5c98329170
fix(web): unify processor creation and entity detail loading states
2026-09-15 13:51:39 +08:00
d497defbf7
fix(runner): keep installation context within each stream resume
2026-09-15 13:51:27 +08:00
9db097399c
ci: recover beta PyPI publication from immutable tags
2026-09-14 17:00:58 +00:00
f7cef62290
test: declare agent usage in beta runtime fixture
2026-09-14 16:56:35 +00:00
89d42bedaa
chore: release 4.11.0-beta.1 with SDK 0.6.0-beta.1
2026-09-14 16:47:47 +00:00
184037a427
feat(bots): bind plugin processor configurations independently
2026-09-15 00:28:13 +08:00
e913658e03
fix(processors): clarify processing modes and reorder choices
2026-09-13 00:18:36 +08:00
1277c6da07
feat(runner): filter marketplace recommendations by explicit usage
2026-09-12 12:51:16 +08:00
fa15f48fd7
feat(models): sort catalog by listing date availability and price
2026-09-12 02:07:33 +08:00
18c1ed93b8
fix(models): show reasoning icon in model selectors
2026-09-12 01:23:06 +08:00
8b85876a19
fix(models): simplify capability badges
2026-09-12 01:09:12 +08:00
18b84566c3
fix(models): flag models without pricing
2026-09-12 01:04:03 +08:00
50d544aa6f
fix(models): align selector metadata
2026-09-12 00:57:55 +08:00
33b4035140
feat(models): show LangBot Models pricing
2026-09-12 00:53:47 +08:00
a3509b3626
feat(models): show LangBot Models availability
2026-09-11 21:17:20 +08:00
e631da0073
fix(runner): align SDK pin and complete real runtime verification ( #2525 )
...
* fix(runner): align SDK pin and workspace-aware integration fixtures
* fix(ci): format sources and resolve current migration head
* test(persistence): align standalone migration fixtures with current models
* test(web): align smoke fixtures with current processor UI
---------
Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com >
2026-09-11 12:57:29 +08:00
24ddcfe13e
fix(i18n): localize Runner component labels
2026-09-11 00:03:09 +08:00
d93e44d82d
feat(runner): authorize contextual platform APIs
2026-09-11 00:02:44 +08:00
f24a7c9bb2
feat(runner): unify plugin execution across agents and event processors
2026-09-10 18:04:38 +08:00
8903a40c41
fix(runtime): preserve explicit replies and report bot configuration errors
2026-09-10 17:21:22 +08:00
b7a04f7a24
fix(bots): streamline detail layout and event listening
2026-09-10 15:29:52 +08:00
15fa0f50e3
fix(ui): distinguish EventProcessor with a trigger icon
2026-09-10 15:18:04 +08:00
d1c79a35e8
fix(4.11): align omni adapters and EventProcessor marketplace support
2026-09-10 15:06:57 +08:00
5ba25c39af
feat(processors): refine plugin processor configuration and presentation
2026-09-09 15:37:12 +08:00
ea3e32c904
feat(processors): streamline event debugging and run inspection
2026-09-08 02:30:59 +08:00
237fa6545d
feat(processors): add explicitly bound plugin event processors
2026-09-08 00:43:35 +08:00
812eb09ee4
fix(pipeline): apply returned plugin event contexts
2026-09-07 23:51:34 +08:00
5d0657b1db
feat(agent-debug): edit event data with compact forms
2026-09-06 01:57:47 +08:00
2a46325232
fix(agent-debug): simplify and localize tool call traces
2026-09-06 00:33:32 +08:00
75f117ae50
fix(provider): preserve explicit streaming finish reasons
2026-09-06 00:33:20 +08:00
f5d6a3b348
fix(agent): tolerate intent annotations on no-argument platform tools
2026-09-05 17:15:20 +08:00
8f0a55a1f4
fix(agent-debug): stream execution traces with platform mocks and coverage
2026-09-05 15:34:29 +08:00
a4d36aa2db
feat(agent): add event-aware tool permissions
2026-09-04 15:37:41 +08:00
7c64756203
fix(ui): improve agent debug and model test feedback
2026-09-03 14:51:01 +08:00
be0214cf4d
feat(storage): group usage by application and runtimes
2026-09-03 00:11:05 +08:00
380bdfeca6
fix(web): contain nested scrolling without blocking forms
2026-09-01 17:29:59 +08:00
a87c814dae
feat(web): improve marketplace install workflows
2026-09-01 16:43:50 +08:00
982d660236
fix(web): harden agent runner marketplace flows
2026-09-01 12:46:16 +08:00
e5e62c8fe9
fix(plugin): keep status responsive during installation
2026-09-01 12:46:16 +08:00
91e09af76a
fix(web): complete pluginized agent onboarding flows
2026-09-01 10:41:29 +08:00
7e51044a87
Merge fix/box-reconnect-skill-context into dev/4.11.x
2026-08-31 19:18:34 +08:00
b4980ab536
fix(box): reload workspace-scoped skills after reconnect
2026-08-31 19:18:19 +08:00
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
1b7ae791b3
fix(plugin): return not found after removal ( #2483 )
...
Co-authored-by: Hyu <chenhyu@proton.me >
2026-08-31 13:40:03 +08:00
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 <chenhyu@proton.me >
2026-08-29 22:34:10 +08:00
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 <185672915+dadachann@users.noreply.github.com >
2026-08-28 11:41:42 +08:00
aeff8d7e30
fix(i18n): complete wizard locale keys
2026-08-28 01:37:45 +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 <langbot@users.noreply.github.com >
Co-authored-by: RockChinQ <rockchinq@gmail.com >
2026-08-28 01:30:30 +08:00
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
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
Hyu