github/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-08-14 08:49:00 +00:00
Code Issues Packages Projects Releases Wiki Activity
deer-flow/CHANGELOG.md
qin-chenghan ad45f59d66
feat(memory): pluggable memory abstraction with self-contained DeerMem backend (#4122) 
* feat(memory): pluggable + self-contained memory system (MemoryManager plan phases 1 & 2)

Phase 1 — Pluggable (steps 0-10):
- ABC MemoryManager (9 methods) + singleton factory + drop-in backend discovery
- DeerMem default backend with core/ (storage/queue/updater/prompt/message_processing)
- NoopMemoryManager backend (proves pluggability)
- All call sites (middleware/hook/prompt/gateway/client/app) routed through manager
- hasattr capability probing for DeerMem-internal methods (no hard imports)
- MemoryConfig gains manager_class field; shared vs DeerMem-private annotated

Phase 2 — Self-contained DeerMem (steps 11-18):
- backend_config passthrough + DeerMemConfig (all DeerMem-private fields moved off MemoryConfig)
- DI: DeerMem owns storage/queue/updater/llm as instance attributes (no global singletons)
- Storage independence: core/paths.py with own root (~/.deermem or ),
  factory auto-injects deer-flow's runtime_home() as absolute base_dir (zero-config)
- LLM independence: core/llm.py via langchain init_chat_model (no create_chat_model)
- Trace independence: optional tracing_callback replaces inject_langfuse_metadata/request_trace_context
- Message processing independence: hide_from_ui default-skip + optional should_keep_hidden_message hook
- Internal imports → relative (only deer_mem.py ABC import is host-relative)
- Carrier (deer_mem.py adapter) / portable (deermem/ config+core) split
- New tests: test_deermem_self_contained + test_memory_manager_pluggable; all memory tests migrated
- Other-agent demo: samples/other_agent_demo/ + automated portability test
- config.example.yaml memory section updated to phase-2 schema

* feat(memory): port consolidation + staleness fix into self-contained DeerMem; phase-2 host hooks

Port upstream #3996 (memory consolidation) and #3993 (staleness KeyError fix)
from origin/MemoryManager into the pluggable, self-contained DeerMem structure
(backends/deermem/deermem/), adapted to the DI MemoryUpdater (config injected,
not get_memory_config globals):

- DeerMemConfig: add consolidation_enabled (opt-in, default false) /
  consolidation_min_facts / consolidation_max_groups_per_cycle /
  consolidation_max_sources
- prompt.py: factsToConsolidate JSON field + {consolidation_section} placeholder
  + CONSOLIDATION_PROMPT constant
- updater.py: _coerce_source_confidence / _select_consolidation_candidates /
  _build_consolidation_section module helpers (matching the existing
  _select_stale_candidates style); consolidation normalization in
  _normalize_memory_update_data; consolidation apply in _apply_updates (after
  max_facts trim, with apply-time guardrails mirroring staleness); staleness
  KeyError fix (f["id"] -> f.get("id") is not None) applied to both the
  staleness guardrail and the consolidation allowed_source_ids comprehension
- config.example.yaml: consolidation section under memory.backend_config
- tests/test_memory_consolidation.py: 40 DI-adapted tests (running, not skipped)
  incl. the staleness KeyError regression

Also includes in-flight phase-2 host-integration work: storage_path semantics
(any absolute/relative value = root dir) and host-default tracing_callback /
should_keep_hidden_message hooks injected into backend_config by the factory.

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(memory): add noop backend template and backends guide

- backends/noop/: complete drop-in template (config.py with zero deer-flow
  imports, noop_manager.py with a 6-step new-backend walkthrough in its
  docstring, commented optional fact-CRUD capabilities).
- backends/README.md: which files to touch when adding/swapping a backend,
  the 5-item backend contract, and common pitfalls.
- manager.py: generalize backend examples in comments (drop mem0-specific
  references).

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(frontend): guard formatTimeAgo against invalid timestamps

Return a neutral placeholder when the input date is invalid (e.g. an empty lastUpdated from a backend with no memories) instead of throwing 'Invalid time value' from date-fns.

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(memory): wire tool-driven memory mode through the MemoryManager ABC

tools.py (memory_search/add/update/delete) now calls get_memory_manager()
instead of the removed host memory module, so tool mode (memory.mode: tool)
works for any backend. DeerMem.search is implemented (case-insensitive
substring match, ranked by confidence) as a stand-in for the planned
semantic retrieval; noop.search returns [] (unchanged). Fact-CRUD tools
use getattr+callable probing -- backends lacking those ops (noop) get a
clear JSON error instead of crashing.

Tests: test_memory_tools rewired to mock the manager (handler tests) +
TestModeGating retained; test_memory_search now covers DeerMem.search;
pluggable stubs test updated (search no longer a stub).

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: resolve lint errors (import sorting, type annotation quotes, E402 in skipped tests)

* docs: restore explanatory comments in config.example.yaml memory section

* fix(security): port html-escape memory facts fix (#4097) to vendored DeerMem prompt.py

* fix(memory): address review + port dropped upstream memory fixes

Review blockers (vendored DeerMem):
- #4044 restore _escape_memory_for_prompt (current_memory blob in
  MEMORY_UPDATE_PROMPT) - prevents </current_memory> breakout
- #4028 html.escape staleness-section cat/content in _build_staleness_section
- #4119 add _escape_summary for injection-path summaries (Work/Personal/
  Current Focus/Recent/Earlier/Background)
- default-model silent no-op: factory injects host default chat model via a
  new host_llm slot (create_chat_model(name=None)); DeerMem prefers host_llm
  over build_llm(model). Zero-config extraction works out of the box again
- MemoryConfigResponse: fix stale docstring (backend-agnostic shape; DeerMem
  knobs live under backend_config, not top-level - restoring flat would
  re-couple the API to DeerMem). Frontend audited: does not read /memory/config
- _host_default_tracing_callback: restore langfuse assistant_id/environment
- search: push category onto the ABC signature; DeerMem filters BEFORE the
  top_k slice (was filtered client-side after slicing -> starved results)
- _do_update_memory_sync: split into wrapper+impl; bind trace_id into the
  request-trace ContextVar on the Timer/executor worker via a new
  trace_context_manager host hook (None trace_id left unbound - no fabrication)
- client.py fact-CRUD now passes user_id (was writing to the global bucket
  while get_memory reads per-user)
- _resolve_manager_class: fail-fast (raise ValueError) on an unresolved
  explicit manager_class instead of silently falling back to DeerMem (memory is
  persistent state - a wrong store is a silent data-integrity footgun)

