mirror/nanobot
1
0
Fork 0
mirror of https://github.com/HKUDS/nanobot.git synced 2026-05-03 00:05:55 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,068 Commits 18 Branches 15 Tags
Commit Graph

2068 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
chengyongru
8f4baaa5ce feat(gateway): support multiple instances with --workspace and --config options 
- Add --workspace/-w flag to specify workspace directory
- Add --config/-c flag to specify config file path
- Move cron store to workspace directory for per-instance isolation
- Enable running multiple nanobot instances simultaneously
 2026-03-02 23:18:54 +08:00
David Markey
ecdfaf0a5a feat(custom-provider): add x-session-affinity header for prompt caching 2026-03-02 11:03:12 +00:00
Re-bin
3c79404194 fix(providers): sanitize thinking_blocks by provider and harden content normalization 2026-03-02 06:58:10 +00:00
Re-bin
1601470436 Merge PR #1399: reload cron store on timer tick 2026-03-02 06:38:00 +00:00
Re-bin
9877195de5 chore(cron): remove redundant timer comment 2026-03-02 06:37:57 +00:00
Re-bin
f3979c0ee6 Merge branch 'main' into pr-1399 2026-03-02 06:30:43 +00:00
Re-bin
3f79245b91 Merge PR #1406: normalize Matrix media metadata and attachment upload call 2026-03-02 06:28:48 +00:00
Re-bin
be4f83a760 Merge branch 'main' into pr-1406 2026-03-02 06:24:53 +00:00
Re-bin
b575606c9e Merge PR #1403: deny-by-default allowFrom with startup validation 2026-03-02 06:13:40 +00:00
Re-bin
bbfc1b40c1 security: deny-by-default allowFrom with wildcard support and startup validation 2026-03-02 06:13:37 +00:00
Wenjie Lei
2c63946519 fix(matrix): normalize media metadata and keyword-call attachment upload 2026-03-01 21:56:08 -08:00
chengyongru
d447be5ca2 security: deny by default in is_allowed for all channels 
When allow_from is not configured, block all access by default
instead of allowing everyone. This prevents unauthorized access
when channels are enabled without explicit allow lists.
 2026-03-02 13:18:43 +08:00
Joel Chan
e9d023f52c feat(discord): add group policy to control group respond behaviour 2026-03-02 12:16:49 +08:00
yzchen
dba93ae83a cron: reload jobs store on each timer tick 2026-03-02 11:19:45 +08:00
chengyongru
aed1ef5529 fix: add SIGTERM, SIGHUP handling and ignore SIGPIPE 
- Add handler for SIGTERM to prevent "Terminated" message on Linux
- Add handler for SIGHUP for terminal closure handling
- Ignore SIGPIPE to prevent silent process termination
- Change os._exit(0) to sys.exit(0) for proper cleanup

Fixes issue #1365

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 11:04:53 +08:00
chengyongru
ae788a17f8 chore: add .worktrees to .gitignore 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 11:03:54 +08:00
Sense_wang
521217a7f5 fix(telegram): enforce group_policy in _on_message 
When `group_policy` is set to "mention", skip messages in group chats
unless the bot is @mentioned or the message is a reply to the bot.

Fixes #1380
 2026-03-01 16:50:36 +00:00
Sense_wang
43329018f7 fix(telegram): add group_policy config for Telegram groups 
Add `group_policy` field to `TelegramConfig` with "open" (default) and
"mention" options, consistent with Slack and Matrix channel configs.
 2026-03-01 16:50:02 +00:00
zerone0x
8571df2e63 fix(feishu): split card messages when content has multiple tables 
Feishu rejects interactive cards that contain more than one table element
(API error 11310: card table number over limit).

Add FeishuChannel._split_elements_by_table_limit() which partitions the flat
card-elements list into groups of at most one table each.  The send() method
now iterates over these groups and sends each as its own card message, so all
tables are delivered to the user instead of the entire message being dropped.

Single-table and table-free messages are unaffected (one card, same as before).

Fixes #1382
 2026-03-01 15:13:44 +01:00
Re-bin
a5962170f6 Merge PR #1370: add web tools proxy support 2026-03-01 12:53:20 +00:00
Re-bin
15529c668e fix(web): sanitize proxy logs and polish search key hint 2026-03-01 12:53:18 +00:00
Re-bin
f5c0c75648 Merge branch 'main' into pr-1370 2026-03-01 12:48:01 +00:00
Re-bin
1109fdc682 Merge PR #1375: improve cron reminder context handling 2026-03-01 12:46:06 +00:00
Re-bin
a7d24192d9 fix(cron): route scheduled jobs through process_direct with english reminder prefix 2026-03-01 12:45:53 +00:00
VITOHJL
468dfc406b feat(cron): improve cron job context handling 
Improve cron job execution context to ensure proper message delivery and
session history recording.

