Files
dev-puppeteer/my-deepagent/tests/integration/test_cli_interactive.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

92 lines
2.8 KiB
Python

"""Integration tests for the interactive REPL CLI entry point."""
from __future__ import annotations
from typing import Any
import pytest
from typer.testing import CliRunner
from my_deepagent.cli.main import app
runner = CliRunner()
def test_help_shows_agent_and_model_options() -> None:
"""--help must list --agent and --model options."""
result = runner.invoke(app, ["--help"])
assert result.exit_code == 0
assert "--agent" in result.output
assert "--model" in result.output
def test_no_subcommand_governance_not_accepted_exits_nonzero(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""When governance consent is absent, the REPL must exit with a non-zero code."""
import my_deepagent.governance as gov_module
monkeypatch.setattr(gov_module, "has_consent", lambda _: False)
result = runner.invoke(app, [])
assert result.exit_code != 0
def test_quit_exits_repl(monkeypatch: pytest.MonkeyPatch, tmp_path: Any) -> None:
"""REPL launched with mocked PromptSession should exit 0 on /quit."""
import my_deepagent.governance as gov_module
import my_deepagent.persona as persona_module
from my_deepagent.enums import Backend, Capability, RiskLevel
from my_deepagent.persona import Persona
# Patch governance to skip consent check
monkeypatch.setattr(gov_module, "has_consent", lambda _: True)
# Build a minimal fake persona with all required fields
fake_persona = Persona(
name="default-interactive",
version=1,
description="test",
backend=Backend.OPENROUTER,
model="openrouter:deepseek/deepseek-chat",
provider_origin="openrouter",
capabilities=(Capability.CODE_EDIT,),
max_risk_level=RiskLevel.LOW,
system_prompt="You are a helpful assistant.",
model_params={},
permissions=(),
subagents=(),
deepagents_backend="state",
)
monkeypatch.setattr(persona_module, "load_personas_from_dir", lambda _: [fake_persona])
# Patch PromptSession to yield "/quit" then raise EOFError
prompt_responses = ["/quit"]
call_count = 0
async def fake_prompt_async(*args: Any, **kwargs: Any) -> str:
nonlocal call_count
if call_count < len(prompt_responses):
resp = prompt_responses[call_count]
call_count += 1
return resp
raise EOFError
from prompt_toolkit import PromptSession
monkeypatch.setattr(PromptSession, "prompt_async", fake_prompt_async)
# Patch Database to avoid real DB I/O
from my_deepagent.persistence import db as db_module
class FakeDB:
async def init_schema(self) -> None:
pass
async def dispose(self) -> None:
pass
monkeypatch.setattr(db_module, "Database", lambda url: FakeDB())
result = runner.invoke(app, [])
assert result.exit_code == 0