Commit Graph
390 Commits
Author SHA1 Message Date
huige66631andRockChinQ ce6b647fe7 feat(mcp): detect OAuth-protected remote MCP servers (#2363)
* feat(mcp): surface OAuth-required server tests

* fix(mcp): show connection failure details in status cards

---------

Co-authored-by: RockChinQ <[email protected]>
2026-09-09 16:13:33 +08:00
Tynwink 1ba3c1ec72 Merge pull request #2520 from langbot-app/feat/api-key-system-context
为 lbctl 增加 API Key 发现与管理能力
当前为 lbctl 提供的能力通过 system.py -> SYSTEM_CAPABILITY_OPERATIONS 维护,后续可通过统一的接口暴露能力,避免频繁维护常量。
2026-09-09 14:47:00 +08:00
TynwinkandCopilot Autofix powered by AI 3a82aa5fcc Potential fix for pull request finding 'Empty except'
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-09-09 14:39:49 +08:00
WODE25500andWODE25500 fc1c998434 fix: Matrix relogin UnboundLocalError (#2516)
Co-authored-by: WODE25500 <[email protected]>
2026-09-09 13:51:42 +08:00
Tynwink2000 d90253cc77 feat(api): advertise provider and model management 2026-09-09 11:18:01 +08:00
Tynwink2000 d8b3dad212 feat(api): support explicit provider secret projection 2026-09-09 10:38:16 +08:00
Tynwink2000 8281eb18c9 feat(api): advertise plugin and skill management 2026-09-09 00:12:40 +08:00
Tynwink2000 4eea3419e8 feat(api): advertise knowledge and MCP management 2026-09-08 23:07:43 +08:00
Tynwink2000 814740ea68 feat(api): advertise managed read operations 2026-09-08 18:53:55 +08:00
Tynwink2000 e6e8258545 feat(api): advertise extension operation capabilities 2026-09-08 17:43:11 +08:00
Tynwink2000 1a69747a06 feat(api): expose task status to api keys 2026-09-08 14:06:13 +08:00
Tynwink2000 1fa5e2f755 feat(api): add system capabilities endpoint 2026-09-08 13:03:02 +08:00
RockChinQ ea3e32c904 feat(processors): streamline event debugging and run inspection 2026-09-08 02:30:59 +08:00
RockChinQ 237fa6545d feat(processors): add explicitly bound plugin event processors 2026-09-08 00:43:35 +08:00
RockChinQ 812eb09ee4 fix(pipeline): apply returned plugin event contexts 2026-09-07 23:51:34 +08:00
267232c24f fix(security): harden password recovery with usable eight-character codes (#2477)
Use eight securely random recovery-code characters with concurrency-safe online throttling. Preserve existing keys and verify recovery through browser and real SQLite integration tests.

Co-authored-by: [email protected] <[email protected]>
Co-authored-by: dadachann <[email protected]>
2026-09-07 15:31:54 +00:00
QuasarRyan d6443b10bc feat(platform): add Mattermost platform adapter (#2515) 2026-09-07 22:46:47 +08:00
Tynwink 0577689da4 Merge pull request #2517 from langbot-app/feat/api-key-system-context
feat(api): add system context endpoint for lbctl
2026-09-07 14:51:31 +08:00
Tynwink2000 bc32eb3ca0 feat(api): add system context endpoint for lbctl 2026-09-07 14:22:27 +08:00
Hyuanddadachann 0f216a0d4d feat(provider): support Codex subscriptions with ChatGPT sign-in (#2513)
* feat(provider): support Codex subscriptions with ChatGPT sign-in

* style: format Codex live integration test

* fix(provider): preserve Codex identity in temporary model tests

* fix(web): portal provider selector without dialog overflow

* fix(web): allow native scrolling in provider dropdown

* fix(provider): surface safe Codex quota and upstream errors

* fix(web): provide reliable Codex copy feedback in dialogs

* feat(provider): confirm cascade deletion from edit dialog

* fix(persistence): discard connections after failed commit

* fix(web): polish provider loading and confirmation motion

---------

Co-authored-by: dadachann <[email protected]>
2026-09-06 23:31:02 +08:00
RockChinQ 75f117ae50 fix(provider): preserve explicit streaming finish reasons 2026-09-06 00:33:20 +08:00
RockChinQ f5d6a3b348 fix(agent): tolerate intent annotations on no-argument platform tools 2026-09-05 17:15:20 +08:00
Hyu 8f0a55a1f4 fix(agent-debug): stream execution traces with platform mocks and coverage 2026-09-05 15:34:29 +08:00
Hyuanddadachann 1cfe87186c docs: update published documentation links (#2509)
Co-authored-by: dadachann <[email protected]>
2026-09-05 00:55:18 +08:00
leonoxoanddadachann 9794df0933 feat(n8n-runner): support async response handling (#2487)
* feat(n8n-runner): support async response handling

