refactor(prompt): remove unused skill functions and clean up code

* feat(auth): introduce backend auth module

Port RFC-001 authentication core from PR #1728:
- JWT token handling (create_access_token, decode_token, TokenPayload)
- Password hashing (bcrypt) with verify_password
- SQLite UserRepository with base interface
- Provider Factory pattern (LocalAuthProvider)
- CLI reset_admin tool
- Auth-specific errors (AuthErrorCode, TokenError, AuthErrorResponse)

Deps:
- bcrypt>=4.0.0
- pyjwt>=2.9.0
- email-validator>=2.0.0
- backend/uv.toml pins public PyPI index

Tests: 12 pure unit tests (test_auth_config.py, test_auth_errors.py).

Scope note: authz.py, test_auth.py, and test_auth_type_system.py are
deferred to commit 2 because they depend on middleware and deps wiring
that is not yet in place. Commit 1 stays "pure new files only" as the
spec mandates.

* feat(auth): wire auth end-to-end (middleware + frontend replacement)

Backend:
- Port auth_middleware, csrf_middleware, langgraph_auth, routers/auth
- Port authz decorator (owner_filter_key defaults to 'owner_id')
- Merge app.py: register AuthMiddleware + CSRFMiddleware + CORS, add
  _ensure_admin_user lifespan hook, _migrate_orphaned_threads helper,
  register auth router
- Merge deps.py: add get_local_provider, get_current_user_from_request,
  get_optional_user_from_request; keep get_current_user as thin str|None
  adapter for feedback router
- langgraph.json: add auth path pointing to langgraph_auth.py:auth
- Rename metadata['user_id'] -> metadata['owner_id'] in langgraph_auth
  (both metadata write and LangGraph filter dict) + test fixtures

Frontend:
- Delete better-auth library and api catch-all route
- Remove better-auth npm dependency and env vars (BETTER_AUTH_SECRET,
  BETTER_AUTH_GITHUB_*) from env.js
- Port frontend/src/core/auth/* (AuthProvider, gateway-config,
  proxy-policy, server-side getServerSideUser, types)
- Port frontend/src/core/api/fetcher.ts
- Port (auth)/layout, (auth)/login, (auth)/setup pages
- Rewrite workspace/layout.tsx as server component that calls
  getServerSideUser and wraps in AuthProvider
- Port workspace/workspace-content.tsx for the client-side sidebar logic

Tests:
- Port 5 auth test files (test_auth, test_auth_middleware,
  test_auth_type_system, test_ensure_admin, test_langgraph_auth)
- 176 auth tests PASS

After this commit: login/logout/registration flow works, but persistence
layer does not yet filter by owner_id. Commit 4 closes that gap.

* feat(auth): account settings page + i18n

- Port account-settings-page.tsx (change password, change email, logout)
- Wire into settings-dialog.tsx as new "account" section with UserIcon,
  rendered first in the section list
- Add i18n keys:
  - en-US/zh-CN: settings.sections.account ("Account" / "账号")
  - en-US/zh-CN: button.logout ("Log out" / "退出登录")
  - types.ts: matching type declarations

* feat(auth): enforce owner_id across 2.0-rc persistence layer

Add request-scoped contextvar-based owner filtering to threads_meta,
runs, run_events, and feedback repositories. Router code is unchanged
— isolation is enforced at the storage layer so that any caller that
forgets to pass owner_id still gets filtered results, and new routes
cannot accidentally leak data.

Core infrastructure
-------------------
- deerflow/runtime/user_context.py (new):
  - ContextVar[CurrentUser | None] with default None
  - runtime_checkable CurrentUser Protocol (structural subtype with .id)
  - set/reset/get/require helpers
  - AUTO sentinel + resolve_owner_id(value, method_name) for sentinel
    three-state resolution: AUTO reads contextvar, explicit str
    overrides, explicit None bypasses the filter (for migration/CLI)

Repository changes
------------------
- ThreadMetaRepository: create/get/search/update_*/delete gain
  owner_id=AUTO kwarg; read paths filter by owner, writes stamp it,
  mutations check ownership before applying
- RunRepository: put/get/list_by_thread/delete gain owner_id=AUTO kwarg
- FeedbackRepository: create/get/list_by_run/list_by_thread/delete
  gain owner_id=AUTO kwarg
- DbRunEventStore: list_messages/list_events/list_messages_by_run/
  count_messages/delete_by_thread/delete_by_run gain owner_id=AUTO
  kwarg. Write paths (put/put_batch) read contextvar softly: when a
  request-scoped user is available, owner_id is stamped; background
  worker writes without a user context pass None which is valid
  (orphan row to be bound by migration)

Schema
------
- persistence/models/run_event.py: RunEventRow.owner_id = Mapped[
  str | None] = mapped_column(String(64), nullable=True, index=True)
- No alembic migration needed: 2.0 ships fresh, Base.metadata.create_all
  picks up the new column automatically

Middleware
----------
- auth_middleware.py: after cookie check, call get_optional_user_from_
  request to load the real User, stamp it into request.state.user AND
  the contextvar via set_current_user, reset in a try/finally. Public
  paths and unauthenticated requests continue without contextvar, and
  @require_auth handles the strict 401 path

Test infrastructure
-------------------
- tests/conftest.py: @pytest.fixture(autouse=True) _auto_user_context
  sets a default SimpleNamespace(id="test-user-autouse") on every test
  unless marked @pytest.mark.no_auto_user. Keeps existing 20+
  persistence tests passing without modification
- pyproject.toml [tool.pytest.ini_options]: register no_auto_user
  marker so pytest does not emit warnings for opt-out tests
- tests/test_user_context.py: 6 tests covering three-state semantics,
  Protocol duck typing, and require/optional APIs
- tests/test_thread_meta_repo.py: one test updated to pass owner_id=
  None explicitly where it was previously relying on the old default

Test results
------------
- test_user_context.py: 6 passed
- test_auth*.py + test_langgraph_auth.py + test_ensure_admin.py: 127
- test_run_event_store / test_run_repository / test_thread_meta_repo
  / test_feedback: 92 passed
- Full backend suite: 1905 passed, 2 failed (both @requires_llm flaky
  integration tests unrelated to auth), 1 skipped

* feat(auth): extend orphan migration to 2.0-rc persistence tables

_ensure_admin_user now runs a three-step pipeline on every boot:

  Step 1 (fatal):     admin user exists / is created / password is reset
  Step 2 (non-fatal): LangGraph store orphan threads → admin
  Step 3 (non-fatal): SQL persistence tables → admin
    - threads_meta
    - runs
    - run_events
    - feedback

Each step is idempotent. The fatal/non-fatal split mirrors PR #1728's
original philosophy: admin creation failure blocks startup (the system
is unusable without an admin), whereas migration failures log a warning
and let the service proceed (a partial migration is recoverable; a
missing admin is not).

Key helpers
-----------
- _iter_store_items(store, namespace, *, page_size=500):
  async generator that cursor-paginates across LangGraph store pages.
  Fixes PR #1728's hardcoded limit=1000 bug that would silently lose
  orphans beyond the first page.

- _migrate_orphaned_threads(store, admin_user_id):
  Rewritten to use _iter_store_items. Returns the migrated count so the
  caller can log it; raises only on unhandled exceptions.

- _migrate_orphan_sql_tables(admin_user_id):
  Imports the 4 ORM models lazily, grabs the shared session factory,
  runs one UPDATE per table in a single transaction, commits once.
  No-op when no persistence backend is configured (in-memory dev).

Tests: test_ensure_admin.py (8 passed)

* test(auth): port AUTH test plan docs + lint/format pass

- Port backend/docs/AUTH_TEST_PLAN.md and AUTH_UPGRADE.md from PR #1728
- Rename metadata.user_id → metadata.owner_id in AUTH_TEST_PLAN.md
  (4 occurrences from the original PR doc)
- ruff auto-fix UP037 in sentinel type annotations: drop quotes around
  "str | None | _AutoSentinel" now that from __future__ import
  annotations makes them implicit string forms
- ruff format: 2 files (app/gateway/app.py, runtime/user_context.py)

Note on test coverage additions:
- conftest.py autouse fixture was already added in commit 4 (had to
  be co-located with the repository changes to keep pre-existing
  persistence tests passing)
- cross-user isolation E2E tests (test_owner_isolation.py) deferred
  — enforcement is already proven by the 98-test repository suite
  via the autouse fixture + explicit _AUTO sentinel exercises
- New test cases (TC-API-17..20, TC-ATK-13, TC-MIG-01..07) listed
  in AUTH_TEST_PLAN.md are deferred to a follow-up PR — they are
  manual-QA test cases rather than pytest code, and the spec-level
  coverage is already met by test_user_context.py + the 98-test
  repository suite.

Final test results:
- Auth suite (test_auth*, test_langgraph_auth, test_ensure_admin,
  test_user_context): 186 passed
- Persistence suite (test_run_event_store, test_run_repository,
  test_thread_meta_repo, test_feedback): 98 passed
- Lint: ruff check + ruff format both clean

* test(auth): add cross-user isolation test suite

10 tests exercising the storage-layer owner filter by manually
switching the user_context contextvar between two users. Verifies
the safety invariant:

  After a repository write with owner_id=A, a subsequent read with
  owner_id=B must not return the row, and vice versa.

Covers all 4 tables that own user-scoped data:

TC-API-17  threads_meta  — read, search, update, delete cross-user
TC-API-18  runs          — get, list_by_thread, delete cross-user
TC-API-19  run_events    — list_messages, list_events, count_messages,
                           delete_by_thread (CRITICAL: raw conversation
                           content leak vector)
TC-API-20  feedback      — get, list_by_run, delete cross-user

Plus two meta-tests verifying the sentinel pattern itself:
- AUTO + unset contextvar raises RuntimeError
- explicit owner_id=None bypasses the filter (migration escape hatch)

Architecture note
-----------------
These tests bypass the HTTP layer by design. The full chain
(cookie → middleware → contextvar → repository) is covered piecewise:

- test_auth_middleware.py: middleware sets contextvar from cookies
- test_owner_isolation.py: repositories enforce isolation when
  contextvar is set to different users

Together they prove the end-to-end safety property without the
ceremony of spinning up a full TestClient + in-memory DB for every
router endpoint.

Tests pass: 231 (full auth + persistence + isolation suite)
Lint: clean

* refactor(auth): migrate user repository to SQLAlchemy ORM

Move the users table into the shared persistence engine so auth
matches the pattern of threads_meta, runs, run_events, and feedback —
one engine, one session factory, one schema init codepath.

New files
---------
- persistence/user/__init__.py, persistence/user/model.py: UserRow
  ORM class with partial unique index on (oauth_provider, oauth_id)
- Registered in persistence/models/__init__.py so
  Base.metadata.create_all() picks it up

Modified
--------
- auth/repositories/sqlite.py: rewritten as async SQLAlchemy,
  identical constructor pattern to the other four repositories
  (def __init__(self, session_factory) + self._sf = session_factory)
- auth/config.py: drop users_db_path field — storage is configured
  through config.database like every other table
- deps.py/get_local_provider: construct SQLiteUserRepository with
  the shared session factory, fail fast if engine is not initialised
- tests/test_auth.py: rewrite test_sqlite_round_trip_new_fields to
  use the shared engine (init_engine + close_engine in a tempdir)
- tests/test_auth_type_system.py: add per-test autouse fixture that
  spins up a scratch engine and resets deps._cached_* singletons

* refactor(auth): remove SQL orphan migration (unused in supported scenarios)

The _migrate_orphan_sql_tables helper existed to bind NULL owner_id
rows in threads_meta, runs, run_events, and feedback to the admin on
first boot. But in every supported upgrade path, it's a no-op:

  1. Fresh install: create_all builds fresh tables, no legacy rows
  2. No-auth → with-auth (no existing persistence DB): persistence
     tables are created fresh by create_all, no legacy rows
  3. No-auth → with-auth (has existing persistence DB from #1930):
     NOT a supported upgrade path — "有 DB 到有 DB" schema evolution
     is out of scope; users wipe DB or run manual ALTER

So the SQL orphan migration never has anything to do in the
supported matrix. Delete the function, simplify _ensure_admin_user
from a 3-step pipeline to a 2-step one (admin creation + LangGraph
store orphan migration only).

LangGraph store orphan migration stays: it serves the real
"no-auth → with-auth" upgrade path where a user's existing LangGraph
thread metadata has no owner_id field and needs to be stamped with
the newly-created admin's id.

Tests: 284 passed (auth + persistence + isolation)
Lint: clean

* security(auth): write initial admin password to 0600 file instead of logs

CodeQL py/clear-text-logging-sensitive-data flagged 3 call sites that
logged the auto-generated admin password to stdout via logger.info().
Production log aggregators (ELK/Splunk/etc) would have captured those
cleartext secrets. Replace with a shared helper that writes to
.deer-flow/admin_initial_credentials.txt with mode 0600, and log only
the path.

New file
--------
- app/gateway/auth/credential_file.py: write_initial_credentials()
  helper. Takes email, password, and a "initial"/"reset" label.
  Creates .deer-flow/ if missing, writes a header comment plus the
  email+password, chmods 0o600, returns the absolute Path.

Modified
--------
- app/gateway/app.py: both _ensure_admin_user paths (fresh creation
  + needs_setup password reset) now write to file and log the path
- app/gateway/auth/reset_admin.py: rewritten to use the shared ORM
  repo (SQLiteUserRepository with session_factory) and the
  credential_file helper. The previous implementation was broken
  after the earlier ORM refactor — it still imported _get_users_conn
  and constructed SQLiteUserRepository() without a session factory.

No tests changed — the three password-log sites are all exercised
via existing test_ensure_admin.py which checks that startup
succeeds, not that a specific string appears in logs.

CodeQL alerts 272, 283, 284: all resolved.

* security(auth): strict JWT validation in middleware (fix junk cookie bypass)

AUTH_TEST_PLAN test 7.5.8 expects junk cookies to be rejected with
401. The previous middleware behaviour was "presence-only": check
that some access_token cookie exists, then pass through. In
combination with my Task-12 decision to skip @require_auth
decorators on routes, this created a gap where a request with any
cookie-shaped string (e.g. access_token=not-a-jwt) would bypass
authentication on routes that do not touch the repository
(/api/models, /api/mcp/config, /api/memory, /api/skills, …).

Fix: middleware now calls get_current_user_from_request() strictly
and catches the resulting HTTPException to render a 401 with the
proper fine-grained error code (token_invalid, token_expired,
user_not_found, …). On success it stamps request.state.user and
the contextvar so repository-layer owner filters work downstream.

The 4 old "_with_cookie_passes" tests in test_auth_middleware.py
were written for the presence-only behaviour; they asserted that
a junk cookie would make the handler return 200. They are renamed
to "_with_junk_cookie_rejected" and their assertions flipped to
401. The negative path (no cookie → 401 not_authenticated)
is unchanged.

Verified:
  no cookie       → 401 not_authenticated
  junk cookie     → 401 token_invalid     (the fixed bug)
  expired cookie  → 401 token_expired

Tests: 284 passed (auth + persistence + isolation)
Lint: clean

* security(auth): wire @require_permission(owner_check=True) on isolation routes

Apply the require_permission decorator to all 28 routes that take a
{thread_id} path parameter. Combined with the strict middleware
(previous commit), this gives the double-layer protection that
AUTH_TEST_PLAN test 7.5.9 documents:

  Layer 1 (AuthMiddleware): cookie + JWT validation, rejects junk
                            cookies and stamps request.state.user
  Layer 2 (@require_permission with owner_check=True): per-resource
                            ownership verification via
                            ThreadMetaStore.check_access — returns
                            404 if a different user owns the thread

The decorator's owner_check branch is rewritten to use the SQL
thread_meta_repo (the 2.0-rc persistence layer) instead of the
LangGraph store path that PR #1728 used (_store_get / get_store
in routers/threads.py). The inject_record convenience is dropped
— no caller in 2.0 needs the LangGraph blob, and the SQL repo has
a different shape.

Routes decorated (28 total):
- threads.py: delete, patch, get, get-state, post-state, post-history
- thread_runs.py: post-runs, post-runs-stream, post-runs-wait,
  list_runs, get_run, cancel_run, join_run, stream_existing_run,
  list_thread_messages, list_run_messages, list_run_events,
  thread_token_usage
- feedback.py: create, list, stats, delete
- uploads.py: upload (added Request param), list, delete
- artifacts.py: get_artifact
- suggestions.py: generate (renamed body parameter to avoid
  conflict with FastAPI Request)

Test fixes:
- test_suggestions_router.py: bypass the decorator via __wrapped__
  (the unit tests cover parsing logic, not auth — no point spinning
  up a thread_meta_repo just to test JSON unwrapping)
- test_auth_middleware.py 4 fake-cookie tests: already updated in
  the previous commit (745bf432)

Tests: 293 passed (auth + persistence + isolation + suggestions)
Lint: clean

* security(auth): defense-in-depth fixes from release validation pass

Eight findings caught while running the AUTH_TEST_PLAN end-to-end against
the deployed sg_dev stack. Each is a pre-condition for shipping
release/2.0-rc that the previous PRs missed.

Backend hardening
- routers/auth.py: rate limiter X-Real-IP now requires AUTH_TRUSTED_PROXIES
  whitelist (CIDR/IP allowlist). Without nginx in front, the previous code
  honored arbitrary X-Real-IP, letting an attacker rotate the header to
  fully bypass the per-IP login lockout.
- routers/auth.py: 36-entry common-password blocklist via Pydantic
  field_validator on RegisterRequest + ChangePasswordRequest. The shared
  _validate_strong_password helper keeps the constraint in one place.
- routers/threads.py: ThreadCreateRequest + ThreadPatchRequest strip
  server-reserved metadata keys (owner_id, user_id) via Pydantic
  field_validator so a forged value can never round-trip back to other
  clients reading the same thread. The actual ownership invariant stays
  on the threads_meta row; this closes the metadata-blob echo gap.
- authz.py + thread_meta/sql.py: require_permission gains a require_existing
  flag plumbed through check_access(require_existing=True). Destructive
  routes (DELETE/PATCH/state-update/runs/feedback) now treat a missing
  thread_meta row as 404 instead of "untracked legacy thread, allow",
  closing the cross-user delete-idempotence gap where any user could
  successfully DELETE another user's deleted thread.
- repositories/sqlite.py + base.py: update_user raises UserNotFoundError
  on a vanished row instead of silently returning the input. Concurrent
  delete during password reset can no longer look like a successful update.
- runtime/user_context.py: resolve_owner_id() coerces User.id (UUID) to
  str at the contextvar boundary so SQLAlchemy String(64) columns can
  bind it. The whole 2.0-rc isolation pipeline was previously broken
  end-to-end (POST /api/threads → 500 "type 'UUID' is not supported").
- persistence/engine.py: SQLAlchemy listener enables PRAGMA journal_mode=WAL,
  synchronous=NORMAL, foreign_keys=ON on every new SQLite connection.
  TC-UPG-06 in the test plan expects WAL; previous code shipped with the
  default 'delete' journal.
- auth_middleware.py: stamp request.state.auth = AuthContext(...) so
  @require_permission's short-circuit fires; previously every isolation
  request did a duplicate JWT decode + users SELECT. Also unifies the
  401 payload through AuthErrorResponse(...).model_dump().
- app.py: _ensure_admin_user restructure removes the noqa F821 scoping
  bug where 'password' was referenced outside the branch that defined it.
  New _announce_credentials helper absorbs the duplicate log block in
  the fresh-admin and reset-admin branches.

* fix(frontend+nginx): rollout CSRF on every state-changing client path

The frontend was 100% broken in gateway-pro mode for any user trying to
open a specific chat thread. Three cumulative bugs each silently
masked the next.

LangGraph SDK CSRF gap (api-client.ts)
- The Client constructor took only apiUrl, no defaultHeaders, no fetch
  interceptor. The SDK's internal fetch never sent X-CSRF-Token, so
  every state-changing /api/langgraph-compat/* call (runs/stream,
  threads/search, threads/{tid}/history, ...) hit CSRFMiddleware and
  got 403 before reaching the auth check. UI symptom: empty thread page
  with no error message; the SPA's hooks swallowed the rejection.
- Fix: pass an onRequest hook that injects X-CSRF-Token from the
  csrf_token cookie per request. Reading the cookie per call (not at
  construction time) handles login / logout / password-change cookie
  rotation transparently. The SDK's prepareFetchOptions calls
  onRequest for both regular requests AND streaming/SSE/reconnect, so
  the same hook covers runs.stream and runs.joinStream.

Raw fetch CSRF gap (7 files)
- Audit: 11 frontend fetch sites, only 2 included CSRF (login/setup +
  account-settings change-password). The other 7 routed through raw
  fetch() with no header — suggestions, memory, agents, mcp, skills,
  uploads, and the local thread cleanup hook all 403'd silently.
- Fix: enhance fetcher.ts:fetchWithAuth to auto-inject X-CSRF-Token on
  POST/PUT/DELETE/PATCH from a single shared readCsrfCookie() helper.
  Convert all 7 raw fetch() callers to fetchWithAuth so the contract
  is centrally enforced. api-client.ts and fetcher.ts share
  readCsrfCookie + STATE_CHANGING_METHODS to avoid drift.

nginx routing + buffering (nginx.local.conf)
- The auth feature shipped without updating the nginx config: per-API
  explicit location blocks but no /api/v1/auth/, /api/feedback, /api/runs.
  The frontend's client-side fetches to /api/v1/auth/login/local 404'd
  from the Next.js side because nginx routed /api/* to the frontend.
- Fix: add catch-all `location /api/` that proxies to the gateway.
  nginx longest-prefix matching keeps the explicit blocks (/api/models,
  /api/threads regex, /api/langgraph/, ...) winning for their paths.
- Fix: disable proxy_buffering + proxy_request_buffering for the
  frontend `location /` block. Without it, nginx tries to spool large
  Next.js chunks into /var/lib/nginx/proxy (root-owned) and fails with
  Permission denied → ERR_INCOMPLETE_CHUNKED_ENCODING → ChunkLoadError.

* test(auth): release-validation test infra and new coverage

Test fixtures and unit tests added during the validation pass.

Router test helpers (NEW: tests/_router_auth_helpers.py)
- make_authed_test_app(): builds a FastAPI test app with a stub
  middleware that stamps request.state.user + request.state.auth and a
  permissive thread_meta_repo mock. TestClient-based router tests
  (test_artifacts_router, test_threads_router) use it instead of bare
  FastAPI() so the new @require_permission(owner_check=True) decorators
  short-circuit cleanly.
- call_unwrapped(): walks the __wrapped__ chain to invoke the underlying
  handler without going through the authz wrappers. Direct-call tests
  (test_uploads_router) use it. Typed with ParamSpec so the wrapped
  signature flows through.

Backend test additions
- test_auth.py: 7 tests for the new _get_client_ip trust model (no
  proxy / trusted proxy / untrusted peer / XFF rejection / invalid
  CIDR / no client). 5 tests for the password blocklist (literal,
  case-insensitive, strong password accepted, change-password binding,
  short-password length-check still fires before blocklist).
  test_update_user_raises_when_row_concurrently_deleted: closes a
  shipped-without-coverage gap on the new UserNotFoundError contract.
- test_thread_meta_repo.py: 4 tests for check_access(require_existing=True)
  — strict missing-row denial, strict owner match, strict owner mismatch,
  strict null-owner still allowed (shared rows survive the tightening).
- test_ensure_admin.py: 3 tests for _migrate_orphaned_threads /
  _iter_store_items pagination, covering the TC-UPG-02 upgrade story
  end-to-end via mock store. Closes the gap where the cursor pagination
  was untested even though the previous PR rewrote it.
- test_threads_router.py: 5 tests for _strip_reserved_metadata
  (owner_id removal, user_id removal, safe-keys passthrough, empty
  input, both-stripped).
- test_auth_type_system.py: replace "password123" fixtures with
  Tr0ub4dor3a / AnotherStr0ngPwd! so the new password blocklist
  doesn't reject the test data.

* docs(auth): refresh TC-DOCKER-05 + document Docker validation gap

- AUTH_TEST_PLAN.md TC-DOCKER-05: the previous expectation
  ("admin password visible in docker logs") was stale after the simplify
  pass that moved credentials to a 0600 file. The grep "Password:" check
  would have silently failed and given a false sense of coverage. New
  expectation matches the actual file-based path: 0600 file in
  DEER_FLOW_HOME, log shows the path (not the secret), reverse-grep
  asserts no leaked password in container logs.
- NEW: docs/AUTH_TEST_DOCKER_GAP.md documents the only un-executed
  block in the test plan (TC-DOCKER-01..06). Reason: sg_dev validation
  host has no Docker daemon installed. The doc maps each Docker case
  to an already-validated bare-metal equivalent (TC-1.1, TC-REENT-01,
  TC-API-02 etc.) so the gap is auditable, and includes pre-flight
  reproduction steps for whoever has Docker available.

---------

Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com>

.env.example

@@ -24,7 +24,6 @@ INFOQUEST_API_KEY=your-infoquest-api-key
 # SLACK_BOT_TOKEN=your-slack-bot-token
 # SLACK_APP_TOKEN=your-slack-app-token
 # TELEGRAM_BOT_TOKEN=your-telegram-bot-token
-# DISCORD_BOT_TOKEN=your-discord-bot-token
 
 # Enable LangSmith to monitor and debug your LLM calls, agent runs, and tool executions.
 # LANGSMITH_TRACING=true
@@ -40,8 +39,3 @@ INFOQUEST_API_KEY=your-infoquest-api-key
 #
 # WECOM_BOT_ID=your-wecom-bot-id
 # WECOM_BOT_SECRET=your-wecom-bot-secret
-# DINGTALK_CLIENT_ID=your-dingtalk-client-id
-# DINGTALK_CLIENT_SECRET=your-dingtalk-client-secret
-
-# Set to "false" to disable Swagger UI, ReDoc, and OpenAPI schema in production
-# GATEWAY_ENABLE_DOCS=false

.github/workflows/e2e-tests.yml

@@ -1,63 +0,0 @@
-name: E2E Tests
-
-on:
-  push:
-    branches: [ 'main' ]
-    paths:
-      - 'frontend/**'
-      - '.github/workflows/e2e-tests.yml'
-  pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
-    paths:
-      - 'frontend/**'
-      - '.github/workflows/e2e-tests.yml'
-
-concurrency:
-  group: e2e-tests-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  e2e-tests:
-    if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: '22'
-
-      - name: Enable Corepack
-        run: corepack enable
-
-      - name: Use pinned pnpm version
-        run: corepack prepare pnpm@10.26.2 --activate
-
-      - name: Install frontend dependencies
-        working-directory: frontend
-        run: pnpm install --frozen-lockfile
-
-      - name: Install Playwright Chromium
-        working-directory: frontend
-        run: npx playwright install chromium --with-deps
-
-      - name: Run E2E tests
-        working-directory: frontend
-        run: pnpm exec playwright test
-        env:
-          SKIP_ENV_VALIDATION: '1'
-
-      - name: Upload Playwright report
-        uses: actions/upload-artifact@v4
-        if: ${{ !cancelled() }}
-        with:
-          name: playwright-report
-          path: frontend/playwright-report/
-          retention-days: 7

.github/workflows/frontend-unit-tests.yml

@@ -1,43 +0,0 @@
-name: Frontend Unit Tests
-
-on:
-  push:
-    branches: [ 'main' ]
-  pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
-
-concurrency:
-  group: frontend-unit-tests-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  frontend-unit-tests:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: '22'
-
-      - name: Enable Corepack
-        run: corepack enable
-
-      - name: Use pinned pnpm version
-        run: corepack prepare pnpm@10.26.2 --activate
-
-      - name: Install frontend dependencies
-        working-directory: frontend
-        run: pnpm install --frozen-lockfile
-
-      - name: Run unit tests of frontend
-        working-directory: frontend
-        run: make test

.gitignore

@@ -40,7 +40,6 @@ coverage/
 skills/custom/*
 logs/
 log/
-debug.log
 
 # Local git hooks (keep only on this machine, do not push)
 .githooks/
@@ -56,7 +55,5 @@ web/
 backend/Dockerfile.langgraph
 config.yaml.bak
 .playwright-mcp
-/frontend/test-results/
-/frontend/playwright-report/
 .gstack/
 .worktrees

.pre-commit-config.yaml

@@ -1,33 +0,0 @@
-repos:
-  # Backend: ruff lint + format via uv (uses the same ruff version as backend deps)
-  - repo: local
-    hooks:
-      - id: ruff
-        name: ruff lint
-        entry: bash -c 'cd backend && uv run ruff check --fix "${@/#backend\//}"' --
-        language: system
-        types_or: [python]
-        files: ^backend/
-      - id: ruff-format
-        name: ruff format
-        entry: bash -c 'cd backend && uv run ruff format "${@/#backend\//}"' --
-        language: system
-        types_or: [python]
-        files: ^backend/
-
-  # Frontend: eslint + prettier (must run from frontend/ for node_modules resolution)
-  - repo: local
-    hooks:
-      - id: frontend-eslint
-        name: eslint (frontend)
-        entry: bash -c 'cd frontend && npx eslint --fix "${@/#frontend\//}"' --
-        language: system
-        types_or: [javascript, tsx, ts]
-        files: ^frontend/
-
-      - id: frontend-prettier
-        name: prettier (frontend)
-        entry: bash -c 'cd frontend && npx prettier --write "${@/#frontend\//}"' --
-        language: system
-        files: ^frontend/
-        types_or: [javascript, tsx, ts, json, css]

CONTRIBUTING.md

@@ -166,7 +166,7 @@ Required tools:
 
 1. **Configure the application** (same as Docker setup above)
 
-2. **Install dependencies** (this also sets up pre-commit hooks):
+2. **Install dependencies**:
    ```bash
    make install
    ```
@@ -298,24 +298,19 @@ Nginx (port 2026) ← Unified entry point
 ```bash
 # Backend tests
 cd backend
-make test
+uv run pytest
 
-# Frontend unit tests
+# Frontend checks
 cd frontend
-make test
-
-# Frontend E2E tests (requires Chromium; builds and auto-starts the Next.js production server)
-cd frontend
-make test-e2e
+pnpm check
 ```
 
 ### PR Regression Checks
 
-Every pull request triggers the following CI workflows:
+Every pull request runs the backend regression workflow at [.github/workflows/backend-unit-tests.yml](.github/workflows/backend-unit-tests.yml), including:
 
-- **Backend unit tests** — [.github/workflows/backend-unit-tests.yml](.github/workflows/backend-unit-tests.yml)
-- **Frontend unit tests** — [.github/workflows/frontend-unit-tests.yml](.github/workflows/frontend-unit-tests.yml)
-- **Frontend E2E tests** — [.github/workflows/e2e-tests.yml](.github/workflows/e2e-tests.yml) (triggered only when `frontend/` files change)
+- `tests/test_provisioner_kubeconfig.py`
+- `tests/test_docker_sandbox_mode_detection.py`
 
 ## Code Style
 

Makefile

@@ -1,6 +1,6 @@
 # DeerFlow - Unified Development Environment
 
-.PHONY: help config config-upgrade check install setup doctor dev dev-daemon start start-daemon stop up down clean docker-init docker-start docker-stop docker-logs docker-logs-frontend docker-logs-gateway
+.PHONY: help config config-upgrade check install setup doctor dev dev-pro dev-daemon dev-daemon-pro start start-pro start-daemon start-daemon-pro stop up up-pro down clean docker-init docker-start docker-start-pro docker-stop docker-logs docker-logs-frontend docker-logs-gateway
 
 BASH ?= bash
 BACKEND_UV_RUN = cd backend && uv run
@@ -23,22 +23,28 @@ help:
 	@echo "  make config          - Generate local config files (aborts if config already exists)"
 	@echo "  make config-upgrade  - Merge new fields from config.example.yaml into config.yaml"
 	@echo "  make check           - Check if all required tools are installed"
-	@echo "  make install         - Install all dependencies (frontend + backend + pre-commit hooks)"
+	@echo "  make install         - Install all dependencies (frontend + backend)"
 	@echo "  make setup-sandbox   - Pre-pull sandbox container image (recommended)"
 	@echo "  make dev             - Start all services in development mode (with hot-reloading)"
+	@echo "  make dev-pro         - Start in dev + Gateway mode (experimental, no LangGraph server)"
 	@echo "  make dev-daemon      - Start dev services in background (daemon mode)"
+	@echo "  make dev-daemon-pro  - Start dev daemon + Gateway mode (experimental)"
 	@echo "  make start           - Start all services in production mode (optimized, no hot-reloading)"
+	@echo "  make start-pro       - Start in prod + Gateway mode (experimental)"
 	@echo "  make start-daemon    - Start prod services in background (daemon mode)"
+	@echo "  make start-daemon-pro - Start prod daemon + Gateway mode (experimental)"
 	@echo "  make stop            - Stop all running services"
 	@echo "  make clean           - Clean up processes and temporary files"
 	@echo ""
 	@echo "Docker Production Commands:"
 	@echo "  make up              - Build and start production Docker services (localhost:2026)"
+	@echo "  make up-pro          - Build and start production Docker in Gateway mode (experimental)"
 	@echo "  make down            - Stop and remove production Docker containers"
 	@echo ""
 	@echo "Docker Development Commands:"
 	@echo "  make docker-init     - Pull the sandbox image"
 	@echo "  make docker-start    - Start Docker services (mode-aware from config.yaml, localhost:2026)"
+	@echo "  make docker-start-pro - Start Docker in Gateway mode (experimental, no LangGraph container)"
 	@echo "  make docker-stop     - Stop Docker development services"
 	@echo "  make docker-logs     - View Docker development logs"
 	@echo "  make docker-logs-frontend - View Docker frontend logs"
@@ -67,8 +73,6 @@ install:
 	@cd backend && uv sync
 	@echo "Installing frontend dependencies..."
 	@cd frontend && pnpm install
-	@echo "Installing pre-commit hooks..."
-	@$(BACKEND_UV_RUN) --with pre-commit pre-commit install
 	@echo "✓ All dependencies installed"
 	@echo ""
 	@echo "=========================================="
@@ -95,7 +99,7 @@ setup-sandbox:
 	echo ""; \
 	if command -v container >/dev/null 2>&1 && [ "$$(uname)" = "Darwin" ]; then \
 		echo "Detected Apple Container on macOS, pulling image..."; \
-		container image pull "$$IMAGE" || echo "⚠ Apple Container pull failed, will try Docker"; \
+		container pull "$$IMAGE" || echo "⚠ Apple Container pull failed, will try Docker"; \
 	fi; \
 	if command -v docker >/dev/null 2>&1; then \
 		echo "Pulling image using Docker..."; \
@@ -117,21 +121,41 @@ dev:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev
 
+# Start all services in dev + Gateway mode (experimental: agent runtime embedded in Gateway)
+dev-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev --gateway
+
 # Start all services in production mode (with optimizations)
 start:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod
 
+# Start all services in prod + Gateway mode (experimental)
+start-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod --gateway
+
 # Start all services in daemon mode (background)
 dev-daemon:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev --daemon
 
+# Start daemon + Gateway mode (experimental)
+dev-daemon-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev --gateway --daemon
+
 # Start prod services in daemon mode (background)
 start-daemon:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod --daemon
 
+# Start prod daemon + Gateway mode (experimental)
+start-daemon-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod --gateway --daemon
+
 # Stop all services
 stop:
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --stop
@@ -156,6 +180,10 @@ docker-init:
 docker-start:
 	@$(RUN_WITH_GIT_BASH) ./scripts/docker.sh start
 
+# Start Docker in Gateway mode (experimental)
+docker-start-pro:
+	@$(RUN_WITH_GIT_BASH) ./scripts/docker.sh start --gateway
+
 # Stop Docker development environment
 docker-stop:
 	@$(RUN_WITH_GIT_BASH) ./scripts/docker.sh stop
@@ -178,6 +206,10 @@ docker-logs-gateway:
 up:
 	@$(RUN_WITH_GIT_BASH) ./scripts/deploy.sh
 
+# Build and start production services in Gateway mode
+up-pro:
+	@$(RUN_WITH_GIT_BASH) ./scripts/deploy.sh --gateway
+
 # Stop and remove production containers
 down:
 	@$(RUN_WITH_GIT_BASH) ./scripts/deploy.sh down

README.md

@@ -243,6 +243,9 @@ make up     # Build images and start all production services
 make down   # Stop and remove containers
 ```
 
+> [!NOTE]
+> The LangGraph agent server currently runs via `langgraph dev` (the open-source CLI server).
+
 Access: http://localhost:2026
 
 See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed Docker development guide.
@@ -251,7 +254,7 @@ See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed Docker development guide.
 
 If you prefer running services locally:
 
-Prerequisite: complete the "Configuration" steps above first (`make setup`). `make dev` requires a valid `config.yaml` in the project root. Set `DEER_FLOW_PROJECT_ROOT` to define that root explicitly, or `DEER_FLOW_CONFIG_PATH` to point at a specific config file. Runtime state defaults to `.deer-flow` under the project root and can be moved with `DEER_FLOW_HOME`; skills default to `skills/` under the project root and can be moved with `DEER_FLOW_SKILLS_PATH`. Run `make doctor` to verify your setup before starting.
+Prerequisite: complete the "Configuration" steps above first (`make setup`). `make dev` requires a valid `config.yaml` in the project root (can be overridden via `DEER_FLOW_CONFIG_PATH`). Run `make doctor` to verify your setup before starting.
 On Windows, run the local development flow from Git Bash. Native `cmd.exe` and PowerShell shells are not supported for the bash-based service scripts, and WSL is not guaranteed because some scripts rely on Git for Windows utilities such as `cygpath`.
 
 1. **Check prerequisites**:
@@ -261,7 +264,7 @@ On Windows, run the local development flow from Git Bash. Native `cmd.exe` and P
 
 2. **Install dependencies**:
    ```bash
-   make install  # Install backend + frontend dependencies + pre-commit hooks
+   make install  # Install backend + frontend dependencies
    ```
 
 3. **(Optional) Pre-pull sandbox image**:
@@ -286,31 +289,53 @@ On Windows, run the local development flow from Git Bash. Native `cmd.exe` and P
 
 #### Startup Modes
 
-DeerFlow runs the agent runtime inside the Gateway API. Development mode enables hot-reload; production mode uses a pre-built frontend.
+DeerFlow supports multiple startup modes across two dimensions:
+
+- **Dev / Prod** — dev enables hot-reload; prod uses pre-built frontend
+- **Standard / Gateway** — standard uses a separate LangGraph server (4 processes); Gateway mode (experimental) embeds the agent runtime in the Gateway API (3 processes)
 
 | | **Local Foreground** | **Local Daemon** | **Docker Dev** | **Docker Prod** |
 |---|---|---|---|---|
 | **Dev** | `./scripts/serve.sh --dev`<br/>`make dev` | `./scripts/serve.sh --dev --daemon`<br/>`make dev-daemon` | `./scripts/docker.sh start`<br/>`make docker-start` | — |
+| **Dev + Gateway** | `./scripts/serve.sh --dev --gateway`<br/>`make dev-pro` | `./scripts/serve.sh --dev --gateway --daemon`<br/>`make dev-daemon-pro` | `./scripts/docker.sh start --gateway`<br/>`make docker-start-pro` | — |
 | **Prod** | `./scripts/serve.sh --prod`<br/>`make start` | `./scripts/serve.sh --prod --daemon`<br/>`make start-daemon` | — | `./scripts/deploy.sh`<br/>`make up` |
+| **Prod + Gateway** | `./scripts/serve.sh --prod --gateway`<br/>`make start-pro` | `./scripts/serve.sh --prod --gateway --daemon`<br/>`make start-daemon-pro` | — | `./scripts/deploy.sh --gateway`<br/>`make up-pro` |
 
 | Action | Local | Docker Dev | Docker Prod |
 |---|---|---|---|
 | **Stop** | `./scripts/serve.sh --stop`<br/>`make stop` | `./scripts/docker.sh stop`<br/>`make docker-stop` | `./scripts/deploy.sh down`<br/>`make down` |
 | **Restart** | `./scripts/serve.sh --restart [flags]` | `./scripts/docker.sh restart` | — |
 
-Gateway owns `/api/langgraph/*` and translates those public LangGraph-compatible paths to its native `/api/*` routers behind nginx.
+> **Gateway mode** eliminates the LangGraph server process — the Gateway API handles agent execution directly via async tasks, managing its own concurrency.
+
+#### Why Gateway Mode?
+
+In standard mode, DeerFlow runs a dedicated [LangGraph Platform](https://langchain-ai.github.io/langgraph/) server alongside the Gateway API. This architecture works well but has trade-offs:
+
+| | Standard Mode | Gateway Mode |
+|---|---|---|
+| **Architecture** | Gateway (REST API) + LangGraph (agent runtime) | Gateway embeds agent runtime |
+| **Concurrency** | `--n-jobs-per-worker` per worker (requires license) | `--workers` × async tasks (no per-worker cap) |
+| **Containers / Processes** | 4 (frontend, gateway, langgraph, nginx) | 3 (frontend, gateway, nginx) |
+| **Resource usage** | Higher (two Python runtimes) | Lower (single Python runtime) |
+| **LangGraph Platform license** | Required for production images | Not required |
+| **Cold start** | Slower (two services to initialize) | Faster |
+
+Both modes are functionally equivalent — the same agents, tools, and skills work in either mode.
 
 #### Docker Production Deployment
 
-`deploy.sh` supports building and starting separately:
+`deploy.sh` supports building and starting separately. Images are mode-agnostic — runtime mode is selected at start time:
 
 ```bash
 # One-step (build + start)
-deploy.sh
+deploy.sh                    # standard mode (default)
+deploy.sh --gateway          # gateway mode
 
-# Two-step (build once, start later)
+# Two-step (build once, start with any mode)
 deploy.sh build              # build all images
-deploy.sh start              # start pre-built images
+deploy.sh start              # start in standard mode
+deploy.sh start --gateway    # start in gateway mode
 
 # Stop
 deploy.sh down
@@ -345,14 +370,13 @@ DeerFlow supports receiving tasks from messaging apps. Channels auto-start when
 | Feishu / Lark | WebSocket | Moderate |
 | WeChat | Tencent iLink (long-polling) | Moderate |
 | WeCom | WebSocket | Moderate |
-| DingTalk | Stream Push (WebSocket) | Moderate |
 
 **Configuration in `config.yaml`:**
 
 ```yaml
 channels:
-  # LangGraph-compatible Gateway API base URL (default: http://localhost:8001/api)
-  langgraph_url: http://localhost:8001/api
+  # LangGraph Server URL (default: http://localhost:2024)
+  langgraph_url: http://localhost:2024
   # Gateway API URL (default: http://localhost:8001)
   gateway_url: http://localhost:8001
 
@@ -415,19 +439,11 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # Client ID of your DingTalk application
-    client_secret: $DINGTALK_CLIENT_SECRET     # Client Secret of your DingTalk application
-    allowed_users: []                          # empty = allow all
-    card_template_id: ""                       # Optional: AI Card template ID for streaming typewriter effect
 ```
 
 Notes:
 - `assistant_id: lead_agent` calls the default LangGraph assistant directly.
 - If `assistant_id` is set to a custom agent name, DeerFlow still routes through `lead_agent` and injects that value as `agent_name`, so the custom agent's SOUL/config takes effect for IM channels.
-- IM channel workers call Gateway's LangGraph-compatible API internally and automatically attach process-local internal auth plus the CSRF cookie/header pair required for thread and run creation.
 
 Set the corresponding API keys in your `.env` file:
 
@@ -450,10 +466,6 @@ WECHAT_ILINK_BOT_ID=your_ilink_bot_id
 # WeCom
 WECOM_BOT_ID=your_bot_id
 WECOM_BOT_SECRET=your_bot_secret
-
-# DingTalk
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Telegram Setup**
@@ -492,15 +504,7 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 4. Make sure backend dependencies include `wecom-aibot-python-sdk`. The channel uses a WebSocket long connection and does not require a public callback URL.
 5. The current integration supports inbound text, image, and file messages. Final images/files generated by the agent are also sent back to the WeCom conversation.
 
-**DingTalk Setup**
-
-1. Create a DingTalk application in the [DingTalk Developer Console](https://open.dingtalk.com/) and enable **Robot** capability.
-2. Set the message receiving mode to **Stream Mode** in the robot configuration page.
-3. Copy the `Client ID` and `Client Secret`, set `DINGTALK_CLIENT_ID` and `DINGTALK_CLIENT_SECRET` in `.env`, and enable the channel in `config.yaml`.
-4. *(Optional)* To enable streaming AI Card replies (typewriter effect), create an **AI Card** template on the [DingTalk Card Platform](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card), then set `card_template_id` in `config.yaml` to the template ID. You also need to apply for the `Card.Streaming.Write` and `Card.Instance.Write` permissions.
-
-
-When DeerFlow runs in Docker Compose, IM channels execute inside the `gateway` container. In that case, do not point `channels.langgraph_url` or `channels.gateway_url` at `localhost`; use container service names such as `http://gateway:8001/api` and `http://gateway:8001`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` and `DEER_FLOW_CHANNELS_GATEWAY_URL`.
+When DeerFlow runs in Docker Compose, IM channels execute inside the `gateway` container. In that case, do not point `channels.langgraph_url` or `channels.gateway_url` at `localhost`; use container service names such as `http://langgraph:2024` and `http://gateway:8001`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` and `DEER_FLOW_CHANNELS_GATEWAY_URL`.
 
 **Commands**
 
@@ -654,8 +658,6 @@ This is the difference between a chatbot with tool access and an agent with an a
 
 **Summarization**: Within a session, DeerFlow manages context aggressively — summarizing completed sub-tasks, offloading intermediate results to the filesystem, compressing what's no longer immediately relevant. This lets it stay sharp across long, multi-step tasks without blowing the context window.
 
-**Strict Tool-Call Recovery**: When a provider or middleware interrupts a tool-call loop, DeerFlow now strips provider-level raw tool-call metadata on forced-stop assistant messages and injects placeholder tool results for dangling calls before the next model invocation. This keeps OpenAI-compatible reasoning models that strictly validate `tool_call_id` sequences from failing with malformed history errors.
-
 ### Long-Term Memory
 
 Most agents forget everything the moment a conversation ends. DeerFlow remembers.

README_fr.md

@@ -290,7 +290,6 @@ DeerFlow peut recevoir des tâches depuis des applications de messagerie. Les ca
 | Telegram | Bot API (long-polling) | Facile |
 | Slack | Socket Mode | Modérée |
 | Feishu / Lark | WebSocket | Modérée |
-| DingTalk | Stream Push (WebSocket) | Modérée |
 
 **Configuration dans `config.yaml` :**
 
@@ -342,13 +341,6 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # ClientId depuis DingTalk Open Platform
-    client_secret: $DINGTALK_CLIENT_SECRET     # ClientSecret depuis DingTalk Open Platform
-    allowed_users: []                          # vide = tout le monde autorisé
-    card_template_id: ""                       # Optionnel : ID de modèle AI Card pour l'effet machine à écrire en streaming
 ```
 
 Définissez les clés API correspondantes dans votre fichier `.env` :
@@ -364,10 +356,6 @@ SLACK_APP_TOKEN=xapp-...
 # Feishu / Lark
 FEISHU_APP_ID=cli_xxxx
 FEISHU_APP_SECRET=your_app_secret
-
-# DingTalk
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Configuration Telegram**
@@ -390,13 +378,6 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 3. Dans **Events**, abonnez-vous à `im.message.receive_v1` et sélectionnez le mode **Long Connection**.
 4. Copiez l'App ID et l'App Secret. Définissez `FEISHU_APP_ID` et `FEISHU_APP_SECRET` dans `.env` et activez le canal dans `config.yaml`.
 
-**Configuration DingTalk**
-
-1. Créez une application sur [DingTalk Open Platform](https://open.dingtalk.com/) et activez la capacité **Robot**.
-2. Dans la page de configuration du robot, définissez le mode de réception des messages sur **Stream**.
-3. Copiez le `Client ID` et le `Client Secret`. Définissez `DINGTALK_CLIENT_ID` et `DINGTALK_CLIENT_SECRET` dans `.env` et activez le canal dans `config.yaml`.
-4. *(Optionnel)* Pour activer les réponses en streaming AI Card (effet machine à écrire), créez un modèle **AI Card** sur la [plateforme de cartes DingTalk](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card), puis définissez `card_template_id` dans `config.yaml` avec l'ID du modèle. Vous devez également demander les permissions `Card.Streaming.Write` et `Card.Instance.Write`.
-
 **Commandes**
 
 Une fois un canal connecté, vous pouvez interagir avec DeerFlow directement depuis le chat :

README_ja.md

@@ -243,7 +243,6 @@ DeerFlowはメッセージングアプリからのタスク受信をサポート
 | Telegram | Bot API（ロングポーリング） | 簡単 |
 | Slack | Socket Mode | 中程度 |
 | Feishu / Lark | WebSocket | 中程度 |
-| DingTalk | Stream Push（WebSocket） | 中程度 |
 
 **`config.yaml`での設定：**
 
@@ -295,13 +294,6 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # DingTalk Open PlatformのClientId
-    client_secret: $DINGTALK_CLIENT_SECRET     # DingTalk Open PlatformのClientSecret
-    allowed_users: []                          # 空 = 全員許可
-    card_template_id: ""                       # オプション：ストリーミングタイプライター効果用のAIカードテンプレートID
 ```
 
 対応するAPIキーを`.env`ファイルに設定します：
@@ -317,10 +309,6 @@ SLACK_APP_TOKEN=xapp-...
 # Feishu / Lark
 FEISHU_APP_ID=cli_xxxx
 FEISHU_APP_SECRET=your_app_secret
-
-# DingTalk
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Telegramのセットアップ**
@@ -343,13 +331,6 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 3. **イベント**で`im.message.receive_v1`を購読し、**ロングコネクション**モードを選択。
 4. App IDとApp Secretをコピー。`.env`に`FEISHU_APP_ID`と`FEISHU_APP_SECRET`を設定し、`config.yaml`でチャネルを有効にします。
 
-**DingTalkのセットアップ**
-
-1. [DingTalk Open Platform](https://open.dingtalk.com/)でアプリを作成し、**ロボット**機能を有効化します。
-2. ロボット設定ページでメッセージ受信モードを**Streamモード**に設定します。
-3. `Client ID`と`Client Secret`をコピー。`.env`に`DINGTALK_CLIENT_ID`と`DINGTALK_CLIENT_SECRET`を設定し、`config.yaml`でチャネルを有効にします。
-4. *（オプション）* ストリーミングAIカード返信（タイプライター効果）を有効にするには、[DingTalkカードプラットフォーム](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card)で**AIカード**テンプレートを作成し、`config.yaml`の`card_template_id`にテンプレートIDを設定します。`Card.Streaming.Write` および `Card.Instance.Write` 権限の申請も必要です。
-
 **コマンド**
 
 チャネル接続後、チャットから直接DeerFlowと対話できます：

README_ru.md

@@ -256,7 +256,6 @@ DeerFlow принимает задачи прямо из мессенджеро
 | Telegram | Bot API (long-polling) | Просто |
 | Slack | Socket Mode | Средне |
 | Feishu / Lark | WebSocket | Средне |
-| DingTalk | Stream Push (WebSocket) | Средне |
 
 **Конфигурация в `config.yaml`:**
 
@@ -279,13 +278,6 @@ channels:
     enabled: true
     bot_token: $TELEGRAM_BOT_TOKEN
     allowed_users: []
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # ClientId с DingTalk Open Platform
-    client_secret: $DINGTALK_CLIENT_SECRET     # ClientSecret с DingTalk Open Platform
-    allowed_users: []                          # пусто = разрешить всем
-    card_template_id: ""                       # Опционально: ID шаблона AI Card для потокового эффекта печатной машинки
 ```
 
 **Настройка Telegram**
@@ -293,13 +285,6 @@ channels:
 1. Напишите [@BotFather](https://t.me/BotFather), отправьте `/newbot` и скопируйте HTTP API-токен.
 2. Укажите `TELEGRAM_BOT_TOKEN` в `.env` и включите канал в `config.yaml`.
 
-**Настройка DingTalk**
-
-1. Создайте приложение на [DingTalk Open Platform](https://open.dingtalk.com/) и включите возможность **Робот**.
-2. На странице настроек робота установите режим приёма сообщений на **Stream**.
-3. Скопируйте `Client ID` и `Client Secret`. Укажите `DINGTALK_CLIENT_ID` и `DINGTALK_CLIENT_SECRET` в `.env` и включите канал в `config.yaml`.
-4. *(Опционально)* Для включения потоковых ответов AI Card (эффект печатной машинки) создайте шаблон **AI Card** на [платформе карточек DingTalk](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card), затем укажите `card_template_id` в `config.yaml` с ID шаблона. Также необходимо запросить разрешения `Card.Streaming.Write` и `Card.Instance.Write`.
-
 **Доступные команды**
 
 | Команда | Описание |

README_zh.md

@@ -194,7 +194,7 @@ make down   # 停止并移除容器
 
 如果你更希望直接在本地启动各个服务：
 
-前提：先完成上面的“配置”步骤（`make config` 和模型 API key 配置）。`make dev` 需要有效配置文件，默认读取项目根目录下的 `config.yaml`。可以用 `DEER_FLOW_PROJECT_ROOT` 显式指定项目根目录，也可以用 `DEER_FLOW_CONFIG_PATH` 指向某个具体配置文件。运行期状态默认写到项目根目录下的 `.deer-flow`，可用 `DEER_FLOW_HOME` 覆盖；skills 默认读取项目根目录下的 `skills/`，可用 `DEER_FLOW_SKILLS_PATH` 覆盖。
+前提：先完成上面的“配置”步骤（`make config` 和模型 API key 配置）。`make dev` 需要有效配置文件，默认读取项目根目录下的 `config.yaml`，也可以通过 `DEER_FLOW_CONFIG_PATH` 覆盖。
 在 Windows 上，请使用 Git Bash 运行本地开发流程。基于 bash 的服务脚本不支持直接在原生 `cmd.exe` 或 PowerShell 中执行，且 WSL 也不保证可用，因为部分脚本依赖 Git for Windows 的 `cygpath` 等工具。
 
 1. **检查依赖环境**：
@@ -248,7 +248,6 @@ DeerFlow 支持从即时通讯应用接收任务。只要配置完成，对应
 | Slack | Socket Mode | 中等 |
 | Feishu / Lark | WebSocket | 中等 |
 | 企业微信智能机器人 | WebSocket | 中等 |
-| 钉钉 | Stream Push（WebSocket） | 中等 |
 
 **`config.yaml` 中的配置示例：**
 
@@ -305,13 +304,6 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # 钉钉开放平台 ClientId
-    client_secret: $DINGTALK_CLIENT_SECRET     # 钉钉开放平台 ClientSecret
-    allowed_users: []                          # 留空表示允许所有人
-    card_template_id: ""                       # 可选：AI 卡片模板 ID，用于流式打字机效果
 ```
 
 说明：
@@ -335,10 +327,6 @@ FEISHU_APP_SECRET=your_app_secret
 # 企业微信智能机器人
 WECOM_BOT_ID=your_bot_id
 WECOM_BOT_SECRET=your_bot_secret
-
-# 钉钉
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Telegram 配置**
@@ -369,13 +357,6 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 4. 安装后端依赖时确保包含 `wecom-aibot-python-sdk`，渠道会通过 WebSocket 长连接接收消息，无需公网回调地址。
 5. 当前支持文本、图片和文件入站消息；agent 生成的最终图片/文件也会回传到企业微信会话中。
 
-**钉钉配置**
-
-1. 在 [钉钉开放平台](https://open.dingtalk.com/) 创建应用，并启用 **机器人** 能力。
-2. 在机器人配置页面设置消息接收模式为 **Stream模式**。
-3. 复制 `Client ID` 和 `Client Secret`，在 `.env` 中设置 `DINGTALK_CLIENT_ID` 和 `DINGTALK_CLIENT_SECRET`，并在 `config.yaml` 中启用该渠道。
-4. *（可选）* 如需开启流式 AI 卡片回复（打字机效果），请在[钉钉卡片平台](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card)创建 **AI 卡片**模板，然后在 `config.yaml` 中将 `card_template_id` 设为该模板 ID。同时需要申请 `Card.Streaming.Write` 和 `Card.Instance.Write` 权限。
-
 **命令**
 
 渠道连接完成后，你可以直接在聊天窗口里和 DeerFlow 交互：

backend/CLAUDE.md

@@ -7,13 +7,15 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 DeerFlow is a LangGraph-based AI super agent system with a full-stack architecture. The backend provides a "super agent" with sandbox execution, persistent memory, subagent delegation, and extensible tool integration - all operating in per-thread isolated environments.
 
 **Architecture**:
-- **Gateway API** (port 8001): REST API plus embedded LangGraph-compatible agent runtime
+- **LangGraph Server** (port 2024): Agent runtime and workflow execution
+- **Gateway API** (port 8001): REST API for models, MCP, skills, memory, artifacts, uploads, and local thread cleanup
 - **Frontend** (port 3000): Next.js web interface
 - **Nginx** (port 2026): Unified reverse proxy entry point
 - **Provisioner** (port 8002, optional in Docker dev): Started only when sandbox is configured for provisioner/Kubernetes mode
 
-**Runtime**:
-- `make dev`, Docker dev, and production all run the agent runtime in Gateway via `RunManager` + `run_agent()` + `StreamBridge` (`packages/harness/deerflow/runtime/`). Nginx exposes that runtime at `/api/langgraph/*` and rewrites it to Gateway's native `/api/*` routers.
+**Runtime Modes**:
+- **Standard mode** (`make dev`): LangGraph Server handles agent execution as a separate process. 4 processes total.
+- **Gateway mode** (`make dev-pro`, experimental): Agent runtime embedded in Gateway via `RunManager` + `run_agent()` + `StreamBridge` (`packages/harness/deerflow/runtime/`). Service manages its own concurrency via async tasks. 3 processes total, no LangGraph Server.
 
