zhayujie
3dd4b84179
feat(models): support claude-opus-4-8
2026-05-29 10:19:45 +08:00
zhayujie
e3eacc77d7
feat(channel): support telegram bot
2026-05-28 15:07:09 +08:00
zhayujie
d106465419
feat(channel): telegram first version
2026-05-28 12:10:00 +08:00
zhayujie
bccce2d7cb
feat(models): support xiaomi mimo
2026-05-28 10:49:52 +08:00
zhayujie
8d67177a1b
feat(agent): support user-initiated cancel for in-flight agent runs
2026-05-26 23:36:09 +08:00
zhayujie
e05f85f3ce
feat: optimize model name display in English
2026-05-25 15:09:53 +08:00
zhayujie
eb74b73351
fix(web): handle non-string web_password to avoid login TypeError
2026-05-25 11:14:14 +08:00
zhayujie
bd85fee7d7
fix(models): persist explicit provider for vision and image capabilities
2026-05-23 20:43:25 +08:00
zhayujie
069bffa3e8
feat: release 2.0.9
2026-05-22 12:25:22 +08:00
zhayujie
cc10d230b0
Merge pull request #2826 from zhayujie/feat-multi-model
...
feat: multi-provider model console
2026-05-22 11:08:13 +08:00
zhayujie
2517f2add8
feat(models): support gpt-5.5
2026-05-22 11:04:55 +08:00
zhayujie
a534266025
feat(models): add qwen3.7-max
2026-05-22 10:54:56 +08:00
zhayujie
8c25395805
feat(models): support gemini-3.5-flash
2026-05-22 10:39:04 +08:00
zhayujie
36b913124b
docs: update models and channels doc
2026-05-22 10:10:07 +08:00
zhayujie
90773ab69f
feat(models): allow viewing and editing search vendor credentials
2026-05-21 20:22:09 +08:00
zhayujie
b7734c3926
feat(search): multi-provider web search + console integration
...
Search tool now supports 4 backends with unified output (bocha,
qianfan, zhipu, linkai) and a routing layer:
- strategy 'auto' (default): pick first configured in canonical order
bocha > qianfan > zhipu > linkai
- strategy 'fixed': pin a specific provider
- agent may pass `provider` to override per-call (only exposed when
≥2 providers configured + auto strategy)
2026-05-21 19:58:03 +08:00
zhayujie
d3faf9c8dc
fix(web): re-render JS-built views on language switch
2026-05-21 17:33:32 +08:00
zhayujie
b8333e351c
feat(voice): rework TTS/ASR stack and unify tool/skill config schema
2026-05-21 16:00:54 +08:00
zhayujie
7c35df7a82
fix: default agent mode to enabled
2026-05-21 11:14:19 +08:00
zhayujie
2b90f377e6
feat(voice): add dashscope & zhipu ASR, in-page mic input
2026-05-20 22:36:37 +08:00
zhayujie
fff7326209
feat(memory): hot-swap embedding provider on rebuild-index
...
Switching embedding provider in the web console no longer requires a
restart and no longer drops the running conversation
2026-05-20 21:32:53 +08:00
zhayujie
c181e500bc
feat(web): redesign multi-models console
...
Overhauls the Models tab in the Web Console with a vendor-first layout and
ships a runtime-accurate dispatcher view for vision and image generation.
2026-05-20 20:59:04 +08:00
a1094174619
4e42f2a017
fix: persist tool error status in conversation history reload
...
When reloading a conversation, failed tool calls incorrectly showed checkmark instead of X because the is_error field was lost in the history rendering pipeline. Propagate is_error from DB extraction through to the frontend rendering to match the live SSE behavior.
2026-05-19 23:50:29 +08:00
zhayujie
4634a7bc2f
fix(web): avoid TypeError on single-file upload
2026-05-17 19:00:07 +08:00
zhayujie
16d9b449c9
feat(web): set the web_host to the default value of 127.0.0.1
2026-05-16 18:18:17 +08:00
zhayujie
8761997757
feat(web): add web_host config and password hint for safer deployment
2026-05-16 17:37:07 +08:00
zhayujie
19bba4abbc
feat(web): vendor all frontend assets locally #2816
2026-05-16 17:22:04 +08:00
tianyu Gu
a0b29d1ffe
fix(web): remove upload dir button, one-time upload all files,path check adapt windows
2026-05-15 18:48:37 +08:00
tianyu Gu
246f0a45c8
feat(web): support folder upload
2026-05-14 17:16:11 +08:00
zhayujie
20d8ae19a7
Merge pull request #2804 from yangluxin613/feat/web-port-browser
...
