Commit Graph

369 Commits

Author SHA1 Message Date
肖应宇 31bb8db442 docs(01): research phase domain 2026-04-07 12:05:50 +08:00
Titan db0ea1ab18 feat(chats): implement dynamic styling based on xclaw_used parameter 2026-04-05 23:39:44 +08:00
Titan 45b95c4538 feat(skills): support batch skill bootstrap via content_ids; clear parent dir once before per-skill write 2026-04-05 18:37:55 +08:00
Titan 2b0581db71 fix: centralize UUID generation and validate query thread_id for skillBootstrap; ensure single execution and correct thread dir 2026-04-05 18:37:55 +08:00
Titan 867bb6de46 feat(skills): add remote YAML bootstrap and materialization APIs 2026-04-05 18:16:05 +08:00
0d05c55565 fix: avoid command palette hydration mismatch on macOS (#1563)
# Conflicts:
#	frontend/src/components/workspace/command-palette.tsx

Co-authored-by: luoxiao6645 <luoxiao6645@gmail.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-04-05 16:35:33 +08:00
DanielWalnut 3fc1e69db3 fix: unblock concurrent threads and workspace hydration (#1839)
* fix: unblock concurrent threads and workspace hydration

* fix: restore async title generation

* fix: address PR review feedback

* style: format lead agent prompt
2026-04-04 21:19:35 +08:00
luobo d8409b116a fix(frontend): keep prompt attachments from breaking before upload (#1833)
* fix(frontend): preserve prompt attachment files during upload

* fix(frontend): harden prompt attachment fallback and tests

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-04-04 14:54:35 +08:00
luobo 3218add274 fix(frontend): block unsupported .app uploads (#1834)
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-04-04 14:42:26 +08:00
Albert Zheng 89043c6e8d fix(frontend): resolve button hydration mismatch with undefined variant/size (#1506)
Server-rendered data-variant={undefined} didn't match client hydration.
Now only render data-variant and data-size when explicitly set.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: JeffJiang <for-eleven@hotmail.com>
2026-04-04 11:21:04 +08:00
Admire 4f829e4f3c Add explicit save action for agent creation (#1798)
* Add explicit save action for agent creation

* Hide internal save prompts and retry agent reads

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-04-03 19:54:42 +08:00
Admire 27d573e27c fix(ui): avoid follow-up suggestion overlap (#1777)
* fix(ui): avoid follow-up suggestion overlap

* fix(ui): address followup review feedback

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-04-03 15:48:41 +08:00
JeffJiang 45eaae684f Add documents site (#1767)
* feat: add docs site

- Implemented dynamic routing for MDX documentation pages with language support.
- Created layout components for documentation with a header and footer.
- Added metadata for various documentation sections in English and Chinese.
- Developed initial content for the DeerFlow App and Harness documentation.
- Introduced i18n hooks and translations for English and Chinese languages.
- Enhanced header component to include navigation links for documentation and blog.
- Established a structure for tutorials and reference materials.
- Created a new translations file to manage locale-specific strings.

* feat: enhance documentation structure and content for application and harness sections

* feat: update .gitignore to include .playwright-mcp and remove obsolete Playwright YAML file

* fix(docs): correct punctuation and formatting in documentation files

* feat(docs): remove outdated index.mdx file from documentation

* fix(docs): update documentation links and improve Chinese description in index.mdx

* fix(docs): update title in Chinese for meta information in _meta.ts
2026-04-03 07:25:40 +08:00
Admire a61a5d4f0b fix(ui): avoid over-segmenting cjk messages (#1726) 2026-04-02 19:45:43 +08:00
yangzheli 438cd7d2f1 fix(frontend): add missing rel="noopener noreferrer" to target="_blank" links (#1741)
* fix(frontend): add missing rel="noopener noreferrer" to target="_blank" links

Prevent tabnabbing attacks and referrer leakage by ensuring all
external links with target="_blank" include both noopener and
noreferrer in the rel attribute.