Changes:
- Add [绯荤粺瀹氭椂浠诲姟] prefix to cron reminder messages to clearly mark
  them as system-driven, not user queries
- Use user role for cron reminder messages (required by some LLM APIs)
- Properly handle MessageTool to avoid duplicate message delivery
- Correctly save turn history with proper skip count
- Ensure Runtime Context is included in the message list

This ensures that:
1. Cron jobs execute with proper context
2. Messages are correctly delivered to users
3. Session history accurately records cron job interactions
4. The LLM understands these are system-driven reminders, not user queries
 2026-03-01 17:05:04 +08:00
chengyongru
82be2ae1a5 feat(tool): add web search proxy 2026-03-01 16:51:54 +08:00
Re-bin
aff8d8e9e1 Merge PR #1361: fix(feishu): parse post wrapper payload for rich text messages 2026-03-01 06:36:32 +00:00
Re-bin
4752e95a24 merge origin/main into pr-1361 2026-03-01 06:36:29 +00:00
Re-bin
c2bbd6d20d Merge branch 'main' into pr-1361 2026-03-01 06:30:10 +00:00
Re-bin
7eae842132 Merge PR #1339: style: unify code formatting 2026-03-01 06:13:29 +00:00
Re-bin
3c6c49cc5d Merge branch 'main' into pr-1339 
Made-with: Cursor

# Conflicts:
#	nanobot/cron/service.py
 2026-03-01 06:06:01 +00:00
Xubin Ren
c69e45f987
Merge PR #1371 to auto-reload jobs.json when modified externally 
fix(cron): auto-reload jobs.json when modified externally
 2026-03-01 14:02:37 +08:00
Re-bin
89e5a28097 fix(cron): auto-reload jobs.json when modified externally 2026-03-01 06:01:47 +00:00
Jack Lu
3ee061b879
Merge branch 'main' into main 2026-03-01 13:35:24 +08:00
Tink
80219baf25 feat(api): add OpenAI-compatible endpoint with x-session-key isolation 2026-03-01 10:53:45 +08:00
yzchen
2fc16596d0 fix(feishu): parse post wrapper payload for rich text messages 2026-03-01 02:17:10 +08:00
Re-bin
f172c9f381 docs: reformat release news with v0.1.4.post3 release 2026-02-28 18:06:56 +00:00
Re-bin
ee9bd6a96c docs: update v0.1.4.post3 release news 2026-02-28 18:04:12 +00:00
Re-bin
4f0530dd61 release: v0.1.4.post3 v0.1.4.post3 2026-02-28 17:55:18 +00:00
Re-bin
925302c01f Merge PR #1330: fix thinking mode support (reasoning_content + thinking_blocks) 2026-02-28 17:37:15 +00:00
Re-bin
5ca386ebf5 fix: preserve reasoning_content and thinking_blocks in session history 2026-02-28 17:37:12 +00:00
Re-bin
a47c2e9a37 Merge branch 'main' into pr-1330 
Made-with: Cursor

# Conflicts:
#	nanobot/providers/litellm_provider.py
 2026-02-28 17:25:53 +00:00
Xubin Ren
422969d468
Merge PR #1348: fix(lark): Remove non-existent stop() call on Lark ws.Client when enable lark channel 
fix(lark): Remove non-existent stop() call on Lark ws.Client when enable lark channel
 2026-03-01 01:23:27 +08:00
Xubin Ren
8c1627c594
Merge PR #1351 to add reasoning_effort config to enable LLM thinking mode 
feat: add reasoning_effort config to enable LLM thinking mode
 2026-03-01 01:20:49 +08:00
Re-bin
f9d72e2e74 feat: add reasoning_effort config to enable LLM thinking mode 2026-02-28 17:18:05 +00:00
zhangxiaoyu.york
9e2f69bd5a tidy up 2026-03-01 00:51:17 +08:00
Re-bin
0a5f3b6194 Merge PR #1346: fix(qq): disable botpy file log on read-only fs 2026-02-28 16:45:08 +00:00
Re-bin
c34e1053f0 fix(qq): disable botpy file log to fix read-only filesystem error 2026-02-28 16:45:06 +00:00
Re-bin
e0a78d78f9 Merge branch 'main' into pr-1346 2026-02-28 16:43:45 +00:00
Xubin Ren
76c3144c7c
Merge PR #1347 to streamline subagent prompt 
refactor: streamline subagent prompt by reusing ContextBuilder and SkillsLoader
 2026-03-01 00:38:44 +08:00