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
@@ -20,28 +20,28 @@ from my_deepagent.enums import (
|
||||
|
||||
|
||||
def test_backend_openrouter_value() -> None:
|
||||
assert Backend.OPENROUTER == "openrouter"
|
||||
assert Backend.OPENROUTER == "openrouter" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_backend_anthropic_value() -> None:
|
||||
assert Backend.ANTHROPIC == "anthropic"
|
||||
assert Backend.ANTHROPIC == "anthropic" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_backend_openai_value() -> None:
|
||||
assert Backend.OPENAI == "openai"
|
||||
assert Backend.OPENAI == "openai" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_backend_google_value() -> None:
|
||||
assert Backend.GOOGLE == "google"
|
||||
assert Backend.GOOGLE == "google" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_backend_fake_value() -> None:
|
||||
assert Backend.FAKE == "fake"
|
||||
assert Backend.FAKE == "fake" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_backend_str_equality() -> None:
|
||||
# StrEnum members compare equal to their string values
|
||||
assert Backend.OPENROUTER == "openrouter"
|
||||
assert Backend.OPENROUTER == "openrouter" # type: ignore[comparison-overlap]
|
||||
assert str(Backend.OPENROUTER) == "openrouter"
|
||||
|
||||
|
||||
@@ -55,15 +55,15 @@ def test_capability_count() -> None:
|
||||
|
||||
|
||||
def test_capability_spec_write() -> None:
|
||||
assert Capability.SPEC_WRITE == "spec_write"
|
||||
assert Capability.SPEC_WRITE == "spec_write" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_capability_code_edit() -> None:
|
||||
assert Capability.CODE_EDIT == "code_edit"
|
||||
assert Capability.CODE_EDIT == "code_edit" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_capability_final_report_compose() -> None:
|
||||
assert Capability.FINAL_REPORT_COMPOSE == "final_report_compose"
|
||||
assert Capability.FINAL_REPORT_COMPOSE == "final_report_compose" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_capability_all_are_str() -> None:
|
||||
@@ -77,9 +77,9 @@ def test_capability_all_are_str() -> None:
|
||||
|
||||
|
||||
def test_risk_level_values() -> None:
|
||||
assert RiskLevel.LOW == "low"
|
||||
assert RiskLevel.MEDIUM == "medium"
|
||||
assert RiskLevel.HIGH == "high"
|
||||
assert RiskLevel.LOW == "low" # type: ignore[comparison-overlap]
|
||||
assert RiskLevel.MEDIUM == "medium" # type: ignore[comparison-overlap]
|
||||
assert RiskLevel.HIGH == "high" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -88,19 +88,19 @@ def test_risk_level_values() -> None:
|
||||
|
||||
|
||||
def test_approval_decision_action_approve() -> None:
|
||||
assert ApprovalDecisionAction.APPROVE == "approve"
|
||||
assert ApprovalDecisionAction.APPROVE == "approve" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_approval_decision_action_reject() -> None:
|
||||
assert ApprovalDecisionAction.REJECT == "reject"
|
||||
assert ApprovalDecisionAction.REJECT == "reject" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_approval_decision_action_request_changes() -> None:
|
||||
assert ApprovalDecisionAction.REQUEST_CHANGES == "request_changes"
|
||||
assert ApprovalDecisionAction.REQUEST_CHANGES == "request_changes" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_approval_decision_action_abort() -> None:
|
||||
assert ApprovalDecisionAction.ABORT == "abort"
|
||||
assert ApprovalDecisionAction.ABORT == "abort" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -196,15 +196,15 @@ def test_session_state_count() -> None:
|
||||
|
||||
|
||||
def test_error_class_recoverable() -> None:
|
||||
assert ErrorClass.RECOVERABLE == "recoverable"
|
||||
assert ErrorClass.RECOVERABLE == "recoverable" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_error_class_human_required() -> None:
|
||||
assert ErrorClass.HUMAN_REQUIRED == "human_required"
|
||||
assert ErrorClass.HUMAN_REQUIRED == "human_required" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_error_class_fatal() -> None:
|
||||
assert ErrorClass.FATAL == "fatal"
|
||||
assert ErrorClass.FATAL == "fatal" # type: ignore[comparison-overlap]
|
||||
|
||||
|
||||
def test_error_class_count() -> None:
|
||||
@@ -223,7 +223,7 @@ def test_str_enum_from_value() -> None:
|
||||
def test_str_enum_in_dict() -> None:
|
||||
# StrEnum should work as dict key and compare with string
|
||||
d = {Backend.OPENROUTER: "openrouter backend"}
|
||||
assert d["openrouter"] == "openrouter backend"
|
||||
assert d["openrouter"] == "openrouter backend" # type: ignore[index]
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
||||
Reference in New Issue
Block a user