Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,706 Commits 1 Branch 1 Tag
main
Commit Graph
11 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
haosenwang1018andXubin Ren d33bf22e91 docs(provider): clarify responses api routing 2026-04-13 15:59:36 +08:00
haosenwang1018andXubin Ren 85c7996766 docs(api): clarify cross-channel message delivery 2026-04-13 15:59:36 +08:00
haosenwang1018andXubin Ren 92ef594b6a fix(mcp): hint on stdio protocol pollution 2026-04-13 09:41:55 +08:00
haosenwang1018andXubin Ren 3573109408 fix(provider): preserve static error helper compatibility 2026-04-13 09:37:31 +08:00
haosenwang1018andXubin Ren c68b3edb9d fix(provider): clarify local 502 recovery hints 2026-04-13 09:37:31 +08:00
haosenwang1018andXubin Ren 7a6416bcb2 test(matrix): skip cleanly when optional deps are missing 2026-04-02 18:17:00 +08:00
haosenwang1018andXubin Ren b6cf7020ac fix: normalize MCP tool schema for OpenAI-compatible providers 2026-03-21 14:35:47 +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
haosenwang1018 8de2f8d588 fix: preserve reasoning_content in message sanitization for thinking models 
_sanitize_messages strips all non-standard keys from messages, including
reasoning_content. Thinking-enabled models like Moonshot Kimi k2.5
require reasoning_content to be present in assistant tool call messages
when thinking mode is on, causing a BadRequestError (#1014).

Add reasoning_content to _ALLOWED_MSG_KEYS so it passes through
sanitization when present.

Fixes #1014
 2026-02-24 04:21:55 +08:00
haosenwang1018 eeaad6e0c2 fix: resolve API key at call time so config changes take effect without restart 
Previously, WebSearchTool cached the API key in __init__, so keys added
to config.json or env vars after gateway startup were never picked up.
This caused a confusing 'BRAVE_API_KEY not configured' error even after
the key was correctly set (issue #1069).

Changes:
- Store the init-time key separately, resolve via property at each call
- Improve error message to guide users toward the correct fix

Closes #1069
 2026-02-24 04:06:22 +08:00