Commit Graph

24 Commits

Author SHA1 Message Date
chungyeong
711d61d245 docs(plan): DR-3 — Temporal deferred to v1.0 multi-tenant ADR; v0.2 PR #2/#3 sequenced
Adds DR-3 to the v4 r1 plan and rewires §1 + §23 to reflect that the v0.x
release line ships zero Temporal code.

Rationale (DR-3 detail in §22):
- v3 and early v4 r1 drafts had Temporal as the canonical durable-workflow
  layer (M5-Py). For 1-user 1-machine CLI/REPL/web-GUI workloads, the same
  durability guarantee is reachable with (1) LangGraph AsyncPostgresSaver
  (already in deps after v0.2 PR #1) + (2) RunPhaseRow / LlmCallRow state
  machine per-commit (already in models) + (3) sweep_orphan_runs at startup
  (already in recovery.py).
- Temporal server + worker + deterministic-workflow rules are weight without
  proportional payoff at this scale. The decision becomes meaningful only
  when v1.0 introduces multi-tenant / multi-machine fanout.
- temporalio NOT added to my-deepagent/pyproject.toml. No apps/worker/.

Patches:
- §1.7 (new): "Workflow Orchestration: NOT USED in v0.x. Deferred to v1.0
  multi-tenant ADR (DR-3)." Explains the LangGraph + DB + sweep replacement
  path and points at §23 for the v0.2 sequencing.
- §22 DR-3 (new): full decision record with rationale, scope, and the
  supersede statement against earlier "M5-Py: Temporal worker NEXT" wording.
- §23 v4 kickoff matrix:
  - v0.2 PR #1 row → DONE (e21a524).
  - v0.2 PR #2a (new): LangGraph AsyncPostgresSaver engine wiring.
  - v0.2 PR #2b (new): `mydeepagent runs resume <id>` real implementation.
  - v0.2 PR #3 (new): FastAPI + SSE + minimal Web GUI.
  - M5-Py → DEFERRED to v1.0+ per DR-3.
  - M8-Py → absorbed into v0.2 PR #3 (no separate apps/api dir; FastAPI
    lives inside my-deepagent/src/my_deepagent/api/).

Open question (recorded in DR-3): v1.0 ADR will compare Temporal vs Hatchet
vs in-house Postgres-based workflow runner.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 21:46:01 +09:00
chungyeong
e21a5241bf feat(my-deepagent): v0.2 PR #1 — Postgres migration (ahead of M8-Py FastAPI)
Switches the production backing store from SQLite to PostgreSQL 16, per DR-2.
The migration trigger is two concurrent writers on the my-deepagent ORM
tables — which first appears with FastAPI (M8-Py). Doing the cut now keeps
the surface area small while M8-Py is still planning.

Production deps: `asyncpg`, `psycopg[binary]`, `langgraph-checkpoint-postgres`.
Test deps: `aiosqlite` (the bulk of unit + integration tests stay on sqlite
tmp_path for speed; the E2E suite and the new checkpointer tests exercise
the live Postgres path).

