mirror/nanobot
1
0
Fork 0
mirror of https://github.com/HKUDS/nanobot.git synced 2026-04-08 12:13:36 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,246 Commits 18 Branches 12 Tags
Commit Graph

773 Commits

Author SHA1 Message Date
Xubin Ren
dbdb43faff feat: channel plugin architecture with decoupled configs 
- Add plugin discovery via Python entry_points (group: nanobot.channels)
- Move 11 channel Config classes from schema.py into their own channel modules
- ChannelsConfig now only keeps send_progress + send_tool_hints (extra=allow)
- Each built-in channel parses dict->Pydantic in __init__, zero internal changes
- All channels implement default_config() for onboard auto-population
- nanobot onboard injects defaults for all discovered channels (built-in + plugins)
- Add nanobot plugins list CLI command
- Add Channel Plugin Guide (docs/CHANNEL_PLUGIN_GUIDE.md)
- Fully backward compatible: existing config.json and sessions work as-is
- 340 tests pass, zero regressions
 2026-03-14 16:13:38 +08:00
Xubin Ren
ca5047b602 feat(web): multi-provider web search + Jina Reader fetch 2026-03-13 05:44:16 +00:00
Xubin Ren
20b4fb3bff fix: langsmith callback 防覆盖 + 加 optional dep 2026-03-13 04:54:22 +00:00
Xubin Ren
da325e4532 Merge branch 'main' into pr-1920 2026-03-13 04:20:14 +00:00
Xubin Ren
4b50a7b6c0 Merge branch 'main' into pr-1916 2026-03-13 03:57:09 +00:00
Xubin Ren
6d3a0ab6c9 fix(memory): validate save_memory payload and raw-archive on repeated failure 
- Require both history_entry and memory_update, reject null/empty values
- Fallback to tool_choice=auto when provider rejects forced function call
- After 3 consecutive consolidation failures, raw-archive messages to
  HISTORY.md without LLM summarization to prevent context window overflow
 2026-03-13 03:53:50 +00:00
Xubin Ren
60c29702cc Merge branch 'main' into pr-1810 
# Conflicts:
#	nanobot/agent/memory.py
#	tests/test_memory_consolidation_types.py
 2026-03-13 03:29:16 +00:00
Xubin Ren
62a2e71748
Merge PR #1958: fix(restart): use -m nanobot for Windows compatibility 
fix(restart): use -m nanobot for Windows compatibility
 2026-03-13 11:19:57 +08:00
Xubin Ren
4f77b9385c fix(memory): fallback to tool_choice=auto when provider rejects forced function call 
Some providers (e.g. Dashscope in thinking mode) reject object-style
tool_choice with "does not support being set to required or object".
Retry once with tool_choice="auto" instead of failing silently.

Made-with: Cursor
 2026-03-13 03:18:08 +00:00
chengyongru
6ad30f12f5 fix(restart): use -m nanobot for Windows compatibility 
On Windows, sys.argv[0] may be just "nanobot" without full path when
running from PATH. os.execv() doesn't search PATH, causing restart to
fail with "No such file or directory".

Fix by using `python -m nanobot` instead of relying on sys.argv[0].

Fixes #1937
 2026-03-13 11:01:01 +08:00
Xubin Ren
ba045f56d8
Merge PR #1941: fix(qq): restore plain text replies for legacy clients 
fix(qq): restore plain text replies for legacy clients
 2026-03-13 10:57:58 +08:00
chengyongru
127ac39063 fix: catch BaseException in MCP connection to handle CancelledError 2026-03-13 10:23:15 +08:00
Frank
a09245e919 fix(qq): restore plain text replies for legacy clients 2026-03-12 12:48:25 -07:00
Re-bin
774452795b fix(memory): use explicit function name in tool_choice for DashScope compatibility 2026-03-12 16:09:24 +00:00
Re-bin
3fa62e7fda fix: remove duplicate dim/arrow prefix in interactive progress line 2026-03-12 15:38:39 +00:00
Re-bin
48c74a11d4 Merge remote-tracking branch 'origin/main' into pr-1930 2026-03-12 15:28:57 +00:00
Re-bin
3467a7faa6 fix: improve local provider auto-selection and update docs for VolcEngine/BytePlus 2026-03-12 15:22:15 +00:00
Jiajun Xie
ec6e099393 feat(ci): add GitHub Actions workflow for test directory 
- nanobot/channels/matrix.py: Add keyword-only parameters restrict_to_workspace/workspace to MatrixChannel.__init__ and assign them to _restrict_to_workspace/_workspace with proper type conversion and path resolution
- tests/test_commands.py: Add _strip_ansi() function to remove ANSI escape codes, use regex assertions for --workspace/--config parameters to allow 1 or 2 dashes
 2026-03-12 21:54:22 +08:00
chengdu121
d51ec7f0e8 fix: preserve interactive CLI formatting for async subagent output 2026-03-12 19:15:04 +08:00
gaoyiman
556cb3e83d feat: add support for Ollama local models in ProvidersConfig 2026-03-12 14:58:03 +08:00
gaoyiman
8865b6848c Merge branch 'main' into feat-volcengine-tuning 2026-03-12 14:56:05 +08:00
HuangMinlong
9e9051229e
Integrate Langsmith for conversation tracking 
Added support for Langsmith API key to enable conversation viewing.
 2026-03-12 14:34:32 +08:00
Re-bin
64888b4b09 Simplify reply context extraction, fix slash commands broken by reply injection, attach reply media regardless of caption 2026-03-12 06:16:57 +00:00
Re-bin
869149ef1e Merge branch 'main' into pr-1900 2026-03-12 06:06:26 +00:00
Re-bin
6141b95037 fix: feishu bot mention detection — user_id can be None, not just empty string 2026-03-12 06:00:39 +00:00
Re-bin
bd1ce8f144 Simplify feishu group_policy: default to mention, clean up mention detection 2026-03-12 04:45:57 +00:00
Re-bin
94e9b06086 Merge branch 'main' into pr-1768 2026-03-12 04:38:49 +00:00
Re-bin
64aeeceed0 Add /restart command: restart the bot process from any channel 2026-03-12 04:33:51 +00:00
Re-bin
231b02963d Merge branch 'main' into pr-1751 
Made-with: Cursor

