chungyeong/dev-puppeteer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
18 Commits 2 Branches 0 Tags
733c9be0bd7595d1d8b4c5af7e3c5452de0cb84c
Commit Graph

18 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
chungyeong
17ba5d723b feat(my-deepagent): v0.1.0 Step 0~5 — scaffolding through deepagent + OpenRouter 
Python rewrite of the agent harness on top of deepagents 0.6.1 + langchain 1.x,
replacing the abandoned TS attempt in packages/. 388 unit/integration tests pass.

Steps
-----
0. Scaffolding — uv workspace, ruff/mypy/pre-commit/alembic, src/tests/docs
   trees with docs/schemas/ seeded from my-deepagent-seed/.
1. Core — config (pydantic-settings with MYDEEPAGENT_ env prefix and TOML
   source), enums (Backend, Capability, RiskLevel, ApprovalDecisionAction,
   ApprovalState, RunState, RunPhaseState, SessionState, ErrorClass),
   errors (MyDeepAgentError + BudgetExhaustedError with PEP-3134 cause +
   context suppression), hash (canonical JSON + sha256).
2. Persona/Workflow/Binding — pydantic v2 schemas with tuple-based deep
   immutability (post-construction hash drift prevented), YAML loaders,
   deterministic auto-select (preferred_backends → version → name → hash),
   override resolution with ineligibility diagnostics, PersonaConsentStore
   with fcntl.flock + tmp+fsync+rename atomic write.
3. Artifact schema registry — Draft202012Validator, multi-root resolution,
   structured ValidationFinding output.
4. Persistence — 18 SQLAlchemy 2.0 async ORM models with FK CASCADE/RESTRICT,
   WAL + busy_timeout + foreign_keys PRAGMA, alembic baseline +
   ux_active_run_repo_base partial unique index, LangGraph SqliteSaver as
   context manager only (lifecycle safety).
5. DeepAgent session — build_agent wires Persona → create_deep_agent with
   LocalShellBackend / FilesystemBackend / StateBackend / CompositeBackend,
   ChatOpenAI(base_url=openrouter) for openrouter: model strings, and 4
   middleware classes (cost / audit-tool / safety-shell / fallback-model).

Critical workarounds
--------------------
- deepagents 0.6.1 rejects FilesystemPermission together with backends that
  implement SandboxBackendProtocol (LocalShellBackend). SafetyShellMiddleware
  enforces destructive-command and secret-path policy at the tool layer
  instead, and build_agent strips the permissions kwarg when the persona's
  deepagents_backend is local_shell.
- FilesystemOperation in deepagents is Literal['read', 'write'] only;
  _map_operations collapses our richer schema (read/write/edit/ls) safely.

Real OpenRouter smoke
---------------------
test_openrouter_deepagents_local_shell_smoke calls DeepSeek via deepagents +
LocalShellBackend + SafetyShellMiddleware end-to-end. PASS, ~$0.000001 cost,
input=9 / output=1 tokens with content "OK".

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-15 19:40:02 +09:00
chungyeong
1fe59d16ca chore: my-deepagent-seed (BudgetTracker PoC + v0.1.0 seed assets) 
Pre-flight assets prepared on the main machine before the new-machine
rewrite of my-deepagent in Python.

- poc/: BudgetTracker + CostMiddleware + MockChatModel PoC.
  Validates wrap_model_call pattern, SQLite WAL + ON CONFLICT upsert,
  per-scope cap accounting. 5/5 pytest PASS in isolated uv venv.
- schemas/: 10 personas (Anthropic Sonnet/Opus/Haiku + DeepSeek mix),
  3 workflows (spec-and-review, bug-fix-with-reproduction,
  code-investigation), 4 artifact JSON Schemas (dev/spec@1,
  dev/phase-plan@1, dev/review-finding-batch@1, common/final-report@1).
- schemas/validate.py: pydantic + Draft202012 cross-validation.
  18/18 assets verified.
- README.md: new-machine bootstrap instructions.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-15 19:39:37 +09:00
chungyeong
c9fed71cc9 feat: add minimum API and web GUI 2026-05-14 01:16:41 +09:00
chungyeong
e5020a59f0 feat: add tui recovery state machine 2026-05-14 00:14:27 +09:00
chungyeong
ef4c56e6b0 feat: add real tmux session manager 2026-05-13 21:44:58 +09:00
chungyeong
aa3033771a feat: add temporal run engine integration 2026-05-13 08:39:19 +09:00
chungyeong
78ebd5ef78 feat: add minimal run engine 2026-05-11 00:46:45 +09:00
chungyeong
64efeabd33 feat: add fake phase harness 2026-05-10 16:48:52 +09:00
chungyeong
be0ddb6e4e feat: persist session transcripts 2026-05-10 01:47:54 +09:00
chungyeong
017528b497 feat: add fake session adapter 2026-05-10 01:27:43 +09:00
chungyeong
1338e72e96 feat: add artifact schema registry 2026-05-10 01:11:37 +09:00
chungyeong
0d90cd97b6 feat: add persona binding algorithm 2026-05-10 00:31:18 +09:00
chungyeong
4a7fc94f5c feat: add core registry schemas 2026-05-09 23:56:10 +09:00
chungyeong
44103839af feat: add core contracts 2026-05-09 22:45:44 +09:00
chungyeong
42f0fb193d feat: add devflow doctor cli 2026-05-09 22:41:38 +09:00
chungyeong
38f3472d9c chore: add postgres schema migrations 2026-05-09 22:30:49 +09:00
chungyeong
6bd4c9382a chore: scaffold devflow workspace 2026-05-09 22:22:13 +09:00