Highlights
- `persistence/db.py`: dialect-aware connect listener. SQLite still gets
  WAL + busy_timeout=5000 + foreign_keys=ON; Postgres gets `SET TIME ZONE 'UTC'`.
  Added `Database.dialect_name` + `drop_schema` (test-only).
- `persistence/checkpointer.py`: SqliteSaver → AsyncPostgresSaver. API is
  now async (`async with`) and takes a connection string. SQLAlchemy URL
  prefixes (`+asyncpg`, `+psycopg`) are auto-stripped to a plain libpq DSN
  (`_to_psycopg_dsn` helper, 4 unit tests).
- `persistence/upsert.py` (new): `insert_for(session)` — dialect-aware UPSERT
  helper. Picks `postgresql.insert` or `sqlite.insert` based on the bound
  engine. Replaces 5 hardcoded `sqlite_insert` call sites in `budget.py`,
  `recovery.py`, `cli/doctor.py`.
- `persistence/models.py`: `RunRow` partial unique index declares both
  `postgresql_where=` and `sqlite_where=` for cross-dialect correctness.
- `config.py`: default `database_url` now
  `postgresql+asyncpg://devflow:devflow@localhost:55432/mydeepagent`. v3
  `devflow` DB preserved untouched; v4 lives in a fresh `mydeepagent` DB.
- `cli/doctor.py` check 8: dialect-aware DB liveness probe. Postgres path
  runs `SELECT 1` (pg_isready equivalent); SQLite keeps `PRAGMA integrity_check`.
- `alembic/env.py`: env-aware URL resolution (`MYDEEPAGENT_DATABASE_URL` >
  `DATABASE_URL` > default). Async driver prefixes are mapped to the sync
  equivalents alembic needs.
- `alembic/versions/9f2a6c79667e_v0_2_baseline_schema_postgres.py` (new):
  fresh baseline autogenerated against live Postgres. Old SQLite migrations
  (`79945fdc2649`, `839f2233e346`) deleted — v0.2 starts a clean history.
- `tests/conftest.py` (new): `pg_db_url` async fixture creates a fresh DB
  per test against docker-compose `devflow-postgres` and drops it on
  teardown after terminating lingering backends.
- `tests/integration/test_checkpointer.py`: rewritten for AsyncPostgresSaver
  (4 pure DSN-converter unit tests + 3 async context-manager integration tests).
- `tests/integration/test_e2e_workflow.py`: switched to `pg_db_url`. Real
  OpenRouter E2E now exercises the production Postgres path end-to-end.

Recovery
- Previous SQLite database at the platformdirs data_dir is NOT auto-migrated;
  v0.1.0 was the only release that wrote to it. Set
  `MYDEEPAGENT_DATABASE_URL=sqlite+aiosqlite:///<path>` to read it.
- The v3 `devflow` Postgres DB is preserved untouched (separate database
  name); to inspect: `psql -h localhost -p 55432 -U devflow -d devflow`.

Gates
- ruff check + ruff format --check + mypy --strict: PASS (102 source files)
- pytest non-E2E: 576 PASS (5.46 s)
- pytest E2E real OpenRouter on Postgres: 1 PASS (122.93 s, ~$0.05/run)

--no-verify: lefthook still TS-only (deleted in 0e61b2d but still queryable
in git history).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 18:11:19 +09:00
chungyeong
55be4f3aa0 docs(plan): correct DB roadmap — Postgres trigger is M8-Py (FastAPI), not M5-Py (Temporal)
Earlier v4 r1 wording implied Postgres would re-enter "with Temporal." That
was a false equivalence: Temporal worker (M5-Py) runs against its own
backing store (`temporal` namespace) and does not touch `my-deepagent`'s
`runs` / `run_phases` / `llm_calls` ORM tables, so M5-Py does not force a
DB migration. The actual trigger for Postgres is a *second concurrent
writer* on the my-deepagent DB, which first appears with FastAPI in M8-Py
(and the later web GUI). SQLite WAL allows only one concurrent writer.

Changes:
- §1.3 Database: replaced "Postgres parked indefinitely" with explicit
  migration-trigger table (CLI=1 writer → SQLite; Temporal worker=still 1
  writer → SQLite; FastAPI=2 writers → Postgres required). Sequencing:
  v0.2 PR #1 (Postgres baseline regen) lands ahead of M8-Py for a clean cut.
- §22 Decision Log: added DR-2 documenting this correction.
- §23 Kickoff Order: inserted "v0.2 PR #1 — Postgres migration" between
  Step-0-purge and M5-Py; annotated M5-Py and M8-Py with their DB
  implications.

Also clarifies that `temporalio` is listed in plan-v4-draft.md but is not
yet pulled into `my-deepagent/pyproject.toml`; install happens with M5-Py.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 17:40:58 +09:00
chungyeong
bd009cbdb2 chore(release): v0.1.0 — Python rewrite first tagged milestone
CHANGELOG entry created. Tag `v0.1.0` follows in the next step.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 17:17:12 +09:00
chungyeong
1d0dfb273b docs: patch plan.md to v4 r1 (Python rewrite spec) + .gitignore node_modules
plan.md v4 r1 patches (per plan-v4-draft.md §0/§1/§2/§3/§8.5/§18/§22/§23):

