You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: resources/help.md
+57-7Lines changed: 57 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -124,6 +124,38 @@ You could delete the GGUF files from this folder. If they are missing, but are n
124
124
125
125
126
126
127
+
## Edit Agent
128
+
129
+
### Overview
130
+
Edit agent view is used for adding and editing agents. From there it is also possible to delete and copy an existing agent as a new one. The identifier of an agent is it's name. For now there is no tools model as part of the agent (the currently selected tools model will be used)
131
+
132
+
### How to use it
133
+
Edit existing agent:
134
+
1. Click Select button and load an agent to be edited.
135
+
2. Change the Description and System Instructions fields (if needed)
136
+
3. Click Add Tools button and select the tools to be used for by the agent.
137
+
4. Click Save button
138
+
139
+
Add new agent:
140
+
1. Click New button
141
+
2. Enter Name, Description and System Instructions for the agent
142
+
3. Click Add Tools button and select the tools to be used for by the agent.
143
+
4. Click Save button
144
+
145
+
Copy existing agent as a new one:
146
+
1. Click Copy as New button
147
+
2. Edit Name, Description and System Instructions for the agent
148
+
3. Click Add Tools button and select the tools to be used for by the agent.
149
+
4. Click Save button
150
+
151
+
Delete agent:
152
+
1. Click Delete button
153
+
3. Select an agent to be deleted from the list
154
+
4. Confirm the deletion of the agent
155
+
156
+
157
+
158
+
127
159
## Edit with AI
128
160
129
161
### Requred servers
@@ -167,12 +199,12 @@ This generate a commit message, based on the current changes.
167
199
168
200

169
201
170
-
## Version 0.0.27 is released (21.09.2025)
202
+
## Version 0.0.32 is released (05.10.2025)
171
203
## What is new
172
-
-xAI Grog4 free (from OpenRouter) added to the initial models
173
-
-Chat with AI with project context removed (agent does it better)
174
-
-Chat with AI about llama-vscode is now with agent, not using webui
175
-
-Agent - new buttons "Tools Model" and "Agent" - possibility to view the selected model and agent and to change them.
204
+
-predefined model DeepSeek V3.1 free 163,800 context (OpenRouter) added
205
+
-predefined model Z.AI: GLM 4.5 Air (free): GLM 4.5 Air - 128.000 context (OpenRouter) added
206
+
-Added agent "Ask" is for review, analysis and suggestions for the code without changing the files
Agent is combination of system prompt and tools. If an agent is selected, it will be used by the Llama Agent UI. On slecting and agent, the selected llama-vscode tools are updated.
322
354
323
-
They have properties: name, description, syste prompt, tools.
355
+
They have properties: name, description, system prompt, tools.
324
356
325
357
Agent could be added/deleted/viewed/selected/deselected/exported/imported
326
358
@@ -330,6 +362,12 @@ Select "Agents..." from llama-vscode menu
330
362
- Add agent...
331
363
Adds an agent
332
364
365
+
- Edit agent...
366
+
Edits an agent
367
+
368
+
- Copy agent...
369
+
Copies an agent
370
+
333
371
- Delete agent...
334
372
Deletes an agent
335
373
@@ -390,6 +428,9 @@ Deselect the currently selected model. If the model is local, the llama.cpp serv
390
428
- Add model from huggingface
391
429
Enter search words to find a model from huggingface. If the model is selected it will be automatically downloaded (if not yet done) and a llama.cpp server will be started with it.
392
430
431
+
- Add chat model from OpenAI compatible provider
432
+
Add chat model from OpenAI compatible provider - OpenRouter or custom (for example local/external llama.cpp server).
433
+
393
434
- Export
394
435
A model could be exported as a .json files. This file could be shared with other users, modified if needed and imported again. Select a model to export it.
395
436
@@ -455,7 +496,7 @@ Select the model you want to delete from the list and delete it.
455
496
- View
456
497
Select a model from the list to view all the details for this model
457
498
458
-
-Selected
499
+
-Select
459
500
Select a model from the list to select it. If the model is a local one (has a command in local start command) a llama.cpp server with this model will be started. Only one completion model could be selected at a time.
460
501
461
502
- Deselect
@@ -464,6 +505,9 @@ Deselect the currently selected model. If the model is local, the llama.cpp serv
464
505
- Add model from huggingface
465
506
Enter search words to find a model from huggingface. If the model is selected it will be automatically downloaded (if not yet done) and a llama.cpp server will be started with it.
466
507
508
+
- Add completion model from OpenAI compatible provider
509
+
Add completion model from OpenAI compatible provider - OpenRouter or custom (for example local/external llama.cpp server).
510
+
467
511
- Export
468
512
A model could be exported as a .json files. This file could be shared with other users, modified if needed and imported again. Select a model to export it.
469
513
@@ -511,6 +555,9 @@ Deselect the currently selected model. If the model is local, the llama.cpp serv
511
555
- Add model from huggingface
512
556
Enter search words to find a model from huggingface. If the model is selected it will be automatically downloaded (if not yet done) and a llama.cpp server will be started with it.
513
557
558
+
- Add embeddings model from OpenAI compatible provider
559
+
Add embeddings model from OpenAI compatible provider - OpenRouter or custom (for example local/external llama.cpp server).
560
+
514
561
- Export
515
562
A model could be exported as a .json files. This file could be shared with others used, modified if needed and imported again. Select a model to export it.
516
563
@@ -608,6 +655,9 @@ Deselect the currently selected model. If the model is local, the llama.cpp serv
608
655
- Add model from huggingface
609
656
Enter search words to find a model from huggingface. If the model is selected it will be automatically downloaded (if not yet done) and a llama.cpp server will be started with it.
610
657
658
+
- Add tools model from OpenAI compatible provider
659
+
Add tools model from OpenAI compatible provider - OpenRouter or custom (for example local/external llama.cpp server).
660
+
611
661
- Export
612
662
A model could be exported as a .json files. This file could be shared with other users, modified if needed and imported again. Select a model to export it.
"description": "Agent for agentic programming - could answer questions, change/add/delete file, execute terminal commands, etc.",
633
633
"systemInstruction": [
634
634
"You are an agent for software development - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.",
635
635
"Only terminate your turn when you are sure that the problem is solved.",
0 commit comments