deer-flow/backend/tests/test_agent_guidance_check.py
Jason Cat 8834a759b8
fix(groundroute): contain malformed web search and fetch payloads (#6603)
* fix(groundroute): contain malformed web search and fetch payloads

web_search and web_fetch assumed the GroundRoute 200 body was an object with
a `results` list of objects, and read it outside the request try/except. A
body that arrived as a bare list, as an object with a non-list `results`, or
with non-object entries raised AttributeError / KeyError out of the tool
boundary, so the tool call failed with a stack trace instead of the provider's
format error.

Validate the payload before normalizing it, following the containment rule
already applied to brave (#6550), serper, serply, sofya, tencent_wsa and
unbrowse: a non-object payload, a non-list `results` container, or a non-empty
list holding no objects returns the structured format error, non-object entries
in an otherwise valid list are skipped in order, and missing, null or empty
results keep returning "No results found".

* fix(groundroute): coerce non-string fetch fields

web_fetch sliced the fetched page's `content` (falling back to `snippet`)
to the snippet limit without checking its type, so a 200 body whose result
object held a number, boolean, or object there raised TypeError / KeyError
out of the tool boundary -- the same escape the previous commit closed for
the container shape. A null title also rendered as "# None".

Coerce non-string content to text before truncating, and render a missing
or non-string title as empty, matching the coercion sofya and unbrowse
already apply to their fetch fields.

* docs(groundroute): scope the falsy-title note to actual behavior

The guidance said a non-string title renders as empty, but the code only
empties falsy titles; a truthy non-string title still renders as its text
form via the f-string. Say "falsy" instead.
2026-10-10 16:56:42 +08:00