Made-with: Cursor

* style: fix code formatting
2026-04-02 17:32:52 +08:00
fb85fcd2d8 Fix/1681 llm call retry handling (#1683)
* fix(runtime): handle llm call errors gracefully

* fix(runtime): preserve graph control flow in llm retry middleware

---------

Co-authored-by: luoxiao6645 <luoxiao6645@gmail.com>
2026-04-02 10:12:17 +08:00
Admire 5573a10519 fix(frontend): persist model selection per thread (#1553)
* fix(frontend): persist model selection per thread

* fix(frontend): apply thread model override on fallback

* refactor(frontend): split thread settings hook

* fix frontend local storage guards
2026-04-01 23:27:03 +08:00
JeffJiang 79f49cdb44 fix(artifact): enhance artifact content loading to include URL for non-write files (#1678) 2026-04-01 11:38:55 +08:00
Rosemary1812 8d84bab712 fix(frontend): improve network error message for agent name check (#1605)
* fix(frontend): distinguish CORS errors   from generic name check failures

* fix(frontend): improve network error message for agent name check

* Fix network error message in zh-CN locale

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-31 21:14:05 +08:00
Admire 3c3b4d2684 fix(frontend): route agent checks to gateway (#1572)
* fix(frontend): route agent checks to gateway

* fix(frontend): proxy langgraph requests locally

* fix(frontend): keep zh-CN text readable

* fix(frontend): add exact local api rewrites

* fix(frontend): support docker-safe internal rewrites

* Update frontend/src/core/agents/api.ts

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-30 21:04:59 +08:00
Admire 4e47e04cb6 chore(uv): speed up Docker builds with mirrors (#1600)
* docker mirror defaults

* fix: make docker mirror defaults overridable

* fix docker compose default pypi index

* fix: restore upstream pypi defaults

* docs: remove misleading env example mirrors

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-30 20:16:44 +08:00
Admire 3297918100 feat: support memory import and export (#1521)
* feat: support memory import and export

* fix(memory): address review feedback

* style: format memory settings page

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-30 17:25:47 +08:00
JeffJiang 5e18b6cf72 fix(config): update SSR fallback in getBaseOrigin function (#1617) 2026-03-30 16:13:32 +08:00
rayhpeng 6cc259dc60 feat(gateway): implement LangGraph Platform API in Gateway, replace langgraph-cli (#1403)
* feat(gateway): implement LangGraph Platform API in Gateway, replace langgraph-cli

Implement all core LangGraph Platform API endpoints in the Gateway,
allowing it to fully replace the langgraph-cli dev server for local
development. This eliminates a heavyweight dependency and simplifies
the development stack.

Changes:
- Add runs lifecycle endpoints (create, stream, wait, cancel, join)
- Add threads CRUD and search endpoints
- Add assistants compatibility endpoints (search, get, graph, schemas)
- Add StreamBridge (in-memory pub/sub for SSE) and async provider
- Add RunManager with atomic create_or_reject (eliminates TOCTOU race)
- Add worker with interrupt/rollback cancel actions and runtime context injection
- Route /api/langgraph/* to Gateway in nginx config
- Skip langgraph-cli startup by default (SKIP_LANGGRAPH_SERVER=0 to restore)
- Add unit tests for RunManager, SSE format, and StreamBridge

* fix: drain bridge queue on client disconnect to prevent backpressure

When on_disconnect=continue, keep consuming events from the bridge
without yielding, so the worker is not blocked by a full queue.
Only on_disconnect=cancel breaks out immediately.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: remove pytest import

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: Fix default stream_mode to ["values", "messages-tuple"]

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: Remove unused if_exists field from ThreadCreateRequest

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: address review comments on gateway LangGraph API

- Mount runs.py router in app.py (missing include_router)
- Normalize interrupt_before/after "*" to node list before run_agent()
- Use entry.id for SSE event ID instead of counter
- Drain bridge queue on disconnect when on_disconnect=continue
- Reuse serialization helper in wait_run() for consistent wire format
- Reject unsupported multitask_strategy with 400
- Remove SKIP_LANGGRAPH_SERVER fallback, always use Gateway

* feat: extract app.state access into deps.py

Encapsulate read/write operations for singleton objects (RunManager,
StreamBridge, checkpointer) held in app.state into a shared utility,
reducing repeated access patterns across router modules.

