mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-11-22 13:29:19 +08:00
## Description Supersedes #2658 (`tejas/mcp-2x-port`, a draft with conflicts against `main` since 2026-10-20). This is that PR's net diff rebased onto `main` as one commit (originally `fc1ba891`, now `7e0094d6`; see below), crediting Tejas Chopra and Jerrett Davis as co-authors, with three changes needed on current `main`. Both MCP servers (`headroom/ccr/mcp_server.py`, `headroom/memory/mcp_server.py`) move from SDK 1's decorator API to SDK 2's constructor callbacks, as #2658 did. The `<2.0.0` cap from #2642 is then lifted. Why now: current Claude Code tries the modern `server/discover` handshake first. On SDK 1, `headroom mcp serve` rejects it and logs `Failed to validate request: 31 validation errors for ClientRequest` on stderr in every session. Claude Code then falls back to legacy `initialize`, so the tools still work. On SDK 2 the modern handshake succeeds and nothing is logged. Changes relative to #2658: 1. **The floor is `mcp>=2.2.0,<3.0.0`, not `>=2.0.0`.** The GitHub advisories mark `mcp` `>=2.0.0, <2.2.0` as affected by CVE-2026-59951 (the reason for #4239's `>=1.30.0` floor), CVE-2026-116684, CVE-2026-116685 and CVE-2026-116686. #2658's lock resolved 2.1.1. The contract test keeps `main`'s CVE guard for the 2.x line and rejects 3.x (see #2977). 2. **`tests/test_ccr_mcp_http.py` is ported.** #1773 added it after #2658 branched, and it fails on SDK 2: `streamable_http_client` now takes an `httpx2.AsyncClient`, yields `(read, write)` without the session-id getter, and its types are snake_case (`protocol_version`). `headroom/ccr/mcp_http.py` itself needs no change. 3. **The lock is regenerated** with uv 0.9.30 (`uv lock --upgrade-package mcp`, still `revision = 3`). **Rebased onto main (`7e0094d6`), 2026-11-03.** The branch is now two linear commits, with no merge commits: - `ce4d6442` feat(mcp)!: port MCP servers to SDK 2.x (was `39c574c2`) - `274f0672` fix(mcp): attribute SDK 2 clients by client_info, not clientInfo (was `c7900848`) The previous head was the merge `4c1b774f` (main `5c785e69` into the branch), which carried the resolution against #4525 (GHSA-8g49-pg6g-xgrf, confining `headroom_read` to the workspace). The rebase replays the port directly on top of #4525 instead. What it changed: - `headroom/ccr/mcp_server.py` conflicted with #4525 in two places: the imports (#4525's `errno` next to the port's `contextvars`) and the tool list, where #4525's workspace-scoped `headroom_read` schema met the port's move from the `@list_tools` decorator to `_on_list_tools`. The resolved file keeps both: SDK 2 callbacks and #4525's confinement and `HEADROOM_MCP_READ_ROOTS` description. It is byte-identical to the file in the previous merge head `4c1b774f`. - `uv.lock` conflicted in one hunk with #4614's `mem0ai` bump: kept this PR's `mcp>=2.2.0,<3.0.0` for the `mcp` and `proxy` extras and #4614's `mem0ai>=2.0.18,<3.0`. `uv lock --check` resolves 253 packages. - Every other file this PR touches is unchanged from `4c1b774f`. The only difference in `pyproject.toml` and `uv.lock` against the previous head is #4614's own diff, line for line. The Strands blocker from the July review no longer applies: `strands-agents` 1.63.0 declares `mcp<2.4,>=1.23.0`, and the lock resolves `mcp` 2.3.0 with it. Dependency justification (CONTRIBUTING, new dep or version bump): | Package | Change | Source | |---|---|---| | `mcp` | 1.30.0 → 2.3.0 | modelcontextprotocol/python-sdk | | `mcp-types` | new, 2.3.0 | same SDK; `mcp` 2.3.0 pins it `==2.3.0` | | `httpx2`, `httpcore2` | new, 2.16.0 | pydantic/httpx2 (Tom Christie); SDK 2's HTTP