happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

SimpleChatTC: update readme wrt promise related trapping

This commit is contained in:
hanishkvc 2025-10-15 23:31:07 +05:30
parent f0a3886d1e
commit 09ce19a95a
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
tools/server/public_simplechat/readme.md
View File

@ -385,16 +385,22 @@ structures also.
DONE: rather both tool_calls structure wrt assistant messages and tool role based tool call DONE: rather both tool_calls structure wrt assistant messages and tool role based tool call
result messages are generated as needed. result messages are generated as needed.
#### Related stuff
Promise as well as users of promise (for now fetch) have been trapped wrt their then and catch flow,
so that any scheduled asynchronous code or related async error handling using promise mechanism also
gets executed, before tool calling returns and thus data / error generated by those async code also
get incorporated in result sent to ai engine on the server side.
#### ToDo #### ToDo
WebFetch and Local web proxy/caching server WebFetch and Local web proxy/caching server
Try and trap promises based flows to ensure all generated results or errors if any are caught Is the promise land trap deep enough, need to think through and explore around this once later.
before responding back to the ai model.
Trap error responses. Trap error responses.
### Debuging the handshake ### Debuging the handshake
When working with llama.cpp server based GenAi/LLM running locally When working with llama.cpp server based GenAi/LLM running locally