mirror/nanobot
1
0
Fork 0
mirror of https://github.com/HKUDS/nanobot.git synced 2026-04-04 18:32:44 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,574 Commits 11 Branches 11 Tags
Commit Graph

1574 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Xubin Ren
3c3a72ef82 update .gitignore 2026-04-03 16:02:23 +00:00
Xubin Ren
7113ad34f4
Merge PR #2733: harden agent runtime for long-running tasks 2026-04-02 22:34:00 +08:00
Xubin Ren
e4b335ce81 refactor: extract runtime response guards into utils runtime module 2026-04-02 13:54:40 +00:00
Xubin Ren
714a4c7bb6 fix(runtime): address review feedback on retry and cleanup 2026-04-02 10:57:12 +00:00
Xubin Ren
eefd7e60f2 Merge remote-tracking branch 'origin/main' into feat/runtime-hardening 2026-04-02 10:40:49 +00:00
Xubin Ren
3558fe4933 fix(cli): honor custom config path in channel commands 2026-04-02 18:37:46 +08:00
masterlyj
11ba733ab6 fix(test): update load_config mock to accept config_path parameter 2026-04-02 18:37:46 +08:00
masterlyj
7332d133a7 feat(cli): add --config option to channels login and status commands 
Allows users to specify custom config file paths when managing channels.

Usage:
  nanobot channels login weixin --config .nanobot-feishu/config.json
    nanobot channels status -c .nanobot-qq/config.json

    - Added optional --config/-c parameter to both commands
    - Defaults to ~/.nanobot/config.json when not specified
    - Maintains backward compatibility
 2026-04-02 18:37:46 +08:00
haosenwang1018
7a6416bcb2 test(matrix): skip cleanly when optional deps are missing 2026-04-02 18:17:00 +08:00
Xubin Ren
cc33057985 refactor(providers): rename openai responses helpers 2026-04-02 13:43:34 +08:00
Xubin Ren
ded0967c18 fix(providers): sanitize azure responses input messages 2026-04-02 13:43:34 +08:00
Kunal Karmakar
61d7411238 Fix failing test 2026-04-02 13:43:34 +08:00
Kunal Karmakar
76226274bf Failing test 2026-04-02 13:43:34 +08:00
Kunal Karmakar
e206cffd7a Add tests and handle json 2026-04-02 13:43:34 +08:00
Kunal Karmakar
ac2ee58791 Add tests and logs 2026-04-02 13:43:34 +08:00
Kunal Karmakar
7c44aa92ca Fill up gaps 2026-04-02 13:43:34 +08:00
Kunal Karmakar
8c0607e079 Use SDK for stream 2026-04-02 13:43:34 +08:00
Kunal Karmakar
0417c3f03b Use OpenAI responses API 2026-04-02 13:43:34 +08:00
Xubin Ren
9ba413c82e test(cron): cover deliver flag on scheduled jobs 2026-04-02 13:03:46 +08:00
lucario
15faa3b115 fix(cron): fix extra indent for properties closing brace and required field 2026-04-02 13:03:46 +08:00
lucario
35b51c0694 fix(cron): fix extra indent for deliver param 2026-04-02 13:03:46 +08:00
lucario
5f2157baeb fix(cron): move deliver param before job_id in parameters schema 2026-04-02 13:03:46 +08:00
archlinux
2e3cb5b20e fix default value True 2026-04-02 13:03:46 +08:00
lucario
73e80b199a feat(cron): add deliver parameter to support silent jobs, default true for backward compatibility 2026-04-02 13:03:46 +08:00
Xubin Ren
a3e4c77fff fix(providers): normalize anthropic cached token usage 2026-04-02 12:51:45 +08:00
chengyongru
da08dee144 feat(provider): show cache hit rate in /status (#2645) 2026-04-02 12:51:45 +08:00
Tejas1Koli
42fa8fa933 fix(providers): only apply cache_control for Claude models on OpenRouter 2026-04-02 04:04:18 +08:00
Tejas1Koli
05fe73947f fix(providers): only apply cache_control for Claude models on OpenRouter 2026-04-02 04:04:18 +08:00
Xubin Ren
485c75e065 test(exec): verify windows drive-root workspace guard 2026-04-02 04:00:03 +08:00
zhangxiaoyu.york
bc2e474079 Fix ExecTool to block root directory paths when restrict_to_workspace is enabled 2026-04-02 04:00:03 +08:00
WormW
ddc9fc4fd2 fix: also check channel match before inheriting default message_id 
Different channels could theoretically share the same chat_id.
Check both channel and chat_id to avoid cross-channel reply issues.