client | | `httpx2-jsfetch` | new, 1.0 | only on `sys_platform == 'emscripten'`; not installed elsewhere | | `strands-agents` | 1.62.0 → 1.63.0 | first release that accepts `mcp` 2.2+ | | `httpx-sse` | removed | SDK 1 only | | `idna` | 3.15 → 3.20 | required by `httpx2` | ## Type of Change - [ ] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [x] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - `headroom/ccr/mcp_server.py`, `headroom/memory/mcp_server.py`: register handlers as `on_list_tools` / `on_call_tool` constructor callbacks, return `ListToolsResult` / `CallToolResult`, and read the request context from the callback argument. These are #2658's changes, including Jerrett's memory-backend cleanup hook. - `pyproject.toml`: `mcp>=2.2.0,<3.0.0` in the `proxy` and `mcp` extras. - `uv.lock`: relocked as described above. - `tests/test_mcp_dependency_contract.py`: both extras must admit 2.2.0 and reject 1.30.0, 2.1.1 and 3.0.0. - `tests/test_mcp_sdk2_contract.py`, `tests/_mcp_stub.py`, `tests/test_mcp_stub.py`, `tests/test_memory/test_mcp_server.py`: from #2658. - `tests/test_ccr_mcp_http.py`: ported to the SDK 2 client. It reads the session id from the `mcp-session-id` response header. - `headroom/ccr/mcp_server.py` `_current_client`: read `client_info` (SDK 2) instead of `clientInfo` (SDK 1), so `headroom_compress` savings events name the client again. `tests/test_mcp_sdk2_contract.py` now builds the SDK's own `InitializeRequestParams`; its old stand-in used `clientInfo` and stayed green while every client was recorded as `unknown`. Before and after, with an SDK 2.3 client named `attribution-probe` over stdio: the ledger recorded `unknown` on both `server/discover` and `initialize`, and now records `attribution-probe` on both (found by Devin's review). ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [ ] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output After the rebase, on `274f0672`: ```text # Python 3.11.17, mcp 2.3.0, strands-agents 1.63.0 $ pytest -q tests/test_mcp_dependency_contract.py tests/test_mcp_sdk2_contract.py tests/test_mcp_stub.py \ tests/test_ccr_mcp_http.py tests/test_memory/test_mcp_server.py \ <every test module that references mcp_server, GHSA or HEADROOM_MCP_READ_ROOTS, incl. tests/test_ccr_mcp_server.py> 840 passed, 2 skipped $ uv lock --check Resolved 253 packages $ ruff check && ruff format --check on every changed .py file (ruff 0.17.2); git diff --check origin/main clean ``` The wider 40-file mcp/strands run below was not repeated after the rebase. Before the rebase: ```text # Python 3.11.17, uv sync --frozen --extra mcp --extra strands --extra proxy --extra otel (mcp 2.3.0, strands-agents 1.63.0) $ pytest -q <every test module that references mcp, strands or the MCP servers: 40 files> 1163 passed, 31 skipped $ pytest -q tests/test_ccr_mcp_http.py tests/test_mcp_dependency_contract.py tests/test_mcp_sdk2_contract.py 9 passed $ pytest -q tests/integrations/test_strands tests/test_strands_tokenizer.py 80 passed, 25 skipped $ uv run --with uv==0.9.30 python -m uv lock --check Resolved 253 packages $ ruff check && ruff format --check on every changed .py file (ruff 0.16.8); git diff --check origin/main clean # [all] export against the union of the extras it includes: no package missing ``` ## Real Behavior Proof - Environment: macOS 27 (arm64), Python 3.11.17; `main` `fc1ba891` (SDK 1.30.0) and this branch (SDK 2.3.0); temporary `HOME`; plus this branch merged into my local runtime branch and installed as the `headroom` uv tool. - Exact command / steps: an SDK 2.3 stdio client starts `headroom mcp serve`, calls `ClientSession.discover()` (`server/discover`, as