chengyongru and GitHub
ff6deda178
fix: modernize dependency recovery guidance ( #5282 )
2026-08-07 13:58:13 +08:00
chengyongru and GitHub
67805f5db8
feat: add provider-native request switches ( #5254 )
2026-08-05 18:26:39 +08:00
Xubin Ren and chengyongru
858f6d96a6
fix(mattermost): preserve thread policy compatibility
2026-08-05 09:31:55 +08:00
concertypin and Xubin Ren
cb2f9d0bbd
fix(webui): configure public websocket URL
2026-08-04 21:53:16 +08:00
concertypin and Xubin Ren
e318e21cad
fix(webui): require proxy-generated auth assertions
2026-08-04 21:53:16 +08:00
concertypin and Xubin Ren
465a918cf8
feat(webui): bypass tokens for trusted proxy auth
2026-08-04 21:53:16 +08:00
concertypin and Xubin Ren
5cd14a42df
feat(webui): support trusted proxy bootstrap auth
2026-08-04 21:53:16 +08:00
chengyongru and GitHub
2fe135db3e
feat(webui): add integrated Vite dev mode ( #5239 )
2026-08-04 16:14:32 +08:00
Xubin Ren
62d34b5eb7
refactor(session): tighten cross-session access
2026-08-04 12:14:51 +08:00
Xubin Ren
f15ea84dd1
fix(session): enforce trusted read scope
2026-08-04 12:14:51 +08:00
Xubin Ren
df11fd92a6
docs(providers): link ModelScope setup sources
2026-08-03 16:57:10 +08:00
Xubin Ren
b29f9dcbcb
docs(providers): align ModelScope setup with current config
2026-08-03 16:57:10 +08:00
Krislu1221 and Xubin Ren
02df20cd55
docs(providers): add ModelScope (魔搭) section
...
ModelScope is a fully implemented provider (nanobot/providers/registry.py,
image_generation.py, schema.py) with async image-generation task submission
and polling, but was previously undocumented in docs/providers.md.
This patch adds a ModelScope entry under 'Common Provider Patterns',
covering:
- Default base URL: https://api-inference.modelscope.cn/v1
- OpenAI-compatible chat/completions endpoint
- Async image-generation flow (task submit + status poll)
- Automatic 'modelscope/' prefix stripping when calling the API
- A minimal nanobot.yaml example
No code changes; docs-only.
2026-08-03 16:57:10 +08:00
Xubin Ren
ac216c3e94
docs(providers): document Eden AI setup and WebUI parity
2026-08-03 16:40:13 +08:00
chengyongru and GitHub
cdb75f8e7d
feat(providers): support DeepSeek Responses API ( #5197 )
2026-08-01 11:53:51 +08:00
chengyongru and GitHub
6a1a45d07a
feat: preserve Responses reasoning state and compact context ( #5172 )
2026-07-30 22:39:43 +08:00
chengyongru and GitHub
606ac56e8f
feat(webui): support remote Codex OAuth login ( #5174 )
2026-07-30 15:06:34 +08:00
chengyongru and GitHub
0c6c0438d4
feat(config): add actionable startup diagnostics and WebUI recovery ( #5110 )
2026-07-28 18:52:05 +08:00
chengyongru and Xubin Ren
ae7b4c8792
fix(sdk): narrow persisted turn callback API
2026-07-28 15:30:28 +08:00
chengyongru and Xubin Ren
fd17c1352a
fix(sdk): harden host integration contracts
2026-07-28 15:30:28 +08:00
chengyongru and Xubin Ren
c050955ae3
feat(sdk): add host integration extension points
2026-07-28 15:30:28 +08:00
chengyongru and GitHub
12f828ea3d
fix(agent): read document attachments on demand ( #5122 )
2026-07-28 13:33:06 +08:00
Xubin Ren
328251289d
docs(deploy): explain Render setup and updates
2026-07-28 12:44:45 +08:00
chengyongru and GitHub
c13df29457
feat(memory): restore Dream model preset override ( #5107 )
2026-07-27 14:43:25 +08:00
chengyongru and GitHub
281b4b7f0b
chore: remove expired v0.3.1 compatibility shims ( #5106 )
2026-07-27 13:53:04 +08:00
chengyongru and Xubin Ren
b3d3a3e6c3
fix(image): delegate DNS to explicit proxy
2026-07-27 10:06:19 +08:00
chengyongru and Xubin Ren
d73794bc68
fix(image): honor provider proxy for URL downloads
2026-07-27 10:06:19 +08:00
Xubin Ren
68717937e8
fix(agent): throttle idle scans by default
2026-07-27 02:15:48 +08:00
Andrew Khmylov and Xubin Ren
7aab7e8830
feat(agent): make idle compaction scan interval configurable
...
