AgentResolverPlugin (Axelor Open Platform 10.0.0 API)

java.lang.Object

com.axelor.ai.chat.plugin.AgentResolverPlugin

All Implemented Interfaces:: ChatPlugin

public class AgentResolverPlugin extends Object implements ChatPlugin

Resolves the agent/model/provider config from the DB and builds a real LangChain4jChatProvider so the LLM actually responds.

Method Summary

Modifier and Type

Method

Description

ChatProvider

decorateProvider(ChatRequest request, ChatProvider provider)

Wraps the provider to intercept or enrich LLM calls (e.g.

int

estimateInjectedTokens(ChatRequest request)

Estimates the number of tokens this plugin will inject into the message list during ChatPlugin.decorateProvider(com.axelor.ai.chat.ChatRequest, com.axelor.ai.chat.ChatProvider).

ChatRequest

onRequest(ChatRequest request)

Called before the loop starts.

int

priority()

Execution priority.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.axelor.ai.chat.ChatPlugin
decorateToolExecutor, decorateWriter, onComplete, onError, onMessage

Method Details
- priority
  
  public int priority()
  
  Description copied from interface: ChatPlugin
  
  Execution priority. Lower values run first. Default is 100.
  
  Specified by:
  
  priority in interface ChatPlugin
- onRequest
  
  public ChatRequest onRequest(ChatRequest request)
  
  Description copied from interface: ChatPlugin
  
  Called before the loop starts. May inspect or transform the request (e.g. resolve agent config, check rate limits).
  
  Specified by:
  
  onRequest in interface ChatPlugin
- estimateInjectedTokens
  
  public int estimateInjectedTokens(ChatRequest request)
  
  Description copied from interface: ChatPlugin
  
  Estimates the number of tokens this plugin will inject into the message list during ChatPlugin.decorateProvider(com.axelor.ai.chat.ChatRequest, com.axelor.ai.chat.ChatProvider). Used by the context window plugin to compute an accurate budget that accounts for system prompts, RAG context, skill content, etc.
  Implementations should return a conservative (high) estimate. Return 0 if this plugin does not inject content.
  
  Specified by:
  
  estimateInjectedTokens in interface ChatPlugin
- decorateProvider
  
  public ChatProvider decorateProvider(ChatRequest request, ChatProvider provider)
  
  Description copied from interface: ChatPlugin
  
  Wraps the provider to intercept or enrich LLM calls (e.g. RAG, system prompt injection).
  
  Specified by:
  
  decorateProvider in interface ChatPlugin