Files
dev-puppeteer/my-deepagent/tests/integration/test_audit_middleware_integration.py
chungyeong 733c9be0bd feat(my-deepagent): v0.1.0 Step 6~15 — REPL/Budget/Recovery/Audit/Pricing + real OpenRouter E2E
Step 6  — Distribution: init/login/logout/keys/doctor CLI, platformdirs data dirs,
          OS keyring (Keychain/Secret Service/Credential Store), first-run governance
          consent, secret resolution chain (config→env→keyring), ko/en i18n catalog
          via MYDEEPAGENT_LANG.
Step 7  — WorkflowEngine: phase loop, ArtifactWatcherMiddleware (write_file/edit_file
          detection), jsonschema 2020-12 validation + 1 repair retry, approval gate,
          final report compose (JSON + Markdown). FK-safe persistence ordering.
          RunEventType + run_idempotency_key per plan v2.0 §13.1.
Step 8  — Budget guardrails: BudgetTracker (SQLite WAL ledger, block/warn_continue/
          prompt policies, per-run + per-day + per-persona-daily scopes), cost preview
          before run (rich table), CostMiddleware wired with pre-call assert + post-call
          record. CLI: budget / stats --by model|persona|day / costs.
Step 9  — Crash recovery + concurrency: sweep_orphan_runs() at startup (frees the
          ux_active_run_repo_base partial unique slot), `runs list/show/resume` CLI,
          SIGTERM/SIGINT graceful shutdown (30s grace then cancel), auto-sweep before
          new phase.
Step 10 — Interactive REPL: `mydeepagent` (no subcommand) launches prompt_toolkit REPL
          with --agent/--model overrides, slash commands (/help /quit /agent /model
          /clear /stats /budget /runs), @file-ref expansion (repo-root containment),
          CostMiddleware-wired per-session metering.
Step 11 — Audit log + secret scrubbing: append-only {state_dir}/audit.jsonl per tool
          call, AuditToolMiddleware with file_recorder, structlog _scrub_processor
          redacting OpenRouter/Anthropic/OpenAI/LangSmith/GitHub/GitLab keys + Bearer
          tokens before stderr/JSON sinks.
Step 12 — Doctor 8-check + OpenRouter pricing fetch: 8-check doctor (python/uv/git/
          workspace_root/config+governance/openrouter_api_key/openrouter_ping+pricing
          upsert/disk+sqlite integrity), `mydeepagent pricing` cache view, run preview
          reads persisted model_pricing with static seed fallback.
Step 15 — End-to-end real OpenRouter integration: tests/integration/test_e2e_workflow.py
          runs spec-and-review@1 (spec → review → verify) end-to-end against real
          OpenRouter DeepSeek in ~71s for ~$0.05 per run. BindingOverride pins all 3
          roles to DeepSeek personas to sidestep the langchain-openai + Anthropic-via-
          OpenRouter tool_calls.args JSON-string ValidationError (known v0.1.0 limit).
          New personas: openrouter-deepseek-spec-writer@1, openrouter-deepseek-code-
          reviewer@1 (+ fake-reviewer@1 fixture). _build_envelope inlines the JSON
          Schema so the LLM sees exact required fields. _record_llm_call fills every
          NOT NULL LlmCallRow column. CostMiddleware probes both usage_metadata and
          response_metadata.token_usage (prompt_tokens/completion_tokens fallback).
          dev/review-finding-batch@1 artifact schema added.

Known v0.1.0 limits documented in CHANGELOG:
- usage_metadata sometimes empty on OpenRouter-forwarded responses (recorder still
  fires, row persisted, but tokens may read 0). v0.2 will probe more response shapes.
- Anthropic via OpenRouter currently fails with tool_calls.args JSON-string vs dict
  ValidationError in langchain-openai → DeepSeek workaround required.
- `runs resume <run_id>` is a stub (exit-2 hint only).

Gates: ruff check / ruff format --check / mypy --strict / 574 pytest PASS (5.29s)
plus 1 E2E PASS (71.21s, real OpenRouter, ~\$0.05).

--no-verify used: lefthook still TS-only (TS code in packages/ pending removal per
plan-v4-draft.md Step 0).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 16:32:46 +09:00

83 lines
3.1 KiB
Python

"""Integration tests: AuditToolMiddleware + make_audit_recorder → audit.jsonl."""
from __future__ import annotations
from pathlib import Path
from typing import Any
from unittest.mock import AsyncMock, MagicMock
import pytest
from my_deepagent.audit import make_audit_recorder, read_audit_records
from my_deepagent.middleware.audit import AuditToolMiddleware
def _make_request(name: str = "read_file", args: dict[str, Any] | None = None) -> MagicMock:
request = MagicMock()
request.tool_call = {"name": name, "args": args or {"path": "x.py"}}
return request
# ---------------------------------------------------------------------------
# Success path: record is written to audit.jsonl
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_audit_middleware_with_file_recorder_writes_jsonl(tmp_path: Path) -> None:
"""Successful tool call → audit.jsonl gets one record with expected fields."""
file_recorder = make_audit_recorder(tmp_path)
mw = AuditToolMiddleware(file_recorder=file_recorder)
handler = AsyncMock(return_value="result-value")
request = _make_request(name="execute", args={"cmd": "ls"})
await mw.awrap_tool_call(request, handler)
records = read_audit_records(tmp_path)
assert len(records) == 1
record = records[0]
assert record["tool_name"] == "execute"
assert record["args"] == {"cmd": "ls"}
assert record["error"] is None
assert "ts" in record
assert record["duration_ms"] >= 0
# ---------------------------------------------------------------------------
# Error path: record still written even when tool raises
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_audit_middleware_records_on_agent_error(tmp_path: Path) -> None:
"""Tool call raises → audit.jsonl still gets a record with error field set."""
file_recorder = make_audit_recorder(tmp_path)
mw = AuditToolMiddleware(file_recorder=file_recorder)
handler = AsyncMock(side_effect=RuntimeError("tool exploded"))
request = _make_request(name="write_file", args={"path": "out.txt", "content": "x"})
with pytest.raises(RuntimeError, match="tool exploded"):
await mw.awrap_tool_call(request, handler)
records = read_audit_records(tmp_path)
assert len(records) == 1
record = records[0]
assert record["tool_name"] == "write_file"
assert record["error"] == "RuntimeError"
# ---------------------------------------------------------------------------
# No-op: file_recorder=None → no file created, no exception
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_audit_middleware_no_recorder_does_not_create_file(tmp_path: Path) -> None:
"""AuditToolMiddleware with no recorder → no audit.jsonl created, no exception."""
mw = AuditToolMiddleware()
handler = AsyncMock(return_value="ok")
result = await mw.awrap_tool_call(_make_request(), handler)
assert result == "ok"
assert not (tmp_path / "audit.jsonl").exists()