`create()` now accepts `workspace_id: str | None | _AutoSentinel = AUTO`
on both the SQL and in-memory implementations (and the abstract base).
AUTO resolves via `resolve_workspace_id()` from the workspace contextvar
that PR4 AuthMiddleware sets; explicit None bypasses for migration paths;
explicit str overrides the contextvar.
Test infrastructure:
- conftest gains an autouse `_auto_workspace_context` fixture mirroring
the existing user fixture. Opt-out via `@pytest.mark.no_auto_workspace`.
- A SQLAlchemy `after_create` listener on `Base.metadata` seeds the
matching `test-workspace-autouse` + `test-user-autouse` rows whenever
`init_engine` runs `create_all()`, so the FK from threads_meta to
workspaces resolves. Alembic migration tests bypass create_all and are
unaffected, keeping real FK constraints under test.
- `test_thread_meta_workspace_filter.py` covers the three AUTO / explicit
/ None paths.
3 new tests pass; 115 existing thread_meta/run/feedback/run_event/owner
tests stay green.
Three SQLite cases + Postgres twins: happy-path upgrade after
populating workspace_id, refuse-with-NULL-leftover raises RuntimeError,
and a UNIQUE(workspace_id, thread_id) IntegrityError reproducer. The
UNIQUE test uses a scratch table because the production schema's
PRIMARY KEY on thread_id would shadow the new UNIQUE index. Index
truthiness asserted instead of bool-equality so SQLite (int 1) and
Postgres (True) both pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Refuses to upgrade if any of the 4 business tables still has NULL
workspace_id rows (pre-flight count then RuntimeError pointing the
operator at scripts/backfill_workspace_id.py). Then op.batch_alter_table
flips each column to NOT NULL and adds the threads_meta
(workspace_id, thread_id) UNIQUE index that PR6 routers will rely on.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Snapshots workspace / membership / users.default_workspace_id row
counts before backfill(dry_run=True), runs the orchestrator, asserts
no counts changed. Pins the dry-run report's per-step semantics:
Step 1 counts candidates without populating defaults, so Step 2's
JOIN reports 0; Step 3 picks up all NULL business rows untouched.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
_ensure_legacy_workspace creates the nil-UUID anchor (slug=legacy)
owned by the platform admin (or oldest user as fallback). Raises a
clear error if the DB has no users at all so we never silently create
an orphaned workspace. Step 3 UPDATEs each table's remaining
workspace_id IS NULL rows to LEGACY_WORKSPACE_ID. Orchestrator wires
ensure-then-loop between Step 2 and Step 3. 3 new tests: orphan
fan-out, no-users error, end-to-end orchestrator with mixed owned +
orphan rows.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Per-table correlated subquery UPDATE (portable across SQLite + Postgres).
Filters workspace_id IS NULL AND user_id IS NOT NULL so already-tagged
rows and orphan rows are skipped. Dry-run mode counts via a JOIN, never
writes. Returns rows-updated for the orchestrator report. 2 new tests:
single-user 4-table fan-out + multi-user isolation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
For each user with NULL default_workspace_id, generate a base slug
from the email, walk past collisions/blacklist via next_available_slug,
create the workspace + owner membership, and set default_workspace_id.
Idempotent: candidates list is filtered by IS NULL, so re-running on a
populated DB is a no-op. 3 new unit tests (creation, idempotence,
blacklist-walker behaviour).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
argparse with --dry-run, async orchestrator that loops the 4 business
tables, and three step stubs (Step 1: users -> workspace creation;
Step 2: UPDATE tables from users.default_workspace_id; Step 3: orphan
rows -> legacy_workspace anchor at the LOCK'd nil UUID). Step bodies
are filled in T5.5-T5.7 alongside their tests.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
ORM-side mirror of alembic 0002. threads_meta gets the matching
(workspace_id, user_id, updated_at) composite index so fresh
create_all() dev databases land on the same shape Alembic produces.
Pre-existing test_alembic_default_workspace_id pins to revision
0001 explicitly since 'head' now includes 0002.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirrors test_alembic_default_workspace_id pattern: synchronous bodies
(env.py uses asyncio.run internally), pre-PR5 schema bootstrap with the
minimal columns the migration touches, upgrade/downgrade assertions for
the workspace_id column + FK + composite index on all 4 business tables.
