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>
This commit is contained in:
chungyeong
154
my-deepagent/tests/integration/test_cli_pricing.py
Normal file
154
my-deepagent/tests/integration/test_cli_pricing.py
Normal file
@@ -0,0 +1,154 @@
|
||||
"""Integration tests for `mydeepagent pricing` CLI command."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import tempfile
|
||||
from datetime import UTC, datetime
|
||||
from unittest.mock import patch
|
||||
|
||||
from typer.testing import CliRunner
|
||||
|
||||
from my_deepagent.cli.main import app
|
||||
from my_deepagent.persistence.db import Database
|
||||
from my_deepagent.persistence.models import ModelPricingRow
|
||||
|
||||
runner = CliRunner()
|
||||
|
||||
|
||||
def _now_iso() -> str:
|
||||
return datetime.now(UTC).isoformat(timespec="seconds")
|
||||
|
||||
|
||||
async def _seed_pricing_rows(db: Database, rows: list[dict[str, object]]) -> None:
|
||||
from sqlalchemy.dialects.sqlite import insert as sqlite_insert
|
||||
|
||||
async with db.session() as s:
|
||||
for r in rows:
|
||||
stmt = (
|
||||
sqlite_insert(ModelPricingRow)
|
||||
.values(**r)
|
||||
.on_conflict_do_update(
|
||||
index_elements=["model"],
|
||||
set_={
|
||||
"input_per_1k_usd": r["input_per_1k_usd"],
|
||||
"output_per_1k_usd": r["output_per_1k_usd"],
|
||||
"context_length": r["context_length"],
|
||||
"fetched_at": r["fetched_at"],
|
||||
},
|
||||
)
|
||||
)
|
||||
await s.execute(stmt)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Test 1: empty DB → "(no pricing data)" message
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_pricing_empty_db_shows_no_data() -> None:
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
db_url = f"sqlite+aiosqlite:///{tmpdir}/test.sqlite3"
|
||||
with patch("my_deepagent.cli.stats.load_config") as mock_cfg:
|
||||
cfg = mock_cfg.return_value
|
||||
cfg.database_url = db_url
|
||||
result = runner.invoke(app, ["pricing"])
|
||||
assert result.exit_code == 0, result.output
|
||||
assert "no pricing data" in result.output
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Test 2: with rows → table shown
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_pricing_with_data_shows_table() -> None:
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
db_url = f"sqlite+aiosqlite:///{tmpdir}/test.sqlite3"
|
||||
db = Database(db_url)
|
||||
|
||||
rows = [
|
||||
{
|
||||
"model": "anthropic/claude-haiku-4-5",
|
||||
"input_per_1k_usd": 1.0,
|
||||
"output_per_1k_usd": 5.0,
|
||||
"context_length": 200_000,
|
||||
"fetched_at": _now_iso(),
|
||||
"raw_payload": "",
|
||||
},
|
||||
{
|
||||
"model": "deepseek/deepseek-chat",
|
||||
"input_per_1k_usd": 0.28,
|
||||
"output_per_1k_usd": 1.12,
|
||||
"context_length": 64_000,
|
||||
"fetched_at": _now_iso(),
|
||||
"raw_payload": "",
|
||||
},
|
||||
]
|
||||
|
||||
async def _init_and_seed() -> None:
|
||||
await db.init_schema()
|
||||
await _seed_pricing_rows(db, rows)
|
||||
await db.dispose()
|
||||
|
||||
asyncio.run(_init_and_seed())
|
||||
|
||||
with patch("my_deepagent.cli.stats.load_config") as mock_cfg:
|
||||
cfg = mock_cfg.return_value
|
||||
cfg.database_url = db_url
|
||||
result = runner.invoke(app, ["pricing"])
|
||||
|
||||
assert result.exit_code == 0, result.output
|
||||
assert "anthropic/claude-haiku-4-5" in result.output
|
||||
assert "deepseek/deepseek-chat" in result.output
|
||||
assert "1.0000" in result.output
|
||||
assert "OpenRouter pricing" in result.output
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Test 3: models are sorted alphabetically
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_pricing_rows_sorted_alphabetically() -> None:
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
db_url = f"sqlite+aiosqlite:///{tmpdir}/test.sqlite3"
|
||||
db = Database(db_url)
|
||||
|
||||
rows = [
|
||||
{
|
||||
"model": "zzz/last-model",
|
||||
"input_per_1k_usd": 9.0,
|
||||
"output_per_1k_usd": 9.0,
|
||||
"context_length": 1000,
|
||||
"fetched_at": _now_iso(),
|
||||
"raw_payload": "",
|
||||
},
|
||||
{
|
||||
"model": "aaa/first-model",
|
||||
"input_per_1k_usd": 1.0,
|
||||
"output_per_1k_usd": 1.0,
|
||||
"context_length": 2000,
|
||||
"fetched_at": _now_iso(),
|
||||
"raw_payload": "",
|
||||
},
|
||||
]
|
||||
|
||||
async def _init_and_seed() -> None:
|
||||
await db.init_schema()
|
||||
await _seed_pricing_rows(db, rows)
|
||||
await db.dispose()
|
||||
|
||||
asyncio.run(_init_and_seed())
|
||||
|
||||
with patch("my_deepagent.cli.stats.load_config") as mock_cfg:
|
||||
cfg = mock_cfg.return_value
|
||||
cfg.database_url = db_url
|
||||
result = runner.invoke(app, ["pricing"])
|
||||
|
||||
assert result.exit_code == 0, result.output
|
||||
pos_first = result.output.find("aaa/first-model")
|
||||
pos_last = result.output.find("zzz/last-model")
|
||||
assert pos_first != -1
|
||||
assert pos_last != -1
|
||||
assert pos_first < pos_last, "aaa/first-model should appear before zzz/last-model"
|
||||
Reference in New Issue
Block a user