Files
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

186 lines
7.0 KiB
Python

"""Unit tests for the my-deepagent CLI (typer CliRunner)."""
from __future__ import annotations
from pathlib import Path
import pytest
from typer.testing import CliRunner
import my_deepagent.keys as keys_module
from my_deepagent.cli.main import app
runner = CliRunner()
class _FakeKeyring:
def __init__(self) -> None:
self.store: dict[tuple[str, str], str] = {}
def get_password(self, service: str, username: str) -> str | None:
return self.store.get((service, username))
def set_password(self, service: str, username: str, value: str) -> None:
self.store[(service, username)] = value
def delete_password(self, service: str, username: str) -> None:
self.store.pop((service, username), None)
@pytest.fixture
def fake_keyring(monkeypatch: pytest.MonkeyPatch) -> _FakeKeyring:
fake = _FakeKeyring()
monkeypatch.setattr(keys_module.keyring, "get_password", fake.get_password)
monkeypatch.setattr(keys_module.keyring, "set_password", fake.set_password)
monkeypatch.setattr(keys_module.keyring, "delete_password", fake.delete_password)
return fake
def test_help_exit_zero() -> None:
result = runner.invoke(app, ["--help"])
assert result.exit_code == 0
assert "mydeepagent" in result.output.lower() or "Usage" in result.output
def test_no_subcommand_launches_repl_governance_check(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""Without governance consent, the REPL exits 1 with an error."""
import my_deepagent.governance as gov_module
monkeypatch.setattr(gov_module, "has_consent", lambda _: False)
result = runner.invoke(app, [])
# governance_not_accepted raises MyDeepAgentError which surfaces as exit 1
assert result.exit_code == 1
def test_doctor_exits_zero_normal_python(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
import sys
import my_deepagent.cli.doctor as doctor_module
# Ensure version is in valid range
monkeypatch.setattr(sys, "version_info", (3, 12, 0, "final", 0))
# Patch has_consent inside the doctor module's namespace
monkeypatch.setattr(doctor_module, "has_consent", lambda _: True)
# Stub out async checks so doctor finishes without real DB / network
monkeypatch.setattr(
doctor_module,
"_check_openrouter_api_key",
lambda cfg: doctor_module.CheckResult("openrouter_api_key", "warn", "mocked"),
)
async def _fake_ping(cfg: object) -> doctor_module.CheckResult:
return doctor_module.CheckResult("openrouter_ping", "warn", "mocked")
async def _fake_disk(cfg: object) -> doctor_module.CheckResult:
return doctor_module.CheckResult("disk+db", "ok", "free=99.9GB, sqlite_integrity=ok")
monkeypatch.setattr(doctor_module, "_check_openrouter_ping_and_upsert", _fake_ping)
monkeypatch.setattr(doctor_module, "_check_disk_and_db", _fake_disk)
result = runner.invoke(app, ["doctor"])
assert result.exit_code == 0
def test_doctor_exits_one_on_bad_python(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
import sys
monkeypatch.setattr(sys, "version_info", (3, 10, 0, "final", 0))
monkeypatch.setattr(sys, "version", "3.10.0 (default, ...)")
result = runner.invoke(app, ["doctor"])
assert result.exit_code == 1
def test_keys_empty_keyring(fake_keyring: _FakeKeyring) -> None:
result = runner.invoke(app, ["keys"])
assert result.exit_code == 0
# Should show "none" message (Korean or English)
assert "없음" in result.output or "none" in result.output.lower()
def test_login_stores_key(fake_keyring: _FakeKeyring) -> None:
result = runner.invoke(app, ["login", "openrouter"], input="sk-or-test-abc123\n")
assert result.exit_code == 0
assert fake_keyring.store.get(("my-deepagent", "openrouter_api_key")) == "sk-or-test-abc123"
def test_login_empty_input_exits_one(fake_keyring: _FakeKeyring) -> None:
result = runner.invoke(app, ["login", "openrouter"], input="\n")
assert result.exit_code == 1
def test_logout_after_login_removes_key(fake_keyring: _FakeKeyring) -> None:
runner.invoke(app, ["login", "openrouter"], input="sk-or-test\n")
result = runner.invoke(app, ["logout", "openrouter"])
assert result.exit_code == 0
assert fake_keyring.store.get(("my-deepagent", "openrouter_api_key")) is None
def test_logout_not_found_shows_message(fake_keyring: _FakeKeyring) -> None:
result = runner.invoke(app, ["logout", "openrouter"])
assert result.exit_code == 0
assert "keyring" in result.output or "없습니다" in result.output or "not_found" in result.output
def test_keys_shows_entry_after_login(fake_keyring: _FakeKeyring) -> None:
runner.invoke(app, ["login", "openrouter"], input="sk-or-v1-abcdefgh1234\n")
result = runner.invoke(app, ["keys"])
assert result.exit_code == 0
assert "openrouter" in result.output
assert "sk-or-v1" in result.output
def test_init_governance_declined_exits_one(
fake_keyring: _FakeKeyring, tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
import my_deepagent.governance as gov_module
monkeypatch.setattr(gov_module, "has_consent", lambda _: False)
# Input: decline governance
result = runner.invoke(app, ["init"], input="no\n")
assert result.exit_code == 1
def test_init_governance_accepted_saves_key(
fake_keyring: _FakeKeyring, tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
import sys
import my_deepagent.cli.doctor as doctor_module
import my_deepagent.cli.init as init_module
import my_deepagent.governance as gov_module
recorded: list[Path] = []
def fake_record_consent(data_dir: Path) -> None:
recorded.append(data_dir)
monkeypatch.setattr(gov_module, "has_consent", lambda _: False)
monkeypatch.setattr(init_module, "record_consent", fake_record_consent)
# Ensure Python version check passes
monkeypatch.setattr(sys, "version_info", (3, 12, 0, "final", 0))
# doctor_command() is called inside init — patch its async sub-checks so it
# completes without network / DB access and passes governance in doctor's namespace.
monkeypatch.setattr(doctor_module, "has_consent", lambda _: True)
monkeypatch.setattr(
doctor_module,
"_check_openrouter_api_key",
lambda cfg: doctor_module.CheckResult("openrouter_api_key", "warn", "mocked"),
)
async def _fake_ping(cfg: object) -> doctor_module.CheckResult:
return doctor_module.CheckResult("openrouter_ping", "warn", "mocked")
async def _fake_disk(cfg: object) -> doctor_module.CheckResult:
return doctor_module.CheckResult("disk+db", "ok", "free=99.9GB, sqlite_integrity=ok")
monkeypatch.setattr(doctor_module, "_check_openrouter_ping_and_upsert", _fake_ping)
monkeypatch.setattr(doctor_module, "_check_disk_and_db", _fake_disk)
# Input: accept governance, then provide API key
result = runner.invoke(app, ["init"], input="yes\nsk-or-init-test\n")
assert result.exit_code == 0
assert len(recorded) == 1
assert fake_keyring.store.get(("my-deepagent", "openrouter_api_key")) == "sk-or-init-test"