* fix(n8n-runner): expose response handling in form

* fix(n8n-runner): preserve async response semantics

---------

Co-authored-by: dadachann <[email protected]>
2026-09-04 22:36:40 +08:00
Hyu a4d36aa2db feat(agent): add event-aware tool permissions 2026-09-04 15:37:41 +08:00
mintya de3c0b00ad fix(bot): roll back inserted bot row when adapter fails to load (#2497)
create_bot inserts the Bot row first and only then instantiates the
adapter via platform_mgr.load_bot. When the adapter constructor raises
(e.g. KeyError on a missing credential key), the insert is already
committed and nothing removes the row: the HTTP layer returns 500 but
a permanently disabled orphan bot stays in the DB. Callers never
receive the bot uuid, so they cannot compensate by deleting it, and
load_bots_from_db skips enable=False bots, so the orphan is never
loaded or surfaced anywhere.

Wrap load_bot in try/except and delete the inserted row before
re-raising. Add a regression test asserting the DELETE is issued when
the adapter constructor fails.
2026-09-04 13:06:12 +08:00
Amir Fathi d942bfe19a fix(wecom): read media_id instead of media in send_message() (#2447)
WecomMessageConverter.yiri2target() always emits {'media_id': ...} for
image/voice/file parts (never 'media'), matching the correct usage
already in reply_message(). send_message(), the entry point plugins
use via PluginToRuntimeAction.SEND_MESSAGE, instead read
content['media'], which is never set, so any image/voice/file part
raises KeyError and aborts the send.

Refs #1687

Signed-off-by: Amir Fathi <[email protected]>
2026-09-04 13:02:40 +08:00
Hyuanddadachann b44b8f474d fix(cloud): provision login workspace just in time (#2505)
* fix(cloud): provision login workspace just in time

* fix(oauth): send callback URI during code exchange

* fix(oauth): preserve callback URI through browser exchange

* fix(oauth): negotiate redirect-bound codes

---------

Co-authored-by: dadachann <[email protected]>
2026-09-03 23:14:44 +08:00
Hyu 7c64756203 fix(ui): improve agent debug and model test feedback 2026-09-03 14:51:01 +08:00
Hyuanddadachann ab52684a01 Revert "fix(cloud): request automatic Space launch (#2501)" (#2503)
This reverts commit d50957fc4f.

Co-authored-by: dadachann <[email protected]>
2026-09-03 12:16:21 +08:00
Hyuanddadachann d50957fc4f fix(cloud): request automatic Space launch (#2501)
Co-authored-by: dadachann <[email protected]>
2026-09-03 11:44:32 +08:00
Hyu be0214cf4d feat(storage): group usage by application and runtimes 2026-09-03 00:11:05 +08:00
Hyuanddadachann c8d8b1aac4 fix(cloud): serialize directory catch-up (#2500)
Co-authored-by: dadachann <[email protected]>
2026-09-02 21:57:53 +08:00
Hyuanddadachann 018dd7a363 fix(cloud): launch newly registered accounts through Space (#2499)
* fix(cloud): launch new accounts through Space

* style: format Cloud entry URL

* fix(cloud): wait for launch workspace projection

---------

Co-authored-by: dadachann <[email protected]>
2026-09-02 21:41:35 +08:00
mintya 5ca30133a3 fix(lark): stop duplicating final reply text in streaming card (#2490)
* fix(lark): stop duplicating final reply text in streaming card

* fix(lark): stop duplicating final reply text in streaming card
2026-09-01 21:24:54 +08:00
Hyuanddadachann 8cf0015502 fix(dingtalk): restore card auto layout (#2491)
Co-authored-by: dadachann <[email protected]>
2026-09-01 17:56:02 +08:00
Hyu a87c814dae feat(web): improve marketplace install workflows 2026-09-01 16:43:50 +08:00
Hyuanddadachann bf8d418ad4 feat(monitoring): paginate sessions and messages (#2489)
* feat(monitoring): paginate sessions and messages

* fix(monitoring): align detail pages with local dates

---------

Co-authored-by: dadachann <[email protected]>
2026-09-01 15:14:29 +08:00
Hyu e5e62c8fe9 fix(plugin): keep status responsive during installation 2026-09-01 12:46:16 +08:00
Hyu 91e09af76a fix(web): complete pluginized agent onboarding flows 2026-09-01 10:41:29 +08:00
Hyu 7e51044a87 Merge fix/box-reconnect-skill-context into dev/4.11.x 2026-08-31 19:18:34 +08:00
Hyu b4980ab536 fix(box): reload workspace-scoped skills after reconnect 2026-08-31 19:18:19 +08:00
Hyu fde04e64f6 Merge remote-tracking branch 'origin/master' into dev/4.11.x
# Conflicts:
#	src/langbot/pkg/api/http/controller/groups/pipelines/pipelines.py
#	src/langbot/pkg/api/http/service/bot.py
#	src/langbot/pkg/provider/runners/localagent.py
#	src/langbot/templates/metadata/pipeline/ai.yaml
#	tests/unit_tests/api/service/test_bot_service.py
#	tests/unit_tests/provider/runners/test_difysvapi_runner.py
#	tests/unit_tests/utils/test_safe_regex.py
#	web/src/app/infra/entities/adapter-categories.ts
#	web/src/app/wizard/page.tsx
#	web/src/i18n/locales/en-US.ts
#	web/src/i18n/locales/ja-JP.ts
#	web/src/i18n/locales/zh-Hans.ts
#	web/tests/e2e/plugin-page-auth.spec.ts
2026-08-31 17:17:47 +08:00
RockChinQandHyu 1b7ae791b3 fix(plugin): return not found after removal (#2483)
Co-authored-by: Hyu <[email protected]>
2026-08-31 13:40:03 +08:00
NeosandHyu e69a80f5e9 Windows 兼容性修复 + Dify API 适配 + 企微 WS 加载优化 (#2470)
* fix: Windows fsync requires write access to file descriptor

