test: sweep every tool through the MCP server against a seeded Gitea

tests/integration/test_sweep.py

@@ -0,0 +1,54 @@
+"""The sweep: every tool is called at least once through the MCP server."""
+
+from __future__ import annotations
+
+import pytest
+
+from aegis_gitea_mcp.catalog import load_catalog
+from tests.integration.conftest import McpSession, RegularUser
+from tests.integration.harness import GiteaInstance
+from tests.integration.sweep_plan import (
+    EXCLUDED,
+    LOG,
+    RAW_TOOL,
+    failing,
+    load_spec,
+    run_sweep,
+    summarize,
+)
+from tests.integration.sweep_seed import Ctx, seed
+
+#: At least this share of the tools must get a real 2xx, so a systematic argument problem
+#: cannot hide behind documented 404 responses.
+MIN_SUCCESS_SHARE = 0.55
+
+
+@pytest.fixture(scope="module")
+def sweep_context(gitea: GiteaInstance, regular_user: RegularUser) -> Ctx:
+    """The seeded resources the sweep's arguments point at."""
+    return seed(gitea, regular_user.login, regular_user.token)
+
+
+async def test_every_tool_reaches_gitea(mcp: McpSession, sweep_context: Ctx) -> None:
+    catalog = load_catalog()
+    listed = {tool.name for tool in (await mcp.client.list_tools()).tools}
+    expected = {op.tool_name for op in catalog.operations} | {RAW_TOOL}
+    assert listed == expected
+    assert len(expected) == 538
+
+    records = await run_sweep(mcp.call, catalog, load_spec(), sweep_context)
+    LOG.sweep = records
+
+    called = [record.tool for record in records]
+    assert len(called) == len(set(called)), "a tool was called twice"
+    assert set(called) == expected - set(EXCLUDED), "tools missing from the sweep"
+
+    bad = failing(records)
+    summary = summarize(records)
+    report = "\n".join(
+        f"  {r.tool}: status={r.status} kind={r.kind} {r.method} {r.path} :: {r.message}"
+        for r in bad
+    )
+    assert not bad, f"{len(bad)} tool(s) with an unexpected result ({summary}):\n{report}"
+    success_share = summary.get("success", 0) / len(records)
+    assert success_share >= MIN_SUCCESS_SHARE, f"only {success_share:.0%} of tools got a 2xx"