Upstream memory fixes dropped by the host->vendored rename conflict, re-ported
to backends/deermem/deermem/core/ (+ deer_mem.py):
- #4073 queue busy-timer-spin -> _reprocess_pending flag (core/queue.py)
- #4074 null source.confidence in staleness -> _coerce_source_confidence
  (core/updater.py: _build_staleness_section + _apply_updates stale sort)
- #4075 factsToRemove is optional (drop from _REQUIRED_MEMORY_UPDATE_TOP_LEVEL_KEYS)
- #4076 null confidence in search ranking -> _coerce_source_confidence
  (deer_mem.py DeerMem.search)

host_llm + trace_context_manager are host-injected via backend_config (factory
in manager.py), keeping backends/deermem/ at exactly one `from deerflow` line
(the ABC contract) - portability test preserved.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: resolve lint errors (F541 f-string without placeholders, E501 line too long)

* fix(memory): restore hide_from_ui clarification preservation, expose mode

Two memory-system fixes (F541/E501 lint was already fixed on this branch):

- filter_messages_for_memory: restore default preservation of well-formed
  human_input_response clarification answers (v2 regression). The
  self-containment refactor made the bare function skip ALL hide_from_ui when
  no hook was passed, but upstream preserves well-formed clarification
  responses by default (test_hide_from_ui_human_input_response_is_preserved).
  Inline a host-agnostic _is_human_clarification_response mirror of
  read_human_input_response as the default keep-decision; the host-injected
  should_keep_hidden_message hook still overrides (production path unchanged).
  Portable package stays zero `from deerflow`.

- /memory/config: expose `mode` (middleware|tool) in MemoryConfigResponse +
  the config/status endpoints + client.get_memory_config. mode is a host-
  shared, behavior-determining field missing from the response projection.
  Sync tests (mock .mode; e2e assert mode present).

- Align manager_class field docstring with fail-fast behavior.

Tests: filter/self-contained/portability (35) + memory-config (4) pass;
ruff clean.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(memory): resolve ruff format failures in memory module + tests

`make lint` runs `ruff format --check` in addition to `ruff check`; 8 memory
files had pending format changes -- 7 pre-existing (deer_mem, updater, tools,
test_memory_queue/router/search/tools) + message_processing from the
hide_from_ui fix. Apply `ruff format`: whitespace/wrapping only, no logic
change. 109 memory tests pass; ruff check + format --check both clean.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(memory): address PR review - legacy field migration, fact_id contract, path/docs

Address willem-bd's review on PR head bc8bf0d4 (risk:high, persistent state):

- config: auto-migrate pre-abstraction top-level memory.* DeerMem fields
  (storage_path, max_facts, debounce_seconds, model_name, token_counting,
  staleness_*, consolidation_*) into backend_config on load + warn, so an
  upgrade does NOT silently revert customized settings (was: silent
  extra='ignore' drop). model_name -> backend_config.model.model. Unknown
  top-level keys warned.
- factory: resolve a relative backend_config.storage_path against runtime_home()
  (base_dir-relative, CWD-independent) to preserve pre-abstraction semantics;
  paths.py stays portable (no runtime_home import).
- tools: memory_add uses the fact_id returned directly by create_fact instead of
  re-deriving it via content-key matching (coupled the tool to the backend's
  content normalization; could misreport a storage cap). create_fact now returns
  (memory_data, fact_id); gateway/client/tool updated. Fix terse
  {"error":"content"} -> {"error":"empty content"}.
- app.py: update stale token_counting=="char" warm-up comment to point at
  manager.warm (DeerMem.warm re-checks char and returns early).
- router: comment explaining reload_memory silent fallback vs fact 501 asymmetry
  (read-only degrade vs write fail-loud).
- CHANGELOG: document breaking changes (/memory/config + client.get_memory_config
  shape flat->backend_config; custom storage_class path moved + __init__ must
  accept config) and the legacy-field auto-migration.
- tests: add regression test pinning the per-user memory path
  ({storage_path}/users/{safe_user_id}/memory.json == host make_safe_user_id)
  across the abstraction; update create_fact mocks for (memory_data, fact_id).

Tests: 273 passed (memory suite); ruff check + format clean.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(memory): address PR review - storage_path, max_facts, tracing, parsing

Six review findings (willem-bd), each verified against upstream:

- storage_path semantics (file -> root dir): migration drops file-style
  (.json) legacy values with a warning; factory raises if storage_path
  resolves to an existing file (avoid silent NotADirectoryError write
  failure). CHANGELOG + config.example.yaml comment updated.
- create_memory_fact enforces max_facts again (via _trim_facts_to_max) and
  returns (memory, None) when the cap evicts the new fact; memory_add tool
  reports "not stored", client raises ValueError, POST /memory/facts -> 409.
- max_facts trim uses _coerce_source_confidence (was raw f.get("confidence",
  0) -> TypeError on non-float imported/legacy confidence, swallowed as
  silent update failure).
- memory-tracing assistant_id restored to "memory_agent" (was "lead-agent"
  copy-paste; matches upstream + DeerMem run_name).
- _is_human_clarification_response cross-checked against
  read_human_input_response (drift guard test).
- empty-string legacy values skipped silently in migration (narrow fix, not
  broad "if not value" which would skip explicit bool False).

