agentcheckup 0.4.0__tar.gz → 0.4.1__tar.gz

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/.github/workflows/publish.yml

@@ -13,10 +13,8 @@ name: Publish
 #     Environment       : pypi
 
 on:
-  # Re-enable the release trigger once the PyPI pending publisher exists:
-  #   on: release: types: [published]
-  # Until then a release would run this and fail with "environment: MISSING",
-  # which is noise on the repository home page.
+  release:
+    types: [published]
   workflow_dispatch:
 
 permissions:

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/CHANGELOG.md

@@ -9,6 +9,31 @@ new ids, and removing a rule is a breaking change.
 
 ## [Unreleased]
 
+## [0.4.1] - 2026-11-07
+
+Both fixes came out of an external fact-check of the project, not from a bug
+report: the repository has no users yet, so nothing surfaced them in the field.
+
+### Fixed
+
+- **`AGT105` was used by two unrelated rules.** "Server did not return a tool
+  list" (suite) and "Remote server uses plain HTTP" (config) shared the id, with
+  different severities. Rule ids are the tool's public API — people put them in
+  suppression lists — so two checks under one name is worse than either check
+  being wrong. The config rule is now `AGT108`; `AGT105` keeps the meaning every
+  document and the README already gave it.
+- **README pointed the GitHub Action at `@v0.3.0`**, a tag that no longer exists.
+  Anyone copying the snippet got a resolution failure. Now `@v0.4.1`.
+- `docs/rules.md` listed `AGT105` twice and described the suite rule as a
+  warning when it had been downgraded to info.
+
+### Added
+
+- `tests/test_registry.py`: ids are unique across all three registries, well
+  formed, and — for every rule that constructs its own `Finding` — the severity
+  emitted matches the severity registered. That last check is the one that would
+  have caught the duplicate before it shipped.
+
 ## [0.4.0] - 2026-11-07
 
 Calibration release, driven by the first run against real servers rather than

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: agentcheckup
-Version: 0.4.0
+Version: 0.4.1
 Summary: Diagnose your agent setup: tool conflicts, risky config, context budget.
 Project-URL: Homepage, https://github.com/wanjiaqing/agentcheckup
 Project-URL: Issues, https://github.com/wanjiaqing/agentcheckup/issues
@@ -149,7 +149,7 @@ The fastest way to keep a manifest from regressing, and the version you pin is
 the version you run — the action installs from its own checkout.
 
 ```yaml
-- uses: wanjiaqing/agentcheckup@v0.3.0
+- uses: wanjiaqing/agentcheckup@v0.4.1
   with:
     config: .mcp.json
     fail-on: warning

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/README.md

@@ -121,7 +121,7 @@ The fastest way to keep a manifest from regressing, and the version you pin is
 the version you run — the action installs from its own checkout.
 
 ```yaml
-- uses: wanjiaqing/agentcheckup@v0.3.0
+- uses: wanjiaqing/agentcheckup@v0.4.1
   with:
     config: .mcp.json
     fail-on: warning

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/docs/rules.md

@@ -163,9 +163,6 @@ also defeats the escaping the client already did.
 Granting the filesystem root gives the agent read-write access to everything. One
 prompt injection is then enough to reach SSH keys and browser profiles.
 
-### AGT105 · warning · Remote server uses plain HTTP
-Tool calls carry your data, often your credentials.
-
 ### AGT106 · error · Config passes a permission-bypass flag
 `--dangerously-skip-permissions`, `--yolo`, `--allow-all`, `--no-sandbox`. These
 disable the only confirmation step between the model and your disk.
@@ -174,11 +171,14 @@ disable the only confirmation step between the model and your disk.
 Config files get committed, screenshotted and pasted into issues. Reference an
 env var instead.
 
+### AGT108 · warning · Remote server uses plain HTTP
+Tool calls carry your data, often your credentials, over an unencrypted link.
+
 ### AGT105 · info · Server did not return a tool list
 The server failed to start, timed out, or is a remote `url` endpoint that cannot
 be introspected over stdio.
 
-This is a warning rather than an error on purpose: one broken server must not
+This is info rather than an error on purpose: one broken server must not
 stop you auditing the other four. But an unreachable server is also an unaudited
 one — its tools were never checked for conflicts.
 