feat(web): auto-switch port on conflict and open browser on startup
2026-05-12 10:35:49 +08:00
ooaaooaa123
ad51aabfd7
feat(web): open browser on startup with safe fallback; friendly error on port conflict
2026-05-10 19:30:07 +08:00
zhayujie
1cf395c041
Merge pull request #2807 from yangluxin613/feat/log-ui
...
feat(log): add level coloring, multiline inherit, and filter checkboxes
2026-05-10 18:59:05 +08:00
zhayujie
907825601d
feat(models): add baidu ernie-5.1
2026-05-10 18:39:38 +08:00
ooaaooaa123
83f2aea123
feat(log): enhance critical log line color visibility
2026-05-10 17:43:26 +08:00
ooaaooaa123
a5c5439315
feat(log): add level coloring, multiline inherit, and filter checkboxes
2026-05-10 17:21:08 +08:00
ooaaooaa123
d2d5d98d78
feat(web): auto-switch port on conflict and open browser on startup
2026-05-10 17:20:45 +08:00
zhayujie
307769b949
feat(mcp): load MCP servers asynchronously at startup
...
Boot MCP servers (npx/uvx) on a background thread instead of blocking
agent init. Built-in tools serve traffic immediately while MCP comes
online; each new agent reads whatever is ready at creation time.
Idempotent via _mcp_loaded flag — concurrent sessions never re-fork
subprocesses. Per-server failures are isolated and warmup is triggered
in app.py so loading overlaps with channel startup.
2026-05-08 15:22:42 +08:00
zhayujie
a5790d82f6
feat(qianfan): scope vision support to multimodal models
2026-05-06 16:11:10 +08:00
zhayujie
c322c0e3a5
docs(models): add ernie-5.0
2026-05-06 12:15:14 +08:00
zhayujie
530fc20596
Merge pull request #2790 from jimmyzhuu/feat/qianfan-provider
...
Add first-class Baidu Qianfan / ERNIE provider
2026-05-06 11:43:32 +08:00
zhayujie
a9c8a59f58
feat(feishu): one-click QR-scan app creation
2026-05-05 18:32:58 +08:00
jimmyzhuu
f653483eea
feat: expose qianfan in configuration surfaces
2026-04-29 16:32:53 +08:00
zhayujie
5c65196e44
feat(web): hint API base version path in config placeholder
2026-04-26 17:10:24 +08:00
zhayujie
0e556b3468
feat: switch default model to deepseek-v4-flash
2026-04-26 15:54:50 +08:00
zhayujie
31820f56e7
fix(deepseek): back-fill reasoning_content for all assistant turns
2026-04-24 16:39:48 +08:00
zhayujie
fd88828abd
fix(models): unify enable_thinking for deepseek-v4
2026-04-24 15:29:43 +08:00
zhayujie
472a8605c0
feat(models): support deepseek-v4-pro and deepseek-v4-flash
2026-04-24 11:35:38 +08:00
zhayujie
b0e00dfceb
feat: support glm-5.1
2026-04-23 16:43:05 +08:00
zhayujie
68ce2e5232
feat(skill): multi-provider image generation with auto-fallback
...
- Add Gemini, Seedream (Volcengine Ark), Qwen (DashScope), MiniMax
providers to image-generation skill with universal sequential
fallback: OpenAI → Gemini → Seedream → Qwen → MiniMax → LinkAI
- Each provider filters unsupported size tiers to valid values
(e.g. Seedream 1K→2K, Qwen 3K→2K, Gemini 3K→2K)
- Pinned model only tries its native provider; auto-routing uses
each provider's default model
- Support skill-namespaced config (config.skill.image-generation.model
→ SKILL_IMAGE_GENERATION_MODEL env var)
- Add image lightbox (click-to-enlarge) in web console
- Add docs for built-in skills (skill-creator, knowledge-wiki,
image-generation) under docs/skills/
2026-04-23 12:39:39 +08:00
zhayujie
81e8bb62ae
feat(skill): support gpt-image-2 in image generation skill
2026-04-22 20:39:49 +08:00