8 new regression tests. make lint + 406 memory tests pass.

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(memory): address internal review - storage fail-fast, build_llm degrade, config warn, noop template

Addresses 4 findings from the PR #4122 internal supplemental review
(parallel to willem-bd's review, no overlap):

- create_storage fail-fast: a misspelled/unimportable storage_class now
  raises ValueError instead of silently falling back to FileMemoryStorage.
  Memory is persistent state, so a wrong store is a data-integrity footgun;
  mirrors the existing manager_class resolution policy. (storage.py)

- noop template create_fact signature: the commented template used
  keyword-only `content` and returned a bare dict, while DeerMem's actual
  create_fact takes positional `content` and returns tuple[dict, str|None]
  (the memory_add tool passes content positionally; gateway/client/tools all
  tuple-unpack). A backend copied from the template would 500 on fact-CRUD.
  Template fixed; delete_fact/update_fact templates left (callers compatible).
  (noop_manager.py)

- build_llm graceful degrade: wrap init_chat_model in try/except, degrade to
  None + WARNING on failure (mirroring _host_default_llm) so a misconfigured
  explicit model does not crash app startup -- non-LLM memory ops still work
  and an update raises at runtime with the error logged. (llm.py)

- from_backend_config unknown-key warning: log a WARNING for unknown
  backend_config keys (mirrors the host layer's load_memory_config_from_dict)
  so a typo like `storage_pat` does not silently fall back to the default and
  write memory to an unintended location. (config.py)

Tests: rewrote 3 create_storage fallback tests to expect ValueError; added 4
tests (build_llm zero-config/degrade, from_backend_config warn/silent).
make lint green; full memory suite passes.

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: lllyfff <2281215061@qq.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: lllyfff <122260771+lllyfff@users.noreply.github.com>
2026-07-15 11:21:04 +08:00