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "agentcheckup"
-version = "0.4.0"
+version = "0.4.1"
 description = "Diagnose your agent setup: tool conflicts, risky config, context budget."
 readme = "README.md"
 requires-python = ">=3.10"

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/src/agentcheckup/report.py

@@ -10,7 +10,7 @@ from . import rules as _rules
 from .engine import Report
 from .models import Finding, Severity
 
-__version__ = "0.4.0"
+__version__ = "0.4.1"
 
 SARIF_LEVEL = {
     Severity.ERROR: "error",

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/src/agentcheckup/rules/config_rules.py

@@ -132,12 +132,12 @@ def broad_fs_root(server: ServerConfig):
     return None
 
 
-@config_rule("AGT105", Severity.WARNING, "Remote server uses plain HTTP")
+@config_rule("AGT108", Severity.WARNING, "Remote server uses plain HTTP")
 def insecure_url(server: ServerConfig):
     """Tool calls carry your data and often your credentials."""
     if server.url and server.url.lower().startswith("http://"):
         return Finding(
-            rule="AGT105",
+            rule="AGT108",
             severity=Severity.WARNING,
             message=f"Server {server.name!r} uses an unencrypted http:// endpoint.",
             tool=server.name,

agentcheckup-0.4.1/tests/test_registry.py

@@ -0,0 +1,77 @@
+"""Guards on the rule registry itself.
+
+Rule ids are the public API of this tool: people put them in suppression lists,
+CI thresholds and issue reports. A duplicate id silently gives two unrelated
+checks the same name, which is worse than either check being wrong.
+
+This file exists because that happened: `AGT105` was used for both "server did
+not return a tool list" (suite) and "remote server uses plain HTTP" (config).
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+import pytest
+
+from agentcheckup.rules import CONFIG_RULES, SUITE_RULES, TOOL_RULES
+
+SRC = Path(__file__).resolve().parents[1] / "src" / "agentcheckup"
+
+ALL_RULES = [*TOOL_RULES, *SUITE_RULES, *CONFIG_RULES]
+
+
+def test_rule_ids_are_unique():
+    ids = [rule.id for rule in ALL_RULES]
+    duplicates = {rule_id for rule_id in ids if ids.count(rule_id) > 1}
+    assert not duplicates, f"duplicate rule ids: {sorted(duplicates)}"
+
+
+def test_rule_ids_are_well_formed():
+    for rule in ALL_RULES:
+        assert re.fullmatch(r"AGT\d{3}", rule.id), rule.id
+
+
+def test_every_rule_has_a_title():
+    for rule in ALL_RULES:
+        assert rule.title.strip(), f"{rule.id} has no title"
+
+
+def test_no_rule_is_registered_twice_across_groups():
+    """A tool rule and a config rule must not share an id either."""
+    groups = {
+        "tool": {r.id for r in TOOL_RULES},
+        "suite": {r.id for r in SUITE_RULES},
+        "config": {r.id for r in CONFIG_RULES},
+    }
+    for a, left in groups.items():
+        for b, right in groups.items():
+            if a >= b:
+                continue
+            overlap = left & right
+            assert not overlap, f"{a} and {b} share {sorted(overlap)}"
+
+
+@pytest.mark.parametrize("rule", ALL_RULES, ids=lambda r: r.id)
+def test_emitted_severity_matches_the_registry(rule):
+    """Catch a rule whose Finding says WARNING while the registry says INFO.
+
+    Without this, a severity change in one place silently disagrees with the
+    other, and the report and the score stop matching the docs.
+    """
+    pattern = re.compile(
+        r'rule="' + re.escape(rule.id) + r'",\s*severity=Severity\.(\w+)'
+    )
+    emitted: set[str] = set()
+    for path in SRC.rglob("*.py"):
+        for match in pattern.finditer(path.read_text(encoding="utf-8")):
+            emitted.add(match.group(1))
+
+    if not emitted:
+        pytest.skip("severity is passed indirectly for this rule")
+
+    expected = rule.severity.name
+    assert emitted == {expected}, (
+        f"{rule.id} is registered as {expected} but emits {sorted(emitted)}"
+    )

{agentcheckup-0.4.0 → agentcheckup-0.4.1}/tests/test_rules.py

@@ -165,7 +165,7 @@ def test_invisible_characters_detected():
 def test_config_fixture_flags_expected_rules():
     report = lint_servers(servers_from_config(FIXTURES / "claude_desktop_config.json"))
     ids = rule_ids(report)
-    for expected in ("AGT101", "AGT103", "AGT104", "AGT105", "AGT106", "AGT107"):
+    for expected in ("AGT101", "AGT103", "AGT104", "AGT106", "AGT107", "AGT108"):
         assert expected in ids, f"{expected} did not fire; got {sorted(ids)}"