Before this change, idle compaction is triggered every 1 second
if the incoming message stream is idle.
When triggered, it enumerates all session files, loads and parses them,
and then checks their expiration.
This becomes too CPU-intensive, especially on low-power devices like Raspberry Pi.
It's unlikely that you actually need to compact every second over the long time.
This change adds a configurable throttling for idle-compaction.
Default behavior is unchanged.
2026-07-27 02:15:48 +08:00
Xubin Ren
cf6ca13b6d
fix(exec): preserve bwrap workspace masking
2026-07-27 00:31:00 +08:00
yu-xin-c and Xubin Ren
01a11b3980
feat(exec): allow extra bwrap bind roots
2026-07-27 00:31:00 +08:00
chengyongru and chengyongru
d576804f23
feat(channels): enable tool hints by default
2026-07-26 21:22:12 +08:00
chengyongru and chengyongru
55405f6cd6
feat: open WebUI after fresh desktop install
2026-07-26 03:28:15 +08:00
Xubin Ren
3f602fbc8c
docs(readme): fold Render into deployment guide
2026-07-25 15:46:46 +08:00
Xubin Ren
d6f6bbddbf
docs(readme): preview the agency release
2026-07-25 15:46:46 +08:00
chengyongru and GitHub
6e0eb46705
feat: launch first-time setup in webui ( #5078 )
2026-07-24 21:16:43 +08:00
George Pickett and Xubin Ren
0b38c48399
feat(webui): add Parallel Search MCP preset
2026-07-24 12:26:37 +08:00
chengyongru and chengyongru
6a9157f477
feat(webui): present chats as topics
2026-07-24 10:29:13 +08:00
chengyongru and chengyongru
15de6be0af
fix(providers): fall back on authentication errors
2026-07-23 14:52:04 +08:00
chengyongru and GitHub
01cdfc8100
fix(telegram): expose proxy setup in WebUI ( #5033 )
2026-07-23 14:18:49 +08:00
chengyongru and chengyongru
f3099286ea
docs: explain slow optional dependency installs
2026-07-23 13:23:55 +08:00
Xubin Ren
2f4f00bb9f
refactor(image): reuse the model picker
2026-07-23 12:42:24 +08:00
chengyongru and GitHub
c7393c785e
feat(providers): add xAI Grok OAuth with capability-gated X Search ( #5035 )
2026-07-23 11:55:16 +08:00
chengyongru and GitHub
c22efb5f7a
feat(agent): make model presets session-scoped ( #4866 )
2026-07-23 00:38:49 +08:00
chengyongru and GitHub
b189a37648
fix(agent): preserve agent-owned state in project workspaces ( #4945 )
2026-07-22 17:25:22 +08:00
yrk and Xubin Ren
be1cc769d5
docs: refine ModelScope documentation wording
2026-07-22 01:35:20 +08:00
yrk and Xubin Ren
9abad4746e
feat(providers): add ModelScope provider for LLM and image generation
2026-07-22 01:35:20 +08:00
chengyongru and chengyongru
1d7bad3909
feat(providers): support Codex fast mode
2026-07-21 17:55:17 +08:00
chengyongru and chengyongru
9d830fb6b6
docs(ollama): explain tool prompt cache reuse
2026-07-20 17:47:04 +08:00
chengyongru and GitHub
8423cf3eeb
fix(channels): complete dependency manifest migration ( #4995 )
...
* fix(channels): complete dependency manifest migration
* docs(docker): clarify custom uid dependency installs
* fix(channels): keep dependency preinstall internal
* refactor(channels): move dependency installer to scripts
* fix(docker): limit runtime write access
2026-07-20 15:24:57 +08:00
chengyongruandGitHub
Xubin Renandchengyongru
concertypinandXubin Ren
Krislu1221andXubin Ren
chengyongruandXubin Ren
chengyongruandXubin Ren
Andrew KhmylovandXubin Ren
yu-xin-candXubin Ren
George PickettandXubin Ren
yrkandXubin Ren