579 lines
30 KiB
Markdown
Raw Blame History

# Changelog
All notable changes to DeerFlow are documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/)
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
### ⚠ Breaking changes
- **memory:** The memory system is now pluggable (`memory.manager_class` selects
a backend; default `deermem` is self-contained). DeerMem-private settings moved
from the top level of `memory:` into `memory.backend_config`, and the
`/memory/config` response (and `client.get_memory_config()`) changed shape.
- **memory:** `/memory/config` and `client.get_memory_config()` no longer return
flat DeerMem fields (`storage_path`, `max_facts`, `debounce_seconds`,
`token_counting`, `guaranteed_*`, `staleness_*`, ...). They return
`{enabled, mode, injection_enabled, manager_class, backend_config}` where
`backend_config` is an opaque dict the active backend self-interprets. Memory
*data* responses (`/memory`, `/memory/status` data) are unchanged. External
API/SDK clients reading the old flat fields must read `backend_config` instead.
- **memory:** Custom `memory.storage_class` moved: the old default path
`deerflow.agents.memory.storage.FileMemoryStorage` no longer exists (now
`deerflow.agents.memory.backends.deermem.deermem.core.storage.FileMemoryStorage`).
Custom `MemoryStorage` subclasses must accept `config` in `__init__` (was
no-arg). A broken/old `storage_class` logs an error and falls back to
`FileMemoryStorage` (won't crash) -- update the path + signature to restore it.
- **memory:** `storage_path` semantics changed from a FILE path to a root
DIRECTORY. Pre-abstraction, an absolute `storage_path` was the shared memory
file (opting out of per-user isolation) and a relative value was the global
file under the data base_dir. Now `storage_path` (absolute or relative) is the
root directory; per-user memory lives at `{storage_path}/users/{uid}/memory.json`.
An upgrade keeping the old default `storage_path: memory.json` (a relative file
name) would orphan per-user memory or hit `NotADirectoryError` on save, so the
legacy migration **drops file-style `storage_path` values (ending in `.json`)
with a warning** and the factory **raises** if `storage_path` resolves to an
existing file. Set `memory.backend_config.storage_path` to a directory for a
custom root.
### Changed
- **memory:** Pre-abstraction top-level `memory.*` DeerMem fields
(`storage_path`, `max_facts`, `debounce_seconds`, `model_name`,
`token_counting`, `staleness_*`, `consolidation_*`, ...) are **auto-migrated
into `backend_config`** on load with a warning, so an upgrade does NOT silently
revert customized settings to defaults (`model_name` ->
`backend_config.model.model`). Move them under `memory.backend_config` in
`config.yaml` to silence the warning.
- **memory:** Added `memory.mode` (`middleware` | `tool`); `tool` mode registers
memory tools (`memory_search`/`add`/`update`/`delete`) the model calls directly
instead of passive per-turn summarization. `manager_class` resolution is now
fail-fast (raises `ValueError` on an unknown backend instead of silently
falling back).
### Fixed
- **models:** Honor `api_base` on every `BaseChatOpenAI` subclass (`VllmChatModel`,
`MindIEChatModel`, `PatchedChatMiMo`, `PatchedChatStepFun`, `PatchedChatMiniMax`),
not just `ChatOpenAI` / `PatchedChatOpenAI`. Those five previously dropped the
configured endpoint silently and then failed every request with an opaque
`unexpected keyword argument 'api_base'`; the unknown-config-key warning was
disabled for them as well. Both now gate on `issubclass(BaseChatOpenAI)`. ([#4146])
## [2.0.0] — 2026-06-15
DeerFlow 2.0 is a ground-up rewrite around a "super agent" harness with
sub-agents, persistent memory, sandbox execution, and an extensible
skills/tools system. It shares no code with the 1.x line, which now lives on
the [`main-1.x` branch](https://github.com/bytedance/deer-flow/tree/main-1.x).
This release closes [milestone 2.0.0](https://github.com/bytedance/deer-flow/milestone/1)
with **180 merged pull requests** since the first 2.0 milestone tag.
### ⚠ Breaking changes
- **harness:** Hydrate runs from `RunStore` and persist interrupted status. Run
cancellation/multitask semantics now require a working RunStore on the
worker that owns the run; cross-worker cancels return 409 instead of
silently appearing successful. ([#2932])
### Added
#### Agents & runtime
- **agent:** Custom-agent self-updates with user isolation — agents can persist
edits to their own `SOUL.md` / `config.yaml` from inside a normal chat.
([#2713])
- **loop-detection:** Make loop detection configurable with per-tool frequency
overrides; keep configurable on/off switch. ([#2586], [#2711])
- **loop-detection:** Defer warning injection so detector pairs cleanly with
tool-call lifecycle. ([#2752])
- **run:** Propagate `model_name` from the gateway request through the runtime
and persistence stack into the SQLite-backed store. ([#2775])
- **subagents:** Stream subagent token usage to the header via terminal task
events. ([#2882])
- **memory:** Add `memory.token_counting` config to opt out of tiktoken for
network-restricted deployments. ([#3465])
- **suggest:** Make AI follow-up question suggestions optional. ([#3591])
#### Models & integrations
- **models:** Add StepFun reasoning model adapter. ([#3461])
- **community:** Add Brave Search web search tool. ([#3528])
- **channels:** Enhance Discord with mention-only mode, thread routing, and
typing indicators. ([#2842])
- **im:** Add user-owned IM channel connections — users can bind their own
Slack/Telegram/Discord/Feishu/DingTalk/WeChat/WeCom accounts on top of the
operator-configured bots. ([#3487])
- **models:** Add patched MiMo reasoning content support. ([#3298])
- **models:** Add MiniMax provider for image/video/podcast skills plus a new
music-generation skill. ([#3437])
- **community:** Add SearXNG and Browserless web search/fetch tools. ([#3451])
- **community:** Add Serper Google Images provider for `image_search`. ([#3575])
- **channels:** Stream Telegram agent replies by editing the placeholder
