apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-03 21:02:40 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

feat: prompt caching
Some checks are pending
Build and Push Docker Images / tag_release (push) Waiting to run
Details
Build and Push Docker Images / build (./surfsense_backend, ./surfsense_backend/Dockerfile, backend, surfsense-backend, ubuntu-24.04-arm, linux/arm64, arm64) (push) Blocked by required conditions
Details
Build and Push Docker Images / build (./surfsense_backend, ./surfsense_backend/Dockerfile, backend, surfsense-backend, ubuntu-latest, linux/amd64, amd64) (push) Blocked by required conditions
Details
Build and Push Docker Images / build (./surfsense_web, ./surfsense_web/Dockerfile, web, surfsense-web, ubuntu-24.04-arm, linux/arm64, arm64) (push) Blocked by required conditions
Details
Build and Push Docker Images / build (./surfsense_web, ./surfsense_web/Dockerfile, web, surfsense-web, ubuntu-latest, linux/amd64, amd64) (push) Blocked by required conditions
Details
Build and Push Docker Images / create_manifest (backend, surfsense-backend) (push) Blocked by required conditions
Details
Build and Push Docker Images / create_manifest (web, surfsense-web) (push) Blocked by required conditions
Details

Browse source 
- Updated `litellm` dependency version from `1.83.4` to `1.83.7`.
- Adjusted `aiohttp` version from `3.13.5` to `3.13.4` in the lock file.
- Implemented `apply_litellm_prompt_caching` in `chat_deepagent.py` to improve prompt caching.
- Added model name resolution logic in `chat_deepagent.py` to ensure correct provider-variant dispatch.
- Enhanced `llm_config.py` to configure prompt caching for various LLM providers.
- Updated tests to verify correct model name forwarding and prompt caching behavior.
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-05-01 05:10:53 -07:00
parent 360b5f8e3a
commit e57c3a7d0c
12 changed files with 877 additions and 156 deletions
Download patch file Download diff file Expand all files Collapse all files

2
surfsense_backend/pyproject.toml
View file

@ -74,7 +74,7 @@ dependencies = [
"deepagents>=0.4.12",
"stripe>=15.0.0",
"azure-ai-documentintelligence>=1.0.2",
"litellm>=1.83.4",
"litellm>=1.83.7",
"langchain-litellm>=0.6.4",
]