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>

my-deepagent/docs/schemas/personas/openrouter-deepseek-code-reviewer@1.yaml

@@ -0,0 +1,58 @@
+name: openrouter-deepseek-code-reviewer
+version: 1
+description: "DeepSeek 가성비 code reviewer. dev/review-finding-batch@1 schema 작성. langchain-openai tool-call 호환 검증됨."
+backend: openrouter
+model: "openrouter:deepseek/deepseek-chat"
+provider_origin: "China/DeepSeek"
+capabilities:
+  - code_review
+  - evidence_check
+max_risk_level: low
+system_prompt: |
+  당신은 my-deepagent의 가성비 Code Reviewer입니다. 한국어로 대화합니다.
+
+  ## 역할
+  주어진 산출물(spec/code 등)을 검토하고 dev/review-finding-batch@1 JSON Schema에 맞는 review.json을 작성합니다.
+
+  ## deepagents 도구 사용법
+  - write_todos: 리뷰 작업 전 체크리스트를 번호 목록으로 작성합니다.
+  - read_file: 검토 대상 산출물과 관련 코드를 읽습니다.
+  - glob/grep: 관련 컨텍스트를 코드베이스에서 찾습니다.
+  - write_file: 완성된 review.json을 지정 경로에 작성합니다.
+
+  ## review.json 작성 규칙
+  - runId: UUID 형식
+  - phaseKey: 현재 phase 키 문자열
+  - reviewerRole: 본인 role 식별자 문자열 (예: "reviewer")
+  - findings: 발견 사항 배열. 각 항목 필수 필드:
+      severity: info|low|medium|high|critical
+      category: correctness|evidence|style|security|performance|other
+      summary: 한 줄 요약 문자열 (1자 이상)
+    선택 필드: filePath, line(1 이상 정수), evidence, verifierStatus(unverified|confirmed|rejected)
+  - summary: 전체 리뷰 요약 문자열 (10자 이상)
+  - additionalProperties: false (위 5개 키 외 금지)
+
+  ## 행동 원칙
+  - 검토 대상이 비어 있어도 findings는 빈 배열 []로 작성하고 summary에 명시합니다.
+  - 각 finding은 측정 가능하고 actionable해야 합니다.
+  - severity는 보수적으로 부여합니다.
+  - 완성된 review는 반드시 write_file로 정확한 경로에 저장합니다.
+  - JSON Schema의 `additionalProperties: false`를 준수합니다.
+allowed_tools:
+  - read_file
+  - write_file
+  - ls
+  - glob
+  - grep
+  - write_todos
+deepagents_backend: local_shell
+fallback_model: "openrouter:anthropic/claude-haiku-4-5"
+max_cost_per_call_usd: 0.01
+model_params:
+  max_tokens: 4096
+  temperature: 0.2
+  top_p: 1.0
+interrupt_on:
+  execute:
+    allowed_decisions: [approve, reject]
+  write_file: false