fix(ingest): compose the MCP timeout with anyio's own cancel scope, not asyncio.wait_for (kø-z)

asyncio.wait_for cancelling stdio_call_tool's run() from outside the anyio
task groups it awaits (stdio_client, ClientSession) never surfaced a
TimeoutError: measured against a real hanging server, the mismatch produced
an anyio.BrokenResourceError wrapped in a BaseExceptionGroup instead. Moving
the deadline to anyio.fail_after, nested inside both task groups, lets
anyio tear down its own structure cleanly and raise a plain TimeoutError,
which is now translated into IngestError(code="mcp_timeout") alongside the
mcp_tool_error/mcp_non_text_content family.

src/portfolio_optimiser/ingest_mcp.py

@@ -140,6 +140,7 @@ def stdio_call_tool(
     """
     import asyncio
 
+    import anyio
     from mcp import ClientSession, StdioServerParameters
     from mcp.client.stdio import stdio_client
 
@@ -157,20 +158,34 @@ def stdio_call_tool(
             env["MCP_CREDENTIAL"] = credential
 
         async def run() -> str:
-            params = StdioServerParameters(command=command, args=list(args), env=env)
-            async with stdio_client(params) as (read, write):
-                async with ClientSession(read, write) as session:
-                    await session.initialize()
-                    result = await session.call_tool(tool, {})
-                    if result.isError:
-                        raise IngestError(
-                            f"MCP tool {tool!r} on {server_ref!r} returned an error result",
-                            code="mcp_tool_error",
-                        )
-                    return _body_from_content(result.content, tool=tool, server_ref=server_ref)
+            # The deadline is an anyio cancel scope, not `asyncio.wait_for`, and it wraps BOTH
+            # nested task groups (`stdio_client`, `ClientSession`) from the INSIDE. `wait_for`
+            # cancels from outside a structure anyio itself owns, and the two cancellation
+            # mechanisms do not compose: measured (2026-08-03), that mismatch surfaced as an
+            # `anyio.BrokenResourceError` wrapped in a `BaseExceptionGroup` — never a `TimeoutError`
+            # — because a background reader task lost its write end mid-teardown. anyio's own scope
+            # is what the task groups already coordinate cancellation through, so nesting inside it
+            # tears down cleanly and raises a plain `TimeoutError` at the `with` statement.
+            with anyio.fail_after(timeout_seconds):
+                params = StdioServerParameters(command=command, args=list(args), env=env)
+                async with stdio_client(params) as (read, write):
+                    async with ClientSession(read, write) as session:
+                        await session.initialize()
+                        result = await session.call_tool(tool, {})
+                        if result.isError:
+                            raise IngestError(
+                                f"MCP tool {tool!r} on {server_ref!r} returned an error result",
+                                code="mcp_tool_error",
+                            )
+                        return _body_from_content(result.content, tool=tool, server_ref=server_ref)
 
         try:
-            return asyncio.run(asyncio.wait_for(run(), timeout=timeout_seconds))
+            return asyncio.run(run())
+        except TimeoutError as exc:
+            raise IngestError(
+                f"MCP tool {tool!r} on {server_ref!r} did not respond within {timeout_seconds}s",
+                code="mcp_timeout",
+            ) from exc
         except BaseException as exc:  # noqa: BLE001 — re-raised unchanged unless we own it
             owned = _unwrap_ingest_error(exc)
             if owned is None:

tests/test_ingest_golden_mcp.py

@@ -120,6 +120,28 @@ def test_tool_error_reaches_the_caller_as_ingest_error(
     assert excinfo.value.code == "mcp_tool_error"
 
 
+def test_tool_timeout_reaches_the_caller_as_ingest_error(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    """A tool that outlives ``timeout_seconds`` must surface as a typed ``IngestError``.
+
+    ``asyncio.wait_for`` wraps ``run()`` — itself two nested anyio task groups
+    (``stdio_client``, ``ClientSession``). Only a REAL hanging server proves what the timeout
+    cancellation actually surfaces as: a canned-tool test never enters a task group and cannot
+    observe this at all (the same reason (x)'s ``mcp_tool_error`` unwrap needed a real subprocess).
+    RED until the timeout is caught and re-raised as an owned ``IngestError``.
+    """
+    script = _write_server(
+        tmp_path,
+        "import time\n@server.tool()\ndef cost_docs() -> str:\n    time.sleep(5)\n    return 'late'\n",
+    )
+    get = _transport(script, monkeypatch, timeout_seconds=0.2)
+
+    with pytest.raises(IngestError) as excinfo:
+        get(f"mcp+stdio://{_SERVER_REF}/cost_docs", None)
+    assert excinfo.value.code == "mcp_timeout"
+
+
 def test_missing_server_ref_fails_before_any_process_is_spawned(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None: