@convex-dev/agent 0.0.1-alpha.4 → 0.0.2

package/README.md

@@ -6,16 +6,18 @@
 
 AI Agent framework built on Convex.
 
-- Automatic storage of chat history, per-user or per-thread.
+- Automatic storage of chat history, per-user or per-thread, that can span multiple agents.
 - RAG for chat context, via hybrid text & vector search, with configuration options.
   Or use the API to query the history yourself and do it your way.
-- Opt-in search for messages from other threads (for the same specifieduser).
+- Opt-in search for messages from other threads (for the same specified user).
 - Tool calls via the AI SDK, along with Convex-specific helpers.
 - Easy workflow integration with the [Workflow component](https://convex.dev/components/workflow).
 - Reactive & realtime updates to asynchronous threads.
 - Support for streaming text and storing the result in the database.
 - Optionally filter tool calls out of the thread history.
 
+[Read the associated Stack post here](https://stack.convex.dev/ai-agents).
+
 Example usage:
 
 ```ts
@@ -31,18 +33,18 @@ const supportAgent = new Agent(components.agent, {
 export const createThread = action({
   args: { prompt: v.string() },
   handler: async (ctx, { prompt }) => {
-    const { threadId, thread } = await supportAgent.createThread(ctx, {});
+    const { threadId, thread } = await supportAgent.createThread(ctx);
     const result = await thread.generateText({ prompt });
     return { threadId, text: result.text };
   },
 });
 
-// Pick up where you left off:
+// Pick up where you left off, with the same or a different agent:
 export const continueThread = action({
   args: { prompt: v.string(), threadId: v.string() },
   handler: async (ctx, { prompt, threadId }) => {
     // This includes previous message history from the thread automatically.
-    const { thread } = await supportAgent.continueThread(ctx, { threadId });
+    const { thread } = await anotherAgent.continueThread(ctx, { threadId });
     const result = await thread.generateText({ prompt });
     return result.text;
   },
@@ -68,7 +70,7 @@ export const supportAgentWorkflow = workflow.define({
 });
 ```
 
-Also see the [Stack article](https://stack.convex.dev/ai-agent).
+Also see the [Stack article](https://stack.convex.dev/ai-agents).
 
 Coming soon:
 
@@ -333,10 +335,36 @@ const messages = await ctx.runQuery(components.agent.embeddings.deleteBatch, {
 ```
 
 See example usage in [example.ts](./example/convex/example.ts).
-Read more in [this Stack post](https://stack.convex.dev/ai-agent).
+Read more in [this Stack post](https://stack.convex.dev/ai-agents).
 
 ```sh
 npm i @convex-dev/agent
 ```
 
+## Troubleshooting
+
+### Circular dependencies
+
+Having the return value of workflows depend on other Convex functions can lead to circular dependencies due to the
+`internal.foo.bar` way of specifying functions. The way to fix this is to explicitly type the return value of the
+workflow. When in doubt, add return types to more `handler` functions, like this:
+
+```diff
+ export const supportAgentWorkflow = workflow.define({
+   args: { prompt: v.string(), userId: v.string(), threadId: v.string() },
++  handler: async (step, { prompt, userId, threadId }): Promise<string> => {
+     // ...
+   },
+ });
+
+ // And regular functions too:
+ export const myFunction = action({
+   args: { prompt: v.string() },
++  handler: async (ctx, { prompt }): Promise<string> => {
+     // ...
+   },
+ });
+```
+
+
 <!-- END: Include on https://convex.dev/components -->