- _fsync_file: os.O_RDONLY -> os.O_RDWR (Windows _commit() requires write access)
- _fsync_directory: tolerate OSError on fsync and os.open (chmod 0o700 blocks access on Windows)

* fix: Dify SSE empty data lines and upload response format mismatch

- Skip malformed/flushed SSE data lines (JSONDecodeError)
- Accept HTTP 200 besides 201 for file upload response
- Unwrap data wrapper in upload response (resp.get('data', resp))

* feat: WeCom WS mode sends empty initial stream frame for loading spinner

Send an empty reply_stream frame immediately after stream session
creation so the WeCom client shows its built-in loading indicator
while the pipeline processes the message (e.g. RAG retrieval).

* fix(compat): harden Windows, Dify, and WeCom changes

* fix(migration): clean interrupted SQLite temp files

---------

Co-authored-by: Hyu <[email protected]>
2026-08-29 22:34:10 +08:00
Hyuanddadachann bafdaf0033 fix(monitoring): restore SQLite token statistics (#2479)
* fix(monitoring): restore SQLite token statistics

Allow the monitored SQLite strftime bucket expression through the tenant SQL guard and preserve structured backend errors in the token dashboard. Add persistence and frontend regressions.\n\nVerified-by: independent-review

* test(runtime): accept reconcile timeout in capacity stub

Keep the PostgreSQL capacity probe aligned with the runtime handler contract and assert the bounded reconcile timeout.

---------

Co-authored-by: dadachann <[email protected]>
2026-08-28 11:41:42 +08:00
be3734ffda feat(wizard): rework agent onboarding flow (#2471)
* feat(wizard): rework agent onboarding flow

* fix(web): support LAN development access

* fix(wizard): parse ranked model selection entries

* feat(wizard): add inbound bot verification

* feat(wizard): add floating page bot verification

* fix(wizard): repair HTTP bot inbound test setup

* feat(wizard): streamline custom model onboarding

* feat(wizard): label page bot test preview

* style(space): apply ruff formatting

* fix(wizard): polish AI engine onboarding

* fix(wizard): clarify local account message test

* feat(wizard): animate AI engine transitions

* fix(wizard): align AI engine setup headers

---------

Co-authored-by: langbot-dev <[email protected]>
Co-authored-by: RockChinQ <[email protected]>
2026-08-28 01:30:30 +08:00
leonoxo 855ae2bdba fix(line): map LINE mentions to At elements so the at-bot rule works (#2478)
The LINE adapter passed text through as a single Plain component,
ignoring the mention payload (mentions[].index/length/isSelf) that the
Line Messaging API includes in the webhook. As a result:

- At(target=bot_account_id) never appeared in the message chain, so the
  'at-bot' group respond rule silently dropped every @bot mention.
- The bot only replied when the message happened to match the prefix
  rule (e.g. starting with 'ai').

Now LINEMessageConverter reads message.message.mention and builds the
chain per mention position:

- Bot mention (isSelf) -> At(target=bot_account_id) so AtBotRule matches
  the same way as other adapters (dingtalk/lark etc.).
- Other mentions -> At(target=<line user id>, display=<mention text>).
  At.__str__ already prepends '@', so the display text carries no
  double '@' and the rendered text (prefix/regexp rules, quotes,
  session context) is byte-identical to before.
- Missing/out-of-bounds mentions are skipped defensively.

target2yiri becomes an instance method (like wechatpad/aiocqhttp) so
the converters can hold bot_account_id; LINEAdapter passes it in from
its own config.
2026-08-27 18:38:27 +08:00
fishzjp b66db86bff fix(provider): stringify MCP tool results for OpenAI-compatible APIs (#2476)
execute_func_call returns list[ContentElement] for MCP tools, but the
runner assigned that list directly to the tool-message content. The
OpenAI chat-completions spec requires tool-message content to be a
string, so OpenAI-compatible endpoints return HTTP 500 when the raw
list is sent.

Serialize the list to a string before building the tool message, using
ContentElement.__str__ which returns the text payload for text elements
and a human-readable placeholder for images and files. Fixes #2457.
2026-08-27 18:19:04 +08:00