mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-10-12 20:49:53 +08:00
fix(chat): use the AI SDK's own mechanisms for quota, retries, stops and notices (#987)
## Problem
A review of how the app uses the Vercel AI SDK (two Claude reviewers and Codex, each finding checked against the SDK's type definitions and source) found five behaviours that are wrong and a set of places where the app re-implements what the SDK already provides:
1. Quota tokens were recorded in `onFinish`, which the SDK does not call when a later step fails; only a user stop was handled (`onAbort`), and the write was not awaited.
2. An automatic retry after a tool error re-sent the request body as it was when the message was sent, so the model was told the "authoritative" canvas XML was the diagram from before the turn, although `display_diagram` commits a drawing before its screenshot check can fail.
3. The screenshot check and the connection test ran their model call on `AbortSignal.timeout` only, so pressing Stop (or closing the dialog) did not stop a paid model call.
4. The client ignored `finishReason`; a reasoning model that spent the whole output budget before calling a tool left the user with no diagram and no message.
5. The connection test counted an `invalid` tool call (a tool that does not exist, unreadable input) as proof of tool support.
## Change
- `onStepFinish` records each step's `usage.totalTokens` and awaits the write; the copies in `onFinish` and `onAbort` are gone.
- `DefaultChatTransport.prepareSendMessagesRequest` sends the current canvas page XML on every request after the first of a turn; the first keeps the exported (or snapshot) XML.
- `validate-diagram` and the connection test pass `req.signal` and use the SDK's `timeout` option; `validate-diagram` reports to Langfuse under `functionId: "validate-diagram"`.
- The connection test only counts a valid tool call.
- The client's `onFinish` shows a notice (with Retry) when `finishReason === "length"` and no tool was called.
- The server validates incoming messages with `safeValidateUIMessages` (400 otherwise), drops client system messages explicitly and prunes empty model messages with `pruneMessages`.
- The chat's tools live in `lib/chat-tools.ts` with an `outputSchema` for the client-side ones; `lib/chat-message.ts` defines `ChatUIMessage` (metadata, a `data-notice` part, `InferUITools`) so `useChat`, `addToolOutput` and the tool handlers are typed.
- Error notices are assistant messages with a `data-notice` part instead of role `system` UI messages.
- Regenerate, edit and retry use `sendMessage({ messageId })`; `isResending` and `flushSync` are gone.
- `isToolUIPart` / `getToolName` replace slicing `"tool-"` off part types; `ToolPartLike` derives from the SDK's part types.
Net: 578 insertions, 439 deletions over 16 files.
## Testing
- New unit tests: a step that fails after a finished step still counts that step's tokens; the screenshot check's model call ends when the request is aborted; an invalid tool call in the connection test gives the warning; malformed messages get a 400. The first and third confirm SDK behaviour the review relied on.
- `tsc`, `biome ci` (0 errors), root `vitest run` 723 passed on the branch rebased onto #986, `next build`: clean
- Playwright, 10 chat-related specs on the dev server: 199 passed, 0 failed, both before and after the rebase onto #986
This commit is contained in:
Dayuan Jiang
@@ -0,0 +1,44 @@
|
||||
import type { InferUITools, UIMessage } from "ai"
|
||||
import type { chatTools } from "@/lib/chat-tools"
|
||||
import type { SelectedCell } from "@/stores/canvas-store"
|
||||
|
||||
/** Shapes sent with a user message (also kept in its metadata) */
|
||||
export type MessageSelection = Pick<SelectedCell, "id" | "label">[]
|
||||
|
||||
export interface ChatMessageMetadata {
|
||||
selectedCells?: MessageSelection
|
||||
}
|
||||
|
||||
/**
|
||||
* A failed request or an answer that drew nothing, shown in the chat with
|
||||
* what to do: an assistant message with this as its only part. The server
|
||||
* ignores data parts, so it never reaches the model.
|
||||
*/
|
||||
export interface ChatNotice {
|
||||
text: string
|
||||
/** Show a button that opens model settings, on the provider that refused */
|
||||
openModelConfig?: boolean
|
||||
providerId?: string
|
||||
}
|
||||
|
||||
export type ChatToolName = keyof InferUITools<typeof chatTools>
|
||||
|
||||
export type ChatUIMessage = UIMessage<
|
||||
ChatMessageMetadata,
|
||||
{ notice: ChatNotice },
|
||||
InferUITools<typeof chatTools>
|
||||
>
|
||||
|
||||
export function noticeMessage(notice: ChatNotice): ChatUIMessage {
|
||||
return {
|
||||
id: `notice-${Date.now()}`,
|
||||
role: "assistant",
|
||||
parts: [{ type: "data-notice", data: notice }],
|
||||
}
|
||||
}
|
||||
|
||||
/** The notice a message carries, if it is one */
|
||||
export function noticeOf(message: ChatUIMessage): ChatNotice | undefined {
|
||||
const part = message.parts.find((p) => p.type === "data-notice")
|
||||
return part?.data
|
||||
}
|
||||
@@ -0,0 +1,138 @@
|
||||
import { type InferUITools, tool } from "ai"
|
||||
import path from "path"
|
||||
import { z } from "zod"
|
||||
import {
|
||||
getShapeLibrary,
|
||||
SHAPE_LIBRARY_LIST,
|
||||
} from "@/packages/mcp-server/src/shape-library.ts"
|
||||
import {
|
||||
STYLE_CLASS_EXAMPLE,
|
||||
SWIMLANE_EXAMPLE,
|
||||
} from "@/packages/mcp-server/src/xml-examples.ts"
|
||||
|
||||
/**
|
||||
* The chat's tools. display_diagram, edit_diagram and append_diagram run in
|
||||
* the browser: the chat engine's tool handler puts their result on the
|
||||
* canvas and reports it back as text, so they have an output schema and no
|
||||
* execute. get_shape_library runs on the server.
|
||||
*/
|
||||
export const chatTools = {
|
||||
display_diagram: tool({
|
||||
description: `Display a diagram on draw.io. Pass ONLY the mxStyle definitions and the mxCell elements - wrapper tags and root cells are added automatically.
|
||||
|
||||
VALIDATION RULES (XML will be rejected if violated):
|
||||
1. Generate ONLY mxStyle definitions and mxCell elements - NO wrapper tags (<mxfile>, <mxGraphModel>, <root>)
|
||||
2. Do NOT include root cells (id="0" or id="1") - they are added automatically
|
||||
3. All mxCell elements must be siblings - never nested
|
||||
4. Every mxCell needs a unique id (start from "2")
|
||||
5. parent defaults to "1"; write parent="<container-id>" only for shapes inside a container
|
||||
6. Escape special chars in values: < > & "
|
||||
|
||||
A shape is one self-closing mxCell with x, y, w and h; an edge is one with source and target (a cell with source or target is always an edge). vertex="1", edge="1", parent="1" and the mxGeometry element are added automatically. Write parent only for a shape inside a container, and an mxGeometry element only for edge waypoints or for a separate label cell placed on an edge: <mxCell id="9" value="yes" style="edgeLabel;" parent="<edge id>" connectable="0"><mxGeometry x="-0.5" relative="1" as="geometry"/></mxCell>. An edge's own text simply goes in its value.
|
||||
|
||||
Example (generate ONLY this - no wrapper tags):
|
||||
${SWIMLANE_EXAMPLE}
|
||||
|
||||
Styles: define a style used by several cells ONCE with <mxStyle name="..." value="..."/> before the cells and use the name in style like a CSS class; overrides after the name win. Name only styles that two or more cells share; names must not be draw.io's own style names (text, ellipse, rhombus, swimlane, label, image, blue, green, red, gray, yellow, orange, purple, pink). A definition applies to the call it is in. html=1 and whiteSpace=wrap are added automatically, never write them. Labels are HTML: use <br> for a line break, never \\n; a literal < or > is written &lt; or &gt;.