message in place. ([#3534])
#### Observability
- **trace:** Set the LangGraph trace name to `lead_agent` (or the custom
agent's `agent_name`) for cleaner Langfuse/LangSmith traces. ([#3101])
- **frontend:** Refine token usage display modes. ([#2329])
- **defaults:** Enable token usage tracking by default. ([#2841])
- **defaults:** Raise default summarization trigger threshold. ([#3174])
- **trace:** Attribute subagent spans to the parent thread's Langfuse trace.
([#3611])
#### Skills
- **skill:** Add `blocking-io-guard` skill for blocking-IO triage and runtime
anchors. ([#3503])
- **skill:** Add maintainer issue and PR workflow skill. ([#3554])
- **skill:** Strengthen the maintainer orchestrator review workflow. ([#3606])
### Performance
- **harness:** Push thread metadata filters into SQL instead of post-filtering
in Python. ([#2865])
- **runtime:** Index runs by `thread_id` to avoid O(n) scans in `RunManager`.
([#3499])
- **runtime:** Index messages in `MemoryRunEventStore` to avoid O(n) scans.
([#3531])
- **persistence:** Cache `Base.to_dict` column reflection per class. ([#3654])
- **sandbox:** Speed up `should_ignore_name` in glob/grep walks. ([#3657])
### Security
- **upload:** Reject symlinked upload destinations. ([#2623])
- **uploads:** Add Windows support for safe symlink-protected uploads.
([#2794])
- **mcp:** Mask sensitive values in MCP config API responses. ([#2667])
- **mcp:** Harden the MCP config endpoint against malformed input. ([#3425])
- **auth:** Reject cross-site auth POSTs. ([#2740])
- **gateway:** Cap skill artifact preview decompression to prevent
zip-bomb-style abuse. ([#2963])
- **sandbox:** Mount the host Docker socket only in aio (DooD) sandbox mode.
([#3517])
- **sandbox:** Do not bind-mount host CLI auth dirs by default. ([#3521])
### Fixed
#### Runtime, gateway & persistence
- **runtime:** Rollback restore checkpoint now supersedes newer checkpoints.
([#2582])
- **runtime:** Persist run message summaries. ([#2850])
- **runtime:** Bound `write_file` execution-failure observations to keep
failure traces from blowing out the context. ([#3133])
- **runtime:** Protect the sync singleton's init and reset paths. ([#3413])
- **runtime:** Avoid PostgreSQL aggregate `FOR UPDATE` on run events.
([#2962])
- **runs:** Restore historical runs from persistent store after a gateway
restart. ([#2989])
- **gateway:** Return ISO 8601 timestamps from threads endpoints. ([#2599])
- **gateway:** Make cancel idempotent for already-interrupted runs. ([#3058])
- **gateway:** Split `stream_existing_run` into per-method routes for unique
OpenAPI `operationId`s. ([#3228])
- **events:** Serialize structured DB event content. ([#2762])
- **persistence:** Emit timezone-aware timestamps from SQLite-backed stores.
([#3130])
- **persistence:** Reuse token usage model grouping expression. ([#2910])
- **runs:** Ignore stale run reconnect conflicts. ([#3284])
- **nginx:** Defer CORS to the gateway allowlist instead of double-applying it.
([#2861])
- **persistence:** Fix runtime journal run lifecycle events. ([#3470])
- **gateway:** Enforce thread ownership on stateless run endpoints. ([#3473])
- **runtime:** Propagate interrupt through SSE values events for the LangGraph
SDK. ([#3605])
- **serialization:** Strip base64 image data from streamed values events.
([#3631])
- **history:** Strip base64 image data from REST endpoint responses. ([#3535])
- **gateway:** Attribute token usage to the actual models. ([#3658])
#### Agents, subagents & middleware
- **subagents:** Make subagent timeout terminal state atomic. ([#2583])
- **subagents:** Use model override for tools and middleware. ([#2641])
- **subagents:** Consolidate `system_prompt` and skills into a single
`SystemMessage`. ([#2701])
- **subagent:** Isolate subagents from the parent run's checkpointer.
([#3559])
- **agents:** Make `update_agent` honor `runtime.context` `user_id` like
`setup_agent` does. ([#2867])
- **agents:** Resolve duplicate `todos` channel type conflict in
`TodoMiddleware`. ([#3200])
- **agents:** Offload blocking filesystem IO in the custom-agent router off
the event loop. ([#3457])
- **agents:** Keep new agent bootstrap in user scope. ([#2784])
- **loop-detection:** Keep tool-call pairing on warn injection. ([#2725])
- **middleware:** Sync raw tool-call metadata. ([#2757])
- **middleware:** Handle invalid tool calls in dangling pairing middleware.
([#2891])
- **middleware:** Prevent todo completion reminder IM-message leak. ([#2907])
- **middleware:** Normalize tool result adjacency before model calls.
([#2939])
- **agents:** Require `config.yaml` in `resolve_agent_dir` to skip memory-only
directories. ([#3481])
- **agents:** Sync `agent_name` across context/configurable and reject empty
soul. ([#3553])
- **middleware:** Offload the uploads scan in `UploadsMiddleware` off the event
loop. ([#3311])
- **middleware:** Offload memory injection off the event loop to prevent
tiktoken blocking. ([#3411])
- **middleware:** Externalize oversized tool output into the sandbox for
non-mounted sandboxes. ([#3417])
- **middleware:** Preserve the sandbox reducer in middleware state. ([#3629])
- **subagents:** Raise general-purpose `max_turns` to 150 and default timeout to
30 min. ([#3610])
#### Memory & tracing
- **memory:** Replace short-lived `asyncio.run()` with a persistent event
loop. ([#2627])
- **memory:** Isolate queued memory updates by agent. ([#2941])
- **memory:** Parse wrapped memory-update JSON responses. ([#3252])
- **tracing:** Propagate `session_id` and `user_id` into Langfuse traces.
([#2944])
- **trace:** Decode unicode escape sequences in non-ASCII memory trace info.
([#3104])
#### Tools, sandbox & MCP
- **mcp:** Fix env resolution in MCP config lists. ([#2556])
- **models:** Record Codex token usage in `usage_metadata`. ([#2585])
- **sandbox:** Supplement `list_running` in `RemoteSandboxBackend`. ([#2716])
- **sandbox:** Disable MSYS path conversion for Git Bash on Windows.
([#2766])
- **sandbox:** Avoid blocking sandbox readiness polling. ([#2822])
- **sandbox:** Uphold the `/mnt/user-data` contract at the `Sandbox` API
