Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,145 Commits 1 Branch 0 Tags
eb6310c43899a9f6429b01a85a04646e55b951bf
Commit Graph

119 Commits

Author SHA1 Message Date
Re-bin
eb6310c438 merge origin/main into pr-1327 
Made-with: Cursor
 2026-03-11 07:30:38 +00:00
Re-bin
62ccda43b9 refactor(memory): switch consolidation to token-based context windows 
Move consolidation policy into MemoryConsolidator, keep backward compatibility for legacy config, and compress history by token budget instead of message count.
 2026-03-10 19:55:06 +00:00
Re-bin
4784eb4128 merge origin/main into pr-1704 2026-03-10 18:09:15 +00:00
Re-bin
4f9857f85f feat(telegram): add configurable group mention policy 2026-03-10 04:34:15 +00:00
Re-bin
8aa754cd2e Merge branch 'main' into pr-1389 2026-03-10 04:26:12 +00:00
chengyongru
a660a25504 feat(wecom): add wecom channel [wobsocket] 
support text/audio[wecom support audio message by default]
 2026-03-09 22:46:35 +08:00
VITOHJL
dbc518098e refactor: implement token-based context compression mechanism 
Major changes:
- Replace message-count-based memory window with token-budget-based compression
- Add max_tokens_input, compression_start_ratio, compression_target_ratio config
- Implement _maybe_compress_history() that triggers based on prompt token usage
- Use _build_compressed_history_view() to provide compressed history to LLM
- Refactor MemoryStore.consolidate() -> consolidate_chunk() for chunk-based compression
- Remove last_consolidated from Session, use _compressed_until metadata instead
- Add background compression scheduling to avoid blocking message processing

Key improvements:
- Compression now based on actual token usage, not arbitrary message counts
- Better handling of long conversations with large context windows
- Non-destructive compression: old messages remain in session, but excluded from prompt
- Automatic compression when history exceeds configured token thresholds
 2026-03-08 14:20:16 +08:00
Kunal Karmakar
33c52cfb74 Merge branch 'main' of https://github.com/kunalk16/nanobot into feat-support-azure-openai 2026-03-06 10:39:29 +00:00
Kunal Karmakar
813d37ad35 Support Azure OpenAI 2026-03-06 08:43:58 +00:00
Re-bin
b817463939 chore: simplify Alibaba Coding Plan to apiBase hint, remove dedicated provider 2026-03-06 07:13:04 +00:00
Re-bin
e81b6ceb49 merge origin/main into pr-1563 2026-03-06 07:01:23 +00:00
Re-bin
b71c1bdca7 fix(mcp): hoist sse/http imports, annotate auto-detection heuristic, restore field comments 2026-03-05 14:44:45 +00:00
Re-bin
2306d4c11c Merge remote-tracking branch 'origin/main' into pr-1488 2026-03-05 14:35:02 +00:00
Re-bin
06fcd2cc3f fix(discord): correct group_policy default to mention and style cleanup 2026-03-05 14:33:14 +00:00
Re-bin
376b7d6d58 Merge remote-tracking branch 'origin/main' into pr-553 2026-03-05 14:28:50 +00:00
ouyangwulin
6770a6e7e9 supported aliyun coding plan. 2026-03-05 17:34:36 +08:00
ouyangwulin
cf3e7e3f38 feat: Add Alibaba Cloud Coding Plan API support 
Add dashscope_coding_plan provider to registry with OpenAI-compatible
endpoint for BaiLian coding assistance.

- Supports API key detection by 'sk-sp-' prefix pattern
- Adds provider config schema entry for proper loading
- Updates documentation with configuration instructions
- Fixes duplicate MatrixConfig class issue in schema
- Follow existing nanobot provider patterns for consistency
 2026-03-05 16:54:15 +08:00
worenidewen
3e83425142 feat(mcp): add SSE transport support with auto-detection 2026-03-04 01:10:19 +08:00
Re-bin
bbfc1b40c1 security: deny-by-default allowFrom with wildcard support and startup validation 2026-03-02 06:13:37 +00:00
Joel Chan
e9d023f52c feat(discord): add group policy to control group respond behaviour 2026-03-02 12:16:49 +08:00
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
chengyongru
82be2ae1a5 feat(tool): add web search proxy 2026-03-01 16:51:54 +08:00
Jack Lu
3ee061b879 Merge branch 'main' into main 2026-03-01 13:35:24 +08:00
Re-bin
f9d72e2e74 feat: add reasoning_effort config to enable LLM thinking mode 2026-02-28 17:18:05 +00:00
JK_Lu
977ca725f2 style: unify code formatting and import order 
- Remove trailing whitespace and normalize blank lines
- Unify string quotes and line breaks for long lines
- Sort imports alphabetically across modules
 2026-02-28 20:55:43 +08:00
Re-bin
12f3365103 fix: remove duplicate import, tidy MatrixConfig comments 2026-02-27 09:53:31 +00:00
Re-bin
2d33371366 Merge remote-tracking branch 'origin/main' into pr-1239 2026-02-27 09:51:33 +00:00
Tanish Rajput
568a54ae3e Initialize Matrix channel in ChannelManager when enabled in config 2026-02-27 11:39:01 +05:30
kimkitsuragi26
6641bad337 feat(feishu): make reaction emoji configurable 
Replace hardcoded THUMBSUP with configurable react_emoji field
in FeishuConfig, consistent with SlackConfig.react_emoji pattern.