|
||||
${STYLE_CLASS_EXAMPLE}
|
||||
|
||||
Notes:
|
||||
- For AWS diagrams, use **AWS 2025 icons**.
|
||||
- For animated connectors, add "flowAnimation=1" to edge style.
|
||||
`,
|
||||
inputSchema: z.object({
|
||||
xml: z.string().describe("XML string to be displayed on draw.io"),
|
||||
}),
|
||||
outputSchema: z.string(),
|
||||
}),
|
||||
edit_diagram: tool({
|
||||
description: `Edit the current diagram by ID-based operations (update/add/delete cells).
|
||||
|
||||
Operations:
|
||||
- update: Replace an existing cell by its id. Provide cell_id and complete new_xml.
|
||||
- add: Add a new cell. Provide cell_id (new unique id) and new_xml.
|
||||
- delete: Remove a cell. Cascade is automatic: children AND edges (source/target) are auto-deleted. Only specify ONE cell_id.
|
||||
|
||||
For update/add, new_xml is the complete mxCell in the compact form (a shape with x, y, w, h; an edge with source and target), with its complete style (named styles are not available in edit_diagram).
|
||||
|
||||
⚠️ JSON ESCAPING: Every " inside new_xml MUST be escaped as \\". Example: id=\\"5\\" value=\\"Label\\"
|
||||
|
||||
Example - Add a rectangle:
|
||||
{"operations": [{"operation": "add", "cell_id": "rect-1", "new_xml": "<mxCell id=\\"rect-1\\" value=\\"Hello\\" style=\\"rounded=1;\\" x=\\"100\\" y=\\"100\\" w=\\"120\\" h=\\"60\\"/>"}]}
|
||||
|
||||
Example - Delete container (children & edges auto-deleted):
|
||||
{"operations": [{"operation": "delete", "cell_id": "2"}]}`,
|
||||
inputSchema: z.object({
|
||||
operations: z
|
||||
.array(
|
||||
z.object({
|
||||
operation: z
|
||||
.enum(["update", "add", "delete"])
|
||||
.describe(
|
||||
"Operation to perform: add, update, or delete",
|
||||
),
|
||||
cell_id: z
|
||||
.string()
|
||||
.describe(
|
||||
"The id of the mxCell. Must match the id attribute in new_xml.",
|
||||
),
|
||||
new_xml: z
|
||||
.string()
|
||||
.optional()
|
||||
.describe(
|
||||
"Complete mxCell XML element (required for update/add)",
|
||||
),
|
||||
}),
|
||||
)
|
||||
.describe("Array of operations to apply"),
|
||||
}),
|
||||
outputSchema: z.string(),
|
||||
}),
|
||||
append_diagram: tool({
|
||||
description: `Continue generating diagram XML when previous display_diagram output was truncated due to length limits.
|
||||
|
||||
WHEN TO USE: Only call this tool after display_diagram was truncated (you'll see an error message about truncation).
|
||||
|
||||
CRITICAL INSTRUCTIONS:
|
||||
1. Do NOT include any wrapper tags - just continue the mxCell elements
|
||||
2. Continue from EXACTLY where your previous output stopped
|
||||
3. Complete the remaining mxCell elements
|
||||
4. If still truncated, call append_diagram again with the next fragment
|
||||
|
||||
Example: If previous output ended with '<mxCell id="x" style="rounded=1', continue with ';" x="40" y="40" w="120" h="60"/>' and complete the remaining elements.`,
|
||||
inputSchema: z.object({
|
||||
xml: z
|
||||
.string()
|
||||
.describe(
|
||||
"Continuation XML fragment to append (NO wrapper tags)",
|
||||
),
|
||||
}),
|
||||
outputSchema: z.string(),
|
||||
}),
|
||||
get_shape_library: tool({
|
||||
description: `Get draw.io shape/icon library documentation with style syntax and shape names.
