Merge pull request 'docs: add subagent tool-budget guardrails for MCP tasks (Closes #259)' (#284) from docs/issue-259-subagent-tool-budget into master

tests/test_operator_guide.py

@@ -134,7 +134,8 @@ class TestControlPlaneGuide(GuideTestBase):
                     "merge_confirmation", "redaction", "separation",
                     "profile_switching", "identity_verification",
                     "work_selection", "global_worktree",
-                    "shell_spawn_hard_stop"):
+                    "shell_spawn_hard_stop", "subagent_tool_budget",
+                    "subagent_delegation"):
             self.assertIn(key, rules)
         self.assertIn("MERGE PR", json.dumps(rules["merge_confirmation"]))
         self.assertTrue(rules["hard_stops"])

tests/test_subagent_tool_budget_docs.py

@@ -0,0 +1,89 @@
+"""Doc-contract checks for subagent tool-budget guardrails (#259).
+
+Single-step MCP tasks must not expand into 100+ tool-call retry spirals with
+WebFetch/Playwright/manual-encoding fallbacks. These tests pin budget defaults,
+native-MCP-first rules, and forbidden detours in the runbooks, portable skill,
+and operator guide.
+"""
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+
+RUNBOOK = REPO_ROOT / "docs" / "llm-workflow-runbooks.md"
+SKILL = REPO_ROOT / "skills" / "llm-project-workflow" / "SKILL.md"
+
+
+def _normalize(text: str) -> str:
+    """Collapse whitespace so phrase checks survive markdown line wrapping."""
+    return " ".join(text.split())
+
+
+def _runbook_text() -> str:
+    return _normalize(RUNBOOK.read_text(encoding="utf-8"))
+
+
+def _skill_text() -> str:
+    return _normalize(SKILL.read_text(encoding="utf-8"))
+
+
+def test_runbook_has_subagent_tool_budget_section():
+    text = _runbook_text()
+    assert "## Subagent Tool-Budget Guardrails" in text
+    for phrase in (
+        "15",
+        "5 minutes",
+        "40",
+        "15 minutes",
+        "gitea_commit_files",
+        "WebFetch",
+        "Playwright",
+        "no retry spirals",
+    ):
+        assert phrase.lower() in text.lower(), f"runbook missing phrase: {phrase!r}"
+
+
+def test_runbook_forbids_subagent_commit_delegation():
+    text = _runbook_text()
+    for phrase in (
+        "do not delegate commit authority to a subagent",
+        "main session first",
+        "native MCP before fallback",
+    ):
+        assert phrase.lower() in text.lower(), f"runbook missing: {phrase!r}"
+
+
+def test_runbook_rejects_fallback_detours_when_mcp_commit_available():
+    lower = _runbook_text().lower()
+    for forbidden in ("webfetch", "playwright", "manual llm-generated base64"):
+        assert forbidden in lower, f"runbook must name forbidden detour: {forbidden!r}"
+    assert "_encode_" in lower
+    assert "gitea_commit_files" in lower
+
+
+def test_skill_doc_declares_subagent_tool_budget_guardrails():
+    text = _skill_text()
+    assert "## Subagent Tool-Budget Guardrails" in text
+    for phrase in (
+        "15 tool calls",
+        "5 minutes",
+        "gitea_commit_files",
+        "WebFetch",
+        "never resume a failed subagent",
+    ):
+        assert phrase.lower() in text.lower(), f"SKILL.md missing phrase: {phrase!r}"
+
+
+def test_operator_guide_rules_include_subagent_tool_budget():
+    import sys
+
+    sys.path.insert(0, str(REPO_ROOT))
+    import gitea_mcp_server
+
+    rule = gitea_mcp_server._GUIDE_RULES["subagent_tool_budget"]
+    for phrase in (
+        "15 tool calls",
+        "gitea_commit_files",
+        "WebFetch",
+        "retry loop",
+    ):
+        assert phrase in rule, f"operator guide rule missing: {phrase!r}"