Postgres cases auto-skip when Docker daemon is unreachable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
ALTER threads_meta / runs / feedback / run_events to add nullable
workspace_id String(36) + FK to workspaces (ON DELETE CASCADE) and a
composite (workspace_id, user_id, updated_at) index on threads_meta for
the workspace-scoped thread-list query. Downgrade reverses all four FKs,
columns, and the index.
Stage 0 PR5 step 1/2; revision 0003 flips NOT NULL after the backfill.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pre-PR4 admins have users.default_workspace_id NULL. Without this
backfill they would log in successfully but immediately bounce off the
workspace gate (T4.7) because their token cannot encode a wid. The
lifespan hook now resolves the admin user and calls
ensure_default_workspace (idempotent — no-op if the user already has
a workspace), so the post-upgrade boot makes the admin usable.
Renamed routers.auth._ensure_default_workspace → ensure_default_workspace
to make it importable across modules.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
GET /auth/me now responds with the new UserMeResponse: the existing
user fields plus default_workspace_id and a workspaces list that
joins WorkspaceRepository.list_by_user with the caller's role from
WorkspaceMembershipRepository.list_by_user. Stage 0 every user has
exactly one entry there, but the shape is forward-compatible for
Stage 2 multi-workspace memberships.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
After PR4 every protected request demands wid. Three JWT-issue paths
must encode it; T4.8/T4.9 covered /initialize and /register, and this
commit closes the remaining two:
- login_local calls _ensure_default_workspace (idempotent — returns
the existing default_workspace_id when set) so users who pre-date
PR4 are backfilled at login time, and signs the new cookie with
wid + role='owner'.
- change_password does the same, ensuring a password change does not
strip the workspace claim and lock the user out on their next
request.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirrors T4.8: the regular registration path now invokes the same
_ensure_default_workspace helper so every new user lands with a
1-person workspace (owner) and a JWT carrying wid + role='owner'.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
initialize_admin now seeds a 1-person workspace immediately after the
admin user is created: WorkspaceRepository.create(name, slug, owner_id)
+ WorkspaceMembershipRepository.add(role='owner') + writes the new
workspace id back to users.default_workspace_id. The session JWT is
re-issued with wid + role='owner' so subsequent requests pass the
T4.7 workspace gate.
Mechanical pieces:
- SQLiteUserRepository row<->user mapping now includes
default_workspace_id (sql update_user too) so the column persists.
- workspace.sql.SLUG_BLACKLIST is now public (was _SLUG_BLACKLIST) and
the registration helper treats blacklisted slugs as "taken" so the
walker steps past reserved names like "admin" instead of crashing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
auto_slug_from_email maps an email's local-part to a schema-valid base
slug (lowercase, [+_.]→'-', alphanumeric-and-hyphen, clamp 32 chars,
fallback to user-{token_hex(4)} for pathological inputs).
next_available_slug walks the {base, base-2, base-3, ...} sequence
against a caller-supplied async exists_check until it lands on a free
slot, truncating base when the suffix would push past 32 chars.
Pulled forward of T4.8/T4.9 because both /auth/initialize and
/auth/register need it. Lives in app.gateway.auth (not persistence)
since "email → slug" is a registration-time concern.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
deps.get_current_user_from_request now stashes the decoded payload on
request.state.auth_payload so AuthMiddleware can populate the
workspace_context ContextVar without a second decode. Reset is paired
in the same try/finally as user_context to keep teardown atomic.
Also adds:
- auth.models.ActiveWorkspace — minimal proxy that satisfies the
CurrentWorkspace protocol (id + role only).
- auth.models.User.default_workspace_id — surfaces the DB column added
in T4.4 so the eventual /auth/me payload can reference it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
After PR4 every JWT must carry wid (workspace_id). decode_token now
returns the new TokenError.WORKSPACE_MISSING when the signature is
valid but the payload lacks wid; expired tokens still report EXPIRED
first so /auth/refresh logic stays correct. AuthErrorCode gains a
matching WORKSPACE_REQUIRED for middleware to surface to clients.