 **Project Structure**:
 ```
@@ -23,7 +25,7 @@ deer-flow/
 ├── extensions_config.json      # MCP servers and skills configuration
 ├── backend/                    # Backend application (this directory)
 │   ├── Makefile               # Backend-only commands (dev, gateway, lint)
-│   ├── langgraph.json         # LangGraph Studio graph configuration
+│   ├── langgraph.json         # LangGraph server configuration
 │   ├── packages/
 │   │   └── harness/           # deerflow-harness package (import: deerflow.*)
 │   │       ├── pyproject.toml
@@ -81,15 +83,16 @@ When making code changes, you MUST update the relevant documentation:
 ```bash
 make check      # Check system requirements
 make install    # Install all dependencies (frontend + backend)
-make dev        # Start all services (Gateway + Frontend + Nginx), with config.yaml preflight
-make start      # Start production services locally
+make dev        # Start all services (LangGraph + Gateway + Frontend + Nginx), with config.yaml preflight
+make dev-pro    # Gateway mode (experimental): skip LangGraph, agent runtime embedded in Gateway
+make start-pro  # Production + Gateway mode (experimental)
 make stop       # Stop all services
 ```
 
 **Backend directory** (for backend development only):
 ```bash
 make install    # Install backend dependencies
-make dev        # Run Gateway API with reload (port 8001)
+make dev        # Run LangGraph server only (port 2024)
 make gateway    # Run Gateway API only (port 8001)
 make test       # Run all backend tests
 make lint       # Lint with ruff
@@ -112,7 +115,7 @@ CI runs these regression tests for every pull request via [.github/workflows/bac
 The backend is split into two layers with a strict dependency direction:
 
 - **Harness** (`packages/harness/deerflow/`): Publishable agent framework package (`deerflow-harness`). Import prefix: `deerflow.*`. Contains agent orchestration, tools, sandbox, models, MCP, skills, config — everything needed to build and run agents.
-- **App** (`app/`): Unpublished application code. Import prefix: `app.*`. Contains the FastAPI Gateway API and IM channel integrations (Feishu, Slack, Telegram, DingTalk).
+- **App** (`app/`): Unpublished application code. Import prefix: `app.*`. Contains the FastAPI Gateway API and IM channel integrations (Feishu, Slack, Telegram).
 
 **Dependency rule**: App imports deerflow, but deerflow never imports app. This boundary is enforced by `tests/test_harness_boundary.py` which runs in CI.
 
@@ -153,26 +156,20 @@ from deerflow.config import get_app_config
 
 ### Middleware Chain
 
-Lead-agent middlewares are assembled in strict append order across `packages/harness/deerflow/agents/middlewares/tool_error_handling_middleware.py` (`build_lead_runtime_middlewares`) and `packages/harness/deerflow/agents/lead_agent/agent.py` (`_build_middlewares`):
+Middlewares execute in strict order in `packages/harness/deerflow/agents/lead_agent/agent.py`:
 
-1. **ThreadDataMiddleware** - Creates per-thread directories under the user's isolation scope (`backend/.deer-flow/users/{user_id}/threads/{thread_id}/user-data/{workspace,uploads,outputs}`); resolves `user_id` via `get_effective_user_id()` (falls back to `"default"` in no-auth mode); Web UI thread deletion now follows LangGraph thread removal with Gateway cleanup of the local thread directory
+1. **ThreadDataMiddleware** - Creates per-thread directories (`backend/.deer-flow/threads/{thread_id}/user-data/{workspace,uploads,outputs}`); Web UI thread deletion now follows LangGraph thread removal with Gateway cleanup of the local `.deer-flow/threads/{thread_id}` directory
 2. **UploadsMiddleware** - Tracks and injects newly uploaded files into conversation
 3. **SandboxMiddleware** - Acquires sandbox, stores `sandbox_id` in state
-4. **DanglingToolCallMiddleware** - Injects placeholder ToolMessages for AIMessage tool_calls that lack responses (e.g., due to user interruption), including raw provider tool-call payloads preserved only in `additional_kwargs["tool_calls"]`
-5. **LLMErrorHandlingMiddleware** - Normalizes provider/model invocation failures into recoverable assistant-facing errors before later middleware/tool stages run
-6. **GuardrailMiddleware** - Pre-tool-call authorization via pluggable `GuardrailProvider` protocol (optional, if `guardrails.enabled` in config). Evaluates each tool call and returns error ToolMessage on deny. Three provider options: built-in `AllowlistProvider` (zero deps), OAP policy providers (e.g. `aport-agent-guardrails`), or custom providers. See [docs/GUARDRAILS.md](docs/GUARDRAILS.md) for setup, usage, and how to implement a provider.
-7. **SandboxAuditMiddleware** - Audits sandboxed shell/file operations for security logging before tool execution continues
-8. **ToolErrorHandlingMiddleware** - Converts tool exceptions into error `ToolMessage`s so the run can continue instead of aborting
-9. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
-10. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
-11. **TokenUsageMiddleware** - Records token usage metrics when token tracking is enabled (optional)
-12. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
-13. **MemoryMiddleware** - Queues conversations for async memory update (filters to user + final AI responses)
-14. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
-15. **DeferredToolFilterMiddleware** - Hides deferred tool schemas from the bound model until tool search is enabled (optional)
-16. **SubagentLimitMiddleware** - Truncates excess `task` tool calls from model response to enforce `MAX_CONCURRENT_SUBAGENTS` limit (optional, if `subagent_enabled`)
-17. **LoopDetectionMiddleware** - Detects repeated tool-call loops; hard-stop responses clear both structured `tool_calls` and raw provider tool-call metadata before forcing a final text answer
-18. **ClarificationMiddleware** - Intercepts `ask_clarification` tool calls, interrupts via `Command(goto=END)` (must be last)
+4. **DanglingToolCallMiddleware** - Injects placeholder ToolMessages for AIMessage tool_calls that lack responses (e.g., due to user interruption)
+5. **GuardrailMiddleware** - Pre-tool-call authorization via pluggable `GuardrailProvider` protocol (optional, if `guardrails.enabled` in config). Evaluates each tool call and returns error ToolMessage on deny. Three provider options: built-in `AllowlistProvider` (zero deps), OAP policy providers (e.g. `aport-agent-guardrails`), or custom providers. See [docs/GUARDRAILS.md](docs/GUARDRAILS.md) for setup, usage, and how to implement a provider.
+6. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
+7. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
+8. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
+9. **MemoryMiddleware** - Queues conversations for async memory update (filters to user + final AI responses)
+10. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
+11. **SubagentLimitMiddleware** - Truncates excess `task` tool calls from model response to enforce `MAX_CONCURRENT_SUBAGENTS` limit (optional, if subagent_enabled)
+12. **ClarificationMiddleware** - Intercepts `ask_clarification` tool calls, interrupts via `Command(goto=END)` (must be last)
 
 ### Configuration System
 
@@ -205,7 +202,7 @@ Configuration priority:
 
 ### Gateway API (`app/gateway/`)
 
-FastAPI application on port 8001 with health check at `GET /health`. Set `GATEWAY_ENABLE_DOCS=false` to disable `/docs`, `/redoc`, and `/openapi.json` in production (default: enabled).
+FastAPI application on port 8001 with health check at `GET /health`.
 
 **Routers**:
 
@@ -219,9 +216,6 @@ FastAPI application on port 8001 with health check at `GET /health`. Set `GATEWA
 | **Threads** (`/api/threads/{id}`) | `DELETE /` - remove DeerFlow-managed local thread data after LangGraph thread deletion; unexpected failures are logged server-side and return a generic 500 detail |
 | **Artifacts** (`/api/threads/{id}/artifacts`) | `GET /{path}` - serve artifacts; active content types (`text/html`, `application/xhtml+xml`, `image/svg+xml`) are always forced as download attachments to reduce XSS risk; `?download=true` still forces download for other file types |
 | **Suggestions** (`/api/threads/{id}/suggestions`) | `POST /` - generate follow-up questions; rich list/block model content is normalized before JSON parsing |
-| **Thread Runs** (`/api/threads/{id}/runs`) | `POST /` - create background run; `POST /stream` - create + SSE stream; `POST /wait` - create + block; `GET /` - list runs; `GET /{rid}` - run details; `POST /{rid}/cancel` - cancel; `GET /{rid}/join` - join SSE; `GET /{rid}/messages` - paginated messages `{data, has_more}`; `GET /{rid}/events` - full event stream; `GET /../messages` - thread messages with feedback; `GET /../token-usage` - aggregate tokens |
-| **Feedback** (`/api/threads/{id}/runs/{rid}/feedback`) | `PUT /` - upsert feedback; `DELETE /` - delete user feedback; `POST /` - create feedback; `GET /` - list feedback; `GET /stats` - aggregate stats; `DELETE /{fid}` - delete specific |
-| **Runs** (`/api/runs`) | `POST /stream` - stateless run + SSE; `POST /wait` - stateless run + block; `GET /{rid}/messages` - paginated messages by run_id `{data, has_more}` (cursor: `after_seq`/`before_seq`); `GET /{rid}/feedback` - list feedback by run_id |
 
 Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` → Gateway.
 
@@ -235,7 +229,7 @@ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` →
 
 **Virtual Path System**:
 - Agent sees: `/mnt/user-data/{workspace,uploads,outputs}`, `/mnt/skills`
-- Physical: `backend/.deer-flow/users/{user_id}/threads/{thread_id}/user-data/...`, `deer-flow/skills/`
+- Physical: `backend/.deer-flow/threads/{thread_id}/user-data/...`, `deer-flow/skills/`
 - Translation: `replace_virtual_path()` / `replace_virtual_paths_in_command()`
 - Detection: `is_local_sandbox()` checks `sandbox_id == "local"`
 
@@ -275,7 +269,7 @@ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` →
 - `invoke_acp_agent` - Invokes external ACP-compatible agents from `config.yaml`
 - ACP launchers must be real ACP adapters. The standard `codex` CLI is not ACP-compatible by itself; configure a wrapper such as `npx -y @zed-industries/codex-acp` or an installed `codex-acp` binary
 - Missing ACP executables now return an actionable error message instead of a raw `[Errno 2]`
-- Each ACP agent uses a per-thread workspace at `{base_dir}/users/{user_id}/threads/{thread_id}/acp-workspace/`. The workspace is accessible to the lead agent via the virtual path `/mnt/acp-workspace/` (read-only). In docker sandbox mode, the directory is volume-mounted into the container at `/mnt/acp-workspace` (read-only); in local sandbox mode, path translation is handled by `tools.py`
+- Each ACP agent uses a per-thread workspace at `{base_dir}/threads/{thread_id}/acp-workspace/`. The workspace is accessible to the lead agent via the virtual path `/mnt/acp-workspace/` (read-only). In docker sandbox mode, the directory is volume-mounted into the container at `/mnt/acp-workspace` (read-only); in local sandbox mode, path translation is handled by `tools.py`
 - `image_search/` - Image search via DuckDuckGo
 
 ### MCP System (`packages/harness/deerflow/mcp/`)
@@ -312,10 +306,9 @@ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` →
 
 ### IM Channels System (`app/channels/`)
 
-Bridges external messaging platforms (Feishu, Slack, Telegram, DingTalk) to the DeerFlow agent via the LangGraph Server.
+Bridges external messaging platforms (Feishu, Slack, Telegram) to the DeerFlow agent via the LangGraph Server.
 
-
-**Architecture**: Channels communicate with Gateway through the `langgraph-sdk` HTTP client (same as the frontend), ensuring threads are created and managed server-side. The internal SDK client injects process-local internal auth plus a matching CSRF cookie/header pair so Gateway accepts state-changing thread/run requests from channel workers without relying on browser session cookies.
+**Architecture**: Channels communicate with the LangGraph Server through `langgraph-sdk` HTTP client (same as the frontend), ensuring threads are created and managed server-side.
 
 **Components**:
 - `message_bus.py` - Async pub/sub hub (`InboundMessage` → queue → dispatcher; `OutboundMessage` → callbacks → channels)
@@ -323,51 +316,40 @@ Bridges external messaging platforms (Feishu, Slack, Telegram, DingTalk) to the
 - `manager.py` - Core dispatcher: creates threads via `client.threads.create()`, routes commands, keeps Slack/Telegram on `client.runs.wait()`, and uses `client.runs.stream(["messages-tuple", "values"])` for Feishu incremental outbound updates
 - `base.py` - Abstract `Channel` base class (start/stop/send lifecycle)
 - `service.py` - Manages lifecycle of all configured channels from `config.yaml`
-- `slack.py` / `feishu.py` / `telegram.py` / `dingtalk.py` - Platform-specific implementations (`feishu.py` tracks the running card `message_id` in memory and patches the same card in place; `dingtalk.py` optionally uses AI Card streaming for in-place updates when `card_template_id` is configured)
+- `slack.py` / `feishu.py` / `telegram.py` - Platform-specific implementations (`feishu.py` tracks the running card `message_id` in memory and patches the same card in place)
 
 **Message Flow**:
 1. External platform -> Channel impl -> `MessageBus.publish_inbound()`
 2. `ChannelManager._dispatch_loop()` consumes from queue
-3. For chat: look up/create thread through Gateway's LangGraph-compatible API
+3. For chat: look up/create thread on LangGraph Server
 4. Feishu chat: `runs.stream()` → accumulate AI text → publish multiple outbound updates (`is_final=False`) → publish final outbound (`is_final=True`)
 5. Slack/Telegram chat: `runs.wait()` → extract final response → publish outbound
 6. Feishu channel sends one running reply card up front, then patches the same card for each outbound update (card JSON sets `config.update_multi=true` for Feishu's patch API requirement)
-7. DingTalk AI Card mode (when `card_template_id` configured): `runs.stream()` → create card with initial text → stream updates via `PUT /v1.0/card/streaming` → finalize on `is_final=True`. Falls back to `sampleMarkdown` if card creation or streaming fails
-8. For commands (`/new`, `/status`, `/models`, `/memory`, `/help`): handle locally or query Gateway API
-9. Outbound → channel callbacks → platform reply
+7. For commands (`/new`, `/status`, `/models`, `/memory`, `/help`): handle locally or query Gateway API
+8. Outbound → channel callbacks → platform reply
 
 **Configuration** (`config.yaml` -> `channels`):
-- `langgraph_url` - LangGraph-compatible Gateway API base URL (default: `http://localhost:8001/api`)
+- `langgraph_url` - LangGraph Server URL (default: `http://localhost:2024`)
 - `gateway_url` - Gateway API URL for auxiliary commands (default: `http://localhost:8001`)
-- In Docker Compose, IM channels run inside the `gateway` container, so `localhost` points back to that container. Use `http://gateway:8001/api` for `langgraph_url` and `http://gateway:8001` for `gateway_url`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` / `DEER_FLOW_CHANNELS_GATEWAY_URL`.
-- Per-channel configs: `feishu` (app_id, app_secret), `slack` (bot_token, app_token), `telegram` (bot_token), `dingtalk` (client_id, client_secret, optional `card_template_id` for AI Card streaming)
-
+- In Docker Compose, IM channels run inside the `gateway` container, so `localhost` points back to that container. Use `http://langgraph:2024` / `http://gateway:8001`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` / `DEER_FLOW_CHANNELS_GATEWAY_URL`.
+- Per-channel configs: `feishu` (app_id, app_secret), `slack` (bot_token, app_token), `telegram` (bot_token)
 
 ### Memory System (`packages/harness/deerflow/agents/memory/`)
 
 **Components**:
 - `updater.py` - LLM-based memory updates with fact extraction, whitespace-normalized fact deduplication (trims leading/trailing whitespace before comparing), and atomic file I/O
-- `queue.py` - Debounced update queue (per-thread deduplication, configurable wait time); captures `user_id` at enqueue time so it survives the `threading.Timer` boundary
+- `queue.py` - Debounced update queue (per-thread deduplication, configurable wait time)
 - `prompt.py` - Prompt templates for memory updates
-- `storage.py` - File-based storage with per-user isolation; cache keyed by `(user_id, agent_name)` tuple
 
-**Per-User Isolation**:
-- Memory is stored per-user at `{base_dir}/users/{user_id}/memory.json`
-- Per-agent per-user memory at `{base_dir}/users/{user_id}/agents/{agent_name}/memory.json`
-- `user_id` is resolved via `get_effective_user_id()` from `deerflow.runtime.user_context`
-- In no-auth mode, `user_id` defaults to `"default"` (constant `DEFAULT_USER_ID`)
-- Absolute `storage_path` in config opts out of per-user isolation
-- **Migration**: Run `PYTHONPATH=. python scripts/migrate_user_isolation.py` to move legacy `memory.json` and `threads/` into per-user layout; supports `--dry-run`
-
-**Data Structure** (stored in `{base_dir}/users/{user_id}/memory.json`):
+**Data Structure** (stored in `backend/.deer-flow/memory.json`):
 - **User Context**: `workContext`, `personalContext`, `topOfMind` (1-3 sentence summaries)
 - **History**: `recentMonths`, `earlierContext`, `longTermBackground`
 - **Facts**: Discrete facts with `id`, `content`, `category` (preference/knowledge/context/behavior/goal), `confidence` (0-1), `createdAt`, `source`
 
 **Workflow**:
-1. `MemoryMiddleware` filters messages (user inputs + final AI responses), captures `user_id` via `get_effective_user_id()`, and queues conversation with the captured `user_id`
+1. `MemoryMiddleware` filters messages (user inputs + final AI responses) and queues conversation
 2. Queue debounces (30s default), batches updates, deduplicates per-thread
-3. Background thread invokes LLM to extract context updates and facts, using the stored `user_id` (not the contextvar, which is unavailable on timer threads)
+3. Background thread invokes LLM to extract context updates and facts
 4. Applies updates atomically (temp file + rename) with cache invalidation, skipping duplicate fact content before append
 5. Next interaction injects top 15 facts + context into `<memory>` tags in system prompt
 
@@ -375,7 +357,7 @@ Focused regression coverage for the updater lives in `backend/tests/test_memory_
 
 **Configuration** (`config.yaml` → `memory`):
 - `enabled` / `injection_enabled` - Master switches
-- `storage_path` - Path to memory.json (absolute path opts out of per-user isolation)
+- `storage_path` - Path to memory.json
 - `debounce_seconds` - Wait time before processing (default: 30)
 - `model_name` - LLM for updates (null = default model)
 - `max_facts` / `fact_confidence_threshold` - Fact storage limits (100 / 0.7)
@@ -410,9 +392,9 @@ Both can be modified at runtime via Gateway API endpoints or `DeerFlowClient` me
 
 `DeerFlowClient` provides direct in-process access to all DeerFlow capabilities without HTTP services. All return types align with the Gateway API response schemas, so consumer code works identically in HTTP and embedded modes.
 
-**Architecture**: Imports the same `deerflow` modules that Gateway API uses. Shares the same config files and data directories. No FastAPI dependency.
+**Architecture**: Imports the same `deerflow` modules that LangGraph Server and Gateway API use. Shares the same config files and data directories. No FastAPI dependency.
 
-**Agent Conversation**:
+**Agent Conversation** (replaces LangGraph Server):
 - `chat(message, thread_id)` — synchronous, accumulates streaming deltas per message-id and returns the final AI text
 - `stream(message, thread_id)` — subscribes to LangGraph `stream_mode=["values", "messages", "custom"]` and yields `StreamEvent`:
   - `"values"` — full state snapshot (title, messages, artifacts); AI text already delivered via `messages` mode is **not** re-synthesized here to avoid duplicate deliveries
@@ -475,15 +457,20 @@ This starts all services and makes the application available at `http://localhos
 | | **Local Foreground** | **Local Daemon** | **Docker Dev** | **Docker Prod** |
 |---|---|---|---|---|
 | **Dev** | `./scripts/serve.sh --dev`<br/>`make dev` | `./scripts/serve.sh --dev --daemon`<br/>`make dev-daemon` | `./scripts/docker.sh start`<br/>`make docker-start` | — |
+| **Dev + Gateway** | `./scripts/serve.sh --dev --gateway`<br/>`make dev-pro` | `./scripts/serve.sh --dev --gateway --daemon`<br/>`make dev-daemon-pro` | `./scripts/docker.sh start --gateway`<br/>`make docker-start-pro` | — |
 | **Prod** | `./scripts/serve.sh --prod`<br/>`make start` | `./scripts/serve.sh --prod --daemon`<br/>`make start-daemon` | — | `./scripts/deploy.sh`<br/>`make up` |
+| **Prod + Gateway** | `./scripts/serve.sh --prod --gateway`<br/>`make start-pro` | `./scripts/serve.sh --prod --gateway --daemon`<br/>`make start-daemon-pro` | — | `./scripts/deploy.sh --gateway`<br/>`make up-pro` |
 
 | Action | Local | Docker Dev | Docker Prod |
 |---|---|---|---|
 | **Stop** | `./scripts/serve.sh --stop`<br/>`make stop` | `./scripts/docker.sh stop`<br/>`make docker-stop` | `./scripts/deploy.sh down`<br/>`make down` |
 | **Restart** | `./scripts/serve.sh --restart [flags]` | `./scripts/docker.sh restart` | — |
 
+Gateway mode embeds the agent runtime in Gateway, no LangGraph server.
+
 **Nginx routing**:
-- `/api/langgraph/*` → Gateway embedded runtime (8001), rewritten to `/api/*`
+- Standard mode: `/api/langgraph/*` → LangGraph Server (2024)
+- Gateway mode: `/api/langgraph/*` → Gateway embedded runtime (8001) (via envsubst)
 - `/api/*` (other) → Gateway API (8001)
 - `/` (non-API) → Frontend (3000)
 
@@ -492,11 +479,15 @@ This starts all services and makes the application available at `http://localhos
 From the **backend** directory:
 
 ```bash
-# Gateway API
+# Terminal 1: LangGraph server
+make dev
+
+# Terminal 2: Gateway API
 make gateway
 ```
 
 Direct access (without nginx):
+- LangGraph: `http://localhost:2024`
 - Gateway: `http://localhost:8001`
 
 ### Frontend Configuration

backend/Makefile

@@ -2,7 +2,7 @@ install:
 	uv sync
 
 dev:
-	PYTHONPATH=. uv run uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001 --reload
+	uv run langgraph dev --no-browser --no-reload --n-jobs-per-worker 10
 
 gateway:
 	PYTHONPATH=. uv run uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001

backend/app/channels/__init__.py

@@ -2,7 +2,7 @@
 
 Provides a pluggable channel system that connects external messaging platforms
 (Feishu/Lark, Slack, Telegram) to the DeerFlow agent via the ChannelManager,
-which uses ``langgraph-sdk`` to communicate with Gateway's LangGraph-compatible API.
+which uses ``langgraph-sdk`` to communicate with the underlying LangGraph Server.
 """
 
 from app.channels.base import Channel

backend/app/channels/base.py

@@ -31,10 +31,6 @@ class Channel(ABC):
     def is_running(self) -> bool:
         return self._running
 
-    @property
-    def supports_streaming(self) -> bool:
-        return False
-
     # -- lifecycle ---------------------------------------------------------
 
     @abstractmethod

backend/app/channels/dingtalk.py

@@ -1,740 +0,0 @@
-"""DingTalk channel implementation."""
-
-from __future__ import annotations
-
-import asyncio
-import json
-import logging
-import re
-import threading
-import time
-from pathlib import Path
-from typing import Any
-
-import httpx
-
-from app.channels.base import Channel
-from app.channels.commands import KNOWN_CHANNEL_COMMANDS
-from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
-
-logger = logging.getLogger(__name__)
-
-DINGTALK_API_BASE = "https://api.dingtalk.com"
-
-_TOKEN_REFRESH_MARGIN_SECONDS = 300
-
-_CONVERSATION_TYPE_P2P = "1"
-_CONVERSATION_TYPE_GROUP = "2"
-
-_MAX_UPLOAD_SIZE_BYTES = 20 * 1024 * 1024
-
-
-def _normalize_conversation_type(raw: Any) -> str:
-    """Normalize ``conversationType`` to ``"1"`` (P2P) or ``"2"`` (group).
-
-    Stream payloads may send int or string values.
-    """
-    if raw is None:
-        return _CONVERSATION_TYPE_P2P
-    s = str(raw).strip()
-    if s == _CONVERSATION_TYPE_GROUP:
-        return _CONVERSATION_TYPE_GROUP
-    return _CONVERSATION_TYPE_P2P
-
-
-def _normalize_allowed_users(allowed_users: Any) -> set[str]:
-    if allowed_users is None:
-        return set()
-    if isinstance(allowed_users, str):
-        values = [allowed_users]
-    elif isinstance(allowed_users, (list, tuple, set)):
-        values = allowed_users
-    else:
-        logger.warning(
-            "DingTalk allowed_users should be a list of user IDs; treating %s as one string value",
-            type(allowed_users).__name__,
-        )
-        values = [allowed_users]
-    return {str(uid) for uid in values if str(uid)}
-
-
-def _is_dingtalk_command(text: str) -> bool:
-    if not text.startswith("/"):
-        return False
-    return text.split(maxsplit=1)[0].lower() in KNOWN_CHANNEL_COMMANDS
-
-
-def _extract_text_from_rich_text(rich_text_list: list) -> str:
-    parts: list[str] = []
-    for item in rich_text_list:
-        if isinstance(item, dict) and "text" in item:
-            parts.append(item["text"])
-    return " ".join(parts)
-
-
-_FENCED_CODE_BLOCK_RE = re.compile(r"```(\w*)\n(.*?)```", re.DOTALL)
-_INLINE_CODE_RE = re.compile(r"`([^`\n]+)`")
-_HORIZONTAL_RULE_RE = re.compile(r"^-{3,}$", re.MULTILINE)
-_TABLE_SEPARATOR_RE = re.compile(r"^\|[-:| ]+\|$", re.MULTILINE)
-
-
-def _convert_markdown_table(text: str) -> str:
-    # DingTalk sampleMarkdown does not render pipe-delimited tables.
-    lines = text.split("\n")
-    result: list[str] = []
-    i = 0
-    while i < len(lines):
-        line = lines[i]
-        # Detect table: header row followed by separator row
-        if i + 1 < len(lines) and line.strip().startswith("|") and _TABLE_SEPARATOR_RE.match(lines[i + 1].strip()):
-            headers = [h.strip() for h in line.strip().strip("|").split("|")]
-            i += 2  # skip header + separator
-            while i < len(lines) and lines[i].strip().startswith("|"):
-                cells = [c.strip() for c in lines[i].strip().strip("|").split("|")]
-                for h, c in zip(headers, cells):
-                    result.append(f"> **{h}**: {c}")
-                result.append("")
-                i += 1
-        else:
-            result.append(line)
-            i += 1
-    return "\n".join(result)
-
-
-def _adapt_markdown_for_dingtalk(text: str) -> str:
-    """Adapt markdown for DingTalk's limited sampleMarkdown renderer."""
-
-    def _code_block_to_quote(match: re.Match) -> str:
-        lang = match.group(1)
-        code = match.group(2).rstrip("\n")
-        prefix = f"> **{lang}**\n" if lang else ""
-        quoted_lines = "\n".join(f"> {line}" for line in code.split("\n"))
-        return f"{prefix}{quoted_lines}\n"
-
-    text = _FENCED_CODE_BLOCK_RE.sub(_code_block_to_quote, text)
-    text = _INLINE_CODE_RE.sub(r"**\1**", text)
-    text = _convert_markdown_table(text)
-    text = _HORIZONTAL_RULE_RE.sub("───────────", text)
-    return text
-
-
-class DingTalkChannel(Channel):
-    """DingTalk IM channel using Stream Push (WebSocket, no public IP needed)."""
-
-    def __init__(self, bus: MessageBus, config: dict[str, Any]) -> None:
-        super().__init__(name="dingtalk", bus=bus, config=config)
-        self._thread: threading.Thread | None = None
-        self._main_loop: asyncio.AbstractEventLoop | None = None
-        self._client_id: str = ""
-        self._client_secret: str = ""
-        self._allowed_users: set[str] = _normalize_allowed_users(config.get("allowed_users"))
-        self._cached_token: str = ""
-        self._token_expires_at: float = 0.0
-        self._token_lock = asyncio.Lock()
-        self._card_template_id: str = config.get("card_template_id", "")
-        self._card_track_ids: dict[str, str] = {}
-        self._dingtalk_client: Any = None
-        self._stream_client: Any = None
-        self._incoming_messages: dict[str, Any] = {}
-        self._incoming_messages_lock = threading.Lock()
-        self._card_repliers: dict[str, Any] = {}
-
-    @property
-    def supports_streaming(self) -> bool:
-        return bool(self._card_template_id)
-
-    async def start(self) -> None:
-        if self._running:
-            return
-
-        try:
-            import dingtalk_stream  # noqa: F401
-        except ImportError:
-            logger.error("dingtalk-stream is not installed. Install it with: uv add dingtalk-stream")
-            return
-
-        client_id = self.config.get("client_id", "")
-        client_secret = self.config.get("client_secret", "")
-
-        if not client_id or not client_secret:
-            logger.error("DingTalk channel requires client_id and client_secret")
-            return
-
-        self._client_id = client_id
-        self._client_secret = client_secret
-        self._main_loop = asyncio.get_running_loop()
-
-        if self._card_template_id:
-            logger.info("[DingTalk] AI Card mode enabled (template=%s)", self._card_template_id)
-
-        self._running = True
-        self.bus.subscribe_outbound(self._on_outbound)
-
-        self._thread = threading.Thread(
-            target=self._run_stream,
-            args=(client_id, client_secret),
-            daemon=True,
-        )
-        self._thread.start()
-        logger.info("DingTalk channel started")
-
-    async def stop(self) -> None:
-        self._running = False
-        self.bus.unsubscribe_outbound(self._on_outbound)
-
-        stream_client = self._stream_client
-        if stream_client is not None:
-            try:
-                if hasattr(stream_client, "disconnect"):
-                    stream_client.disconnect()
-            except Exception:
-                logger.debug("[DingTalk] error disconnecting stream client", exc_info=True)
-
-        self._dingtalk_client = None
-        self._stream_client = None
-        with self._incoming_messages_lock:
-            self._incoming_messages.clear()
-        self._card_repliers.clear()
-        self._card_track_ids.clear()
-        if self._thread:
-            self._thread.join(timeout=5)
-            self._thread = None
-        logger.info("DingTalk channel stopped")
-
-    def _resolve_routing(self, msg: OutboundMessage) -> tuple[str, str, str]:
-        """Return (conversation_type, sender_staff_id, conversation_id).
-
-        Uses msg.chat_id as the primary routing key; metadata as fallback.
-        """
-        conversation_type = _normalize_conversation_type(msg.metadata.get("conversation_type"))
-        sender_staff_id = msg.metadata.get("sender_staff_id", "")
-        conversation_id = msg.metadata.get("conversation_id", "")
-        if conversation_type == _CONVERSATION_TYPE_GROUP:
-            conversation_id = msg.chat_id or conversation_id
-        else:
-            sender_staff_id = msg.chat_id or sender_staff_id
-        return conversation_type, sender_staff_id, conversation_id
-
-    async def send(self, msg: OutboundMessage, *, _max_retries: int = 3) -> None:
-        conversation_type, sender_staff_id, conversation_id = self._resolve_routing(msg)
-        robot_code = self._client_id
-
-        # Card mode: stream update to existing AI card
-        source_key = self._make_card_source_key_from_outbound(msg)
-        out_track_id = self._card_track_ids.get(source_key)
-
-        # ``card_template_id`` enables ``runs.stream`` (non-final + final outbounds).
-        # If card creation failed, skip non-final chunks to avoid duplicate messages.
-        if self._card_template_id and not out_track_id and not msg.is_final:
-            return
-
-        if out_track_id:
-            try:
-                await self._stream_update_card(
-                    out_track_id,
-                    msg.text,
-                    is_finalize=msg.is_final,
-                )
-            except Exception:
-                logger.warning("[DingTalk] card stream failed, falling back to sampleMarkdown")
-                if msg.is_final:
-                    self._card_track_ids.pop(source_key, None)
-                    self._card_repliers.pop(out_track_id, None)
-                    await self._send_markdown_fallback(robot_code, conversation_type, sender_staff_id, conversation_id, msg.text)
-                    return
-            if msg.is_final:
-                self._card_track_ids.pop(source_key, None)
-                self._card_repliers.pop(out_track_id, None)
-            return
-
-        # Non-card mode: send sampleMarkdown with retry
-        last_exc: Exception | None = None
-        for attempt in range(_max_retries):
-            try:
-                if conversation_type == _CONVERSATION_TYPE_GROUP:
-                    await self._send_group_message(robot_code, conversation_id, msg.text, at_user_ids=[sender_staff_id] if sender_staff_id else None)
-                else:
-                    await self._send_p2p_message(robot_code, sender_staff_id, msg.text)
-                return
-            except Exception as exc:
-                last_exc = exc
-                if attempt < _max_retries - 1:
-                    delay = 2**attempt
-                    logger.warning(
-                        "[DingTalk] send failed (attempt %d/%d), retrying in %ds: %s",
-                        attempt + 1,
-                        _max_retries,
-                        delay,
-                        exc,
-                    )
-                    await asyncio.sleep(delay)
-
-        logger.error("[DingTalk] send failed after %d attempts: %s", _max_retries, last_exc)
-        if last_exc is None:
-            raise RuntimeError("DingTalk send failed without an exception from any attempt")
-        raise last_exc
-
-    async def _send_markdown_fallback(
-        self,
-        robot_code: str,
-        conversation_type: str,
-        sender_staff_id: str,
-        conversation_id: str,
-        text: str,
-    ) -> None:
-        try:
-            if conversation_type == _CONVERSATION_TYPE_GROUP:
-                await self._send_group_message(robot_code, conversation_id, text)
-            else:
-                await self._send_p2p_message(robot_code, sender_staff_id, text)
-        except Exception:
-            logger.exception("[DingTalk] markdown fallback also failed")
-            raise
-
-    async def send_file(self, msg: OutboundMessage, attachment: ResolvedAttachment) -> bool:
-        if attachment.size > _MAX_UPLOAD_SIZE_BYTES:
-            logger.warning("[DingTalk] file too large (%d bytes), skipping: %s", attachment.size, attachment.filename)
-            return False
-
-        conversation_type, sender_staff_id, conversation_id = self._resolve_routing(msg)
-        robot_code = self._client_id
-
-        try:
-            media_id = await self._upload_media(attachment.actual_path, "image" if attachment.is_image else "file")
-            if not media_id:
-                return False
-
-            if attachment.is_image:
-                msg_key = "sampleImageMsg"
-                msg_param = json.dumps({"photoURL": media_id})
-            else:
-                msg_key = "sampleFile"
-                msg_param = json.dumps(
-                    {
-                        "fileUrl": media_id,
-                        "fileName": attachment.filename,
-                        "fileSize": str(attachment.size),
-                    }
-                )
-
-            token = await self._get_access_token()
-            async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-                if conversation_type == _CONVERSATION_TYPE_GROUP:
-                    response = await client.post(
-                        f"{DINGTALK_API_BASE}/v1.0/robot/groupMessages/send",
-                        headers=self._api_headers(token),
-                        json={
-                            "msgKey": msg_key,
-                            "msgParam": msg_param,
-                            "robotCode": robot_code,
-                            "openConversationId": conversation_id,
-                        },
-                    )
-                else:
-                    response = await client.post(
-                        f"{DINGTALK_API_BASE}/v1.0/robot/oToMessages/batchSend",
-                        headers=self._api_headers(token),
-                        json={
-                            "msgKey": msg_key,
-                            "msgParam": msg_param,
-                            "robotCode": robot_code,
-                            "userIds": [sender_staff_id],
-                        },
-                    )
-                response.raise_for_status()
-
-            logger.info("[DingTalk] file sent: %s", attachment.filename)
-            return True
-        except (httpx.HTTPError, OSError, ValueError, TypeError, AttributeError):
-            logger.exception("[DingTalk] failed to send file: %s", attachment.filename)
-            return False
-
-    # -- stream client (runs in dedicated thread) --------------------------
-
-    def _run_stream(self, client_id: str, client_secret: str) -> None:
-        try:
-            import dingtalk_stream
-
-            credential = dingtalk_stream.Credential(client_id, client_secret)
-            client = dingtalk_stream.DingTalkStreamClient(credential)
-            self._stream_client = client
-            client.register_callback_handler(
-                dingtalk_stream.chatbot.ChatbotMessage.TOPIC,
-                _DingTalkMessageHandler(self),
-            )
-            client.start_forever()
-        except Exception:
-            if self._running:
-                logger.exception("DingTalk Stream Push error")
-        finally:
-            self._stream_client = None
-
-    def _on_chatbot_message(self, message: Any) -> None:
-        if not self._running:
-            return
-        try:
-            sender_staff_id = message.sender_staff_id or ""
-            conversation_type = _normalize_conversation_type(message.conversation_type)
-            conversation_id = message.conversation_id or ""
-            msg_id = message.message_id or ""
-            sender_nick = message.sender_nick or ""
-
-            if self._allowed_users and sender_staff_id not in self._allowed_users:
-                logger.debug("[DingTalk] ignoring message from non-allowed user: %s", sender_staff_id)
-                return
-
-            text = self._extract_text(message)
-            if not text:
-                logger.info("[DingTalk] empty text, ignoring message")
-                return
-
-            logger.info(
-                "[DingTalk] parsed message: conv_type=%s, msg_id=%s, sender=%s(%s), text=%r",
-                conversation_type,
-                msg_id,
-                sender_staff_id,
-                sender_nick,
-                text[:100],
-            )
-
-            if _is_dingtalk_command(text):
-                msg_type = InboundMessageType.COMMAND
-            else:
-                msg_type = InboundMessageType.CHAT
-
-            # P2P: topic_id=None (single thread per user, like Telegram private chat)
-            # Group: topic_id=msg_id (each new message starts a new topic, like Feishu)
-            topic_id: str | None = msg_id if conversation_type == _CONVERSATION_TYPE_GROUP else None
-
-            # chat_id uses conversation_id for groups, sender_staff_id for P2P
-            chat_id = conversation_id if conversation_type == _CONVERSATION_TYPE_GROUP else sender_staff_id
-
-            inbound = self._make_inbound(
-                chat_id=chat_id,
-                user_id=sender_staff_id,
-                text=text,
-                msg_type=msg_type,
-                thread_ts=msg_id,
-                metadata={
-                    "conversation_type": conversation_type,
-                    "conversation_id": conversation_id,
-                    "sender_staff_id": sender_staff_id,
-                    "sender_nick": sender_nick,
-                    "message_id": msg_id,
-                },
-            )
-            inbound.topic_id = topic_id
-
-            if self._card_template_id:
-                source_key = self._make_card_source_key(inbound)
-                with self._incoming_messages_lock:
-                    self._incoming_messages[source_key] = message
-
-            if self._main_loop and self._main_loop.is_running():
-                logger.info("[DingTalk] publishing inbound message to bus (type=%s, msg_id=%s)", msg_type.value, msg_id)
-                fut = asyncio.run_coroutine_threadsafe(
-                    self._prepare_inbound(chat_id, inbound),
-                    self._main_loop,
-                )
-                fut.add_done_callback(lambda f, mid=msg_id: self._log_future_error(f, "prepare_inbound", mid))
-            else:
-                logger.warning("[DingTalk] main loop not running, cannot publish inbound message")
-        except Exception:
-            logger.exception("[DingTalk] error processing chatbot message")
-
-    @staticmethod
-    def _extract_text(message: Any) -> str:
-        msg_type = message.message_type
-        if msg_type == "text" and message.text:
-            return message.text.content.strip()
-        if msg_type == "richText" and message.rich_text_content:
-            return _extract_text_from_rich_text(message.rich_text_content.rich_text_list).strip()
-        return ""
-
-    async def _prepare_inbound(self, chat_id: str, inbound: InboundMessage) -> None:
-        # Running reply must finish before publish_inbound so AI card tracks are
-        # registered before the manager emits streaming outbounds.
-        await self._send_running_reply(chat_id, inbound)
-        await self.bus.publish_inbound(inbound)
-
-    async def _send_running_reply(self, chat_id: str, inbound: InboundMessage) -> None:
-        conversation_type = inbound.metadata.get("conversation_type", _CONVERSATION_TYPE_P2P)
-        sender_staff_id = inbound.metadata.get("sender_staff_id", "")
-        conversation_id = inbound.metadata.get("conversation_id", "")
-        text = "\u23f3 Working on it..."
-
-        try:
-            if self._card_template_id:
-                source_key = self._make_card_source_key(inbound)
-                with self._incoming_messages_lock:
-                    chatbot_message = self._incoming_messages.pop(source_key, None)
-                out_track_id = await self._create_and_deliver_card(
-                    text,
-                    chatbot_message=chatbot_message,
-                )
-                if out_track_id:
-                    self._card_track_ids[source_key] = out_track_id
-                    logger.info("[DingTalk] AI card running reply sent for chat=%s", chat_id)
-                    return
-
-            robot_code = self._client_id
-            if conversation_type == _CONVERSATION_TYPE_GROUP:
-                await self._send_text_message_to_group(robot_code, conversation_id, text)
-            else:
-                await self._send_text_message_to_user(robot_code, sender_staff_id, text)
-            logger.info("[DingTalk] 'Working on it...' reply sent for chat=%s", chat_id)
-        except Exception:
-            logger.exception("[DingTalk] failed to send running reply for chat=%s", chat_id)
-
-    # -- DingTalk API helpers ----------------------------------------------
-
-    async def _get_access_token(self) -> str:
-        if self._cached_token and time.monotonic() < self._token_expires_at:
-            return self._cached_token
-        async with self._token_lock:
-            if self._cached_token and time.monotonic() < self._token_expires_at:
-                return self._cached_token
-            async with httpx.AsyncClient(timeout=httpx.Timeout(10.0)) as client:
-                response = await client.post(
-                    f"{DINGTALK_API_BASE}/v1.0/oauth2/accessToken",
-                    json={"appKey": self._client_id, "appSecret": self._client_secret},  # DingTalk API field names
-                )
-                response.raise_for_status()
-                data = response.json()
-
-                if not isinstance(data, dict):
-                    raise ValueError(f"DingTalk access token response must be a JSON object, got {type(data).__name__}")
-
-                access_token = data.get("accessToken")
-                if not isinstance(access_token, str) or not access_token.strip():
-                    raise ValueError("DingTalk access token response did not contain a usable accessToken")
-
-                raw_expires_in = data.get("expireIn", 7200)
-                try:
-                    expires_in = int(raw_expires_in)
-                except (TypeError, ValueError):
-                    logger.warning("[DingTalk] invalid expireIn value %r, using default 7200s", raw_expires_in)
-                    expires_in = 7200
-
-                self._cached_token = access_token.strip()
-                self._token_expires_at = time.monotonic() + expires_in - _TOKEN_REFRESH_MARGIN_SECONDS
-                return self._cached_token
-
-    @staticmethod
-    def _api_headers(token: str) -> dict[str, str]:
-        return {
-            "x-acs-dingtalk-access-token": token,
-            "Content-Type": "application/json",
-        }
-
-    async def _send_text_message_to_user(self, robot_code: str, user_id: str, text: str) -> None:
-        token = await self._get_access_token()
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/oToMessages/batchSend",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleText",
-                    "msgParam": json.dumps({"content": text}),
-                    "robotCode": robot_code,
-                    "userIds": [user_id],
-                },
-            )
-            response.raise_for_status()
-
-    async def _send_text_message_to_group(self, robot_code: str, conversation_id: str, text: str) -> None:
-        token = await self._get_access_token()
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/groupMessages/send",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleText",
-                    "msgParam": json.dumps({"content": text}),
-                    "robotCode": robot_code,
-                    "openConversationId": conversation_id,
-                },
-            )
-            response.raise_for_status()
-
-    async def _send_p2p_message(self, robot_code: str, user_id: str, text: str) -> None:
-        text = _adapt_markdown_for_dingtalk(text)
-        token = await self._get_access_token()
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/oToMessages/batchSend",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleMarkdown",
-                    "msgParam": json.dumps({"title": "DeerFlow", "text": text}),
-                    "robotCode": robot_code,
-                    "userIds": [user_id],
-                },
-            )
-            response.raise_for_status()
-            data = response.json()
-            if data.get("processQueryKey"):
-                logger.info("[DingTalk] P2P message sent to user=%s", user_id)
-            else:
-                logger.warning("[DingTalk] P2P send response: %s", data)
-
-    async def _send_group_message(
-        self,
-        robot_code: str,
-        conversation_id: str,
-        text: str,
-        *,
-        at_user_ids: list[str] | None = None,  # noqa: ARG002
-    ) -> None:
-        # at_user_ids accepted for call-site compatibility but not passed to the API
-        # (sampleMarkdown does not support @mentions).
-        text = _adapt_markdown_for_dingtalk(text)
-        token = await self._get_access_token()
-
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/groupMessages/send",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleMarkdown",
-                    "msgParam": json.dumps({"title": "DeerFlow", "text": text}),
-                    "robotCode": robot_code,
-                    "openConversationId": conversation_id,
-                },
-            )
-            response.raise_for_status()
-            data = response.json()
-            if data.get("processQueryKey"):
-                logger.info("[DingTalk] group message sent to conversation=%s", conversation_id)
-            else:
-                logger.warning("[DingTalk] group send response: %s", data)
-
-    # -- AI Card streaming helpers -------------------------------------------
-
-    def _make_card_source_key(self, inbound: InboundMessage) -> str:
-        m = inbound.metadata
-        return f"{m.get('conversation_type', '')}:{m.get('sender_staff_id', '')}:{m.get('conversation_id', '')}:{m.get('message_id', '')}"
-
-    def _make_card_source_key_from_outbound(self, msg: OutboundMessage) -> str:
-        m = msg.metadata
-        correlation_id = m.get("message_id") or msg.thread_ts or ""
-        return f"{m.get('conversation_type', '')}:{m.get('sender_staff_id', '')}:{m.get('conversation_id', '')}:{correlation_id}"
-
-    async def _create_and_deliver_card(
-        self,
-        initial_text: str,
-        *,
-        chatbot_message: Any = None,
-    ) -> str | None:
-        if self._dingtalk_client is None or chatbot_message is None:
-            logger.warning("[DingTalk] SDK client or chatbot_message unavailable, skipping AI card")
-            return None
-
-        try:
-            from dingtalk_stream.card_replier import AICardReplier
-        except ImportError:
-            logger.warning("[DingTalk] dingtalk-stream card_replier not available")
-            return None
-
-        try:
-            replier = AICardReplier(self._dingtalk_client, chatbot_message)
-            card_instance_id = await replier.async_create_and_deliver_card(
-                card_template_id=self._card_template_id,
-                card_data={"content": initial_text},
-            )
-            if not card_instance_id:
-                return None
-
-            self._card_repliers[card_instance_id] = replier
-            logger.info("[DingTalk] AI card created: outTrackId=%s", card_instance_id)
-            return card_instance_id
-        except Exception:
-            logger.exception("[DingTalk] failed to create AI card")
-            return None
-
-    async def _stream_update_card(
-        self,
-        out_track_id: str,
-        content: str,
-        *,
-        is_finalize: bool = False,
-        is_error: bool = False,
-    ) -> None:
-        replier = self._card_repliers.get(out_track_id)
-        if not replier:
-            raise RuntimeError(f"No AICardReplier found for track ID {out_track_id}")
-
-        await replier.async_streaming(
-            card_instance_id=out_track_id,
-            content_key="content",
-            content_value=content,
-            append=False,
-            finished=is_finalize,
-            failed=is_error,
-        )
-
-    # -- media upload --------------------------------------------------------
-
-    async def _upload_media(self, file_path: str | Path, media_type: str) -> str | None:
-        try:
-            file_bytes = await asyncio.to_thread(Path(file_path).read_bytes)
-            token = await self._get_access_token()
-            async with httpx.AsyncClient(timeout=httpx.Timeout(60.0)) as client:
-                response = await client.post(
-                    f"{DINGTALK_API_BASE}/v1.0/files/upload",
-                    headers={"x-acs-dingtalk-access-token": token},
-                    files={"file": ("upload", file_bytes)},
-                    data={"type": media_type},
-                )
-                response.raise_for_status()
-                try:
-                    payload = response.json()
-                except json.JSONDecodeError:
-                    logger.exception("[DingTalk] failed to decode upload response JSON: %s", file_path)
-                    return None
-                if not isinstance(payload, dict):
-                    logger.warning("[DingTalk] unexpected upload response type %s for %s", type(payload).__name__, file_path)
-                    return None
-                return payload.get("mediaId")
-        except (httpx.HTTPError, OSError):
-            logger.exception("[DingTalk] failed to upload media: %s", file_path)
-            return None
-
-    @staticmethod
-    def _log_future_error(fut: Any, name: str, msg_id: str) -> None:
-        try:
-            exc = fut.exception()
-            if exc:
-                logger.error("[DingTalk] %s failed for msg_id=%s: %s", name, msg_id, exc)
-        except (asyncio.CancelledError, asyncio.InvalidStateError):
-            pass
-
-
-class _DingTalkMessageHandler:
-    """Callback handler registered with dingtalk-stream."""
-
-    def __init__(self, channel: DingTalkChannel) -> None:
-        self._channel = channel
-
-    def pre_start(self) -> None:
-        if hasattr(self, "dingtalk_client") and self.dingtalk_client is not None:
-            self._channel._dingtalk_client = self.dingtalk_client
-
-    async def raw_process(self, callback_message: Any) -> Any:
-        import dingtalk_stream
-        from dingtalk_stream.frames import Headers
-
-        code, message = await self.process(callback_message)
-        ack_message = dingtalk_stream.AckMessage()
-        ack_message.code = code
-        ack_message.headers.message_id = callback_message.headers.message_id
-        ack_message.headers.content_type = Headers.CONTENT_TYPE_APPLICATION_JSON
-        ack_message.data = {"response": message}
-        return ack_message
-
-    async def process(self, callback: Any) -> tuple[int, str]:
-        import dingtalk_stream
-
-        incoming_message = dingtalk_stream.ChatbotMessage.from_dict(callback.data)
-        self._channel._on_chatbot_message(incoming_message)
-        return dingtalk_stream.AckMessage.STATUS_OK, "OK"

backend/app/channels/discord.py

@@ -1,273 +0,0 @@
-"""Discord channel integration using discord.py."""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-import threading
-from typing import Any
-
-from app.channels.base import Channel
-from app.channels.message_bus import InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
-
-logger = logging.getLogger(__name__)
-
-_DISCORD_MAX_MESSAGE_LEN = 2000
-
-
-class DiscordChannel(Channel):
-    """Discord bot channel.
-
-    Configuration keys (in ``config.yaml`` under ``channels.discord``):
-        - ``bot_token``: Discord Bot token.
-        - ``allowed_guilds``: (optional) List of allowed Discord guild IDs. Empty = allow all.
-    """
-
-    def __init__(self, bus: MessageBus, config: dict[str, Any]) -> None:
-        super().__init__(name="discord", bus=bus, config=config)
-        self._bot_token = str(config.get("bot_token", "")).strip()
-        self._allowed_guilds: set[int] = set()
-        for guild_id in config.get("allowed_guilds", []):
-            try:
-                self._allowed_guilds.add(int(guild_id))
-            except (TypeError, ValueError):
-                continue
-
-        self._client = None
-        self._thread: threading.Thread | None = None
-        self._discord_loop: asyncio.AbstractEventLoop | None = None
-        self._main_loop: asyncio.AbstractEventLoop | None = None
-        self._discord_module = None
-
-    async def start(self) -> None:
-        if self._running:
-            return
-
-        try:
-            import discord
-        except ImportError:
-            logger.error("discord.py is not installed. Install it with: uv add discord.py")
-            return
-
-        if not self._bot_token:
-            logger.error("Discord channel requires bot_token")
-            return
-
-        intents = discord.Intents.default()
-        intents.messages = True
-        intents.guilds = True
-        intents.message_content = True
-
-        client = discord.Client(
-            intents=intents,
-            allowed_mentions=discord.AllowedMentions.none(),
-        )
-        self._client = client
-        self._discord_module = discord
-        self._main_loop = asyncio.get_event_loop()
-
-        @client.event
-        async def on_message(message) -> None:
-            await self._on_message(message)
-
-        self._running = True
-        self.bus.subscribe_outbound(self._on_outbound)
-
-        self._thread = threading.Thread(target=self._run_client, daemon=True)
-        self._thread.start()
-        logger.info("Discord channel started")
-
-    async def stop(self) -> None:
-        self._running = False
-        self.bus.unsubscribe_outbound(self._on_outbound)
-
-        if self._client and self._discord_loop and self._discord_loop.is_running():
-            close_future = asyncio.run_coroutine_threadsafe(self._client.close(), self._discord_loop)
-            try:
-                await asyncio.wait_for(asyncio.wrap_future(close_future), timeout=10)
-            except TimeoutError:
-                logger.warning("[Discord] client close timed out after 10s")
-            except Exception:
-                logger.exception("[Discord] error while closing client")
-
-        if self._thread:
-            self._thread.join(timeout=10)
-            self._thread = None
-
-        self._client = None
-        self._discord_loop = None
-        self._discord_module = None
-        logger.info("Discord channel stopped")
-
-    async def send(self, msg: OutboundMessage) -> None:
-        target = await self._resolve_target(msg)
-        if target is None:
-            logger.error("[Discord] target not found for chat_id=%s thread_ts=%s", msg.chat_id, msg.thread_ts)
-            return
-
-        text = msg.text or ""
-        for chunk in self._split_text(text):
-            send_future = asyncio.run_coroutine_threadsafe(target.send(chunk), self._discord_loop)
-            await asyncio.wrap_future(send_future)
-
-    async def send_file(self, msg: OutboundMessage, attachment: ResolvedAttachment) -> bool:
-        target = await self._resolve_target(msg)
-        if target is None:
-            logger.error("[Discord] target not found for file upload chat_id=%s thread_ts=%s", msg.chat_id, msg.thread_ts)
-            return False
-
-        if self._discord_module is None:
-            return False
-
-        try:
-            fp = open(str(attachment.actual_path), "rb")  # noqa: SIM115
-            file = self._discord_module.File(fp, filename=attachment.filename)
-            send_future = asyncio.run_coroutine_threadsafe(target.send(file=file), self._discord_loop)
-            await asyncio.wrap_future(send_future)
-            logger.info("[Discord] file uploaded: %s", attachment.filename)
-            return True
-        except Exception:
-            logger.exception("[Discord] failed to upload file: %s", attachment.filename)
-            return False
-
-    async def _on_message(self, message) -> None:
-        if not self._running or not self._client:
-            return
-
-        if message.author.bot:
-            return
-
-        if self._client.user and message.author.id == self._client.user.id:
-            return
-
-        guild = message.guild
-        if self._allowed_guilds:
-            if guild is None or guild.id not in self._allowed_guilds:
-                return
-
-        text = (message.content or "").strip()
-        if not text:
-            return
-
-        if self._discord_module is None:
-            return
-
-        if isinstance(message.channel, self._discord_module.Thread):
-            chat_id = str(message.channel.parent_id or message.channel.id)
-            thread_id = str(message.channel.id)
-        else:
-            thread = await self._create_thread(message)
-            if thread is None:
-                return
-            chat_id = str(message.channel.id)
-            thread_id = str(thread.id)
-
-        msg_type = InboundMessageType.COMMAND if text.startswith("/") else InboundMessageType.CHAT
-        inbound = self._make_inbound(
-            chat_id=chat_id,
-            user_id=str(message.author.id),
-            text=text,
-            msg_type=msg_type,
-            thread_ts=thread_id,
-            metadata={
-                "guild_id": str(guild.id) if guild else None,
-                "channel_id": str(message.channel.id),
-                "message_id": str(message.id),
-            },
-        )
-        inbound.topic_id = thread_id
-
-        if self._main_loop and self._main_loop.is_running():
-            future = asyncio.run_coroutine_threadsafe(self.bus.publish_inbound(inbound), self._main_loop)
-            future.add_done_callback(lambda f: logger.exception("[Discord] publish_inbound failed", exc_info=f.exception()) if f.exception() else None)
-
-    def _run_client(self) -> None:
-        self._discord_loop = asyncio.new_event_loop()
-        asyncio.set_event_loop(self._discord_loop)
-        try:
-            self._discord_loop.run_until_complete(self._client.start(self._bot_token))
-        except Exception:
-            if self._running:
-                logger.exception("Discord client error")
-        finally:
-            try:
-                if self._client and not self._client.is_closed():
-                    self._discord_loop.run_until_complete(self._client.close())
-            except Exception:
-                logger.exception("Error during Discord shutdown")
-
-    async def _create_thread(self, message):
-        try:
-            thread_name = f"deerflow-{message.author.display_name}-{message.id}"[:100]
-            return await message.create_thread(name=thread_name)
-        except Exception:
-            logger.exception("[Discord] failed to create thread for message=%s (threads may be disabled or missing permissions)", message.id)
-            try:
-                await message.channel.send("Could not create a thread for your message. Please check that threads are enabled in this channel.")
-            except Exception:
-                pass
-            return None
-
-    async def _resolve_target(self, msg: OutboundMessage):
-        if not self._client or not self._discord_loop:
-            return None
-
-        target_ids: list[str] = []
-        if msg.thread_ts:
-            target_ids.append(msg.thread_ts)
-        if msg.chat_id and msg.chat_id not in target_ids:
-            target_ids.append(msg.chat_id)
-
-        for raw_id in target_ids:
-            target = await self._get_channel_or_thread(raw_id)
-            if target is not None:
-                return target
-        return None
-
-    async def _get_channel_or_thread(self, raw_id: str):
-        if not self._client or not self._discord_loop:
-            return None
-
-        try:
-            target_id = int(raw_id)
-        except (TypeError, ValueError):
-            return None
-
-        get_future = asyncio.run_coroutine_threadsafe(self._fetch_channel(target_id), self._discord_loop)
-        try:
-            return await asyncio.wrap_future(get_future)
-        except Exception:
-            logger.exception("[Discord] failed to resolve target id=%s", raw_id)
-            return None
-
-    async def _fetch_channel(self, target_id: int):
-        if not self._client:
-            return None
-
-        channel = self._client.get_channel(target_id)
-        if channel is not None:
-            return channel
-
-        try:
-            return await self._client.fetch_channel(target_id)
-        except Exception:
-            return None
-
-    @staticmethod
-    def _split_text(text: str) -> list[str]:
-        if not text:
-            return [""]
-
-        chunks: list[str] = []
-        remaining = text
-        while len(remaining) > _DISCORD_MAX_MESSAGE_LEN:
-            split_at = remaining.rfind("\n", 0, _DISCORD_MAX_MESSAGE_LEN)
-            if split_at <= 0:
-                split_at = _DISCORD_MAX_MESSAGE_LEN
-            chunks.append(remaining[:split_at])
-            remaining = remaining[split_at:].lstrip("\n")
-
-        if remaining:
-            chunks.append(remaining)
-
-        return chunks

backend/app/channels/feishu.py

@@ -13,7 +13,6 @@ from app.channels.base import Channel
 from app.channels.commands import KNOWN_CHANNEL_COMMANDS
 from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
 from deerflow.config.paths import VIRTUAL_PATH_PREFIX, get_paths
-from deerflow.runtime.user_context import get_effective_user_id
 from deerflow.sandbox.sandbox_provider import get_sandbox_provider
 
 logger = logging.getLogger(__name__)
@@ -63,10 +62,6 @@ class FeishuChannel(Channel):
         self._GetMessageResourceRequest = None
         self._thread_lock = threading.Lock()
 
-    @property
-    def supports_streaming(self) -> bool:
-        return True
-
     async def start(self) -> None:
         if self._running:
             return
@@ -349,9 +344,8 @@ class FeishuChannel(Channel):
             return f"Failed to obtain the [{type}]"
 
         paths = get_paths()
-        user_id = get_effective_user_id()
-        paths.ensure_thread_dirs(thread_id, user_id=user_id)
-        uploads_dir = paths.sandbox_uploads_dir(thread_id, user_id=user_id).resolve()
+        paths.ensure_thread_dirs(thread_id)
+        uploads_dir = paths.sandbox_uploads_dir(thread_id).resolve()
 
         ext = "png" if type == "image" else "bin"
         raw_filename = getattr(response, "file_name", "") or f"feishu_{file_key[-12:]}.{ext}"

backend/app/channels/manager.py

@@ -1,4 +1,4 @@
-"""ChannelManager — consumes inbound messages and dispatches them to the DeerFlow agent via Gateway."""
+"""ChannelManager — consumes inbound messages and dispatches them to the DeerFlow agent via LangGraph Server."""
 
 from __future__ import annotations
 
@@ -17,13 +17,10 @@ from langgraph_sdk.errors import ConflictError
 from app.channels.commands import KNOWN_CHANNEL_COMMANDS
 from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
 from app.channels.store import ChannelStore
-from app.gateway.csrf_middleware import CSRF_COOKIE_NAME, CSRF_HEADER_NAME, generate_csrf_token
-from app.gateway.internal_auth import create_internal_auth_headers
-from deerflow.runtime.user_context import get_effective_user_id
 
 logger = logging.getLogger(__name__)
 
-DEFAULT_LANGGRAPH_URL = "http://localhost:8001/api"
+DEFAULT_LANGGRAPH_URL = "http://localhost:2024"
 DEFAULT_GATEWAY_URL = "http://localhost:8001"
 DEFAULT_ASSISTANT_ID = "lead_agent"
 CUSTOM_AGENT_NAME_PATTERN = re.compile(r"^[A-Za-z0-9-]+$")
@@ -38,8 +35,6 @@ STREAM_UPDATE_MIN_INTERVAL_SECONDS = 0.35
 THREAD_BUSY_MESSAGE = "This conversation is already processing another request. Please wait for it to finish and try again."
 