* feat: extract deerflow.runtime.serialization module with tests

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: replace duplicated serialization with deerflow.runtime.serialization

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: extract app/gateway/services.py with run lifecycle logic

Create a service layer that centralizes SSE formatting, input/config
normalization, and run lifecycle management. Router modules will delegate
to these functions instead of using private cross-imported helpers.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: wire routers to use services layer, remove cross-module private imports

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* style: apply ruff formatting to refactored files

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(runtime): support LangGraph dev server and add compat route

- Enable official LangGraph dev server for local development workflow
- Decouple runtime components from agents package for better separation
- Provide gateway-backed fallback route when dev server is skipped
- Simplify lifecycle management using context manager in gateway

* feat(runtime): add Store providers with auto-backend selection

- Add async_provider.py and provider.py under deerflow/runtime/store/
- Support memory, sqlite, postgres backends matching checkpointer config
- Integrate into FastAPI lifespan via AsyncExitStack in deps.py
- Replace hardcoded InMemoryStore with config-driven factory

* refactor(gateway): migrate thread management from checkpointer to Store and resolve multiple endpoint failures

- Add Store-backed CRUD helpers (_store_get, _store_put, _store_upsert)
- Replace checkpoint-scanning search with two-phase strategy:
  phase 1 reads Store (O(threads)), phase 2 backfills from checkpointer
  for legacy/LangGraph Server threads with lazy migration
- Extend Store record schema with values field for title persistence
- Sync thread title from checkpoint to Store after run completion
- Fix /threads/{id}/runs/{run_id}/stream 405 by accepting both
  GET and POST methods; POST handles interrupt/rollback actions
- Fix /threads/{id}/state 500 by separating read_config and
  write_config, adding checkpoint_ns to configurable, and
  shallow-copying checkpoint/metadata before mutation
- Sync title to Store on state update for immediate search reflection
- Move _upsert_thread_in_store into services.py, remove duplicate logic
- Add _sync_thread_title_after_run: await run task, read final
  checkpoint title, write back to Store record
- Spawn title sync as background task from start_run when Store exists

* refactor(runtime): deduplicate store and checkpointer provider logic

Extract _ensure_sqlite_parent_dir() helper into checkpointer/provider.py
and use it in all three places that previously inlined the same mkdir logic.
Consolidate duplicate error constants in store/async_provider.py by importing
from store/provider.py instead of redefining them.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(runtime): move SQLite helpers to runtime/store, checkpointer imports from store

_resolve_sqlite_conn_str and _ensure_sqlite_parent_dir now live in
runtime/store/provider.py. agents/checkpointer/provider and
agents/checkpointer/async_provider import from there, reversing the
previous dependency direction (store → checkpointer becomes
checkpointer → store).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(runtime): extract SQLite helpers into runtime/store/_sqlite_utils.py

Move resolve_sqlite_conn_str and ensure_sqlite_parent_dir out of
checkpointer/provider.py into a dedicated _sqlite_utils module.
Functions are now public (no underscore prefix), making cross-module
imports semantically correct. All four provider files import from
the single shared location.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(gateway): use adelete_thread to fully remove thread checkpoints on delete

AsyncSqliteSaver has no adelete method — the previous hasattr check
always evaluated to False, silently leaving all checkpoint rows in the
database. Switch to adelete_thread(thread_id) which deletes every
checkpoint and pending-write row for the thread across all namespaces
(including sub-graph checkpoints).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(gateway): remove dead bridge_cm/ckpt_cm code and fix StrEnum lint

app.py had unreachable code after the async-with lifespan refactor:
bridge_cm and ckpt_cm were referenced but never defined (F821), and
the channel service startup/shutdown was outside the langgraph_runtime
block so it never ran. Move channel service lifecycle inside the
async-with block where it belongs.