Co-authored-by: layla <111667698+04cb@users.noreply.github.com>
 2026-04-02 03:46:54 +08:00
WormW
6973bfff24 fix(agent): message tool incorrectly replies to original chat when targeting different chat_id 
When the message tool is used to send a message to a different chat_id

than the current conversation, it was incorrectly including the default

message_id from the original context. This caused channels like Feishu

to send the message as a reply to the original chat instead of creating

a new message in the target chat.

Changes:

- Only use default message_id when chat_id matches the default context

- When targeting a different chat, set message_id to None to avoid

  unintended reply behavior
 2026-04-02 03:46:54 +08:00
Xubin Ren
7e719f41cc test(providers): cover github copilot lazy export 2026-04-02 03:46:40 +08:00
Xubin Ren
2ec68582eb fix(sdk): route github copilot through oauth provider 2026-04-02 03:46:40 +08:00
RongLei
c5f0997381 fix: refresh copilot token before requests 
Address PR review feedback by avoiding an async method reference as the OpenAI client api_key.

Initialize the client with a placeholder key, refresh the Copilot token before each chat/chat_stream call, and update the runtime client api_key before dispatch.

Add a regression test that verifies the client api_key is refreshed to a real string before chat requests.

Generated with GitHub Copilot, GPT-5.4.
 2026-04-02 03:46:40 +08:00
RongLei
a37bc26ed3 fix: restore GitHub Copilot auth flow 
Implement the real GitHub device flow and Copilot token exchange for the GitHub Copilot provider.

Also route github-copilot models through a dedicated backend and strip the provider prefix before API requests.

Add focused regression coverage for provider wiring and model normalization.

Generated with GitHub Copilot, GPT-5.4.
 2026-04-02 03:46:40 +08:00
Xubin Ren
fbedf7ad77 feat: harden agent runtime for long-running tasks 2026-04-01 19:12:49 +00:00
Xubin Ren
63d646f731
Merge PR #2676: fix(test): fix flaky test_fixed_session_requests_are_serialized 
fix(test): fix flaky test_fixed_session_requests_are_serialized
 2026-03-31 22:08:47 +08:00
chengyongru
69624779dc fix(test): fix flaky test_fixed_session_requests_are_serialized 
Remove the fragile barrier-based synchronization that could cause
deadlock when the second request is scheduled first. Instead, rely
on the session lock for serialization and handle either execution
order in assertions.
 2026-03-31 21:50:33 +08:00
Xubin Ren
a4dfbdf996
Merge PR #2614: feat(weixin): weixin multimodal capabilities and align with version 2.1.1 
feat(weixin): weixin multimodal capabilities and align with version 2.1.1
 2026-03-31 19:43:02 +08:00
Xubin Ren
949a10f536 fix(weixin): reset QR poll host after refresh 2026-03-31 19:40:13 +08:00
xcosmosbox
2a6c616080 fix(WeiXin): fix full_url download error 2026-03-31 19:40:13 +08:00
xcosmosbox
1bcd5f9742 fix(weixin): fix test file version reader 2026-03-31 19:40:13 +08:00
xcosmosbox
26947db479 feat(weixin): add voice message, typing keepalive, getConfig cache, and QR polling resilience 2026-03-31 19:40:13 +08:00
xcosmosbox
0514233217 fix(weixin): align full_url AES key handling and quoted media fallback logic with reference 
1. Fix full_url path for non-image media to require AES key and skip download when missing,
   instead of persisting encrypted bytes as valid media.
2. Restrict quoted media fallback trigger to only when no top-level media item exists,
   not when top-level media download/decryption fails.
 2026-03-31 19:40:13 +08:00
xcosmosbox
345c393e53 feat(weixin): implement getConfig and sendTyping 2026-03-31 19:40:13 +08:00
xcosmosbox
faf2b07923 feat(weixin): add fallback logic for referenced media download 2026-03-31 19:40:13 +08:00
xcosmosbox
efd42cc236 feat(weixin): implement QR redirect handling 2026-03-31 19:40:13 +08:00
xcosmosbox
3823042290 fix(weixin): correct PKCS7 unpadding for AES-ECB; support full_url for media download 2026-03-31 19:40:13 +08:00
xcosmosbox
5bdb7a90b1 feat(weixin): 
1.align protocol headers with package.json metadata
2.support upload_full_url with fallback to upload_param
 2026-03-31 19:40:13 +08:00