 CHANNEL_CAPABILITIES = {
-    "dingtalk": {"supports_streaming": False},
-    "discord": {"supports_streaming": False},
     "feishu": {"supports_streaming": True},
     "slack": {"supports_streaming": False},
     "telegram": {"supports_streaming": False},
@@ -49,13 +44,6 @@ CHANNEL_CAPABILITIES = {
 
 InboundFileReader = Callable[[dict[str, Any], httpx.AsyncClient], Awaitable[bytes | None]]
 
-_METADATA_DROP_KEYS = frozenset({"raw_message", "ref_msg"})
-
-
-def _slim_metadata(meta: dict[str, Any]) -> dict[str, Any]:
-    """Return a shallow copy of *meta* with known-large keys removed."""
-    return {k: v for k, v in meta.items() if k not in _METADATA_DROP_KEYS}
-
 
 INBOUND_FILE_READERS: dict[str, InboundFileReader] = {}
 
@@ -353,15 +341,14 @@ def _resolve_attachments(thread_id: str, artifacts: list[str]) -> list[ResolvedA
 
     attachments: list[ResolvedAttachment] = []
     paths = get_paths()
-    user_id = get_effective_user_id()
-    outputs_dir = paths.sandbox_outputs_dir(thread_id, user_id=user_id).resolve()
+    outputs_dir = paths.sandbox_outputs_dir(thread_id).resolve()
     for virtual_path in artifacts:
         # Security: only allow files from the agent outputs directory
         if not virtual_path.startswith(_OUTPUTS_VIRTUAL_PREFIX):
             logger.warning("[Manager] rejected non-outputs artifact path: %s", virtual_path)
             continue
         try:
-            actual = paths.resolve_virtual_path(thread_id, virtual_path, user_id=user_id)
+            actual = paths.resolve_virtual_path(thread_id, virtual_path)
             # Verify the resolved path is actually under the outputs directory
             # (guards against path-traversal even after prefix check)
             try:
@@ -519,7 +506,7 @@ class ChannelManager:
     """Core dispatcher that bridges IM channels to the DeerFlow agent.
 
     It reads from the MessageBus inbound queue, creates/reuses threads on
-    Gateway's LangGraph-compatible API, sends messages via ``runs.wait``, and publishes
+    the LangGraph Server, sends messages via ``runs.wait``, and publishes
     outbound responses back through the bus.
     """
 
@@ -544,20 +531,12 @@ class ChannelManager:
         self._default_session = _as_dict(default_session)
         self._channel_sessions = dict(channel_sessions or {})
         self._client = None  # lazy init — langgraph_sdk async client
-        self._csrf_token = generate_csrf_token()
         self._semaphore: asyncio.Semaphore | None = None
         self._running = False
         self._task: asyncio.Task | None = None
 
     @staticmethod
     def _channel_supports_streaming(channel_name: str) -> bool:
-        from .service import get_channel_service
-
-        service = get_channel_service()
-        if service:
-            channel = service.get_channel(channel_name)
-            if channel is not None:
-                return channel.supports_streaming
         return CHANNEL_CAPABILITIES.get(channel_name, {}).get("supports_streaming", False)
 
     def _resolve_session_layer(self, msg: InboundMessage) -> tuple[dict[str, Any], dict[str, Any]]:
@@ -604,14 +583,7 @@ class ChannelManager:
         if self._client is None:
             from langgraph_sdk import get_client
 
-            self._client = get_client(
-                url=self._langgraph_url,
-                headers={
-                    **create_internal_auth_headers(),
-                    CSRF_HEADER_NAME: self._csrf_token,
-                    "Cookie": f"{CSRF_COOKIE_NAME}={self._csrf_token}",
-                },
-            )
+            self._client = get_client(url=self._langgraph_url)
         return self._client
 
     # -- lifecycle ---------------------------------------------------------
@@ -694,7 +666,7 @@ class ChannelManager:
     # -- chat handling -----------------------------------------------------
 
     async def _create_thread(self, client, msg: InboundMessage) -> str:
-        """Create a new thread through Gateway and store the mapping."""
+        """Create a new thread on the LangGraph Server and store the mapping."""
         thread = await client.threads.create()
         thread_id = thread["thread_id"]
         self.store.set_thread_id(
@@ -704,7 +676,7 @@ class ChannelManager:
             topic_id=msg.topic_id,
             user_id=msg.user_id,
         )
-        logger.info("[Manager] new thread created through Gateway: thread_id=%s for chat_id=%s topic_id=%s", thread_id, msg.chat_id, msg.topic_id)
+        logger.info("[Manager] new thread created on LangGraph Server: thread_id=%s for chat_id=%s topic_id=%s", thread_id, msg.chat_id, msg.topic_id)
         return thread_id
 
     async def _handle_chat(self, msg: InboundMessage, extra_context: dict[str, Any] | None = None) -> None:
@@ -787,7 +759,6 @@ class ChannelManager:
             artifacts=artifacts,
             attachments=attachments,
             thread_ts=msg.thread_ts,
-            metadata=_slim_metadata(msg.metadata),
         )
         logger.info("[Manager] publishing outbound message to bus: channel=%s, chat_id=%s", msg.channel_name, msg.chat_id)
         await self.bus.publish_outbound(outbound)
@@ -849,7 +820,6 @@ class ChannelManager:
                         text=latest_text,
                         is_final=False,
                         thread_ts=msg.thread_ts,
-                        metadata=_slim_metadata(msg.metadata),
                     )
                 )
                 last_published_text = latest_text
@@ -894,7 +864,6 @@ class ChannelManager:
                     attachments=attachments,
                     is_final=True,
                     thread_ts=msg.thread_ts,
-                    metadata=_slim_metadata(msg.metadata),
                 )
             )
 
@@ -914,7 +883,7 @@ class ChannelManager:
             return
 
         if command == "new":
-            # Create a new thread through Gateway
+            # Create a new thread on the LangGraph Server
             client = self._get_client()
             thread = await client.threads.create()
             new_thread_id = thread["thread_id"]
@@ -953,7 +922,6 @@ class ChannelManager:
             thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id) or "",
             text=reply,
             thread_ts=msg.thread_ts,
-            metadata=_slim_metadata(msg.metadata),
         )
         await self.bus.publish_outbound(outbound)
 
@@ -987,6 +955,5 @@ class ChannelManager:
             thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id) or "",
             text=error_text,
             thread_ts=msg.thread_ts,
-            metadata=_slim_metadata(msg.metadata),
         )
         await self.bus.publish_outbound(outbound)

backend/app/channels/service.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 import logging
 import os
-from typing import TYPE_CHECKING, Any
+from typing import Any
 
 from app.channels.base import Channel
 from app.channels.manager import DEFAULT_GATEWAY_URL, DEFAULT_LANGGRAPH_URL, ChannelManager
@@ -13,13 +13,8 @@ from app.channels.store import ChannelStore
 
 logger = logging.getLogger(__name__)
 
-if TYPE_CHECKING:
-    from deerflow.config.app_config import AppConfig
-
 # Channel name → import path for lazy loading
 _CHANNEL_REGISTRY: dict[str, str] = {
-    "dingtalk": "app.channels.dingtalk:DingTalkChannel",
-    "discord": "app.channels.discord:DiscordChannel",
     "feishu": "app.channels.feishu:FeishuChannel",
     "slack": "app.channels.slack:SlackChannel",
     "telegram": "app.channels.telegram:TelegramChannel",
@@ -27,17 +22,6 @@ _CHANNEL_REGISTRY: dict[str, str] = {
     "wecom": "app.channels.wecom:WeComChannel",
 }
 
-# Keys that indicate a user has configured credentials for a channel.
-_CHANNEL_CREDENTIAL_KEYS: dict[str, list[str]] = {
-    "dingtalk": ["client_id", "client_secret"],
-    "discord": ["bot_token"],
-    "feishu": ["app_id", "app_secret"],
-    "slack": ["bot_token", "app_token"],
-    "telegram": ["bot_token"],
-    "wecom": ["bot_id", "bot_secret"],
-    "wechat": ["bot_token"],
-}
-
 _CHANNELS_LANGGRAPH_URL_ENV = "DEER_FLOW_CHANNELS_LANGGRAPH_URL"
 _CHANNELS_GATEWAY_URL_ENV = "DEER_FLOW_CHANNELS_GATEWAY_URL"
 
@@ -80,15 +64,14 @@ class ChannelService:
         self._running = False
 
     @classmethod
-    def from_app_config(cls, app_config: AppConfig | None = None) -> ChannelService:
+    def from_app_config(cls) -> ChannelService:
         """Create a ChannelService from the application config."""
-        if app_config is None:
-            from deerflow.config.app_config import get_app_config
+        from deerflow.config.app_config import get_app_config
 
-            app_config = get_app_config()
+        config = get_app_config()
         channels_config = {}
         # extra fields are allowed by AppConfig (extra="allow")
-        extra = app_config.model_extra or {}
+        extra = config.model_extra or {}
         if "channels" in extra:
             channels_config = extra["channels"]
         return cls(channels_config=channels_config)
@@ -104,16 +87,7 @@ class ChannelService:
             if not isinstance(channel_config, dict):
                 continue
             if not channel_config.get("enabled", False):
-                cred_keys = _CHANNEL_CREDENTIAL_KEYS.get(name, [])
-                has_creds = any(not isinstance(channel_config.get(k), bool) and channel_config.get(k) is not None and str(channel_config[k]).strip() for k in cred_keys)
-                if has_creds:
-                    logger.warning(
-                        "Channel '%s' has credentials configured but is disabled. Set enabled: true under channels.%s in config.yaml to activate it.",
-                        name,
-                        name,
-                    )
-                else:
-                    logger.info("Channel %s is disabled, skipping", name)
+                logger.info("Channel %s is disabled, skipping", name)
                 continue
 
             await self._start_channel(name, channel_config)
@@ -168,16 +142,11 @@ class ChannelService:
 
         try:
             channel = channel_cls(bus=self.bus, config=config)
-            self._channels[name] = channel
             await channel.start()
-            if not channel.is_running:
-                self._channels.pop(name, None)
-                logger.error("Channel %s did not enter a running state after start()", name)
-                return False
+            self._channels[name] = channel
             logger.info("Channel %s started", name)
             return True
         except Exception:
-            self._channels.pop(name, None)
             logger.exception("Failed to start channel %s", name)
             return False
 
@@ -212,12 +181,12 @@ def get_channel_service() -> ChannelService | None:
     return _channel_service
 
 
-async def start_channel_service(app_config: AppConfig | None = None) -> ChannelService:
+async def start_channel_service() -> ChannelService:
     """Create and start the global ChannelService from app config."""
     global _channel_service
     if _channel_service is not None:
         return _channel_service
-    _channel_service = ChannelService.from_app_config(app_config)
+    _channel_service = ChannelService.from_app_config()
     await _channel_service.start()
     return _channel_service
 

backend/app/channels/slack.py

@@ -16,31 +16,13 @@ logger = logging.getLogger(__name__)
 _slack_md_converter = SlackMarkdownConverter()
 
 
-def _normalize_allowed_users(allowed_users: Any) -> set[str]:
-    if allowed_users is None:
-        return set()
-    if isinstance(allowed_users, str):
-        values = [allowed_users]
-    elif isinstance(allowed_users, list | tuple | set):
-        values = allowed_users
-    else:
-        logger.warning(
-            "Slack allowed_users should be a list of Slack user IDs or a single Slack user ID string; treating %s as one string value",
-            type(allowed_users).__name__,
-        )
-        values = [allowed_users]
-    return {str(user_id) for user_id in values if str(user_id)}
-
-
 class SlackChannel(Channel):
     """Slack IM channel using Socket Mode (WebSocket, no public IP).
 
     Configuration keys (in ``config.yaml`` under ``channels.slack``):
         - ``bot_token``: Slack Bot User OAuth Token (xoxb-...).
         - ``app_token``: Slack App-Level Token (xapp-...) for Socket Mode.
-        - ``allowed_users``: (optional) List of allowed Slack user IDs, or a
-          single Slack user ID string as shorthand. Empty = allow all. Other
-          scalar values are treated as a single string with a warning.
+        - ``allowed_users``: (optional) List of allowed Slack user IDs. Empty = allow all.
     """
 
     def __init__(self, bus: MessageBus, config: dict[str, Any]) -> None:
@@ -48,7 +30,7 @@ class SlackChannel(Channel):
         self._socket_client = None
         self._web_client = None
         self._loop: asyncio.AbstractEventLoop | None = None
-        self._allowed_users = _normalize_allowed_users(config.get("allowed_users", []))
+        self._allowed_users: set[str] = {str(user_id) for user_id in config.get("allowed_users", [])}
 
     async def start(self) -> None:
         if self._running:

backend/app/channels/wecom.py

@@ -29,10 +29,6 @@ class WeComChannel(Channel):
         self._ws_stream_ids: dict[str, str] = {}
         self._working_message = "Working on it..."
 
-    @property
-    def supports_streaming(self) -> bool:
-        return True
-
     def _clear_ws_context(self, thread_ts: str | None) -> None:
         if not thread_ts:
             return

backend/app/gateway/app.py

@@ -1,8 +1,8 @@
-import asyncio
 import logging
 import os
 from collections.abc import AsyncGenerator
 from contextlib import asynccontextmanager
+from datetime import UTC
 
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
@@ -28,13 +28,9 @@ from app.gateway.routers import (
     threads,
     uploads,
 )
-from deerflow.config import app_config as deerflow_app_config
-from deerflow.config.app_config import apply_logging_level
+from deerflow.config.app_config import get_app_config
 
-AppConfig = deerflow_app_config.AppConfig
-get_app_config = deerflow_app_config.get_app_config
-
-# Default logging; lifespan overrides from config.yaml log_level.
+# Configure logging
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
@@ -43,74 +39,79 @@ logging.basicConfig(
 
 logger = logging.getLogger(__name__)
 
-# Upper bound (seconds) each lifespan shutdown hook is allowed to run.
-# Bounds worker exit time so uvicorn's reload supervisor does not keep
-# firing signals into a worker that is stuck waiting for shutdown cleanup.
-_SHUTDOWN_HOOK_TIMEOUT_SECONDS = 5.0
-
 
 async def _ensure_admin_user(app: FastAPI) -> None:
-    """Startup hook: handle first boot and migrate orphan threads otherwise.
+    """Auto-create the admin user on first boot if no users exist.
 
     After admin creation, migrate orphan threads from the LangGraph
-    store (metadata.user_id unset) to the admin account. This is the
+    store (metadata.owner_id unset) to the admin account. This is the
     "no-auth → with-auth" upgrade path: users who ran DeerFlow without
     authentication have existing LangGraph thread data that needs an
     owner assigned.
-        First boot (no admin exists):
-            - Does NOT create any user accounts automatically.
-            - The operator must visit ``/setup`` to create the first admin.
 
-    Subsequent boots (admin already exists):
-      - Runs the one-time "no-auth → with-auth" orphan thread migration for
-        existing LangGraph thread metadata that has no owner_id.
-
-    No SQL persistence migration is needed: the four user_id columns
+    No SQL persistence migration is needed: the four owner_id columns
     (threads_meta, runs, run_events, feedback) only come into existence
     alongside the auth module via create_all, so freshly created tables
-    never contain NULL-owner rows.
+    never contain NULL-owner rows. "Existing persistence DB + new auth"
+    is not a supported upgrade path — fresh install or wipe-and-retry.
+
+    Multi-worker safe: relies on SQLite UNIQUE constraint to resolve
+    races during admin creation. Only the worker that successfully
+    creates/updates the admin prints the password; losers silently skip.
     """
-    from sqlalchemy import select
+    import secrets
 
+    from app.gateway.auth.credential_file import write_initial_credentials
     from app.gateway.deps import get_local_provider
-    from deerflow.persistence.engine import get_session_factory
-    from deerflow.persistence.user.model import UserRow
 
-    try:
-        provider = get_local_provider()
-    except RuntimeError:
-        # Auth persistence may not be initialized in some test/boot paths.
-        # Skip admin migration work rather than failing gateway startup.
-        logger.warning("Auth persistence not ready; skipping admin bootstrap check")
-        return
-
-    sf = get_session_factory()
-    if sf is None:
-        return
-
-    admin_count = await provider.count_admin_users()
-
-    if admin_count == 0:
+    def _announce_credentials(email: str, password: str, *, label: str, headline: str) -> None:
+        """Write the password to a 0600 file and log the path (never the secret)."""
+        cred_path = write_initial_credentials(email, password, label=label)
         logger.info("=" * 60)
-        logger.info("  First boot detected — no admin account exists.")
-        logger.info("  Visit /setup to complete admin account creation.")
+        logger.info("  %s", headline)
+        logger.info("  Credentials written to: %s (mode 0600)", cred_path)
+        logger.info("  Change it after login: Settings -> Account")
         logger.info("=" * 60)
-        return
 
-    # Admin already exists — run orphan thread migration for any
-    # LangGraph thread metadata that pre-dates the auth module.
-    async with sf() as session:
-        stmt = select(UserRow).where(UserRow.system_role == "admin").limit(1)
-        row = (await session.execute(stmt)).scalar_one_or_none()
+    provider = get_local_provider()
+    user_count = await provider.count_users()
 
-    if row is None:
-        return  # Should not happen (admin_count > 0 above), but be safe.
+    admin = None
 
-    admin_id = str(row.id)
+    if user_count == 0:
+        password = secrets.token_urlsafe(16)
+        try:
+            admin = await provider.create_user(email="admin@deerflow.dev", password=password, system_role="admin", needs_setup=True)
+        except ValueError:
+            return  # Another worker already created the admin.
+        _announce_credentials(admin.email, password, label="initial", headline="Admin account created on first boot")
+    else:
+        # Admin exists but setup never completed — reset password so operator
+        # can always find it in the console without needing the CLI.
+        # Multi-worker guard: if admin was created less than 30s ago, another
+        # worker just created it and will print the password — skip reset.
+        admin = await provider.get_user_by_email("admin@deerflow.dev")
+        if admin and admin.needs_setup:
+            import time
+
+            age = time.time() - admin.created_at.replace(tzinfo=UTC).timestamp()
+            if age >= 30:
+                from app.gateway.auth.password import hash_password_async
+
+                password = secrets.token_urlsafe(16)
+                admin.password_hash = await hash_password_async(password)
+                admin.token_version += 1
+                await provider.update_user(admin)
+                _announce_credentials(admin.email, password, label="reset", headline="Admin account setup incomplete — password reset")
+
+    if admin is None:
+        return  # Nothing to bind orphans to.
+
+    admin_id = str(admin.id)
 
     # LangGraph store orphan migration — non-fatal.
     # This covers the "no-auth → with-auth" upgrade path for users
-    # whose existing LangGraph thread metadata has no user_id set.
+    # whose existing LangGraph thread metadata has no owner_id set.
     store = getattr(app.state, "store", None)
     if store is not None:
         try:
@@ -142,7 +143,7 @@ async def _iter_store_items(store, namespace, *, page_size: int = 500):
 
 
 async def _migrate_orphaned_threads(store, admin_user_id: str) -> int:
-    """Migrate LangGraph store threads with no user_id to the given admin.
+    """Migrate LangGraph store threads with no owner_id to the given admin.
 
     Uses cursor pagination so all orphans are migrated regardless of
     count. Returns the number of rows migrated.
@@ -150,8 +151,8 @@ async def _migrate_orphaned_threads(store, admin_user_id: str) -> int:
     migrated = 0
     async for item in _iter_store_items(store, ("threads",)):
         metadata = item.value.get("metadata", {})
-        if not metadata.get("user_id"):
-            metadata["user_id"] = admin_user_id
+        if not metadata.get("owner_id"):
+            metadata["owner_id"] = admin_user_id
             item.value["metadata"] = metadata
             await store.aput(("threads",), item.key, item.value)
             migrated += 1
@@ -164,8 +165,7 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
 
     # Load config and check necessary environment variables at startup
     try:
-        app.state.config = get_app_config()
-        apply_logging_level(app.state.config.log_level)
+        get_app_config()
         logger.info("Configuration loaded successfully")
     except Exception as e:
         error_msg = f"Failed to load configuration during gateway startup: {e}"
@@ -186,26 +186,18 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
         try:
             from app.channels.service import start_channel_service
 
-            channel_service = await start_channel_service(app.state.config)
+            channel_service = await start_channel_service()
             logger.info("Channel service started: %s", channel_service.get_status())
         except Exception:
             logger.exception("No IM channels configured or channel service failed to start")
 
         yield
 
-        # Stop channel service on shutdown (bounded to prevent worker hang)
+        # Stop channel service on shutdown
         try:
             from app.channels.service import stop_channel_service
 
-            await asyncio.wait_for(
-                stop_channel_service(),
-                timeout=_SHUTDOWN_HOOK_TIMEOUT_SECONDS,
-            )
-        except TimeoutError:
-            logger.warning(
-                "Channel service shutdown exceeded %.1fs; proceeding with worker exit.",
-                _SHUTDOWN_HOOK_TIMEOUT_SECONDS,
-            )
+            await stop_channel_service()
         except Exception:
             logger.exception("Failed to stop channel service")
 
@@ -218,8 +210,6 @@ def create_app() -> FastAPI:
     Returns:
         Configured FastAPI application instance.
     """
-    config = get_gateway_config()
-    docs_kwargs = {"docs_url": "/docs", "redoc_url": "/redoc", "openapi_url": "/openapi.json"} if config.enable_docs else {"docs_url": None, "redoc_url": None, "openapi_url": None}
 
     app = FastAPI(
         title="DeerFlow API Gateway",
@@ -244,7 +234,9 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
         """,
         version="0.1.0",
         lifespan=lifespan,
-        **docs_kwargs,
+        docs_url="/docs",
+        redoc_url="/redoc",
+        openapi_url="/openapi.json",
         openapi_tags=[
             {
                 "name": "models",

backend/app/gateway/auth/config.py

@@ -4,8 +4,11 @@ import logging
 import os
 import secrets
 
+from dotenv import load_dotenv
 from pydantic import BaseModel, Field
 
+load_dotenv()
+
 logger = logging.getLogger(__name__)
 
 
@@ -34,9 +37,6 @@ def get_auth_config() -> AuthConfig:
     """Get the global AuthConfig instance. Parses from env on first call."""
     global _auth_config
     if _auth_config is None:
-        from dotenv import load_dotenv
-
-        load_dotenv()
         jwt_secret = os.environ.get("AUTH_JWT_SECRET")
         if not jwt_secret:
             jwt_secret = secrets.token_urlsafe(32)

backend/app/gateway/auth/errors.py

@@ -20,7 +20,6 @@ class AuthErrorCode(StrEnum):
     EMAIL_ALREADY_EXISTS = "email_already_exists"
     PROVIDER_NOT_FOUND = "provider_not_found"
     NOT_AUTHENTICATED = "not_authenticated"
-    SYSTEM_ALREADY_INITIALIZED = "system_already_initialized"
 
 
 class TokenError(StrEnum):

backend/app/gateway/auth/local_provider.py

@@ -1,14 +1,10 @@
 """Local email/password authentication provider."""
 
-import logging
-
 from app.gateway.auth.models import User
-from app.gateway.auth.password import hash_password_async, needs_rehash, verify_password_async
+from app.gateway.auth.password import hash_password_async, verify_password_async
 from app.gateway.auth.providers import AuthProvider
 from app.gateway.auth.repositories.base import UserRepository
 
-logger = logging.getLogger(__name__)
-
 
 class LocalAuthProvider(AuthProvider):
     """Email/password authentication provider using local database."""
@@ -47,15 +43,6 @@ class LocalAuthProvider(AuthProvider):
         if not await verify_password_async(password, user.password_hash):
             return None
 
-        if needs_rehash(user.password_hash):
-            try:
-                user.password_hash = await hash_password_async(password)
-                await self._repo.update_user(user)
-            except Exception:
-                # Rehash is an opportunistic upgrade; a transient DB error must not
-                # prevent an otherwise-valid login from succeeding.
-                logger.warning("Failed to rehash password for user %s; login will still succeed", user.email, exc_info=True)
-
         return user
 
     async def get_user(self, user_id: str) -> User | None:
@@ -91,10 +78,6 @@ class LocalAuthProvider(AuthProvider):
         """Return total number of registered users."""
         return await self._repo.count_users()
 
-    async def count_admin_users(self) -> int:
-        """Return number of admin users."""
-        return await self._repo.count_admin_users()
-
     async def update_user(self, user: User) -> User:
         """Update an existing user."""
         return await self._repo.update_user(user)

backend/app/gateway/auth/password.py

@@ -1,66 +1,18 @@
-"""Password hashing utilities with versioned hash format.
-
-Hash format: ``$dfv<N>$<bcrypt_hash>`` where ``<N>`` is the version.
-
-- **v1** (legacy): ``bcrypt(password)`` — plain bcrypt, susceptible to
-  72-byte silent truncation.
-- **v2** (current): ``bcrypt(b64(sha256(password)))`` — SHA-256 pre-hash
-  avoids the 72-byte truncation limit so the full password contributes
-  to the hash.
-
-Verification auto-detects the version and falls back to v1 for hashes
-without a prefix, so existing deployments upgrade transparently on next
-login.
-"""
+"""Password hashing utilities using bcrypt directly."""
 
 import asyncio
-import base64
-import hashlib
 
 import bcrypt
 
-_CURRENT_VERSION = 2
-_PREFIX_V2 = "$dfv2$"
-_PREFIX_V1 = "$dfv1$"
-
-
-def _pre_hash_v2(password: str) -> bytes:
-    """SHA-256 pre-hash to bypass bcrypt's 72-byte limit."""
-    return base64.b64encode(hashlib.sha256(password.encode("utf-8")).digest())
-
 
 def hash_password(password: str) -> str:
-    """Hash a password (current version: v2 — SHA-256 + bcrypt)."""
-    raw = bcrypt.hashpw(_pre_hash_v2(password), bcrypt.gensalt()).decode("utf-8")
-    return f"{_PREFIX_V2}{raw}"
+    """Hash a password using bcrypt."""
+    return bcrypt.hashpw(password.encode("utf-8"), bcrypt.gensalt()).decode("utf-8")
 
 
 def verify_password(plain_password: str, hashed_password: str) -> bool:
-    """Verify a password, auto-detecting the hash version.
-
-    Accepts v2 (``$dfv2$…``), v1 (``$dfv1$…``), and bare bcrypt hashes
-    (treated as v1 for backward compatibility with pre-versioning data).
-    """
-    try:
-        if hashed_password.startswith(_PREFIX_V2):
-            bcrypt_hash = hashed_password[len(_PREFIX_V2) :]
-            return bcrypt.checkpw(_pre_hash_v2(plain_password), bcrypt_hash.encode("utf-8"))
-
-        if hashed_password.startswith(_PREFIX_V1):
-            bcrypt_hash = hashed_password[len(_PREFIX_V1) :]
-        else:
-            bcrypt_hash = hashed_password
-
-        return bcrypt.checkpw(plain_password.encode("utf-8"), bcrypt_hash.encode("utf-8"))
-    except ValueError:
-        # bcrypt raises ValueError for malformed or corrupt hashes (e.g., invalid salt).
-        # Fail closed rather than crashing the request.
-        return False
-
-
-def needs_rehash(hashed_password: str) -> bool:
-    """Return True if the hash uses an older version and should be rehashed."""
-    return not hashed_password.startswith(_PREFIX_V2)
+    """Verify a password against its hash."""
+    return bcrypt.checkpw(plain_password.encode("utf-8"), hashed_password.encode("utf-8"))
 
 
 async def hash_password_async(password: str) -> str:

backend/app/gateway/auth/providers.py

@@ -12,12 +12,12 @@ class AuthProvider(ABC):
 
         Returns User if authentication succeeds, None otherwise.
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user(self, user_id: str) -> "User | None":
         """Retrieve user by ID."""
-        raise NotImplementedError
+        ...
 
 
 # Import User at runtime to avoid circular imports

backend/app/gateway/auth/repositories/base.py

@@ -35,7 +35,7 @@ class UserRepository(ABC):
         Raises:
             ValueError: If email already exists
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user_by_id(self, user_id: str) -> User | None:
@@ -47,7 +47,7 @@ class UserRepository(ABC):
         Returns:
             User if found, None otherwise
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user_by_email(self, email: str) -> User | None:
@@ -59,7 +59,7 @@ class UserRepository(ABC):
         Returns:
             User if found, None otherwise
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def update_user(self, user: User) -> User:
@@ -76,17 +76,12 @@ class UserRepository(ABC):
                 a hard failure (not a no-op) so callers cannot mistake a
                 concurrent-delete race for a successful update.
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def count_users(self) -> int:
         """Return total number of registered users."""
-        raise NotImplementedError
-
-    @abstractmethod
-    async def count_admin_users(self) -> int:
-        """Return number of users with system_role == 'admin'."""
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user_by_oauth(self, provider: str, oauth_id: str) -> User | None:
@@ -99,4 +94,4 @@ class UserRepository(ABC):
         Returns:
             User if found, None otherwise
         """
-        raise NotImplementedError
+        ...

backend/app/gateway/auth/repositories/sqlite.py

@@ -114,11 +114,6 @@ class SQLiteUserRepository(UserRepository):
         async with self._sf() as session:
             return await session.scalar(stmt) or 0
 
-    async def count_admin_users(self) -> int:
-        stmt = select(func.count()).select_from(UserRow).where(UserRow.system_role == "admin")
-        async with self._sf() as session:
-            return await session.scalar(stmt) or 0
-
     async def get_user_by_oauth(self, provider: str, oauth_id: str) -> User | None:
         stmt = select(UserRow).where(UserRow.oauth_provider == provider, UserRow.oauth_id == oauth_id)
         async with self._sf() as session:

backend/app/gateway/auth_middleware.py

@@ -18,7 +18,6 @@ from starlette.types import ASGIApp
 
 from app.gateway.auth.errors import AuthErrorCode, AuthErrorResponse
 from app.gateway.authz import _ALL_PERMISSIONS, AuthContext
-from app.gateway.internal_auth import INTERNAL_AUTH_HEADER_NAME, get_internal_user, is_valid_internal_auth_token
 from deerflow.runtime.user_context import reset_current_user, set_current_user
 
 # Paths that never require authentication.
@@ -37,7 +36,6 @@ _PUBLIC_EXACT_PATHS: frozenset[str] = frozenset(
         "/api/v1/auth/register",
         "/api/v1/auth/logout",
         "/api/v1/auth/setup-status",
-        "/api/v1/auth/initialize",
     }
 )
 
@@ -76,12 +74,8 @@ class AuthMiddleware(BaseHTTPMiddleware):
         if _is_public(request.url.path):
             return await call_next(request)
 
-        internal_user = None
-        if is_valid_internal_auth_token(request.headers.get(INTERNAL_AUTH_HEADER_NAME)):
-            internal_user = get_internal_user()
-
         # Non-public path: require session cookie
-        if internal_user is None and not request.cookies.get("access_token"):
+        if not request.cookies.get("access_token"):
             return JSONResponse(
                 status_code=401,
                 content={
@@ -105,13 +99,10 @@ class AuthMiddleware(BaseHTTPMiddleware):
         # bubble up, so we catch and render it as JSONResponse here.
         from app.gateway.deps import get_current_user_from_request
 
-        if internal_user is not None:
-            user = internal_user
-        else:
-            try:
-                user = await get_current_user_from_request(request)
-            except HTTPException as exc:
-                return JSONResponse(status_code=exc.status_code, content={"detail": exc.detail})
+        try:
+            user = await get_current_user_from_request(request)
+        except HTTPException as exc:
+            return JSONResponse(status_code=exc.status_code, content={"detail": exc.detail})
 
         # Stamp both request.state.user (for the contextvar pattern)
         # and request.state.auth (so @require_permission's "auth is

backend/app/gateway/authz.py

@@ -30,9 +30,7 @@ Inspired by LangGraph Auth system: https://github.com/langchain-ai/langgraph/blo
 from __future__ import annotations
 
 import functools
-import inspect
 from collections.abc import Callable
-from types import SimpleNamespace
 from typing import TYPE_CHECKING, Any, ParamSpec, TypeVar
 
 from fastapi import HTTPException, Request
@@ -119,15 +117,6 @@ _ALL_PERMISSIONS: list[str] = [
 ]
 
 
-def _make_test_request_stub() -> Any:
-    """Create a minimal request-like object for direct unit calls.
-
-    Used when decorated route handlers are invoked without FastAPI's
-    request injection. Includes fields accessed by auth helpers.
-    """
-    return SimpleNamespace(state=SimpleNamespace(), cookies={}, _deerflow_test_bypass_auth=True)
-
-
 async def _authenticate(request: Request) -> AuthContext:
     """Authenticate request and return AuthContext.
 
@@ -145,11 +134,7 @@ async def _authenticate(request: Request) -> AuthContext:
 
 
 def require_auth[**P, T](func: Callable[P, T]) -> Callable[P, T]:
-    """Decorator that authenticates the request and enforces authentication.
-
-    Independently raises HTTP 401 for unauthenticated requests, regardless of
-    whether ``AuthMiddleware`` is present in the ASGI stack. Sets the resolved
-    ``AuthContext`` on ``request.state.auth`` for downstream handlers.
+    """Decorator that authenticates the request and sets AuthContext.
 
     Must be placed ABOVE other decorators (executes after them).
 
@@ -162,33 +147,19 @@ def require_auth[**P, T](func: Callable[P, T]) -> Callable[P, T]:
             ...
 
     Raises:
-        HTTPException: 401 if the request is unauthenticated.
-        ValueError: If 'request' parameter is missing.
+        ValueError: If 'request' parameter is missing
     """
 
     @functools.wraps(func)
     async def wrapper(*args: Any, **kwargs: Any) -> Any:
         request = kwargs.get("request")
         if request is None:
-            # Unit tests may call decorated handlers directly without a
-            # FastAPI Request object. Inject a minimal request stub when
-            # the wrapped function declares `request`.
-            if "request" in inspect.signature(func).parameters:
-                kwargs["request"] = _make_test_request_stub()
-            else:
-                raise ValueError("require_auth decorator requires 'request' parameter")
-            request = kwargs["request"]
-
-        if getattr(request, "_deerflow_test_bypass_auth", False):
-            return await func(*args, **kwargs)
+            raise ValueError("require_auth decorator requires 'request' parameter")
 
         # Authenticate and set context
         auth_context = await _authenticate(request)
         request.state.auth = auth_context
 
-        if not auth_context.is_authenticated:
-            raise HTTPException(status_code=401, detail="Authentication required")
-
         return await func(*args, **kwargs)
 
     return wrapper
@@ -239,17 +210,7 @@ def require_permission(
         async def wrapper(*args: Any, **kwargs: Any) -> Any:
             request = kwargs.get("request")
             if request is None:
-                # Unit tests may call decorated route handlers directly without
-                # constructing a FastAPI Request object. Inject a minimal stub
-                # when the wrapped function declares `request`.
-                if "request" in inspect.signature(func).parameters:
-                    kwargs["request"] = _make_test_request_stub()
-                else:
-                    return await func(*args, **kwargs)
-                request = kwargs["request"]
-
-            if getattr(request, "_deerflow_test_bypass_auth", False):
-                return await func(*args, **kwargs)
+                raise ValueError("require_permission decorator requires 'request' parameter")
 
             auth: AuthContext = getattr(request.state, "auth", None)
             if auth is None:
@@ -272,18 +233,18 @@ def require_permission(
             # (``threads_meta`` table). We verify ownership via
             # ``ThreadMetaStore.check_access``: it returns True for
             # missing rows (untracked legacy thread) and for rows whose
-            # ``user_id`` is NULL (shared / pre-auth data), so this is
+            # ``owner_id`` is NULL (shared / pre-auth data), so this is
             # strict-deny rather than strict-allow — only an *existing*
-            # row with a *different* user_id triggers 404.
+            # row with a *different* owner_id triggers 404.
             if owner_check:
                 thread_id = kwargs.get("thread_id")
                 if thread_id is None:
                     raise ValueError("require_permission with owner_check=True requires 'thread_id' parameter")
 
-                from app.gateway.deps import get_thread_store
+                from app.gateway.deps import get_thread_meta_repo
 
-                thread_store = get_thread_store(request)
-                allowed = await thread_store.check_access(
+                thread_meta_repo = get_thread_meta_repo(request)
+                allowed = await thread_meta_repo.check_access(
                     thread_id,
                     str(auth.user.id),
                     require_existing=require_existing,

backend/app/gateway/config.py

@@ -9,7 +9,6 @@ class GatewayConfig(BaseModel):
     host: str = Field(default="0.0.0.0", description="Host to bind the gateway server")
     port: int = Field(default=8001, description="Port to bind the gateway server")
     cors_origins: list[str] = Field(default_factory=lambda: ["http://localhost:3000"], description="Allowed CORS origins")
-    enable_docs: bool = Field(default=True, description="Enable Swagger/ReDoc/OpenAPI endpoints")
 
 
 _gateway_config: GatewayConfig | None = None
@@ -24,6 +23,5 @@ def get_gateway_config() -> GatewayConfig:
             host=os.getenv("GATEWAY_HOST", "0.0.0.0"),
             port=int(os.getenv("GATEWAY_PORT", "8001")),
             cors_origins=cors_origins_str.split(","),
-            enable_docs=os.getenv("GATEWAY_ENABLE_DOCS", "true").lower() == "true",
         )
     return _gateway_config

backend/app/gateway/csrf_middleware.py

@@ -48,7 +48,6 @@ _AUTH_EXEMPT_PATHS: frozenset[str] = frozenset(
         "/api/v1/auth/login/local",
         "/api/v1/auth/logout",
         "/api/v1/auth/register",
-        "/api/v1/auth/initialize",
     }
 )
 

backend/app/gateway/deps.py

@@ -1,41 +1,25 @@
 """Centralized accessors for singleton objects stored on ``app.state``.
 
 **Getters** (used by routers): raise 503 when a required dependency is
-missing, except ``get_store`` which returns ``None``.
+missing, except ``get_store`` and ``get_thread_meta_repo`` which return
+``None``.
 
 Initialization is handled directly in ``app.py`` via :class:`AsyncExitStack`.
 """
 
 from __future__ import annotations
 
-from collections.abc import AsyncGenerator, Callable
+from collections.abc import AsyncGenerator
 from contextlib import AsyncExitStack, asynccontextmanager
-from typing import TYPE_CHECKING, TypeVar, cast
+from typing import TYPE_CHECKING
 
 from fastapi import FastAPI, HTTPException, Request
-from langgraph.types import Checkpointer
 
-from deerflow.config.app_config import AppConfig
-from deerflow.persistence.feedback import FeedbackRepository
-from deerflow.runtime import RunContext, RunManager, StreamBridge
-from deerflow.runtime.events.store.base import RunEventStore
-from deerflow.runtime.runs.store.base import RunStore
+from deerflow.runtime import RunContext, RunManager
 
 if TYPE_CHECKING:
     from app.gateway.auth.local_provider import LocalAuthProvider
     from app.gateway.auth.repositories.sqlite import SQLiteUserRepository
-    from deerflow.persistence.thread_meta.base import ThreadMetaStore
-
-
-T = TypeVar("T")
-
-
-def get_config(request: Request) -> AppConfig:
-    """Return the app-scoped ``AppConfig`` stored on ``app.state``."""
-    config = getattr(request.app.state, "config", None)
-    if config is None:
-        raise HTTPException(status_code=503, detail="Configuration not available")
-    return config
 
 
 @asynccontextmanager
@@ -47,42 +31,40 @@ async def langgraph_runtime(app: FastAPI) -> AsyncGenerator[None, None]:
         async with langgraph_runtime(app):
             yield
     """
+    from deerflow.agents.checkpointer.async_provider import make_checkpointer
+    from deerflow.config import get_app_config
     from deerflow.persistence.engine import close_engine, get_session_factory, init_engine_from_config
     from deerflow.runtime import make_store, make_stream_bridge
-    from deerflow.runtime.checkpointer.async_provider import make_checkpointer
     from deerflow.runtime.events.store import make_run_event_store
 
     async with AsyncExitStack() as stack:
-        config = getattr(app.state, "config", None)
-        if config is None:
-            raise RuntimeError("langgraph_runtime() requires app.state.config to be initialized")
-
-        app.state.stream_bridge = await stack.enter_async_context(make_stream_bridge(config))
+        app.state.stream_bridge = await stack.enter_async_context(make_stream_bridge())
 
         # Initialize persistence engine BEFORE checkpointer so that
         # auto-create-database logic runs first (postgres backend).
+        config = get_app_config()
         await init_engine_from_config(config.database)
 
-        app.state.checkpointer = await stack.enter_async_context(make_checkpointer(config))
-        app.state.store = await stack.enter_async_context(make_store(config))
+        app.state.checkpointer = await stack.enter_async_context(make_checkpointer())
+        app.state.store = await stack.enter_async_context(make_store())
 
         # Initialize repositories — one get_session_factory() call for all.
         sf = get_session_factory()
         if sf is not None:
             from deerflow.persistence.feedback import FeedbackRepository
             from deerflow.persistence.run import RunRepository
+            from deerflow.persistence.thread_meta import ThreadMetaRepository
 
             app.state.run_store = RunRepository(sf)
             app.state.feedback_repo = FeedbackRepository(sf)
+            app.state.thread_meta_repo = ThreadMetaRepository(sf)
         else:
+            from deerflow.persistence.thread_meta import MemoryThreadMetaStore
             from deerflow.runtime.runs.store.memory import MemoryRunStore
 
             app.state.run_store = MemoryRunStore()
             app.state.feedback_repo = None
-
-        from deerflow.persistence.thread_meta import make_thread_store
-
-        app.state.thread_store = make_thread_store(sf, app.state.store)
+            app.state.thread_meta_repo = MemoryThreadMetaStore(app.state.store)
 
         # Run event store (has its own factory with config-driven backend selection)
         run_events_config = getattr(config, "run_events", None)
@@ -98,29 +80,29 @@ async def langgraph_runtime(app: FastAPI) -> AsyncGenerator[None, None]:
 
 
 # ---------------------------------------------------------------------------
-# Getters – called by routers per-request
+# Getters -- called by routers per-request
 # ---------------------------------------------------------------------------
 
 
-def _require(attr: str, label: str) -> Callable[[Request], T]:
+def _require(attr: str, label: str):
     """Create a FastAPI dependency that returns ``app.state.<attr>`` or 503."""
 
-    def dep(request: Request) -> T:
+    def dep(request: Request):
         val = getattr(request.app.state, attr, None)
         if val is None:
             raise HTTPException(status_code=503, detail=f"{label} not available")
-        return cast(T, val)
+        return val
 
     dep.__name__ = dep.__qualname__ = f"get_{attr}"
     return dep
 
 
-get_stream_bridge: Callable[[Request], StreamBridge] = _require("stream_bridge", "Stream bridge")
-get_run_manager: Callable[[Request], RunManager] = _require("run_manager", "Run manager")
-get_checkpointer: Callable[[Request], Checkpointer] = _require("checkpointer", "Checkpointer")
-get_run_event_store: Callable[[Request], RunEventStore] = _require("run_event_store", "Run event store")
-get_feedback_repo: Callable[[Request], FeedbackRepository] = _require("feedback_repo", "Feedback")
-get_run_store: Callable[[Request], RunStore] = _require("run_store", "Run store")
+get_stream_bridge = _require("stream_bridge", "Stream bridge")
+get_run_manager = _require("run_manager", "Run manager")
+get_checkpointer = _require("checkpointer", "Checkpointer")
+get_run_event_store = _require("run_event_store", "Run event store")
+get_feedback_repo = _require("feedback_repo", "Feedback")
+get_run_store = _require("run_store", "Run store")
 
 
 def get_store(request: Request):
@@ -128,27 +110,25 @@ def get_store(request: Request):
     return getattr(request.app.state, "store", None)
 
 
-def get_thread_store(request: Request) -> ThreadMetaStore:
-    """Return the thread metadata store (SQL or memory-backed)."""
-    val = getattr(request.app.state, "thread_store", None)
-    if val is None:
-        raise HTTPException(status_code=503, detail="Thread metadata store not available")
-    return val
+get_thread_meta_repo = _require("thread_meta_repo", "Thread metadata store")
 
 
 def get_run_context(request: Request) -> RunContext:
     """Build a :class:`RunContext` from ``app.state`` singletons.
 
-    Returns a *base* context with infrastructure dependencies.
+    Returns a *base* context with infrastructure dependencies.  Callers that
+    need per-run fields (e.g. ``follow_up_to_run_id``) should use
+    ``dataclasses.replace(ctx, follow_up_to_run_id=...)`` before passing it
+    to :func:`run_agent`.
     """
-    config = get_config(request)
+    from deerflow.config import get_app_config
+
     return RunContext(
         checkpointer=get_checkpointer(request),
         store=get_store(request),
         event_store=get_run_event_store(request),
-        run_events_config=getattr(config, "run_events", None),
-        thread_store=get_thread_store(request),
-        app_config=config,
+        run_events_config=getattr(get_app_config(), "run_events", None),
+        thread_meta_repo=get_thread_meta_repo(request),
     )
 
 

backend/app/gateway/internal_auth.py

@@ -1,26 +0,0 @@
-"""Process-local authentication for Gateway internal callers."""
-
-from __future__ import annotations
-
-import secrets
-from types import SimpleNamespace
-
-from deerflow.runtime.user_context import DEFAULT_USER_ID
-
-INTERNAL_AUTH_HEADER_NAME = "X-DeerFlow-Internal-Token"
-_INTERNAL_AUTH_TOKEN = secrets.token_urlsafe(32)
-
-
-def create_internal_auth_headers() -> dict[str, str]:
-    """Return headers that authenticate same-process Gateway internal calls."""
-    return {INTERNAL_AUTH_HEADER_NAME: _INTERNAL_AUTH_TOKEN}
-
-
-def is_valid_internal_auth_token(token: str | None) -> bool:
-    """Return True when *token* matches the process-local internal token."""
-    return bool(token) and secrets.compare_digest(token, _INTERNAL_AUTH_TOKEN)
-
-
-def get_internal_user():
-    """Return the synthetic user used for trusted internal channel calls."""
-    return SimpleNamespace(id=DEFAULT_USER_ID, system_role="internal")

backend/app/gateway/langgraph_auth.py

@@ -73,7 +73,7 @@ async def authenticate(request):
     if isinstance(payload, TokenError):
         raise Auth.exceptions.HTTPException(
             status_code=401,
-            detail="Invalid token",
+            detail=f"Token error: {payload.value}",
         )
 
     user = await get_local_provider().get_user(payload.sub)
@@ -93,14 +93,14 @@ async def authenticate(request):
 
 @auth.on
 async def add_owner_filter(ctx: Auth.types.AuthContext, value: dict):
-    """Inject user_id metadata on writes; filter by user_id on reads.
+    """Inject owner_id metadata on writes; filter by owner_id on reads.
 
-    Gateway stores thread ownership as ``metadata.user_id``.
+    Gateway stores thread ownership as ``metadata.owner_id``.
     This handler ensures LangGraph Server enforces the same isolation.
     """
-    # On create/update: stamp user_id into metadata
+    # On create/update: stamp owner_id into metadata
     metadata = value.setdefault("metadata", {})
-    metadata["user_id"] = ctx.user.identity
+    metadata["owner_id"] = ctx.user.identity
 
     # Return filter dict — LangGraph applies it to search/read/delete
-    return {"user_id": ctx.user.identity}
+    return {"owner_id": ctx.user.identity}

backend/app/gateway/path_utils.py

@@ -5,7 +5,6 @@ from pathlib import Path
 from fastapi import HTTPException
 
 from deerflow.config.paths import get_paths
-from deerflow.runtime.user_context import get_effective_user_id
 
 
 def resolve_thread_virtual_path(thread_id: str, virtual_path: str) -> Path:
@@ -23,7 +22,7 @@ def resolve_thread_virtual_path(thread_id: str, virtual_path: str) -> Path:
         HTTPException: If the path is invalid or outside allowed directories.
     """
     try:
-        return get_paths().resolve_virtual_path(thread_id, virtual_path, user_id=get_effective_user_id())
+        return get_paths().resolve_virtual_path(thread_id, virtual_path)
     except ValueError as e:
         status = 403 if "traversal" in str(e) else 400
         raise HTTPException(status_code=status, detail=str(e))

backend/app/gateway/routers/agents.py

@@ -8,7 +8,6 @@ import yaml
 from fastapi import APIRouter, HTTPException
 from pydantic import BaseModel, Field
 
-from deerflow.config.agents_api_config import get_agents_api_config
 from deerflow.config.agents_config import AgentConfig, list_custom_agents, load_agent_config, load_agent_soul
 from deerflow.config.paths import get_paths
 
@@ -25,7 +24,6 @@ class AgentResponse(BaseModel):
     description: str = Field(default="", description="Agent description")
     model: str | None = Field(default=None, description="Optional model override")
     tool_groups: list[str] | None = Field(default=None, description="Optional tool group whitelist")
-    skills: list[str] | None = Field(default=None, description="Optional skill whitelist (None=all, []=none)")
     soul: str | None = Field(default=None, description="SOUL.md content")
 
 
@@ -42,7 +40,6 @@ class AgentCreateRequest(BaseModel):
     description: str = Field(default="", description="Agent description")
     model: str | None = Field(default=None, description="Optional model override")
     tool_groups: list[str] | None = Field(default=None, description="Optional tool group whitelist")
-    skills: list[str] | None = Field(default=None, description="Optional skill whitelist (None=all enabled, []=none)")
     soul: str = Field(default="", description="SOUL.md content — agent personality and behavioral guardrails")
 
 
@@ -52,7 +49,6 @@ class AgentUpdateRequest(BaseModel):
     description: str | None = Field(default=None, description="Updated description")
     model: str | None = Field(default=None, description="Updated model override")
     tool_groups: list[str] | None = Field(default=None, description="Updated tool group whitelist")
-    skills: list[str] | None = Field(default=None, description="Updated skill whitelist (None=all, []=none)")
     soul: str | None = Field(default=None, description="Updated SOUL.md content")
 
 
@@ -77,15 +73,6 @@ def _normalize_agent_name(name: str) -> str:
     return name.lower()
 
 
-def _require_agents_api_enabled() -> None:
-    """Reject access unless the custom-agent management API is explicitly enabled."""
-    if not get_agents_api_config().enabled:
-        raise HTTPException(
-            status_code=403,
-            detail=("Custom-agent management API is disabled. Set agents_api.enabled=true to expose agent and user-profile routes over HTTP."),
-        )
-
-
 def _agent_config_to_response(agent_cfg: AgentConfig, include_soul: bool = False) -> AgentResponse:
     """Convert AgentConfig to AgentResponse."""
     soul: str | None = None
@@ -97,7 +84,6 @@ def _agent_config_to_response(agent_cfg: AgentConfig, include_soul: bool = False
         description=agent_cfg.description,
         model=agent_cfg.model,
         tool_groups=agent_cfg.tool_groups,
-        skills=agent_cfg.skills,
         soul=soul,
     )
 
@@ -114,8 +100,6 @@ async def list_agents() -> AgentsListResponse:
     Returns:
         List of all custom agents with their metadata and soul content.
     """
-    _require_agents_api_enabled()
-
     try:
         agents = list_custom_agents()
         return AgentsListResponse(agents=[_agent_config_to_response(a, include_soul=True) for a in agents])
@@ -141,7 +125,6 @@ async def check_agent_name(name: str) -> dict:
     Raises:
         HTTPException: 422 if the name is invalid.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     normalized = _normalize_agent_name(name)
     available = not get_paths().agent_dir(normalized).exists()
@@ -166,7 +149,6 @@ async def get_agent(name: str) -> AgentResponse:
     Raises:
         HTTPException: 404 if agent not found.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     name = _normalize_agent_name(name)
 
@@ -199,7 +181,6 @@ async def create_agent_endpoint(request: AgentCreateRequest) -> AgentResponse:
     Raises:
         HTTPException: 409 if agent already exists, 422 if name is invalid.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(request.name)
     normalized_name = _normalize_agent_name(request.name)
 
@@ -219,8 +200,6 @@ async def create_agent_endpoint(request: AgentCreateRequest) -> AgentResponse:
             config_data["model"] = request.model
         if request.tool_groups is not None:
             config_data["tool_groups"] = request.tool_groups
-        if request.skills is not None:
-            config_data["skills"] = request.skills
 
         config_file = agent_dir / "config.yaml"
         with open(config_file, "w", encoding="utf-8") as f:
@@ -264,7 +243,6 @@ async def update_agent(name: str, request: AgentUpdateRequest) -> AgentResponse:
     Raises:
         HTTPException: 404 if agent not found.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     name = _normalize_agent_name(name)
 
@@ -277,32 +255,21 @@ async def update_agent(name: str, request: AgentUpdateRequest) -> AgentResponse:
 
     try:
         # Update config if any config fields changed
-        # Use model_fields_set to distinguish "field omitted" from "explicitly set to null".
-        # This is critical for skills where None means "inherit all" (not "don't change").
-        fields_set = request.model_fields_set
-        config_changed = bool(fields_set & {"description", "model", "tool_groups", "skills"})
+        config_changed = any(v is not None for v in [request.description, request.model, request.tool_groups])
 
         if config_changed:
             updated: dict = {
                 "name": agent_cfg.name,
-                "description": request.description if "description" in fields_set else agent_cfg.description,
+                "description": request.description if request.description is not None else agent_cfg.description,
             }
-            new_model = request.model if "model" in fields_set else agent_cfg.model
+            new_model = request.model if request.model is not None else agent_cfg.model
             if new_model is not None:
                 updated["model"] = new_model
 
-            new_tool_groups = request.tool_groups if "tool_groups" in fields_set else agent_cfg.tool_groups
+            new_tool_groups = request.tool_groups if request.tool_groups is not None else agent_cfg.tool_groups
             if new_tool_groups is not None:
                 updated["tool_groups"] = new_tool_groups
 
-            # skills: None = inherit all, [] = no skills, ["a","b"] = whitelist
-            if "skills" in fields_set:
-                new_skills = request.skills
-            else:
-                new_skills = agent_cfg.skills
-            if new_skills is not None:
-                updated["skills"] = new_skills
-
             config_file = agent_dir / "config.yaml"
             with open(config_file, "w", encoding="utf-8") as f:
                 yaml.dump(updated, f, default_flow_style=False, allow_unicode=True)
@@ -348,8 +315,6 @@ async def get_user_profile() -> UserProfileResponse:
     Returns:
         UserProfileResponse with content=None if USER.md does not exist yet.
     """
-    _require_agents_api_enabled()
-
     try:
         user_md_path = get_paths().user_md_file
         if not user_md_path.exists():
@@ -376,8 +341,6 @@ async def update_user_profile(request: UserProfileUpdateRequest) -> UserProfileR
     Returns:
         UserProfileResponse with the saved content.
     """
-    _require_agents_api_enabled()
-
     try:
         paths = get_paths()
         paths.base_dir.mkdir(parents=True, exist_ok=True)
@@ -404,7 +367,6 @@ async def delete_agent(name: str) -> None:
     Raises:
         HTTPException: 404 if agent not found.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     name = _normalize_agent_name(name)
 

backend/app/gateway/routers/auth.py

@@ -146,13 +146,7 @@ def _set_session_cookie(response: Response, token: str, request: Request) -> Non
 
 
 # ── Rate Limiting ────────────────────────────────────────────────────────
-# In-process dict — not shared across workers.
-#
-# **Limitation**: with multi-worker deployments (e.g., gunicorn -w N), each
-# worker maintains its own lockout table, so an attacker effectively gets
-# N × _MAX_LOGIN_ATTEMPTS guesses before being locked out everywhere. For
-# production multi-worker setups, replace this with a shared store (Redis,
-# database-backed counter) to enforce a true per-IP limit.
+# In-process dict — not shared across workers. Sufficient for single-worker deployments.
 
