agentleFS
waynesuttonwaynesutton/markdown-site/.cursor/rules/convex2.mdc

markdown-site / rules

Cursor rule628 starsChanged 7 months agoMITView on GitHub

description: Guidelines and best practices for building Convex projects, including database schema design, queries, mutations, and real-world examples globs: */\.ts,**/_.tsx,\\/.js,\*/_.jsx - always create type-safe code - ALWAYS use the new function syntax for Convex functions. For example: typescript import { query } from "./_generated/server"; import { v } from "convex/values"; export const f = query({ args: {}, returns: v.null(), handler: async (ctx, args) => { // Function body }, }); - HTTP endpoints are defined in convex/http.ts and require an…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this convex2.mdc into the rules it gives an agent

37 rules. About 0 are common, 4 are distinctive, and 33 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 33

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    always create type-safe code

    line 20
  2. Distinctive:

    ALWAYS use the new function syntax for Convex functions.

    line 21
  3. Very specific:

    Always use the v.null() validator when returning a null value.

    line 90
  4. Very specific:

    Use internalQuery, internalMutation, and internalAction to register internal functions.

    line 121
  5. Very specific:

    Use query, mutation, and action to register public functions.

    line 122
  6. Very specific:

    ALWAYS include argument and return validators for all Convex functions.

    line 124
  7. Very specific:

    If the JavaScript implementation of a Convex function doesn't have a return value, it implicitly returns null.

    line 125
  8. Very specific:

    Use ctx.runQuery to call a query from a query, mutation, or action.

    line 129
  9. Very specific:

    Use ctx.runMutation to call a mutation from a mutation or action.

    line 130
  10. Very specific:

    Use ctx.runAction to call an action from an action.

    line 131
  11. Distinctive:

    ONLY call an action from another action if you need to cross runtimes (e.g.

    line 132
  12. Very specific:

    All of these calls take in a FunctionReference.

    line 134
  13. Very specific:

    When using ctx.runQuery, ctx.runMutation, or ctx.runAction to call a function in the same file, specify a type annotation on the return …

    line 135
  14. Very specific:

    Use the api object defined by the framework in convex/_generated/api.ts to call public functions registered with query, mutation, or action.

    line 158
  15. Very specific:

    Use the internal object defined by the framework in convex/_generated/api.ts to call internal (or private) functions registered with …

    line 159
  16. Very specific:

    Use query, mutation, and action to define public functions.

    line 167
  17. Very specific:

    Use internalQuery, internalMutation, and internalAction to define private, internal functions.

    line 168
  18. Very specific:

    Use v.record() for defining a record type.

    line 199
  19. Very specific:

    Always define your schema in convex/schema.ts.

    line 203
  20. Very specific:

    Always import the schema definition functions from convex/server:

    line 204
  21. Very specific:

    Always include all index fields in the index name.

    line 206
  22. Very specific:

    Always use as const for string literals in discriminated union types.

    line 235
  23. Very specific:

    When using the Array type, make sure to always define your arrays as const array: Array<T> = [...].

    line 236
  24. Very specific:

    When using the Record type, make sure to always define your records as const record: Record<KeyType, ValueType> = {...}.

    line 237
  25. Very specific:

    Always add @types/node to your package.json when using any Node.js built-in modules.

    line 238
  26. Very specific:

    Do NOT use filter in queries.

    line 253
  27. Very specific:

    Use .unique() to get a single document from a query.

    line 255
  28. Very specific:

    When using async iteration, don't use .collect() or .take(n) on the result of a query.

    line 256
  29. Distinctive:

    Document queries that use indexes will be ordered based on the columns in the index and can avoid slow table scans.

    line 262
  30. Very specific:

    Use ctx.db.replace to fully replace an existing document.

    line 266
  31. Very specific:

    Use ctx.db.patch to shallow merge updates into an existing document.

    line 267
  32. Very specific:

    Always add "use node"; to the top of files containing actions that use Node.js built-in modules.

    line 271
  33. Very specific:

    Never use ctx.db inside of an action.

    line 272
  34. Very specific:

    Only use the crons.interval or crons.cron methods to schedule cron jobs.

    line 291
  35. Very specific:

    If a cron calls an internal function, always import the internal object from '\_generated/api`, even if the internal function is registered …

    line 316
  36. Very specific:

    Do NOT use the deprecated ctx.storage.getMetadata call for loading a file's metadata.

    line 322
  37. Very specific:

    Instead, query the _storage system table.

    line 324

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
convex2.mdc
---
description:
globs:
alwaysApply: true
---

---

description: Guidelines and best practices for building Convex projects, including database schema design, queries, mutations, and real-world examples
globs: **/\*.ts,**/_.tsx,\*\*/_.js,\*_/_.jsx

---

# Convex guidelines

## Function guidelines

### New function syntax

- always create type-safe code
- ALWAYS use the new function syntax for Convex functions. For example:
  `typescript
    import { query } from "./_generated/server";
    import { v } from "convex/values";
    export const f = query({
        args: {},
        returns: v.null(),
        handler: async (ctx, args) => {
        // Function body
        },
    });
    `

### Http endpoint syntax

- HTTP endpoints are defined in `convex/http.ts` and require an `httpAction` decorator. For example:
  `typescript
    import { httpRouter } from "convex/server";
    import { httpAction } from "./_generated/server";
    const http = httpRouter();
    http.route({
        path: "/echo",
        method: "POST",
        handler: httpAction(async (ctx, req) => {
        const body = await req.bytes();
        return new Response(body, { status: 200 });
        }),
    });
    `
- HTTP endpoints are always registered at the exact path you specify in the `path` field. For example, if you specify `/api/someRoute`, the endpoint will be registered at `/api/someRoute`.

### Validators

- Below is an example of an array validator:
  ```typescript
  import { mutation } from "./\_generated/server";
  import { v } from "convex/values";

                            export default mutation({
                            args: {
                                simpleArray: v.array(v.union(v.string(), v.number())),
                            },
                            handler: async (ctx, args) => {
                                //...
                            },
                            });
                            ```

- Below is an example of a schema with validators that codify a discriminated union type:
  ```typescript
  import { defineSchema, defineTable } from "convex/server";
  import { v } from "convex/values";

                            export default defineSchema({
                                results: defineTable(
                                    v.union(
                                        v.object({
                                            kind: v.literal("error"),
                                            errorMessage: v.string(),
                                        }),
                                        v.object({
                                            kind: v.literal("success"),
                                            value: v.number(),
                                        }),
                                    ),
                                )
                            });
                            ```

- Always use the `v.null()` validator when returning a null value. Below is an example query that returns a null value:
  ```typescript
  import { query } from "./\_generated/server";
  import { v } from "convex/values";

                                  export const exampleQuery = query({
                                    args: {},
                                    returns: v.null(),
                                    handler: async (ctx, args) => {
                                        console.log("This query returns a null value");
                                        return null;
                                    },
                                  });
                                  ```

- Here are the valid Convex types along with their respective validators:
  Convex Type | TS/JS type | Example Usage | Validator for argument validation and schemas | Notes |
  | ----------- | ------------| -----------------------| -----------------------------------------------| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
  | Id | string | `doc._id` | `v.id(tableName)` | |
  | Null | null | `null` | `v.null()` | JavaScript's `undefined` is not a valid Convex value. Functions the return `undefined` or do not return will return `null` when called from a client. Use `null` instead. |
  | Int64 | bigint | `3n` | `v.int64()` | Int64s only support BigInts between -2^63 and 2^63-1. Convex supports `bigint`s in most modern browsers. |
  | Float64 | number | `3.1` | `v.number()` | Convex supports all IEEE-754 double-precision floating point numbers (such as NaNs). Inf and NaN are JSON serialized as strings. |
  | Boolean | boolean | `true` | `v.boolean()` |
  | String | string | `"abc"` | `v.string()` | Strings are stored as UTF-8 and must be valid Unicode sequences. Strings must be smaller than the 1MB total size limit when encoded as UTF-8. |
  | Bytes | ArrayBuffer | `new ArrayBuffer(8)` | `v.bytes()` | Convex supports first class bytestrings, passed in as `ArrayBuffer`s. Bytestrings must be smaller than the 1MB total size limit for Convex types. |
  | Array | Array] | `[1, 3.2, "abc"]` | `v.array(values)` | Arrays can have at most 8192 values. |
  | Object | Object | `{a: "abc"}` | `v.object({property: value})` | Convex only supports "plain old JavaScript objects" (objects that do not have a custom prototype). Objects can have at most 1024 entries. Field names must be nonempty and not start with "$" or "_". |
| Record      | Record      | `{"a": "1", "b": "2"}` | `v.record(keys, values)`                       | Records are objects at runtime, but can have dynamic keys. Keys must be only ASCII characters, nonempty, and not start with "$" or "\_". |

### Function registration

- Use `internalQuery`, `internalMutation`, and `internalAction` to register internal functions. These functions are private and aren't part of an app's API. They can only be called by other Convex functions. These functions are always imported from `./_generated/server`.
- Use `query`, `mutation`, and `action` to register public functions. These functions are part of the public API and are exposed to the public Internet. Do NOT use `query`, `mutation`, or `action` to register sensitive internal functions that should be kept private.
- You CANNOT register a function through the `api` or `internal` objects.
- ALWAYS include argument and return validators for all Convex functions. This includes all of `query`, `internalQuery`, `mutation`, `internalMutation`, `action`, and `internalAction`. If a function doesn't return anything, include `returns: v.null()` as its output validator.
- If the JavaScript implementation of a Convex function doesn't have a return value, it implicitly returns `null`.

### Function calling

- Use `ctx.runQuery` to call a query from a query, mutation, or action.
- Use `ctx.runMutation` to call a mutation from a mutation or action.
- Use `ctx.runAction` to call an action from an action.
- ONLY call an action from another action if you need to cross runtimes (e.g. from V8 to Node). Otherwise, pull out the shared code into a helper async function and call that directly instead.
- Try to use as few calls from actions to queries and mutations as possible. Queries and mutations are transactions, so splitting logic up into multiple calls introduces the risk of race conditions.
- All of these calls take in a `FunctionReference`. Do NOT try to pass the callee function directly into one of these calls.
- When using `ctx.runQuery`, `ctx.runMutation`, or `ctx.runAction` to call a function in the same file, specify a type annotation on the return value to work around TypeScript circularity limitations. For example,
  ```
  export const f = query({
  args: { name: v.string() },
  returns: v.string(),
  handler: async (ctx, args) => {
  return "Hello " + args.name;
  },
  });

                            export const g = query({
                              args: {},
                              returns: v.null(),
                              handler: async (ctx, args) => {
                                const result: string = await ctx.runQuery(api.example.f, { name: "Bob" });
                                return null;
                              },
                            });
                            ```

### Function references

- Function references are pointers to registered Convex functions.
- Use the `api` object defined by the framework in `convex/_generated/api.ts` to call public functions registered with `query`, `mutation`, or `action`.
- Use the `internal` object defined by the framework in `convex/_generated/api.ts` to call internal (or private) functions registered with `internalQuery`, `internalMutation`, or `internalAction`.
- Convex uses file-based routing, so a public function defined in `convex/example.ts` named `f` has a function reference of `api.example.f`.
- A private function defined in `convex/example.ts` named `g` has a function reference of `internal.example.g`.
- Functions can also registered within directories nested within the `convex/` folder. For example, a public function `h` defined in `convex/messages/access.ts` has a function reference of `api.messages.access.h`.

### Api design

- Convex uses file-based routing, so thoughtfully organize files with public query, mutation, or action functions within the `convex/` directory.
- Use `query`, `mutation`, and `action` to define public functions.
- Use `internalQuery`, `internalMutation`, and `internalAction` to define private, internal functions.

### Pagination

- Paginated queries are queries that return a list of results in incremental pages.
- You can define pagination using the following syntax:

                            ```ts
                            import { v } from "convex/values";
                            import { query, mutation } from "./_generated/server";
                            import { paginationOptsValidator } from "convex/server";
                            export const listWithExtraArg = query({
                                args: { paginationOpts: paginationOptsValidator, author: v.string() },
                                handler: async (ctx, args) => {
                                    return await ctx.db
                                    .query("messages")
                                    .filter((q) => q.eq(q.field("author"), args.author))
                                    .order("desc")
                                    .paginate(args.paginationOpts);
                                },
                            });
                            ```
                            Note: `paginationOpts` is an object with the following properties:
                            - `numItems`: the maximum number of documents to return (the validator is `v.number()`)
                            - `cursor`: the cursor to use to fetch the next page of documents (the validator is `v.union(v.string(), v.null())`)

- A query that ends in `.paginate()` returns an object that has the following properties: - page (contains an array of documents that you fetches) - isDone (a boolean that represents whether or not this is the last page of documents) - continueCursor (a string that represents the cursor to use to fetch the next page of documents)

## Validator guidelines

- `v.bigint()` is deprecated for representing signed 64-bit integers. Use `v.int64()` instead.
- Use `v.record()` for defining a record type. `v.map()` and `v.set()` are not supported.

## Schema guidelines

- Always define your schema in `convex/schema.ts`.
- Always import the schema definition functions from `convex/server`:
- System fields are automatically added to all documents and are prefixed with an underscore. The two system fields that are automatically added to all documents are `_creationTime` which has the validator `v.number()` and `_id` which has the validator `v.id(tableName)`.
- Always include all index fields in the index name. For example, if an index is defined as `["field1", "field2"]`, the index name should be "by_field1_and_field2".
- Index fields must be queried in the same order they are defined. If you want to be able to query by "field1" then "field2" and by "field2" then "field1", you must create separate indexes.

## Typescript guidelines

- You can use the helper typescript type `Id` imported from './\_generated/dataModel' to get the type of the id for a given table. For example if there is a table called 'users' you can use `Id<'users'>` to get the type of the id for that table.
- If you need to define a `Record` make sure that you correctly provide the type of the key and value in the type. For example a validator `v.record(v.id('users'), v.string())` would have the type `Record<Id<'users'>, string>`. Below is an example of using `Record` with an `Id` type in a query:
  ```ts
  import { query } from "./\_generated/server";
  import { Doc, Id } from "./\_generated/dataModel";

                    export const exampleQuery = query({
                        args: { userIds: v.array(v.id("users")) },
                        returns: v.record(v.id("users"), v.string()),
                        handler: async (ctx, args) => {
                            const idToUsername: Record<Id<"users">, string> = {};
                            for (const userId of args.userIds) {
                                const user = await ctx.db.get(userId);
                                if (user) {
                                    users[user._id] = user.username;
                                }
                            }

                            return idToUsername;
                        },
                    });
                    ```

- Be strict with types, particularly around id's of documents. For example, if a function takes in an id for a document in the 'users' table, take in `Id<'users'>` rather than `string`.
- Always use `as const` for string literals in discriminated union types.
- When using the `Array` type, make sure to always define your arrays as `const array: Array<T> = [...];`
- When using the `Record` type, make sure to always define your records as `const record: Record<KeyType, ValueType> = {...};`
- Always add `@types/node` to your `package.json` when using any Node.js built-in modules.

## Full text search guidelines

- A query for "10 messages in channel '#general' that best match the query 'hello hi' in their body" would look like:

const messages = await ctx.db
.query("messages")
.withSearchIndex("search_body", (q) =>
q.search("body", "hello hi").eq("channel", "#general"),
)
.take(10);

## Query guidelines

- Do NOT use `filter` in queries. Instead, define an index in the schema and use `withIndex` instead.
- Convex queries do NOT support `.delete()`. Instead, `.collect()` the results, iterate over them, and call `ctx.db.delete(row._id)` on each result.
- Use `.unique()` to get a single document from a query. This method will throw an error if there are multiple documents that match the query.
- When using async iteration, don't use `.collect()` or `.take(n)` on the result of a query. Instead, use the `for await (const row of query)` syntax.

### Ordering

- By default Convex always returns documents in ascending `_creationTime` order.
- You can use `.order('asc')` or `.order('desc')` to pick whether a query is in ascending or descending order. If the order isn't specified, it defaults to ascending.
- Document queries that use indexes will be ordered based on the columns in the index and can avoid slow table scans.

## Mutation guidelines

- Use `ctx.db.replace` to fully replace an existing document. This method will throw an error if the document does not exist.
- Use `ctx.db.patch` to shallow merge updates into an existing document. This method will throw an error if the document does not exist.

## Action guidelines

- Always add `"use node";` to the top of files containing actions that use Node.js built-in modules.
- Never use `ctx.db` inside of an action. Actions don't have access to the database.
- Below is an example of the syntax for an action:
  ```ts
  import { action } from "./\_generated/server";

                    export const exampleAction = action({
                        args: {},
                        returns: v.null(),
                        handler: async (ctx, args) => {
                            console.log("This action does not return anything");
                            return null;
                        },
                    });
                    ```

## Scheduling guidelines

### Cron guidelines

- Only use the `crons.interval` or `crons.cron` methods to schedule cron jobs. Do NOT use the `crons.hourly`, `crons.daily`, or `crons.weekly` helpers.
- Both cron methods take in a FunctionReference. Do NOT try to pass the function directly into one of these methods.
- Define crons by declaring the top-level `crons` object, calling some methods on it, and then exporting it as default. For example,
  ```ts
  import { cronJobs } from "convex/server";
  import { internal } from "./\_generated/api";
  import { internalAction } from "./\_generated/server";

                            const empty = internalAction({
                              args: {},
                              returns: v.null(),
                              handler: async (ctx, args) => {
                                console.log("empty");
                              },
                            });

                            const crons = cronJobs();

                            // Run `internal.crons.empty` every two hours.
                            crons.interval("delete inactive users", { hours: 2 }, internal.crons.empty, {});

                            export default crons;
                            ```

- You can register Convex functions within `crons.ts` just like any other file.
- If a cron calls an internal function, always import the `internal` object from '\_generated/api`, even if the internal function is registered in the same file.

## File storage guidelines

- Convex includes file storage for large files like images, videos, and PDFs.
- The `ctx.storage.getUrl()` method returns a signed URL for a given file. It returns `null` if the file doesn't exist.
- Do NOT use the deprecated `ctx.storage.getMetadata` call for loading a file's metadata.

                    Instead, query the `_storage` system table. For example, you can use `ctx.db.system.get` to get an `Id<"_storage">`.
                    ```
                    import { query } from "./_generated/server";
                    import { Id } from "./_generated/dataModel";

                    type FileMetadata = {
                        _id: Id<"_storage">;
                        _creationTime: number;
                        contentType?: string;
                        sha256: string;
                        size: number;
                    }

                    export const exampleQuery = query({
                        args: { fileId: v.id("_storage") },
                        returns: v.null();
                        handler: async (ctx, args) => {
                            const metadata: FileMetadata | null = await ctx.db.system.get(args.fileId);
                            console.log(metadata);
                            return null;
                        },
                    });
                    ```

- Convex storage stores items as `Blob` objects. You must convert all items to/from a `Blob` when using Convex storage.

# Examples:

## Example: chat-app

### Task

```
Create a real-time chat application backend with AI responses. The app should:
- Allow creating users with names
- Support multiple chat channels
- Enable users to send messages to channels
- Automatically generate AI responses to user messages
- Show recent message history

The backend should provide APIs for:
1. User management (creation)
2. Channel management (creation)
3. Message operations (sending, listing)
4. AI response generation using openai's GPT-4

Messages should be stored with their channel, author, and content. The system should maintain message order
and limit history display to the 10 most recent messages per channel.

```

### Analysis

1. Task Requirements Summary:

- Build a real-time chat backend with AI integration
- Support user creation
- Enable channel-based conversations
- Store and retrieve messages with proper ordering
- Generate AI responses automatically

2. Main Components Needed:

- Database tables: users, channels, messages
- Public APIs for user/channel management
- Message handling functions
- Internal AI response generation system
- Context loading for AI responses

3. Public API and Internal Functions Design:
   Public Mutations:

- createUser:
  - file path: convex/index.ts
  - arguments: {name: v.string()}
  - returns: v.object({userId: v.id("users")})
  - purpose: Create a new user with a given name
- createChannel:
  - file path: convex/index.ts
  - arguments: {name: v.string()}
  - returns: v.object({channelId: v.id("channels")})
  - purpose: Create a new channel with a given name
- sendMessage:
  - file path: convex/index.ts
  - arguments: {channelId: v.id("channels"), authorId: v.id("users"), content: v.string()}
  - returns: v.null()
  - purpose: Send a message to a channel and schedule a response from the AI

Public Queries:

- listMessages:
  - file path: convex/index.ts
  - arguments: {channelId: v.id("channels")}
  - returns: v.array(v.object({
    \_id: v.id("messages"),
    \_creationTime: v.number(),
    channelId: v.id("channels"),
    authorId: v.optional(v.id("users")),
    content: v.string(),
    }))
  - purpose: List the 10 most recent messages from a channel in descending creation order

Internal Functions:

- generateResponse:
  - file path: convex/index.ts
  - arguments: {channelId: v.id("channels")}
  - returns: v.null()
  - purpose: Generate a response from the AI for a given channel
- loadContext:
  - file path: convex/index.ts
  - arguments: {channelId: v.id("channels")}
  - returns: v.array(v.object({
    \_id: v.id("messages"),
    \_creationTime: v.number(),
    channelId: v.id("channels"),
    authorId: v.optional(v.id("users")),
    content: v.string(),
    }))
- writeAgentResponse:
  - file path: convex/index.ts
  - arguments: {channelId: v.id("channels"), content: v.string()}
  - returns: v.null()
  - purpose: Write an AI response to a given channel

4. Schema Design:

- users
  - validator: { name: v.string() }
  - indexes: <none>
- channels
  - validator: { name: v.string() }
  - indexes: <none>
- messages
  - validator: { channelId: v.id("channels"), authorId: v.optional(v.id("users")), content: v.string() }
  - indexes
    - by_channel: ["channelId"]

5. Background Processing:

- AI response generation runs asynchronously after each user message
- Uses openai's GPT-4 to generate contextual responses
- Maintains conversation context using recent message history

### Implementation

#### package.json

```typescript
{
  "name": "chat-app",
  "description": "This example shows how to build a chat app without authentication.",
  "version": "1.0.0",
  "dependencies": {
    "convex": "^1.17.4",
    "openai": "^4.79.0"
  },
  "devDependencies": {
    "typescript": "^5.7.3"
  }
}
```

#### tsconfig.json

```typescript
{
  "compilerOptions": {
    "target": "ESNext",
    "lib": ["DOM", "DOM.Iterable", "ESNext"],
    "skipLibCheck": true,
    "allowSyntheticDefaultImports": true,
    "strict": true,
    "forceConsistentCasingInFileNames": true,
    "module": "ESNext",
    "moduleResolution": "Bundler",
    "resolveJsonModule": true,
    "isolatedModules": true,
    "allowImportingTsExtensions": true,
    "noEmit": true,
    "jsx": "react-jsx"
  },
  "exclude": ["convex"],
  "include": ["**/src/**/*.tsx", "**/src/**/*.ts", "vite.config.ts"]
}
```

#### convex/index.ts

```typescript
import {
  query,
  mutation,
  internalQuery,
  internalMutation,
  internalAction,
} from "./_generated/server";
import { v } from "convex/values";
import openai from "openai";
import { internal } from "./_generated/api";

/**
 * Create a user with a given name.
 */
export const createUser = mutation({
  args: {
    name: v.string(),
  },
  returns: v.id("users"),
  handler: async (ctx, args) => {
    return await ctx.db.insert("users", { name: args.name });
  },
});

/**
 * Create a channel with a given name.
 */
export const createChannel = mutation({
  args: {
    name: v.string(),
  },
  returns: v.id("channels"),
  handler: async (ctx, args) => {
    return await ctx.db.insert("channels", { name: args.name });
  },
});

/**
 * List the 10 most recent messages from a channel in descending creation order.
 */
export const listMessages = query({
  args: {
    channelId: v.id("channels"),
  },
  returns: v.array(
    v.object({
      _id: v.id("messages"),
      _creationTime: v.number(),
      channelId: v.id("channels"),
      authorId: v.optional(v.id("users")),
      content: v.string(),
    }),
  ),
  handler: async (ctx, args) => {
    const messages = await ctx.db
      .query("messages")
      .withIndex("by_channel", (q) => q.eq("channelId", args.channelId))
      .order("desc")
      .take(10);
    return messages;
  },
});

/**
 * Send a message to a channel and schedule a response from the AI.
 */
export const sendMessage = mutation({
  args: {
    channelId: v.id("channels"),
    authorId: v.id("users"),
    content: v.string(),
  },
  returns: v.null(),
  handler: async (ctx, args) => {
    const channel = await ctx.db.get(args.channelId);
    if (!channel) {
      throw new Error("Channel not found");
    }
    const user = await ctx.db.get(args.authorId);
    if (!user) {
      throw new Error("User not found");
    }
    await ctx.db.insert("messages", {
      channelId: args.channelId,
      authorId: args.authorId,
      content: args.content,
    });
    await ctx.scheduler.runAfter(0, internal.index.generateResponse, {
      channelId: args.channelId,
    });
    return null;
  },
});

const openai = new openai();

export const generateResponse = internalAction({
  args: {
    channelId: v.id("channels"),
  },
  returns: v.null(),
  handler: async (ctx, args) => {
    const context = await ctx.runQuery(internal.index.loadContext, {
      channelId: args.channelId,
    });
    const response = await openai.chat.completions.create({
      model: "gpt-4o",
      messages: context,
    });
    const content = response.choices[0].message.content;
    if (!content) {
      throw new Error("No content in response");
    }
    await ctx.runMutation(internal.index.writeAgentResponse, {
      channelId: args.channelId,
      content,
    });
    return null;
  },
});

export const loadContext = internalQuery({
  args: {
    channelId: v.id("channels"),
  },
  returns: v.array(
    v.object({
      role: v.union(v.literal("user"), v.literal("assistant")),
      content: v.string(),
    }),
  ),
  handler: async (ctx, args) => {
    const channel = await ctx.db.get(args.channelId);
    if (!channel) {
      throw new Error("Channel not found");
    }
    const messages = await ctx.db
      .query("messages")
      .withIndex("by_channel", (q) => q.eq("channelId", args.channelId))
      .order("desc")
      .take(10);

    const result = [];
    for (const message of messages) {
      if (message.authorId) {
        const user = await ctx.db.get(message.authorId);
        if (!user) {
          throw new Error("User not found");
        }
        result.push({
          role: "user" as const,
          content: `${user.name}: ${message.content}`,
        });
      } else {
        result.push({ role: "assistant" as const, content: message.content });
      }
    }
    return result;
  },
});

export const writeAgentResponse = internalMutation({
  args: {
    channelId: v.id("channels"),
    content: v.string(),
  },
  returns: v.null(),
  handler: async (ctx, args) => {
    await ctx.db.insert("messages", {
      channelId: args.channelId,
      content: args.content,
    });
    return null;
  },
});
```

#### convex/schema.ts

```typescript
import { defineSchema, defineTable } from "convex/server";
import { v } from "convex/values";

export default defineSchema({
  channels: defineTable({
    name: v.string(),
  }),

  users: defineTable({
    name: v.string(),
  }),

  messages: defineTable({
    channelId: v.id("channels"),
    authorId: v.optional(v.id("users")),
    content: v.string(),
  }).index("by_channel", ["channelId"]),
});
```

#### src/App.tsx

```typescript
export default function App() {
  return <div>Hello World</div>;
}
```

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.