Updates 13 existing test sites that issued tokens without wid to pass
workspace_id="ws-test" + role="owner", reflecting the new contract.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
TokenPayload gains optional wid (workspace_id) and role claims;
create_access_token accepts them as keyword-only args and only
encodes them when provided. Existing tokens and existing callers
keep working unchanged — the contract that protected requests
must carry wid is enforced by middleware (PR4 T4.6/T4.7), not by
the JWT type system.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a nullable FK column to mirror alembic 0001. On fresh deployments
metadata.create_all() will create users with this column; existing
deployments rely on the alembic migration to add it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Verifies alembic upgrade 0001 adds users.default_workspace_id (with FK
to workspaces) and that downgrade cleanly removes it. Runs on both
dialects because the migration uses op.batch_alter_table for SQLite
ALTER compatibility.
Tests are intentionally sync — alembic's command layer is sync and
env.py calls asyncio.run(); running under pytest-anyio would deadlock
on the inner event loop.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First Alembic revision for the DeerFlow application schema. Adds a
nullable users.default_workspace_id column with an ON DELETE SET NULL
FK to workspaces(id), so newly-registered users can be routed back to
their default workspace on next login without consulting memberships.
Uses op.batch_alter_table for SQLite ALTER compatibility (sqlite is
still a supported dev fallback).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(task): remove max_turns parameter from task tool interface
Subagents should always use their configured max_turns value. Exposing
this parameter allowed callers to override the admin-configured limit,
which is undesirable. The value is now exclusively driven by subagent
config (per-agent overrides and global defaults in config.yaml).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix(tools): introduce Runtime type alias to eliminate Pydantic serialization warning
Add deerflow/tools/types.py with:
Runtime = ToolRuntime[dict[str, Any], ThreadState]
Replace every runtime: ToolRuntime[ContextT, ThreadState] and
runtime: ToolRuntime[dict[str, Any], ThreadState] annotation in
sandbox/tools.py, present_file_tool.py, task_tool.py, view_image_tool.py,
and skill_manage_tool.py with the new Runtime alias.
The unbound ContextT TypeVar (default None) caused
PydanticSerializationUnexpectedValue warnings on every tool call because
LangChain's BaseTool._parse_input calls model_dump() on the auto-generated
args_schema while DeerFlow passes a dict as runtime context.
Binding the context to dict[str, Any] aligns Pydantic's serialization
expectations with reality and removes the noise from all run modes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(tools): extend Runtime alias to setup_agent and update_agent tools
Replace bare ToolRuntime annotations in setup_agent_tool.py and
update_agent_tool.py with the shared Runtime alias introduced in the
previous commit, and add both tools to the Pydantic serialization
warning regression test (13 cases total).
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(tools): loosen Pydantic warning filter to avoid version-specific format
Replace the brittle "field_name='context'" substring check with a looser
"context" match so the assertion stays valid if Pydantic changes its
internal warning format across versions.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(tools): simplify warning filter and clean up docstring
Remove the "context" substring condition from the Pydantic warning
filter — asserting that no PydanticSerializationUnexpectedValue fires
at all is both simpler and more comprehensive, since the test payload
contains only the tool's own args plus runtime.
Also update the module docstring to remove the version-specific warning
format example that was inconsistent with the looser filter.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Make loop detection configurable
Expose LoopDetectionMiddleware thresholds through config.yaml while preserving existing defaults and allowing the middleware to be disabled.
Refs bytedance/deer-flow#2517
* feat(loop-detection): add per-tool tool_freq_overrides to Phase 1
Adds ToolFreqOverride model and tool_freq_overrides field to
LoopDetectionConfig, wires it through LoopDetectionMiddleware, and
documents the option in config.example.yaml.
Resolves the gap flagged in the #2586 review: without per-tool overrides,
users hit by #2510/#2511 (RNA-seq workflows exceeding the bash hard limit)
had no way to raise thresholds for one tool without loosening the global
limit for every tool.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* docs(loop-detection): document tool_freq_overrides in LoopDetectionMiddleware docstring
Add the missing Args entry for tool_freq_overrides, explaining the
(warn, hard_limit) tuple structure and how per-tool thresholds supersede
the global tool_freq_warn / tool_freq_hard_limit for named tools.