 _MAX_LOGIN_ATTEMPTS = 5
 _LOCKOUT_SECONDS = 300  # 5 minutes
@@ -382,80 +376,11 @@ async def get_me(request: Request):
     return UserResponse(id=str(user.id), email=user.email, system_role=user.system_role, needs_setup=user.needs_setup)
 
 
-_SETUP_STATUS_COOLDOWN: dict[str, float] = {}
-_SETUP_STATUS_COOLDOWN_SECONDS = 60
-_MAX_TRACKED_SETUP_STATUS_IPS = 10000
-
-
 @router.get("/setup-status")
-async def setup_status(request: Request):
-    """Check if an admin account exists. Returns needs_setup=True when no admin exists."""
-    client_ip = _get_client_ip(request)
-    now = time.time()
-    last_check = _SETUP_STATUS_COOLDOWN.get(client_ip, 0)
-    elapsed = now - last_check
-    if elapsed < _SETUP_STATUS_COOLDOWN_SECONDS:
-        retry_after = max(1, int(_SETUP_STATUS_COOLDOWN_SECONDS - elapsed))
-        raise HTTPException(
-            status_code=status.HTTP_429_TOO_MANY_REQUESTS,
-            detail="Setup status check is rate limited",
-            headers={"Retry-After": str(retry_after)},
-        )
-    # Evict stale entries when dict grows too large to bound memory usage.
-    if len(_SETUP_STATUS_COOLDOWN) >= _MAX_TRACKED_SETUP_STATUS_IPS:
-        cutoff = now - _SETUP_STATUS_COOLDOWN_SECONDS
-        stale = [k for k, t in _SETUP_STATUS_COOLDOWN.items() if t < cutoff]
-        for k in stale:
-            del _SETUP_STATUS_COOLDOWN[k]
-        # If still too large after evicting expired entries, remove oldest half.
-        if len(_SETUP_STATUS_COOLDOWN) >= _MAX_TRACKED_SETUP_STATUS_IPS:
-            by_time = sorted(_SETUP_STATUS_COOLDOWN.items(), key=lambda kv: kv[1])
-            for k, _ in by_time[: len(by_time) // 2]:
-                del _SETUP_STATUS_COOLDOWN[k]
-    _SETUP_STATUS_COOLDOWN[client_ip] = now
-    admin_count = await get_local_provider().count_admin_users()
-    return {"needs_setup": admin_count == 0}
-
-
-class InitializeAdminRequest(BaseModel):
-    """Request model for first-boot admin account creation."""
-
-    email: EmailStr
-    password: str = Field(..., min_length=8)
-
-    _strong_password = field_validator("password")(classmethod(lambda cls, v: _validate_strong_password(v)))
-
-
-@router.post("/initialize", response_model=UserResponse, status_code=status.HTTP_201_CREATED)
-async def initialize_admin(request: Request, response: Response, body: InitializeAdminRequest):
-    """Create the first admin account on initial system setup.
-
-    Only callable when no admin exists. Returns 409 Conflict if an admin
-    already exists.
-
-    On success, the admin account is created with ``needs_setup=False`` and
-    the session cookie is set.
-    """
-    admin_count = await get_local_provider().count_admin_users()
-    if admin_count > 0:
-        raise HTTPException(
-            status_code=status.HTTP_409_CONFLICT,
-            detail=AuthErrorResponse(code=AuthErrorCode.SYSTEM_ALREADY_INITIALIZED, message="System already initialized").model_dump(),
-        )
-
-    try:
-        user = await get_local_provider().create_user(email=body.email, password=body.password, system_role="admin", needs_setup=False)
-    except ValueError:
-        # DB unique-constraint race: another concurrent request beat us.
-        raise HTTPException(
-            status_code=status.HTTP_409_CONFLICT,
-            detail=AuthErrorResponse(code=AuthErrorCode.SYSTEM_ALREADY_INITIALIZED, message="System already initialized").model_dump(),
-        )
-
-    token = create_access_token(str(user.id), token_version=user.token_version)
-    _set_session_cookie(response, token, request)
-
-    return UserResponse(id=str(user.id), email=user.email, system_role=user.system_role)
+async def setup_status():
+    """Check if admin account exists. Always False after first boot."""
+    user_count = await get_local_provider().count_users()
+    return {"needs_setup": user_count == 0}
 
 
 # ── OAuth Endpoints (Future/Placeholder) ─────────────────────────────────

backend/app/gateway/routers/feedback.py

@@ -30,16 +30,11 @@ class FeedbackCreateRequest(BaseModel):
     message_id: str | None = Field(default=None, description="Optional: scope feedback to a specific message")
 
 
-class FeedbackUpsertRequest(BaseModel):
-    rating: int = Field(..., description="Feedback rating: +1 (positive) or -1 (negative)")
-    comment: str | None = Field(default=None, description="Optional text feedback")
-
-
 class FeedbackResponse(BaseModel):
     feedback_id: str
     run_id: str
     thread_id: str
-    user_id: str | None = None
+    owner_id: str | None = None
     message_id: str | None = None
     rating: int
     comment: str | None = None
@@ -58,57 +53,6 @@ class FeedbackStatsResponse(BaseModel):
 # ---------------------------------------------------------------------------
 
 
-@router.put("/{thread_id}/runs/{run_id}/feedback", response_model=FeedbackResponse)
-@require_permission("threads", "write", owner_check=True, require_existing=True)
-async def upsert_feedback(
-    thread_id: str,
-    run_id: str,
-    body: FeedbackUpsertRequest,
-    request: Request,
-) -> dict[str, Any]:
-    """Create or update feedback for a run (idempotent)."""
-    if body.rating not in (1, -1):
-        raise HTTPException(status_code=400, detail="rating must be +1 or -1")
-
-    user_id = await get_current_user(request)
-
-    run_store = get_run_store(request)
-    run = await run_store.get(run_id)
-    if run is None:
-        raise HTTPException(status_code=404, detail=f"Run {run_id} not found")
-    if run.get("thread_id") != thread_id:
-        raise HTTPException(status_code=404, detail=f"Run {run_id} not found in thread {thread_id}")
-
-    feedback_repo = get_feedback_repo(request)
-    return await feedback_repo.upsert(
-        run_id=run_id,
-        thread_id=thread_id,
-        rating=body.rating,
-        user_id=user_id,
-        comment=body.comment,
-    )
-
-
-@router.delete("/{thread_id}/runs/{run_id}/feedback")
-@require_permission("threads", "delete", owner_check=True, require_existing=True)
-async def delete_run_feedback(
-    thread_id: str,
-    run_id: str,
-    request: Request,
-) -> dict[str, bool]:
-    """Delete the current user's feedback for a run."""
-    user_id = await get_current_user(request)
-    feedback_repo = get_feedback_repo(request)
-    deleted = await feedback_repo.delete_by_run(
-        thread_id=thread_id,
-        run_id=run_id,
-        user_id=user_id,
-    )
-    if not deleted:
-        raise HTTPException(status_code=404, detail="No feedback found for this run")
-    return {"success": True}
-
-
 @router.post("/{thread_id}/runs/{run_id}/feedback", response_model=FeedbackResponse)
 @require_permission("threads", "write", owner_check=True, require_existing=True)
 async def create_feedback(
@@ -136,7 +80,7 @@ async def create_feedback(
         run_id=run_id,
         thread_id=thread_id,
         rating=body.rating,
-        user_id=user_id,
+        owner_id=user_id,
         message_id=body.message_id,
         comment=body.comment,
     )

backend/app/gateway/routers/memory.py

@@ -13,7 +13,6 @@ from deerflow.agents.memory.updater import (
     update_memory_fact,
 )
 from deerflow.config.memory_config import get_memory_config
-from deerflow.runtime.user_context import get_effective_user_id
 
 router = APIRouter(prefix="/api", tags=["memory"])
 
@@ -148,7 +147,7 @@ async def get_memory() -> MemoryResponse:
         }
         ```
     """
-    memory_data = get_memory_data(user_id=get_effective_user_id())
+    memory_data = get_memory_data()
     return MemoryResponse(**memory_data)
 
 
@@ -168,7 +167,7 @@ async def reload_memory() -> MemoryResponse:
     Returns:
         The reloaded memory data.
     """
-    memory_data = reload_memory_data(user_id=get_effective_user_id())
+    memory_data = reload_memory_data()
     return MemoryResponse(**memory_data)
 
 
@@ -182,7 +181,7 @@ async def reload_memory() -> MemoryResponse:
 async def clear_memory() -> MemoryResponse:
     """Clear all persisted memory data."""
     try:
-        memory_data = clear_memory_data(user_id=get_effective_user_id())
+        memory_data = clear_memory_data()
     except OSError as exc:
         raise HTTPException(status_code=500, detail="Failed to clear memory data.") from exc
 
@@ -203,7 +202,6 @@ async def create_memory_fact_endpoint(request: FactCreateRequest) -> MemoryRespo
             content=request.content,
             category=request.category,
             confidence=request.confidence,
-            user_id=get_effective_user_id(),
         )
     except ValueError as exc:
         raise _map_memory_fact_value_error(exc) from exc
@@ -223,7 +221,7 @@ async def create_memory_fact_endpoint(request: FactCreateRequest) -> MemoryRespo
 async def delete_memory_fact_endpoint(fact_id: str) -> MemoryResponse:
     """Delete a single fact from memory by fact id."""
     try:
-        memory_data = delete_memory_fact(fact_id, user_id=get_effective_user_id())
+        memory_data = delete_memory_fact(fact_id)
     except KeyError as exc:
         raise HTTPException(status_code=404, detail=f"Memory fact '{fact_id}' not found.") from exc
     except OSError as exc:
@@ -247,7 +245,6 @@ async def update_memory_fact_endpoint(fact_id: str, request: FactPatchRequest) -
             content=request.content,
             category=request.category,
             confidence=request.confidence,
-            user_id=get_effective_user_id(),
         )
     except ValueError as exc:
         raise _map_memory_fact_value_error(exc) from exc
@@ -268,7 +265,7 @@ async def update_memory_fact_endpoint(fact_id: str, request: FactPatchRequest) -
 )
 async def export_memory() -> MemoryResponse:
     """Export the current memory data."""
-    memory_data = get_memory_data(user_id=get_effective_user_id())
+    memory_data = get_memory_data()
     return MemoryResponse(**memory_data)
 
 
@@ -282,7 +279,7 @@ async def export_memory() -> MemoryResponse:
 async def import_memory(request: MemoryResponse) -> MemoryResponse:
     """Import and persist memory data."""
     try:
-        memory_data = import_memory_data(request.model_dump(), user_id=get_effective_user_id())
+        memory_data = import_memory_data(request.model_dump())
     except OSError as exc:
         raise HTTPException(status_code=500, detail="Failed to import memory data.") from exc
 
@@ -340,7 +337,7 @@ async def get_memory_status() -> MemoryStatusResponse:
         Combined memory configuration and current data.
     """
     config = get_memory_config()
-    memory_data = get_memory_data(user_id=get_effective_user_id())
+    memory_data = get_memory_data()
 
     return MemoryStatusResponse(
         config=MemoryConfigResponse(

backend/app/gateway/routers/models.py

@@ -1,8 +1,7 @@
-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, HTTPException
 from pydantic import BaseModel, Field
 
-from app.gateway.deps import get_config
-from deerflow.config.app_config import AppConfig
+from deerflow.config import get_app_config
 
 router = APIRouter(prefix="/api", tags=["models"])
 
@@ -18,17 +17,10 @@ class ModelResponse(BaseModel):
     supports_reasoning_effort: bool = Field(default=False, description="Whether model supports reasoning effort")
 
 
-class TokenUsageResponse(BaseModel):
-    """Token usage display configuration."""
-
-    enabled: bool = Field(default=False, description="Whether token usage display is enabled")
-
-
 class ModelsListResponse(BaseModel):
     """Response model for listing all models."""
 
     models: list[ModelResponse]
-    token_usage: TokenUsageResponse
 
 
 @router.get(
@@ -37,14 +29,14 @@ class ModelsListResponse(BaseModel):
     summary="List All Models",
     description="Retrieve a list of all available AI models configured in the system.",
 )
-async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResponse:
+async def list_models() -> ModelsListResponse:
     """List all available models from configuration.
 
     Returns model information suitable for frontend display,
     excluding sensitive fields like API keys and internal configuration.
 
     Returns:
-        A list of all configured models with their metadata and token usage display settings.
+        A list of all configured models with their metadata.
 
     Example Response:
         ```json
@@ -52,27 +44,21 @@ async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResp
             "models": [
                 {
                     "name": "gpt-4",
-                    "model": "gpt-4",
                     "display_name": "GPT-4",
                     "description": "OpenAI GPT-4 model",
-                    "supports_thinking": false,
-                    "supports_reasoning_effort": false
+                    "supports_thinking": false
                 },
                 {
                     "name": "claude-3-opus",
-                    "model": "claude-3-opus",
                     "display_name": "Claude 3 Opus",
                     "description": "Anthropic Claude 3 Opus model",
-                    "supports_thinking": true,
-                    "supports_reasoning_effort": false
+                    "supports_thinking": true
                 }
-            ],
-            "token_usage": {
-                "enabled": true
-            }
+            ]
         }
         ```
     """
+    config = get_app_config()
     models = [
         ModelResponse(
             name=model.name,
@@ -84,10 +70,7 @@ async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResp
         )
         for model in config.models
     ]
-    return ModelsListResponse(
-        models=models,
-        token_usage=TokenUsageResponse(enabled=config.token_usage.enabled),
-    )
+    return ModelsListResponse(models=models)
 
 
 @router.get(
@@ -96,7 +79,7 @@ async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResp
     summary="Get Model Details",
     description="Retrieve detailed information about a specific AI model by its name.",
 )
-async def get_model(model_name: str, config: AppConfig = Depends(get_config)) -> ModelResponse:
+async def get_model(model_name: str) -> ModelResponse:
     """Get a specific model by name.
 
     Args:
@@ -118,6 +101,7 @@ async def get_model(model_name: str, config: AppConfig = Depends(get_config)) ->
         }
         ```
     """
+    config = get_app_config()
     model = config.get_model_config(model_name)
     if model is None:
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")

backend/app/gateway/routers/runs.py

@@ -11,11 +11,10 @@ import asyncio
 import logging
 import uuid
 
-from fastapi import APIRouter, HTTPException, Query, Request
+from fastapi import APIRouter, Request
 from fastapi.responses import StreamingResponse
 
-from app.gateway.authz import require_permission
-from app.gateway.deps import get_checkpointer, get_feedback_repo, get_run_event_store, get_run_manager, get_run_store, get_stream_bridge
+from app.gateway.deps import get_checkpointer, get_run_manager, get_stream_bridge
 from app.gateway.routers.thread_runs import RunCreateRequest
 from app.gateway.services import sse_consumer, start_run
 from deerflow.runtime import serialize_channel_values
@@ -86,58 +85,3 @@ async def stateless_wait(body: RunCreateRequest, request: Request) -> dict:
         logger.exception("Failed to fetch final state for run %s", record.run_id)
 
     return {"status": record.status.value, "error": record.error}
-
-
-# ---------------------------------------------------------------------------
-# Run-scoped read endpoints
-# ---------------------------------------------------------------------------
-
-
-async def _resolve_run(run_id: str, request: Request) -> dict:
-    """Fetch run by run_id with user ownership check. Raises 404 if not found."""
-    run_store = get_run_store(request)
-    record = await run_store.get(run_id)  # user_id=AUTO filters by contextvar
-    if record is None:
-        raise HTTPException(status_code=404, detail=f"Run {run_id} not found")
-    return record
-
-
-@router.get("/{run_id}/messages")
-@require_permission("runs", "read")
-async def run_messages(
-    run_id: str,
-    request: Request,
-    limit: int = Query(default=50, le=200, ge=1),
-    before_seq: int | None = Query(default=None),
-    after_seq: int | None = Query(default=None),
-) -> dict:
-    """Return paginated messages for a run (cursor-based).
-
-    Pagination:
-    - after_seq: messages with seq > after_seq (forward)
-    - before_seq: messages with seq < before_seq (backward)
-    - neither: latest messages
-
-    Response: { data: [...], has_more: bool }
-    """
-    run = await _resolve_run(run_id, request)
-    event_store = get_run_event_store(request)
-    rows = await event_store.list_messages_by_run(
-        run["thread_id"],
-        run_id,
-        limit=limit + 1,
-        before_seq=before_seq,
-        after_seq=after_seq,
-    )
-    has_more = len(rows) > limit
-    data = rows[:limit] if has_more else rows
-    return {"data": data, "has_more": has_more}
-
-
-@router.get("/{run_id}/feedback")
-@require_permission("runs", "read")
-async def run_feedback(run_id: str, request: Request) -> list[dict]:
-    """Return all feedback for a run."""
-    run = await _resolve_run(run_id, request)
-    feedback_repo = get_feedback_repo(request)
-    return await feedback_repo.list_by_run(run["thread_id"], run_id)

backend/app/gateway/routers/skills.py

@@ -1,20 +1,29 @@
 import json
 import logging
+import shutil
 from pathlib import Path
 
-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, HTTPException
 from pydantic import BaseModel, Field
 
-from app.gateway.deps import get_config
 from app.gateway.path_utils import resolve_thread_virtual_path
 from deerflow.agents.lead_agent.prompt import refresh_skills_system_prompt_cache_async
-from deerflow.config.app_config import AppConfig
 from deerflow.config.extensions_config import ExtensionsConfig, SkillStateConfig, get_extensions_config, reload_extensions_config
-from deerflow.skills import Skill
-from deerflow.skills.installer import SkillAlreadyExistsError
+from deerflow.skills import Skill, load_skills
+from deerflow.skills.installer import SkillAlreadyExistsError, install_skill_from_archive
+from deerflow.skills.manager import (
+    append_history,
+    atomic_write,
+    custom_skill_exists,
+    ensure_custom_skill_is_editable,
+    get_custom_skill_dir,
+    get_custom_skill_file,
+    get_skill_history_file,
+    read_custom_skill_content,
+    read_history,
+    validate_skill_markdown_content,
+)
 from deerflow.skills.security_scanner import scan_skill_content
-from deerflow.skills.storage import get_or_new_skill_storage
-from deerflow.skills.types import SKILL_MD_FILE, SkillCategory
 
 logger = logging.getLogger(__name__)
 
@@ -27,7 +36,7 @@ class SkillResponse(BaseModel):
     name: str = Field(..., description="Name of the skill")
     description: str = Field(..., description="Description of what the skill does")
     license: str | None = Field(None, description="License information")
-    category: SkillCategory = Field(..., description="Category of the skill (public or custom)")
+    category: str = Field(..., description="Category of the skill (public or custom)")
     enabled: bool = Field(default=True, description="Whether this skill is enabled")
 
 
@@ -91,9 +100,9 @@ def _skill_to_response(skill: Skill) -> SkillResponse:
     summary="List All Skills",
     description="Retrieve a list of all available skills from both public and custom directories.",
 )
-async def list_skills(config: AppConfig = Depends(get_config)) -> SkillsListResponse:
+async def list_skills() -> SkillsListResponse:
     try:
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         return SkillsListResponse(skills=[_skill_to_response(skill) for skill in skills])
     except Exception as e:
         logger.error(f"Failed to load skills: {e}", exc_info=True)
@@ -106,10 +115,10 @@ async def list_skills(config: AppConfig = Depends(get_config)) -> SkillsListResp
     summary="Install Skill",
     description="Install a skill from a .skill file (ZIP archive) located in the thread's user-data directory.",
 )
-async def install_skill(request: SkillInstallRequest, config: AppConfig = Depends(get_config)) -> SkillInstallResponse:
+async def install_skill(request: SkillInstallRequest) -> SkillInstallResponse:
     try:
         skill_file_path = resolve_thread_virtual_path(request.thread_id, request.path)
-        result = await get_or_new_skill_storage(app_config=config).ainstall_skill_from_archive(skill_file_path)
+        result = install_skill_from_archive(skill_file_path)
         await refresh_skills_system_prompt_cache_async()
         return SkillInstallResponse(**result)
     except FileNotFoundError as e:
@@ -126,9 +135,9 @@ async def install_skill(request: SkillInstallRequest, config: AppConfig = Depend
 
 
 @router.get("/skills/custom", response_model=SkillsListResponse, summary="List Custom Skills")
-async def list_custom_skills(config: AppConfig = Depends(get_config)) -> SkillsListResponse:
+async def list_custom_skills() -> SkillsListResponse:
     try:
-        skills = [skill for skill in get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False) if skill.category == SkillCategory.CUSTOM]
+        skills = [skill for skill in load_skills(enabled_only=False) if skill.category == "custom"]
         return SkillsListResponse(skills=[_skill_to_response(skill) for skill in skills])
     except Exception as e:
         logger.error("Failed to list custom skills: %s", e, exc_info=True)
@@ -136,14 +145,13 @@ async def list_custom_skills(config: AppConfig = Depends(get_config)) -> SkillsL
 
 
 @router.get("/skills/custom/{skill_name}", response_model=CustomSkillContentResponse, summary="Get Custom Skill Content")
-async def get_custom_skill(skill_name: str, config: AppConfig = Depends(get_config)) -> CustomSkillContentResponse:
+async def get_custom_skill(skill_name: str) -> CustomSkillContentResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
-        skill = next((s for s in skills if s.name == skill_name and s.category == SkillCategory.CUSTOM), None)
+        skills = load_skills(enabled_only=False)
+        skill = next((s for s in skills if s.name == skill_name and s.category == "custom"), None)
         if skill is None:
             raise HTTPException(status_code=404, detail=f"Custom skill '{skill_name}' not found")
-        return CustomSkillContentResponse(**_skill_to_response(skill).model_dump(), content=get_or_new_skill_storage(app_config=config).read_custom_skill(skill_name))
+        return CustomSkillContentResponse(**_skill_to_response(skill).model_dump(), content=read_custom_skill_content(skill_name))
     except HTTPException:
         raise
     except Exception as e:
@@ -152,31 +160,30 @@ async def get_custom_skill(skill_name: str, config: AppConfig = Depends(get_conf
 
 
 @router.put("/skills/custom/{skill_name}", response_model=CustomSkillContentResponse, summary="Edit Custom Skill")
-async def update_custom_skill(skill_name: str, request: CustomSkillUpdateRequest, config: AppConfig = Depends(get_config)) -> CustomSkillContentResponse:
+async def update_custom_skill(skill_name: str, request: CustomSkillUpdateRequest) -> CustomSkillContentResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        storage = get_or_new_skill_storage(app_config=config)
-        storage.ensure_custom_skill_is_editable(skill_name)
-        storage.validate_skill_markdown_content(skill_name, request.content)
-        scan = await scan_skill_content(request.content, executable=False, location=f"{skill_name}/{SKILL_MD_FILE}", app_config=config)
+        ensure_custom_skill_is_editable(skill_name)
+        validate_skill_markdown_content(skill_name, request.content)
+        scan = await scan_skill_content(request.content, executable=False, location=f"{skill_name}/SKILL.md")
         if scan.decision == "block":
             raise HTTPException(status_code=400, detail=f"Security scan blocked the edit: {scan.reason}")
-        prev_content = storage.read_custom_skill(skill_name)
-        storage.write_custom_skill(skill_name, SKILL_MD_FILE, request.content)
-        storage.append_history(
+        skill_file = get_custom_skill_dir(skill_name) / "SKILL.md"
+        prev_content = skill_file.read_text(encoding="utf-8")
+        atomic_write(skill_file, request.content)
+        append_history(
             skill_name,
             {
                 "action": "human_edit",
                 "author": "human",
                 "thread_id": None,
-                "file_path": SKILL_MD_FILE,
+                "file_path": "SKILL.md",
                 "prev_content": prev_content,
                 "new_content": request.content,
                 "scanner": {"decision": scan.decision, "reason": scan.reason},
             },
         )
         await refresh_skills_system_prompt_cache_async()
-        return await get_custom_skill(skill_name, config)
+        return await get_custom_skill(skill_name)
     except HTTPException:
         raise
     except FileNotFoundError as e:
@@ -189,22 +196,24 @@ async def update_custom_skill(skill_name: str, request: CustomSkillUpdateRequest
 
 
 @router.delete("/skills/custom/{skill_name}", summary="Delete Custom Skill")
-async def delete_custom_skill(skill_name: str, config: AppConfig = Depends(get_config)) -> dict[str, bool]:
+async def delete_custom_skill(skill_name: str) -> dict[str, bool]:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        storage = get_or_new_skill_storage(app_config=config)
-        storage.delete_custom_skill(
+        ensure_custom_skill_is_editable(skill_name)
+        skill_dir = get_custom_skill_dir(skill_name)
+        prev_content = read_custom_skill_content(skill_name)
+        append_history(
             skill_name,
-            history_meta={
+            {
                 "action": "human_delete",
                 "author": "human",
                 "thread_id": None,
-                "file_path": SKILL_MD_FILE,
-                "prev_content": None,
+                "file_path": "SKILL.md",
+                "prev_content": prev_content,
                 "new_content": None,
                 "scanner": {"decision": "allow", "reason": "Deletion requested."},
             },
         )
+        shutil.rmtree(skill_dir)
         await refresh_skills_system_prompt_cache_async()
         return {"success": True}
     except FileNotFoundError as e:
@@ -217,13 +226,11 @@ async def delete_custom_skill(skill_name: str, config: AppConfig = Depends(get_c
 
 
 @router.get("/skills/custom/{skill_name}/history", response_model=CustomSkillHistoryResponse, summary="Get Custom Skill History")
-async def get_custom_skill_history(skill_name: str, config: AppConfig = Depends(get_config)) -> CustomSkillHistoryResponse:
+async def get_custom_skill_history(skill_name: str) -> CustomSkillHistoryResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        storage = get_or_new_skill_storage(app_config=config)
-        if not storage.custom_skill_exists(skill_name) and not storage.get_skill_history_file(skill_name).exists():
+        if not custom_skill_exists(skill_name) and not get_skill_history_file(skill_name).exists():
             raise HTTPException(status_code=404, detail=f"Custom skill '{skill_name}' not found")
-        return CustomSkillHistoryResponse(history=storage.read_history(skill_name))
+        return CustomSkillHistoryResponse(history=read_history(skill_name))
     except HTTPException:
         raise
     except Exception as e:
@@ -232,39 +239,38 @@ async def get_custom_skill_history(skill_name: str, config: AppConfig = Depends(
 
 
 @router.post("/skills/custom/{skill_name}/rollback", response_model=CustomSkillContentResponse, summary="Rollback Custom Skill")
-async def rollback_custom_skill(skill_name: str, request: SkillRollbackRequest, config: AppConfig = Depends(get_config)) -> CustomSkillContentResponse:
+async def rollback_custom_skill(skill_name: str, request: SkillRollbackRequest) -> CustomSkillContentResponse:
     try:
-        storage = get_or_new_skill_storage(app_config=config)
-        if not storage.custom_skill_exists(skill_name) and not storage.get_skill_history_file(skill_name).exists():
+        if not custom_skill_exists(skill_name) and not get_skill_history_file(skill_name).exists():
             raise HTTPException(status_code=404, detail=f"Custom skill '{skill_name}' not found")
-        history = storage.read_history(skill_name)
+        history = read_history(skill_name)
         if not history:
             raise HTTPException(status_code=400, detail=f"Custom skill '{skill_name}' has no history")
         record = history[request.history_index]
         target_content = record.get("prev_content")
         if target_content is None:
             raise HTTPException(status_code=400, detail="Selected history entry has no previous content to roll back to")
-        storage.validate_skill_markdown_content(skill_name, target_content)
-        scan = await scan_skill_content(target_content, executable=False, location=f"{skill_name}/{SKILL_MD_FILE}", app_config=config)
-        skill_file = storage.get_custom_skill_file(skill_name)
+        validate_skill_markdown_content(skill_name, target_content)
+        scan = await scan_skill_content(target_content, executable=False, location=f"{skill_name}/SKILL.md")
+        skill_file = get_custom_skill_file(skill_name)
         current_content = skill_file.read_text(encoding="utf-8") if skill_file.exists() else None
         history_entry = {
             "action": "rollback",
             "author": "human",
             "thread_id": None,
-            "file_path": SKILL_MD_FILE,
+            "file_path": "SKILL.md",
             "prev_content": current_content,
             "new_content": target_content,
             "rollback_from_ts": record.get("ts"),
             "scanner": {"decision": scan.decision, "reason": scan.reason},
         }
         if scan.decision == "block":
-            storage.append_history(skill_name, history_entry)
+            append_history(skill_name, history_entry)
             raise HTTPException(status_code=400, detail=f"Rollback blocked by security scanner: {scan.reason}")
-        storage.write_custom_skill(skill_name, SKILL_MD_FILE, target_content)
-        storage.append_history(skill_name, history_entry)
+        atomic_write(skill_file, target_content)
+        append_history(skill_name, history_entry)
         await refresh_skills_system_prompt_cache_async()
-        return await get_custom_skill(skill_name, config)
+        return await get_custom_skill(skill_name)
     except HTTPException:
         raise
     except IndexError:
@@ -284,10 +290,9 @@ async def rollback_custom_skill(skill_name: str, request: SkillRollbackRequest,
     summary="Get Skill Details",
     description="Retrieve detailed information about a specific skill by its name.",
 )
-async def get_skill(skill_name: str, config: AppConfig = Depends(get_config)) -> SkillResponse:
+async def get_skill(skill_name: str) -> SkillResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         skill = next((s for s in skills if s.name == skill_name), None)
 
         if skill is None:
@@ -307,10 +312,9 @@ async def get_skill(skill_name: str, config: AppConfig = Depends(get_config)) ->
     summary="Update Skill",
     description="Update a skill's enabled status by modifying the extensions_config.json file.",
 )
-async def update_skill(skill_name: str, request: SkillUpdateRequest, config: AppConfig = Depends(get_config)) -> SkillResponse:
+async def update_skill(skill_name: str, request: SkillUpdateRequest) -> SkillResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         skill = next((s for s in skills if s.name == skill_name), None)
 
         if skill is None:
@@ -336,7 +340,7 @@ async def update_skill(skill_name: str, request: SkillUpdateRequest, config: App
         reload_extensions_config()
         await refresh_skills_system_prompt_cache_async()
 
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         updated_skill = next((s for s in skills if s.name == skill_name), None)
 
         if updated_skill is None:

backend/app/gateway/routers/suggestions.py

@@ -1,13 +1,11 @@
 import json
 import logging
 
-from fastapi import APIRouter, Depends, Request
+from fastapi import APIRouter, Request
 from langchain_core.messages import HumanMessage, SystemMessage
 from pydantic import BaseModel, Field
 
 from app.gateway.authz import require_permission
-from app.gateway.deps import get_config
-from deerflow.config.app_config import AppConfig
 from deerflow.models import create_chat_model
 
 logger = logging.getLogger(__name__)
@@ -102,12 +100,7 @@ def _format_conversation(messages: list[SuggestionMessage]) -> str:
     description="Generate short follow-up questions a user might ask next, based on recent conversation context.",
 )
 @require_permission("threads", "read", owner_check=True)
-async def generate_suggestions(
-    thread_id: str,
-    body: SuggestionsRequest,
-    request: Request,
-    config: AppConfig = Depends(get_config),
-) -> SuggestionsResponse:
+async def generate_suggestions(thread_id: str, body: SuggestionsRequest, request: Request) -> SuggestionsResponse:
     if not body.messages:
         return SuggestionsResponse(suggestions=[])
 
@@ -129,8 +122,8 @@ async def generate_suggestions(
     user_content = f"Conversation Context:\n{conversation}\n\nGenerate {n} follow-up questions"
 
     try:
-        model = create_chat_model(name=body.model_name, thinking_enabled=False, app_config=config)
-        response = await model.ainvoke([SystemMessage(content=system_instruction), HumanMessage(content=user_content)], config={"run_name": "suggest_agent"})
+        model = create_chat_model(name=body.model_name, thinking_enabled=False)
+        response = await model.ainvoke([SystemMessage(content=system_instruction), HumanMessage(content=user_content)])
         raw = _extract_response_text(response.content)
         suggestions = _parse_json_string_list(raw) or []
         cleaned = [s.replace("\n", " ").strip() for s in suggestions if s.strip()]

backend/app/gateway/routers/thread_runs.py

@@ -20,7 +20,7 @@ from fastapi.responses import Response, StreamingResponse
 from pydantic import BaseModel, Field
 
 from app.gateway.authz import require_permission
-from app.gateway.deps import get_checkpointer, get_current_user, get_feedback_repo, get_run_event_store, get_run_manager, get_run_store, get_stream_bridge
+from app.gateway.deps import get_checkpointer, get_run_event_store, get_run_manager, get_run_store, get_stream_bridge
 from app.gateway.services import sse_consumer, start_run
 from deerflow.runtime import RunRecord, serialize_channel_values
 
@@ -54,6 +54,7 @@ class RunCreateRequest(BaseModel):
     after_seconds: float | None = Field(default=None, description="Delayed execution")
     if_not_exists: Literal["reject", "create"] = Field(default="create", description="Thread creation policy")
     feedback_keys: list[str] | None = Field(default=None, description="LangSmith feedback keys")
+    follow_up_to_run_id: str | None = Field(default=None, description="Run ID this message follows up on. Auto-detected from latest successful run if not provided.")
 
 
 class RunResponse(BaseModel):
@@ -290,67 +291,17 @@ async def list_thread_messages(
     before_seq: int | None = Query(default=None),
     after_seq: int | None = Query(default=None),
 ) -> list[dict]:
-    """Return displayable messages for a thread (across all runs), with feedback attached."""
+    """Return displayable messages for a thread (across all runs)."""
     event_store = get_run_event_store(request)
-    messages = await event_store.list_messages(thread_id, limit=limit, before_seq=before_seq, after_seq=after_seq)
-
-    # Attach feedback to the last AI message of each run
-    feedback_repo = get_feedback_repo(request)
-    user_id = await get_current_user(request)
-    feedback_map = await feedback_repo.list_by_thread_grouped(thread_id, user_id=user_id)
-
-    # Find the last ai_message per run_id
-    last_ai_per_run: dict[str, int] = {}  # run_id -> index in messages list
-    for i, msg in enumerate(messages):
-        if msg.get("event_type") == "ai_message":
-            last_ai_per_run[msg["run_id"]] = i
-
-    # Attach feedback field
-    last_ai_indices = set(last_ai_per_run.values())
-    for i, msg in enumerate(messages):
-        if i in last_ai_indices:
-            run_id = msg["run_id"]
-            fb = feedback_map.get(run_id)
-            msg["feedback"] = (
-                {
-                    "feedback_id": fb["feedback_id"],
-                    "rating": fb["rating"],
-                    "comment": fb.get("comment"),
-                }
-                if fb
-                else None
-            )
-        else:
-            msg["feedback"] = None
-
-    return messages
+    return await event_store.list_messages(thread_id, limit=limit, before_seq=before_seq, after_seq=after_seq)
 
 
 @router.get("/{thread_id}/runs/{run_id}/messages")
 @require_permission("runs", "read", owner_check=True)
-async def list_run_messages(
-    thread_id: str,
-    run_id: str,
-    request: Request,
-    limit: int = Query(default=50, le=200, ge=1),
-    before_seq: int | None = Query(default=None),
-    after_seq: int | None = Query(default=None),
-) -> dict:
-    """Return paginated messages for a specific run.
-
-    Response: { data: [...], has_more: bool }
-    """
+async def list_run_messages(thread_id: str, run_id: str, request: Request) -> list[dict]:
+    """Return displayable messages for a specific run."""
     event_store = get_run_event_store(request)
-    rows = await event_store.list_messages_by_run(
-        thread_id,
-        run_id,
-        limit=limit + 1,
-        before_seq=before_seq,
-        after_seq=after_seq,
-    )
-    has_more = len(rows) > limit
-    data = rows[:limit] if has_more else rows
-    return {"data": data, "has_more": has_more}
+    return await event_store.list_messages_by_run(thread_id, run_id)
 
 
 @router.get("/{thread_id}/runs/{run_id}/events")

backend/app/gateway/routers/threads.py

@@ -25,7 +25,6 @@ from app.gateway.deps import get_checkpointer
 from app.gateway.utils import sanitize_log_param
 from deerflow.config.paths import Paths, get_paths
 from deerflow.runtime import serialize_channel_values
-from deerflow.runtime.user_context import get_effective_user_id
 
 logger = logging.getLogger(__name__)
 router = APIRouter(prefix="/api/threads", tags=["threads"])
@@ -35,7 +34,7 @@ router = APIRouter(prefix="/api/threads", tags=["threads"])
 # them. Pydantic ``@field_validator("metadata")`` strips them on every
 # inbound model below so a malicious client cannot reflect a forged
 # owner identity through the API surface. Defense-in-depth — the
-# row-level invariant is still ``threads_meta.user_id`` populated from
+# row-level invariant is still ``threads_meta.owner_id`` populated from
 # the auth contextvar; this list closes the metadata-blob echo gap.
 _SERVER_RESERVED_METADATA_KEYS: frozenset[str] = frozenset({"owner_id", "user_id"})
 
@@ -143,11 +142,11 @@ class ThreadHistoryRequest(BaseModel):
 # ---------------------------------------------------------------------------
 
 
-def _delete_thread_data(thread_id: str, paths: Paths | None = None, *, user_id: str | None = None) -> ThreadDeleteResponse:
+def _delete_thread_data(thread_id: str, paths: Paths | None = None) -> ThreadDeleteResponse:
     """Delete local persisted filesystem data for a thread."""
     path_manager = paths or get_paths()
     try:
-        path_manager.delete_thread_dir(thread_id, user_id=user_id)
+        path_manager.delete_thread_dir(thread_id)
     except ValueError as exc:
         raise HTTPException(status_code=422, detail=str(exc)) from exc
     except FileNotFoundError:
@@ -195,10 +194,10 @@ async def delete_thread_data(thread_id: str, request: Request) -> ThreadDeleteRe
     and removes the thread_meta row from the configured ThreadMetaStore
     (sqlite or memory).
     """
-    from app.gateway.deps import get_thread_store
+    from app.gateway.deps import get_thread_meta_repo
 
     # Clean local filesystem
-    response = _delete_thread_data(thread_id, user_id=get_effective_user_id())
+    response = _delete_thread_data(thread_id)
 
     # Remove checkpoints (best-effort)
     checkpointer = getattr(request.app.state, "checkpointer", None)
@@ -212,8 +211,8 @@ async def delete_thread_data(thread_id: str, request: Request) -> ThreadDeleteRe
     # Remove thread_meta row (best-effort) — required for sqlite backend
     # so the deleted thread no longer appears in /threads/search.
     try:
-        thread_store = get_thread_store(request)
-        await thread_store.delete(thread_id)
+        thread_meta_repo = get_thread_meta_repo(request)
+        await thread_meta_repo.delete(thread_id)
     except Exception:
         logger.debug("Could not delete thread_meta for %s (not critical)", sanitize_log_param(thread_id))
 
@@ -228,17 +227,17 @@ async def create_thread(body: ThreadCreateRequest, request: Request) -> ThreadRe
     and an empty checkpoint (so state endpoints work immediately).
     Idempotent: returns the existing record when ``thread_id`` already exists.
     """
-    from app.gateway.deps import get_thread_store
+    from app.gateway.deps import get_thread_meta_repo
 
     checkpointer = get_checkpointer(request)
-    thread_store = get_thread_store(request)
+    thread_meta_repo = get_thread_meta_repo(request)
     thread_id = body.thread_id or str(uuid.uuid4())
     now = time.time()
     # ``body.metadata`` is already stripped of server-reserved keys by
     # ``ThreadCreateRequest._strip_reserved`` — see the model definition.
 
     # Idempotency: return existing record when already present
-    existing_record = await thread_store.get(thread_id)
+    existing_record = await thread_meta_repo.get(thread_id)
     if existing_record is not None:
         return ThreadResponse(
             thread_id=thread_id,
@@ -250,7 +249,7 @@ async def create_thread(body: ThreadCreateRequest, request: Request) -> ThreadRe
 
     # Write thread_meta so the thread appears in /threads/search immediately
     try:
-        await thread_store.create(
+        await thread_meta_repo.create(
             thread_id,
             assistant_id=getattr(body, "assistant_id", None),
             metadata=body.metadata,
@@ -294,9 +293,9 @@ async def search_threads(body: ThreadSearchRequest, request: Request) -> list[Th
     Delegates to the configured ThreadMetaStore implementation
     (SQL-backed for sqlite/postgres, Store-backed for memory mode).
     """
-    from app.gateway.deps import get_thread_store
+    from app.gateway.deps import get_thread_meta_repo
 
-    repo = get_thread_store(request)
+    repo = get_thread_meta_repo(request)
     rows = await repo.search(
         metadata=body.metadata or None,
         status=body.status,
@@ -321,22 +320,22 @@ async def search_threads(body: ThreadSearchRequest, request: Request) -> list[Th
 @require_permission("threads", "write", owner_check=True, require_existing=True)
 async def patch_thread(thread_id: str, body: ThreadPatchRequest, request: Request) -> ThreadResponse:
     """Merge metadata into a thread record."""
-    from app.gateway.deps import get_thread_store
+    from app.gateway.deps import get_thread_meta_repo
 
-    thread_store = get_thread_store(request)
-    record = await thread_store.get(thread_id)
+    thread_meta_repo = get_thread_meta_repo(request)
+    record = await thread_meta_repo.get(thread_id)
     if record is None:
         raise HTTPException(status_code=404, detail=f"Thread {thread_id} not found")
 
     # ``body.metadata`` already stripped by ``ThreadPatchRequest._strip_reserved``.
     try:
-        await thread_store.update_metadata(thread_id, body.metadata)
+        await thread_meta_repo.update_metadata(thread_id, body.metadata)
     except Exception:
         logger.exception("Failed to patch thread %s", sanitize_log_param(thread_id))
         raise HTTPException(status_code=500, detail="Failed to update thread")
 
     # Re-read to get the merged metadata + refreshed updated_at
-    record = await thread_store.get(thread_id) or record
+    record = await thread_meta_repo.get(thread_id) or record
     return ThreadResponse(
         thread_id=thread_id,
         status=record.get("status", "idle"),
@@ -355,12 +354,12 @@ async def get_thread(thread_id: str, request: Request) -> ThreadResponse:
     execution status from the checkpointer.  Falls back to the checkpointer
     alone for threads that pre-date ThreadMetaStore adoption (backward compat).
     """
-    from app.gateway.deps import get_thread_store
+    from app.gateway.deps import get_thread_meta_repo
 
-    thread_store = get_thread_store(request)
+    thread_meta_repo = get_thread_meta_repo(request)
     checkpointer = get_checkpointer(request)
 
-    record: dict | None = await thread_store.get(thread_id)
+    record: dict | None = await thread_meta_repo.get(thread_id)
 
     # Derive accurate status from the checkpointer
     config = {"configurable": {"thread_id": thread_id, "checkpoint_ns": ""}}
@@ -403,7 +402,6 @@ async def get_thread(thread_id: str, request: Request) -> ThreadResponse:
     )
 
 
-# ---------------------------------------------------------------------------
 @router.get("/{thread_id}/state", response_model=ThreadStateResponse)
 @require_permission("threads", "read", owner_check=True)
 async def get_thread_state(thread_id: str, request: Request) -> ThreadStateResponse:
@@ -442,10 +440,8 @@ async def get_thread_state(thread_id: str, request: Request) -> ThreadStateRespo
     next_tasks = [t.name for t in tasks_raw if hasattr(t, "name")]
     tasks = [{"id": getattr(t, "id", ""), "name": getattr(t, "name", "")} for t in tasks_raw]
 
-    values = serialize_channel_values(channel_values)
-
     return ThreadStateResponse(
-        values=values,
+        values=serialize_channel_values(channel_values),
         next=next_tasks,
         metadata=metadata,
         checkpoint={"id": checkpoint_id, "ts": str(metadata.get("created_at", ""))},
@@ -466,10 +462,10 @@ async def update_thread_state(thread_id: str, body: ThreadStateUpdateRequest, re
     ThreadMetaStore abstraction so that ``/threads/search`` reflects the
     change immediately in both sqlite and memory backends.
     """
-    from app.gateway.deps import get_thread_store
+    from app.gateway.deps import get_thread_meta_repo
 
     checkpointer = get_checkpointer(request)
-    thread_store = get_thread_store(request)
+    thread_meta_repo = get_thread_meta_repo(request)
 
     # checkpoint_ns must be present in the config for aput — default to ""
     # (the root graph namespace).  checkpoint_id is optional; omitting it
@@ -533,7 +529,7 @@ async def update_thread_state(thread_id: str, body: ThreadStateUpdateRequest, re
         new_title = body.values["title"]
         if new_title:  # Skip empty strings and None
             try:
-                await thread_store.update_display_name(thread_id, new_title)
+                await thread_meta_repo.update_display_name(thread_id, new_title)
             except Exception:
                 logger.debug("Failed to sync title to thread_meta for %s (non-fatal)", sanitize_log_param(thread_id))
 
@@ -586,7 +582,7 @@ async def get_thread_history(thread_id: str, body: ThreadHistoryRequest, request
             if thread_data := channel_values.get("thread_data"):
                 values["thread_data"] = thread_data
 
-            # Attach messages only to the latest checkpoint entry.
+            # Attach messages from checkpointer only for the latest checkpoint
             if is_latest_checkpoint:
                 messages = channel_values.get("messages")
                 if messages:

backend/app/gateway/routers/uploads.py

@@ -4,15 +4,12 @@ import logging
 import os
 import stat
 
-from fastapi import APIRouter, Depends, File, HTTPException, Request, UploadFile
+from fastapi import APIRouter, File, HTTPException, Request, UploadFile
 from pydantic import BaseModel
 
 from app.gateway.authz import require_permission
-from app.gateway.deps import get_config
-from deerflow.config.app_config import AppConfig
 from deerflow.config.paths import get_paths
-from deerflow.runtime.user_context import get_effective_user_id
-from deerflow.sandbox.sandbox_provider import SandboxProvider, get_sandbox_provider
+from deerflow.sandbox.sandbox_provider import get_sandbox_provider
 from deerflow.uploads.manager import (
     PathTraversalError,
     delete_file_safe,
@@ -30,11 +27,6 @@ logger = logging.getLogger(__name__)
 
 router = APIRouter(prefix="/api/threads/{thread_id}/uploads", tags=["uploads"])
 
-UPLOAD_CHUNK_SIZE = 8192
-DEFAULT_MAX_FILES = 10
-DEFAULT_MAX_FILE_SIZE = 50 * 1024 * 1024
-DEFAULT_MAX_TOTAL_SIZE = 100 * 1024 * 1024
-
 
 class UploadResponse(BaseModel):
     """Response model for file upload."""
@@ -44,14 +36,6 @@ class UploadResponse(BaseModel):
     message: str
 
 
-class UploadLimits(BaseModel):
-    """Application-level upload limits exposed to clients."""
-
-    max_files: int
-    max_file_size: int
-    max_total_size: int
-
-
 def _make_file_sandbox_writable(file_path: os.PathLike[str] | str) -> None:
     """Ensure uploaded files remain writable when mounted into non-local sandboxes.
 
@@ -70,124 +54,27 @@ def _make_file_sandbox_writable(file_path: os.PathLike[str] | str) -> None:
     os.chmod(file_path, writable_mode, **chmod_kwargs)
 
 
-def _uses_thread_data_mounts(sandbox_provider: SandboxProvider) -> bool:
-    return bool(getattr(sandbox_provider, "uses_thread_data_mounts", False))
-
-
-def _get_uploads_config_value(app_config: AppConfig, key: str, default: object) -> object:
-    """Read a value from the uploads config, supporting dict and attribute access."""
-    uploads_cfg = getattr(app_config, "uploads", None)
-    if isinstance(uploads_cfg, dict):
-        return uploads_cfg.get(key, default)
-    return getattr(uploads_cfg, key, default)
-
-
-def _get_upload_limit(app_config: AppConfig, key: str, default: int, *, legacy_key: str | None = None) -> int:
-    try:
-        value = _get_uploads_config_value(app_config, key, None)
-        if value is None and legacy_key is not None:
-            value = _get_uploads_config_value(app_config, legacy_key, None)
-        if value is None:
-            value = default
-        limit = int(value)
-        if limit <= 0:
-            raise ValueError
-        return limit
-    except Exception:
-        logger.warning("Invalid uploads.%s value; falling back to %d", key, default)
-        return default
-
-
-def _get_upload_limits(app_config: AppConfig) -> UploadLimits:
-    return UploadLimits(
-        max_files=_get_upload_limit(app_config, "max_files", DEFAULT_MAX_FILES, legacy_key="max_file_count"),
-        max_file_size=_get_upload_limit(app_config, "max_file_size", DEFAULT_MAX_FILE_SIZE, legacy_key="max_single_file_size"),
-        max_total_size=_get_upload_limit(app_config, "max_total_size", DEFAULT_MAX_TOTAL_SIZE),
-    )
-
-
-def _cleanup_uploaded_paths(paths: list[os.PathLike[str] | str]) -> None:
-    for path in reversed(paths):
-        try:
-            os.unlink(path)
-        except FileNotFoundError:
-            pass
-        except Exception:
-            logger.warning("Failed to clean up upload path after rejected request: %s", path, exc_info=True)
-
-
-async def _write_upload_file_streaming(
-    file: UploadFile,
-    file_path: os.PathLike[str] | str,
-    *,
-    display_filename: str,
-    max_single_file_size: int,
-    max_total_size: int,
-    total_size: int,
-) -> tuple[int, int]:
-    file_size = 0
-    with open(file_path, "wb") as output:
-        while chunk := await file.read(UPLOAD_CHUNK_SIZE):
-            file_size += len(chunk)
-            total_size += len(chunk)
-            if file_size > max_single_file_size:
-                raise HTTPException(status_code=413, detail=f"File too large: {display_filename}")
-            if total_size > max_total_size:
-                raise HTTPException(status_code=413, detail="Total upload size too large")
-            output.write(chunk)
-    return file_size, total_size
-
-
-def _auto_convert_documents_enabled(app_config: AppConfig) -> bool:
-    """Return whether automatic host-side document conversion is enabled.
-
-    The secure default is disabled unless an operator explicitly opts in via
-    uploads.auto_convert_documents in config.yaml.
-    """
-    try:
-        raw = _get_uploads_config_value(app_config, "auto_convert_documents", False)
-        if isinstance(raw, str):
-            return raw.strip().lower() in {"1", "true", "yes", "on"}
-        return bool(raw)
-    except Exception:
-        return False
-
-
 @router.post("", response_model=UploadResponse)
-@require_permission("threads", "write", owner_check=True, require_existing=False)
+@require_permission("threads", "write", owner_check=True, require_existing=True)
 async def upload_files(
     thread_id: str,
     request: Request,
     files: list[UploadFile] = File(...),
-    config: AppConfig = Depends(get_config),
 ) -> UploadResponse:
     """Upload multiple files to a thread's uploads directory."""
     if not files:
         raise HTTPException(status_code=400, detail="No files provided")
 
-    limits = _get_upload_limits(config)
-    if len(files) > limits.max_files:
-        raise HTTPException(status_code=413, detail=f"Too many files: maximum is {limits.max_files}")
-
     try:
         uploads_dir = ensure_uploads_dir(thread_id)
     except ValueError as e:
         raise HTTPException(status_code=400, detail=str(e))
-    sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id, user_id=get_effective_user_id())
+    sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id)
     uploaded_files = []
-    written_paths = []
-    sandbox_sync_targets = []
-    total_size = 0
 
     sandbox_provider = get_sandbox_provider()
-    sync_to_sandbox = not _uses_thread_data_mounts(sandbox_provider)
-    sandbox = None
-    if sync_to_sandbox:
-        sandbox_id = sandbox_provider.acquire(thread_id)
-        sandbox = sandbox_provider.get(sandbox_id)
-        if sandbox is None:
-            raise HTTPException(status_code=500, detail="Failed to acquire sandbox")
-    auto_convert_documents = _auto_convert_documents_enabled(config)
+    sandbox_id = sandbox_provider.acquire(thread_id)
+    sandbox = sandbox_provider.get(sandbox_id)
 
     for file in files:
         if not file.filename:
@@ -200,41 +87,35 @@ async def upload_files(
             continue
 
         try:
+            content = await file.read()
             file_path = uploads_dir / safe_filename
-            written_paths.append(file_path)
-            file_size, total_size = await _write_upload_file_streaming(
-                file,
-                file_path,
-                display_filename=safe_filename,
-                max_single_file_size=limits.max_file_size,
-                max_total_size=limits.max_total_size,
-                total_size=total_size,
-            )
+            file_path.write_bytes(content)
 
             virtual_path = upload_virtual_path(safe_filename)
 
-            if sync_to_sandbox:
-                sandbox_sync_targets.append((file_path, virtual_path))
+            if sandbox_id != "local":
+                _make_file_sandbox_writable(file_path)
+                sandbox.update_file(virtual_path, content)
 
             file_info = {
                 "filename": safe_filename,
-                "size": str(file_size),
+                "size": str(len(content)),
                 "path": str(sandbox_uploads / safe_filename),
                 "virtual_path": virtual_path,
                 "artifact_url": upload_artifact_url(thread_id, safe_filename),
             }
 
-            logger.info(f"Saved file: {safe_filename} ({file_size} bytes) to {file_info['path']}")
+            logger.info(f"Saved file: {safe_filename} ({len(content)} bytes) to {file_info['path']}")
 
             file_ext = file_path.suffix.lower()
-            if auto_convert_documents and file_ext in CONVERTIBLE_EXTENSIONS:
+            if file_ext in CONVERTIBLE_EXTENSIONS:
                 md_path = await convert_file_to_markdown(file_path)
                 if md_path:
-                    written_paths.append(md_path)
                     md_virtual_path = upload_virtual_path(md_path.name)
 
-                    if sync_to_sandbox:
-                        sandbox_sync_targets.append((md_path, md_virtual_path))
+                    if sandbox_id != "local":
+                        _make_file_sandbox_writable(md_path)
+                        sandbox.update_file(md_virtual_path, md_path.read_bytes())
 
                     file_info["markdown_file"] = md_path.name
                     file_info["markdown_path"] = str(sandbox_uploads / md_path.name)
@@ -243,19 +124,10 @@ async def upload_files(
 
             uploaded_files.append(file_info)
 
-        except HTTPException as e:
-            _cleanup_uploaded_paths(written_paths)
-            raise e
         except Exception as e:
             logger.error(f"Failed to upload {file.filename}: {e}")
-            _cleanup_uploaded_paths(written_paths)
             raise HTTPException(status_code=500, detail=f"Failed to upload {file.filename}: {str(e)}")
 
-    if sync_to_sandbox:
-        for file_path, virtual_path in sandbox_sync_targets:
-            _make_file_sandbox_writable(file_path)
-            sandbox.update_file(virtual_path, file_path.read_bytes())
-
     return UploadResponse(
         success=True,
         files=uploaded_files,
@@ -263,17 +135,6 @@ async def upload_files(
     )
 
 
-@router.get("/limits", response_model=UploadLimits)
-@require_permission("threads", "read", owner_check=True)
-async def get_upload_limits(
-    thread_id: str,
-    request: Request,
-    config: AppConfig = Depends(get_config),
-) -> UploadLimits:
-    """Return upload limits used by the gateway for this thread."""
-    return _get_upload_limits(config)
-
-
 @router.get("/list", response_model=dict)
 @require_permission("threads", "read", owner_check=True)
 async def list_uploaded_files(thread_id: str, request: Request) -> dict:
@@ -286,7 +147,7 @@ async def list_uploaded_files(thread_id: str, request: Request) -> dict:
     enrich_file_listing(result, thread_id)
 
     # Gateway additionally includes the sandbox-relative path.
-    sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id, user_id=get_effective_user_id())
+    sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id)
     for f in result["files"]:
         f["path"] = str(sandbox_uploads / f["filename"])
 

backend/app/gateway/services.py

@@ -8,16 +8,16 @@ frames, and consuming stream bridge events.  Router modules
 from __future__ import annotations
 
 import asyncio
+import dataclasses
 import json
 import logging
 import re
-from collections.abc import Mapping
 from typing import Any
 
 from fastapi import HTTPException, Request
 from langchain_core.messages import HumanMessage
 
-from app.gateway.deps import get_run_context, get_run_manager, get_stream_bridge
+from app.gateway.deps import get_run_context, get_run_manager, get_run_store, get_stream_bridge
 from app.gateway.utils import sanitize_log_param
 from deerflow.runtime import (
     END_SENTINEL,
@@ -98,52 +98,13 @@ def normalize_input(raw_input: dict[str, Any] | None) -> dict[str, Any]:
 _DEFAULT_ASSISTANT_ID = "lead_agent"
 
 
-# Whitelist of run-context keys that the langgraph-compat layer forwards from
-# ``body.context`` into the run config. ``config["context"]`` exists in
-# LangGraph >=0.6, but these values must be written to both ``configurable``
-# (for legacy ``_get_runtime_config`` consumers) and ``context`` because
-# LangGraph >=1.1.9 no longer makes ``ToolRuntime.context`` fall back to
-# ``configurable`` for consumers like ``setup_agent``.
-_CONTEXT_CONFIGURABLE_KEYS: frozenset[str] = frozenset(
-    {
-        "model_name",
-        "mode",
-        "thinking_enabled",
-        "reasoning_effort",
-        "is_plan_mode",
-        "subagent_enabled",
-        "max_concurrent_subagents",
-        "agent_name",
-        "is_bootstrap",
-    }
-)
-
-
-def merge_run_context_overrides(config: dict[str, Any], context: Mapping[str, Any] | None) -> None:
-    """Merge whitelisted keys from ``body.context`` into both ``config['configurable']``
-    and ``config['context']`` so they are visible to legacy configurable readers and
-    to LangGraph ``ToolRuntime.context`` consumers (e.g. the ``setup_agent`` tool —
-    see issue #2677)."""
-    if not context:
-        return
-    configurable = config.setdefault("configurable", {})
-    runtime_context = config.setdefault("context", {})
-    for key in _CONTEXT_CONFIGURABLE_KEYS:
-        if key in context:
-            if isinstance(configurable, dict):
-                configurable.setdefault(key, context[key])
-            if isinstance(runtime_context, dict):
-                runtime_context.setdefault(key, context[key])
-
-
 def resolve_agent_factory(assistant_id: str | None):
     """Resolve the agent factory callable from config.
 