Default remains THUMBSUP for backward compatibility.
 2026-02-27 11:45:44 +08:00
Re-bin
cc425102ac docs: update Matrix channel guideline and schema 2026-02-26 03:08:00 +00:00
Re-bin
84f2f3c316 Merge remote-tracking branch 'origin/main' into pr-420 2026-02-26 02:48:21 +00:00
Re-bin
65477e4bf3 feat: support explicit provider selection in config 2026-02-26 02:15:42 +00:00
Re-bin
e1a2ef4f29 Merge branch 'main' into pr-1083 2026-02-25 15:50:00 +00:00
aiguozhi123456
7be278517e fix(exec): use empty default and os.pathsep for cross-platform 2026-02-24 12:13:52 +00:00
Re-bin
ec55f77912 fix(heartbeat): replace HEARTBEAT_OK token with virtual tool-call decision 2026-02-24 11:04:56 +00:00
aiguozhi123456
abcce1e1db feat(exec): add path_append config to extend PATH for subprocess 2026-02-24 03:18:23 +00:00
Re-bin
d9462284e1 improve agent reliability: behavioral constraints, full tool history, error hints 2026-02-23 09:13:08 +00:00
Re-bin
491739223d fix: lower default temperature from 0.7 to 0.1 2026-02-23 08:24:53 +00:00
Re-bin
df2c837e25 feat(channels): split send_progress into send_progress + send_tool_hints 2026-02-23 07:12:41 +00:00
Yingwen Luo-LUOYW
31a873ca59 Merge branch 'main' of https://github.com/HKUDS/nanobot 2026-02-23 09:41:56 +08:00
Yingwen Luo-LUOYW
0c412b3728 feat(channels): add send_progress option to control progress message delivery 
Add a boolean config option `channels.sendProgress` (default: false) to
control whether progress messages (marked with `_progress` metadata) are
sent to chat channels. When disabled, progress messages are filtered
out in the outbound dispatcher.
 2026-02-23 09:41:13 +08:00
Re-bin
437ebf4e6e feat(mcp): make tool_timeout configurable per server via config 2026-02-22 18:04:13 +00:00
Alexander Minges
dd61a9143a fix: remove accidental whitespace-only formatting changes from schema.py 2026-02-20 18:11:29 +01:00
Alexander Minges
97cb85ee0b feat(matrix): add outbound media uploads and unify media limits with maxMediaBytes 
- Use OutboundMessage.media for Matrix file/image/audio/video sends
- Apply effective media limit as min(m.upload.size, maxMediaBytes)
- Rename matrix config key maxInboundMediaBytes -> maxMediaBytes (no legacy fallback)
 2026-02-20 18:02:13 +01:00
Alexander Minges
566ad1dfc7 feat(matrix): make e2ee configurable with enabled default 2026-02-20 17:57:10 +01:00
Alexander Minges
a482a89df6 feat(matrix): support inbound media attachments 2026-02-20 17:56:11 +01:00
Alexander Minges
fa2049fc60 feat(matrix): add group policy and strict mention gating 2026-02-20 17:55:05 +01:00
Alexander Minges
7c33d3cbe2 feat(matrix): add configurable graceful sync shutdown 2026-02-20 17:52:32 +01:00
djmaze
d3ddeb3067 fix: activate E2E and accept room invites in Matrix channels 2026-02-20 17:48:14 +01:00
Re-bin
e1854c4373 feat: make Telegram reply-to-message behavior configurable, default false 2026-02-20 11:13:10 +00:00