feat(my-deepagent): v0.3 PR #1 — interactive session persistence + LangGraph saver wiring

v0.3의 토대. REPL/GUI 둘 다 장기 대화를 영속해서 `mydeepagent --session <id>`
또는 `GET /api/sessions/{id}`로 어디서든 이어 진행 가능. Claude Code의
`claude --resume` 등가 능력.

Data model
- `persistence/models.py`:
  - 신규 `MessageRow` 테이블 — (session_id, seq) UNIQUE, role/content/
    tool_calls/token_count/is_summary/archived/ts. LangGraph checkpoint =
    source of truth, 이 테이블은 GUI/CLI 빠른 조회 mirror. divergence
    rebuild 매커니즘 없음 (단순성 우선).
  - `InteractiveSessionRow` 컬럼 8개 추가:
      total_input_tokens, total_output_tokens (PR #2 tiktoken으로 정밀화 예정),
      model, project_key (sha256(realpath(repo_path))[:16]),
      title (첫 user msg 50자), plan_mode (PR #5), parent_session_id (PR #6),
      depth (PR #6 sub-agent depth ≤ 3).
- `alembic/versions/684e70f4536a_*.py` (신규):
  - `op.batch_alter_table` 사용 — SQLite ALTER constraint 미지원 우회. Postgres는
    native DDL.
  - 자동생성이 제안한 LangGraph 테이블 (`checkpoints` 등) drop 라인은 의도적으로
    제거 (langgraph-checkpoint-postgres가 자체 관리).
  - server_default 박아서 기존 row 안전.

CLI
- `cli/interactive.py`:
  - REPL 진입 시 `get_checkpointer_ctx(config.database_url)` 컨텍스트 열고
    REPL 전체 동안 유지. `build_agent(..., checkpointer=saver)`로 deepagents에
    LangGraph saver wire. v0.2 PR #10의 CostMiddleware / AuditToolMiddleware
    보존.
  - `_invoke_and_stream`이 ainvoke 전후 명시적 MessageRow insert
    (user → ainvoke → assistant). last_message_at + total_*_tokens 누적 +
    첫 user msg로 title 자동 setter.
  - `InteractiveSession.thread_suffix` 도입. /model / /agent / /clear 호출
    시 suffix bump → LangGraph thread_id = `{session_id}:{suffix}` 로 새
    deepagents 컨텍스트 시작 (compaction과 같은 패턴, PR #2 재사용).
  - 신규 `--session <id|prefix>` 옵션: 기존 row 로드 (ended이면 거부) 또는
    신규 row insert (AgentPersonaRow upsert + project_key 박음).
  - `/clear` 슬래시 갱신: messages.archived=True + 새 thread 시작. 세션 자체
    는 살아있음 — `sessions show <id> --all`로 조회 가능.
- `cli/sessions.py` (신규): `mydeepagent sessions list/show/resume/end`.
  show <id> [--all]이 archived 메시지까지. 6+ char prefix + 중복 시 명시
  에러.
- `cli/main.py`: --session 옵션 + sessions 서브명령 + interactive_command
  시그니처 확장.

HTTP API
- `api/models.py`: SessionSummary / MessageInfo / SessionDetail /
  CreateSessionRequest / PostMessageRequest / SessionAck DTO 신규 (모두
  extra="forbid").
- `api/routes/sessions.py` (신규):
    GET  /api/sessions?limit=&state=
    GET  /api/sessions/{id}?all=true     (마지막 200 메시지)
    POST /api/sessions                    (persona_name, model_override, repo_path)
    POST /api/sessions/{id}/messages      (사용자 메시지 append, 동기 persist;
                                            PR #7 GUI에서 background ainvoke 추가)
    GET  /api/sessions/{id}/stream        (SSE — 0.5s polling, last-event-id 헤더
                                            + ?last_seq 둘 다 지원)
    POST /api/sessions/{id}/end
- `api/app.py`: sessions 라우터 마운트.