     Custom agents are implemented as ``lead_agent`` + an ``agent_name``
-    injected into ``configurable`` or ``context`` — see
-    :func:`build_run_config`.  All ``assistant_id`` values therefore map to the
-    same factory; the routing happens inside ``make_lead_agent`` when it reads
-    ``cfg["agent_name"]``.
+    injected into ``configurable`` — see :func:`build_run_config`.  All
+    ``assistant_id`` values therefore map to the same factory; the routing
+    happens inside ``make_lead_agent`` when it reads ``cfg["agent_name"]``.
     """
     from deerflow.agents.lead_agent.agent import make_lead_agent
 
@@ -160,12 +121,10 @@ def build_run_config(
     """Build a RunnableConfig dict for the agent.
 
     When *assistant_id* refers to a custom agent (anything other than
-    ``"lead_agent"`` / ``None``), the name is forwarded as ``agent_name`` in
-    whichever runtime options container is active: ``context`` for
-    LangGraph >= 0.6.0 requests, otherwise ``configurable``.
-    ``make_lead_agent`` reads this key to load the matching
-    ``agents/<name>/SOUL.md`` and per-agent config — without it the agent
-    silently runs as the default lead agent.
+    ``"lead_agent"`` / ``None``), the name is forwarded as
+    ``configurable["agent_name"]``.  ``make_lead_agent`` reads this key to
+    load the matching ``agents/<name>/SOUL.md`` and per-agent config —
+    without it the agent silently runs as the default lead agent.
 
     This mirrors the channel manager's ``_resolve_run_params`` logic so that
     the LangGraph Platform-compatible HTTP API and the IM channel path behave
@@ -184,14 +143,7 @@ def build_run_config(
                     thread_id,
                     list(request_config.get("configurable", {}).keys()),
                 )
-            context_value = request_config["context"]
-            if context_value is None:
-                context = {}
-            elif isinstance(context_value, Mapping):
-                context = dict(context_value)
-            else:
-                raise ValueError("request config 'context' must be a mapping or null.")
-            config["context"] = context
+            config["context"] = request_config["context"]
         else:
             configurable = {"thread_id": thread_id}
             configurable.update(request_config.get("configurable", {}))
@@ -203,19 +155,13 @@ def build_run_config(
         config["configurable"] = {"thread_id": thread_id}
 
     # Inject custom agent name when the caller specified a non-default assistant.
-    # Honour an explicit agent_name in the active runtime options container.
-    if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID:
-        normalized = assistant_id.strip().lower().replace("_", "-")
-        if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
-            raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
-        if "configurable" in config:
-            target = config["configurable"]
-        elif "context" in config:
-            target = config["context"]
-        else:
-            target = config.setdefault("configurable", {})
-        if target is not None and "agent_name" not in target:
-            target["agent_name"] = normalized
+    # Honour an explicit configurable["agent_name"] in the request if already set.
+    if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID and "configurable" in config:
+        if "agent_name" not in config["configurable"]:
+            normalized = assistant_id.strip().lower().replace("_", "-")
+            if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
+                raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
+            config["configurable"]["agent_name"] = normalized
     if metadata:
         config.setdefault("metadata", {}).update(metadata)
     return config
@@ -249,6 +195,21 @@ async def start_run(
 
     disconnect = DisconnectMode.cancel if body.on_disconnect == "cancel" else DisconnectMode.continue_
 
+    # Resolve follow_up_to_run_id: explicit from request, or auto-detect from latest successful run
+    follow_up_to_run_id = getattr(body, "follow_up_to_run_id", None)
+    if follow_up_to_run_id is None:
+        run_store = get_run_store(request)
+        try:
+            recent_runs = await run_store.list_by_thread(thread_id, limit=1)
+            if recent_runs and recent_runs[0].get("status") == "success":
+                follow_up_to_run_id = recent_runs[0]["run_id"]
+        except Exception:
+            pass  # Don't block run creation
+
+    # Enrich base context with per-run field
+    if follow_up_to_run_id:
+        run_ctx = dataclasses.replace(run_ctx, follow_up_to_run_id=follow_up_to_run_id)
+
     try:
         record = await run_mgr.create_or_reject(
             thread_id,
@@ -257,6 +218,7 @@ async def start_run(
             metadata=body.metadata or {},
             kwargs={"input": body.input, "config": body.config},
             multitask_strategy=body.multitask_strategy,
+            follow_up_to_run_id=follow_up_to_run_id,
         )
     except ConflictError as exc:
         raise HTTPException(status_code=409, detail=str(exc)) from exc
@@ -267,15 +229,15 @@ async def start_run(
     # even for threads that were never explicitly created via POST /threads
     # (e.g. stateless runs).
     try:
-        existing = await run_ctx.thread_store.get(thread_id)
+        existing = await run_ctx.thread_meta_repo.get(thread_id)
         if existing is None:
-            await run_ctx.thread_store.create(
+            await run_ctx.thread_meta_repo.create(
                 thread_id,
                 assistant_id=body.assistant_id,
                 metadata=body.metadata,
             )
         else:
-            await run_ctx.thread_store.update_status(thread_id, "running")
+            await run_ctx.thread_meta_repo.update_status(thread_id, "running")
     except Exception:
         logger.warning("Failed to upsert thread_meta for %s (non-fatal)", sanitize_log_param(thread_id))
 
@@ -283,11 +245,25 @@ async def start_run(
     graph_input = normalize_input(body.input)
     config = build_run_config(thread_id, body.config, body.metadata, assistant_id=body.assistant_id)
 
-    # Merge DeerFlow-specific context overrides into both ``configurable`` and ``context``.
+    # Merge DeerFlow-specific context overrides into configurable.
     # The ``context`` field is a custom extension for the langgraph-compat layer
     # that carries agent configuration (model_name, thinking_enabled, etc.).
     # Only agent-relevant keys are forwarded; unknown keys (e.g. thread_id) are ignored.
-    merge_run_context_overrides(config, getattr(body, "context", None))
+    context = getattr(body, "context", None)
+    if context:
+        _CONTEXT_CONFIGURABLE_KEYS = {
+            "model_name",
+            "mode",
+            "thinking_enabled",
+            "reasoning_effort",
+            "is_plan_mode",
+            "subagent_enabled",
+            "max_concurrent_subagents",
+        }
+        configurable = config.setdefault("configurable", {})
+        for key in _CONTEXT_CONFIGURABLE_KEYS:
+            if key in context:
+                configurable.setdefault(key, context[key])
 
     stream_modes = normalize_stream_modes(body.stream_mode)
 
@@ -309,7 +285,7 @@ async def start_run(
     record.task = task
 
     # Title sync is handled by worker.py's finally block which reads the
-    # title from the checkpoint and calls thread_store.update_display_name
+    # title from the checkpoint and calls thread_meta_repo.update_display_name
     # after the run completes.
 
     return record

backend/debug.py

@@ -19,70 +19,24 @@ import asyncio
 import logging
 
 from dotenv import load_dotenv
+from langchain_core.messages import HumanMessage
 
-try:
-    from prompt_toolkit import PromptSession
-    from prompt_toolkit.history import InMemoryHistory
-
-    _HAS_PROMPT_TOOLKIT = True
-except ImportError:
-    _HAS_PROMPT_TOOLKIT = False
+from deerflow.agents import make_lead_agent
 
 load_dotenv()
 
-_LOG_FMT = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-_LOG_DATEFMT = "%Y-%m-%d %H:%M:%S"
-
-
-def _setup_logging(log_level: int = logging.INFO) -> None:
-    """Route logs to ``debug.log`` using *log_level* for the initial root/file setup.
-
-    This configures the root logger and the ``debug.log`` file handler so logs do
-    not print on the interactive console. It is idempotent: any pre-existing
-    handlers on the root logger (e.g. installed by ``logging.basicConfig`` in
-    transitively imported modules) are removed so the debug session output only
-    lands in ``debug.log``.
-
-    Note: later config-driven logging adjustments may change named logger
-    verbosity without raising the root logger or file-handler thresholds set
-    here, so the eventual contents of ``debug.log`` may not be filtered solely by
-    this function's ``log_level`` argument.
-    """
-    root = logging.root
-    for h in list(root.handlers):
-        root.removeHandler(h)
-        h.close()
-    root.setLevel(log_level)
-
-    file_handler = logging.FileHandler("debug.log", mode="a", encoding="utf-8")
-    file_handler.setLevel(log_level)
-    file_handler.setFormatter(logging.Formatter(_LOG_FMT, datefmt=_LOG_DATEFMT))
-    root.addHandler(file_handler)
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    datefmt="%Y-%m-%d %H:%M:%S",
+)
 
 
 async def main():
-    # Install file logging first so warnings emitted while loading config do not
-    # leak onto the interactive terminal via Python's lastResort handler.
-    _setup_logging()
-
-    from deerflow.config import get_app_config
-    from deerflow.config.app_config import apply_logging_level
-
-    app_config = get_app_config()
-    apply_logging_level(app_config.log_level)
-
-    # Delay the rest of the deerflow imports until *after* logging is installed
-    # so that any import-time side effects (e.g. deerflow.agents starts a
-    # background skill-loader thread on import) emit logs to debug.log instead
-    # of leaking onto the interactive terminal via Python's lastResort handler.
-    from langchain_core.messages import HumanMessage
-    from langgraph.runtime import Runtime
-
-    from deerflow.agents import make_lead_agent
-    from deerflow.mcp import initialize_mcp_tools
-
     # Initialize MCP tools at startup
     try:
+        from deerflow.mcp import initialize_mcp_tools
+
         await initialize_mcp_tools()
     except Exception as e:
         print(f"Warning: Failed to initialize MCP tools: {e}")
@@ -98,27 +52,16 @@ async def main():
         }
     }
 
-    runtime = Runtime(context={"thread_id": config["configurable"]["thread_id"]})
-    config["configurable"]["__pregel_runtime"] = runtime
-
     agent = make_lead_agent(config)
 
-    session = PromptSession(history=InMemoryHistory()) if _HAS_PROMPT_TOOLKIT else None
-
     print("=" * 50)
     print("Lead Agent Debug Mode")
     print("Type 'quit' or 'exit' to stop")
-    print(f"Logs: debug.log (log_level={app_config.log_level})")
-    if not _HAS_PROMPT_TOOLKIT:
-        print("Tip: `uv sync --group dev` to enable arrow-key & history support")
     print("=" * 50)
 
     while True:
         try:
-            if session:
-                user_input = (await session.prompt_async("\nYou: ")).strip()
-            else:
-                user_input = input("\nYou: ").strip()
+            user_input = input("\nYou: ").strip()
             if not user_input:
                 continue
             if user_input.lower() in ("quit", "exit"):
@@ -127,15 +70,15 @@ async def main():
 
             # Invoke the agent
             state = {"messages": [HumanMessage(content=user_input)]}
-            result = await agent.ainvoke(state, config=config)
+            result = await agent.ainvoke(state, config=config, context={"thread_id": "debug-thread-001"})
 
             # Print the response
             if result.get("messages"):
                 last_message = result["messages"][-1]
                 print(f"\nAgent: {last_message.content}")
 
-        except (KeyboardInterrupt, EOFError):
-            print("\nGoodbye!")
+        except KeyboardInterrupt:
+            print("\nInterrupted. Goodbye!")
             break
         except Exception as e:
             print(f"\nError: {e}")

backend/docs/ARCHITECTURE.md

@@ -199,7 +199,7 @@ class ThreadState(AgentState):
 │   Built-in Tools    │  │  Configured Tools   │  │     MCP Tools       │
 │  (packages/harness/deerflow/tools/)       │  │  (config.yaml)      │  │  (extensions.json)  │
 ├─────────────────────┤  ├─────────────────────┤  ├─────────────────────┤
-│ - present_files     │  │ - web_search        │  │ - github            │
+│ - present_file      │  │ - web_search        │  │ - github            │
 │ - ask_clarification │  │ - web_fetch         │  │ - filesystem        │
 │ - view_image        │  │ - bash              │  │ - postgres          │
 │                     │  │ - read_file         │  │ - brave-search      │

backend/docs/CONFIGURATION.md

@@ -259,8 +259,6 @@ sandbox:
 
 When you configure `sandbox.mounts`, DeerFlow exposes those `container_path` values in the agent prompt so the agent can discover and operate on mounted directories directly instead of assuming everything must live under `/mnt/user-data`.
 
-For bare-metal Docker sandbox runs that use localhost, DeerFlow binds the sandbox HTTP port to `127.0.0.1` by default so it is not exposed on every host interface. Docker-outside-of-Docker deployments that connect through `host.docker.internal` keep the broad legacy bind for compatibility. Set `DEER_FLOW_SANDBOX_BIND_HOST` explicitly if your deployment needs a different bind address.
-
 ### Skills
 
 Configure the skills directory for specialized workflows:
@@ -321,16 +319,11 @@ models:
 - `DEEPSEEK_API_KEY` - DeepSeek API key
 - `NOVITA_API_KEY` - Novita API key (OpenAI-compatible endpoint)
 - `TAVILY_API_KEY` - Tavily search API key
-- `DEER_FLOW_PROJECT_ROOT` - Project root for relative runtime paths
 - `DEER_FLOW_CONFIG_PATH` - Custom config file path
-- `DEER_FLOW_EXTENSIONS_CONFIG_PATH` - Custom extensions config file path
-- `DEER_FLOW_HOME` - Runtime state directory (defaults to `.deer-flow` under the project root)
-- `DEER_FLOW_SKILLS_PATH` - Skills directory when `skills.path` is omitted
-- `GATEWAY_ENABLE_DOCS` - Set to `false` to disable Swagger UI (`/docs`), ReDoc (`/redoc`), and OpenAPI schema (`/openapi.json`) endpoints (default: `true`)
 
 ## Configuration Location
 
-The configuration file should be placed in the **project root directory** (`deer-flow/config.yaml`). Set `DEER_FLOW_PROJECT_ROOT` when the process may start from another working directory, or set `DEER_FLOW_CONFIG_PATH` to point at a specific file.
+The configuration file should be placed in the **project root directory** (`deer-flow/config.yaml`), not in the backend directory.
 
 ## Configuration Priority
 
@@ -338,12 +331,12 @@ DeerFlow searches for configuration in this order:
 
 1. Path specified in code via `config_path` argument
 2. Path from `DEER_FLOW_CONFIG_PATH` environment variable
-3. `config.yaml` under `DEER_FLOW_PROJECT_ROOT`, or under the current working directory when `DEER_FLOW_PROJECT_ROOT` is unset
-4. Legacy backend/repository-root locations for monorepo compatibility
+3. `config.yaml` in current working directory (typically `backend/` when running)
+4. `config.yaml` in parent directory (project root: `deer-flow/`)
 
 ## Best Practices
 
-1. **Place `config.yaml` in project root** - Set `DEER_FLOW_PROJECT_ROOT` if the runtime starts elsewhere
+1. **Place `config.yaml` in project root** - Not in `backend/` directory
 2. **Never commit `config.yaml`** - It's already in `.gitignore`
 3. **Use environment variables for secrets** - Don't hardcode API keys
 4. **Keep `config.example.yaml` updated** - Document all new options
@@ -354,7 +347,7 @@ DeerFlow searches for configuration in this order:
 
 ### "Config file not found"
 - Ensure `config.yaml` exists in the **project root** directory (`deer-flow/config.yaml`)
-- If the runtime starts outside the project root, set `DEER_FLOW_PROJECT_ROOT`
+- The backend searches parent directory by default, so root location is preferred
 - Alternatively, set `DEER_FLOW_CONFIG_PATH` environment variable to custom location
 
 ### "Invalid API key"
@@ -364,7 +357,7 @@ DeerFlow searches for configuration in this order:
 ### "Skills not loading"
 - Check that `deer-flow/skills/` directory exists
 - Verify skills have valid `SKILL.md` files
-- Check `skills.path` or `DEER_FLOW_SKILLS_PATH` if using a custom path
+- Check `skills.path` configuration if using custom path
 
 ### "Docker sandbox fails to start"
 - Ensure Docker is running

backend/docs/FILE_UPLOAD.md

@@ -2,12 +2,12 @@
 
 ## 概述
 
-DeerFlow 后端提供了完整的文件上传功能，支持多文件上传，并可选地将 Office 文档和 PDF 转换为 Markdown 格式。
+DeerFlow 后端提供了完整的文件上传功能，支持多文件上传，并自动将 Office 文档和 PDF 转换为 Markdown 格式。
 
 ## 功能特性
 
 - ✅ 支持多文件同时上传
-- ✅ 可选地转换文档为 Markdown（PDF、PPT、Excel、Word）
+- ✅ 自动转换文档为 Markdown（PDF、PPT、Excel、Word）
 - ✅ 文件存储在线程隔离的目录中
 - ✅ Agent 自动感知已上传的文件
 - ✅ 支持文件列表查询和删除
@@ -22,8 +22,6 @@ POST /api/threads/{thread_id}/uploads
 **请求体：** `multipart/form-data`
 - `files`: 一个或多个文件
 
-网关会在应用层限制上传规模，默认最多 10 个文件、单文件 50 MiB、单次请求总计 100 MiB。可通过 `config.yaml` 的 `uploads.max_files`、`uploads.max_file_size`、`uploads.max_total_size` 调整；前端会读取同一组限制并在选择文件时提示，超过限制时后端返回 `413 Payload Too Large`。
-
 **响应：**
 ```json
 {
@@ -50,23 +48,7 @@ POST /api/threads/{thread_id}/uploads
 - `virtual_path`: Agent 在沙箱中使用的虚拟路径
 - `artifact_url`: 前端通过 HTTP 访问文件的 URL
 
-### 2. 查询上传限制
-```
-GET /api/threads/{thread_id}/uploads/limits
-```
-
-返回网关当前生效的上传限制，供前端在用户选择文件前提示和拦截。
-
-**响应：**
-```json
-{
-  "max_files": 10,
-  "max_file_size": 52428800,
-  "max_total_size": 104857600
-}
-```
-
-### 3. 列出已上传文件
+### 2. 列出已上传文件
 ```
 GET /api/threads/{thread_id}/uploads/list
 ```
@@ -89,7 +71,7 @@ GET /api/threads/{thread_id}/uploads/list
 }
 ```
 
-### 4. 删除文件
+### 3. 删除文件
 ```
 DELETE /api/threads/{thread_id}/uploads/{filename}
 ```
@@ -104,7 +86,7 @@ DELETE /api/threads/{thread_id}/uploads/{filename}
 
 ## 支持的文档格式
 
-以下格式在显式启用 `uploads.auto_convert_documents: true` 时会自动转换为 Markdown：
+以下格式会自动转换为 Markdown：
 - PDF (`.pdf`)
 - PowerPoint (`.ppt`, `.pptx`)
 - Excel (`.xls`, `.xlsx`)
@@ -112,8 +94,6 @@ DELETE /api/threads/{thread_id}/uploads/{filename}
 
 转换后的 Markdown 文件会保存在同一目录下，文件名为原文件名 + `.md` 扩展名。
 
-默认情况下，自动转换是关闭的，以避免在网关主机上对不受信任的 Office/PDF 上传执行解析。只有在受信任部署中明确接受此风险时，才应将 `uploads.auto_convert_documents` 设置为 `true`。
-
 ## Agent 集成
 
 ### 自动文件列举
@@ -227,7 +207,6 @@ backend/.deer-flow/threads/
 - 最大文件大小：100MB（可在 nginx.conf 中配置 `client_max_body_size`）
 - 文件名安全性：系统会自动验证文件路径，防止目录遍历攻击
 - 线程隔离：每个线程的上传文件相互隔离，无法跨线程访问
-- 自动文档转换默认关闭；如需启用，需在 `config.yaml` 中显式设置 `uploads.auto_convert_documents: true`
 
 ## 技术实现
 

backend/docs/GUARDRAILS.md

@@ -296,7 +296,7 @@ These are the tool names your provider will see in `request.tool_name`:
 | `web_search` | Web search query |
 | `web_fetch` | Fetch URL content |
 | `image_search` | Image search |
-| `present_files` | Present file to user |
+| `present_file` | Present file to user |
 | `view_image` | Display image |
 | `ask_clarification` | Ask user a question |
 | `task` | Delegate to subagent |

backend/docs/HARNESS_APP_SPLIT.md

@@ -0,0 +1,343 @@
+# DeerFlow 后端拆分设计文档：Harness + App
+
+> 状态：Draft
+> 作者：DeerFlow Team
+> 日期：2026-03-13
+
+## 1. 背景与动机
+
+DeerFlow 后端当前是一个单一 Python 包（`src.*`），包含了从底层 agent 编排到上层用户产品的所有代码。随着项目发展，这种结构带来了几个问题：
+
+- **复用困难**：其他产品（CLI 工具、Slack bot、第三方集成）想用 agent 能力，必须依赖整个后端，包括 FastAPI、IM SDK 等不需要的依赖
+- **职责模糊**：agent 编排逻辑和用户产品逻辑混在同一个 `src/` 下，边界不清晰
+- **依赖膨胀**：LangGraph Server 运行时不需要 FastAPI/uvicorn/Slack SDK，但当前必须安装全部依赖
+
+本文档提出将后端拆分为两部分：**deerflow-harness**（可发布的 agent 框架包）和 **app**（不打包的用户产品代码）。
+
+## 2. 核心概念
+
+### 2.1 Harness（线束/框架层）
+
+Harness 是 agent 的构建与编排框架，回答 **"如何构建和运行 agent"** 的问题：
+
+- Agent 工厂与生命周期管理
+- Middleware pipeline
+- 工具系统（内置工具 + MCP + 社区工具）
+- 沙箱执行环境
+- 子 agent 委派
+- 记忆系统
+- 技能加载与注入
+- 模型工厂
+- 配置系统
+
+**Harness 是一个可发布的 Python 包**（`deerflow-harness`），可以独立安装和使用。
+
+**Harness 的设计原则**：对上层应用完全无感知。它不知道也不关心谁在调用它——可以是 Web App、CLI、Slack Bot、或者一个单元测试。
+
+### 2.2 App（应用层）
+
+App 是面向用户的产品代码，回答 **"如何将 agent 呈现给用户"** 的问题：
+
+- Gateway API（FastAPI REST 接口）
+- IM Channels（飞书、Slack、Telegram 集成）
+- Custom Agent 的 CRUD 管理
+- 文件上传/下载的 HTTP 接口
+
+**App 不打包、不发布**，它是 DeerFlow 项目内部的应用代码，直接运行。
+
+**App 依赖 Harness，但 Harness 不依赖 App。**
+
+### 2.3 边界划分
+
+| 模块 | 归属 | 说明 |
+|------|------|------|
+| `config/` | Harness | 配置系统是基础设施 |
+| `reflection/` | Harness | 动态模块加载工具 |
+| `utils/` | Harness | 通用工具函数 |
+| `agents/` | Harness | Agent 工厂、middleware、state、memory |
+| `subagents/` | Harness | 子 agent 委派系统 |
+| `sandbox/` | Harness | 沙箱执行环境 |
+| `tools/` | Harness | 工具注册与发现 |
+| `mcp/` | Harness | MCP 协议集成 |
+| `skills/` | Harness | 技能加载、解析、定义 schema |
+| `models/` | Harness | LLM 模型工厂 |
+| `community/` | Harness | 社区工具（tavily、jina 等） |
+| `client.py` | Harness | 嵌入式 Python 客户端 |
+| `gateway/` | App | FastAPI REST API |
+| `channels/` | App | IM 平台集成 |
+
+**关于 Custom Agents**：agent 定义格式（`config.yaml` + `SOUL.md` schema）由 Harness 层的 `config/agents_config.py` 定义，但文件的存储、CRUD、发现机制由 App 层的 `gateway/routers/agents.py` 负责。
+
+## 3. 目标架构
+
+### 3.1 目录结构
+
+```
+backend/
+├── packages/
+│   └── harness/
+│       ├── pyproject.toml          # deerflow-harness 包定义
+│       └── deerflow/               # Python 包根（import 前缀: deerflow.*）
+│           ├── __init__.py
+│           ├── config/
+│           ├── reflection/
+│           ├── utils/
+│           ├── agents/
+│           │   ├── lead_agent/
+│           │   ├── middlewares/
+│           │   ├── memory/
+│           │   ├── checkpointer/
+│           │   └── thread_state.py
+│           ├── subagents/
+│           ├── sandbox/
+│           ├── tools/
+│           ├── mcp/
+│           ├── skills/
+│           ├── models/
+│           ├── community/
+│           └── client.py
+├── app/                            # 不打包（import 前缀: app.*）
+│   ├── __init__.py
+│   ├── gateway/
+│   │   ├── __init__.py
+│   │   ├── app.py
+│   │   ├── config.py
+│   │   ├── path_utils.py
+│   │   └── routers/
+│   └── channels/
+│       ├── __init__.py
+│       ├── base.py
+│       ├── manager.py
+│       ├── service.py
+│       ├── store.py
+│       ├── message_bus.py
+│       ├── feishu.py
+│       ├── slack.py
+│       └── telegram.py
+├── pyproject.toml                  # uv workspace root
+├── langgraph.json
+├── tests/
+├── docs/
+└── Makefile
+```
+
+### 3.2 Import 规则
+
+两个层使用不同的 import 前缀，职责边界一目了然：
+
+```python
+# ---------------------------------------------------------------
+# Harness 内部互相引用（deerflow.* 前缀）
+# ---------------------------------------------------------------
+from deerflow.agents import make_lead_agent
+from deerflow.models import create_chat_model
+from deerflow.config import get_app_config
+from deerflow.tools import get_available_tools
+
+# ---------------------------------------------------------------
+# App 内部互相引用（app.* 前缀）
+# ---------------------------------------------------------------
+from app.gateway.app import app
+from app.gateway.routers.uploads import upload_files
+from app.channels.service import start_channel_service
+
+# ---------------------------------------------------------------
+# App 调用 Harness（单向依赖，Harness 永远不 import app）
+# ---------------------------------------------------------------
+from deerflow.agents import make_lead_agent
+from deerflow.models import create_chat_model
+from deerflow.skills import load_skills
+from deerflow.config.extensions_config import get_extensions_config
+```
+
+**App 调用 Harness 示例 — Gateway 中启动 agent**：
+
+```python
+# app/gateway/routers/chat.py
+from deerflow.agents.lead_agent.agent import make_lead_agent
+from deerflow.models import create_chat_model
+from deerflow.config import get_app_config
+
+async def create_chat_session(thread_id: str, model_name: str):
+    config = get_app_config()
+    model = create_chat_model(name=model_name)
+    agent = make_lead_agent(config=...)
+    # ... 使用 agent 处理用户消息
+```
+
+**App 调用 Harness 示例 — Channel 中查询 skills**：
+
+```python
+# app/channels/manager.py
+from deerflow.skills import load_skills
+from deerflow.agents.memory.updater import get_memory_data
+
+def handle_status_command():
+    skills = load_skills(enabled_only=True)
+    memory = get_memory_data()
+    return f"Skills: {len(skills)}, Memory facts: {len(memory.get('facts', []))}"
+```
+
+**禁止方向**：Harness 代码中绝不能出现 `from app.` 或 `import app.`。
+
+### 3.3 为什么 App 不打包
+
+| 方面 | 打包（放 packages/ 下） | 不打包（放 backend/app/） |
+|------|------------------------|--------------------------|
+| 命名空间 | 需要 pkgutil `extend_path` 合并，或独立前缀 | 天然独立，`app.*` vs `deerflow.*` |
+| 发布需求 | 没有——App 是项目内部代码 | 不需要 pyproject.toml |
+| 复杂度 | 需要管理两个包的构建、版本、依赖声明 | 直接运行，零额外配置 |
+| 运行方式 | `pip install deerflow-app` | `PYTHONPATH=. uvicorn app.gateway.app:app` |
+
+App 的唯一消费者是 DeerFlow 项目自身，没有独立发布的需求。放在 `backend/app/` 下作为普通 Python 包，通过 `PYTHONPATH` 或 editable install 让 Python 找到即可。
+
+### 3.4 依赖关系
+
+```
+┌─────────────────────────────────────┐
+│  app/  (不打包，直接运行)             │
+│  ├── fastapi, uvicorn               │
+│  ├── slack-sdk, lark-oapi, ...      │
+│  └── import deerflow.*              │
+└──────────────┬──────────────────────┘
+               │
+               ▼
+┌─────────────────────────────────────┐
+│  deerflow-harness  (可发布的包)       │
+│  ├── langgraph, langchain           │
+│  ├── markitdown, pydantic, ...      │
+│  └── 零 app 依赖                     │
+└─────────────────────────────────────┘
+```
+
+**依赖分类**：
+
+| 分类 | 依赖包 |
+|------|--------|
+| Harness only | agent-sandbox, langchain*, langgraph*, markdownify, markitdown, pydantic, pyyaml, readabilipy, tavily-python, firecrawl-py, tiktoken, ddgs, duckdb, httpx, kubernetes, dotenv |
+| App only | fastapi, uvicorn, sse-starlette, python-multipart, lark-oapi, slack-sdk, python-telegram-bot, markdown-to-mrkdwn |
+| Shared | langgraph-sdk（channels 用 HTTP client）, pydantic, httpx |
+
+### 3.5 Workspace 配置
+
+`backend/pyproject.toml`（workspace root）：
+
+```toml
+[project]
+name = "deer-flow"
+version = "0.1.0"
+requires-python = ">=3.12"
+dependencies = ["deerflow-harness"]
+
+[dependency-groups]
+dev = ["pytest>=8.0.0", "ruff>=0.14.11"]
+# App 的额外依赖（fastapi 等）也声明在 workspace root，因为 app 不打包
+app = ["fastapi", "uvicorn", "sse-starlette", "python-multipart"]
+channels = ["lark-oapi", "slack-sdk", "python-telegram-bot"]
+
+[tool.uv.workspace]
+members = ["packages/harness"]
+
+[tool.uv.sources]
+deerflow-harness = { workspace = true }
+```
+
+## 4. 当前的跨层依赖问题
+
+在拆分之前，需要先解决 `client.py` 中两处从 harness 到 app 的反向依赖：
+
+### 4.1 `_validate_skill_frontmatter`
+
+```python
+# client.py — harness 导入了 app 层代码
+from src.gateway.routers.skills import _validate_skill_frontmatter
+```
+
+**解决方案**：将该函数提取到 `deerflow/skills/validation.py`。这是一个纯逻辑函数（解析 YAML frontmatter、校验字段），与 FastAPI 无关。
+
+### 4.2 `CONVERTIBLE_EXTENSIONS` + `convert_file_to_markdown`
+
+```python
+# client.py — harness 导入了 app 层代码
+from src.gateway.routers.uploads import CONVERTIBLE_EXTENSIONS, convert_file_to_markdown
+```
+
+**解决方案**：将它们提取到 `deerflow/utils/file_conversion.py`。仅依赖 `markitdown` + `pathlib`，是通用工具函数。
+
+## 5. 基础设施变更
+
+### 5.1 LangGraph Server
+
+LangGraph Server 只需要 harness 包。`langgraph.json` 更新：
+
+```json
+{
+  "dependencies": ["./packages/harness"],
+  "graphs": {
+    "lead_agent": "deerflow.agents:make_lead_agent"
+  },
+  "checkpointer": {
+    "path": "./packages/harness/deerflow/agents/checkpointer/async_provider.py:make_checkpointer"
+  }
+}
+```
+
+### 5.2 Gateway API
+
+```bash
+# serve.sh / Makefile
+# PYTHONPATH 包含 backend/ 根目录，使 app.* 和 deerflow.* 都能被找到
+PYTHONPATH=. uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001
+```
+
+### 5.3 Nginx
+
+无需变更（只做 URL 路由，不涉及 Python 模块路径）。
+
+### 5.4 Docker
+
+Dockerfile 中的 module 引用从 `src.` 改为 `deerflow.` / `app.`，`COPY` 命令需覆盖 `packages/` 和 `app/` 目录。
+
+## 6. 实施计划
+
+分 3 个 PR 递进执行：
+
+### PR 1：提取共享工具函数（Low Risk）
+
+1. 创建 `src/skills/validation.py`，从 `gateway/routers/skills.py` 提取 `_validate_skill_frontmatter`
+2. 创建 `src/utils/file_conversion.py`，从 `gateway/routers/uploads.py` 提取文件转换逻辑
+3. 更新 `client.py`、`gateway/routers/skills.py`、`gateway/routers/uploads.py` 的 import
+4. 运行全部测试确认无回归
+
+### PR 2：Rename + 物理拆分（High Risk，原子操作）
+
+1. 创建 `packages/harness/` 目录，创建 `pyproject.toml`
+2. `git mv` 将 harness 相关模块从 `src/` 移入 `packages/harness/deerflow/`
+3. `git mv` 将 app 相关模块从 `src/` 移入 `app/`
+4. 全局替换 import：
+   - harness 模块：`src.*` → `deerflow.*`（所有 `.py` 文件、`langgraph.json`、测试、文档）
+   - app 模块：`src.gateway.*` → `app.gateway.*`、`src.channels.*` → `app.channels.*`
+5. 更新 workspace root `pyproject.toml`
+6. 更新 `langgraph.json`、`Makefile`、`Dockerfile`
+7. `uv sync` + 全部测试 + 手动验证服务启动
+
+### PR 3：边界检查 + 文档（Low Risk）
+
+1. 添加 lint 规则：检查 harness 不 import app 模块
+2. 更新 `CLAUDE.md`、`README.md`
+
+## 7. 风险与缓解
+
+| 风险 | 影响 | 缓解措施 |
+|------|------|----------|
+| 全局 rename 误伤 | 字符串中的 `src` 被错误替换 | 正则精确匹配 `\bsrc\.`，review diff |
+| LangGraph Server 找不到模块 | 服务启动失败 | `langgraph.json` 的 `dependencies` 指向正确的 harness 包路径 |
+| App 的 `PYTHONPATH` 缺失 | Gateway/Channel 启动 import 报错 | Makefile/Docker 统一设置 `PYTHONPATH=.` |
+| `config.yaml` 中的 `use` 字段引用旧路径 | 运行时模块解析失败 | `config.yaml` 中的 `use` 字段同步更新为 `deerflow.*` |
+| 测试中 `sys.path` 混乱 | 测试失败 | 用 editable install（`uv sync`）确保 deerflow 可导入，`conftest.py` 中添加 `app/` 到 `sys.path` |
+
+## 8. 未来演进
+
+- **独立发布**：harness 可以发布到内部 PyPI，让其他项目直接 `pip install deerflow-harness`
+- **插件化 App**：不同的 app（web、CLI、bot）可以各自独立，都依赖同一个 harness
+- **更细粒度拆分**：如果 harness 内部模块继续增长，可以进一步拆分（如 `deerflow-sandbox`、`deerflow-mcp`）

backend/docs/MCP_SERVER.md

@@ -45,41 +45,6 @@ Example:
 }
 ```
 
-## Custom Tool Interceptors
-
-You can register custom interceptors that run before every MCP tool call. This is useful for injecting per-request headers (e.g., user auth tokens from the LangGraph execution context), logging, or metrics.
-
-Declare interceptors in `extensions_config.json` using the `mcpInterceptors` field:
-
-```json
-{
-  "mcpInterceptors": [
-    "my_package.mcp.auth:build_auth_interceptor"
-  ],
-  "mcpServers": { ... }
-}
-```
-
-Each entry is a Python import path in `module:variable` format (resolved via `resolve_variable`). The variable must be a **no-arg builder function** that returns an async interceptor compatible with `MultiServerMCPClient`’s `tool_interceptors` interface, or `None` to skip.
-
-Example interceptor that injects auth headers from LangGraph metadata:
-
-```python
-def build_auth_interceptor():
-    async def interceptor(request, handler):
-        from langgraph.config import get_config
-        metadata = get_config().get("metadata", {})
-        headers = dict(request.headers or {})
-        if token := metadata.get("auth_token"):
-            headers["X-Auth-Token"] = token
-        return await handler(request.override(headers=headers))
-    return interceptor
-```
-
-- A single string value is accepted and normalized to a one-element list.
-- Invalid paths or builder failures are logged as warnings without blocking other interceptors.
-- The builder return value must be `callable`; non-callable values are skipped with a warning.
-
 ## How It Works
 
 MCP servers expose tools that are automatically discovered and integrated into DeerFlow’s agent system at runtime. Once enabled, these tools become available to agents without additional code changes.

backend/docs/SETUP.md

@@ -23,9 +23,6 @@ DeerFlow uses a YAML configuration file that should be placed in the **project r
    # Option A: Set environment variables (recommended)
    export OPENAI_API_KEY="your-key-here"
 
-   # Optional: pin the project root when running from another directory
-   export DEER_FLOW_PROJECT_ROOT="/path/to/deer-flow"
-
    # Option B: Edit config.yaml directly
    vim config.yaml  # or your preferred editor
    ```
@@ -38,20 +35,17 @@ DeerFlow uses a YAML configuration file that should be placed in the **project r
 
 ## Important Notes
 
-- **Location**: `config.yaml` should be in `deer-flow/` (project root)
+- **Location**: `config.yaml` should be in `deer-flow/` (project root), not `deer-flow/backend/`
 - **Git**: `config.yaml` is automatically ignored by git (contains secrets)
-- **Runtime root**: Set `DEER_FLOW_PROJECT_ROOT` if DeerFlow may start from outside the project root
-- **Runtime data**: State defaults to `.deer-flow` under the project root; set `DEER_FLOW_HOME` to move it
-- **Skills**: Skills default to `skills/` under the project root; set `DEER_FLOW_SKILLS_PATH` or `skills.path` to move them
+- **Priority**: If both `backend/config.yaml` and `../config.yaml` exist, backend version takes precedence
 
 ## Configuration File Locations
 
 The backend searches for `config.yaml` in this order:
 
-1. Explicit `config_path` argument from code
-2. `DEER_FLOW_CONFIG_PATH` environment variable (if set)
-3. `config.yaml` under `DEER_FLOW_PROJECT_ROOT`, or the current working directory when `DEER_FLOW_PROJECT_ROOT` is unset
-4. Legacy backend/repository-root locations for monorepo compatibility
+1. `DEER_FLOW_CONFIG_PATH` environment variable (if set)
+2. `backend/config.yaml` (current directory when running from backend/)
+3. `deer-flow/config.yaml` (parent directory - **recommended location**)
 
 **Recommended**: Place `config.yaml` in project root (`deer-flow/config.yaml`).
 
@@ -83,8 +77,8 @@ python -c "from deerflow.config.app_config import AppConfig; print(AppConfig.res
 
 If it can't find the config:
 1. Ensure you've copied `config.example.yaml` to `config.yaml`
-2. Verify you're in the project root, or set `DEER_FLOW_PROJECT_ROOT`
-3. Check the file exists: `ls -la config.yaml`
+2. Verify you're in the correct directory
+3. Check the file exists: `ls -la ../config.yaml`
 
 ### Permission denied
 
@@ -95,4 +89,4 @@ chmod 600 ../config.yaml  # Protect sensitive configuration
 ## See Also
 
 - [Configuration Guide](CONFIGURATION.md) - Detailed configuration options
-- [Architecture Overview](../CLAUDE.md) - System architecture
+- [Architecture Overview](../CLAUDE.md) - System architecture

backend/docs/TITLE_GENERATION_IMPLEMENTATION.md

@@ -124,7 +124,7 @@ title:
 # checkpointer.py
 from langgraph.checkpoint.sqlite import SqliteSaver
 
-checkpointer = SqliteSaver.from_conn_string("deerflow.db")
+checkpointer = SqliteSaver.from_conn_string("checkpoints.db")
 ```
 
 ```json

backend/docs/TODO.md

@@ -11,7 +11,6 @@
 - [x] Add Plan Mode with TodoList middleware
 - [x] Add vision model support with ViewImageMiddleware
 - [x] Skills system with SKILL.md format
-- [x] Replace `time.sleep(5)` with `asyncio.sleep()` in `packages/harness/deerflow/tools/builtins/task_tool.py` (subagent polling)
 
 ## Planned Features
 
@@ -22,9 +21,10 @@
 - [ ] Support for more document formats in upload
 - [ ] Skill marketplace / remote skill installation
 - [ ] Optimize async concurrency in agent hot path (IM channels multi-task scenario)
-- [ ] Replace `subprocess.run()` with `asyncio.create_subprocess_shell()` in `packages/harness/deerflow/sandbox/local/local_sandbox.py`
+  - Replace `time.sleep(5)` with `asyncio.sleep()` in `packages/harness/deerflow/tools/builtins/task_tool.py` (subagent polling)
+  - Replace `subprocess.run()` with `asyncio.create_subprocess_shell()` in `packages/harness/deerflow/sandbox/local/local_sandbox.py`
   - Replace sync `requests` with `httpx.AsyncClient` in community tools (tavily, jina_ai, firecrawl, infoquest, image_search)
-  - [x] Replace sync `model.invoke()` with async `model.ainvoke()` in title_middleware and memory updater
+  - Replace sync `model.invoke()` with async `model.ainvoke()` in title_middleware and memory updater
   - Consider `asyncio.to_thread()` wrapper for remaining blocking file I/O
   - For production: use `langgraph up` (multi-worker) instead of `langgraph dev` (single-worker)
 

backend/docs/summarization.md

@@ -41,13 +41,6 @@ summarization:
 
   # Custom summary prompt (optional)
   summary_prompt: null
-
-  # Tool names treated as skill file reads for skill rescue
-  skill_file_read_tool_names:
-    - read_file
-    - read
-    - view
-    - cat
 ```
 
 ### Configuration Options
@@ -132,26 +125,6 @@ keep:
 - **Default**: `null` (uses LangChain's default prompt)
 - **Description**: Custom prompt template for generating summaries. The prompt should guide the model to extract the most important context.
 
-#### `preserve_recent_skill_count`
-- **Type**: Integer (≥ 0)
-- **Default**: `5`
-- **Description**: Number of most-recently-loaded skill files (tool results whose tool name is in `skill_file_read_tool_names` and whose target path is under `skills.container_path`, e.g. `/mnt/skills/...`) that are rescued from summarization. Prevents the agent from losing skill instructions after compression. Set to `0` to disable skill rescue entirely.
-
-#### `preserve_recent_skill_tokens`
-- **Type**: Integer (≥ 0)
-- **Default**: `25000`
-- **Description**: Total token budget reserved for rescued skill reads. Once this budget is exhausted, older skill bundles are allowed to be summarized.
-
-#### `preserve_recent_skill_tokens_per_skill`
-- **Type**: Integer (≥ 0)
-- **Default**: `5000`
-- **Description**: Per-skill token cap. Any individual skill read whose tool result exceeds this size is not rescued (it falls through to the summarizer like ordinary content).
-
-#### `skill_file_read_tool_names`
-- **Type**: List of strings
-- **Default**: `["read_file", "read", "view", "cat"]`
-- **Description**: Tool names treated as skill file reads during summarization rescue. A tool call is only eligible for skill rescue when its name appears in this list and its target path is under `skills.container_path`.
-
 **Default Prompt Behavior:**
 The default LangChain prompt instructs the model to:
 - Extract highest quality/most relevant context
@@ -174,7 +147,6 @@ The default LangChain prompt instructs the model to:
    - A single summary message is added
    - Recent messages are preserved
 6. **AI/Tool Pair Protection**: The system ensures AI messages and their corresponding tool messages stay together
-7. **Skill Rescue**: Before the summary is generated, the most recently loaded skill files (tool results whose tool name is in `skill_file_read_tool_names` and whose target path is under `skills.container_path`) are lifted out of the summarization set and prepended to the preserved tail. Selection walks newest-first under three budgets: `preserve_recent_skill_count`, `preserve_recent_skill_tokens`, and `preserve_recent_skill_tokens_per_skill`. The triggering AIMessage and all of its paired ToolMessages move together so tool_call ↔ tool_result pairing stays intact.
 
 ### Token Counting
 

backend/langgraph.json

@@ -12,6 +12,6 @@
     "path": "./app/gateway/langgraph_auth.py:auth"
   },
   "checkpointer": {
-    "path": "./packages/harness/deerflow/runtime/checkpointer/async_provider.py:make_checkpointer"
+    "path": "./packages/harness/deerflow/agents/checkpointer/async_provider.py:make_checkpointer"
   }
 }

backend/packages/harness/deerflow/agents/__init__.py

@@ -1,3 +1,4 @@
+from .checkpointer import get_checkpointer, make_checkpointer, reset_checkpointer
 from .factory import create_deerflow_agent
 from .features import Next, Prev, RuntimeFeatures
 from .lead_agent import make_lead_agent
@@ -17,4 +18,7 @@ __all__ = [
     "make_lead_agent",
     "SandboxState",
     "ThreadState",
+    "get_checkpointer",
+    "reset_checkpointer",
+    "make_checkpointer",
 ]

backend/packages/harness/deerflow/agents/checkpointer/async_provider.py

@@ -7,12 +7,12 @@ Supported backends: memory, sqlite, postgres.
 
 Usage (e.g. FastAPI lifespan)::
 
-    from deerflow.runtime.checkpointer.async_provider import make_checkpointer
+    from deerflow.agents.checkpointer.async_provider import make_checkpointer
 
     async with make_checkpointer() as checkpointer:
         app.state.checkpointer = checkpointer  # InMemorySaver if not configured
 
-For sync usage see :mod:`deerflow.runtime.checkpointer.provider`.
+For sync usage see :mod:`deerflow.agents.checkpointer.provider`.
 """
 
 from __future__ import annotations
@@ -24,12 +24,12 @@ from collections.abc import AsyncIterator
 
 from langgraph.types import Checkpointer
 
-from deerflow.config.app_config import AppConfig, get_app_config
-from deerflow.runtime.checkpointer.provider import (
+from deerflow.agents.checkpointer.provider import (
     POSTGRES_CONN_REQUIRED,
     POSTGRES_INSTALL,
     SQLITE_INSTALL,
 )
+from deerflow.config.app_config import get_app_config
 from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
 
 logger = logging.getLogger(__name__)
@@ -123,11 +123,11 @@ async def _async_checkpointer_from_database(db_config) -> AsyncIterator[Checkpoi
 
 
 @contextlib.asynccontextmanager
-async def make_checkpointer(app_config: AppConfig | None = None) -> AsyncIterator[Checkpointer]:
+async def make_checkpointer() -> AsyncIterator[Checkpointer]:
     """Async context manager that yields a checkpointer for the caller's lifetime.
     Resources are opened on enter and closed on exit -- no global state::
 
-        async with make_checkpointer(app_config) as checkpointer:
+        async with make_checkpointer() as checkpointer:
             app.state.checkpointer = checkpointer
 
     Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
@@ -138,17 +138,16 @@ async def make_checkpointer(app_config: AppConfig | None = None) -> AsyncIterato
     3. Default InMemorySaver
     """
 
-    if app_config is None:
-        app_config = get_app_config()
+    config = get_app_config()
 
     # Legacy: standalone checkpointer config takes precedence
-    if app_config.checkpointer is not None:
-        async with _async_checkpointer(app_config.checkpointer) as saver:
+    if config.checkpointer is not None:
+        async with _async_checkpointer(config.checkpointer) as saver:
             yield saver
             return
 
     # Unified database config
-    db_config = getattr(app_config, "database", None)
+    db_config = getattr(config, "database", None)
     if db_config is not None and db_config.backend != "memory":
         async with _async_checkpointer_from_database(db_config) as saver:
             yield saver

backend/packages/harness/deerflow/agents/checkpointer/provider.py

@@ -7,7 +7,7 @@ Supported backends: memory, sqlite, postgres.
 
 Usage::
 
-    from deerflow.runtime.checkpointer.provider import get_checkpointer, checkpointer_context
+    from deerflow.agents.checkpointer.provider import get_checkpointer, checkpointer_context
 
     # Singleton — reused across calls, closed on process exit
     cp = get_checkpointer()
@@ -25,9 +25,9 @@ from collections.abc import Iterator
 
 from langgraph.types import Checkpointer
 
-from deerflow.config.app_config import AppConfig, get_app_config
+from deerflow.config.app_config import get_app_config
 from deerflow.config.checkpointer_config import CheckpointerConfig
-from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
+from deerflow.runtime.store._sqlite_utils import resolve_sqlite_conn_str
 
 logger = logging.getLogger(__name__)
 
@@ -67,7 +67,6 @@ def _sync_checkpointer_cm(config: CheckpointerConfig) -> Iterator[Checkpointer]:
             raise ImportError(SQLITE_INSTALL) from exc
 
         conn_str = resolve_sqlite_conn_str(config.connection_string or "store.db")
-        ensure_sqlite_parent_dir(conn_str)
         with SqliteSaver.from_conn_string(conn_str) as saver:
             saver.setup()
             logger.info("Checkpointer: using SqliteSaver (%s)", conn_str)
@@ -98,78 +97,9 @@ def _sync_checkpointer_cm(config: CheckpointerConfig) -> Iterator[Checkpointer]:
 
 _checkpointer: Checkpointer | None = None
 _checkpointer_ctx = None  # open context manager keeping the connection alive
-_explicit_checkpointers: dict[int, Checkpointer] = {}
-_explicit_checkpointer_contexts: dict[int, object] = {}
 
 
-def _default_in_memory_checkpointer() -> Checkpointer:
-    from langgraph.checkpoint.memory import InMemorySaver
-
-    logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
-    return InMemorySaver()
-
-
-def _persistent_database_backend(db_config) -> str | None:
-    backend = getattr(db_config, "backend", None)
-    if backend in {"sqlite", "postgres"}:
-        return backend
-    return None
-
-
-@contextlib.contextmanager
-def _sync_checkpointer_from_database_cm(db_config) -> Iterator[Checkpointer]:
-    """Context manager that creates a sync checkpointer from unified DatabaseConfig."""
-    backend = _persistent_database_backend(db_config)
-    if backend is None:
-        yield _default_in_memory_checkpointer()
-        return
-
-    if backend == "sqlite":
-        try:
-            from langgraph.checkpoint.sqlite import SqliteSaver
-        except ImportError as exc:
-            raise ImportError(SQLITE_INSTALL) from exc
-
-        conn_str = db_config.checkpointer_sqlite_path
-        ensure_sqlite_parent_dir(conn_str)
-        with SqliteSaver.from_conn_string(conn_str) as saver:
-            saver.setup()
-            logger.info("Checkpointer: using SqliteSaver (%s)", conn_str)
-            yield saver
-        return
-
-    if backend == "postgres":
-        try:
-            from langgraph.checkpoint.postgres import PostgresSaver
-        except ImportError as exc:
-            raise ImportError(POSTGRES_INSTALL) from exc
-
-        if not db_config.postgres_url:
-            raise ValueError("database.postgres_url is required for the postgres backend")
-
-        with PostgresSaver.from_conn_string(db_config.postgres_url) as saver:
-            saver.setup()
-            logger.info("Checkpointer: using PostgresSaver")
-            yield saver
-        return
-
-    raise ValueError(f"Unknown database backend: {backend!r}")
-
-
-def _build_checkpointer_from_app_config(app_config: AppConfig) -> tuple[Checkpointer, object | None]:
-    if app_config.checkpointer is not None:
-        ctx = _sync_checkpointer_cm(app_config.checkpointer)
-        return ctx.__enter__(), ctx
-
-    db_config = getattr(app_config, "database", None)
-    if _persistent_database_backend(db_config) is not None:
-        ctx = _sync_checkpointer_from_database_cm(db_config)
-        return ctx.__enter__(), ctx
-
-    return _default_in_memory_checkpointer(), None
-
-
-def get_checkpointer(app_config: AppConfig | None = None) -> Checkpointer:
+def get_checkpointer() -> Checkpointer:
     """Return the global sync checkpointer singleton, creating it on first call.
 
     Returns an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
@@ -180,18 +110,6 @@ def get_checkpointer(app_config: AppConfig | None = None) -> Checkpointer:
     """
     global _checkpointer, _checkpointer_ctx
 
-    if app_config is not None:
-        cache_key = id(app_config)
-        cached = _explicit_checkpointers.get(cache_key)
-        if cached is not None:
-            return cached
-
-        explicit_checkpointer, explicit_ctx = _build_checkpointer_from_app_config(app_config)
-        _explicit_checkpointers[cache_key] = explicit_checkpointer
-        if explicit_ctx is not None:
-            _explicit_checkpointer_contexts[cache_key] = explicit_ctx
-        return explicit_checkpointer
-
     if _checkpointer is not None:
         return _checkpointer
 
@@ -202,30 +120,28 @@ def get_checkpointer(app_config: AppConfig | None = None) -> Checkpointer:
     from deerflow.config.checkpointer_config import get_checkpointer_config
 
     config = get_checkpointer_config()
-    global_app_config = _app_config
 
-    if config is None and global_app_config is None:
+    if config is None and _app_config is None:
         # Only load app config lazily when neither the app config nor an explicit
         # checkpointer config has been initialized yet. This keeps tests that
         # intentionally set the global checkpointer config isolated from any
         # ambient config.yaml on disk.
         try:
-            global_app_config = get_app_config()
+            get_app_config()
         except FileNotFoundError:
             # In test environments without config.yaml, this is expected.
             pass
         config = get_checkpointer_config()
+    if config is None:
+        from langgraph.checkpoint.memory import InMemorySaver
 
-    if config is not None:
-        _checkpointer_ctx = _sync_checkpointer_cm(config)
-        _checkpointer = _checkpointer_ctx.__enter__()
+        logger.info("Checkpointer: using InMemorySaver (in-process, not persistent)")
+        _checkpointer = InMemorySaver()
         return _checkpointer
 
-    if global_app_config is not None:
-        _checkpointer, _checkpointer_ctx = _build_checkpointer_from_app_config(global_app_config)
-        return _checkpointer
+    _checkpointer_ctx = _sync_checkpointer_cm(config)
+    _checkpointer = _checkpointer_ctx.__enter__()
 
-    _checkpointer = _default_in_memory_checkpointer()
     return _checkpointer
 
 
@@ -244,18 +160,6 @@ def reset_checkpointer() -> None:
         _checkpointer_ctx = None
     _checkpointer = None
 
-    for cache_key, ctx in list(_explicit_checkpointer_contexts.items()):
-        try:
-            ctx.__exit__(None, None, None)
-        except Exception:
-            logger.warning("Error during explicit checkpointer cleanup", exc_info=True)
-        finally:
-            _explicit_checkpointer_contexts.pop(cache_key, None)
-            _explicit_checkpointers.pop(cache_key, None)
-
-    _explicit_checkpointers.clear()
-    _explicit_checkpointer_contexts.clear()
-
 
 # ---------------------------------------------------------------------------
 # Sync context manager
@@ -263,7 +167,7 @@ def reset_checkpointer() -> None:
 
 
 @contextlib.contextmanager
-def checkpointer_context(app_config: AppConfig | None = None) -> Iterator[Checkpointer]:
+def checkpointer_context() -> Iterator[Checkpointer]:
     """Sync context manager that yields a checkpointer and cleans up on exit.
 