- §0 header: v3 r13 → v4 r1 + note explaining the language migration. v3 CC
  counter frozen at CC-39; v4 begins its own series (DR-1 below).
- §1 Stack Decisions: full rewrite for Python (uv / pydantic v2 /
  pydantic-settings / SQLAlchemy 2 async + aiosqlite / typer + prompt_toolkit
  / structlog / FastAPI + sse-starlette).
- §2 Directory Layout: collapse v3 multi-package monorepo → single
  `my-deepagent/` project. TS `apps/`, `packages/`, `tests/`, `scripts/` are
  gone after `0e61b2d`.
- §3 doctor: 13-check (Node/pnpm/Docker/Drizzle) → 8-check (python/uv/git/
  workspace_root/config+governance/openrouter_api_key/openrouter_ping+pricing
  upsert/disk+sqlite integrity).
- §8.5 OpenRouter Adapter: full rewrite. v3 marker-extraction HTTP adapter
  (CC-39) is superseded by the deepagents 0.6.1 multi-turn tool-using agent
  driven by `my_deepagent.session.build_agent`. Native write_file/read_file/
  bash via LocalShellBackend; SafetyShellMiddleware enforces destructive
  command + deny-path policy; ArtifactWatcherMiddleware observes artifact
  writes; CostMiddleware records usage. Known v0.1.0 limits documented:
  usage_metadata empty on OpenRouter-forwarded responses, Anthropic-via-
  OpenRouter tool_calls.args ValidationError requires DeepSeek workaround.
- §18 Errors: add `token_budget_exceeded` and `tool_quota_exceeded` under
  human_required.
- §22 Decision Log: add DR-1 "v3 → v4 major bump" with rationale, scope,
  recovery path (pre-python-rewrite tag at c9fed71).
- §23 Kickoff Order: v3 historical order preserved + v4 Python step matrix
  showing Step 0~12 + Step 15 DONE, Step 13/14 (tmux/TUI recovery) DEFERRED.

§4~§17 (DB schema, enums, hashing, template/persona/binding, session
runtime, prompt envelope, artifact schema registry, run events, fake
adapter, state machines, approval state, run engine + Temporal contract,
WriteSet/worktree, SSE contract) are language-neutral domain spec and remain
unchanged for the Python implementation.

.gitignore: re-add `node_modules/` (legacy Node tree kept ignored until
`rm -rf` cleanup outside git).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 17:16:47 +09:00
chungyeong
0e61b2d907 chore: Step 0 — purge TS monorepo per plan-v4 (Python rewrite complete)
Removes the pre-Python-rewrite TypeScript implementation in full. All domain
functionality has been re-implemented in Python under my-deepagent/ (Step 1~15,
579 unit/integration tests + 1 real-OpenRouter E2E PASS).

Deleted directories (4):
- apps/      — TS api/cli/web/worker apps; replaced by my-deepagent/src/my_deepagent/cli/
- packages/  — TS core/db/run-engine/session/workflows packages; replaced by my-deepagent/src/my_deepagent/{config,enums,persona,workflow,binding,persistence,engine,session,…}
- tests/     — TS workspace smoke tests + fixtures; replaced by my-deepagent/tests/{unit,integration}/
- scripts/   — migrate.ts, seed.ts; replaced by my-deepagent alembic + persistence/db.py

Deleted files (10):
- pnpm-lock.yaml, pnpm-workspace.yaml, package.json
- biome.json, lefthook.yml, vitest.workspace.ts, drizzle.config.ts
- tsconfig.base.json, tsconfig.json, tsconfig.typecheck.json
- .nvmrc

Recovery point:
- Tag `pre-python-rewrite` at c9fed71 — `git checkout pre-python-rewrite -- <path>`
  retrieves any historical TS file if ever needed.

Preserved (per plan-v4-draft.md):
- docs/                      — plan.md (v3 r13, will be patched to v4 r1 next), schemas/
- docker-compose.yml         — Postgres + Temporal containers (still relevant for M5)
- .env.example               — base env contract
- my-deepagent/              — Python implementation
- my-deepagent-seed/         — v0.1.0 bootstrap kit (PoC + seed yaml/json), kept as
                               historical reference; pruning is a separate decision.

.gitignore rewritten for Python-only project (.venv, __pycache__, *.sqlite3, …)
with Node entries dropped.

--no-verify: lefthook (TS-only) was just deleted with this commit.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 17:11:41 +09:00
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