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

docs/llm-workflow-runbooks.md

@@ -312,6 +312,39 @@ Required behavior (fail closed, issue #258):
 
 Doc-contract tests: `tests/test_shell_spawn_hard_stop_docs.py`.
 
+## Subagent Tool-Budget Guardrails
+
+General-purpose subagents tasked with **deterministic MCP work** (for example a
+single `gitea_commit_files` call) have expanded to 100–122 tool calls,
+WebFetch/Playwright fallbacks, and throwaway helper-script generation instead of
+calling the native MCP tool once (observed during #152 closure, issue #259).
+
+**Default budgets** (fail closed when exceeded):
+
+| Task class | Max tool calls | Max wall time |
+|------------|----------------|---------------|
+| Single-step MCP mutation (`commit_files`, `create_pr`, `lock_issue`) | 15 | 5 minutes |
+| Review / merge queue inspection | 40 | 15 minutes |
+| Exploration / codebase search (non-mutating) | 60 | 20 minutes |
+
+**Required behavior:**
+
+1. **Main session first.** When the active author profile allows
+   `gitea.repo.commit` and `gitea_commit_files` is visible, the main session
+   must call it directly — do not delegate commit authority to a subagent
+   (see #260).
+2. **Native MCP before fallback.** After a shell spawn failure (#258), attempt
+   the native MCP tool once before any alternate path. Shell unavailability
+   never authorizes WebFetch, Playwright, or manual base64 encoding.
+3. **No retry spirals.** Never resume a failed subagent into a larger retry
+   loop or spawn a second subagent for the same deterministic step. Stop and
+   emit a recovery report instead.
+4. **Forbidden detours** when `gitea_commit_files` is available: WebFetch,
+   Playwright/browser automation, manual LLM-generated base64, and ad-hoc
+   `_encode_*` / `_emit_*` helper scripts left in the repo.
+
+Doc-contract tests: `tests/test_subagent_tool_budget_docs.py`.
+
 ## Branch worktree isolation
 
 All LLM implementation and review work happens in an isolated branch worktree

gitea_mcp_server.py

@@ -3874,6 +3874,16 @@ _GUIDE_RULES = {
         "paths (e.g. gitea_commit_files) for remaining mutations. Shell "
         "unavailability never authorizes WebFetch/browser/manual-encoding "
         "fallbacks (#258)."),
+    "subagent_tool_budget": (
+        "General-purpose subagents on deterministic MCP tasks must stay within "
+        "budget: single-step mutations (commit_files, create_pr, lock_issue) "
+        "max 15 tool calls / 5 min; review/merge queue inspection max 40 / "
+        "15 min. The main session with gitea.repo.commit must call "
+        "gitea_commit_files directly — no subagent delegation (#260). After "
+        "shell spawn failure (#258), attempt native MCP once; never authorize "
+        "WebFetch/Playwright/manual base64 when gitea_commit_files is "
+        "available. Never resume a failed subagent into a larger retry loop "
+        "(#259)."),
     "subagent_delegation": (
         "Deterministic write workflows (issue claim, branch creation, code "
         "edits, commits, PR creation, review, merge, cleanup) run inline in "

skills/llm-project-workflow/SKILL.md

@@ -106,6 +106,31 @@ Implementation: `(fix|feat|docs|chore)/issue-<number>-<short-description>`
 
 Review: `review/pr-<number>-<short-description>`
 
+## Subagent Tool-Budget Guardrails
+
+General-purpose subagents on **single-step MCP tasks** (for example
+`gitea_commit_files`) must not expand into 100+ tool-call retry spirals with
+WebFetch/Playwright/manual-encoding fallbacks (issue #259).
+
+Default budgets (stop when exceeded):
+
+- **Single-step MCP mutation** (`commit_files`, `create_pr`, `lock_issue`):
+  15 tool calls, 5 minutes wall time.
+- **Review / merge queue inspection**: 40 tool calls, 15 minutes.
+- **Non-mutating exploration**: 60 tool calls, 20 minutes.
+
+Rules:
+
+1. When the main session has `gitea.repo.commit`, call `gitea_commit_files`
+   directly — do not delegate commit to a subagent (#260).
+2. After shell spawn failure (#258), attempt the native MCP tool once before
+   any fallback; shell unavailability never authorizes WebFetch/Playwright/
+   manual base64.
+3. Never resume a failed subagent into a larger retry loop or spawn a second
+   subagent for the same deterministic step — stop and report.
+4. When `gitea_commit_files` is available, forbid WebFetch, Playwright,
+   manual encoding, and ad-hoc `_encode_*` / `_emit_*` helpers in the repo.
+
 Worktree folder: branch with `/` replaced by `-` under `branches/`.
 
 Helpers: `scripts/worktree-start`, `scripts/worktree-review`,

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}"