boundary. ([#2881])
- **sandbox:** Scope provisioner PVC data by user. ([#2973])
- **sandbox:** Merge idempotent sandbox state updates. ([#3518])
- **tools:** Introduce `Runtime` type alias to eliminate Pydantic serialization
warnings. ([#2774])
- **tools:** Preserve `tool_search` promotions across re-entrant
`get_available_tools`. ([#2885])
- **harness:** Wrap async-only config tools for sync client execution.
([#2878])
- **harness:** Wrap all async-only tools for sync clients. ([#2935])
- **tool-search:** Reliably hide deferred MCP schemas by removing the
ContextVar. ([#3342])
- **search:** Fix DDGS Wikipedia region handling. ([#3423])
- **web_fetch:** Support a proxy for the Jina reader in restricted networks.
([#3430])
- **sandbox:** Persist lazily-acquired sandbox state via `Command`. ([#3464])
- **sandbox:** Fix stale AIO sandbox cache reuse. ([#3494])
- **sandbox:** Create a shell session before retrying on a fresh id. ([#3577])
- **sandbox:** Stop flagging string-literal path fragments as unsafe absolute
paths. ([#3623])
- **sandbox:** Return an actionable hint when `read_file` hits a binary file.
([#3624])
- **mcp:** Make stdio MCP-produced files resolvable via virtual sandbox paths.
([#3600])
- **mcp:** Surface admin-required state on the settings tools page. ([#3533])
- **mcp:** Add a tools cache reset endpoint. ([#3602])
- **uploads:** Fix the upload file size contract. ([#3408])
#### Skills & channels
- **skills:** Enforce `allowed-tools` metadata. ([#2626])
- **skills:** Harden slash skill activation across chat channels. ([#3466])
- **skills:** Fix custom skill install permissions. ([#3241])
- **channels:** Authenticate gateway command requests. ([#2742])
- **skills:** Surface the offending line and a quoting hint on SKILL.md YAML
errors. ([#3335])
- **skills:** Keep skill archive installation off the event loop. ([#3505])
- **channels:** Ignore hidden control messages when extracting replies.
([#3270])
- **channels:** Reload config on channel restart. ([#3514])
- **channels:** Surface WeCom WebSocket connection failures. ([#3526])
- **channels:** Close the Discord file handle after upload. ([#3561])
- **channels:** Require a bound identity for user-owned IM messages. ([#3578])
- **channels:** Scope IM files and helper commands to the owner. ([#3579])
- **channels:** Make runtime provider state authoritative. ([#3580])
- **channels:** Harden runtime credential management APIs. ([#3581])
- **channels:** Make the channel connect flow deterministic. ([#3582])
- **channels:** Centralize shared channel retry helpers. ([#3583])
- **channels:** Add operational guardrails. ([#3584])
- **channels:** Unsubscribe channel listeners by equality. ([#3608])
#### Auth
- **auth:** Replace setup-status 429 rate limit with a cached response.
([#2915])
- **auth:** Persist auto-generated JWT secret so it survives restarts.
([#2933])
- **auth:** Align auth-disabled mode with mock history loading. ([#3471])
#### Frontend
- **frontend:** Restore `localhost` fallback for `getGatewayConfig` in prod
mode. ([#2718])
- **chat:** Prevent the first user message from being swallowed in new
conversations. ([#2731])
- **frontend:** Use backend thread token usage for the header total. ([#2800])
- **frontend:** Wait for async chat submit before clearing the input.
([#2940])
- **frontend:** Resolve login page flickering and the resize-observer loop.
([#2954])
- **frontend:** Deduplicate restored thread messages. ([#2958])
- **frontend:** Avoid duplicate optimistic user message. ([#3002])
- **frontend:** Hide the copy button for streaming assistant messages.
([#3176])
- **frontend:** Show a new thread in the sidebar immediately on creation.
([#3283])
- **frontend:** Isolate new chat thread messages. ([#3508])
- **frontend:** Cap deeply nested list indentation to prevent render crashes.
([#3393], [#3570])
- **token-usage:** Dedupe token usage aggregation by message id. ([#2770])
- **frontend:** Fall back to Streamdown clipboard copy. ([#3397])
- **frontend:** Remove the Backspace shortcut for deleting prompt attachments.
([#3410])
- **frontend:** Restructure the Memory settings toolbar into two rows. ([#3433])
- **suggestions:** Strip inline `<think>` reasoning before parsing follow-up
questions. ([#3435])
- **frontend:** Stop fetching follow-up suggestions when they are disabled.
([#3599])
- **frontend:** Paginate the workspace chat list beyond 50 threads. ([#3485])
- **frontend:** Prevent user message bubble overflow with long unbreakable
strings. ([#3488])
- **frontend:** Keep the workspace interactive when the SSR auth probe cannot
reach the gateway. ([#3495])
- **frontend:** Render user messages as plain text and cap blockquote nesting.
([#3502])
- **frontend:** Reset the active chat after deletion. ([#3519])
- **frontend:** Improve the mobile workspace layout. ([#3646])
- **frontend:** Render full content for multi-part AI messages. ([#3649])
#### Build, deploy, scripts & config
- **packaging:** Add `postgres` extra for store/checkpointer support; clarify
install guidance. ([#2584])
- **harness:** Resolve runtime paths from the project root. ([#2642])
- **docker:** Force nginx to resolve upstream names at request time.
([#2717])
- **docker:** Default Gateway to a single worker to prevent multi-worker
breakage. ([#3475])
- **scripts:** Preserve `uv` extras across `make dev` restarts. ([#2767],
[#2754])
- **scripts:** Clean up local nginx on stop. ([#3005])
- **deploy:** Fall back to `python` / `openssl` when `python3` is absent for
secret generation. ([#3074])
- **config:** Make the reload boundary discoverable from code. ([#3144],
[#3153])
- **replay-e2e:** Key replay fixtures by caller and conversation. ([#3453])
- **setup:** Refresh LLM provider wizard defaults. ([#3421])
- **config:** Coerce null `config.yaml` list sections to an empty list. ([#3434])
- **scripts:** Exclude runtime state from gateway reload. ([#3426])
- **scripts:** Create the backend/sandbox dir before the uvicorn reload-exclude.
([#3460])
- **scripts:** Stop next-server correctly after `make start-daemon`. ([#3498])