     Unlike :func:`get_checkpointer`, this does **not** cache the instance —
@@ -276,16 +180,12 @@ def checkpointer_context(app_config: AppConfig | None = None) -> Iterator[Checkp
     Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
     """
 
-    resolved_app_config = app_config or get_app_config()
-    if resolved_app_config.checkpointer is not None:
-        with _sync_checkpointer_cm(resolved_app_config.checkpointer) as saver:
-            yield saver
+    config = get_app_config()
+    if config.checkpointer is None:
+        from langgraph.checkpoint.memory import InMemorySaver
+
+        yield InMemorySaver()
         return
 
-    db_config = getattr(resolved_app_config, "database", None)
-    if _persistent_database_backend(db_config) is not None:
-        with _sync_checkpointer_from_database_cm(db_config) as saver:
-            yield saver
-        return
-
-    yield _default_in_memory_checkpointer()
+    with _sync_checkpointer_cm(config.checkpointer) as saver:
+        yield saver

backend/packages/harness/deerflow/agents/factory.py

@@ -254,11 +254,9 @@ def _assemble_from_features(
             from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
 
             chain.append(ViewImageMiddleware())
+        from deerflow.tools.builtins import view_image_tool
 
-        if feat.sandbox is not False:
-            from deerflow.tools.builtins import view_image_tool
-
-            extra_tools.append(view_image_tool)
+        extra_tools.append(view_image_tool)
 
     # --- [11] Subagent ---
     if feat.subagent is not False:

backend/packages/harness/deerflow/agents/lead_agent/agent.py

@@ -1,41 +1,31 @@
 import logging
 
 from langchain.agents import create_agent
-from langchain.agents.middleware import AgentMiddleware
+from langchain.agents.middleware import AgentMiddleware, SummarizationMiddleware
 from langchain_core.runnables import RunnableConfig
 
 from deerflow.agents.lead_agent.prompt import apply_prompt_template
-from deerflow.agents.memory.summarization_hook import memory_flush_hook
 from deerflow.agents.middlewares.clarification_middleware import ClarificationMiddleware
 from deerflow.agents.middlewares.loop_detection_middleware import LoopDetectionMiddleware
 from deerflow.agents.middlewares.memory_middleware import MemoryMiddleware
 from deerflow.agents.middlewares.subagent_limit_middleware import SubagentLimitMiddleware
-from deerflow.agents.middlewares.summarization_middleware import BeforeSummarizationHook, DeerFlowSummarizationMiddleware
 from deerflow.agents.middlewares.title_middleware import TitleMiddleware
 from deerflow.agents.middlewares.todo_middleware import TodoMiddleware
 from deerflow.agents.middlewares.token_usage_middleware import TokenUsageMiddleware
 from deerflow.agents.middlewares.tool_error_handling_middleware import build_lead_runtime_middlewares
 from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
 from deerflow.agents.thread_state import ThreadState
-from deerflow.config.agents_config import load_agent_config, validate_agent_name
-from deerflow.config.app_config import AppConfig, get_app_config
+from deerflow.config.agents_config import load_agent_config
+from deerflow.config.app_config import get_app_config
+from deerflow.config.summarization_config import get_summarization_config
 from deerflow.models import create_chat_model
 
 logger = logging.getLogger(__name__)
 
 
-def _get_runtime_config(config: RunnableConfig) -> dict:
-    """Merge legacy configurable options with LangGraph runtime context."""
-    cfg = dict(config.get("configurable", {}) or {})
-    context = config.get("context", {}) or {}
-    if isinstance(context, dict):
-        cfg.update(context)
-    return cfg
-
-
-def _resolve_model_name(requested_model_name: str | None = None, *, app_config: AppConfig | None = None) -> str:
+def _resolve_model_name(requested_model_name: str | None = None) -> str:
     """Resolve a runtime model name safely, falling back to default if invalid. Returns None if no models are configured."""
-    app_config = app_config or get_app_config()
+    app_config = get_app_config()
     default_model_name = app_config.models[0].name if app_config.models else None
     if default_model_name is None:
         raise ValueError("No chat models are configured. Please configure at least one model in config.yaml.")
@@ -48,10 +38,9 @@ def _resolve_model_name(requested_model_name: str | None = None, *, app_config:
     return default_model_name
 
 
-def _create_summarization_middleware(*, app_config: AppConfig | None = None) -> DeerFlowSummarizationMiddleware | None:
+def _create_summarization_middleware() -> SummarizationMiddleware | None:
     """Create and configure the summarization middleware from config."""
-    resolved_app_config = app_config or get_app_config()
-    config = resolved_app_config.summarization
+    config = get_summarization_config()
 
     if not config.enabled:
         return None
@@ -72,9 +61,9 @@ def _create_summarization_middleware(*, app_config: AppConfig | None = None) ->
     # as middleware rather than lead_agent (SummarizationMiddleware is a
     # LangChain built-in, so we tag the model at creation time).
     if config.model_name:
-        model = create_chat_model(name=config.model_name, thinking_enabled=False, app_config=resolved_app_config)
+        model = create_chat_model(name=config.model_name, thinking_enabled=False)
     else:
-        model = create_chat_model(thinking_enabled=False, app_config=resolved_app_config)
+        model = create_chat_model(thinking_enabled=False)
     model = model.with_config(tags=["middleware:summarize"])
 
     # Prepare kwargs
@@ -90,24 +79,7 @@ def _create_summarization_middleware(*, app_config: AppConfig | None = None) ->
     if config.summary_prompt is not None:
         kwargs["summary_prompt"] = config.summary_prompt
 
-    hooks: list[BeforeSummarizationHook] = []
-    if resolved_app_config.memory.enabled:
-        hooks.append(memory_flush_hook)
-
-    # The logic below relies on two assumptions holding true: this factory is
-    # the sole entry point for DeerFlowSummarizationMiddleware, and the runtime
-    # config is not expected to change after startup.
-    skills_container_path = resolved_app_config.skills.container_path or "/mnt/skills"
-
-    return DeerFlowSummarizationMiddleware(
-        **kwargs,
-        skills_container_path=skills_container_path,
-        skill_file_read_tool_names=config.skill_file_read_tool_names,
-        before_summarization=hooks,
-        preserve_recent_skill_count=config.preserve_recent_skill_count,
-        preserve_recent_skill_tokens=config.preserve_recent_skill_tokens,
-        preserve_recent_skill_tokens_per_skill=config.preserve_recent_skill_tokens_per_skill,
-    )
+    return SummarizationMiddleware(**kwargs)
 
 
 def _create_todo_list_middleware(is_plan_mode: bool) -> TodoMiddleware | None:
@@ -235,14 +207,7 @@ Being proactive with task management demonstrates thoroughness and ensures all r
 # ViewImageMiddleware should be before ClarificationMiddleware to inject image details before LLM
 # ToolErrorHandlingMiddleware should be before ClarificationMiddleware to convert tool exceptions to ToolMessages
 # ClarificationMiddleware should be last to intercept clarification requests after model calls
-def _build_middlewares(
-    config: RunnableConfig,
-    model_name: str | None,
-    agent_name: str | None = None,
-    custom_middlewares: list[AgentMiddleware] | None = None,
-    *,
-    app_config: AppConfig | None = None,
-):
+def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_name: str | None = None, custom_middlewares: list[AgentMiddleware] | None = None):
     """Build middleware chain based on runtime configuration.
 
     Args:
@@ -253,47 +218,46 @@ def _build_middlewares(
     Returns:
         List of middleware instances.
     """
-    resolved_app_config = app_config or get_app_config()
-    middlewares = build_lead_runtime_middlewares(app_config=resolved_app_config, lazy_init=True)
+    middlewares = build_lead_runtime_middlewares(lazy_init=True)
 
     # Add summarization middleware if enabled
-    summarization_middleware = _create_summarization_middleware(app_config=resolved_app_config)
+    summarization_middleware = _create_summarization_middleware()
     if summarization_middleware is not None:
         middlewares.append(summarization_middleware)
 
     # Add TodoList middleware if plan mode is enabled
-    cfg = _get_runtime_config(config)
-    is_plan_mode = cfg.get("is_plan_mode", False)
+    is_plan_mode = config.get("configurable", {}).get("is_plan_mode", False)
     todo_list_middleware = _create_todo_list_middleware(is_plan_mode)
     if todo_list_middleware is not None:
         middlewares.append(todo_list_middleware)
 
     # Add TokenUsageMiddleware when token_usage tracking is enabled
-    if resolved_app_config.token_usage.enabled:
+    if get_app_config().token_usage.enabled:
         middlewares.append(TokenUsageMiddleware())
 
     # Add TitleMiddleware
-    middlewares.append(TitleMiddleware(app_config=resolved_app_config))
+    middlewares.append(TitleMiddleware())
 
     # Add MemoryMiddleware (after TitleMiddleware)
-    middlewares.append(MemoryMiddleware(agent_name=agent_name, memory_config=resolved_app_config.memory))
+    middlewares.append(MemoryMiddleware(agent_name=agent_name))
 
     # Add ViewImageMiddleware only if the current model supports vision.
     # Use the resolved runtime model_name from make_lead_agent to avoid stale config values.
-    model_config = resolved_app_config.get_model_config(model_name) if model_name else None
+    app_config = get_app_config()
+    model_config = app_config.get_model_config(model_name) if model_name else None
     if model_config is not None and model_config.supports_vision:
         middlewares.append(ViewImageMiddleware())
 
     # Add DeferredToolFilterMiddleware to hide deferred tool schemas from model binding
-    if resolved_app_config.tool_search.enabled:
+    if app_config.tool_search.enabled:
         from deerflow.agents.middlewares.deferred_tool_filter_middleware import DeferredToolFilterMiddleware
 
         middlewares.append(DeferredToolFilterMiddleware())
 
     # Add SubagentLimitMiddleware to truncate excess parallel task calls
-    subagent_enabled = cfg.get("subagent_enabled", False)
+    subagent_enabled = config.get("configurable", {}).get("subagent_enabled", False)
     if subagent_enabled:
-        max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
+        max_concurrent_subagents = config.get("configurable", {}).get("max_concurrent_subagents", 3)
         middlewares.append(SubagentLimitMiddleware(max_concurrent=max_concurrent_subagents))
 
     # LoopDetectionMiddleware — detect and break repetitive tool call loops
@@ -309,19 +273,11 @@ def _build_middlewares(
 
 
 def make_lead_agent(config: RunnableConfig):
-    """LangGraph graph factory; keep the signature compatible with LangGraph Server."""
-    runtime_config = _get_runtime_config(config)
-    runtime_app_config = runtime_config.get("app_config")
-    return _make_lead_agent(config, app_config=runtime_app_config or get_app_config())
-
-
-def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
     # Lazy import to avoid circular dependency
     from deerflow.tools import get_available_tools
     from deerflow.tools.builtins import setup_agent
 
-    cfg = _get_runtime_config(config)
-    resolved_app_config = app_config
+    cfg = config.get("configurable", {})
 
     thinking_enabled = cfg.get("thinking_enabled", True)
     reasoning_effort = cfg.get("reasoning_effort", None)
@@ -330,16 +286,17 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
     subagent_enabled = cfg.get("subagent_enabled", False)
     max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
     is_bootstrap = cfg.get("is_bootstrap", False)
-    agent_name = validate_agent_name(cfg.get("agent_name"))
+    agent_name = cfg.get("agent_name")
 
     agent_config = load_agent_config(agent_name) if not is_bootstrap else None
     # Custom agent model from agent config (if any), or None to let _resolve_model_name pick the default
     agent_model_name = agent_config.model if agent_config and agent_config.model else None
 
     # Final model name resolution: request → agent config → global default, with fallback for unknown names
-    model_name = _resolve_model_name(requested_model_name or agent_model_name, app_config=resolved_app_config)
+    model_name = _resolve_model_name(requested_model_name or agent_model_name)
 
-    model_config = resolved_app_config.get_model_config(model_name)
+    app_config = get_app_config()
+    model_config = app_config.get_model_config(model_name)
 
     if model_config is None:
         raise ValueError("No chat model could be resolved. Please configure at least one model in config.yaml or provide a valid 'model_name'/'model' in the request.")
@@ -370,42 +327,26 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
             "reasoning_effort": reasoning_effort,
             "is_plan_mode": is_plan_mode,
             "subagent_enabled": subagent_enabled,
-            "tool_groups": agent_config.tool_groups if agent_config else None,
-            "available_skills": ["bootstrap"] if is_bootstrap else (agent_config.skills if agent_config and agent_config.skills is not None else None),
         }
     )
 
     if is_bootstrap:
         # Special bootstrap agent with minimal prompt for initial custom agent creation flow
         return create_agent(
-            model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config),
-            tools=get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled, app_config=resolved_app_config) + [setup_agent],
-            middleware=_build_middlewares(config, model_name=model_name, app_config=resolved_app_config),
-            system_prompt=apply_prompt_template(
-                subagent_enabled=subagent_enabled,
-                max_concurrent_subagents=max_concurrent_subagents,
-                available_skills=set(["bootstrap"]),
-                app_config=resolved_app_config,
-            ),
+            model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled),
+            tools=get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled) + [setup_agent],
+            middleware=_build_middlewares(config, model_name=model_name),
+            system_prompt=apply_prompt_template(subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, available_skills=set(["bootstrap"])),
             state_schema=ThreadState,
         )
 
     # Default lead agent (unchanged behavior)
     return create_agent(
-        model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, app_config=resolved_app_config),
-        tools=get_available_tools(
-            model_name=model_name,
-            groups=agent_config.tool_groups if agent_config else None,
-            subagent_enabled=subagent_enabled,
-            app_config=resolved_app_config,
-        ),
-        middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name, app_config=resolved_app_config),
+        model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort),
+        tools=get_available_tools(model_name=model_name, groups=agent_config.tool_groups if agent_config else None, subagent_enabled=subagent_enabled),
+        middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name),
         system_prompt=apply_prompt_template(
-            subagent_enabled=subagent_enabled,
-            max_concurrent_subagents=max_concurrent_subagents,
-            agent_name=agent_name,
-            available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None,
-            app_config=resolved_app_config,
+            subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, agent_name=agent_name, available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None
         ),
         state_schema=ThreadState,
     )

backend/packages/harness/deerflow/agents/lead_agent/prompt.py

@@ -1,20 +1,14 @@
-from __future__ import annotations
-
 import asyncio
 import logging
 import threading
 from datetime import datetime
 from functools import lru_cache
-from typing import TYPE_CHECKING
 
 from deerflow.config.agents_config import load_agent_soul
-from deerflow.skills.storage import get_or_new_skill_storage
-from deerflow.skills.types import Skill, SkillCategory
+from deerflow.skills import load_skills
+from deerflow.skills.types import Skill
 from deerflow.subagents import get_available_subagent_names
 
-if TYPE_CHECKING:
-    from deerflow.config.app_config import AppConfig
-
 logger = logging.getLogger(__name__)
 
 _ENABLED_SKILLS_REFRESH_WAIT_TIMEOUT_SECONDS = 5.0
@@ -26,7 +20,7 @@ _enabled_skills_refresh_event = threading.Event()
 
 
 def _load_enabled_skills_sync() -> list[Skill]:
-    return list(get_or_new_skill_storage().load_skills(enabled_only=True))
+    return list(load_skills(enabled_only=True))
 
 
 def _start_enabled_skills_refresh_thread() -> None:
@@ -117,21 +111,8 @@ def _get_enabled_skills():
     return []
 
 
-def _get_enabled_skills_for_config(app_config: AppConfig | None = None) -> list[Skill]:
-    """Return enabled skills using the caller's config source.
-
-    When a concrete ``app_config`` is supplied, bypass the global enabled-skills
-    cache so the skill list and skill paths are resolved from the same config
-    object. This keeps request-scoped config injection consistent even while the
-    release branch still supports global fallback paths.
-    """
-    if app_config is None:
-        return _get_enabled_skills()
-    return list(get_or_new_skill_storage(app_config=app_config).load_skills(enabled_only=True))
-
-
-def _skill_mutability_label(category: SkillCategory | str) -> str:
-    return "[custom, editable]" if category == SkillCategory.CUSTOM else "[built-in]"
+def _skill_mutability_label(category: str) -> str:
+    return "[custom, editable]" if category == "custom" else "[built-in]"
 
 
 def clear_skills_system_prompt_cache() -> None:
@@ -142,6 +123,31 @@ async def refresh_skills_system_prompt_cache_async() -> None:
     await asyncio.to_thread(_invalidate_enabled_skills_cache().wait)
 
 
+def _reset_skills_system_prompt_cache_state() -> None:
+    global _enabled_skills_cache, _enabled_skills_refresh_active, _enabled_skills_refresh_version
+
+    _get_cached_skills_prompt_section.cache_clear()
+    with _enabled_skills_lock:
+        _enabled_skills_cache = None
+        _enabled_skills_refresh_active = False
+        _enabled_skills_refresh_version = 0
+        _enabled_skills_refresh_event.clear()
+
+
+def _refresh_enabled_skills_cache() -> None:
+    """Backward-compatible test helper for direct synchronous reload."""
+    try:
+        skills = _load_enabled_skills_sync()
+    except Exception:
+        logger.exception("Failed to load enabled skills for prompt injection")
+        skills = []
+
+    with _enabled_skills_lock:
+        _enabled_skills_cache = skills
+        _enabled_skills_refresh_active = False
+        _enabled_skills_refresh_event.set()
+
+
 def _build_skill_evolution_section(skill_evolution_enabled: bool) -> str:
     if not skill_evolution_enabled:
         return ""
@@ -158,37 +164,7 @@ Skip simple one-off tasks.
 """
 
 
-def _build_available_subagents_description(available_names: list[str], bash_available: bool, *, app_config: AppConfig | None = None) -> str:
-    """Dynamically build subagent type descriptions from registry.
-
-    Mirrors Codex's pattern where agent_type_description is dynamically generated
-    from all registered roles, so the LLM knows about every available type.
-    """
-    # Built-in descriptions (kept for backward compatibility with existing prompt quality)
-    builtin_descriptions = {
-        "general-purpose": "For ANY non-trivial task - web research, code exploration, file operations, analysis, etc.",
-        "bash": (
-            "For command execution (git, build, test, deploy operations)" if bash_available else "Not available in the current sandbox configuration. Use direct file/web tools or switch to AioSandboxProvider for isolated shell access."
-        ),
-    }
-
-    # Lazy import moved outside loop to avoid repeated import overhead
-    from deerflow.subagents.registry import get_subagent_config
-
-    lines = []
-    for name in available_names:
-        if name in builtin_descriptions:
-            lines.append(f"- **{name}**: {builtin_descriptions[name]}")
-        else:
-            config = get_subagent_config(name, app_config=app_config)
-            if config is not None:
-                desc = config.description.split("\n")[0].strip()  # First line only for brevity
-                lines.append(f"- **{name}**: {desc}")
-
-    return "\n".join(lines)
-
-
-def _build_subagent_section(max_concurrent: int, *, app_config: AppConfig | None = None) -> str:
+def _build_subagent_section(max_concurrent: int) -> str:
     """Build the subagent system prompt section with dynamic concurrency limit.
 
     Args:
@@ -198,12 +174,13 @@ def _build_subagent_section(max_concurrent: int, *, app_config: AppConfig | None
         Formatted subagent section string.
     """
     n = max_concurrent
-    available_names = get_available_subagent_names(app_config=app_config) if app_config is not None else get_available_subagent_names()
-    bash_available = "bash" in available_names
-
-    # Dynamically build subagent type descriptions from registry (aligned with Codex's
-    # agent_type_description pattern where all registered roles are listed in the tool spec).
-    available_subagents = _build_available_subagents_description(available_names, bash_available, app_config=app_config)
+    bash_available = "bash" in get_available_subagent_names()
+    available_subagents = (
+        "- **general-purpose**: For ANY non-trivial task - web research, code exploration, file operations, analysis, etc.\n- **bash**: For command execution (git, build, test, deploy operations)"
+        if bash_available
+        else "- **general-purpose**: For ANY non-trivial task - web research, code exploration, file operations, analysis, etc.\n"
+        "- **bash**: Not available in the current sandbox configuration. Use direct file/web tools or switch to AioSandboxProvider for isolated shell access."
+    )
     direct_tool_examples = "bash, ls, read_file, web_search, etc." if bash_available else "ls, read_file, web_search, etc."
     direct_execution_example = (
         '# User asks: "Run the tests"\n# Thinking: Cannot decompose into parallel sub-tasks\n# → Execute directly\n\nbash("npm test")  # Direct execution, not task()'
@@ -443,7 +420,7 @@ You: "Deploying to staging..." [proceed]
 - Treat `/mnt/user-data/workspace` as your default current working directory for coding and file-editing tasks
 - When writing scripts or commands that create/read files from the workspace, prefer relative paths such as `hello.txt`, `../uploads/data.csv`, and `../outputs/report.md`
 - Avoid hardcoding `/mnt/user-data/...` inside generated scripts when a relative path from the workspace is enough
-- Final deliverables must be copied to `/mnt/user-data/outputs` and presented using `present_files` tool
+- Final deliverables must be copied to `/mnt/user-data/outputs` and presented using `present_file` tool
 {acp_section}
 </working_directory>
 
@@ -530,32 +507,24 @@ combined with a FastAPI gateway for REST API access [citation:FastAPI](https://f
 """
 
 
-def _get_memory_context(agent_name: str | None = None, *, app_config: AppConfig | None = None) -> str:
+def _get_memory_context(agent_name: str | None = None) -> str:
     """Get memory context for injection into system prompt.
 
     Args:
         agent_name: If provided, loads per-agent memory. If None, loads global memory.
-        app_config: Explicit application config. When provided, memory options
-            are read from this value instead of the global config singleton.
 
     Returns:
         Formatted memory context string wrapped in XML tags, or empty string if disabled.
     """
     try:
         from deerflow.agents.memory import format_memory_for_injection, get_memory_data
-        from deerflow.runtime.user_context import get_effective_user_id
-
-        if app_config is None:
-            from deerflow.config.memory_config import get_memory_config
-
-            config = get_memory_config()
-        else:
-            config = app_config.memory
+        from deerflow.config.memory_config import get_memory_config
 
+        config = get_memory_config()
         if not config.enabled or not config.injection_enabled:
             return ""
 
-        memory_data = get_memory_data(agent_name, user_id=get_effective_user_id())
+        memory_data = get_memory_data(agent_name)
         memory_content = format_memory_for_injection(memory_data, max_tokens=config.max_injection_tokens)
 
         if not memory_content.strip():
@@ -565,8 +534,8 @@ def _get_memory_context(agent_name: str | None = None, *, app_config: AppConfig
 {memory_content}
 </memory>
 """
-    except Exception:
-        logger.exception("Failed to load memory context")
+    except Exception as e:
+        logger.error("Failed to load memory context: %s", e)
         return ""
 
 
@@ -602,24 +571,19 @@ You have access to skills that provide optimized workflows for specific tasks. E
 </skill_system>"""
 
 
-def get_skills_prompt_section(available_skills: set[str] | None = None, *, app_config: AppConfig | None = None) -> str:
+def get_skills_prompt_section(available_skills: set[str] | None = None) -> str:
     """Generate the skills prompt section with available skills list."""
-    skills = _get_enabled_skills_for_config(app_config)
+    skills = _get_enabled_skills()
 
-    if app_config is None:
-        try:
-            from deerflow.config import get_app_config
+    try:
+        from deerflow.config import get_app_config
 
-            config = get_app_config()
-            container_base_path = config.skills.container_path
-            skill_evolution_enabled = config.skill_evolution.enabled
-        except Exception:
-            container_base_path = "/mnt/skills"
-            skill_evolution_enabled = False
-    else:
-        config = app_config
+        config = get_app_config()
         container_base_path = config.skills.container_path
         skill_evolution_enabled = config.skill_evolution.enabled
+    except Exception:
+        container_base_path = "/mnt/skills"
+        skill_evolution_enabled = False
 
     if not skills and not skill_evolution_enabled:
         return ""
@@ -643,7 +607,7 @@ def get_agent_soul(agent_name: str | None) -> str:
     return ""
 
 
-def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) -> str:
+def get_deferred_tools_prompt_section() -> str:
     """Generate <available-deferred-tools> block for the system prompt.
 
     Lists only deferred tool names so the agent knows what exists
@@ -652,17 +616,12 @@ def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) ->
     """
     from deerflow.tools.builtins.tool_search import get_deferred_registry
 
-    if app_config is None:
-        try:
-            from deerflow.config import get_app_config
+    try:
+        from deerflow.config import get_app_config
 
-            config = get_app_config()
-        except Exception:
+        if not get_app_config().tool_search.enabled:
             return ""
-    else:
-        config = app_config
-
-    if not config.tool_search.enabled:
+    except Exception:
         return ""
 
     registry = get_deferred_registry()
@@ -673,19 +632,15 @@ def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) ->
     return f"<available-deferred-tools>\n{names}\n</available-deferred-tools>"
 
 
-def _build_acp_section(*, app_config: AppConfig | None = None) -> str:
+def _build_acp_section() -> str:
     """Build the ACP agent prompt section, only if ACP agents are configured."""
-    if app_config is None:
-        try:
-            from deerflow.config.acp_config import get_acp_agents
+    try:
+        from deerflow.config.acp_config import get_acp_agents
 
-            agents = get_acp_agents()
-        except Exception:
+        agents = get_acp_agents()
+        if not agents:
             return ""
-    else:
-        agents = getattr(app_config, "acp_agents", {}) or {}
-
-    if not agents:
+    except Exception:
         return ""
 
     return (
@@ -693,24 +648,19 @@ def _build_acp_section(*, app_config: AppConfig | None = None) -> str:
         "- ACP agents (e.g. codex, claude_code) run in their own independent workspace — NOT in `/mnt/user-data/`\n"
         "- When writing prompts for ACP agents, describe the task only — do NOT reference `/mnt/user-data` paths\n"
         "- ACP agent results are accessible at `/mnt/acp-workspace/` (read-only) — use `ls`, `read_file`, or `bash cp` to retrieve output files\n"
-        "- To deliver ACP output to the user: copy from `/mnt/acp-workspace/<file>` to `/mnt/user-data/outputs/<file>`, then use `present_files`"
+        "- To deliver ACP output to the user: copy from `/mnt/acp-workspace/<file>` to `/mnt/user-data/outputs/<file>`, then use `present_file`"
     )
 
 
-def _build_custom_mounts_section(*, app_config: AppConfig | None = None) -> str:
+def _build_custom_mounts_section() -> str:
     """Build a prompt section for explicitly configured sandbox mounts."""
-    if app_config is None:
-        try:
-            from deerflow.config import get_app_config
+    try:
+        from deerflow.config import get_app_config
 
-            config = get_app_config()
-        except Exception:
-            logger.exception("Failed to load configured sandbox mounts for the lead-agent prompt")
-            return ""
-    else:
-        config = app_config
-
-    mounts = config.sandbox.mounts or []
+        mounts = get_app_config().sandbox.mounts or []
+    except Exception:
+        logger.exception("Failed to load configured sandbox mounts for the lead-agent prompt")
+        return ""
 
     if not mounts:
         return ""
@@ -724,20 +674,13 @@ def _build_custom_mounts_section(*, app_config: AppConfig | None = None) -> str:
     return f"\n**Custom Mounted Directories:**\n{mounts_list}\n- If the user needs files outside `/mnt/user-data`, use these absolute container paths directly when they match the requested directory"
 
 
-def apply_prompt_template(
-    subagent_enabled: bool = False,
-    max_concurrent_subagents: int = 3,
-    *,
-    agent_name: str | None = None,
-    available_skills: set[str] | None = None,
-    app_config: AppConfig | None = None,
-) -> str:
+def apply_prompt_template(subagent_enabled: bool = False, max_concurrent_subagents: int = 3, *, agent_name: str | None = None, available_skills: set[str] | None = None) -> str:
     # Get memory context
-    memory_context = _get_memory_context(agent_name, app_config=app_config)
+    memory_context = _get_memory_context(agent_name)
 
     # Include subagent section only if enabled (from runtime parameter)
     n = max_concurrent_subagents
-    subagent_section = _build_subagent_section(n, app_config=app_config) if subagent_enabled else ""
+    subagent_section = _build_subagent_section(n) if subagent_enabled else ""
 
     # Add subagent reminder to critical_reminders if enabled
     subagent_reminder = (
@@ -758,14 +701,14 @@ def apply_prompt_template(
     )
 
     # Get skills section
-    skills_section = get_skills_prompt_section(available_skills, app_config=app_config)
+    skills_section = get_skills_prompt_section(available_skills)
 
     # Get deferred tools section (tool_search)
-    deferred_tools_section = get_deferred_tools_prompt_section(app_config=app_config)
+    deferred_tools_section = get_deferred_tools_prompt_section()
 
     # Build ACP agent section only if ACP agents are configured
-    acp_section = _build_acp_section(app_config=app_config)
-    custom_mounts_section = _build_custom_mounts_section(app_config=app_config)
+    acp_section = _build_acp_section()
+    custom_mounts_section = _build_custom_mounts_section()
     acp_and_mounts_section = "\n".join(section for section in (acp_section, custom_mounts_section) if section)
 
     # Format the prompt with dynamic skills and memory

backend/packages/harness/deerflow/agents/memory/message_processing.py

@@ -1,109 +0,0 @@
-"""Shared helpers for turning conversations into memory update inputs."""
-
-from __future__ import annotations
-
-import re
-from copy import copy
-from typing import Any
-
-_UPLOAD_BLOCK_RE = re.compile(r"<uploaded_files>[\s\S]*?</uploaded_files>\n*", re.IGNORECASE)
-_CORRECTION_PATTERNS = (
-    re.compile(r"\bthat(?:'s| is) (?:wrong|incorrect)\b", re.IGNORECASE),
-    re.compile(r"\byou misunderstood\b", re.IGNORECASE),
-    re.compile(r"\btry again\b", re.IGNORECASE),
-    re.compile(r"\bredo\b", re.IGNORECASE),
-    re.compile(r"不对"),
-    re.compile(r"你理解错了"),
-    re.compile(r"你理解有误"),
-    re.compile(r"重试"),
-    re.compile(r"重新来"),
-    re.compile(r"换一种"),
-    re.compile(r"改用"),
-)
-_REINFORCEMENT_PATTERNS = (
-    re.compile(r"\byes[,.]?\s+(?:exactly|perfect|that(?:'s| is) (?:right|correct|it))\b", re.IGNORECASE),
-    re.compile(r"\bperfect(?:[.!?]|$)", re.IGNORECASE),
-    re.compile(r"\bexactly\s+(?:right|correct)\b", re.IGNORECASE),
-    re.compile(r"\bthat(?:'s| is)\s+(?:exactly\s+)?(?:right|correct|what i (?:wanted|needed|meant))\b", re.IGNORECASE),
-    re.compile(r"\bkeep\s+(?:doing\s+)?that\b", re.IGNORECASE),
-    re.compile(r"\bjust\s+(?:like\s+)?(?:that|this)\b", re.IGNORECASE),
-    re.compile(r"\bthis is (?:great|helpful)\b(?:[.!?]|$)", re.IGNORECASE),
-    re.compile(r"\bthis is what i wanted\b(?:[.!?]|$)", re.IGNORECASE),
-    re.compile(r"对[，,]?\s*就是这样(?:[。！？!?.]|$)"),
-    re.compile(r"完全正确(?:[。！？!?.]|$)"),
-    re.compile(r"(?:对[，,]?\s*)?就是这个意思(?:[。！？!?.]|$)"),
-    re.compile(r"正是我想要的(?:[。！？!?.]|$)"),
-    re.compile(r"继续保持(?:[。！？!?.]|$)"),
-)
-
-
-def extract_message_text(message: Any) -> str:
-    """Extract plain text from message content for filtering and signal detection."""
-    content = getattr(message, "content", "")
-    if isinstance(content, list):
-        text_parts: list[str] = []
-        for part in content:
-            if isinstance(part, str):
-                text_parts.append(part)
-            elif isinstance(part, dict):
-                text_val = part.get("text")
-                if isinstance(text_val, str):
-                    text_parts.append(text_val)
-        return " ".join(text_parts)
-    return str(content)
-
-
-def filter_messages_for_memory(messages: list[Any]) -> list[Any]:
-    """Keep only user inputs and final assistant responses for memory updates."""
-    filtered = []
-    skip_next_ai = False
-    for msg in messages:
-        msg_type = getattr(msg, "type", None)
-
-        if msg_type == "human":
-            content_str = extract_message_text(msg)
-            if "<uploaded_files>" in content_str:
-                stripped = _UPLOAD_BLOCK_RE.sub("", content_str).strip()
-                if not stripped:
-                    skip_next_ai = True
-                    continue
-                clean_msg = copy(msg)
-                clean_msg.content = stripped
-                filtered.append(clean_msg)
-                skip_next_ai = False
-            else:
-                filtered.append(msg)
-                skip_next_ai = False
-        elif msg_type == "ai":
-            tool_calls = getattr(msg, "tool_calls", None)
-            if not tool_calls:
-                if skip_next_ai:
-                    skip_next_ai = False
-                    continue
-                filtered.append(msg)
-
-    return filtered
-
-
-def detect_correction(messages: list[Any]) -> bool:
-    """Detect explicit user corrections in recent conversation turns."""
-    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
-
-    for msg in recent_user_msgs:
-        content = extract_message_text(msg).strip()
-        if content and any(pattern.search(content) for pattern in _CORRECTION_PATTERNS):
-            return True
-
-    return False
-
-
-def detect_reinforcement(messages: list[Any]) -> bool:
-    """Detect explicit positive reinforcement signals in recent conversation turns."""
-    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
-
-    for msg in recent_user_msgs:
-        content = extract_message_text(msg).strip()
-        if content and any(pattern.search(content) for pattern in _REINFORCEMENT_PATTERNS):
-            return True
-
-    return False

backend/packages/harness/deerflow/agents/memory/queue.py

@@ -20,7 +20,6 @@ class ConversationContext:
     messages: list[Any]
     timestamp: datetime = field(default_factory=lambda: datetime.now(UTC))
     agent_name: str | None = None
-    user_id: str | None = None
     correction_detected: bool = False
     reinforcement_detected: bool = False
 
@@ -45,7 +44,6 @@ class MemoryUpdateQueue:
         thread_id: str,
         messages: list[Any],
         agent_name: str | None = None,
-        user_id: str | None = None,
         correction_detected: bool = False,
         reinforcement_detected: bool = False,
     ) -> None:
@@ -55,9 +53,6 @@ class MemoryUpdateQueue:
             thread_id: The thread ID.
             messages: The conversation messages.
             agent_name: If provided, memory is stored per-agent. If None, uses global memory.
-            user_id: The user ID captured at enqueue time. Stored in ConversationContext so it
-                survives the threading.Timer boundary (ContextVar does not propagate across
-                raw threads).
             correction_detected: Whether recent turns include an explicit correction signal.
             reinforcement_detected: Whether recent turns include a positive reinforcement signal.
         """
@@ -66,93 +61,48 @@ class MemoryUpdateQueue:
             return
 
         with self._lock:
-            self._enqueue_locked(
+            existing_context = next(
+                (context for context in self._queue if context.thread_id == thread_id),
+                None,
+            )
+            merged_correction_detected = correction_detected or (existing_context.correction_detected if existing_context is not None else False)
+            merged_reinforcement_detected = reinforcement_detected or (existing_context.reinforcement_detected if existing_context is not None else False)
+            context = ConversationContext(
                 thread_id=thread_id,
                 messages=messages,
                 agent_name=agent_name,
-                user_id=user_id,
-                correction_detected=correction_detected,
-                reinforcement_detected=reinforcement_detected,
+                correction_detected=merged_correction_detected,
+                reinforcement_detected=merged_reinforcement_detected,
             )
+
+            # Check if this thread already has a pending update
+            # If so, replace it with the newer one
+            self._queue = [c for c in self._queue if c.thread_id != thread_id]
+            self._queue.append(context)
+
+            # Reset or start the debounce timer
             self._reset_timer()
 
         logger.info("Memory update queued for thread %s, queue size: %d", thread_id, len(self._queue))
 
-    def add_nowait(
-        self,
-        thread_id: str,
-        messages: list[Any],
-        agent_name: str | None = None,
-        user_id: str | None = None,
-        correction_detected: bool = False,
-        reinforcement_detected: bool = False,
-    ) -> None:
-        """Add a conversation and start processing immediately in the background."""
-        config = get_memory_config()
-        if not config.enabled:
-            return
-
-        with self._lock:
-            self._enqueue_locked(
-                thread_id=thread_id,
-                messages=messages,
-                agent_name=agent_name,
-                user_id=user_id,
-                correction_detected=correction_detected,
-                reinforcement_detected=reinforcement_detected,
-            )
-            self._schedule_timer(0)
-
-        logger.info("Memory update queued for immediate processing on thread %s, queue size: %d", thread_id, len(self._queue))
-
-    def _enqueue_locked(
-        self,
-        *,
-        thread_id: str,
-        messages: list[Any],
-        agent_name: str | None,
-        user_id: str | None,
-        correction_detected: bool,
-        reinforcement_detected: bool,
-    ) -> None:
-        existing_context = next(
-            (context for context in self._queue if context.thread_id == thread_id),
-            None,
-        )
-        merged_correction_detected = correction_detected or (existing_context.correction_detected if existing_context is not None else False)
-        merged_reinforcement_detected = reinforcement_detected or (existing_context.reinforcement_detected if existing_context is not None else False)
-        context = ConversationContext(
-            thread_id=thread_id,
-            messages=messages,
-            agent_name=agent_name,
-            user_id=user_id,
-            correction_detected=merged_correction_detected,
-            reinforcement_detected=merged_reinforcement_detected,
-        )
-
-        self._queue = [c for c in self._queue if c.thread_id != thread_id]
-        self._queue.append(context)
-
     def _reset_timer(self) -> None:
         """Reset the debounce timer."""
         config = get_memory_config()
-        self._schedule_timer(config.debounce_seconds)
 
-        logger.debug("Memory update timer set for %ss", config.debounce_seconds)
-
-    def _schedule_timer(self, delay_seconds: float) -> None:
-        """Schedule queue processing after the provided delay."""
         # Cancel existing timer if any
         if self._timer is not None:
             self._timer.cancel()
 
+        # Start new timer
         self._timer = threading.Timer(
-            delay_seconds,
+            config.debounce_seconds,
             self._process_queue,
         )
         self._timer.daemon = True
         self._timer.start()
 
+        logger.debug("Memory update timer set for %ss", config.debounce_seconds)
+
     def _process_queue(self) -> None:
         """Process all queued conversation contexts."""
         # Import here to avoid circular dependency
@@ -160,8 +110,8 @@ class MemoryUpdateQueue:
 
         with self._lock:
             if self._processing:
-                # Preserve immediate flush semantics even if another worker is active.
-                self._schedule_timer(0)
+                # Already processing, reschedule
+                self._reset_timer()
                 return
 
             if not self._queue:
@@ -186,7 +136,6 @@ class MemoryUpdateQueue:
                         agent_name=context.agent_name,
                         correction_detected=context.correction_detected,
                         reinforcement_detected=context.reinforcement_detected,
-                        user_id=context.user_id,
                     )
                     if success:
                         logger.info("Memory updated successfully for thread %s", context.thread_id)
@@ -215,13 +164,6 @@ class MemoryUpdateQueue:
 
         self._process_queue()
 
-    def flush_nowait(self) -> None:
-        """Start queue processing immediately in a background thread."""
-        with self._lock:
-            # Daemon thread: queued messages may be lost if the process exits
-            # before _process_queue completes. Acceptable for best-effort memory updates.
-            self._schedule_timer(0)
-
     def clear(self) -> None:
         """Clear the queue without processing.
 

backend/packages/harness/deerflow/agents/memory/storage.py

@@ -4,7 +4,6 @@ import abc
 import json
 import logging
 import threading
-import uuid
 from datetime import UTC, datetime
 from pathlib import Path
 from typing import Any
@@ -44,17 +43,17 @@ class MemoryStorage(abc.ABC):
     """Abstract base class for memory storage providers."""
 
     @abc.abstractmethod
-    def load(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+    def load(self, agent_name: str | None = None) -> dict[str, Any]:
         """Load memory data for the given agent."""
         pass
 
     @abc.abstractmethod
-    def reload(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+    def reload(self, agent_name: str | None = None) -> dict[str, Any]:
         """Force reload memory data for the given agent."""
         pass
 
     @abc.abstractmethod
-    def save(self, memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> bool:
+    def save(self, memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
         """Save memory data for the given agent."""
         pass
 
@@ -64,11 +63,9 @@ class FileMemoryStorage(MemoryStorage):
 
     def __init__(self):
         """Initialize the file memory storage."""
-        # Per-user/agent memory cache: keyed by (user_id, agent_name) tuple (None = global)
+        # Per-agent memory cache: keyed by agent_name (None = global)
         # Value: (memory_data, file_mtime)
-        self._memory_cache: dict[tuple[str | None, str | None], tuple[dict[str, Any], float | None]] = {}
-        # Guards all reads and writes to _memory_cache across concurrent callers.
-        self._cache_lock = threading.Lock()
+        self._memory_cache: dict[str | None, tuple[dict[str, Any], float | None]] = {}
 
     def _validate_agent_name(self, agent_name: str) -> None:
         """Validate that the agent name is safe to use in filesystem paths.
@@ -81,29 +78,21 @@ class FileMemoryStorage(MemoryStorage):
         if not AGENT_NAME_PATTERN.match(agent_name):
             raise ValueError(f"Invalid agent name {agent_name!r}: names must match {AGENT_NAME_PATTERN.pattern}")
 
-    def _get_memory_file_path(self, agent_name: str | None = None, *, user_id: str | None = None) -> Path:
+    def _get_memory_file_path(self, agent_name: str | None = None) -> Path:
         """Get the path to the memory file."""
-        if user_id is not None:
-            if agent_name is not None:
-                self._validate_agent_name(agent_name)
-                return get_paths().user_agent_memory_file(user_id, agent_name)
-            config = get_memory_config()
-            if config.storage_path and Path(config.storage_path).is_absolute():
-                return Path(config.storage_path)
-            return get_paths().user_memory_file(user_id)
-        # Legacy: no user_id
         if agent_name is not None:
             self._validate_agent_name(agent_name)
             return get_paths().agent_memory_file(agent_name)
+
         config = get_memory_config()
         if config.storage_path:
             p = Path(config.storage_path)
             return p if p.is_absolute() else get_paths().base_dir / p
         return get_paths().memory_file
 
-    def _load_memory_from_file(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+    def _load_memory_from_file(self, agent_name: str | None = None) -> dict[str, Any]:
         """Load memory data from file."""
-        file_path = self._get_memory_file_path(agent_name, user_id=user_id)
+        file_path = self._get_memory_file_path(agent_name)
 
         if not file_path.exists():
             return create_empty_memory()
@@ -116,60 +105,46 @@ class FileMemoryStorage(MemoryStorage):
             logger.warning("Failed to load memory file: %s", e)
             return create_empty_memory()
 
-    @staticmethod
-    def _cache_key(agent_name: str | None = None, *, user_id: str | None = None) -> tuple[str | None, str | None]:
-        return (user_id, agent_name)
-
-    def load(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+    def load(self, agent_name: str | None = None) -> dict[str, Any]:
         """Load memory data (cached with file modification time check)."""
-        file_path = self._get_memory_file_path(agent_name, user_id=user_id)
-        cache_key = self._cache_key(agent_name, user_id=user_id)
+        file_path = self._get_memory_file_path(agent_name)
 
         try:
             current_mtime = file_path.stat().st_mtime if file_path.exists() else None
         except OSError:
             current_mtime = None
 
-        with self._cache_lock:
-            cached = self._memory_cache.get(cache_key)
-            if cached is not None and cached[1] == current_mtime:
-                return cached[0]
+        cached = self._memory_cache.get(agent_name)
 
-        memory_data = self._load_memory_from_file(agent_name, user_id=user_id)
+        if cached is None or cached[1] != current_mtime:
+            memory_data = self._load_memory_from_file(agent_name)
+            self._memory_cache[agent_name] = (memory_data, current_mtime)
+            return memory_data
 
-        with self._cache_lock:
-            self._memory_cache[cache_key] = (memory_data, current_mtime)
+        return cached[0]
 
-        return memory_data
-
-    def reload(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+    def reload(self, agent_name: str | None = None) -> dict[str, Any]:
         """Reload memory data from file, forcing cache invalidation."""
-        file_path = self._get_memory_file_path(agent_name, user_id=user_id)
-        memory_data = self._load_memory_from_file(agent_name, user_id=user_id)
-        cache_key = self._cache_key(agent_name, user_id=user_id)
+        file_path = self._get_memory_file_path(agent_name)
+        memory_data = self._load_memory_from_file(agent_name)
 
         try:
             mtime = file_path.stat().st_mtime if file_path.exists() else None
         except OSError:
             mtime = None
 
-        with self._cache_lock:
-            self._memory_cache[cache_key] = (memory_data, mtime)
+        self._memory_cache[agent_name] = (memory_data, mtime)
         return memory_data
 
-    def save(self, memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> bool:
+    def save(self, memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
         """Save memory data to file and update cache."""
-        file_path = self._get_memory_file_path(agent_name, user_id=user_id)
-        cache_key = self._cache_key(agent_name, user_id=user_id)
+        file_path = self._get_memory_file_path(agent_name)
 
         try:
             file_path.parent.mkdir(parents=True, exist_ok=True)
-            # Shallow-copy before adding lastUpdated so the caller's dict is not
-            # mutated as a side-effect, and the cache reference is not silently
-            # updated before the file write succeeds.
-            memory_data = {**memory_data, "lastUpdated": utc_now_iso_z()}
+            memory_data["lastUpdated"] = utc_now_iso_z()
 
-            temp_path = file_path.with_suffix(f".{uuid.uuid4().hex}.tmp")
+            temp_path = file_path.with_suffix(".tmp")
             with open(temp_path, "w", encoding="utf-8") as f:
                 json.dump(memory_data, f, indent=2, ensure_ascii=False)
 
@@ -180,8 +155,7 @@ class FileMemoryStorage(MemoryStorage):
             except OSError:
                 mtime = None
 
-            with self._cache_lock:
-                self._memory_cache[cache_key] = (memory_data, mtime)
+            self._memory_cache[agent_name] = (memory_data, mtime)
             logger.info("Memory saved to %s", file_path)
             return True
         except OSError as e:

backend/packages/harness/deerflow/agents/memory/summarization_hook.py

@@ -1,31 +0,0 @@
-"""Hooks fired before summarization removes messages from state."""
-
-from __future__ import annotations
-
-from deerflow.agents.memory.message_processing import detect_correction, detect_reinforcement, filter_messages_for_memory
-from deerflow.agents.memory.queue import get_memory_queue
-from deerflow.agents.middlewares.summarization_middleware import SummarizationEvent
-from deerflow.config.memory_config import get_memory_config
-
-
-def memory_flush_hook(event: SummarizationEvent) -> None:
-    """Flush messages about to be summarized into the memory queue."""
-    if not get_memory_config().enabled or not event.thread_id:
-        return
-
-    filtered_messages = filter_messages_for_memory(list(event.messages_to_summarize))
-    user_messages = [message for message in filtered_messages if getattr(message, "type", None) == "human"]
-    assistant_messages = [message for message in filtered_messages if getattr(message, "type", None) == "ai"]
-    if not user_messages or not assistant_messages:
-        return
-
-    correction_detected = detect_correction(filtered_messages)
-    reinforcement_detected = not correction_detected and detect_reinforcement(filtered_messages)
-    queue = get_memory_queue()
-    queue.add_nowait(
-        thread_id=event.thread_id,
-        messages=filtered_messages,
-        agent_name=event.agent_name,
-        correction_detected=correction_detected,
-        reinforcement_detected=reinforcement_detected,
-    )

backend/packages/harness/deerflow/agents/memory/updater.py

@@ -1,9 +1,5 @@
 """Memory updater for reading, writing, and updating memory data."""
 
-import asyncio
-import atexit
-import concurrent.futures
-import copy
 import json
 import logging
 import math
@@ -26,45 +22,32 @@ from deerflow.models import create_chat_model
 logger = logging.getLogger(__name__)
 
 
-# Thread pool for offloading sync memory updates when called from an async
-# context.  Unlike the previous asyncio.run() approach, this runs *sync*
-# model.invoke() calls — no event loop is created, so the langchain async
-# httpx client pool (globally cached via @lru_cache) is never touched and
-# cross-loop connection reuse is impossible.
-_SYNC_MEMORY_UPDATER_EXECUTOR = concurrent.futures.ThreadPoolExecutor(
-    max_workers=4,
-    thread_name_prefix="memory-updater-sync",
-)
-atexit.register(lambda: _SYNC_MEMORY_UPDATER_EXECUTOR.shutdown(wait=False))
-
-
 def _create_empty_memory() -> dict[str, Any]:
     """Backward-compatible wrapper around the storage-layer empty-memory factory."""
     return create_empty_memory()
 
 
-def _save_memory_to_file(memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> bool:
+def _save_memory_to_file(memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
     """Backward-compatible wrapper around the configured memory storage save path."""
-    return get_memory_storage().save(memory_data, agent_name, user_id=user_id)
+    return get_memory_storage().save(memory_data, agent_name)
 
 
-def get_memory_data(agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+def get_memory_data(agent_name: str | None = None) -> dict[str, Any]:
     """Get the current memory data via storage provider."""
-    return get_memory_storage().load(agent_name, user_id=user_id)
+    return get_memory_storage().load(agent_name)
 
 
-def reload_memory_data(agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+def reload_memory_data(agent_name: str | None = None) -> dict[str, Any]:
     """Reload memory data via storage provider."""
-    return get_memory_storage().reload(agent_name, user_id=user_id)
+    return get_memory_storage().reload(agent_name)
 
 
-def import_memory_data(memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+def import_memory_data(memory_data: dict[str, Any], agent_name: str | None = None) -> dict[str, Any]:
     """Persist imported memory data via storage provider.
 
     Args:
         memory_data: Full memory payload to persist.
         agent_name: If provided, imports into per-agent memory.
-        user_id: If provided, scopes memory to a specific user.
 
     Returns:
         The saved memory data after storage normalization.
@@ -73,15 +56,15 @@ def import_memory_data(memory_data: dict[str, Any], agent_name: str | None = Non
         OSError: If persisting the imported memory fails.
     """
     storage = get_memory_storage()
-    if not storage.save(memory_data, agent_name, user_id=user_id):
+    if not storage.save(memory_data, agent_name):
         raise OSError("Failed to save imported memory data")
-    return storage.load(agent_name, user_id=user_id)
+    return storage.load(agent_name)
 
 
-def clear_memory_data(agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+def clear_memory_data(agent_name: str | None = None) -> dict[str, Any]:
     """Clear all stored memory data and persist an empty structure."""
     cleared_memory = create_empty_memory()
-    if not _save_memory_to_file(cleared_memory, agent_name, user_id=user_id):
+    if not _save_memory_to_file(cleared_memory, agent_name):
         raise OSError("Failed to save cleared memory data")
     return cleared_memory
 
@@ -98,8 +81,6 @@ def create_memory_fact(
     category: str = "context",
     confidence: float = 0.5,
     agent_name: str | None = None,
-    *,
-    user_id: str | None = None,
 ) -> dict[str, Any]:
     """Create a new fact and persist the updated memory data."""
     normalized_content = content.strip()
@@ -109,7 +90,7 @@ def create_memory_fact(
     normalized_category = category.strip() or "context"
     validated_confidence = _validate_confidence(confidence)
     now = utc_now_iso_z()
-    memory_data = get_memory_data(agent_name, user_id=user_id)
+    memory_data = get_memory_data(agent_name)
     updated_memory = dict(memory_data)
     facts = list(memory_data.get("facts", []))
     facts.append(
@@ -124,15 +105,15 @@ def create_memory_fact(
     )
     updated_memory["facts"] = facts
 
-    if not _save_memory_to_file(updated_memory, agent_name, user_id=user_id):
+    if not _save_memory_to_file(updated_memory, agent_name):
         raise OSError("Failed to save memory data after creating fact")
 
     return updated_memory
 
 
-def delete_memory_fact(fact_id: str, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
+def delete_memory_fact(fact_id: str, agent_name: str | None = None) -> dict[str, Any]:
     """Delete a fact by its id and persist the updated memory data."""
-    memory_data = get_memory_data(agent_name, user_id=user_id)
+    memory_data = get_memory_data(agent_name)
     facts = memory_data.get("facts", [])
     updated_facts = [fact for fact in facts if fact.get("id") != fact_id]
     if len(updated_facts) == len(facts):
@@ -141,7 +122,7 @@ def delete_memory_fact(fact_id: str, agent_name: str | None = None, *, user_id:
     updated_memory = dict(memory_data)
     updated_memory["facts"] = updated_facts
 
-    if not _save_memory_to_file(updated_memory, agent_name, user_id=user_id):
+    if not _save_memory_to_file(updated_memory, agent_name):
         raise OSError(f"Failed to save memory data after deleting fact '{fact_id}'")
 
     return updated_memory
@@ -153,11 +134,9 @@ def update_memory_fact(
     category: str | None = None,
     confidence: float | None = None,
     agent_name: str | None = None,
-    *,
-    user_id: str | None = None,
 ) -> dict[str, Any]:
     """Update an existing fact and persist the updated memory data."""
-    memory_data = get_memory_data(agent_name, user_id=user_id)
+    memory_data = get_memory_data(agent_name)
     updated_memory = dict(memory_data)
     updated_facts: list[dict[str, Any]] = []
     found = False
@@ -184,7 +163,7 @@ def update_memory_fact(
 
     updated_memory["facts"] = updated_facts
 
-    if not _save_memory_to_file(updated_memory, agent_name, user_id=user_id):
+    if not _save_memory_to_file(updated_memory, agent_name):
         raise OSError(f"Failed to save memory data after updating fact '{fact_id}'")
 
     return updated_memory
@@ -290,154 +269,6 @@ class MemoryUpdater:
         model_name = self._model_name or config.model_name
         return create_chat_model(name=model_name, thinking_enabled=False)
 
-    def _build_correction_hint(
-        self,
-        correction_detected: bool,
-        reinforcement_detected: bool,
-    ) -> str:
-        """Build optional prompt hints for correction and reinforcement signals."""
-        correction_hint = ""
-        if correction_detected:
-            correction_hint = (
-                "IMPORTANT: Explicit correction signals were detected in this conversation. "
-                "Pay special attention to what the agent got wrong, what the user corrected, "
-                "and record the correct approach as a fact with category "
-                '"correction" and confidence >= 0.95 when appropriate.'
-            )
-        if reinforcement_detected:
-            reinforcement_hint = (
-                "IMPORTANT: Positive reinforcement signals were detected in this conversation. "
-                "The user explicitly confirmed the agent's approach was correct or helpful. "
-                "Record the confirmed approach, style, or preference as a fact with category "
-                '"preference" or "behavior" and confidence >= 0.9 when appropriate.'
-            )
-            correction_hint = (correction_hint + "\n" + reinforcement_hint).strip() if correction_hint else reinforcement_hint
-
-        return correction_hint
-
-    def _prepare_update_prompt(
-        self,
-        messages: list[Any],
-        agent_name: str | None,
-        correction_detected: bool,
-        reinforcement_detected: bool,
-        user_id: str | None = None,
-    ) -> tuple[dict[str, Any], str] | None:
-        """Load memory and build the update prompt for a conversation."""
-        config = get_memory_config()
-        if not config.enabled or not messages:
-            return None
-
-        current_memory = get_memory_data(agent_name, user_id=user_id)
-        conversation_text = format_conversation_for_update(messages)
-        if not conversation_text.strip():
-            return None
-
-        correction_hint = self._build_correction_hint(
-            correction_detected=correction_detected,
-            reinforcement_detected=reinforcement_detected,
-        )
-        prompt = MEMORY_UPDATE_PROMPT.format(
-            current_memory=json.dumps(current_memory, indent=2),
-            conversation=conversation_text,
-            correction_hint=correction_hint,
-        )
-        return current_memory, prompt
-
-    def _finalize_update(
-        self,
-        current_memory: dict[str, Any],
-        response_content: Any,
-        thread_id: str | None,
-        agent_name: str | None,
-        user_id: str | None = None,
-    ) -> bool:
-        """Parse the model response, apply updates, and persist memory."""
-        response_text = _extract_text(response_content).strip()
-
-        if response_text.startswith("```"):
-            lines = response_text.split("\n")
-            response_text = "\n".join(lines[1:-1] if lines[-1] == "```" else lines[1:])
-
-        update_data = json.loads(response_text)
-        # Deep-copy before in-place mutation so a subsequent save() failure
-        # cannot corrupt the still-cached original object reference.
-        updated_memory = self._apply_updates(copy.deepcopy(current_memory), update_data, thread_id)
-        updated_memory = _strip_upload_mentions_from_memory(updated_memory)
-        return get_memory_storage().save(updated_memory, agent_name, user_id=user_id)
-
-    async def aupdate_memory(
-        self,
-        messages: list[Any],
-        thread_id: str | None = None,
-        agent_name: str | None = None,
-        correction_detected: bool = False,
-        reinforcement_detected: bool = False,
-        user_id: str | None = None,
-    ) -> bool:
-        """Update memory asynchronously by delegating to the sync path.
-
-        Uses ``asyncio.to_thread`` to run the *sync* ``model.invoke()`` path
-        in a worker thread so no second event loop is created and the
-        langchain async httpx client pool (shared with the lead agent) is
-        never touched.  This eliminates the cross-loop connection-reuse bug
-        described in issue #2615.
-        """
-        return await asyncio.to_thread(
-            self._do_update_memory_sync,
-            messages=messages,
-            thread_id=thread_id,
-            agent_name=agent_name,
-            correction_detected=correction_detected,
-            reinforcement_detected=reinforcement_detected,
-            user_id=user_id,
-        )
-
-    def _do_update_memory_sync(
-        self,
-        messages: list[Any],
-        thread_id: str | None = None,
-        agent_name: str | None = None,
-        correction_detected: bool = False,
-        reinforcement_detected: bool = False,
-        user_id: str | None = None,
-    ) -> bool:
-        """Pure-sync memory update using ``model.invoke()``.
-
-        Uses the *sync* LLM call path so no event loop is created.  This
-        guarantees that the langchain provider's globally cached async
-        httpx ``AsyncClient`` / connection pool (the one shared with the
-        lead agent) is never touched — no cross-loop connection reuse is
-        possible.
-        """
-        try:
-            prepared = self._prepare_update_prompt(
-                messages=messages,
-                agent_name=agent_name,
-                correction_detected=correction_detected,
-                reinforcement_detected=reinforcement_detected,
-                user_id=user_id,
-            )
-            if prepared is None:
-                return False
-
-            current_memory, prompt = prepared
-            model = self._get_model()
-            response = model.invoke(prompt, config={"run_name": "memory_agent"})
-            return self._finalize_update(
-                current_memory=current_memory,
-                response_content=response.content,
-                thread_id=thread_id,
-                agent_name=agent_name,
-                user_id=user_id,
-            )
-        except json.JSONDecodeError as e:
-            logger.warning("Failed to parse LLM response for memory update: %s", e)
-            return False
-        except Exception as e:
-            logger.exception("Memory update failed: %s", e)
-            return False
-
     def update_memory(
         self,
         messages: list[Any],
@@ -445,18 +276,8 @@ class MemoryUpdater:
         agent_name: str | None = None,
         correction_detected: bool = False,
         reinforcement_detected: bool = False,
-        user_id: str | None = None,
     ) -> bool:
-        """Synchronously update memory using the sync LLM path.
-
-        Uses ``model.invoke()`` (sync HTTP) which operates on a completely
-        separate connection pool from the async ``AsyncClient`` shared by
-        the lead agent.  This eliminates the cross-loop connection-reuse
-        bug described in issue #2615.
-
-        When called from within a running event loop (e.g. from a LangGraph
-        node), the blocking sync call is offloaded to a thread pool so the
-        caller's loop is not blocked.
+        """Update memory based on conversation messages.
 