|
||||
|
||||
Available libraries:
|
||||
${SHAPE_LIBRARY_LIST}
|
||||
|
||||
Call this tool to get shape names and usage syntax for a specific library.`,
|
||||
inputSchema: z.object({
|
||||
library: z
|
||||
.string()
|
||||
.describe(
|
||||
"Library name (e.g., 'aws4', 'kubernetes', 'flowchart')",
|
||||
),
|
||||
}),
|
||||
execute: async ({ library }) => {
|
||||
// Only known library names reach the file system
|
||||
const result = await getShapeLibrary(
|
||||
library,
|
||||
path.join(process.cwd(), "docs/shape-libraries"),
|
||||
)
|
||||
return result.ok ? result.text : result.error
|
||||
},
|
||||
}),
|
||||
}
|
||||
|
||||
/** The tool names and their input and output types, for the UI messages */
|
||||
export type ChatTools = InferUITools<typeof chatTools>
|
||||
+8
-4
@@ -1,6 +1,7 @@
|
||||
import { LangfuseClient } from "@langfuse/client"
|
||||
import { observe, updateActiveTrace } from "@langfuse/tracing"
|
||||
import * as api from "@opentelemetry/api"
|
||||
import type { TelemetrySettings } from "ai"
|
||||
import { randomUUID } from "crypto"
|
||||
|
||||
// Singleton LangfuseClient instance for direct API calls
|
||||
@@ -115,20 +116,23 @@ export function endTrace() {
|
||||
}
|
||||
}
|
||||
|
||||
// Get telemetry config for streamText
|
||||
// Telemetry settings for streamText and generateText
|
||||
export function getTelemetryConfig(params: {
|
||||
sessionId?: string
|
||||
userId?: string
|
||||
}) {
|
||||
/** Names the trace of a model call outside the chat's observe() span */
|
||||
functionId?: string
|
||||
}): TelemetrySettings | undefined {
|
||||
if (!isLangfuseEnabled()) return undefined
|
||||
|
||||
return {
|
||||
isEnabled: true,
|
||||
functionId: params.functionId,
|
||||
recordInputs: true,
|
||||
recordOutputs: true,
|
||||
metadata: {
|
||||
sessionId: params.sessionId,
|
||||
userId: params.userId,
|
||||
...(params.sessionId && { sessionId: params.sessionId }),
|
||||
...(params.userId && { userId: params.userId }),
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -199,13 +199,16 @@ export async function testModelConnection(
|
||||
tools: { ping: PING_TOOL },
|
||||
maxOutputTokens: 1024,
|
||||
maxRetries: 0,
|
||||
abortSignal: AbortSignal.timeout(TEST_TIMEOUT_MS),
|
||||
// Ends with the request: the user closed the dialog or the page
|
||||
abortSignal: req.signal,
|
||||
timeout: TEST_TIMEOUT_MS,
|
||||
})
|
||||
let calledTool = false
|
||||
let finishReason: string | undefined
|
||||
for await (const part of result.fullStream) {
|
||||
if (part.type === "error") throw part.error
|
||||
// The timeout ends the stream with an abort part, not an error
|
||||
// The timeout (or the request's end) ends the stream with an
|
||||
// abort part, not an error
|
||||
if (part.type === "abort") {
|
||||
const timeout = new Error(
|
||||
`The model did not answer within ${TEST_TIMEOUT_MS / 1000} s.`,
|
||||
@@ -213,7 +216,9 @@ export async function testModelConnection(
|
||||
timeout.name = "TimeoutError"
|
||||
throw timeout
|
||||
}
|
||||
if (part.type === "tool-call") {
|
||||
// A call of a tool that does not exist, or with unreadable
|
||||
// input, arrives marked invalid: no proof of tool support
|
||||
if (part.type === "tool-call" && !part.invalid) {
|
||||
calledTool = true
|
||||
break
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user