apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-08 23:32:40 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: updated agent harness

Browse source
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-04-28 09:22:19 -07:00
parent 9ec9b64348
commit 31a372bb84
139 changed files with 12583 additions and 1111 deletions
Download patch file Download diff file Expand all files Collapse all files

1
surfsense_backend/app/agents/new_chat/prompts/providers/__init__.py Normal file
View file

@ -0,0 +1 @@

5
surfsense_backend/app/agents/new_chat/prompts/providers/anthropic.md Normal file
View file

@ -0,0 +1,5 @@
<provider_hints>
You are running on an Anthropic Claude model. Use XML tags liberally to structure
intermediate reasoning when the task is complex. Prefer step-by-step plans inside
`<thinking>` blocks before producing the final answer.
</provider_hints>

1
surfsense_backend/app/agents/new_chat/prompts/providers/default.md Normal file
View file

@ -0,0 +1 @@

4
surfsense_backend/app/agents/new_chat/prompts/providers/google.md Normal file
View file

@ -0,0 +1,4 @@
<provider_hints>
You are running on a Google Gemini model. Prefer concise, structured responses.
When using tools, follow the function-calling protocol and avoid verbose preludes.
</provider_hints>

5
surfsense_backend/app/agents/new_chat/prompts/providers/openai_classic.md Normal file
View file

@ -0,0 +1,5 @@
<provider_hints>
You are running on a classic OpenAI chat model (GPT-4 family). Use direct
function-calling for tools. When editing files, use the standard `edit_file`
or `write_file` tools rather than diff-based patches.
</provider_hints>

5
surfsense_backend/app/agents/new_chat/prompts/providers/openai_reasoning.md Normal file
View file

@ -0,0 +1,5 @@
<provider_hints>
You are running on an OpenAI reasoning model (o-series / GPT-5+). Be terse and
direct in your responses. When editing files, prefer the `apply_patch` tool format
where available. Avoid restating the user request before answering.
</provider_hints>