- **makefile:** Fix per-commit hooks installation. ([#3569])
- **replay-e2e:** Match replay by conversation, not the living system prompt.
([#3436])
### Changed
- **provider (refactor):** Share assistant payload replay matching across
providers. ([#3307])
- **lead-agent (refactor):** Make `build_middlewares` public to drop the last
cross-module private import. ([#3458])
- **todo (refactor):** Remove the unused completion reminder counter. ([#3530])
### Documentation
- Document blocking-IO detection usage and maintenance. ([#3233])
- Clean standalone LangGraph server remnants from docs. ([#3301])
- Add AI assistance disclosure to the PR template and CONTRIBUTING. ([#3398])
- Document custom AIO sandbox images. ([#3548])
### Internal
- **dev:** Add async/thread boundary detector. ([#2936])
- **runtime:** Add lifecycle end-to-end coverage. ([#2946])
- **windows:** Add `PYTHONIOENCODING` and `PYTHONUTF8` to backend Makefile
targets. ([#3069])
- **blocking-io:** Fail-loud repo-root resolution and shared detector CLI
shim. ([#3512])
- **runtime:** Add a Blockbuster runtime anchor for `JsonlRunEventStore` async
IO. ([#3313])
- **ci:** Consolidate PR/issue labeling and fix the reviewing-job crash and
label thrash. ([#3455])
[2.0.0]: https://github.com/bytedance/deer-flow/releases/tag/v2.0.0
[#2329]: https://github.com/bytedance/deer-flow/pull/2329
[#2556]: https://github.com/bytedance/deer-flow/pull/2556
[#2582]: https://github.com/bytedance/deer-flow/pull/2582
[#2583]: https://github.com/bytedance/deer-flow/pull/2583
[#2584]: https://github.com/bytedance/deer-flow/pull/2584
[#2585]: https://github.com/bytedance/deer-flow/pull/2585
[#2586]: https://github.com/bytedance/deer-flow/pull/2586
[#2599]: https://github.com/bytedance/deer-flow/pull/2599
[#2623]: https://github.com/bytedance/deer-flow/pull/2623
[#2626]: https://github.com/bytedance/deer-flow/pull/2626
[#2627]: https://github.com/bytedance/deer-flow/pull/2627
[#2641]: https://github.com/bytedance/deer-flow/pull/2641
[#2642]: https://github.com/bytedance/deer-flow/pull/2642
[#2667]: https://github.com/bytedance/deer-flow/pull/2667
[#2701]: https://github.com/bytedance/deer-flow/pull/2701
[#2711]: https://github.com/bytedance/deer-flow/pull/2711
[#2713]: https://github.com/bytedance/deer-flow/pull/2713
[#2716]: https://github.com/bytedance/deer-flow/pull/2716
[#2717]: https://github.com/bytedance/deer-flow/pull/2717
[#2718]: https://github.com/bytedance/deer-flow/pull/2718
[#2725]: https://github.com/bytedance/deer-flow/pull/2725
[#2731]: https://github.com/bytedance/deer-flow/pull/2731
[#2740]: https://github.com/bytedance/deer-flow/pull/2740
[#2742]: https://github.com/bytedance/deer-flow/pull/2742
[#2752]: https://github.com/bytedance/deer-flow/pull/2752
[#2754]: https://github.com/bytedance/deer-flow/pull/2754
[#2757]: https://github.com/bytedance/deer-flow/pull/2757
[#2762]: https://github.com/bytedance/deer-flow/pull/2762
[#2766]: https://github.com/bytedance/deer-flow/pull/2766
[#2767]: https://github.com/bytedance/deer-flow/pull/2767
[#2770]: https://github.com/bytedance/deer-flow/pull/2770
[#2774]: https://github.com/bytedance/deer-flow/pull/2774
[#2775]: https://github.com/bytedance/deer-flow/pull/2775
[#2784]: https://github.com/bytedance/deer-flow/pull/2784
[#2794]: https://github.com/bytedance/deer-flow/pull/2794
[#2800]: https://github.com/bytedance/deer-flow/pull/2800
[#2822]: https://github.com/bytedance/deer-flow/pull/2822
[#2841]: https://github.com/bytedance/deer-flow/pull/2841
[#2842]: https://github.com/bytedance/deer-flow/pull/2842
[#2850]: https://github.com/bytedance/deer-flow/pull/2850
[#2861]: https://github.com/bytedance/deer-flow/pull/2861
[#2865]: https://github.com/bytedance/deer-flow/pull/2865
[#2867]: https://github.com/bytedance/deer-flow/pull/2867
[#2878]: https://github.com/bytedance/deer-flow/pull/2878
[#2881]: https://github.com/bytedance/deer-flow/pull/2881
[#2882]: https://github.com/bytedance/deer-flow/pull/2882
[#2885]: https://github.com/bytedance/deer-flow/pull/2885
[#2891]: https://github.com/bytedance/deer-flow/pull/2891
[#2907]: https://github.com/bytedance/deer-flow/pull/2907
[#2910]: https://github.com/bytedance/deer-flow/pull/2910
[#2915]: https://github.com/bytedance/deer-flow/pull/2915
[#2932]: https://github.com/bytedance/deer-flow/pull/2932
[#2933]: https://github.com/bytedance/deer-flow/pull/2933
[#2935]: https://github.com/bytedance/deer-flow/pull/2935
[#2936]: https://github.com/bytedance/deer-flow/pull/2936
[#2939]: https://github.com/bytedance/deer-flow/pull/2939
[#2940]: https://github.com/bytedance/deer-flow/pull/2940
[#2941]: https://github.com/bytedance/deer-flow/pull/2941
[#2944]: https://github.com/bytedance/deer-flow/pull/2944
[#2946]: https://github.com/bytedance/deer-flow/pull/2946
[#2954]: https://github.com/bytedance/deer-flow/pull/2954
[#2958]: https://github.com/bytedance/deer-flow/pull/2958
[#2962]: https://github.com/bytedance/deer-flow/pull/2962
[#2963]: https://github.com/bytedance/deer-flow/pull/2963
[#2973]: https://github.com/bytedance/deer-flow/pull/2973
[#2989]: https://github.com/bytedance/deer-flow/pull/2989
[#3002]: https://github.com/bytedance/deer-flow/pull/3002
[#3005]: https://github.com/bytedance/deer-flow/pull/3005
[#3058]: https://github.com/bytedance/deer-flow/pull/3058
[#3069]: https://github.com/bytedance/deer-flow/pull/3069
[#3074]: https://github.com/bytedance/deer-flow/pull/3074
[#3101]: https://github.com/bytedance/deer-flow/pull/3101
[#3104]: https://github.com/bytedance/deer-flow/pull/3104
[#3130]: https://github.com/bytedance/deer-flow/pull/3130
[#3133]: https://github.com/bytedance/deer-flow/pull/3133
[#3144]: https://github.com/bytedance/deer-flow/pull/3144
[#3153]: https://github.com/bytedance/deer-flow/pull/3153
[#3174]: https://github.com/bytedance/deer-flow/pull/3174
[#3176]: https://github.com/bytedance/deer-flow/pull/3176
[#3200]: https://github.com/bytedance/deer-flow/pull/3200
[#3228]: https://github.com/bytedance/deer-flow/pull/3228
[#3233]: https://github.com/bytedance/deer-flow/pull/3233