211 lines
9.0 KiB
Python

from __future__ import annotations
import importlib.util
from pathlib import Path, PurePosixPath
import pytest
REPO_ROOT = Path(__file__).resolve().parents[2]
CHECKER_PATH = REPO_ROOT / "scripts" / "check_agent_guidance.py"
EXPECTED_GUIDANCE_PATHS = {
"AGENTS.md",
"backend/AGENTS.md",
"backend/tests/AGENTS.md",
"frontend/AGENTS.md",
"backend/app/gateway/AGENTS.md",
"backend/app/gateway/routers/AGENTS.md",
"backend/app/channels/AGENTS.md",
"backend/packages/harness/deerflow/AGENTS.md",
"backend/packages/harness/deerflow/agents/AGENTS.md",
"backend/packages/harness/deerflow/agents/middlewares/AGENTS.md",
"backend/packages/harness/deerflow/agents/memory/AGENTS.md",
"backend/packages/harness/deerflow/agents/task_continuity/AGENTS.md",
"backend/packages/harness/deerflow/community/brave/AGENTS.md",
"backend/packages/harness/deerflow/community/groundroute/AGENTS.md",
"backend/packages/harness/deerflow/community/jina_ai/AGENTS.md",
"backend/packages/harness/deerflow/community/ragflow/AGENTS.md",
"backend/packages/harness/deerflow/community/serper/AGENTS.md",
"backend/packages/harness/deerflow/community/tavily/AGENTS.md",
"backend/packages/harness/deerflow/community/e2b_sandbox/AGENTS.md",
"backend/packages/harness/deerflow/community/aio_sandbox/AGENTS.md",
"backend/packages/harness/deerflow/config/AGENTS.md",
"backend/packages/harness/deerflow/extensions/AGENTS.md",
"backend/packages/harness/deerflow/runtime/AGENTS.md",
"backend/packages/harness/deerflow/sandbox/AGENTS.md",
"backend/packages/harness/deerflow/mcp/AGENTS.md",
"backend/packages/harness/deerflow/models/AGENTS.md",
"backend/packages/harness/deerflow/persistence/AGENTS.md",
"backend/packages/harness/deerflow/persistence/migrations/AGENTS.md",
"backend/packages/harness/deerflow/persistence/user/AGENTS.md",
"backend/packages/harness/deerflow/reflection/AGENTS.md",
"backend/packages/harness/deerflow/skills/AGENTS.md",
"backend/packages/harness/deerflow/storage/AGENTS.md",
"backend/packages/harness/deerflow/subagents/AGENTS.md",
"backend/packages/harness/deerflow/tools/AGENTS.md",
"backend/packages/harness/deerflow/tracing/AGENTS.md",
"backend/packages/harness/deerflow/tui/AGENTS.md",
"backend/packages/harness/deerflow/typesafe/AGENTS.md",
"backend/packages/harness/deerflow/uploads/AGENTS.md",
"backend/packages/harness/deerflow/utils/AGENTS.md",
"frontend/src/AGENTS.md",
"scripts/AGENTS.md",
"examples/deerflow-extension-agent-teams/AGENTS.md",
}
def _load_checker():
assert CHECKER_PATH.exists(), f"{CHECKER_PATH} must exist"
spec = importlib.util.spec_from_file_location("deerflow_agent_guidance_check", CHECKER_PATH)
assert spec is not None
assert spec.loader is not None
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return module
checker = _load_checker()
def _files(**overrides: str) -> dict[PurePosixPath, str]:
files = {PurePosixPath("AGENTS.md"): "# Repository instructions\n"}
files.update({PurePosixPath(path): text for path, text in overrides.items()})
return files
def _codes(findings, severity: str | None = None) -> list[str]:
return [finding.code for finding in findings if severity is None or finding.severity == severity]
def test_normalized_utf8_size_uses_lf_and_counts_non_ascii_bytes() -> None:
assert checker.normalized_utf8_size("a\r\n中\r") == len("a\n中\n".encode())
@pytest.mark.parametrize(
("path", "soft", "hard"),
[
("AGENTS.md", 16 * 1024, 20 * 1024),
("backend/AGENTS.md", 28 * 1024, 32 * 1024),
("backend/app/gateway/AGENTS.md", 40 * 1024, 48 * 1024),
],
)
def test_budget_depends_on_directory_level(path: str, soft: int, hard: int) -> None:
assert checker.agent_budget(PurePosixPath(path)) == (soft, hard)
def test_single_file_over_hard_limit_is_an_error(tmp_path: Path) -> None:
findings = checker.analyze(tmp_path, _files(**{"AGENTS.md": "x" * (20 * 1024 + 1)}))
assert "AG001" in _codes(findings, "error")
def test_effective_ancestor_chain_can_fail_when_each_file_is_valid(tmp_path: Path) -> None:
files = _files(
**{
"AGENTS.md": "r" * (15 * 1024),
"backend/AGENTS.md": "m" * (31 * 1024),
"backend/app/AGENTS.md": "l" * (47 * 1024),
"backend/app/gateway/AGENTS.md": "g" * (47 * 1024),
}
)
findings = checker.analyze(tmp_path, files)