# Conflicts:
#	nanobot/agent/loop.py
 2026-03-12 03:53:59 +00:00
Re-bin
0a0017ff45 fix: raise tool result history limit to 16k and force save_memory in consolidation 2026-03-12 03:08:53 +00:00
Re-bin
35260ca157 fix: raise persisted tool result limit to 16k 2026-03-12 02:50:28 +00:00
John Doe
3f799531cc Add media download functionality 2026-03-12 06:43:59 +07:00
John Doe
1eedee0c40 add reply context extraction for Telegram messages 2026-03-12 06:23:02 +07:00
Re-bin
0d94211a93 enhance: improve filesystem & shell tools with pagination, fallback matching, and smarter output 2026-03-11 16:20:11 +00:00
Re-bin
9d0db072a3 fix: guard quoted home paths in shell tool 2026-03-11 15:43:04 +00:00
Re-bin
85609c99b3 Merge remote-tracking branch 'origin/main' into pr-1827 2026-03-11 15:32:52 +00:00
Re-bin
9fc74bde9a Merge remote-tracking branch 'origin/main' into pr-1874 2026-03-11 15:26:39 +00:00
Re-bin
254cfd48ba refactor: auto-discover channels via pkgutil, eliminate hardcoded registry 2026-03-11 14:23:19 +00:00
Re-bin
c72c2ce7e2 refactor: move generation settings to provider level, eliminate parameter passthrough 2026-03-11 09:47:04 +00:00
Re-bin
a180e84536 Merge remote-tracking branch 'origin/main' into pr-1868 2026-03-11 09:10:29 +00:00
Re-bin
4478838424 fix(pr-1863): complete Ollama provider routing and README docs 2026-03-11 08:42:12 +00:00
Re-bin
a6f37f61e8 Merge remote-tracking branch 'origin/main' into pr-1863 2026-03-11 08:22:02 +00:00
Re-bin
7ceddcded6 fix(wecom): await async disconnect, add SDK attribution in README 2026-03-11 08:04:14 +00:00
Re-bin
d0b4f0d70d feat(wecom): add WeCom channel with SDK pinned to GitHub tag v0.1.2 2026-03-11 07:57:12 +00:00
WhalerO
6ef7ab53d0 refactor: centralize tool call serialization in ToolCallRequest 2026-03-11 15:32:43 +08:00
WhalerO
ed82f95f0c fix: preserve provider-specific tool call metadata for Gemini 2026-03-11 15:32:26 +08:00
Re-bin
eb6310c438 merge origin/main into pr-1327 
Made-with: Cursor
 2026-03-11 07:30:38 +00:00
ethanclaw
12104c8d46 fix(memory): pass temperature, max_tokens and reasoning_effort to memory consolidation 
Fix issue #1823: Memory consolidation does not inherit agent temperature
and maxTokens configuration.

The agent's configured generation parameters were not being passed through
to the memory consolidation call, causing it to fall back to default values.
This resulted in the consolidation response being truncated before the
save_memory tool call was emitted.

- Pass temperature, max_tokens, reasoning_effort from AgentLoop to
  MemoryConsolidator and then to MemoryStore.consolidate()
- Forward these parameters to the provider.chat_with_retry() call

Fixes #1823
 2026-03-11 14:22:33 +08:00
Jerome Sonnet (letzdoo)
dee4f27dce feat: add Ollama as a local LLM provider 
Add native Ollama support so local models (e.g. nemotron-3-nano) can be
used without an API key. Adds ProviderSpec with ollama_chat LiteLLM
prefix, ProvidersConfig field, and skips API key validation for local
providers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 08:13:14 +04:00
Re-bin
76c6063141 chore: normalize helpers.py file mode 2026-03-11 03:50:54 +00:00