Replace str+Enum inheritance in RunStatus and DisconnectMode with
StrEnum as suggested by UP042.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* style: format with ruff

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: JeffJiang <for-eleven@hotmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-30 16:02:23 +08:00
Admire 468f443c0a feat: support manual add and edit for memory facts (#1538)
* feat: support manual add and edit for memory facts

* fix: restore memory updater save helper

* fix: address memory fact review feedback

* fix: remove duplicate memory fact edit action

* docs: simplify memory fact review setup

* docs: relax memory review startup instructions

* fix: clear rebase marker in memory settings page

* fix: address memory fact review and format issues

* fix: address memory fact review feedback

* refactor: make memory fact updates explicit patch semantics

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-29 23:53:23 +08:00
Sleepy Ranx 🌙 52f482503a fix(frontend): prevent submit during IME composition (#1562) 2026-03-29 22:36:38 +08:00
Echo-Nie f3799ff9cc docs: fix some broken links (#1567)
* Fix path for TitleMiddleware implementation

* Fix link to Provisioner Setup Guide in CONFIGURATION.md

* Update file path for TitleMiddleware implementation

* Update image paths in Leica photography article
2026-03-29 21:52:28 +08:00
greatmengqi 1b3de8a9f3 style: format unformatted files and add .omc/ to prettierignore (#1539)
Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com>
2026-03-29 16:45:31 +08:00
greatmengqi bc3e314ff1 ci: enforce code formatting checks for backend and frontend (#1536) 2026-03-29 15:34:38 +08:00
Admire a9dbb3de9c feat: add memory management actions and local filters in memory settings (#1467)
* Add MVP memory management actions

* Fix memory settings locale coverage

* Polish memory management interactions

* Add memory search and type filters

* Refine memory settings review feedback

* docs: simplify memory settings review setup

* fix: restore memory updater compatibility helpers

* fix: address memory settings review feedback

* docs: soften memory sample review wording

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: JeffJiang <for-eleven@hotmail.com>
2026-03-29 13:14:45 +08:00
zihao a99b01cda6 fix(frontend): separate mock and default LangGraph clients (#1504)
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-28 16:33:22 +08:00
7. Sun 4e14405284 fix: prevent SpeechRecognition instance leaks on render (#1369)
* fix: remove unstable dependencies from speech recognition effect

* fix: use refs to prevent stale closures in speech recognition

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-28 16:20:38 +08:00
JeffJiang a406a2623e fix: refactor to use getBaseOrigin for URL construction in backend and LangGraph base URL functions (#1494) 2026-03-28 12:18:03 +08:00
luo jiyin 0f7d9462ff docs(frontend): update better-auth README notes (#1487) 2026-03-27 22:58:55 +08:00
luo jiyin ef940f7992 chore(frontend): align format scripts with Makefile and README (#1481)
* chore(frontend): add format scripts

* docs(frontend): document format commands
2026-03-27 22:49:41 +08:00
Kaushik Rajan 18bf05728c fix: add build-arg support for proxies and mirrors in Docker builds (#1346)
* fix: add build-arg support for proxies and mirrors in Docker builds (#1260)

Pin Debian images to bookworm, make UV source image configurable,
and pass APT_MIRROR/NPM_REGISTRY/UV_IMAGE through docker-compose.

* fix: ensure build args use consistent defaults across compose and Dockerfiles

UV_IMAGE: ${UV_IMAGE:-} resolved to empty when unset, overriding the
Dockerfile ARG default and breaking `FROM ${UV_IMAGE}`. Also configure
COREPACK_NPM_REGISTRY before pnpm download and propagate NPM_REGISTRY
into the prod stage.

* fix: dearmor NodeSource GPG key to resolve signing error

Pipe the downloaded key through gpg --dearmor so apt can verify
the repository signature (fixes NO_PUBKEY 2F59B5F99B1BE0B4).

---------

Co-authored-by: JeffJiang <for-eleven@hotmail.com>
2026-03-27 10:35:40 +08:00
7. Sun efaed5badc fix: remove unused radix Icon import from suggestion (#1368)
* fix: use create_chat_model for summarization alias

* fix: remove unused radix Icon import from suggestion

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-26 21:14:56 +08:00
Henry Li e827bc6037 feat: hide model ID for safety reason, only show the display_name (#1410)
Co-authored-by: Henry Li <lixin.henry@bytedance.com>
2026-03-26 21:13:32 +08:00
RockeyDon c7b97b6084 Add packages section to pnpm-workspace.yaml (#1382)
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-26 16:09:35 +08:00
JeffJiang 59f556c434 fix(config): return full URLs for backend and LangGraph base URLs (#1392) 2026-03-26 15:43:37 +08:00
Simon Su 270b5fd280 fix(frontend): add stable ids for chat resizable panels (#1341)
Signed-off-by: sysusugan <sugan@foxmail.com>
2026-03-25 20:58:15 +08:00
evenboos 75f17412f8 fix: repair frontend check command and docs (#1281)
* fix: repair frontend check command and docs