Also run ruff format on the three files flagged by the lint check.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(loop-detection): validate LoopDetectionMiddleware __init__ params eagerly
Raise clear ValueError at construction time instead of crashing at
unpack-time inside _track_and_check when bad values are passed:
- tool_freq_overrides: must be 2-tuples of positive ints with hard_limit >= warn
- scalar thresholds: warn_threshold, hard_limit, tool_freq_warn,
tool_freq_hard_limit must be >= 1 and hard limits must >= their warn pairs
- window_size, max_tracked_threads must be >= 1
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(test): isolate credential loader directory-path test from real ~/.claude
The test didn't monkeypatch HOME, so on any machine with real Claude Code
credentials at ~/.claude/.credentials.json the function fell through to
those credentials and the assertion failed. Adding HOME redirect ensures
the default credential path doesn't exist during the test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* style(test): add blank lines after import pytest in TestInitValidation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(loop-detection): collapse dual validation to LoopDetectionConfig
Modifications
- LoopDetectionMiddleware.__init__: stripped of all ValueError raises;
becomes a plain field-assignment constructor.
- LoopDetectionMiddleware.from_config: classmethod that builds the
middleware from a Pydantic-validated LoopDetectionConfig and handles
the ToolFreqOverride -> tuple[int, int] conversion.
- agents/factory.py: SDK construction routed through
LoopDetectionMiddleware.from_config(LoopDetectionConfig()) so the
defaults path is Pydantic-validated too.
- agents/lead_agent/agent.py: uses from_config instead of unpacking
config fields by hand.
- tests/test_loop_detection_middleware.py: deleted TestInitValidation
(16 methods exercising the removed __init__ checks); added
TestFromConfig (4 tests: scalar field mapping, override tuple
conversion, empty overrides, behavioral smoke test).
Result: one validation layer (Pydantic), zero duplication, no __new__
hacks. Both production construction sites flow through LoopDetectionConfig.
Test results
make test -> 2977 passed, 18 skipped, 0 failed (137s)
make format -> All checks passed; 411 files left unchanged
* feat(agents): make loop_detection configurable in create_deerflow_agent
Adds a `loop_detection: bool | AgentMiddleware = True` field to
RuntimeFeatures, mirroring the existing pattern used by `sandbox`,
`memory`, and `vision`. SDK users can now disable LoopDetectionMiddleware
or replace it with a custom instance built from their own
LoopDetectionConfig — e.g.
`LoopDetectionMiddleware.from_config(my_cfg)` — instead of being stuck
with the hardcoded defaults previously installed by the SDK factory.
The lead-agent path (which already reads AppConfig.loop_detection) is
unchanged, and the default `True` preserves prior always-on behavior for
all existing callers.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: knight0940 <631532668@qq.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Amorend <142649913+knight0940@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* feat(agent): add update_agent tool for in-chat custom-agent self-updates (#2616)
Custom agents had no built-in way to persist updates to their own SOUL.md /
config.yaml from a normal chat — `setup_agent` was only bound during the
bootstrap flow, so when the user asked the agent to refine its description
or personality, the agent would shell out via bash/write_file and the edits
landed in a temporary sandbox/tool workspace instead of
`{base_dir}/agents/{agent_name}/`.
Changes:
- New `update_agent` builtin tool with partial-update semantics (only the
fields you pass are written) and atomic temp-file + os.replace writes so
a failed update never corrupts existing SOUL.md / config.yaml.
- Lead agent now binds `update_agent` in the non-bootstrap path whenever
`agent_name` is set in the runtime context. Default agent (no
agent_name) and bootstrap flow are unchanged.
- New `<self_update>` system-prompt section is injected for custom agents,
instructing them to use `update_agent` — and explicitly NOT bash /
write_file — to persist self-updates.
- Tests: 11 new cases in `tests/test_update_agent_tool.py` covering
validation (missing/invalid agent_name, unknown agent, no fields),
partial updates (soul-only, description-only, skills=[] vs omitted),
no-op detection, atomic-write safety, and AgentConfig round-tripping;
plus 2 new cases in `tests/test_lead_agent_prompt.py` covering the
self-update prompt section.
- Docs: updated backend/CLAUDE.md builtin tools list and tools.mdx
(en/zh) with the new tool description.
* feat(agent): isolate custom agents per user
Store custom agent definitions under the effective user, keep legacy agents readable until migration, and cover API/tool/migration behavior with tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: consistent write/delete targets & add --user-id to migration
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(loop-detection): keep tool-call pairing on warn injection (#2724)
* make format
* fix(loop-detection): avoid IMMessage leak to downstream consumer
* fix(channels): filter loop warning text from IM replies
1445043649