Files
dev-puppeteer/my-deepagent/tests/unit/test_pricing.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

230 lines
7.2 KiB
Python

"""Unit tests for src/my_deepagent/monitoring/pricing.py."""
from __future__ import annotations
import httpx
import pytest
import respx
from my_deepagent.errors import MyDeepAgentError
from my_deepagent.monitoring.pricing import (
ModelPrice,
PricingCache,
_parse_pricing_payload,
fetch_openrouter_pricing,
)
# ---------------------------------------------------------------------------
# _parse_pricing_payload
# ---------------------------------------------------------------------------
def test_parse_valid_payload_returns_model_prices() -> None:
data: dict[str, object] = {
"data": [
{
"id": "deepseek/deepseek-chat",
"pricing": {"prompt": "0.000001", "completion": "0.000002"},
"context_length": 32768,
},
{
"id": "anthropic/claude-sonnet",
"pricing": {"prompt": "0.000003", "completion": "0.000015"},
"context_length": 200000,
},
]
}
result = _parse_pricing_payload(data)
assert len(result) == 2
assert result[0].model == "deepseek/deepseek-chat"
assert result[0].input_per_1k_usd == pytest.approx(0.001)
assert result[0].output_per_1k_usd == pytest.approx(0.002)
assert result[0].context_length == 32768
assert result[1].model == "anthropic/claude-sonnet"
def test_parse_empty_data_list_returns_empty() -> None:
result = _parse_pricing_payload({"data": []})
assert result == []
def test_parse_data_is_not_list_returns_empty() -> None:
# data is a dict instead of list — malformed response
result = _parse_pricing_payload({"data": {"id": "bad"}})
assert result == []
def test_parse_missing_data_key_returns_empty() -> None:
result = _parse_pricing_payload({})
assert result == []
def test_parse_skips_entries_without_id() -> None:
data: dict[str, object] = {
"data": [
{"pricing": {"prompt": "0.000001", "completion": "0.000002"}, "context_length": 1000},
]
}
result = _parse_pricing_payload(data)
assert result == []
def test_parse_skips_entries_with_invalid_pricing_values() -> None:
data: dict[str, object] = {
"data": [
{
"id": "model/x",
"pricing": {"prompt": "not-a-number", "completion": "also-bad"},
"context_length": 1000,
}
]
}
result = _parse_pricing_payload(data)
assert result == []
def test_parse_handles_null_pricing_gracefully() -> None:
data: dict[str, object] = {
"data": [
{"id": "model/y", "pricing": None, "context_length": 0},
]
}
result = _parse_pricing_payload(data)
# pricing=None -> {} -> prompt/completion default to "0"
assert len(result) == 1
assert result[0].input_per_1k_usd == 0.0
assert result[0].output_per_1k_usd == 0.0
def test_parse_handles_missing_context_length() -> None:
data: dict[str, object] = {
"data": [
{"id": "model/z", "pricing": {"prompt": "0.000001", "completion": "0.000002"}},
]
}
result = _parse_pricing_payload(data)
assert len(result) == 1
assert result[0].context_length == 0
def test_parse_non_dict_entry_is_skipped() -> None:
data: dict[str, object] = {"data": ["not-a-dict", None]}
result = _parse_pricing_payload(data)
assert result == []
# ---------------------------------------------------------------------------
# PricingCache.compute_cost
# ---------------------------------------------------------------------------
def test_compute_cost_known_model() -> None:
cache = PricingCache()
cache.set(
[
ModelPrice(
model="deepseek/deepseek-chat",
input_per_1k_usd=0.001,
output_per_1k_usd=0.002,
context_length=32768,
)
]
)
cost = cache.compute_cost("deepseek/deepseek-chat", input_tokens=1000, output_tokens=500)
assert cost == pytest.approx(0.001 * 1.0 + 0.002 * 0.5)
def test_compute_cost_openrouter_prefix_stripped() -> None:
cache = PricingCache()
cache.set(
[
ModelPrice(
model="deepseek/deepseek-chat",
input_per_1k_usd=0.001,
output_per_1k_usd=0.002,
context_length=32768,
)
]
)
# Should strip "openrouter:" prefix when looking up
cost = cache.compute_cost(
"openrouter:deepseek/deepseek-chat", input_tokens=1000, output_tokens=0
)
assert cost == pytest.approx(0.001)
def test_compute_cost_unknown_model_returns_zero() -> None:
cache = PricingCache()
cost = cache.compute_cost("unknown/model", input_tokens=1000, output_tokens=1000)
assert cost == 0.0
def test_compute_cost_zero_tokens_returns_zero() -> None:
cache = PricingCache()
cache.set(
[ModelPrice(model="m/x", input_per_1k_usd=1.0, output_per_1k_usd=2.0, context_length=1000)]
)
assert cache.compute_cost("m/x", input_tokens=0, output_tokens=0) == 0.0
def test_pricing_cache_get_strips_openrouter_prefix() -> None:
cache = PricingCache()
cache.set(
[ModelPrice(model="a/b", input_per_1k_usd=0.5, output_per_1k_usd=1.0, context_length=0)]
)
assert cache.get("openrouter:a/b") is not None
assert cache.get("a/b") is not None
# ---------------------------------------------------------------------------
# fetch_openrouter_pricing (respx mock)
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_fetch_openrouter_pricing_success() -> None:
payload = {
"data": [
{
"id": "deepseek/deepseek-chat",
"pricing": {"prompt": "0.000001", "completion": "0.000002"},
"context_length": 64000,
}
]
}
with respx.mock:
respx.get("https://openrouter.ai/api/v1/models").mock(
return_value=httpx.Response(200, json=payload)
)
result = await fetch_openrouter_pricing(
api_key="sk-or-test", base_url="https://openrouter.ai/api/v1"
)
assert len(result) == 1
assert result[0].model == "deepseek/deepseek-chat"
@pytest.mark.asyncio
async def test_fetch_openrouter_pricing_http_error_raises_recoverable() -> None:
with respx.mock:
respx.get("https://openrouter.ai/api/v1/models").mock(
return_value=httpx.Response(401, json={"error": "unauthorized"})
)
with pytest.raises(MyDeepAgentError) as exc_info:
await fetch_openrouter_pricing(
api_key="bad-key", base_url="https://openrouter.ai/api/v1"
)
assert exc_info.value.code == "network_blip"
@pytest.mark.asyncio
async def test_fetch_openrouter_pricing_connect_error_raises_recoverable() -> None:
with respx.mock:
respx.get("https://openrouter.ai/api/v1/models").mock(
side_effect=httpx.ConnectError("connection refused")
)
with pytest.raises(MyDeepAgentError) as exc_info:
await fetch_openrouter_pricing(
api_key="sk-or-test", base_url="https://openrouter.ai/api/v1"
)
assert exc_info.value.code == "network_blip"