* docs: 补充 Linux 下 Docker 权限排障说明
2026-03-24 17:02:54 +08:00
dependabot[bot] 4bd4475d7d build(deps): bump h3 from 1.15.5 to 1.15.10 in /frontend (#1280)
Bumps [h3](https://github.com/h3js/h3) from 1.15.5 to 1.15.10.
- [Release notes](https://github.com/h3js/h3/releases)
- [Changelog](https://github.com/h3js/h3/blob/v1.15.10/CHANGELOG.md)
- [Commits](https://github.com/h3js/h3/compare/v1.15.5...v1.15.10)

---
updated-dependencies:
- dependency-name: h3
  dependency-version: 1.15.10
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-03-24 14:39:57 +08:00
Willem Jiang 0d0ccbb03a chron(ci):setup the lint check in frontend (#1276)
* chron(ci):setup the lint check in frontend

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix(ci): correct lint-check.yml indentation, add Python 3.12 setup, upgrade checkout to v4 (#1277)

* Initial plan

* Fix lint-check.yml: fix steps indentation, add Python 3.12 setup, upgrade checkout to v4

Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com>
Agent-Logs-Url: https://github.com/bytedance/deer-flow/sessions/7b4d4fad-f024-453a-9f93-5fc2dd83b471

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
2026-03-24 10:48:18 +08:00
Willem Jiang e8218f67ce fix(frontend): fix the build error of i18n (#1274) 2026-03-24 09:55:39 +08:00
Gao Mingfei 5087b4aaac fix(frontend): filter task tool calls when rendering SubtaskCard (#1242)
Only tool calls with name === "task" should be rendered as SubtaskCard.
Previously all tool_calls were mapped to IDs, causing SubtaskCard to
render for non-task tool calls whose IDs were never registered in the
subtask context, resulting in a TypeError on task.status.

Signed-off-by: Gao Mingfei <g199209@gmail.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-24 09:44:36 +08:00
Matt Van Horn b6d0becb35 feat(frontend): display token usage per conversation turn (#1229)
Surface the usage_metadata that PR #1218 added to the streaming API.
A compact indicator in the chat header shows cumulative tokens consumed
per thread, with a tooltip breakdown of input/output/total counts.

Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-24 08:59:35 +08:00
amdoi7. 35c7d536ee fix(threads): clean up local thread data after thread deletion (#1262)
* fix(threads): clean up local thread data after thread deletion

Delete DeerFlow-managed thread directories after the web UI removes a LangGraph thread.
This keeps local thread data in sync with conversation deletion and adds regression coverage for the cleanup flow.

* fix(threads): address thread cleanup review feedback

Encode thread cleanup URLs in the web client, keep cache updates explicit when no thread search data is cached, and return a generic 500 response from the cleanup endpoint while documenting the sanitized error behavior.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-24 00:36:08 +08:00
Willem Jiang 02585c9da8 fix(hotkey):support to open settings with hotkey (#1259) 2026-03-23 18:53:06 +08:00
Matt Van Horn e5cd2d3242 feat(frontend): add Cmd+K command palette and keyboard shortcuts (#1230)
* feat(frontend): add Cmd+K command palette and keyboard shortcuts

Wire up the existing shadcn/ui Command component as a global command
palette. Adds a useGlobalShortcuts hook for Cmd+K (palette), Cmd+Shift+N
(new chat), Cmd+, (settings), and Cmd+/ (shortcuts help overlay).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(frontend): address Copilot review feedback on command palette

- Normalize event.key with toLowerCase() for reliable Shift+key matching
- Replace dead deerflow:open-settings event with router.push navigation
- Use platform-appropriate Shift label (Shift+ on Windows/Linux, glyph on Mac)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-03-23 18:35:35 +08:00