flashrank, mlx, mlx-lm, safetensors) and pg0-embedded as optional extras: [local-ml], [embedded-db], [all] - hindsight-api becomes a zero-code meta-package depending on hindsight-api-slim[all] for full backward compatibility - Add hindsight-all-slim meta-package: hindsight-api-slim + client + embed - hindsight-all updated to depend on hindsight-api-slim[all] - pg0.py: lazy-import pg0 with clear ImportError pointing to [embedded-db] - Dockerfile: replace sed hack with proper uv sync --extra flags - Update release.yml, test.yml, lint.sh, release.sh, CLAUDE.md and all path references throughout the repo * refactor: rename hindsight/ directory to hindsight-all/ * docs: document hindsight-api-slim and hindsight-all-slim package variants Add package variants table and extras explanation to installation.md * docs: remove emojis from installation.md, use professional tone * docs: link Docker slim variant to pip package variants section * docs: consolidate Docker image variants into single table * ci: fix working-directory paths after package restructure - Replace all hindsight-api → hindsight-api-slim in test.yml - Replace hindsight → hindsight-all in test.yml - Add --extra embedded-db to test-embed API install step * ci: add local-ml and embedded-db extras to API sync steps These extras were previously implicit in the old hindsight-api package (which bundled everything). Now that hindsight-api-slim uses optional extras, we must explicitly request local-ml and embedded-db in CI. * ci: add API install step with embedded-db to test-embed smoke test The smoke test starts hindsight-api as a daemon, which requires pg0-embedded. Add a dedicated install step for hindsight-api-slim with embedded-db extra so the daemon can start successfully. * ci: remove --no-install-project when using optional extras When --no-install-project is combined with --extra, the optional deps are not installed because extras require the project to be active. Remove --no-install-project from steps that need local-ml or embedded-db. * ci: fix ordering of uv sync steps to preserve optional extras When uv sync runs for a different workspace member, it removes optional extras installed for other members. Fix by always running extra-requiring API sync last, after other workspace member syncs. Also remove --no-install-project from embedded-db sync in test-embed, as --no-install-project prevents optional extras from being active. * ci: add local-ml extra to test-embed API install for smoke test The smoke test starts the full API server which needs sentence-transformers for local embeddings (default provider). Add local-ml extra to the install. * ci: simplify extras with --all-extras and add slim pip smoke test - Replace explicit --extra local-ml --extra embedded-db with --all-extras for cleaner, more maintainable sync steps - Add test-pip-slim job: tests hindsight-api-slim[embedded-db] without local ML models, using Cohere for embeddings/reranking (mirrors Docker slim smoke test approach) * ci: simplify slim smoke test to health check only (mirrors Docker test)
280 lines
13 KiB
Python
280 lines
13 KiB
Python
"""Integration test for MCP endpoint routing.
|
|
|
|
This test verifies that /mcp/ and /mcp/{bank_id}/ expose different tool sets,
|
|
and that URLs with or without trailing slashes both work (no 307 redirect).
|
|
"""
|
|
|
|
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"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mcp_no_trailing_slash_works(memory):
|
|
"""Test that /mcp (no trailing slash) discovers tools without 307 redirect.
|
|
|
|
Starlette's Mount class redirects /mcp to /mcp/ with a 307 Temporary Redirect.
|
|
Many MCP clients don't follow POST redirects, causing 0 tools to be discovered.
|
|
MCPMiddleware wraps the app directly (no Mount), so the redirect never happens.
|
|
"""
|
|
from hindsight_api.api import create_app
|
|
|
|
app = create_app(memory, mcp_api_enabled=True, initialize_memory=False)
|
|
|
|
async with app.router.lifespan_context(app):
|
|
from httpx import ASGITransport
|
|
|
|
async with httpx.AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as http_client:
|
|
# /mcp (no slash) should work the same as /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()
|
|
result = await session.list_tools()
|
|
|
|
tools = {t.name for t in result.tools}
|
|
assert len(tools) >= 11, f"Expected at least 11 tools from /mcp, got {len(tools)}: {tools}"
|
|
assert "retain" in tools
|
|
assert "recall" in tools
|
|
assert "list_banks" in tools
|
|
|
|
# /mcp/my-bank (single-bank, no slash) should also work
|
|
async with streamable_http_client("http://test/mcp/my-bank", http_client=http_client) as (
|
|
read_stream,
|
|
write_stream,
|
|
_,
|
|
):
|
|
async with ClientSession(read_stream, write_stream) as session:
|
|
await session.initialize()
|
|
result = await session.list_tools()
|
|
|
|
tools = {t.name for t in result.tools}
|
|
assert "retain" in tools
|
|
assert "list_banks" not in tools, "Single-bank /mcp/my-bank should NOT expose list_banks"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mcp_tool_execution_through_client(memory):
|
|
"""Test that tools can be called (not just discovered) through the MCP client.
|
|
|
|
This verifies the full pipeline: HTTP → middleware → FastMCP → tool → engine → response.
|
|
Previous tests only checked tool discovery (list_tools), not actual execution.
|
|
"""
|
|
from httpx import ASGITransport
|
|
|
|
from hindsight_api.api import create_app
|
|
|
|
app = create_app(memory, mcp_api_enabled=True, initialize_memory=False)
|
|
|
|
async with app.router.lifespan_context(app):
|
|
async with httpx.AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as http_client:
|
|
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()
|
|
|
|
# Execute list_banks tool
|
|
result = await session.call_tool("list_banks", arguments={})
|
|
assert result is not None
|
|
assert len(result.content) > 0
|
|
# The result text should be valid JSON with a "banks" key
|
|
import json
|
|
|
|
response_text = result.content[0].text
|
|
parsed = json.loads(response_text)
|
|
assert "banks" in parsed
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mcp_mental_model_validation_through_client(memory):
|
|
"""Test that input validation works through the real MCP transport.
|
|
|
|
Verifies that invalid inputs return error messages without crashing,
|
|
and that the engine is never called with invalid data.
|
|
"""
|
|
from httpx import ASGITransport
|
|
|
|
from hindsight_api.api import create_app
|
|
|
|
app = create_app(memory, mcp_api_enabled=True, initialize_memory=False)
|
|
|
|
async with app.router.lifespan_context(app):
|
|
async with httpx.AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as http_client:
|
|
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()
|
|
|
|
# Test: empty name should return validation error
|
|
import json
|
|
|
|
result = await session.call_tool(
|
|
"create_mental_model",
|
|
arguments={"name": "", "source_query": "test query"},
|
|
)
|
|
assert result is not None
|
|
parsed = json.loads(result.content[0].text)
|
|
assert "error" in parsed
|
|
assert "name cannot be empty" in parsed["error"]
|
|
|
|
# Test: max_tokens out of range should return validation error
|
|
result = await session.call_tool(
|
|
"create_mental_model",
|
|
arguments={"name": "Test", "source_query": "test query", "max_tokens": 0},
|
|
)
|
|
parsed = json.loads(result.content[0].text)
|
|
assert "error" in parsed
|
|
assert "max_tokens must be between 256 and 8192" in parsed["error"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mcp_bank_named_sse_routes_to_single_bank(memory):
|
|
"""Test that a bank named 'sse' routes to single-bank mode.
|
|
|
|
Regression test: the old MCP_ENDPOINTS blocklist prevented banks named 'sse'
|
|
or 'messages' from being accessed via path routing. They fell through to
|
|
multi-bank mode instead.
|
|
"""
|
|
from httpx import ASGITransport
|
|
|
|
from hindsight_api.api import create_app
|
|
|
|
app = create_app(memory, mcp_api_enabled=True, initialize_memory=False)
|
|
|
|
async with app.router.lifespan_context(app):
|
|
async with httpx.AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as http_client:
|
|
async with streamable_http_client("http://test/mcp/sse/", http_client=http_client) as (
|
|
read_stream,
|
|
write_stream,
|
|
_,
|
|
):
|
|
async with ClientSession(read_stream, write_stream) as session:
|
|
await session.initialize()
|
|
result = await session.list_tools()
|
|
tools = {t.name for t in result.tools}
|
|
|
|
# Should be single-bank mode (no bank management tools)
|
|
assert "retain" in tools
|
|
assert "recall" in tools
|
|
assert "list_banks" not in tools, "Bank 'sse' should route to single-bank mode"
|
|
assert "create_bank" not in tools
|
|
|
|
# retain should NOT have bank_id parameter (single-bank mode)
|
|
retain_tool = next(t for t in result.tools if t.name == "retain")
|
|
params = set(retain_tool.inputSchema.get("properties", {}).keys())
|
|
assert "bank_id" not in params
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mcp_bank_named_messages_routes_to_single_bank(memory):
|
|
"""Test that a bank named 'messages' routes to single-bank mode.
|
|
|
|
Same regression test as test_mcp_bank_named_sse_routes_to_single_bank but for 'messages'.
|
|
"""
|
|
from httpx import ASGITransport
|
|
|
|
from hindsight_api.api import create_app
|
|
|
|
app = create_app(memory, mcp_api_enabled=True, initialize_memory=False)
|
|
|
|
async with app.router.lifespan_context(app):
|
|
async with httpx.AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as http_client:
|
|
async with streamable_http_client("http://test/mcp/messages/", http_client=http_client) as (
|
|
read_stream,
|
|
write_stream,
|
|
_,
|
|
):
|
|
async with ClientSession(read_stream, write_stream) as session:
|
|
await session.initialize()
|
|
result = await session.list_tools()
|
|
tools = {t.name for t in result.tools}
|
|
|
|
assert "retain" in tools
|
|
assert "list_banks" not in tools, "Bank 'messages' should route to single-bank mode"
|