[#3241]: https://github.com/bytedance/deer-flow/pull/3241
[#3252]: https://github.com/bytedance/deer-flow/pull/3252
[#3270]: https://github.com/bytedance/deer-flow/pull/3270
[#3283]: https://github.com/bytedance/deer-flow/pull/3283
[#3284]: https://github.com/bytedance/deer-flow/pull/3284
[#3298]: https://github.com/bytedance/deer-flow/pull/3298
[#3301]: https://github.com/bytedance/deer-flow/pull/3301
[#3307]: https://github.com/bytedance/deer-flow/pull/3307
[#3311]: https://github.com/bytedance/deer-flow/pull/3311
[#3313]: https://github.com/bytedance/deer-flow/pull/3313
[#3335]: https://github.com/bytedance/deer-flow/pull/3335
[#3342]: https://github.com/bytedance/deer-flow/pull/3342
[#3393]: https://github.com/bytedance/deer-flow/pull/3393
[#3397]: https://github.com/bytedance/deer-flow/pull/3397
[#3398]: https://github.com/bytedance/deer-flow/pull/3398
[#3408]: https://github.com/bytedance/deer-flow/pull/3408
[#3410]: https://github.com/bytedance/deer-flow/pull/3410
[#3411]: https://github.com/bytedance/deer-flow/pull/3411
[#3413]: https://github.com/bytedance/deer-flow/pull/3413
[#3417]: https://github.com/bytedance/deer-flow/pull/3417
[#3421]: https://github.com/bytedance/deer-flow/pull/3421
[#3423]: https://github.com/bytedance/deer-flow/pull/3423
[#3425]: https://github.com/bytedance/deer-flow/pull/3425
[#3426]: https://github.com/bytedance/deer-flow/pull/3426
[#3430]: https://github.com/bytedance/deer-flow/pull/3430
[#3433]: https://github.com/bytedance/deer-flow/pull/3433
[#3434]: https://github.com/bytedance/deer-flow/pull/3434
[#3435]: https://github.com/bytedance/deer-flow/pull/3435
[#3436]: https://github.com/bytedance/deer-flow/pull/3436
[#3437]: https://github.com/bytedance/deer-flow/pull/3437
[#3451]: https://github.com/bytedance/deer-flow/pull/3451
[#3453]: https://github.com/bytedance/deer-flow/pull/3453
[#3455]: https://github.com/bytedance/deer-flow/pull/3455
[#3457]: https://github.com/bytedance/deer-flow/pull/3457
[#3458]: https://github.com/bytedance/deer-flow/pull/3458
[#3460]: https://github.com/bytedance/deer-flow/pull/3460
[#3461]: https://github.com/bytedance/deer-flow/pull/3461
[#3464]: https://github.com/bytedance/deer-flow/pull/3464
[#3465]: https://github.com/bytedance/deer-flow/pull/3465
[#3466]: https://github.com/bytedance/deer-flow/pull/3466
[#3470]: https://github.com/bytedance/deer-flow/pull/3470
[#3471]: https://github.com/bytedance/deer-flow/pull/3471
[#3473]: https://github.com/bytedance/deer-flow/pull/3473
[#3475]: https://github.com/bytedance/deer-flow/pull/3475
[#3481]: https://github.com/bytedance/deer-flow/pull/3481
[#3485]: https://github.com/bytedance/deer-flow/pull/3485
[#3487]: https://github.com/bytedance/deer-flow/pull/3487
[#3488]: https://github.com/bytedance/deer-flow/pull/3488
[#3494]: https://github.com/bytedance/deer-flow/pull/3494
[#3495]: https://github.com/bytedance/deer-flow/pull/3495
[#3498]: https://github.com/bytedance/deer-flow/pull/3498
[#3499]: https://github.com/bytedance/deer-flow/pull/3499
[#3502]: https://github.com/bytedance/deer-flow/pull/3502
[#3503]: https://github.com/bytedance/deer-flow/pull/3503
[#3505]: https://github.com/bytedance/deer-flow/pull/3505
[#3508]: https://github.com/bytedance/deer-flow/pull/3508
[#3512]: https://github.com/bytedance/deer-flow/pull/3512
[#3514]: https://github.com/bytedance/deer-flow/pull/3514
[#3517]: https://github.com/bytedance/deer-flow/pull/3517
[#3518]: https://github.com/bytedance/deer-flow/pull/3518
[#3519]: https://github.com/bytedance/deer-flow/pull/3519
[#3521]: https://github.com/bytedance/deer-flow/pull/3521
[#3526]: https://github.com/bytedance/deer-flow/pull/3526
[#3528]: https://github.com/bytedance/deer-flow/pull/3528
[#3530]: https://github.com/bytedance/deer-flow/pull/3530
[#3531]: https://github.com/bytedance/deer-flow/pull/3531
[#3533]: https://github.com/bytedance/deer-flow/pull/3533
[#3534]: https://github.com/bytedance/deer-flow/pull/3534
[#3535]: https://github.com/bytedance/deer-flow/pull/3535
[#3548]: https://github.com/bytedance/deer-flow/pull/3548
[#3553]: https://github.com/bytedance/deer-flow/pull/3553
[#3554]: https://github.com/bytedance/deer-flow/pull/3554
[#3559]: https://github.com/bytedance/deer-flow/pull/3559
[#3561]: https://github.com/bytedance/deer-flow/pull/3561
[#3569]: https://github.com/bytedance/deer-flow/pull/3569
[#3570]: https://github.com/bytedance/deer-flow/pull/3570
[#3575]: https://github.com/bytedance/deer-flow/pull/3575
[#3577]: https://github.com/bytedance/deer-flow/pull/3577
[#3578]: https://github.com/bytedance/deer-flow/pull/3578
[#3579]: https://github.com/bytedance/deer-flow/pull/3579
[#3580]: https://github.com/bytedance/deer-flow/pull/3580
[#3581]: https://github.com/bytedance/deer-flow/pull/3581
[#3582]: https://github.com/bytedance/deer-flow/pull/3582
[#3583]: https://github.com/bytedance/deer-flow/pull/3583
[#3584]: https://github.com/bytedance/deer-flow/pull/3584
[#3591]: https://github.com/bytedance/deer-flow/pull/3591
[#3599]: https://github.com/bytedance/deer-flow/pull/3599
[#3600]: https://github.com/bytedance/deer-flow/pull/3600
[#3602]: https://github.com/bytedance/deer-flow/pull/3602
[#3605]: https://github.com/bytedance/deer-flow/pull/3605
[#3606]: https://github.com/bytedance/deer-flow/pull/3606
[#3608]: https://github.com/bytedance/deer-flow/pull/3608
[#3610]: https://github.com/bytedance/deer-flow/pull/3610
[#3611]: https://github.com/bytedance/deer-flow/pull/3611
[#3623]: https://github.com/bytedance/deer-flow/pull/3623
[#3624]: https://github.com/bytedance/deer-flow/pull/3624
[#3629]: https://github.com/bytedance/deer-flow/pull/3629
[#3631]: https://github.com/bytedance/deer-flow/pull/3631
[#3646]: https://github.com/bytedance/deer-flow/pull/3646
[#3649]: https://github.com/bytedance/deer-flow/pull/3649
[#3654]: https://github.com/bytedance/deer-flow/pull/3654
[#3657]: https://github.com/bytedance/deer-flow/pull/3657
[#3658]: https://github.com/bytedance/deer-flow/pull/3658
[#4146]: https://github.com/bytedance/deer-flow/pull/4146
Reference in New Issue View Git Blame Copy Permalink