assert "AG001" not in _codes(findings, "error")
assert "AG002" in _codes(findings, "error")
def test_legacy_hard_violation_may_shrink_but_may_not_grow(tmp_path: Path) -> None:
base = _files(**{"AGENTS.md": "x" * (20 * 1024)})
smaller = _files(**{"AGENTS.md": "x" * (20 * 1024 - 1)})
grown = _files(**{"AGENTS.md": "x" * (20 * 1024 + 1)})
smaller_findings = checker.analyze(tmp_path, smaller, base_files=base)
grown_findings = checker.analyze(tmp_path, grown, base_files=base)
assert "AG001" not in _codes(smaller_findings, "error")
assert "AG001" in _codes(grown_findings, "error")
def test_discovery_uses_exact_agents_basename() -> None:
paths = [
PurePosixPath("AGENTS.md"),
PurePosixPath("backend/AGENTS.md"),
PurePosixPath("backend/CLAUDE.md"),
PurePosixPath("backend/docs/GITHUB_AGENTS.md"),
]
assert checker.guidance_paths(paths) == {
PurePosixPath("AGENTS.md"),
PurePosixPath("backend/AGENTS.md"),
}
def test_repository_has_the_approved_scoped_guidance_shape() -> None:
actual = {path.as_posix() for path in checker.guidance_paths(checker._worktree_paths(REPO_ROOT))}
assert actual == EXPECTED_GUIDANCE_PATHS
def test_repository_guidance_stays_below_hard_budgets_and_avoids_doc_indexes() -> None:
for relative_text in EXPECTED_GUIDANCE_PATHS:
relative = PurePosixPath(relative_text)
path = REPO_ROOT / relative_text
assert path.is_file(), relative
_, hard = checker.agent_budget(relative)
text = path.read_text(encoding="utf-8")
assert checker.normalized_utf8_size(text) <= hard, relative
assert "Subsystem Index" not in text
def test_local_guidance_files_contain_the_split_original_sections() -> None:
expected_headings = {
"backend/app/gateway/AGENTS.md": "### Gateway API (`app/gateway/`)",
"backend/app/channels/AGENTS.md": "### IM Channels System (`app/channels/`)",
"backend/packages/harness/deerflow/agents/AGENTS.md": "### Agent System",
"backend/packages/harness/deerflow/agents/middlewares/AGENTS.md": "### Middleware Chain",
"backend/packages/harness/deerflow/agents/memory/AGENTS.md": "### Memory System",
"backend/packages/harness/deerflow/config/AGENTS.md": "### Configuration System",
"backend/packages/harness/deerflow/extensions/AGENTS.md": "### Python Extension System",
"backend/packages/harness/deerflow/runtime/AGENTS.md": "### Checkpoint Channel Modes",
"backend/packages/harness/deerflow/sandbox/AGENTS.md": "### Sandbox System",
"backend/packages/harness/deerflow/mcp/AGENTS.md": "### MCP System",
"backend/packages/harness/deerflow/models/AGENTS.md": "### Model Factory",
"backend/packages/harness/deerflow/persistence/migrations/AGENTS.md": "### Schema Migrations",
"backend/packages/harness/deerflow/reflection/AGENTS.md": "### Reflection System",
"backend/packages/harness/deerflow/skills/AGENTS.md": "### Skills System",
"backend/packages/harness/deerflow/subagents/AGENTS.md": "### Subagent System",
"backend/packages/harness/deerflow/tools/AGENTS.md": "### Tool System",
"backend/packages/harness/deerflow/tracing/AGENTS.md": "### Tracing System",
"backend/packages/harness/deerflow/tui/AGENTS.md": "### Terminal Workbench / TUI",
"frontend/src/AGENTS.md": "### Data Flow",
}
for relative_text, heading in expected_headings.items():
text = (REPO_ROOT / relative_text).read_text(encoding="utf-8")
assert heading in text, relative_text
assert "Before changing files in this directory" not in text, relative_text
def test_mcp_task_lease_token_migration_is_documented() -> None:
guidance = (REPO_ROOT / "backend" / "packages" / "harness" / "deerflow" / "persistence" / "migrations" / "AGENTS.md").read_text(encoding="utf-8")
for required in (
"0026_mcp_task_lease_tokens.py",
"0016_subagent_batches",
"lease_token",
"notification_lease_token",
):
assert required in guidance
def test_repository_exposes_one_local_and_one_ci_entrypoint() -> None:
makefile = (REPO_ROOT / "Makefile").read_text(encoding="utf-8")
workflow = (REPO_ROOT / ".github" / "workflows" / "lint-check.yml").read_text(encoding="utf-8")
assert "check-agent-guidance:" in makefile
assert "scripts/check_agent_guidance.py" in makefile
assert workflow.count("agent-guidance:") == 1
assert "fetch-depth: 0" in workflow
assert "--base-ref" in workflow
assert "--before" in workflow