Tests
- `tests/integration/test_session_persist.py` (5 시나리오):
    1. create + post → row + 메시지 + title + token 누적 영속
    2. list가 신규 3 세션 모두 포함
    3. prefix resolution + 404
    4. end 후 메시지 거부 (409)
    5. ?all=true가 archived 메시지 surfacing

Gates
- ruff check + ruff format + mypy --strict: PASS (124 source files)
- pytest non-E2E: 608 PASS (25.86 s) — v0.2 PR #3 후 603에서 +5 신규
- pytest E2E real OpenRouter on Postgres: PASS 82.07 s (베이스라인 60–122s
  범위 내; DR-3 +20% 임계점 통과)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
chungyeong
2026-05-17 20:06:21 +09:00
parent ac428ba747
commit f8335e4515
10 changed files with 1510 additions and 48 deletions

View File

@@ -0,0 +1,98 @@
"""v0.3 PR #1 session messages + 8 columns
Revision ID: 684e70f4536a
Revises: 9f2a6c79667e
Create Date: 2026-05-17 19:48:45.442605
Adds the `messages` table (per-session conversation mirror; LangGraph
checkpoint remains the source of truth) and 8 columns on
`interactive_sessions` for token tracking, project key, title, plan mode,
and sub-agent parent linkage.
The `checkpoints` / `checkpoint_writes` / `checkpoint_blobs` /
`checkpoint_migrations` tables are owned by langgraph-checkpoint-postgres
(see persistence/checkpointer.py — AsyncPostgresSaver.setup()). They are
NOT modeled in our ORM, so alembic autogenerate proposed dropping them.
That drop is intentionally NOT applied here; LangGraph manages its own
schema.
"""
from collections.abc import Sequence
import sqlalchemy as sa
from alembic import op
# revision identifiers, used by Alembic.
revision: str = "684e70f4536a"
down_revision: str | Sequence[str] | None = "9f2a6c79667e"
branch_labels: str | Sequence[str] | None = None
depends_on: str | Sequence[str] | None = None
def upgrade() -> None:
"""Upgrade schema.
Uses `op.batch_alter_table` for `interactive_sessions` so the column
additions + new self-FK work on SQLite too (SQLite does not support
ALTER constraints — alembic batch mode rewrites the table). Postgres
runs the same DDL transactionally with no rebuild.
"""
op.create_table(
"messages",
sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
sa.Column("session_id", sa.String(length=36), nullable=False),
sa.Column("seq", sa.Integer(), nullable=False),
sa.Column("role", sa.Text(), nullable=False),
sa.Column("content", sa.Text(), nullable=False),
sa.Column("tool_calls", sa.JSON(), nullable=True),
sa.Column("token_count", sa.Integer(), nullable=False, server_default="0"),
sa.Column("is_summary", sa.Boolean(), nullable=False, server_default=sa.false()),
sa.Column("archived", sa.Boolean(), nullable=False, server_default=sa.false()),
sa.Column("ts", sa.Text(), nullable=False),
sa.ForeignKeyConstraint(["session_id"], ["interactive_sessions.id"], ondelete="CASCADE"),
sa.PrimaryKeyConstraint("id"),
sa.UniqueConstraint("session_id", "seq", name="uq_messages_session_seq"),
)
op.create_index("messages_session_seq_idx", "messages", ["session_id", "seq"], unique=False)
# 8 new columns + self-FK on interactive_sessions via batch_alter_table
# (SQLite compatibility — Postgres runs the same operations natively).
with op.batch_alter_table("interactive_sessions") as batch_op:
batch_op.add_column(
sa.Column("total_input_tokens", sa.Integer(), nullable=False, server_default="0")
)
batch_op.add_column(
sa.Column("total_output_tokens", sa.Integer(), nullable=False, server_default="0")
)
batch_op.add_column(sa.Column("model", sa.Text(), nullable=True))
batch_op.add_column(sa.Column("project_key", sa.Text(), nullable=True))
batch_op.add_column(sa.Column("title", sa.Text(), nullable=True))
batch_op.add_column(
sa.Column("plan_mode", sa.Boolean(), nullable=False, server_default=sa.false())
)
batch_op.add_column(sa.Column("parent_session_id", sa.String(length=36), nullable=True))
batch_op.add_column(sa.Column("depth", sa.Integer(), nullable=False, server_default="0"))
batch_op.create_foreign_key(
"fk_interactive_sessions_parent_session_id",
"interactive_sessions",
["parent_session_id"],
["id"],
ondelete="CASCADE",
)
def downgrade() -> None:
"""Downgrade schema."""
with op.batch_alter_table("interactive_sessions") as batch_op:
batch_op.drop_constraint("fk_interactive_sessions_parent_session_id", type_="foreignkey")
batch_op.drop_column("depth")
batch_op.drop_column("parent_session_id")
batch_op.drop_column("plan_mode")
batch_op.drop_column("title")
batch_op.drop_column("project_key")
batch_op.drop_column("model")
batch_op.drop_column("total_output_tokens")
batch_op.drop_column("total_input_tokens")
op.drop_index("messages_session_seq_idx", table_name="messages")
op.drop_table("messages")