Remove url rewriting in fastify

docs/docs/agent-concepts.md

@@ -1,27 +1,27 @@
 # Agent concepts
 
-## Agent types
+## Agent categories
 
 ### 1. Autonomous agents
 
-Sophia comes with two autonomous agents (XML and CodeGen), which applying reasoning to break down
+Sophia comes with two autonomous agent types (XML and CodeGen), which applying reasoning to break down
 a user request into a plan to be completed by the available function calls.
 
+The Slack chatbot uses an autonomous agent to provide a response to a user.
+
 Function calls may be to API integrations or create sub-agents.
 
 ### 2. Workflow agents
 
-Workflow agents have the control flow logic in code, and the results of the LLM calls
+Workflow agents have the control flow logic defined in code, and the results of the LLM calls
 may determine the conditional control flow through the workflow.  This includes the Software Developer/Code Editing agents.
 
-An autonomous agent may start a workflow agent via a function call, and a workflow may start an autonomous agent.
-
 ## Agent context
 
 The codebase makes use of `AsyncLocalStorage`, which is similar to `ThreadLocal` in Java and `threading.local()` in Python,
 to provide easy lookup of agent state, current user, tool configuration, and default LLMs.
 
-This does require the agent code to run within a context 
+This requires the agent code to run within a AsyncLocalStorage context.
 ```typescript
 export const agentContextStorage = new AsyncLocalStorage<AgentContext>();
 

src/fastify/fastifyApp.ts

@@ -39,12 +39,6 @@ export type RouteDefinition = (fastify: TypeBoxFastifyInstance) => Promise<void>
 
 export const fastifyInstance: TypeBoxFastifyInstance = fastify({
 	maxParamLength: 256,
-	rewriteUrl: (req) => {
-		if (req.url.startsWith(UI_PREFIX)) {
-			return UI_PREFIX;
-		}
-		return req.url;
-	},
 }).withTypeProvider<TypeBoxTypeProvider>();
 
 export interface FastifyConfig {

src/llm/base-llm.ts

@@ -243,6 +243,7 @@ export abstract class BaseLLM implements LLM {
 		return true;
 	}
 
+	/** Model id form the Vercel AI package */
 	aiModel(): LanguageModel {
 		throw new Error('Unsupported implementation');
 	}

src/routes/agent/agent-start-route.ts

@@ -1,14 +1,13 @@
 import { Type } from '@sinclair/typebox';
 import { LlmFunctions } from '#agent/LlmFunctions';
+import { AgentType } from '#agent/agentContextTypes';
+import { AgentExecution, startAgent } from '#agent/agentRunner';
 import { send } from '#fastify/index';
+import { functionFactory } from '#functionSchema/functionDecorators';
 import { getLLM } from '#llm/llmFactory';
 import { logger } from '#o11y/logger';
-import { AppFastifyInstance } from '../../app';
-import { AgentExecution, startAgent } from '#agent/agentRunner';
 import { currentUser } from '#user/userService/userContext';
-import { functionFactory } from '#functionSchema/functionDecorators';
-import {AgentType} from "#agent/agentContextTypes";
-
+import { AppFastifyInstance } from '../../app';
 
 const v1BasePath = '/api/agent/v1';