oobabooga
dcbb323cb6
UI: Improve web search security by rejecting non-HTTP links
2026-05-16 17:39:10 -07:00
oobabooga
4c16b9458f
UI: Fix token count not being set in non-streaming mode
2026-05-16 17:35:30 -07:00
oobabooga
aa7d6bf048
Electron: Validate model_dir path before applying it
2026-05-16 17:34:58 -07:00
oobabooga
59c67f9da9
Change dependabot to target the main branch
2026-05-16 17:26:54 -07:00
oobabooga
d803e29d7f
Fix continue-mode regressions across template families
2026-05-16 13:40:24 -07:00
MeemeeLab
9a396e1749
Fix incorrect prompts generated with continue mode
...
When using the continue function, add_generation_prompt was set to False,
bypassing any template logic that depends on it. This caused missing tokens
or headers that some models inject at the start of an assistant turn.
Gemma 4 was particularly sensitive to this, producing garbled output due
to the missing thought channel header (<|channel>thought\n<channel|>).
Fix by popping the last incomplete assistant message and re-rendering the
prompt with add_generation_prompt=True, then appending the partial content
afterward. This ensures the prompt is structurally identical to normal
generation regardless of the model's template.
GPT-OSS and Seed-OSS thinking block handling is preserved via the existing
fake-message approach, as those models manage thinking content differently.
2026-05-16 13:40:15 -07:00
oobabooga
be7f3a20f2
Electron: Add spellcheck toggle in the Session tab ( closes #7550 )
2026-05-16 10:48:02 -07:00
oobabooga
bf6c8cd966
Tighten spacing between dropdowns and refresh buttons
2026-05-16 10:23:38 -07:00
oobabooga
f327da7831
Improve the looks of the Session tab
2026-05-16 09:59:42 -07:00
oobabooga
6378c5cd57
Electron: Add "Check for updates" button in the Session tab
2026-05-16 08:53:40 -07:00
oobabooga
ceade2eb1b
docs: reorder API examples by importance
2026-05-15 13:20:46 -07:00
oobabooga
dbf922006c
Revert "Soften slider and checkbox label colors in light theme"
...
This reverts commit 3c4a1402a8
2026-05-15 12:47:50 -07:00
oobabooga
8e34c7b1b0
Show live context size while generating
2026-05-15 12:45:05 -07:00
oobabooga
3c4a1402a8
Soften slider and checkbox label colors in light theme
2026-05-15 12:10:27 -07:00
oobabooga
5270943c63
Fix Show controls text style in hover menu
2026-05-15 11:57:23 -07:00
oobabooga
626b0899c0
Polish character dropdown in chat tab
2026-05-15 11:49:40 -07:00
oobabooga
2a27ceae93
Hide reasoning and tools controls in chat mode
2026-05-15 11:44:09 -07:00
oobabooga
6033be53ac
Reorder right sidebar: Mode/Character/Chat style on top
2026-05-15 09:43:22 -07:00
oobabooga
82d931e8ea
Keep web search blocks closed when user closes them mid-stream
2026-05-15 09:27:42 -07:00
oobabooga
bed909d46c
Auto-select sibling mmproj when loading a model ( closes #7564 )
2026-05-15 06:39:30 -07:00
oobabooga
0f88365b0e
Rename "Send dummy message/reply" to "Insert user/assistant message"
2026-05-14 19:59:56 -07:00
Highlander
646f10dd22
fix(win): set PYTHONUTF8 for non-ASCII locale Windows compatibility ( #7560 )
2026-05-14 15:34:36 -03:00
oobabooga
1e8136dc2a
Small simplifications
2026-05-14 11:21:18 -07:00
oobabooga
58774c8cb1
Also fix streaming leak across all other chat actions
2026-05-14 11:07:59 -07:00
oobabooga
630141912b
Fix streaming output leaking across chats ( closes #7555 )
2026-05-14 08:36:49 -07:00
oobabooga
a711849fa7
Detect mmproj files in the models folder (simplifies LM Studio migration)
2026-05-14 08:02:45 -07:00
oobabooga
66c3c49c54
Treat negative ctx-size as auto
2026-05-13 21:15:43 -07:00
oobabooga
6a1a959140
Add missing file
2026-05-13 20:37:31 -07:00
oobabooga
47fdee9cb1
Electron: Add a folder picker for the models directory
2026-05-13 20:34:07 -07:00
oobabooga
2c254cb80d
docs: Small API example change
2026-05-13 13:17:48 -07:00
oobabooga
66f01d6f20
Electron: Add right-click context menu for copying text
2026-05-13 09:50:51 -07:00
oobabooga
13f5d378e5
Make web_search tool call results pretty
2026-05-12 17:50:36 -07:00
oobabooga
79630e9bb1
Remove backend="duckduckgo" from ddgs ( https://github.com/oobabooga/textgen/issues/7548#issuecomment-4433225429 )
2026-05-12 16:47:17 -07:00
oobabooga
b863696b47
Downgrade xformers to make exllamav3 0.0.34 work
2026-05-11 22:56:50 -07:00
oobabooga
f4f556a504
Add snippet support to the web_search tool ( closes #7548 )
2026-05-11 22:56:27 -07:00
oobabooga
9a098a9f54
Update exllamav3 to 0.0.34
2026-05-11 06:57:58 -07:00
oobabooga
f29e22093d
Update README
2026-05-10 21:41:05 -07:00
oobabooga
95c0a261f5
Switch flash-attn wheels from kingbri1 to mjun0812
2026-05-07 14:15:09 -07:00
oobabooga
3b9d0feedc
Update README
2026-05-07 10:27:35 -07:00
oobabooga
3ce136e918
Update README
2026-05-07 10:22:49 -07:00
oobabooga
4549fc6d2d
Update llama.cpp
2026-05-07 08:53:40 -07:00
oobabooga
206b9d21a2
Increase bottom padding of the last chat/chat-instruct message
2026-05-07 06:48:32 -07:00
oobabooga
88d47dc412
Don't clear chat input when no model is loaded ( closes #7542 )
2026-05-07 06:34:10 -07:00
oobabooga
5c0fab6e00
Add a scroll animation when new chat messages are sent (Gemini-like)
2026-05-07 06:23:18 -07:00
oobabooga
bde878f0a3
Electron: disable spellcheck
2026-05-06 22:15:23 -07:00
oobabooga
4d3f355f04
Add a --no-electron flag
2026-05-06 22:02:56 -07:00
oobabooga
3e38f44a2e
Fix speculative decoding broken by llama.cpp arg rename ( closes #7541 )
2026-05-06 21:06:36 -07:00
oobabooga
bf50e7e705
Fix --listen mode in the new Electron launcher
2026-05-06 20:47:23 -07:00
oobabooga
8536d58178
Update llama.cpp
2026-05-06 11:30:29 -07:00
oobabooga
71525d51a6
Fix truncation length reverting after model load on UI reload ( closes #7540 )
2026-05-06 07:00:39 -07:00
oobabooga