         Args:
             messages: List of conversation messages.
@@ -464,40 +285,82 @@ class MemoryUpdater:
             agent_name: If provided, updates per-agent memory. If None, updates global memory.
             correction_detected: Whether recent turns include an explicit correction signal.
             reinforcement_detected: Whether recent turns include a positive reinforcement signal.
-            user_id: If provided, scopes memory to a specific user.
 
         Returns:
             True if update was successful, False otherwise.
         """
-        try:
-            loop = asyncio.get_running_loop()
-        except RuntimeError:
-            loop = None
+        config = get_memory_config()
+        if not config.enabled:
+            return False
 
-        if loop is not None and loop.is_running():
-            try:
-                future = _SYNC_MEMORY_UPDATER_EXECUTOR.submit(
-                    self._do_update_memory_sync,
-                    messages=messages,
-                    thread_id=thread_id,
-                    agent_name=agent_name,
-                    correction_detected=correction_detected,
-                    reinforcement_detected=reinforcement_detected,
-                    user_id=user_id,
-                )
-                return future.result()
-            except Exception:
-                logger.exception("Failed to offload memory update to executor")
+        if not messages:
+            return False
+
+        try:
+            # Get current memory
+            current_memory = get_memory_data(agent_name)
+
+            # Format conversation for prompt
+            conversation_text = format_conversation_for_update(messages)
+
+            if not conversation_text.strip():
                 return False
 
-        return self._do_update_memory_sync(
-            messages=messages,
-            thread_id=thread_id,
-            agent_name=agent_name,
-            correction_detected=correction_detected,
-            reinforcement_detected=reinforcement_detected,
-            user_id=user_id,
-        )
+            # Build prompt
+            correction_hint = ""
+            if correction_detected:
+                correction_hint = (
+                    "IMPORTANT: Explicit correction signals were detected in this conversation. "
+                    "Pay special attention to what the agent got wrong, what the user corrected, "
+                    "and record the correct approach as a fact with category "
+                    '"correction" and confidence >= 0.95 when appropriate.'
+                )
+            if reinforcement_detected:
+                reinforcement_hint = (
+                    "IMPORTANT: Positive reinforcement signals were detected in this conversation. "
+                    "The user explicitly confirmed the agent's approach was correct or helpful. "
+                    "Record the confirmed approach, style, or preference as a fact with category "
+                    '"preference" or "behavior" and confidence >= 0.9 when appropriate.'
+                )
+                correction_hint = (correction_hint + "\n" + reinforcement_hint).strip() if correction_hint else reinforcement_hint
+
+            prompt = MEMORY_UPDATE_PROMPT.format(
+                current_memory=json.dumps(current_memory, indent=2),
+                conversation=conversation_text,
+                correction_hint=correction_hint,
+            )
+
+            # Call LLM
+            model = self._get_model()
+            response = model.invoke(prompt)
+            response_text = _extract_text(response.content).strip()
+
+            # Parse response
+            # Remove markdown code blocks if present
+            if response_text.startswith("```"):
+                lines = response_text.split("\n")
+                response_text = "\n".join(lines[1:-1] if lines[-1] == "```" else lines[1:])
+
+            update_data = json.loads(response_text)
+
+            # Apply updates
+            updated_memory = self._apply_updates(current_memory, update_data, thread_id)
+
+            # Strip file-upload mentions from all summaries before saving.
+            # Uploaded files are session-scoped and won't exist in future sessions,
+            # so recording upload events in long-term memory causes the agent to
+            # try (and fail) to locate those files in subsequent conversations.
+            updated_memory = _strip_upload_mentions_from_memory(updated_memory)
+
+            # Save
+            return get_memory_storage().save(updated_memory, agent_name)
+
+        except json.JSONDecodeError as e:
+            logger.warning("Failed to parse LLM response for memory update: %s", e)
+            return False
+        except Exception as e:
+            logger.exception("Memory update failed: %s", e)
+            return False
 
     def _apply_updates(
         self,
@@ -592,7 +455,6 @@ def update_memory_from_conversation(
     agent_name: str | None = None,
     correction_detected: bool = False,
     reinforcement_detected: bool = False,
-    user_id: str | None = None,
 ) -> bool:
     """Convenience function to update memory from a conversation.
 
@@ -602,10 +464,9 @@ def update_memory_from_conversation(
         agent_name: If provided, updates per-agent memory. If None, updates global memory.
         correction_detected: Whether recent turns include an explicit correction signal.
         reinforcement_detected: Whether recent turns include a positive reinforcement signal.
-        user_id: If provided, scopes memory to a specific user.
 
     Returns:
         True if successful, False otherwise.
     """
     updater = MemoryUpdater()
-    return updater.update_memory(messages, thread_id, agent_name, correction_detected, reinforcement_detected, user_id=user_id)
+    return updater.update_memory(messages, thread_id, agent_name, correction_detected, reinforcement_detected)

backend/packages/harness/deerflow/agents/middlewares/clarification_middleware.py

@@ -3,7 +3,6 @@
 import json
 import logging
 from collections.abc import Callable
-from hashlib import sha256
 from typing import override
 
 from langchain.agents import AgentState
@@ -37,13 +36,6 @@ class ClarificationMiddleware(AgentMiddleware[ClarificationMiddlewareState]):
 
     state_schema = ClarificationMiddlewareState
 
-    def _stable_message_id(self, tool_call_id: str, formatted_message: str) -> str:
-        """Build a deterministic message ID so retried clarification calls replace, not append."""
-        if tool_call_id:
-            return f"clarification:{tool_call_id}"
-        digest = sha256(formatted_message.encode("utf-8")).hexdigest()[:16]
-        return f"clarification:{digest}"
-
     def _is_chinese(self, text: str) -> bool:
         """Check if text contains Chinese characters.
 
@@ -139,7 +131,6 @@ class ClarificationMiddleware(AgentMiddleware[ClarificationMiddlewareState]):
         # Create a ToolMessage with the formatted question
         # This will be added to the message history
         tool_message = ToolMessage(
-            id=self._stable_message_id(tool_call_id, formatted_message),
             content=formatted_message,
             tool_call_id=tool_call_id,
             name="ask_clarification",

backend/packages/harness/deerflow/agents/middlewares/dangling_tool_call_middleware.py

@@ -13,7 +13,6 @@ at the correct positions (immediately after each dangling AIMessage), not append
 to the end of the message list as before_model + add_messages reducer would do.
 """
 
-import json
 import logging
 from collections.abc import Awaitable, Callable
 from typing import override
@@ -34,44 +33,6 @@ class DanglingToolCallMiddleware(AgentMiddleware[AgentState]):
     offending AIMessage so the LLM receives a well-formed conversation.
     """
 
-    @staticmethod
-    def _message_tool_calls(msg) -> list[dict]:
-        """Return normalized tool calls from structured fields or raw provider payloads."""
-        tool_calls = getattr(msg, "tool_calls", None) or []
-        if tool_calls:
-            return list(tool_calls)
-
-        raw_tool_calls = (getattr(msg, "additional_kwargs", None) or {}).get("tool_calls") or []
-        normalized: list[dict] = []
-        for raw_tc in raw_tool_calls:
-            if not isinstance(raw_tc, dict):
-                continue
-
-            function = raw_tc.get("function")
-            name = raw_tc.get("name")
-            if not name and isinstance(function, dict):
-                name = function.get("name")
-
-            args = raw_tc.get("args", {})
-            if not args and isinstance(function, dict):
-                raw_args = function.get("arguments")
-                if isinstance(raw_args, str):
-                    try:
-                        parsed_args = json.loads(raw_args)
-                    except (TypeError, ValueError, json.JSONDecodeError):
-                        parsed_args = {}
-                    args = parsed_args if isinstance(parsed_args, dict) else {}
-
-            normalized.append(
-                {
-                    "id": raw_tc.get("id"),
-                    "name": name or "unknown",
-                    "args": args if isinstance(args, dict) else {},
-                }
-            )
-
-        return normalized
-
     def _build_patched_messages(self, messages: list) -> list | None:
         """Return a new message list with patches inserted at the correct positions.
 
@@ -90,7 +51,7 @@ class DanglingToolCallMiddleware(AgentMiddleware[AgentState]):
         for msg in messages:
             if getattr(msg, "type", None) != "ai":
                 continue
-            for tc in self._message_tool_calls(msg):
+            for tc in getattr(msg, "tool_calls", None) or []:
                 tc_id = tc.get("id")
                 if tc_id and tc_id not in existing_tool_msg_ids:
                     needs_patch = True
@@ -109,7 +70,7 @@ class DanglingToolCallMiddleware(AgentMiddleware[AgentState]):
             patched.append(msg)
             if getattr(msg, "type", None) != "ai":
                 continue
-            for tc in self._message_tool_calls(msg):
+            for tc in getattr(msg, "tool_calls", None) or []:
                 tc_id = tc.get("id")
                 if tc_id and tc_id not in existing_tool_msg_ids and tc_id not in patched_ids:
                     patched.append(

backend/packages/harness/deerflow/agents/middlewares/deferred_tool_filter_middleware.py

@@ -16,9 +16,6 @@ from typing import override
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
 from langchain.agents.middleware.types import ModelCallResult, ModelRequest, ModelResponse
-from langchain_core.messages import ToolMessage
-from langgraph.prebuilt.tool_node import ToolCallRequest
-from langgraph.types import Command
 
 logger = logging.getLogger(__name__)
 
@@ -38,7 +35,7 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
         if not registry:
             return request
 
-        deferred_names = registry.deferred_names
+        deferred_names = {e.name for e in registry.entries}
         active_tools = [t for t in request.tools if getattr(t, "name", None) not in deferred_names]
 
         if len(active_tools) < len(request.tools):
@@ -46,28 +43,6 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
 
         return request.override(tools=active_tools)
 
-    def _blocked_tool_message(self, request: ToolCallRequest) -> ToolMessage | None:
-        from deerflow.tools.builtins.tool_search import get_deferred_registry
-
-        registry = get_deferred_registry()
-        if not registry:
-            return None
-
-        tool_name = str(request.tool_call.get("name") or "")
-        if not tool_name:
-            return None
-
-        if not registry.contains(tool_name):
-            return None
-
-        tool_call_id = str(request.tool_call.get("id") or "missing_tool_call_id")
-        return ToolMessage(
-            content=(f"Error: Tool '{tool_name}' is deferred and has not been promoted yet. Call tool_search first to expose and promote this tool's schema, then retry."),
-            tool_call_id=tool_call_id,
-            name=tool_name,
-            status="error",
-        )
-
     @override
     def wrap_model_call(
         self,
@@ -76,17 +51,6 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
     ) -> ModelCallResult:
         return handler(self._filter_tools(request))
 
-    @override
-    def wrap_tool_call(
-        self,
-        request: ToolCallRequest,
-        handler: Callable[[ToolCallRequest], ToolMessage | Command],
-    ) -> ToolMessage | Command:
-        blocked = self._blocked_tool_message(request)
-        if blocked is not None:
-            return blocked
-        return handler(request)
-
     @override
     async def awrap_model_call(
         self,
@@ -94,14 +58,3 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
         handler: Callable[[ModelRequest], Awaitable[ModelResponse]],
     ) -> ModelCallResult:
         return await handler(self._filter_tools(request))
-
-    @override
-    async def awrap_tool_call(
-        self,
-        request: ToolCallRequest,
-        handler: Callable[[ToolCallRequest], Awaitable[ToolMessage | Command]],
-    ) -> ToolMessage | Command:
-        blocked = self._blocked_tool_message(request)
-        if blocked is not None:
-            return blocked
-        return await handler(request)

backend/packages/harness/deerflow/agents/middlewares/llm_error_handling_middleware.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import asyncio
 import logging
-import threading
 import time
 from collections.abc import Awaitable, Callable
 from email.utils import parsedate_to_datetime
@@ -20,8 +19,6 @@ from langchain.agents.middleware.types import (
 from langchain_core.messages import AIMessage
 from langgraph.errors import GraphBubbleUp
 
-from deerflow.config.app_config import AppConfig
-
 logger = logging.getLogger(__name__)
 
 _RETRIABLE_STATUS_CODES = {408, 409, 425, 429, 500, 502, 503, 504}
@@ -70,71 +67,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
     retry_base_delay_ms: int = 1000
     retry_cap_delay_ms: int = 8000
 
-    def __init__(self, *, app_config: AppConfig, **kwargs: Any) -> None:
-        super().__init__(**kwargs)
-
-        self.circuit_failure_threshold = app_config.circuit_breaker.failure_threshold
-        self.circuit_recovery_timeout_sec = app_config.circuit_breaker.recovery_timeout_sec
-
-        # Circuit Breaker state
-        self._circuit_lock = threading.Lock()
-        self._circuit_failure_count = 0
-        self._circuit_open_until = 0.0
-        self._circuit_state = "closed"
-        self._circuit_probe_in_flight = False
-
-    def _check_circuit(self) -> bool:
-        """Returns True if circuit is OPEN (fast fail), False otherwise."""
-        with self._circuit_lock:
-            now = time.time()
-
-            if self._circuit_state == "open":
-                if now < self._circuit_open_until:
-                    return True
-                self._circuit_state = "half_open"
-                self._circuit_probe_in_flight = False
-
-            if self._circuit_state == "half_open":
-                if self._circuit_probe_in_flight:
-                    return True
-                self._circuit_probe_in_flight = True
-                return False
-
-            return False
-
-    def _record_success(self) -> None:
-        with self._circuit_lock:
-            if self._circuit_state != "closed" or self._circuit_failure_count > 0:
-                logger.info("Circuit breaker reset (Closed). LLM service recovered.")
-            self._circuit_failure_count = 0
-            self._circuit_open_until = 0.0
-            self._circuit_state = "closed"
-            self._circuit_probe_in_flight = False
-
-    def _record_failure(self) -> None:
-        with self._circuit_lock:
-            if self._circuit_state == "half_open":
-                self._circuit_open_until = time.time() + self.circuit_recovery_timeout_sec
-                self._circuit_state = "open"
-                self._circuit_probe_in_flight = False
-                logger.error(
-                    "Circuit breaker probe failed (Open). Will probe again after %ds.",
-                    self.circuit_recovery_timeout_sec,
-                )
-                return
-
-            self._circuit_failure_count += 1
-            if self._circuit_failure_count >= self.circuit_failure_threshold:
-                self._circuit_open_until = time.time() + self.circuit_recovery_timeout_sec
-                if self._circuit_state != "open":
-                    self._circuit_state = "open"
-                    self._circuit_probe_in_flight = False
-                    logger.error(
-                        "Circuit breaker tripped (Open). Threshold reached (%d). Will probe after %ds.",
-                        self.circuit_failure_threshold,
-                        self.circuit_recovery_timeout_sec,
-                    )
-
     def _classify_error(self, exc: BaseException) -> tuple[bool, str]:
         detail = _extract_error_detail(exc)
         lowered = detail.lower()
@@ -151,8 +83,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
             "APITimeoutError",
             "APIConnectionError",
             "InternalServerError",
-            "ReadError",  # httpx.ReadError: connection dropped mid-stream
-            "RemoteProtocolError",  # httpx: server closed connection unexpectedly
         }:
             return True, "transient"
         if status_code in _RETRIABLE_STATUS_CODES:
@@ -174,9 +104,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
         reason_text = "provider is busy" if reason == "busy" else "provider request failed temporarily"
         return f"LLM request retry {attempt}/{self.retry_max_attempts}: {reason_text}. Retrying in {seconds}s."
 
-    def _build_circuit_breaker_message(self) -> str:
-        return "The configured LLM provider is currently unavailable due to continuous failures. Circuit breaker is engaged to protect the system. Please wait a moment before trying again."
-
     def _build_user_message(self, exc: BaseException, reason: str) -> str:
         detail = _extract_error_detail(exc)
         if reason == "quota":
@@ -211,20 +138,12 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
         request: ModelRequest,
         handler: Callable[[ModelRequest], ModelResponse],
     ) -> ModelCallResult:
-        if self._check_circuit():
-            return AIMessage(content=self._build_circuit_breaker_message())
-
         attempt = 1
         while True:
             try:
-                response = handler(request)
-                self._record_success()
-                return response
+                return handler(request)
             except GraphBubbleUp:
                 # Preserve LangGraph control-flow signals (interrupt/pause/resume).
-                with self._circuit_lock:
-                    if self._circuit_state == "half_open":
-                        self._circuit_probe_in_flight = False
                 raise
             except Exception as exc:
                 retriable, reason = self._classify_error(exc)
@@ -247,8 +166,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
                     _extract_error_detail(exc),
                     exc_info=exc,
                 )
-                if retriable:
-                    self._record_failure()
                 return AIMessage(content=self._build_user_message(exc, reason))
 
     @override
@@ -257,20 +174,12 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
         request: ModelRequest,
         handler: Callable[[ModelRequest], Awaitable[ModelResponse]],
     ) -> ModelCallResult:
-        if self._check_circuit():
-            return AIMessage(content=self._build_circuit_breaker_message())
-
         attempt = 1
         while True:
             try:
-                response = await handler(request)
-                self._record_success()
-                return response
+                return await handler(request)
             except GraphBubbleUp:
                 # Preserve LangGraph control-flow signals (interrupt/pause/resume).
-                with self._circuit_lock:
-                    if self._circuit_state == "half_open":
-                        self._circuit_probe_in_flight = False
                 raise
             except Exception as exc:
                 retriable, reason = self._classify_error(exc)
@@ -293,8 +202,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
                     _extract_error_detail(exc),
                     exc_info=exc,
                 )
-                if retriable:
-                    self._record_failure()
                 return AIMessage(content=self._build_user_message(exc, reason))
 
 

backend/packages/harness/deerflow/agents/middlewares/loop_detection_middleware.py

@@ -17,7 +17,6 @@ import json
 import logging
 import threading
 from collections import OrderedDict, defaultdict
-from copy import deepcopy
 from typing import override
 
 from langchain.agents import AgentState
@@ -32,8 +31,6 @@ _DEFAULT_WARN_THRESHOLD = 3  # inject warning after 3 identical calls
 _DEFAULT_HARD_LIMIT = 5  # force-stop after 5 identical calls
 _DEFAULT_WINDOW_SIZE = 20  # track last N tool calls
 _DEFAULT_MAX_TRACKED_THREADS = 100  # LRU eviction limit
-_DEFAULT_TOOL_FREQ_WARN = 30  # warn after 30 calls to the same tool type
-_DEFAULT_TOOL_FREQ_HARD_LIMIT = 50  # force-stop after 50 calls to the same tool type
 
 
 def _normalize_tool_call_args(raw_args: object) -> tuple[dict, str | None]:
@@ -128,14 +125,8 @@ def _hash_tool_calls(tool_calls: list[dict]) -> str:
 
 _WARNING_MSG = "[LOOP DETECTED] You are repeating the same tool calls. Stop calling tools and produce your final answer now. If you cannot complete the task, summarize what you accomplished so far."
 
-_TOOL_FREQ_WARNING_MSG = (
-    "[LOOP DETECTED] You have called {tool_name} {count} times without producing a final answer. Stop calling tools and produce your final answer now. If you cannot complete the task, summarize what you accomplished so far."
-)
-
 _HARD_STOP_MSG = "[FORCED STOP] Repeated tool calls exceeded the safety limit. Producing final answer with results collected so far."
 
-_TOOL_FREQ_HARD_STOP_MSG = "[FORCED STOP] Tool {tool_name} called {count} times — exceeded the per-tool safety limit. Producing final answer with results collected so far."
-
 
 class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
     """Detects and breaks repetitive tool call loops.
@@ -149,12 +140,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             Default: 20.
         max_tracked_threads: Maximum number of threads to track before
             evicting the least recently used. Default: 100.
-        tool_freq_warn: Number of calls to the same tool *type* (regardless
-            of arguments) before injecting a frequency warning. Catches
-            cross-file read loops that hash-based detection misses.
-            Default: 30.
-        tool_freq_hard_limit: Number of calls to the same tool type before
-            forcing a stop. Default: 50.
     """
 
     def __init__(
@@ -163,23 +148,16 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         hard_limit: int = _DEFAULT_HARD_LIMIT,
         window_size: int = _DEFAULT_WINDOW_SIZE,
         max_tracked_threads: int = _DEFAULT_MAX_TRACKED_THREADS,
-        tool_freq_warn: int = _DEFAULT_TOOL_FREQ_WARN,
-        tool_freq_hard_limit: int = _DEFAULT_TOOL_FREQ_HARD_LIMIT,
     ):
         super().__init__()
         self.warn_threshold = warn_threshold
         self.hard_limit = hard_limit
         self.window_size = window_size
         self.max_tracked_threads = max_tracked_threads
-        self.tool_freq_warn = tool_freq_warn
-        self.tool_freq_hard_limit = tool_freq_hard_limit
         self._lock = threading.Lock()
         # Per-thread tracking using OrderedDict for LRU eviction
         self._history: OrderedDict[str, list[str]] = OrderedDict()
         self._warned: dict[str, set[str]] = defaultdict(set)
-        # Per-thread, per-tool-type cumulative call counts
-        self._tool_freq: dict[str, dict[str, int]] = defaultdict(lambda: defaultdict(int))
-        self._tool_freq_warned: dict[str, set[str]] = defaultdict(set)
 
     def _get_thread_id(self, runtime: Runtime) -> str:
         """Extract thread_id from runtime context for per-thread tracking."""
@@ -196,19 +174,11 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         while len(self._history) > self.max_tracked_threads:
             evicted_id, _ = self._history.popitem(last=False)
             self._warned.pop(evicted_id, None)
-            self._tool_freq.pop(evicted_id, None)
-            self._tool_freq_warned.pop(evicted_id, None)
             logger.debug("Evicted loop tracking for thread %s (LRU)", evicted_id)
 
     def _track_and_check(self, state: AgentState, runtime: Runtime) -> tuple[str | None, bool]:
         """Track tool calls and check for loops.
 
-        Two detection layers:
-          1. **Hash-based** (existing): catches identical tool call sets.
-          2. **Frequency-based** (new): catches the same *tool type* being
-             called many times with varying arguments (e.g. ``read_file``
-             on 40 different files).
-
         Returns:
             (warning_message_or_none, should_hard_stop)
         """
@@ -243,7 +213,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             count = history.count(call_hash)
             tool_names = [tc.get("name", "?") for tc in tool_calls]
 
-            # --- Layer 1: hash-based (identical call sets) ---
             if count >= self.hard_limit:
                 logger.error(
                     "Loop hard limit reached — forcing stop",
@@ -270,40 +239,8 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
                         },
                     )
                     return _WARNING_MSG, False
-
-            # --- Layer 2: per-tool-type frequency ---
-            freq = self._tool_freq[thread_id]
-            for tc in tool_calls:
-                name = tc.get("name", "")
-                if not name:
-                    continue
-                freq[name] += 1
-                tc_count = freq[name]
-
-                if tc_count >= self.tool_freq_hard_limit:
-                    logger.error(
-                        "Tool frequency hard limit reached — forcing stop",
-                        extra={
-                            "thread_id": thread_id,
-                            "tool_name": name,
-                            "count": tc_count,
-                        },
-                    )
-                    return _TOOL_FREQ_HARD_STOP_MSG.format(tool_name=name, count=tc_count), True
-
-                if tc_count >= self.tool_freq_warn:
-                    warned = self._tool_freq_warned[thread_id]
-                    if name not in warned:
-                        warned.add(name)
-                        logger.warning(
-                            "Tool frequency warning — too many calls to same tool type",
-                            extra={
-                                "thread_id": thread_id,
-                                "tool_name": name,
-                                "count": tc_count,
-                            },
-                        )
-                        return _TOOL_FREQ_WARNING_MSG.format(tool_name=name, count=tc_count), False
+                # Warning already injected for this hash — suppress
+                return None, False
 
         return None, False
 
@@ -324,26 +261,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         # Fallback: coerce unexpected types to str to avoid TypeError
         return str(content) + f"\n\n{text}"
 
-    @staticmethod
-    def _build_hard_stop_update(last_msg, content: str | list) -> dict:
-        """Clear tool-call metadata so forced-stop messages serialize as plain assistant text."""
-        update = {
-            "tool_calls": [],
-            "content": content,
-        }
-
-        additional_kwargs = dict(getattr(last_msg, "additional_kwargs", {}) or {})
-        for key in ("tool_calls", "function_call"):
-            additional_kwargs.pop(key, None)
-        update["additional_kwargs"] = additional_kwargs
-
-        response_metadata = deepcopy(getattr(last_msg, "response_metadata", {}) or {})
-        if response_metadata.get("finish_reason") == "tool_calls":
-            response_metadata["finish_reason"] = "stop"
-        update["response_metadata"] = response_metadata
-
-        return update
-
     def _apply(self, state: AgentState, runtime: Runtime) -> dict | None:
         warning, hard_stop = self._track_and_check(state, runtime)
 
@@ -351,8 +268,12 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             # Strip tool_calls from the last AIMessage to force text output
             messages = state.get("messages", [])
             last_msg = messages[-1]
-            content = self._append_text(last_msg.content, warning or _HARD_STOP_MSG)
-            stripped_msg = last_msg.model_copy(update=self._build_hard_stop_update(last_msg, content))
+            stripped_msg = last_msg.model_copy(
+                update={
+                    "tool_calls": [],
+                    "content": self._append_text(last_msg.content, _HARD_STOP_MSG),
+                }
+            )
             return {"messages": [stripped_msg]}
 
         if warning:
@@ -362,7 +283,7 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             # the conversation; injecting one mid-conversation crashes
             # langchain_anthropic's _format_messages(). HumanMessage works
             # with all providers. See #1299.
-            return {"messages": [HumanMessage(content=warning, name="loop_warning")]}
+            return {"messages": [HumanMessage(content=warning)]}
 
         return None
 
@@ -380,10 +301,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             if thread_id:
                 self._history.pop(thread_id, None)
                 self._warned.pop(thread_id, None)
-                self._tool_freq.pop(thread_id, None)
-                self._tool_freq_warned.pop(thread_id, None)
             else:
                 self._history.clear()
                 self._warned.clear()
-                self._tool_freq.clear()
-                self._tool_freq_warned.clear()

backend/packages/harness/deerflow/agents/middlewares/memory_middleware.py

@@ -1,23 +1,50 @@
 """Middleware for memory mechanism."""
 
 import logging
-from typing import TYPE_CHECKING, override
+import re
+from typing import Any, override
 
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
 from langgraph.config import get_config
 from langgraph.runtime import Runtime
 
-from deerflow.agents.memory.message_processing import detect_correction, detect_reinforcement, filter_messages_for_memory
 from deerflow.agents.memory.queue import get_memory_queue
 from deerflow.config.memory_config import get_memory_config
-from deerflow.runtime.user_context import get_effective_user_id
-
-if TYPE_CHECKING:
-    from deerflow.config.memory_config import MemoryConfig
 
 logger = logging.getLogger(__name__)
 
+_UPLOAD_BLOCK_RE = re.compile(r"<uploaded_files>[\s\S]*?</uploaded_files>\n*", re.IGNORECASE)
+_CORRECTION_PATTERNS = (
+    re.compile(r"\bthat(?:'s| is) (?:wrong|incorrect)\b", re.IGNORECASE),
+    re.compile(r"\byou misunderstood\b", re.IGNORECASE),
+    re.compile(r"\btry again\b", re.IGNORECASE),
+    re.compile(r"\bredo\b", re.IGNORECASE),
+    re.compile(r"不对"),
+    re.compile(r"你理解错了"),
+    re.compile(r"你理解有误"),
+    re.compile(r"重试"),
+    re.compile(r"重新来"),
+    re.compile(r"换一种"),
+    re.compile(r"改用"),
+)
+
+_REINFORCEMENT_PATTERNS = (
+    re.compile(r"\byes[,.]?\s+(?:exactly|perfect|that(?:'s| is) (?:right|correct|it))\b", re.IGNORECASE),
+    re.compile(r"\bperfect(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"\bexactly\s+(?:right|correct)\b", re.IGNORECASE),
+    re.compile(r"\bthat(?:'s| is)\s+(?:exactly\s+)?(?:right|correct|what i (?:wanted|needed|meant))\b", re.IGNORECASE),
+    re.compile(r"\bkeep\s+(?:doing\s+)?that\b", re.IGNORECASE),
+    re.compile(r"\bjust\s+(?:like\s+)?(?:that|this)\b", re.IGNORECASE),
+    re.compile(r"\bthis is (?:great|helpful)\b(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"\bthis is what i wanted\b(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"对[，,]?\s*就是这样(?:[。！？!?.]|$)"),
+    re.compile(r"完全正确(?:[。！？!?.]|$)"),
+    re.compile(r"(?:对[，,]?\s*)?就是这个意思(?:[。！？!?.]|$)"),
+    re.compile(r"正是我想要的(?:[。！？!?.]|$)"),
+    re.compile(r"继续保持(?:[。！？!?.]|$)"),
+)
+
 
 class MemoryMiddlewareState(AgentState):
     """Compatible with the `ThreadState` schema."""
@@ -25,6 +52,125 @@ class MemoryMiddlewareState(AgentState):
     pass
 
 
+def _extract_message_text(message: Any) -> str:
+    """Extract plain text from message content for filtering and signal detection."""
+    content = getattr(message, "content", "")
+    if isinstance(content, list):
+        text_parts: list[str] = []
+        for part in content:
+            if isinstance(part, str):
+                text_parts.append(part)
+            elif isinstance(part, dict):
+                text_val = part.get("text")
+                if isinstance(text_val, str):
+                    text_parts.append(text_val)
+        return " ".join(text_parts)
+    return str(content)
+
+
+def _filter_messages_for_memory(messages: list[Any]) -> list[Any]:
+    """Filter messages to keep only user inputs and final assistant responses.
+
+    This filters out:
+    - Tool messages (intermediate tool call results)
+    - AI messages with tool_calls (intermediate steps, not final responses)
+    - The <uploaded_files> block injected by UploadsMiddleware into human messages
+      (file paths are session-scoped and must not persist in long-term memory).
+      The user's actual question is preserved; only turns whose content is entirely
+      the upload block (nothing remains after stripping) are dropped along with
+      their paired assistant response.
+
+    Only keeps:
+    - Human messages (with the ephemeral upload block removed)
+    - AI messages without tool_calls (final assistant responses), unless the
+      paired human turn was upload-only and had no real user text.
+
+    Args:
+        messages: List of all conversation messages.
+
+    Returns:
+        Filtered list containing only user inputs and final assistant responses.
+    """
+    filtered = []
+    skip_next_ai = False
+    for msg in messages:
+        msg_type = getattr(msg, "type", None)
+
+        if msg_type == "human":
+            content_str = _extract_message_text(msg)
+            if "<uploaded_files>" in content_str:
+                # Strip the ephemeral upload block; keep the user's real question.
+                stripped = _UPLOAD_BLOCK_RE.sub("", content_str).strip()
+                if not stripped:
+                    # Nothing left — the entire turn was upload bookkeeping;
+                    # skip it and the paired assistant response.
+                    skip_next_ai = True
+                    continue
+                # Rebuild the message with cleaned content so the user's question
+                # is still available for memory summarisation.
+                from copy import copy
+
+                clean_msg = copy(msg)
+                clean_msg.content = stripped
+                filtered.append(clean_msg)
+                skip_next_ai = False
+            else:
+                filtered.append(msg)
+                skip_next_ai = False
+        elif msg_type == "ai":
+            tool_calls = getattr(msg, "tool_calls", None)
+            if not tool_calls:
+                if skip_next_ai:
+                    skip_next_ai = False
+                    continue
+                filtered.append(msg)
+        # Skip tool messages and AI messages with tool_calls
+
+    return filtered
+
+
+def detect_correction(messages: list[Any]) -> bool:
+    """Detect explicit user corrections in recent conversation turns.
+
+    The queue keeps only one pending context per thread, so callers pass the
+    latest filtered message list. Checking only recent user turns keeps signal
+    detection conservative while avoiding stale corrections from long histories.
+    """
+    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
+
+    for msg in recent_user_msgs:
+        content = _extract_message_text(msg).strip()
+        if not content:
+            continue
+        if any(pattern.search(content) for pattern in _CORRECTION_PATTERNS):
+            return True
+
+    return False
+
+
+def detect_reinforcement(messages: list[Any]) -> bool:
+    """Detect explicit positive reinforcement signals in recent conversation turns.
+
+    Complements detect_correction() by identifying when the user confirms the
+    agent's approach was correct. This allows the memory system to record what
+    worked well, not just what went wrong.
+
+    The queue keeps only one pending context per thread, so callers pass the
+    latest filtered message list. Checking only recent user turns keeps signal
+    detection conservative while avoiding stale signals from long histories.
+    """
+    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
+
+    for msg in recent_user_msgs:
+        content = _extract_message_text(msg).strip()
+        if not content:
+            continue
+        if any(pattern.search(content) for pattern in _REINFORCEMENT_PATTERNS):
+            return True
+
+    return False
+
+
 class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
     """Middleware that queues conversation for memory update after agent execution.
 
@@ -37,17 +183,14 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
 
     state_schema = MemoryMiddlewareState
 
-    def __init__(self, agent_name: str | None = None, *, memory_config: "MemoryConfig | None" = None):
+    def __init__(self, agent_name: str | None = None):
         """Initialize the MemoryMiddleware.
 
         Args:
             agent_name: If provided, memory is stored per-agent. If None, uses global memory.
-            memory_config: Explicit memory config. When omitted, legacy global
-                config fallback is used.
         """
         super().__init__()
         self._agent_name = agent_name
-        self._memory_config = memory_config
 
     @override
     def after_agent(self, state: MemoryMiddlewareState, runtime: Runtime) -> dict | None:
@@ -60,7 +203,7 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
         Returns:
             None (no state changes needed from this middleware).
         """
-        config = self._memory_config or get_memory_config()
+        config = get_memory_config()
         if not config.enabled:
             return None
 
@@ -80,7 +223,7 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
             return None
 
         # Filter to only keep user inputs and final assistant responses
-        filtered_messages = filter_messages_for_memory(messages)
+        filtered_messages = _filter_messages_for_memory(messages)
 
         # Only queue if there's meaningful conversation
         # At minimum need one user message and one assistant response
@@ -93,16 +236,11 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
         # Queue the filtered conversation for memory update
         correction_detected = detect_correction(filtered_messages)
         reinforcement_detected = not correction_detected and detect_reinforcement(filtered_messages)
-        # Capture user_id at enqueue time while the request context is still alive.
-        # threading.Timer fires on a different thread where ContextVar values are not
-        # propagated, so we must store user_id explicitly in ConversationContext.
-        user_id = get_effective_user_id()
         queue = get_memory_queue()
         queue.add(
             thread_id=thread_id,
             messages=filtered_messages,
             agent_name=self._agent_name,
-            user_id=user_id,
             correction_detected=correction_detected,
             reinforcement_detected=reinforcement_detected,
         )

backend/packages/harness/deerflow/agents/middlewares/summarization_middleware.py

@@ -1,354 +0,0 @@
-"""Summarization middleware extensions for DeerFlow."""
-
-from __future__ import annotations
-
-import logging
-from collections.abc import Collection
-from dataclasses import dataclass
-from typing import Any, Protocol, override, runtime_checkable
-
-from langchain.agents import AgentState
-from langchain.agents.middleware import SummarizationMiddleware
-from langchain_core.messages import AIMessage, AnyMessage, HumanMessage, RemoveMessage, ToolMessage
-from langgraph.config import get_config
-from langgraph.graph.message import REMOVE_ALL_MESSAGES
-from langgraph.runtime import Runtime
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass(frozen=True)
-class SummarizationEvent:
-    """Context emitted before conversation history is summarized away."""
-
-    messages_to_summarize: tuple[AnyMessage, ...]
-    preserved_messages: tuple[AnyMessage, ...]
-    thread_id: str | None
-    agent_name: str | None
-    runtime: Runtime
-
-
-@runtime_checkable
-class BeforeSummarizationHook(Protocol):
-    """Hook invoked before summarization removes messages from state."""
-
-    def __call__(self, event: SummarizationEvent) -> None: ...
-
-
-def _resolve_thread_id(runtime: Runtime) -> str | None:
-    """Resolve the current thread ID from runtime context or LangGraph config."""
-    thread_id = runtime.context.get("thread_id") if runtime.context else None
-    if thread_id is None:
-        try:
-            config_data = get_config()
-        except RuntimeError:
-            return None
-        thread_id = config_data.get("configurable", {}).get("thread_id")
-    return thread_id
-
-
-def _resolve_agent_name(runtime: Runtime) -> str | None:
-    """Resolve the current agent name from runtime context or LangGraph config."""
-    agent_name = runtime.context.get("agent_name") if runtime.context else None
-    if agent_name is None:
-        try:
-            config_data = get_config()
-        except RuntimeError:
-            return None
-        agent_name = config_data.get("configurable", {}).get("agent_name")
-    return agent_name
-
-
-def _tool_call_path(tool_call: dict[str, Any]) -> str | None:
-    """Best-effort extraction of a file path argument from a read_file-like tool call."""
-    args = tool_call.get("args") or {}
-    if not isinstance(args, dict):
-        return None
-    for key in ("path", "file_path", "filepath"):
-        value = args.get(key)
-        if isinstance(value, str) and value:
-            return value
-    return None
-
-
-def _clone_ai_message(
-    message: AIMessage,
-    tool_calls: list[dict[str, Any]],
-    *,
-    content: Any | None = None,
-) -> AIMessage:
-    """Clone an AIMessage while replacing its tool_calls list and optional content."""
-    update: dict[str, Any] = {"tool_calls": tool_calls}
-    if content is not None:
-        update["content"] = content
-    return message.model_copy(update=update)
-
-
-@dataclass
-class _SkillBundle:
-    """Skill-related tool calls and tool results associated with one AIMessage."""
-
-    ai_index: int
-    skill_tool_indices: tuple[int, ...]
-    skill_tool_call_ids: frozenset[str]
-    skill_tool_tokens: int
-    skill_key: str
-
-
-class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
-    """Summarization middleware with pre-compression hook dispatch and skill rescue."""
-
-    def __init__(
-        self,
-        *args,
-        skills_container_path: str | None = None,
-        skill_file_read_tool_names: Collection[str] | None = None,
-        before_summarization: list[BeforeSummarizationHook] | None = None,
-        preserve_recent_skill_count: int = 5,
-        preserve_recent_skill_tokens: int = 25_000,
-        preserve_recent_skill_tokens_per_skill: int = 5_000,
-        **kwargs,
-    ) -> None:
-        super().__init__(*args, **kwargs)
-        self._skills_container_path = skills_container_path or "/mnt/skills"
-        self._skill_file_read_tool_names = frozenset(skill_file_read_tool_names or {"read_file", "read", "view", "cat"})
-        self._before_summarization_hooks = before_summarization or []
-        self._preserve_recent_skill_count = max(0, preserve_recent_skill_count)
-        self._preserve_recent_skill_tokens = max(0, preserve_recent_skill_tokens)
-        self._preserve_recent_skill_tokens_per_skill = max(0, preserve_recent_skill_tokens_per_skill)
-
-    def before_model(self, state: AgentState, runtime: Runtime) -> dict | None:
-        return self._maybe_summarize(state, runtime)
-
-    async def abefore_model(self, state: AgentState, runtime: Runtime) -> dict | None:
-        return await self._amaybe_summarize(state, runtime)
-
-    def _maybe_summarize(self, state: AgentState, runtime: Runtime) -> dict | None:
-        messages = state["messages"]
-        self._ensure_message_ids(messages)
-
-        total_tokens = self.token_counter(messages)
-        if not self._should_summarize(messages, total_tokens):
-            return None
-
-        cutoff_index = self._determine_cutoff_index(messages)
-        if cutoff_index <= 0:
-            return None
-
-        messages_to_summarize, preserved_messages = self._partition_with_skill_rescue(messages, cutoff_index)
-        self._fire_hooks(messages_to_summarize, preserved_messages, runtime)
-        summary = self._create_summary(messages_to_summarize)
-        new_messages = self._build_new_messages(summary)
-
-        return {
-            "messages": [
-                RemoveMessage(id=REMOVE_ALL_MESSAGES),
-                *new_messages,
-                *preserved_messages,
-            ]
-        }
-
-    async def _amaybe_summarize(self, state: AgentState, runtime: Runtime) -> dict | None:
-        messages = state["messages"]
-        self._ensure_message_ids(messages)
-
-        total_tokens = self.token_counter(messages)
-        if not self._should_summarize(messages, total_tokens):
-            return None
-
-        cutoff_index = self._determine_cutoff_index(messages)
-        if cutoff_index <= 0:
-            return None
-
-        messages_to_summarize, preserved_messages = self._partition_with_skill_rescue(messages, cutoff_index)
-        self._fire_hooks(messages_to_summarize, preserved_messages, runtime)
-        summary = await self._acreate_summary(messages_to_summarize)
-        new_messages = self._build_new_messages(summary)
-
-        return {
-            "messages": [
-                RemoveMessage(id=REMOVE_ALL_MESSAGES),
-                *new_messages,
-                *preserved_messages,
-            ]
-        }
-
-    @override
-    def _build_new_messages(self, summary: str) -> list[HumanMessage]:
-        """Override the base implementation to let the human message with the special name 'summary'.
-        And this message will be ignored to display in the frontend, but still can be used as context for the model.
-        """
-        return [HumanMessage(content=f"Here is a summary of the conversation to date:\n\n{summary}", name="summary")]
-
-    def _partition_with_skill_rescue(
-        self,
-        messages: list[AnyMessage],
-        cutoff_index: int,
-    ) -> tuple[list[AnyMessage], list[AnyMessage]]:
-        """Partition like the parent, then rescue recently-loaded skill bundles."""
-        to_summarize, preserved = self._partition_messages(messages, cutoff_index)
-
-        if self._preserve_recent_skill_count == 0 or self._preserve_recent_skill_tokens == 0 or not to_summarize:
-            return to_summarize, preserved
-
-        try:
-            bundles = self._find_skill_bundles(to_summarize, self._skills_container_path)
-        except Exception:
-            logger.exception("Skill-preserving summarization rescue failed; falling back to default partition")
-            return to_summarize, preserved
-
-        if not bundles:
-            return to_summarize, preserved
-
-        rescue_bundles = self._select_bundles_to_rescue(bundles)
-        if not rescue_bundles:
-            return to_summarize, preserved
-
-        bundles_by_ai_index = {bundle.ai_index: bundle for bundle in rescue_bundles}
-        rescue_tool_indices = {idx for bundle in rescue_bundles for idx in bundle.skill_tool_indices}
-        rescued: list[AnyMessage] = []
-        remaining: list[AnyMessage] = []
-        for i, msg in enumerate(to_summarize):
-            bundle = bundles_by_ai_index.get(i)
-            if bundle is not None and isinstance(msg, AIMessage):
-                rescued_tool_calls = [tc for tc in msg.tool_calls if tc.get("id") in bundle.skill_tool_call_ids]
-                remaining_tool_calls = [tc for tc in msg.tool_calls if tc.get("id") not in bundle.skill_tool_call_ids]
-
-                if rescued_tool_calls:
-                    rescued.append(_clone_ai_message(msg, rescued_tool_calls, content=""))
-                if remaining_tool_calls or msg.content:
-                    remaining.append(_clone_ai_message(msg, remaining_tool_calls))
-                continue
-
-            if i in rescue_tool_indices:
-                rescued.append(msg)
-                continue
-
-            remaining.append(msg)
-
-        return remaining, rescued + preserved
-
-    def _find_skill_bundles(
-        self,
-        messages: list[AnyMessage],
-        skills_root: str,
-    ) -> list[_SkillBundle]:
-        """Locate AIMessage + paired ToolMessage groups that load skill files."""
-        bundles: list[_SkillBundle] = []
-        n = len(messages)
-        i = 0
-        while i < n:
-            msg = messages[i]
-            if not (isinstance(msg, AIMessage) and msg.tool_calls):
-                i += 1
-                continue
-
-            tool_calls = list(msg.tool_calls)
-            skill_paths_by_id: dict[str, str] = {}
-            for tc in tool_calls:
-                if self._is_skill_tool_call(tc, skills_root):
-                    tc_id = tc.get("id")
-                    path = _tool_call_path(tc)
-                    if tc_id and path:
-                        skill_paths_by_id[tc_id] = path
-
-            if not skill_paths_by_id:
-                i += 1
-                continue
-
-            skill_tool_tokens = 0
-            skill_key_parts: list[str] = []
-            skill_tool_indices: list[int] = []
-            matched_skill_call_ids: set[str] = set()
-
-            j = i + 1
-            while j < n and isinstance(messages[j], ToolMessage):
-                j += 1
-
-            for k in range(i + 1, j):
-                tool_msg = messages[k]
-                if isinstance(tool_msg, ToolMessage) and tool_msg.tool_call_id in skill_paths_by_id:
-                    skill_tool_tokens += self.token_counter([tool_msg])
-                    skill_key_parts.append(skill_paths_by_id[tool_msg.tool_call_id])
-                    skill_tool_indices.append(k)
-                    matched_skill_call_ids.add(tool_msg.tool_call_id)
-
-            if not skill_tool_indices:
-                i = j
-                continue
-
-            bundles.append(
-                _SkillBundle(
-                    ai_index=i,
-                    skill_tool_indices=tuple(skill_tool_indices),
-                    skill_tool_call_ids=frozenset(matched_skill_call_ids),
-                    skill_tool_tokens=skill_tool_tokens,
-                    skill_key="|".join(sorted(skill_key_parts)),
-                )
-            )
-            i = j
-
-        return bundles
-
-    def _select_bundles_to_rescue(self, bundles: list[_SkillBundle]) -> list[_SkillBundle]:
-        """Pick bundles to keep, walking newest-first under count/token budgets."""
-        selected: list[_SkillBundle] = []
-        if not bundles:
-            return selected
-
-        seen_skill_keys: set[str] = set()
-        total_tokens = 0
-        kept = 0
-
-        for bundle in reversed(bundles):
-            if kept >= self._preserve_recent_skill_count:
-                break
-            if bundle.skill_key in seen_skill_keys:
-                continue
-            if bundle.skill_tool_tokens > self._preserve_recent_skill_tokens_per_skill:
-                continue
-            if total_tokens + bundle.skill_tool_tokens > self._preserve_recent_skill_tokens:
-                continue
-
-            selected.append(bundle)
-            total_tokens += bundle.skill_tool_tokens
-            kept += 1
-            seen_skill_keys.add(bundle.skill_key)
-
-        selected.reverse()
-        return selected
-
-    def _is_skill_tool_call(self, tool_call: dict[str, Any], skills_root: str) -> bool:
-        """Return True when ``tool_call`` reads a file under the configured skills root."""
-        name = tool_call.get("name") or ""
-        if name not in self._skill_file_read_tool_names:
-            return False
-        path = _tool_call_path(tool_call)
-        if not path:
-            return False
-        normalized_root = skills_root.rstrip("/")
-        return path == normalized_root or path.startswith(normalized_root + "/")
-
-    def _fire_hooks(
-        self,
-        messages_to_summarize: list[AnyMessage],
-        preserved_messages: list[AnyMessage],
-        runtime: Runtime,
-    ) -> None:
-        if not self._before_summarization_hooks:
-            return
-
-        event = SummarizationEvent(
-            messages_to_summarize=tuple(messages_to_summarize),
-            preserved_messages=tuple(preserved_messages),
-            thread_id=_resolve_thread_id(runtime),
-            agent_name=_resolve_agent_name(runtime),
-            runtime=runtime,
-        )
-
-        for hook in self._before_summarization_hooks:
-            try:
-                hook(event)
-            except Exception:
-                hook_name = getattr(hook, "__name__", None) or type(hook).__name__
-                logger.exception("before_summarization hook %s failed", hook_name)

backend/packages/harness/deerflow/agents/middlewares/thread_data_middleware.py

@@ -1,16 +1,13 @@
 import logging
-from datetime import UTC, datetime
 from typing import NotRequired, override
 
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
-from langchain_core.messages import HumanMessage
 from langgraph.config import get_config
 from langgraph.runtime import Runtime
 
 from deerflow.agents.thread_state import ThreadDataState
 from deerflow.config.paths import Paths, get_paths
-from deerflow.runtime.user_context import get_effective_user_id
 
 logger = logging.getLogger(__name__)
 
@@ -49,34 +46,32 @@ class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
         self._paths = Paths(base_dir) if base_dir else get_paths()
         self._lazy_init = lazy_init
 
-    def _get_thread_paths(self, thread_id: str, user_id: str | None = None) -> dict[str, str]:
+    def _get_thread_paths(self, thread_id: str) -> dict[str, str]:
         """Get the paths for a thread's data directories.
 
         Args:
             thread_id: The thread ID.
-            user_id: Optional user ID for per-user path isolation.
 
         Returns:
             Dictionary with workspace_path, uploads_path, and outputs_path.
         """
         return {
-            "workspace_path": str(self._paths.sandbox_work_dir(thread_id, user_id=user_id)),
-            "uploads_path": str(self._paths.sandbox_uploads_dir(thread_id, user_id=user_id)),
-            "outputs_path": str(self._paths.sandbox_outputs_dir(thread_id, user_id=user_id)),
+            "workspace_path": str(self._paths.sandbox_work_dir(thread_id)),
+            "uploads_path": str(self._paths.sandbox_uploads_dir(thread_id)),
+            "outputs_path": str(self._paths.sandbox_outputs_dir(thread_id)),
         }
 
-    def _create_thread_directories(self, thread_id: str, user_id: str | None = None) -> dict[str, str]:
+    def _create_thread_directories(self, thread_id: str) -> dict[str, str]:
         """Create the thread data directories.
 
         Args:
             thread_id: The thread ID.
-            user_id: Optional user ID for per-user path isolation.
 
         Returns:
             Dictionary with the created directory paths.
         """
-        self._paths.ensure_thread_dirs(thread_id, user_id=user_id)
-        return self._get_thread_paths(thread_id, user_id=user_id)
+        self._paths.ensure_thread_dirs(thread_id)
+        return self._get_thread_paths(thread_id)
 
     @override
     def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime) -> dict | None:
@@ -89,30 +84,16 @@ class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
         if thread_id is None:
             raise ValueError("Thread ID is required in runtime context or config.configurable")
 
-        user_id = get_effective_user_id()
-
         if self._lazy_init:
             # Lazy initialization: only compute paths, don't create directories
-            paths = self._get_thread_paths(thread_id, user_id=user_id)
+            paths = self._get_thread_paths(thread_id)
         else:
             # Eager initialization: create directories immediately
-            paths = self._create_thread_directories(thread_id, user_id=user_id)
+            paths = self._create_thread_directories(thread_id)
             logger.debug("Created thread data directories for thread %s", thread_id)
 
-        messages = list(state.get("messages", []))
-        last_message = messages[-1] if messages else None
-
-        if last_message and isinstance(last_message, HumanMessage):
-            messages[-1] = HumanMessage(
-                content=last_message.content,
-                id=last_message.id,
-                name=last_message.name or "user-input",
-                additional_kwargs={**last_message.additional_kwargs, "run_id": runtime.context.get("run_id"), "timestamp": datetime.now(UTC).isoformat()},
-            )
-
         return {
             "thread_data": {
                 **paths,
-            },
-            "messages": messages,
+            }
         }

backend/packages/harness/deerflow/agents/middlewares/title_middleware.py

@@ -1,8 +1,7 @@
 """Middleware for automatic thread title generation."""
 
 import logging
-import re
-from typing import TYPE_CHECKING, Any, NotRequired, override
+from typing import Any, NotRequired, override
 
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
@@ -12,10 +11,6 @@ from langgraph.runtime import Runtime
 from deerflow.config.title_config import get_title_config
 from deerflow.models import create_chat_model
 
-if TYPE_CHECKING:
-    from deerflow.config.app_config import AppConfig
-    from deerflow.config.title_config import TitleConfig
-
 logger = logging.getLogger(__name__)
 
 
@@ -30,18 +25,6 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
 
     state_schema = TitleMiddlewareState
 
-    def __init__(self, *, app_config: "AppConfig | None" = None, title_config: "TitleConfig | None" = None):
-        super().__init__()
-        self._app_config = app_config
-        self._title_config = title_config
-
-    def _get_title_config(self):
-        if self._title_config is not None:
-            return self._title_config
-        if self._app_config is not None:
-            return self._app_config.title
-        return get_title_config()
-
     def _normalize_content(self, content: object) -> str:
         if isinstance(content, str):
             return content
@@ -63,7 +46,7 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
 
     def _should_generate_title(self, state: TitleMiddlewareState) -> bool:
         """Check if we should generate a title for this thread."""
-        config = self._get_title_config()
+        config = get_title_config()
         if not config.enabled:
             return False
 
@@ -88,14 +71,14 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
 
         Returns (prompt_string, user_msg) so callers can use user_msg as fallback.
         """
-        config = self._get_title_config()
+        config = get_title_config()
         messages = state.get("messages", [])
 
         user_msg_content = next((m.content for m in messages if m.type == "human"), "")
         assistant_msg_content = next((m.content for m in messages if m.type == "ai"), "")
 
         user_msg = self._normalize_content(user_msg_content)
-        assistant_msg = self._strip_think_tags(self._normalize_content(assistant_msg_content))
+        assistant_msg = self._normalize_content(assistant_msg_content)
 
         prompt = config.prompt_template.format(
             max_words=config.max_words,
@@ -104,20 +87,15 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
         )
         return prompt, user_msg
 
-    def _strip_think_tags(self, text: str) -> str:
-        """Remove <think>...</think> blocks emitted by reasoning models (e.g. minimax, DeepSeek-R1)."""
-        return re.sub(r"<think>[\s\S]*?</think>", "", text, flags=re.IGNORECASE).strip()
-
     def _parse_title(self, content: object) -> str:
         """Normalize model output into a clean title string."""
-        config = self._get_title_config()
+        config = get_title_config()
         title_content = self._normalize_content(content)
-        title_content = self._strip_think_tags(title_content)
         title = title_content.strip().strip('"').strip("'")
         return title[: config.max_chars] if len(title) > config.max_chars else title
 
     def _fallback_title(self, user_msg: str) -> str:
-        config = self._get_title_config()
+        config = get_title_config()
         fallback_chars = min(config.max_chars, 50)
         if len(user_msg) > fallback_chars:
             return user_msg[:fallback_chars].rstrip() + "..."
@@ -134,7 +112,6 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
         except Exception:
             parent = {}
         config = {**parent}
-        config["run_name"] = "title_agent"
         config["tags"] = [*(config.get("tags") or []), "middleware:title"]
         return config
 
@@ -151,17 +128,14 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
         if not self._should_generate_title(state):
             return None
 
-        config = self._get_title_config()
+        config = get_title_config()
         prompt, user_msg = self._build_title_prompt(state)
 
         try:
-            model_kwargs = {"thinking_enabled": False}
-            if self._app_config is not None:
-                model_kwargs["app_config"] = self._app_config
             if config.model_name:
-                model = create_chat_model(name=config.model_name, **model_kwargs)
+                model = create_chat_model(name=config.model_name, thinking_enabled=False)
             else:
-                model = create_chat_model(**model_kwargs)
+                model = create_chat_model(thinking_enabled=False)
             response = await model.ainvoke(prompt, config=self._get_runnable_config())
             title = self._parse_title(response.content)
             if title:

backend/packages/harness/deerflow/agents/middlewares/todo_middleware.py

@@ -1,14 +1,9 @@
-"""Middleware that extends TodoListMiddleware with context-loss detection and premature-exit prevention.
+"""Middleware that extends TodoListMiddleware with context-loss detection.
 