Claude Code does first), falls back to `initialize()` if that is rejected, then lists tools and calls `headroom_stats`. The server's stderr is captured. - Observed result: on `main`, `server/discover` is rejected with -32602 and the legacy `initialize` is used; stderr has 94 lines, starting `WARNING: Failed to validate request: 31 validation errors for ClientRequest`; 3 tools are listed and the call succeeds. On this branch the modern `server/discover` is accepted and stderr has 0 lines; 3 tools are listed and the call succeeds. The installed build behaves the same. - Not tested: Windows; the memory MCP server against a live client (unit and contract tests only); Strands agents against a live MCP server (`tests/integrations/test_strands` and `tests/test_strands_tokenizer.py`: 80 passed, 25 skipped); a real network client against the Streamable HTTP transport (the ASGI contract test only). ## Runtime Rollout Safety - Rollout-managed feature(s): none - Minimum rollout channel: n/a, dependency and server API change - Stable/default behavior changed: yes; the MCP servers require SDK 2.2+ and speak the modern handshake; the tools and their JSON results are unchanged - Kill switch / disable path: none; pin `headroom-ai` to the previous release to stay on SDK 1 - Unsafe override required: no - Qualification impact: environments that pin `mcp<2` alongside `headroom-ai[mcp]` or `[proxy]` no longer resolve - Rollback path: revert this commit, which restores the `<2.0.0` cap ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have commented my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [x] I did **not** edit `CHANGELOG.md` — it is generated by release-please from my Conventional Commit PR title (a CI guard enforces this) ## Screenshots (if applicable) N/A ## Additional Notes Proposed on #2658 (https://github.com/headroomlabs-ai/headroom/pull/2658#issuecomment-6562744017). If maintainers would rather keep #2658, `ce4d6442` and `274f0672` (previously `39c574c2` and `c7900848`) can be cherry-picked onto `tejas/mcp-2x-port` instead, and I'll close this. `mypy headroom/ccr/mcp_server.py headroom/memory/mcp_server.py headroom/ccr/mcp_http.py` with SDK 2.3 installed reports one error, in `headroom/providers/model_metadata.py:79`, which `main` reports too; none in the changed files. Full `mypy headroom` was not run. No docs change: the MCP tool names, arguments and results are unchanged. --------- Co-authored-by: Kenneth Wong <17061293+KennethWKZ@users.noreply.github.com> Co-authored-by: Tejas Chopra <chopratejas@gmail.com> Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
488 lines
17 KiB
Python
488 lines
17 KiB
Python
import asyncio
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock
|
|
|
|
import numpy as np
|
|
|
|
from headroom.memory.models import Memory
|
|
from tests._mcp_stub import import_module_with_mcp_stub
|
|
|
|
mcp_server_mod = import_module_with_mcp_stub("headroom.memory.mcp_server")
|
|
|
|
|
|
class _CapturingServer:
|
|
"""MCP 2.x takes handlers as constructor callbacks rather than decorators."""
|
|
|
|
def __init__(self, name: str, on_list_tools=None, on_call_tool=None, **_: object) -> None:
|
|
self.name = name
|
|
self.list_tools_handler = on_list_tools
|
|
self.call_tool_handler = on_call_tool
|
|
|
|
|
|
class _CallParams:
|
|
"""Stand-in for ``mcp.types.CallToolRequestParams``."""
|
|
|
|
def __init__(self, name: str, arguments: dict | None = None) -> None:
|
|
self.name = name
|
|
self.arguments = arguments
|
|
|
|
|
|
def test_warm_up_backend_batches_embedding_and_indexing() -> None:
|
|
"""Warm-up should batch missing embeddings and vector indexing."""
|
|
warmup_embedding = np.ones(384, dtype=np.float32)
|
|
batch_embeddings = [
|
|
np.full(384, 2.0, dtype=np.float32),
|
|
np.full(384, 3.0, dtype=np.float32),
|
|
]
|
|
|
|
embedder = SimpleNamespace(
|
|
embed=AsyncMock(return_value=warmup_embedding),
|
|
embed_batch=AsyncMock(return_value=batch_embeddings),
|
|
)
|
|
store = SimpleNamespace(save_batch=AsyncMock())
|
|
vector_index = SimpleNamespace(index_batch=AsyncMock(return_value=3))
|
|
|
|
memory_without_embedding_a = Memory(content="First", user_id="alice")
|
|
memory_with_embedding = Memory(
|
|
content="Second",
|
|
user_id="alice",
|
|
embedding=np.full(384, 5.0, dtype=np.float32),
|
|
)
|
|
memory_without_embedding_b = Memory(content="Third", user_id="alice")
|
|
memories = [
|
|
memory_without_embedding_a,
|
|
memory_with_embedding,
|
|
memory_without_embedding_b,
|
|
]
|
|
|
|
backend = SimpleNamespace(
|
|
_ensure_initialized=AsyncMock(),
|
|
_hierarchical_memory=SimpleNamespace(
|
|
_embedder=embedder,
|
|
_store=store,
|
|
_vector_index=vector_index,
|
|
),
|
|
get_user_memories=AsyncMock(return_value=memories),
|
|
)
|
|
|
|
asyncio.run(mcp_server_mod._warm_up_backend(backend, "alice"))
|
|
|
|
backend._ensure_initialized.assert_awaited_once()
|
|
backend.get_user_memories.assert_awaited_once_with("alice", limit=500)
|
|
embedder.embed.assert_awaited_once_with("warmup")
|
|
embedder.embed_batch.assert_awaited_once_with(["First", "Third"])
|
|
store.save_batch.assert_awaited_once_with(
|
|
[memory_without_embedding_a, memory_without_embedding_b]
|
|
)
|
|
vector_index.index_batch.assert_awaited_once_with(memories)
|
|
assert np.array_equal(memory_without_embedding_a.embedding, batch_embeddings[0])
|
|
assert np.array_equal(memory_without_embedding_b.embedding, batch_embeddings[1])
|
|
|
|
|
|
def test_tool_call_waits_for_handshake_warm_up(monkeypatch) -> None:
|
|
async def scenario() -> None:
|
|
warm_up_started = asyncio.Event()
|
|
release_warm_up = asyncio.Event()
|
|
backend = SimpleNamespace()
|
|
|
|
async def warm_up(candidate, user_id: str) -> None:
|
|
assert candidate is backend
|
|
assert user_id == "alice"
|
|
warm_up_started.set()
|
|
await release_warm_up.wait()
|
|
|
|
handle_search = AsyncMock(return_value=["search result"])
|
|
monkeypatch.setattr(mcp_server_mod, "Server", _CapturingServer)
|
|
monkeypatch.setattr(mcp_server_mod, "LocalBackend", lambda config: backend)
|
|
monkeypatch.setattr(mcp_server_mod, "_warm_up_backend", warm_up)
|
|
monkeypatch.setattr(mcp_server_mod, "_handle_search", handle_search)
|
|
|
|
server = mcp_server_mod.create_memory_server("memory.db", user_id="alice")
|
|
await server.list_tools_handler(None, None)
|
|
await warm_up_started.wait()
|
|
|
|
tool_call = asyncio.create_task(
|
|
server.call_tool_handler(None, _CallParams("memory_search", {"query": "preferences"}))
|
|
)
|
|
await asyncio.sleep(0)
|
|
|
|
handle_search.assert_not_awaited()
|
|
assert not tool_call.done()
|
|
|
|
release_warm_up.set()
|
|
assert (await tool_call).content == ["search result"]
|
|
handle_search.assert_awaited_once_with(
|
|
backend,
|
|
{"query": "preferences"},
|
|
"alice",
|
|
)
|
|
|
|
asyncio.run(scenario())
|
|
|
|
|
|
def test_failed_handshake_init_is_discarded_and_retried(monkeypatch) -> None:
|
|
async def scenario() -> None:
|
|
first_warm_up_started = asyncio.Event()
|
|
fail_first_warm_up = asyncio.Event()
|
|
failed_backend_closed = asyncio.Event()
|
|
|
|
async def close_failed_backend() -> None:
|
|
failed_backend_closed.set()
|
|
|
|
failed_backend = SimpleNamespace(close=AsyncMock(side_effect=close_failed_backend))
|
|
ready_backend = SimpleNamespace(close=AsyncMock())
|
|
backends = iter([failed_backend, ready_backend])
|
|
|
|
async def warm_up(candidate, user_id: str) -> None:
|
|
assert user_id == "alice"
|
|
if candidate is failed_backend:
|
|
first_warm_up_started.set()
|
|
await fail_first_warm_up.wait()
|
|
raise RuntimeError("warm-up failed")
|
|
|
|
handle_search = AsyncMock(return_value=["search result"])
|
|
monkeypatch.setattr(mcp_server_mod, "Server", _CapturingServer)
|
|
monkeypatch.setattr(mcp_server_mod, "LocalBackend", lambda config: next(backends))
|
|
monkeypatch.setattr(mcp_server_mod, "_warm_up_backend", warm_up)
|
|
monkeypatch.setattr(mcp_server_mod, "_handle_search", handle_search)
|
|
|
|
server = mcp_server_mod.create_memory_server("memory.db", user_id="alice")
|
|
await server.list_tools_handler(None, None)
|
|
await first_warm_up_started.wait()
|
|
|
|
fail_first_warm_up.set()
|
|
await failed_backend_closed.wait()
|
|
await asyncio.sleep(0)
|
|
|
|
failed_backend.close.assert_awaited_once()
|
|
handle_search.assert_not_awaited()
|
|
|
|
result = await server.call_tool_handler(
|
|
None, _CallParams("memory_search", {"query": "preferences"})
|
|
)
|
|
assert result.content == ["search result"]
|
|
handle_search.assert_awaited_once_with(
|
|
ready_backend,
|
|
{"query": "preferences"},
|
|
"alice",
|
|
)
|
|
ready_backend.close.assert_not_awaited()
|
|
|
|
asyncio.run(scenario())
|
|
|
|
|
|
def test_concurrent_tool_calls_share_backend_initialization(monkeypatch) -> None:
|
|
async def scenario() -> None:
|
|
warm_up_started = asyncio.Event()
|
|
release_warm_up = asyncio.Event()
|
|
backend = SimpleNamespace()
|
|
created_backends = 0
|
|
|
|
def create_backend(config):
|
|
nonlocal created_backends
|
|
created_backends += 1
|
|
return backend
|
|
|
|
async def warm_up(candidate, user_id: str) -> None:
|
|
assert candidate is backend
|
|
assert user_id == "alice"
|
|
warm_up_started.set()
|
|
await release_warm_up.wait()
|
|
|
|
handle_search = AsyncMock(return_value=["search result"])
|
|
monkeypatch.setattr(mcp_server_mod, "Server", _CapturingServer)
|
|
monkeypatch.setattr(mcp_server_mod, "LocalBackend", create_backend)
|
|
monkeypatch.setattr(mcp_server_mod, "_warm_up_backend", warm_up)
|
|
monkeypatch.setattr(mcp_server_mod, "_handle_search", handle_search)
|
|
|
|
server = mcp_server_mod.create_memory_server("memory.db", user_id="alice")
|
|
calls = [
|
|
asyncio.create_task(
|
|
server.call_tool_handler(
|
|
None, _CallParams("memory_search", {"query": f"query-{index}"})
|
|
)
|
|
)
|
|
for index in range(2)
|
|
]
|
|
await warm_up_started.wait()
|
|
await asyncio.sleep(0)
|
|
|
|
assert created_backends == 1
|
|
handle_search.assert_not_awaited()
|
|
|
|
release_warm_up.set()
|
|
assert [r.content for r in await asyncio.gather(*calls)] == [
|
|
["search result"],
|
|
["search result"],
|
|
]
|
|
assert handle_search.await_count == 2
|
|
assert all(call.args[0] is backend for call in handle_search.await_args_list)
|
|
|
|
asyncio.run(scenario())
|
|
|
|
|
|
def test_server_cleanup_closes_initialized_backend_once(monkeypatch) -> None:
|
|
async def scenario() -> None:
|
|
backend = SimpleNamespace(close=AsyncMock())
|
|
monkeypatch.setattr(mcp_server_mod, "Server", _CapturingServer)
|
|
monkeypatch.setattr(mcp_server_mod, "LocalBackend", lambda config: backend)
|
|
monkeypatch.setattr(mcp_server_mod, "_warm_up_backend", AsyncMock())
|
|
|
|
server = mcp_server_mod.create_memory_server("memory.db", user_id="alice")
|
|
await server.list_tools_handler(None, None)
|
|
await asyncio.sleep(0)
|
|
|
|
close_backend = server._headroom_close
|
|
await close_backend()
|
|
await close_backend()
|
|
|
|
backend.close.assert_awaited_once()
|
|
|
|
asyncio.run(scenario())
|
|
|
|
|
|
def test_server_cleanup_cancels_pending_backend_initialization(monkeypatch) -> None:
|
|
async def scenario() -> None:
|
|
init_started = asyncio.Event()
|
|
backend = SimpleNamespace(close=AsyncMock())
|
|
|
|
async def warm_up(_backend, _user_id: str) -> None:
|
|
init_started.set()
|
|
await asyncio.Event().wait()
|
|
|
|
monkeypatch.setattr(mcp_server_mod, "Server", _CapturingServer)
|
|
monkeypatch.setattr(mcp_server_mod, "LocalBackend", lambda config: backend)
|
|
monkeypatch.setattr(mcp_server_mod, "_warm_up_backend", warm_up)
|
|
|
|
server = mcp_server_mod.create_memory_server("memory.db", user_id="alice")
|
|
await server.list_tools_handler(None, None)
|
|
await init_started.wait()
|
|
|
|
await server._headroom_close()
|
|
|
|
backend.close.assert_awaited_once()
|
|
|
|
asyncio.run(scenario())
|
|
|
|
|
|
def test_run_closes_backend_when_stdio_exits(monkeypatch) -> None:
|
|
async def scenario() -> None:
|
|
close_backend = AsyncMock()
|
|
server = SimpleNamespace(
|
|
create_initialization_options=lambda: {},
|
|
run=AsyncMock(),
|
|
_headroom_close=close_backend,
|
|
)
|
|
|
|
class _StdioContext:
|
|
async def __aenter__(self):
|
|
return object(), object()
|
|
|
|
async def __aexit__(self, exc_type, exc_value, traceback):
|
|
return False
|
|
|
|
monkeypatch.setattr(mcp_server_mod, "create_memory_server", lambda *args: server)
|
|
monkeypatch.setattr(mcp_server_mod, "stdio_server", lambda: _StdioContext())
|
|
|
|
await mcp_server_mod._run("memory.db", "alice")
|
|
|
|
server.run.assert_awaited_once()
|
|
close_backend.assert_awaited_once()
|
|
|
|
asyncio.run(scenario())
|
|
|
|
|
|
def test_memory_mcp_startup_context_reports_dynamic_project_db(tmp_path) -> None:
|
|
project_dir = tmp_path / "project-a"
|
|
project_dir.mkdir()
|
|
configured_db = str(project_dir / ".headroom" / "memory.db")
|
|
|
|
context = mcp_server_mod._memory_mcp_startup_context(
|
|
configured_db,
|
|
project_dir,
|
|
db_flag_present=False,
|
|
)
|
|
|
|
assert context == {
|
|
"configured_db": configured_db,
|
|
"resolved_db": configured_db,
|
|
"config_source": "cwd-default",
|
|
"cwd": str(project_dir),
|
|
"project_root": str(project_dir),
|
|
"storage_scope": "active-project",
|
|
"path_exists": False,
|
|
"path_readable": False,
|
|
"resolution": "dynamic-cwd",
|
|
}
|
|
|
|
|
|
def test_memory_mcp_startup_context_reports_static_external_db(tmp_path) -> None:
|
|
project_dir = tmp_path / "project-a"
|
|
project_dir.mkdir()
|
|
external_db = tmp_path / "shared-memory" / "memory.db"
|
|
external_db.parent.mkdir()
|
|
external_db.write_text("sqlite placeholder")
|
|
|
|
context = mcp_server_mod._memory_mcp_startup_context(
|
|
str(external_db),
|
|
project_dir,
|
|
db_flag_present=True,
|
|
)
|
|
|
|
assert context == {
|
|
"configured_db": str(external_db),
|
|
"resolved_db": str(external_db.resolve(strict=False)),
|
|
"config_source": "cli-flag",
|
|
"cwd": str(project_dir),
|
|
"project_root": str(project_dir),
|
|
"storage_scope": "external-memory-db",
|
|
"path_exists": True,
|
|
"path_readable": True,
|
|
"resolution": "static-cli",
|
|
}
|
|
|
|
|
|
def test_memory_mcp_startup_context_reports_custom_db_path(tmp_path) -> None:
|
|
project_dir = tmp_path / "project-a"
|
|
project_dir.mkdir()
|
|
custom_db = tmp_path / "queries.db"
|
|
|
|
context = mcp_server_mod._memory_mcp_startup_context(
|
|
str(custom_db),
|
|
project_dir,
|
|
db_flag_present=True,
|
|
)
|
|
|
|
assert context["storage_scope"] == "custom-db-path"
|
|
assert context["config_source"] == "cli-flag"
|
|
assert context["path_exists"] is False
|
|
assert context["path_readable"] is False
|
|
|
|
|
|
def test_main_logs_memory_mcp_startup_context(monkeypatch, tmp_path, caplog) -> None:
|
|
project_dir = tmp_path / "project-a"
|
|
project_dir.mkdir()
|
|
monkeypatch.chdir(project_dir)
|
|
monkeypatch.setenv("USER", "codex-user")
|
|
monkeypatch.setattr(mcp_server_mod.logging, "basicConfig", lambda **kwargs: None)
|
|
monkeypatch.setattr(mcp_server_mod.sys, "argv", ["memory-mcp"])
|
|
|
|
captured_run_payloads: list[object] = []
|
|
monkeypatch.setattr(
|
|
mcp_server_mod,
|
|
"_run",
|
|
lambda db_path, user_id: ("run", db_path, user_id),
|
|
)
|
|
monkeypatch.setattr(
|
|
mcp_server_mod.asyncio,
|
|
"run",
|
|
lambda payload: captured_run_payloads.append(payload),
|
|
)
|
|
|
|
caplog.set_level("INFO", logger="headroom.memory.mcp")
|
|
|
|
mcp_server_mod.main()
|
|
|
|
assert captured_run_payloads == [
|
|
("run", str(project_dir / ".headroom" / "memory.db"), "codex-user")
|
|
]
|
|
assert any(
|
|
"Memory MCP startup: configured_db=" in record.message
|
|
and "config_source=cwd-default" in record.message
|
|
and "storage_scope=active-project" in record.message
|
|
and "resolution=dynamic-cwd" in record.message
|
|
for record in caplog.records
|
|
)
|
|
|
|
|
|
def test_search_records_access_only_for_returned_memories() -> None:
|
|
active = Memory(content="Active preference", user_id="alice")
|
|
extra = Memory(content="Lower-ranked preference", user_id="alice")
|
|
backend = SimpleNamespace(
|
|
search_memories=AsyncMock(
|
|
return_value=[
|
|
SimpleNamespace(memory=active, score=0.9, related_entities=[]),
|
|
SimpleNamespace(memory=extra, score=0.8, related_entities=[]),
|
|
]
|
|
),
|
|
get_memory=AsyncMock(
|
|
side_effect=lambda memory_id: {
|
|
active.id: active,
|
|
extra.id: extra,
|
|
}[memory_id]
|
|
),
|
|
record_access=AsyncMock(return_value=1),
|
|
)
|
|
|
|
result = asyncio.run(
|
|
mcp_server_mod._handle_search(
|
|
backend,
|
|
{"query": "preference", "top_k": 1},
|
|
"alice",
|
|
)
|
|
)
|
|
|
|
backend.record_access.assert_awaited_once_with([active.id])
|
|
assert "Active preference" in result[0].kwargs["text"]
|
|
assert "Lower-ranked preference" not in result[0].kwargs["text"]
|
|
|
|
|
|
def test_search_does_not_record_superseded_memories() -> None:
|
|
superseded = Memory(content="Old preference", user_id="alice")
|
|
replacement = Memory(content="Current preference", user_id="alice")
|
|
superseded.superseded_by = replacement.id
|
|
backend = SimpleNamespace(
|
|
search_memories=AsyncMock(
|
|
return_value=[SimpleNamespace(memory=superseded, score=0.9, related_entities=[])]
|
|
),
|
|
get_memory=AsyncMock(return_value=superseded),
|
|
record_access=AsyncMock(),
|
|
)
|
|
|
|
result = asyncio.run(mcp_server_mod._handle_search(backend, {"query": "preference"}, "alice"))
|
|
|
|
backend.record_access.assert_not_awaited()
|
|
assert result[0].kwargs["text"] == "No memories found."
|
|
|
|
|
|
def test_search_fails_open_when_access_tracking_fails() -> None:
|
|
memory = Memory(content="Useful preference", user_id="alice")
|
|
backend = SimpleNamespace(
|
|
search_memories=AsyncMock(
|
|
return_value=[SimpleNamespace(memory=memory, score=0.9, related_entities=[])]
|
|
),
|
|
get_memory=AsyncMock(return_value=memory),
|
|
record_access=AsyncMock(side_effect=RuntimeError("write failed")),
|
|
)
|
|
|
|
result = asyncio.run(mcp_server_mod._handle_search(backend, {"query": "preference"}, "alice"))
|
|
|
|
assert "Useful preference" in result[0].kwargs["text"]
|
|
|
|
|
|
def test_save_does_not_supersede_a_semantically_similar_memory() -> None:
|
|
existing = Memory(content="Use compact output by default", user_id="alice")
|
|
saved = Memory(content="Keep semantic compression disabled", user_id="alice")
|
|
backend = SimpleNamespace(
|
|
search_memories=AsyncMock(return_value=[SimpleNamespace(memory=existing, score=0.91)]),
|
|
update_memory=AsyncMock(),
|
|
save_memory=AsyncMock(return_value=saved),
|
|
)
|
|
|
|
result = asyncio.run(
|
|
mcp_server_mod._handle_save(
|
|
backend,
|
|
{"facts": ["Keep semantic compression disabled"], "importance": 0.9},
|
|
"alice",
|
|
)
|
|
)
|
|
|
|
backend.search_memories.assert_not_awaited()
|
|
backend.update_memory.assert_not_awaited()
|
|
backend.save_memory.assert_awaited_once_with(
|
|
content="Keep semantic compression disabled",
|
|
user_id="alice",
|
|
importance=0.9,
|
|
)
|
|
assert result[0].kwargs["text"].startswith("Saved 1 new, updated 0 existing")
|