 When the message history is truncated (e.g., by SummarizationMiddleware), the
 original `write_todos` tool call and its ToolMessage can be scrolled out of the
 active context window. This middleware detects that situation and injects a
 reminder message so the model still knows about the outstanding todo list.
-
-Additionally, this middleware prevents the agent from exiting the loop while
-there are still incomplete todo items. When the model produces a final response
-(no tool calls) but todos are not yet complete, the middleware injects a reminder
-and jumps back to the model node to force continued engagement.
 """
 
 from __future__ import annotations
@@ -17,7 +12,6 @@ from typing import Any, override
 
 from langchain.agents.middleware import TodoListMiddleware
 from langchain.agents.middleware.todo import PlanningState, Todo
-from langchain.agents.middleware.types import hook_config
 from langchain_core.messages import AIMessage, HumanMessage
 from langgraph.runtime import Runtime
 
@@ -40,11 +34,6 @@ def _reminder_in_messages(messages: list[Any]) -> bool:
     return False
 
 
-def _completion_reminder_count(messages: list[Any]) -> int:
-    """Return the number of todo_completion_reminder HumanMessages in *messages*."""
-    return sum(1 for msg in messages if isinstance(msg, HumanMessage) and getattr(msg, "name", None) == "todo_completion_reminder")
-
-
 def _format_todos(todos: list[Todo]) -> str:
     """Format a list of Todo items into a human-readable string."""
     lines: list[str] = []
@@ -68,7 +57,7 @@ class TodoMiddleware(TodoListMiddleware):
     def before_model(
         self,
         state: PlanningState,
-        runtime: Runtime,
+        runtime: Runtime,  # noqa: ARG002
     ) -> dict[str, Any] | None:
         """Inject a todo-list reminder when write_todos has left the context window."""
         todos: list[Todo] = state.get("todos") or []  # type: ignore[assignment]
@@ -109,71 +98,3 @@ class TodoMiddleware(TodoListMiddleware):
     ) -> dict[str, Any] | None:
         """Async version of before_model."""
         return self.before_model(state, runtime)
-
-    # Maximum number of completion reminders before allowing the agent to exit.
-    # This prevents infinite loops when the agent cannot make further progress.
-    _MAX_COMPLETION_REMINDERS = 2
-
-    @hook_config(can_jump_to=["model"])
-    @override
-    def after_model(
-        self,
-        state: PlanningState,
-        runtime: Runtime,
-    ) -> dict[str, Any] | None:
-        """Prevent premature agent exit when todo items are still incomplete.
-
-        In addition to the base class check for parallel ``write_todos`` calls,
-        this override intercepts model responses that have no tool calls while
-        there are still incomplete todo items. It injects a reminder
-        ``HumanMessage`` and jumps back to the model node so the agent
-        continues working through the todo list.
-
-        A retry cap of ``_MAX_COMPLETION_REMINDERS`` (default 2) prevents
-        infinite loops when the agent cannot make further progress.
-        """
-        # 1. Preserve base class logic (parallel write_todos detection).
-        base_result = super().after_model(state, runtime)
-        if base_result is not None:
-            return base_result
-
-        # 2. Only intervene when the agent wants to exit (no tool calls).
-        messages = state.get("messages") or []
-        last_ai = next((m for m in reversed(messages) if isinstance(m, AIMessage)), None)
-        if not last_ai or last_ai.tool_calls:
-            return None
-
-        # 3. Allow exit when all todos are completed or there are no todos.
-        todos: list[Todo] = state.get("todos") or []  # type: ignore[assignment]
-        if not todos or all(t.get("status") == "completed" for t in todos):
-            return None
-
-        # 4. Enforce a reminder cap to prevent infinite re-engagement loops.
-        if _completion_reminder_count(messages) >= self._MAX_COMPLETION_REMINDERS:
-            return None
-
-        # 5. Inject a reminder and force the agent back to the model.
-        incomplete = [t for t in todos if t.get("status") != "completed"]
-        incomplete_text = "\n".join(f"- [{t.get('status', 'pending')}] {t.get('content', '')}" for t in incomplete)
-        reminder = HumanMessage(
-            name="todo_completion_reminder",
-            content=(
-                "<system_reminder>\n"
-                "You have incomplete todo items that must be finished before giving your final response:\n\n"
-                f"{incomplete_text}\n\n"
-                "Please continue working on these tasks. Call `write_todos` to mark items as completed "
-                "as you finish them, and only respond when all items are done.\n"
-                "</system_reminder>"
-            ),
-        )
-        return {"jump_to": "model", "messages": [reminder]}
-
-    @override
-    @hook_config(can_jump_to=["model"])
-    async def aafter_model(
-        self,
-        state: PlanningState,
-        runtime: Runtime,
-    ) -> dict[str, Any] | None:
-        """Async version of after_model."""
-        return self.after_model(state, runtime)

backend/packages/harness/deerflow/agents/middlewares/tool_error_handling_middleware.py

@@ -11,8 +11,6 @@ from langgraph.errors import GraphBubbleUp
 from langgraph.prebuilt.tool_node import ToolCallRequest
 from langgraph.types import Command
 
-from deerflow.config.app_config import AppConfig
-
 logger = logging.getLogger(__name__)
 
 _MISSING_TOOL_CALL_ID = "missing_tool_call_id"
@@ -69,7 +67,6 @@ class ToolErrorHandlingMiddleware(AgentMiddleware[AgentState]):
 
 def _build_runtime_middlewares(
     *,
-    app_config: AppConfig,
     include_uploads: bool,
     include_dangling_tool_call_patch: bool,
     lazy_init: bool = True,
@@ -94,10 +91,12 @@ def _build_runtime_middlewares(
 
         middlewares.append(DanglingToolCallMiddleware())
 
-    middlewares.append(LLMErrorHandlingMiddleware(app_config=app_config))
+    middlewares.append(LLMErrorHandlingMiddleware())
 
     # Guardrail middleware (if configured)
-    guardrails_config = app_config.guardrails
+    from deerflow.config.guardrails_config import get_guardrails_config
+
+    guardrails_config = get_guardrails_config()
     if guardrails_config.enabled and guardrails_config.provider:
         import inspect
 
@@ -126,42 +125,19 @@ def _build_runtime_middlewares(
     return middlewares
 
 
-def build_lead_runtime_middlewares(*, app_config: AppConfig, lazy_init: bool = True) -> list[AgentMiddleware]:
+def build_lead_runtime_middlewares(*, lazy_init: bool = True) -> list[AgentMiddleware]:
     """Middlewares shared by lead agent runtime before lead-only middlewares."""
     return _build_runtime_middlewares(
-        app_config=app_config,
         include_uploads=True,
         include_dangling_tool_call_patch=True,
         lazy_init=lazy_init,
     )
 
 
-def build_subagent_runtime_middlewares(
-    *,
-    app_config: AppConfig | None = None,
-    model_name: str | None = None,
-    lazy_init: bool = True,
-) -> list[AgentMiddleware]:
+def build_subagent_runtime_middlewares(*, lazy_init: bool = True) -> list[AgentMiddleware]:
     """Middlewares shared by subagent runtime before subagent-only middlewares."""
-    if app_config is None:
-        from deerflow.config import get_app_config
-
-        app_config = get_app_config()
-
-    middlewares = _build_runtime_middlewares(
-        app_config=app_config,
+    return _build_runtime_middlewares(
         include_uploads=False,
         include_dangling_tool_call_patch=True,
         lazy_init=lazy_init,
     )
-
-    if model_name is None and app_config.models:
-        model_name = app_config.models[0].name
-
-    model_config = app_config.get_model_config(model_name) if model_name else None
-    if model_config is not None and model_config.supports_vision:
-        from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
-
-        middlewares.append(ViewImageMiddleware())
-
-    return middlewares

backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py

@@ -10,7 +10,6 @@ from langchain_core.messages import HumanMessage
 from langgraph.runtime import Runtime
 
 from deerflow.config.paths import Paths, get_paths
-from deerflow.runtime.user_context import get_effective_user_id
 from deerflow.utils.file_conversion import extract_outline
 
 logger = logging.getLogger(__name__)
@@ -222,7 +221,7 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
                 thread_id = get_config().get("configurable", {}).get("thread_id")
             except RuntimeError:
                 pass  # get_config() raises outside a runnable context (e.g. unit tests)
-        uploads_dir = self._paths.sandbox_uploads_dir(thread_id, user_id=get_effective_user_id()) if thread_id else None
+        uploads_dir = self._paths.sandbox_uploads_dir(thread_id) if thread_id else None
 
         # Get newly uploaded files from the current message's additional_kwargs.files
         new_files = self._files_from_kwargs(last_message, uploads_dir) or []
@@ -263,27 +262,22 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
         files_message = self._create_files_message(new_files, historical_files)
 
         # Extract original content - handle both string and list formats
-        original_content = last_message.content
-        if isinstance(original_content, str):
-            # Simple case: string content, just prepend files message
-            updated_content = f"{files_message}\n\n{original_content}"
-        elif isinstance(original_content, list):
-            # Complex case: list content (multimodal), preserve all blocks
-            # Prepend files message as the first text block
-            files_block = {"type": "text", "text": f"{files_message}\n\n"}
-            # Keep all original blocks (including images)
-            updated_content = [files_block, *original_content]
-        else:
-            # Other types, preserve as-is
-            updated_content = original_content
+        original_content = ""
+        if isinstance(last_message.content, str):
+            original_content = last_message.content
+        elif isinstance(last_message.content, list):
+            text_parts = []
+            for block in last_message.content:
+                if isinstance(block, dict) and block.get("type") == "text":
+                    text_parts.append(block.get("text", ""))
+            original_content = "\n".join(text_parts)
 
         # Create new message with combined content.
         # Preserve additional_kwargs (including files metadata) so the frontend
         # can read structured file info from the streamed message.
         updated_message = HumanMessage(
-            content=updated_content,
+            content=f"{files_message}\n\n{original_content}",
             id=last_message.id,
-            name=last_message.name,
             additional_kwargs=last_message.additional_kwargs,
         )
 

backend/packages/harness/deerflow/client.py

@@ -40,8 +40,7 @@ from deerflow.config.app_config import get_app_config, reload_app_config
 from deerflow.config.extensions_config import ExtensionsConfig, SkillStateConfig, get_extensions_config, reload_extensions_config
 from deerflow.config.paths import get_paths
 from deerflow.models import create_chat_model
-from deerflow.runtime.user_context import get_effective_user_id
-from deerflow.skills.storage import get_or_new_skill_storage
+from deerflow.skills.installer import install_skill_from_archive
 from deerflow.uploads.manager import (
     claim_unique_filename,
     delete_file_safe,
@@ -228,29 +227,22 @@ class DeerFlowClient:
         max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
 
         kwargs: dict[str, Any] = {
-            "model": create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=self._app_config),
+            "model": create_chat_model(name=model_name, thinking_enabled=thinking_enabled),
             "tools": self._get_tools(model_name=model_name, subagent_enabled=subagent_enabled),
-            "middleware": _build_middlewares(
-                config,
-                model_name=model_name,
-                agent_name=self._agent_name,
-                custom_middlewares=self._middlewares,
-                app_config=self._app_config,
-            ),
+            "middleware": _build_middlewares(config, model_name=model_name, agent_name=self._agent_name, custom_middlewares=self._middlewares),
             "system_prompt": apply_prompt_template(
                 subagent_enabled=subagent_enabled,
                 max_concurrent_subagents=max_concurrent_subagents,
                 agent_name=self._agent_name,
                 available_skills=self._available_skills,
-                app_config=self._app_config,
             ),
             "state_schema": ThreadState,
         }
         checkpointer = self._checkpointer
         if checkpointer is None:
-            from deerflow.runtime.checkpointer import get_checkpointer
+            from deerflow.agents.checkpointer import get_checkpointer
 
-            checkpointer = get_checkpointer(app_config=self._app_config)
+            checkpointer = get_checkpointer()
         if checkpointer is not None:
             kwargs["checkpointer"] = checkpointer
 
@@ -258,15 +250,12 @@ class DeerFlowClient:
         self._agent_config_key = key
         logger.info("Agent created: agent_name=%s, model=%s, thinking=%s", self._agent_name, model_name, thinking_enabled)
 
-    def _get_tools(self, *, model_name: str | None, subagent_enabled: bool):
+    @staticmethod
+    def _get_tools(*, model_name: str | None, subagent_enabled: bool):
         """Lazy import to avoid circular dependency at module level."""
         from deerflow.tools import get_available_tools
 
-        return get_available_tools(
-            model_name=model_name,
-            subagent_enabled=subagent_enabled,
-            app_config=self._app_config,
-        )
+        return get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled)
 
     @staticmethod
     def _serialize_tool_calls(tool_calls) -> list[dict]:
@@ -385,9 +374,9 @@ class DeerFlowClient:
         """
         checkpointer = self._checkpointer
         if checkpointer is None:
-            from deerflow.runtime.checkpointer.provider import get_checkpointer
+            from deerflow.agents.checkpointer.provider import get_checkpointer
 
-            checkpointer = get_checkpointer(app_config=self._app_config)
+            checkpointer = get_checkpointer()
 
         thread_info_map = {}
 
@@ -440,9 +429,9 @@ class DeerFlowClient:
         """
         checkpointer = self._checkpointer
         if checkpointer is None:
-            from deerflow.runtime.checkpointer.provider import get_checkpointer
+            from deerflow.agents.checkpointer.provider import get_checkpointer
 
-            checkpointer = get_checkpointer(app_config=self._app_config)
+            checkpointer = get_checkpointer()
 
         config = {"configurable": {"thread_id": thread_id}}
         checkpoints = []
@@ -733,10 +722,6 @@ class DeerFlowClient:
             Dict with "models" key containing list of model info dicts,
             matching the Gateway API ``ModelsListResponse`` schema.
         """
-        token_usage_enabled = getattr(getattr(self._app_config, "token_usage", None), "enabled", False)
-        if not isinstance(token_usage_enabled, bool):
-            token_usage_enabled = False
-
         return {
             "models": [
                 {
@@ -748,8 +733,7 @@ class DeerFlowClient:
                     "supports_reasoning_effort": getattr(model, "supports_reasoning_effort", False),
                 }
                 for model in self._app_config.models
-            ],
-            "token_usage": {"enabled": token_usage_enabled},
+            ]
         }
 
     def list_skills(self, enabled_only: bool = False) -> dict:
@@ -762,6 +746,8 @@ class DeerFlowClient:
             Dict with "skills" key containing list of skill info dicts,
             matching the Gateway API ``SkillsListResponse`` schema.
         """
+        from deerflow.skills.loader import load_skills
+
         return {
             "skills": [
                 {
@@ -771,7 +757,7 @@ class DeerFlowClient:
                     "category": s.category,
                     "enabled": s.enabled,
                 }
-                for s in get_or_new_skill_storage().load_skills(enabled_only=enabled_only)
+                for s in load_skills(enabled_only=enabled_only)
             ]
         }
 
@@ -783,19 +769,19 @@ class DeerFlowClient:
         """
         from deerflow.agents.memory.updater import get_memory_data
 
-        return get_memory_data(user_id=get_effective_user_id())
+        return get_memory_data()
 
     def export_memory(self) -> dict:
         """Export current memory data for backup or transfer."""
         from deerflow.agents.memory.updater import get_memory_data
 
-        return get_memory_data(user_id=get_effective_user_id())
+        return get_memory_data()
 
     def import_memory(self, memory_data: dict) -> dict:
         """Import and persist full memory data."""
         from deerflow.agents.memory.updater import import_memory_data
 
-        return import_memory_data(memory_data, user_id=get_effective_user_id())
+        return import_memory_data(memory_data)
 
     def get_model(self, name: str) -> dict | None:
         """Get a specific model's configuration by name.
@@ -880,9 +866,9 @@ class DeerFlowClient:
         Returns:
             Skill info dict, or None if not found.
         """
-        from deerflow.skills.storage import get_or_new_skill_storage
+        from deerflow.skills.loader import load_skills
 
-        skill = next((s for s in get_or_new_skill_storage().load_skills(enabled_only=False) if s.name == name), None)
+        skill = next((s for s in load_skills(enabled_only=False) if s.name == name), None)
         if skill is None:
             return None
         return {
@@ -907,9 +893,9 @@ class DeerFlowClient:
             ValueError: If the skill is not found.
             OSError: If the config file cannot be written.
         """
-        from deerflow.skills.storage import get_or_new_skill_storage
+        from deerflow.skills.loader import load_skills
 
-        skills = get_or_new_skill_storage().load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         skill = next((s for s in skills if s.name == name), None)
         if skill is None:
             raise ValueError(f"Skill '{name}' not found")
@@ -932,7 +918,7 @@ class DeerFlowClient:
         self._agent_config_key = None
         reload_extensions_config()
 
-        updated = next((s for s in get_or_new_skill_storage().load_skills(enabled_only=False) if s.name == name), None)
+        updated = next((s for s in load_skills(enabled_only=False) if s.name == name), None)
         if updated is None:
             raise RuntimeError(f"Skill '{name}' disappeared after update")
         return {
@@ -956,7 +942,7 @@ class DeerFlowClient:
             FileNotFoundError: If the file does not exist.
             ValueError: If the file is invalid.
         """
-        return get_or_new_skill_storage().install_skill_from_archive(skill_path)
+        return install_skill_from_archive(skill_path)
 
     # ------------------------------------------------------------------
     # Public API — memory management
@@ -970,13 +956,13 @@ class DeerFlowClient:
         """
         from deerflow.agents.memory.updater import reload_memory_data
 
-        return reload_memory_data(user_id=get_effective_user_id())
+        return reload_memory_data()
 
     def clear_memory(self) -> dict:
         """Clear all persisted memory data."""
         from deerflow.agents.memory.updater import clear_memory_data
 
-        return clear_memory_data(user_id=get_effective_user_id())
+        return clear_memory_data()
 
     def create_memory_fact(self, content: str, category: str = "context", confidence: float = 0.5) -> dict:
         """Create a single fact manually."""
@@ -1193,7 +1179,7 @@ class DeerFlowClient:
             ValueError: If the path is invalid.
         """
         try:
-            actual = get_paths().resolve_virtual_path(thread_id, path, user_id=get_effective_user_id())
+            actual = get_paths().resolve_virtual_path(thread_id, path)
         except ValueError as exc:
             if "traversal" in str(exc):
                 from deerflow.uploads.manager import PathTraversalError

backend/packages/harness/deerflow/community/aio_sandbox/aio_sandbox.py

@@ -48,12 +48,6 @@ class AioSandbox(Sandbox):
             self._home_dir = context.home_dir
         return self._home_dir
 
-    # Default no_change_timeout for exec_command (seconds).  Matches the
-    # client-level timeout so that long-running commands which produce no
-    # output are not prematurely terminated by the sandbox's built-in 120 s
-    # default.
-    _DEFAULT_NO_CHANGE_TIMEOUT = 600
-
     def execute_command(self, command: str) -> str:
         """Execute a shell command in the sandbox.
 
@@ -72,13 +66,13 @@ class AioSandbox(Sandbox):
         """
         with self._lock:
             try:
-                result = self._client.shell.exec_command(command=command, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
+                result = self._client.shell.exec_command(command=command)
                 output = result.data.output if result.data else ""
 
                 if output and _ERROR_OBSERVATION_SIGNATURE in output:
                     logger.warning("ErrorObservation detected in sandbox output, retrying with a fresh session")
                     fresh_id = str(uuid.uuid4())
-                    result = self._client.shell.exec_command(command=command, id=fresh_id, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
+                    result = self._client.shell.exec_command(command=command, id=fresh_id)
                     output = result.data.output if result.data else ""
 
                 return output if output else "(no output)"
@@ -114,7 +108,7 @@ class AioSandbox(Sandbox):
         """
         with self._lock:
             try:
-                result = self._client.shell.exec_command(command=f"find {shlex.quote(path)} -maxdepth {max_depth} -type f -o -type d 2>/dev/null | head -500", no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
+                result = self._client.shell.exec_command(command=f"find {shlex.quote(path)} -maxdepth {max_depth} -type f -o -type d 2>/dev/null | head -500")
                 output = result.data.output if result.data else ""
                 if output:
                     return [line.strip() for line in output.strip().split("\n") if line.strip()]

backend/packages/harness/deerflow/community/aio_sandbox/aio_sandbox_provider.py

@@ -27,7 +27,6 @@ except ImportError:  # pragma: no cover - Windows fallback
 
 from deerflow.config import get_app_config
 from deerflow.config.paths import VIRTUAL_PATH_PREFIX, get_paths
-from deerflow.runtime.user_context import get_effective_user_id
 from deerflow.sandbox.sandbox import Sandbox
 from deerflow.sandbox.sandbox_provider import SandboxProvider
 
@@ -120,16 +119,6 @@ class AioSandboxProvider(SandboxProvider):
         if self._config.get("idle_timeout", DEFAULT_IDLE_TIMEOUT) > 0:
             self._start_idle_checker()
 
-    @property
-    def uses_thread_data_mounts(self) -> bool:
-        """Whether thread workspace/uploads/outputs are visible via mounts.
-
-        Local container backends bind-mount the thread data directories, so files
-        written by the gateway are already visible when the sandbox starts.
-        Remote backends may require explicit file sync.
-        """
-        return isinstance(self._backend, LocalContainerBackend)
-
     # ── Factory methods ──────────────────────────────────────────────────
 
     def _create_backend(self) -> SandboxBackend:
@@ -271,16 +260,15 @@ class AioSandboxProvider(SandboxProvider):
         mounted Docker socket (DooD), the host Docker daemon can resolve the paths.
         """
         paths = get_paths()
-        user_id = get_effective_user_id()
-        paths.ensure_thread_dirs(thread_id, user_id=user_id)
+        paths.ensure_thread_dirs(thread_id)
 
         return [
-            (paths.host_sandbox_work_dir(thread_id, user_id=user_id), f"{VIRTUAL_PATH_PREFIX}/workspace", False),
-            (paths.host_sandbox_uploads_dir(thread_id, user_id=user_id), f"{VIRTUAL_PATH_PREFIX}/uploads", False),
-            (paths.host_sandbox_outputs_dir(thread_id, user_id=user_id), f"{VIRTUAL_PATH_PREFIX}/outputs", False),
+            (paths.host_sandbox_work_dir(thread_id), f"{VIRTUAL_PATH_PREFIX}/workspace", False),
+            (paths.host_sandbox_uploads_dir(thread_id), f"{VIRTUAL_PATH_PREFIX}/uploads", False),
+            (paths.host_sandbox_outputs_dir(thread_id), f"{VIRTUAL_PATH_PREFIX}/outputs", False),
             # ACP workspace: read-only inside the sandbox (lead agent reads results;
             # the ACP subprocess writes from the host side, not from within the container).
-            (paths.host_acp_workspace_dir(thread_id, user_id=user_id), "/mnt/acp-workspace", True),
+            (paths.host_acp_workspace_dir(thread_id), "/mnt/acp-workspace", True),
         ]
 
     @staticmethod
@@ -492,9 +480,8 @@ class AioSandboxProvider(SandboxProvider):
         across multiple processes, preventing container-name conflicts.
         """
         paths = get_paths()
-        user_id = get_effective_user_id()
-        paths.ensure_thread_dirs(thread_id, user_id=user_id)
-        lock_path = paths.thread_dir(thread_id, user_id=user_id) / f"{sandbox_id}.lock"
+        paths.ensure_thread_dirs(thread_id)
+        lock_path = paths.thread_dir(thread_id) / f"{sandbox_id}.lock"
 
         with open(lock_path, "a", encoding="utf-8") as lock_file:
             locked = False

backend/packages/harness/deerflow/community/aio_sandbox/local_backend.py

@@ -9,7 +9,6 @@ from __future__ import annotations
 import json
 import logging
 import os
-import shlex
 import subprocess
 from datetime import datetime
 
@@ -87,88 +86,6 @@ def _format_container_mount(runtime: str, host_path: str, container_path: str, r
     return ["-v", mount_spec]
 
 
-def _redact_container_command_for_log(cmd: list[str]) -> list[str]:
-    """Return a Docker/Container command with environment values redacted."""
-    redacted: list[str] = []
-    redact_next_env = False
-
-    for arg in cmd:
-        if redact_next_env:
-            if "=" in arg:
-                key = arg.split("=", 1)[0]
-                redacted.append(f"{key}=<redacted>" if key else "<redacted>")
-            else:
-                redacted.append(arg)
-            redact_next_env = False
-            continue
-
-        if arg in {"-e", "--env"}:
-            redacted.append(arg)
-            redact_next_env = True
-            continue
-
-        if arg.startswith("--env="):
-            value = arg.removeprefix("--env=")
-            if "=" in value:
-                key = value.split("=", 1)[0]
-                redacted.append(f"--env={key}=<redacted>" if key else "--env=<redacted>")
-            else:
-                redacted.append(arg)
-            continue
-
-        redacted.append(arg)
-
-    return redacted
-
-
-def _format_container_command_for_log(cmd: list[str]) -> str:
-    if os.name == "nt":
-        return subprocess.list2cmdline(cmd)
-    return shlex.join(cmd)
-
-
-def _normalize_sandbox_host(host: str) -> str:
-    return host.strip().lower()
-
-
-def _is_ipv6_loopback_sandbox_host(host: str) -> bool:
-    return _normalize_sandbox_host(host) in {"::1", "[::1]"}
-
-
-def _is_loopback_sandbox_host(host: str) -> bool:
-    return _normalize_sandbox_host(host) in {"", "localhost", "127.0.0.1", "::1", "[::1]"}
-
-
-def _resolve_docker_bind_host(sandbox_host: str | None = None, bind_host: str | None = None) -> str:
-    """Choose the host interface for legacy Docker ``-p`` sandbox publishing.
-
-    Bare-metal/local runs talk to sandboxes through localhost and should not
-    expose the sandbox HTTP API on every host interface.  Docker-outside-of-
-    Docker deployments commonly use ``host.docker.internal`` from another
-    container; keep their legacy broad bind unless operators opt into a
-    narrower bind with ``DEER_FLOW_SANDBOX_BIND_HOST``.  When operators choose
-    an IPv6 loopback sandbox host, bind Docker to IPv6 loopback as well so the
-    advertised sandbox URL and published socket use the same address family.
-    """
-    explicit_bind = bind_host if bind_host is not None else os.environ.get("DEER_FLOW_SANDBOX_BIND_HOST")
-    if explicit_bind is not None:
-        explicit_bind = explicit_bind.strip()
-        if explicit_bind:
-            logger.debug("Docker sandbox bind: %s (explicit bind host override)", explicit_bind)
-            return explicit_bind
-
-    host = sandbox_host if sandbox_host is not None else os.environ.get("DEER_FLOW_SANDBOX_HOST", "localhost")
-    if _is_ipv6_loopback_sandbox_host(host):
-        logger.debug("Docker sandbox bind: [::1] (IPv6 loopback sandbox host)")
-        return "[::1]"
-    if _is_loopback_sandbox_host(host):
-        logger.debug("Docker sandbox bind: 127.0.0.1 (loopback default)")
-        return "127.0.0.1"
-
-    logger.debug("Docker sandbox bind: 0.0.0.0 (non-loopback sandbox host compatibility)")
-    return "0.0.0.0"
-
-
 class LocalContainerBackend(SandboxBackend):
     """Backend that manages sandbox containers locally using Docker or Apple Container.
 
@@ -507,17 +424,12 @@ class LocalContainerBackend(SandboxBackend):
         if self._runtime == "docker":
             cmd.extend(["--security-opt", "seccomp=unconfined"])
 
-        if self._runtime == "docker":
-            port_mapping = f"{_resolve_docker_bind_host()}:{port}:8080"
-        else:
-            port_mapping = f"{port}:8080"
-
         cmd.extend(
             [
                 "--rm",
                 "-d",
                 "-p",
-                port_mapping,
+                f"{port}:8080",
                 "--name",
                 container_name,
             ]
@@ -552,8 +464,7 @@ class LocalContainerBackend(SandboxBackend):
 
         cmd.append(self._image)
 
-        log_cmd = _format_container_command_for_log(_redact_container_command_for_log(cmd))
-        logger.info(f"Starting container using {self._runtime}: {log_cmd}")
+        logger.info(f"Starting container using {self._runtime}: {' '.join(cmd)}")
 
         try:
             result = subprocess.run(cmd, capture_output=True, text=True, check=True)

backend/packages/harness/deerflow/community/jina_ai/jina_client.py

@@ -38,6 +38,6 @@ class JinaClient:
 
             return response.text
         except Exception as e:
-            error_message = f"Request to Jina API failed: {type(e).__name__}: {e}"
-            logger.warning(error_message)
+            error_message = f"Request to Jina API failed: {str(e)}"
+            logger.exception(error_message)
             return f"Error: {error_message}"

backend/packages/harness/deerflow/community/jina_ai/tools.py

@@ -1,5 +1,3 @@
-import asyncio
-
 from langchain.tools import tool
 
 from deerflow.community.jina_ai.jina_client import JinaClient
@@ -28,5 +26,5 @@ async def web_fetch_tool(url: str) -> str:
     html_content = await jina_client.crawl(url, return_format="html", timeout=timeout)
     if isinstance(html_content, str) and html_content.startswith("Error:"):
         return html_content
-    article = await asyncio.to_thread(readability_extractor.extract_article, html_content)
+    article = readability_extractor.extract_article(html_content)
     return article.to_markdown()[:4096]

backend/packages/harness/deerflow/config/agents_api_config.py

@@ -1,32 +0,0 @@
-"""Configuration for the custom agents management API."""
-
-from pydantic import BaseModel, Field
-
-
-class AgentsApiConfig(BaseModel):
-    """Configuration for custom-agent and user-profile management routes."""
-
-    enabled: bool = Field(
-        default=False,
-        description=("Whether to expose the custom-agent management API over HTTP. When disabled, the gateway rejects read/write access to custom agent SOUL.md, config, and USER.md prompt-management routes."),
-    )
-
-
-_agents_api_config: AgentsApiConfig = AgentsApiConfig()
-
-
-def get_agents_api_config() -> AgentsApiConfig:
-    """Get the current agents API configuration."""
-    return _agents_api_config
-
-
-def set_agents_api_config(config: AgentsApiConfig) -> None:
-    """Set the agents API configuration."""
-    global _agents_api_config
-    _agents_api_config = config
-
-
-def load_agents_api_config_from_dict(config_dict: dict) -> None:
-    """Load agents API configuration from a dictionary."""
-    global _agents_api_config
-    _agents_api_config = AgentsApiConfig(**config_dict)

backend/packages/harness/deerflow/config/agents_config.py

@@ -15,17 +15,6 @@ SOUL_FILENAME = "SOUL.md"
 AGENT_NAME_PATTERN = re.compile(r"^[A-Za-z0-9-]+$")
 
 
-def validate_agent_name(name: str | None) -> str | None:
-    """Validate a custom agent name before using it in filesystem paths."""
-    if name is None:
-        return None
-    if not isinstance(name, str):
-        raise ValueError("Invalid agent name. Expected a string or None.")
-    if not AGENT_NAME_PATTERN.fullmatch(name):
-        raise ValueError(f"Invalid agent name '{name}'. Must match pattern: {AGENT_NAME_PATTERN.pattern}")
-    return name
-
-
 class AgentConfig(BaseModel):
     """Configuration for a custom agent."""
 
@@ -57,7 +46,8 @@ def load_agent_config(name: str | None) -> AgentConfig | None:
     if name is None:
         return None
 
-    name = validate_agent_name(name)
+    if not AGENT_NAME_PATTERN.match(name):
+        raise ValueError(f"Invalid agent name '{name}'. Must match pattern: {AGENT_NAME_PATTERN.pattern}")
     agent_dir = get_paths().agent_dir(name)
     config_file = agent_dir / "config.yaml"
 

backend/packages/harness/deerflow/config/app_config.py

@@ -8,8 +8,7 @@ import yaml
 from dotenv import load_dotenv
 from pydantic import BaseModel, ConfigDict, Field
 
-from deerflow.config.acp_config import ACPAgentConfig, load_acp_config_from_dict
-from deerflow.config.agents_api_config import AgentsApiConfig, load_agents_api_config_from_dict
+from deerflow.config.acp_config import load_acp_config_from_dict
 from deerflow.config.checkpointer_config import CheckpointerConfig, load_checkpointer_config_from_dict
 from deerflow.config.database_config import DatabaseConfig
 from deerflow.config.extensions_config import ExtensionsConfig
@@ -17,7 +16,6 @@ from deerflow.config.guardrails_config import GuardrailsConfig, load_guardrails_
 from deerflow.config.memory_config import MemoryConfig, load_memory_config_from_dict
 from deerflow.config.model_config import ModelConfig
 from deerflow.config.run_events_config import RunEventsConfig
-from deerflow.config.runtime_paths import existing_project_file
 from deerflow.config.sandbox_config import SandboxConfig
 from deerflow.config.skill_evolution_config import SkillEvolutionConfig
 from deerflow.config.skills_config import SkillsConfig
@@ -34,54 +32,17 @@ load_dotenv()
 logger = logging.getLogger(__name__)
 
 
-CONFIG_FILE_DATABASE_DEFAULTS = {
-    "backend": "sqlite",
-    "sqlite_dir": ".deer-flow/data",
-}
-
-
-class CircuitBreakerConfig(BaseModel):
-    """Configuration for the LLM Circuit Breaker."""
-
-    failure_threshold: int = Field(default=5, description="Number of consecutive failures before tripping the circuit")
-    recovery_timeout_sec: int = Field(default=60, description="Time in seconds before attempting to recover the circuit")
-
-
-def _legacy_config_candidates() -> tuple[Path, ...]:
-    """Return source-tree config.yaml locations for monorepo compatibility."""
+def _default_config_candidates() -> tuple[Path, ...]:
+    """Return deterministic config.yaml locations without relying on cwd."""
     backend_dir = Path(__file__).resolve().parents[4]
     repo_root = backend_dir.parent
     return (backend_dir / "config.yaml", repo_root / "config.yaml")
 
 
-def logging_level_from_config(name: str | None) -> int:
-    """Map ``config.yaml`` ``log_level`` string to a :mod:`logging` level constant."""
-    mapping = logging.getLevelNamesMapping()
-    return mapping.get((name or "info").strip().upper(), logging.INFO)
-
-
-def apply_logging_level(name: str | None) -> None:
-    """Resolve *name* to a logging level and apply it to the ``deerflow``/``app`` logger hierarchies.
-
-    Only the ``deerflow`` and ``app`` logger levels are changed so that
-    third-party library verbosity (e.g. uvicorn, sqlalchemy) is not
-    affected. Root handler levels are lowered (never raised) so that
-    messages from the configured loggers can propagate through without
-    being filtered, while preserving handler thresholds that may be
-    intentionally restrictive for third-party log output.
-    """
-    level = logging_level_from_config(name)
-    for logger_name in ("deerflow", "app"):
-        logging.getLogger(logger_name).setLevel(level)
-    for handler in logging.root.handlers:
-        if level < handler.level:
-            handler.setLevel(level)
-
-
 class AppConfig(BaseModel):
     """Config for the DeerFlow application"""
 
-    log_level: str = Field(default="info", description="Logging level for deerflow and app modules (debug/info/warning/error); third-party libraries are not affected")
+    log_level: str = Field(default="info", description="Logging level for deerflow modules (debug/info/warning/error)")
     token_usage: TokenUsageConfig = Field(default_factory=TokenUsageConfig, description="Token usage tracking configuration")
     models: list[ModelConfig] = Field(default_factory=list, description="Available models")
     sandbox: SandboxConfig = Field(description="Sandbox configuration")
@@ -94,12 +55,9 @@ class AppConfig(BaseModel):
     title: TitleConfig = Field(default_factory=TitleConfig, description="Automatic title generation configuration")
     summarization: SummarizationConfig = Field(default_factory=SummarizationConfig, description="Conversation summarization configuration")
     memory: MemoryConfig = Field(default_factory=MemoryConfig, description="Memory subsystem configuration")
-    agents_api: AgentsApiConfig = Field(default_factory=AgentsApiConfig, description="Custom-agent management API configuration")
-    acp_agents: dict[str, ACPAgentConfig] = Field(default_factory=dict, description="ACP-compatible agent configuration")
     subagents: SubagentsAppConfig = Field(default_factory=SubagentsAppConfig, description="Subagent runtime configuration")
     guardrails: GuardrailsConfig = Field(default_factory=GuardrailsConfig, description="Guardrail middleware configuration")
-    circuit_breaker: CircuitBreakerConfig = Field(default_factory=CircuitBreakerConfig, description="LLM circuit breaker configuration")
-    model_config = ConfigDict(extra="allow")
+    model_config = ConfigDict(extra="allow", frozen=False)
     database: DatabaseConfig = Field(default_factory=DatabaseConfig, description="Unified database backend configuration")
     run_events: RunEventsConfig = Field(default_factory=RunEventsConfig, description="Run event storage configuration")
     checkpointer: CheckpointerConfig | None = Field(default=None, description="Checkpointer configuration")
@@ -112,8 +70,7 @@ class AppConfig(BaseModel):
         Priority:
         1. If provided `config_path` argument, use it.
         2. If provided `DEER_FLOW_CONFIG_PATH` environment variable, use it.
-        3. Otherwise, search the caller project root.
-        4. Finally, search legacy backend/repository-root defaults for monorepo compatibility.
+        3. Otherwise, search deterministic backend/repository-root defaults from `_default_config_candidates()`.
         """
         if config_path:
             path = Path(config_path)
@@ -126,14 +83,10 @@ class AppConfig(BaseModel):
                 raise FileNotFoundError(f"Config file specified by environment variable `DEER_FLOW_CONFIG_PATH` not found at {path}")
             return path
         else:
-            project_config = existing_project_file(("config.yaml",))
-            if project_config is not None:
-                return project_config
-
-            for path in _legacy_config_candidates():
+            for path in _default_config_candidates():
                 if path.exists():
                     return path
-            raise FileNotFoundError("`config.yaml` file not found in the project root or legacy backend/repository root locations")
+            raise FileNotFoundError("`config.yaml` file not found at the default backend or repository root locations")
 
     @classmethod
     def from_file(cls, config_path: str | None = None) -> Self:
@@ -155,7 +108,6 @@ class AppConfig(BaseModel):
         cls._check_config_version(config_data, resolved_path)
 
         config_data = cls.resolve_env_variables(config_data)
-        cls._apply_database_defaults(config_data)
 
         # Load title config if present
         if "title" in config_data:
@@ -169,10 +121,6 @@ class AppConfig(BaseModel):
         if "memory" in config_data:
             load_memory_config_from_dict(config_data["memory"])
 
-        # Always refresh agents API config so removed config sections reset
-        # singleton-backed state to its default/disabled values on reload.
-        load_agents_api_config_from_dict(config_data.get("agents_api") or {})
-
         # Load subagents config if present
         if "subagents" in config_data:
             load_subagents_config_from_dict(config_data["subagents"])
@@ -185,10 +133,6 @@ class AppConfig(BaseModel):
         if "guardrails" in config_data:
             load_guardrails_config_from_dict(config_data["guardrails"])
 
-        # Load circuit_breaker config if present
-        if "circuit_breaker" in config_data:
-            config_data["circuit_breaker"] = config_data["circuit_breaker"]
-
         # Load checkpointer config if present
         if "checkpointer" in config_data:
             load_checkpointer_config_from_dict(config_data["checkpointer"])
@@ -207,18 +151,6 @@ class AppConfig(BaseModel):
         result = cls.model_validate(config_data)
         return result
 
-    @classmethod
-    def _apply_database_defaults(cls, config_data: dict[str, Any]) -> None:
-        """Apply config.yaml defaults for persistence when the section is absent."""
-        database_config = config_data.get("database")
-        if database_config is None:
-            database_config = {}
-            config_data["database"] = database_config
-        if not isinstance(database_config, dict):
-            return
-        for key, value in CONFIG_FILE_DATABASE_DEFAULTS.items():
-            database_config.setdefault(key, value)
-
     @classmethod
     def _check_config_version(cls, config_data: dict, config_path: Path) -> None:
         """Check if the user's config.yaml is outdated compared to config.example.yaml.
@@ -323,9 +255,6 @@ class AppConfig(BaseModel):
         return next((group for group in self.tool_groups if group.name == name), None)
 
 
-# Compatibility singleton layer for code paths that have not yet been
-# migrated to explicit ``AppConfig`` threading. New composition roots should
-# prefer constructing ``AppConfig`` once and passing it down directly.
 _app_config: AppConfig | None = None
 _app_config_path: Path | None = None
 _app_config_mtime: float | None = None

backend/packages/harness/deerflow/config/database_config.py

@@ -4,12 +4,8 @@ Controls BOTH the LangGraph checkpointer and the DeerFlow application
 persistence layer (runs, threads metadata, users, etc.). The user
 configures one backend; the system handles physical separation details.
 
-SQLite mode: checkpointer and app share a single .db file
-({sqlite_dir}/deerflow.db) with WAL journal mode enabled on every
-connection. WAL allows concurrent readers and a single writer without
-blocking, making a unified file safe for both workloads.  Writers
-that contend for the lock wait via the default 5-second sqlite3
-busy timeout rather than failing immediately.
+SQLite mode: checkpointer and app use different .db files in the same
+directory to avoid write-lock contention. This is automatic.
 
 Postgres mode: both use the same database URL but maintain independent
 connection pools with different lifecycles.
@@ -44,7 +40,7 @@ class DatabaseConfig(BaseModel):
     )
     sqlite_dir: str = Field(
         default=".deer-flow/data",
-        description=("Directory for the SQLite database file. Both checkpointer and application data share {sqlite_dir}/deerflow.db."),
+        description=("Directory for SQLite database files. Checkpointer uses {sqlite_dir}/checkpoints.db, application data uses {sqlite_dir}/app.db."),
     )
     postgres_url: str = Field(
         default="",
@@ -73,27 +69,21 @@ class DatabaseConfig(BaseModel):
 
         return str(Path(self.sqlite_dir).resolve())
 
-    @property
-    def sqlite_path(self) -> str:
-        """Unified SQLite file path shared by checkpointer and app."""
-        return os.path.join(self._resolved_sqlite_dir, "deerflow.db")
-
-    # Backward-compatible aliases
     @property
     def checkpointer_sqlite_path(self) -> str:
-        """SQLite file path for the LangGraph checkpointer (alias for sqlite_path)."""
-        return self.sqlite_path
+        """SQLite file path for the LangGraph checkpointer."""
+        return os.path.join(self._resolved_sqlite_dir, "checkpoints.db")
 
     @property
     def app_sqlite_path(self) -> str:
-        """SQLite file path for application ORM data (alias for sqlite_path)."""
-        return self.sqlite_path
+        """SQLite file path for application ORM data."""
+        return os.path.join(self._resolved_sqlite_dir, "app.db")
 
     @property
     def app_sqlalchemy_url(self) -> str:
         """SQLAlchemy async URL for the application ORM engine."""
         if self.backend == "sqlite":
-            return f"sqlite+aiosqlite:///{self.sqlite_path}"
+            return f"sqlite+aiosqlite:///{self.app_sqlite_path}"
         if self.backend == "postgres":
             url = self.postgres_url
             if url.startswith("postgresql://"):

backend/packages/harness/deerflow/config/extensions_config.py

@@ -7,8 +7,6 @@ from typing import Any, Literal
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from deerflow.config.runtime_paths import existing_project_file
-
 
 class McpOAuthConfig(BaseModel):
     """OAuth configuration for an MCP server (HTTP/SSE transports)."""
@@ -75,8 +73,8 @@ class ExtensionsConfig(BaseModel):
         Priority:
         1. If provided `config_path` argument, use it.
         2. If provided `DEER_FLOW_EXTENSIONS_CONFIG_PATH` environment variable, use it.
-        3. Otherwise, search the caller project root for `extensions_config.json`, then `mcp_config.json`.
-        4. For backward compatibility, also search legacy backend/repository-root defaults.
+        3. Otherwise, check for `extensions_config.json` in the current directory, then in the parent directory.
+        4. For backward compatibility, also check for `mcp_config.json` if `extensions_config.json` is not found.
         5. If not found, return None (extensions are optional).
 
         Args:
@@ -85,9 +83,8 @@ class ExtensionsConfig(BaseModel):
         Resolution order:
             1. If provided `config_path` argument, use it.
             2. If provided `DEER_FLOW_EXTENSIONS_CONFIG_PATH` environment variable, use it.
-            3. Otherwise, search the caller project root for
+            3. Otherwise, search backend/repository-root defaults for
                `extensions_config.json`, then legacy `mcp_config.json`.
-            4. Finally, search backend/repository-root defaults for monorepo compatibility.
 
         Returns:
             Path to the extensions config file if found, otherwise None.
@@ -103,10 +100,6 @@ class ExtensionsConfig(BaseModel):
                 raise FileNotFoundError(f"Extensions config file specified by environment variable `DEER_FLOW_EXTENSIONS_CONFIG_PATH` not found at {path}")
             return path
         else:
-            project_config = existing_project_file(("extensions_config.json", "mcp_config.json"))
-            if project_config is not None:
-                return project_config
-
             backend_dir = Path(__file__).resolve().parents[4]
             repo_root = backend_dir.parent
             for path in (

backend/packages/harness/deerflow/config/memory_config.py

@@ -14,9 +14,8 @@ class MemoryConfig(BaseModel):
         default="",
         description=(
             "Path to store memory data. "
-            "If empty, defaults to per-user memory at `{base_dir}/users/{user_id}/memory.json`. "
-            "Absolute paths are used as-is and opt out of per-user isolation "
-            "(all users share the same file). "
+            "If empty, defaults to `{base_dir}/memory.json` (see Paths.memory_file). "
+            "Absolute paths are used as-is. "
             "Relative paths are resolved against `Paths.base_dir` "
             "(not the backend working directory). "
             "Note: if you previously set this to `.deer-flow/memory.json`, "

backend/packages/harness/deerflow/config/paths.py

@@ -3,18 +3,16 @@ import re
 import shutil
 from pathlib import Path, PureWindowsPath
 
-from deerflow.config.runtime_paths import runtime_home
-
 # Virtual path prefix seen by agents inside the sandbox
 VIRTUAL_PATH_PREFIX = "/mnt/user-data"
 
 _SAFE_THREAD_ID_RE = re.compile(r"^[A-Za-z0-9_\-]+$")
-_SAFE_USER_ID_RE = re.compile(r"^[A-Za-z0-9_\-]+$")
 
 
 def _default_local_base_dir() -> Path:
-    """Return the caller project's writable DeerFlow state directory."""
-    return runtime_home()
+    """Return the repo-local DeerFlow state directory without relying on cwd."""
+    backend_dir = Path(__file__).resolve().parents[4]
+    return backend_dir / ".deer-flow"
 
 
 def _validate_thread_id(thread_id: str) -> str:
@@ -24,13 +22,6 @@ def _validate_thread_id(thread_id: str) -> str:
     return thread_id
 
 
-def _validate_user_id(user_id: str) -> str:
-    """Validate a user ID before using it in filesystem paths."""
-    if not _SAFE_USER_ID_RE.match(user_id):
-        raise ValueError(f"Invalid user_id {user_id!r}: only alphanumeric characters, hyphens, and underscores are allowed.")
-    return user_id
-
-
 def _join_host_path(base: str, *parts: str) -> str:
     """Join host filesystem path segments while preserving native style.
 
@@ -82,7 +73,7 @@ class Paths:
     BaseDir resolution (in priority order):
         1. Constructor argument `base_dir`
         2. DEER_FLOW_HOME environment variable
-        3. Caller project fallback: `{project_root}/.deer-flow`
+        3. Repo-local fallback derived from this module path: `{backend_dir}/.deer-flow`
     """
 
     def __init__(self, base_dir: str | Path | None = None) -> None:
@@ -143,63 +134,44 @@ class Paths:
         """Per-agent memory file: `{base_dir}/agents/{name}/memory.json`."""
         return self.agent_dir(name) / "memory.json"
 
-    def user_dir(self, user_id: str) -> Path:
-        """Directory for a specific user: `{base_dir}/users/{user_id}/`."""
-        return self.base_dir / "users" / _validate_user_id(user_id)
-
-    def user_memory_file(self, user_id: str) -> Path:
-        """Per-user memory file: `{base_dir}/users/{user_id}/memory.json`."""
-        return self.user_dir(user_id) / "memory.json"
-
-    def user_agent_memory_file(self, user_id: str, agent_name: str) -> Path:
-        """Per-user per-agent memory: `{base_dir}/users/{user_id}/agents/{name}/memory.json`."""
-        return self.user_dir(user_id) / "agents" / agent_name.lower() / "memory.json"
-
-    def thread_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
+    def thread_dir(self, thread_id: str) -> Path:
         """
-        Host path for a thread's data.
-
-        When *user_id* is provided:
-            `{base_dir}/users/{user_id}/threads/{thread_id}/`
-        Otherwise (legacy layout):
-            `{base_dir}/threads/{thread_id}/`
+        Host path for a thread's data: `{base_dir}/threads/{thread_id}/`
 
         This directory contains a `user-data/` subdirectory that is mounted
         as `/mnt/user-data/` inside the sandbox.
 
         Raises:
-            ValueError: If `thread_id` or `user_id` contains unsafe characters (path
-                        separators or `..`) that could cause directory traversal.
+            ValueError: If `thread_id` contains unsafe characters (path separators
+                        or `..`) that could cause directory traversal.
         """
-        if user_id is not None:
-            return self.user_dir(user_id) / "threads" / _validate_thread_id(thread_id)
         return self.base_dir / "threads" / _validate_thread_id(thread_id)
 
-    def sandbox_work_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
+    def sandbox_work_dir(self, thread_id: str) -> Path:
         """
         Host path for the agent's workspace directory.
         Host: `{base_dir}/threads/{thread_id}/user-data/workspace/`
         Sandbox: `/mnt/user-data/workspace/`
         """
-        return self.thread_dir(thread_id, user_id=user_id) / "user-data" / "workspace"
+        return self.thread_dir(thread_id) / "user-data" / "workspace"
 
-    def sandbox_uploads_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
+    def sandbox_uploads_dir(self, thread_id: str) -> Path:
         """
         Host path for user-uploaded files.
         Host: `{base_dir}/threads/{thread_id}/user-data/uploads/`
         Sandbox: `/mnt/user-data/uploads/`
         """
-        return self.thread_dir(thread_id, user_id=user_id) / "user-data" / "uploads"
+        return self.thread_dir(thread_id) / "user-data" / "uploads"
 
-    def sandbox_outputs_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
+    def sandbox_outputs_dir(self, thread_id: str) -> Path:
         """
         Host path for agent-generated artifacts.
         Host: `{base_dir}/threads/{thread_id}/user-data/outputs/`
         Sandbox: `/mnt/user-data/outputs/`
         """
-        return self.thread_dir(thread_id, user_id=user_id) / "user-data" / "outputs"
+        return self.thread_dir(thread_id) / "user-data" / "outputs"
 
-    def acp_workspace_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
+    def acp_workspace_dir(self, thread_id: str) -> Path:
         """
         Host path for the ACP workspace of a specific thread.
         Host: `{base_dir}/threads/{thread_id}/acp-workspace/`
@@ -208,43 +180,41 @@ class Paths:
         Each thread gets its own isolated ACP workspace so that concurrent
         sessions cannot read each other's ACP agent outputs.
         """
-        return self.thread_dir(thread_id, user_id=user_id) / "acp-workspace"
+        return self.thread_dir(thread_id) / "acp-workspace"
 
-    def sandbox_user_data_dir(self, thread_id: str, *, user_id: str | None = None) -> Path:
+    def sandbox_user_data_dir(self, thread_id: str) -> Path:
         """
         Host path for the user-data root.
         Host: `{base_dir}/threads/{thread_id}/user-data/`
         Sandbox: `/mnt/user-data/`
         """
-        return self.thread_dir(thread_id, user_id=user_id) / "user-data"
+        return self.thread_dir(thread_id) / "user-data"
 
-    def host_thread_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
+    def host_thread_dir(self, thread_id: str) -> str:
         """Host path for a thread directory, preserving Windows path syntax."""
-        if user_id is not None:
-            return _join_host_path(self._host_base_dir_str(), "users", _validate_user_id(user_id), "threads", _validate_thread_id(thread_id))
         return _join_host_path(self._host_base_dir_str(), "threads", _validate_thread_id(thread_id))
 
-    def host_sandbox_user_data_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
+    def host_sandbox_user_data_dir(self, thread_id: str) -> str:
         """Host path for a thread's user-data root."""
-        return _join_host_path(self.host_thread_dir(thread_id, user_id=user_id), "user-data")
+        return _join_host_path(self.host_thread_dir(thread_id), "user-data")
 
-    def host_sandbox_work_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
+    def host_sandbox_work_dir(self, thread_id: str) -> str:
         """Host path for the workspace mount source."""
-        return _join_host_path(self.host_sandbox_user_data_dir(thread_id, user_id=user_id), "workspace")
+        return _join_host_path(self.host_sandbox_user_data_dir(thread_id), "workspace")
 
-    def host_sandbox_uploads_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
+    def host_sandbox_uploads_dir(self, thread_id: str) -> str:
         """Host path for the uploads mount source."""
-        return _join_host_path(self.host_sandbox_user_data_dir(thread_id, user_id=user_id), "uploads")
+        return _join_host_path(self.host_sandbox_user_data_dir(thread_id), "uploads")
 
-    def host_sandbox_outputs_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
+    def host_sandbox_outputs_dir(self, thread_id: str) -> str:
         """Host path for the outputs mount source."""
-        return _join_host_path(self.host_sandbox_user_data_dir(thread_id, user_id=user_id), "outputs")
+        return _join_host_path(self.host_sandbox_user_data_dir(thread_id), "outputs")
 
-    def host_acp_workspace_dir(self, thread_id: str, *, user_id: str | None = None) -> str:
+    def host_acp_workspace_dir(self, thread_id: str) -> str:
         """Host path for the ACP workspace mount source."""
-        return _join_host_path(self.host_thread_dir(thread_id, user_id=user_id), "acp-workspace")
+        return _join_host_path(self.host_thread_dir(thread_id), "acp-workspace")
 
-    def ensure_thread_dirs(self, thread_id: str, *, user_id: str | None = None) -> None:
+    def ensure_thread_dirs(self, thread_id: str) -> None:
         """Create all standard sandbox directories for a thread.
 
         Directories are created with mode 0o777 so that sandbox containers
@@ -258,24 +228,24 @@ class Paths:
         ACP agent invocation.
         """
         for d in [
-            self.sandbox_work_dir(thread_id, user_id=user_id),
-            self.sandbox_uploads_dir(thread_id, user_id=user_id),
-            self.sandbox_outputs_dir(thread_id, user_id=user_id),
-            self.acp_workspace_dir(thread_id, user_id=user_id),
+            self.sandbox_work_dir(thread_id),
+            self.sandbox_uploads_dir(thread_id),
+            self.sandbox_outputs_dir(thread_id),
+            self.acp_workspace_dir(thread_id),
         ]:
             d.mkdir(parents=True, exist_ok=True)
             d.chmod(0o777)
 
-    def delete_thread_dir(self, thread_id: str, *, user_id: str | None = None) -> None:
+    def delete_thread_dir(self, thread_id: str) -> None:
         """Delete all persisted data for a thread.
 
         The operation is idempotent: missing thread directories are ignored.
         """
-        thread_dir = self.thread_dir(thread_id, user_id=user_id)
+        thread_dir = self.thread_dir(thread_id)
         if thread_dir.exists():
             shutil.rmtree(thread_dir)
 
-    def resolve_virtual_path(self, thread_id: str, virtual_path: str, *, user_id: str | None = None) -> Path:
+    def resolve_virtual_path(self, thread_id: str, virtual_path: str) -> Path:
         """Resolve a sandbox virtual path to the actual host filesystem path.
 
         Args:
@@ -283,7 +253,6 @@ class Paths:
             virtual_path: Virtual path as seen inside the sandbox, e.g.
                           ``/mnt/user-data/outputs/report.pdf``.
                           Leading slashes are stripped before matching.
-            user_id: Optional user ID for user-scoped path resolution.
 
         Returns:
             The resolved absolute host filesystem path.
@@ -301,7 +270,7 @@ class Paths:
             raise ValueError(f"Path must start with /{prefix}")
 
         relative = stripped[len(prefix) :].lstrip("/")
-        base = self.sandbox_user_data_dir(thread_id, user_id=user_id).resolve()
+        base = self.sandbox_user_data_dir(thread_id).resolve()
         actual = (base / relative).resolve()
 
         try: