Files
next-ai-draw-io/tests/e2e/lib/helpers.ts
dayuan.jiang cd1df1eb6a feat(diagram-engine): wire up restructure_diagram + stencil catalog
Closes the loop: the model can now build and edit AWS architecture diagrams by
declaring structure, and never writes an mxCell again.

catalog.ts — 983 AWS icon and 19 group stencils as a name→style map, generated from
drawio-ai-kit's catalog (itself generated from jgraph's draw.io shape index). Styles
are verbatim, so the official category colours, connection points and aspect=fixed
come along for free and nothing is hand-assembled. An invented name is rejected with
suggestions instead of rendering as a blank square, which is what draw.io does with
an unknown resIcon today.

operations.ts — what the model actually sends: add_icon / add_container / move /
link / set_dir and so on, applied in order against the tree. Guards the things that
break a diagram quietly: duplicate ids (draw.io drops one of the two cells), edges
left pointing at a removed node, and moving a container inside itself.

index.ts — the entry point. current XML → parse → apply ops → check names → layout →
render → new XML. The tree is not stored between calls; it is re-derived from the
canvas every time, so a user's manual edits are input to the next layout rather than
state to reconcile.

Token cost, measured with Claude's tokenizer rather than estimated:
  - build a VPC diagram:  515 tok as operations vs 3180 as XML   (6.2x)
  - add one icon:          27 tok as an operation vs 3823 re-emitting (142x)
  - read current state:   216 tok as an outline vs 3180 as XML   (14.7x)

The 142x is the one that matters day to day: "add a Redis" is one operation, not a
rewrite of the whole diagram.

Routing in the system prompt sends AWS architecture through this path and leaves
flowcharts, BPMN, sequence diagrams, mind maps and Azure/GCP on display_diagram —
the layout engine's primitives (nested rows, columns, grids) do not model a sequence
diagram's lifelines or a mind map's radial spread, and pretending otherwise would
make those worse rather than better.

Also: added a NOTICE recording the MIT port and the AWS Architecture Icons terms,
and a narrow .gitignore exception so the generated catalog is tracked while the
root data/ directory (admin settings, contains secrets) stays ignored.

403 unit tests + 3 new e2e. Verified in the real app: a structural tool call renders
with real stencils and container markers; a second call adds one node and keeps
everything from the first; an invented name is refused and nothing is drawn. The 13
existing diagram e2e tests still pass.
2026-08-09 13:49:11 +09:00

121 lines
3.4 KiB
TypeScript

/**
* Shared test helpers for E2E tests
*/
/**
* Creates a mock SSE response for the chat API
* Format matches AI SDK UI message stream protocol
*/
export function createMockSSEResponse(
xml: string,
text: string,
toolName = "display_diagram",
) {
const messageId = `msg_${Date.now()}`
const toolCallId = `call_${Date.now()}`
const textId = `text_${Date.now()}`
const events = [
{ type: "start", messageId },
{ type: "text-start", id: textId },
{ type: "text-delta", id: textId, delta: text },
{ type: "text-end", id: textId },
{ type: "tool-input-start", toolCallId, toolName },
{ type: "tool-input-available", toolCallId, toolName, input: { xml } },
{
type: "tool-output-available",
toolCallId,
output: "Successfully displayed the diagram",
},
{ type: "finish" },
]
return (
events.map((e) => `data: ${JSON.stringify(e)}\n\n`).join("") +
"data: [DONE]\n\n"
)
}
/**
* Creates a mock SSE response for a tool whose input is not `{ xml }`.
*
* createMockSSEResponse hardcodes the display_diagram shape; this takes the input
* object verbatim, so tools like restructure_diagram can be driven through the same
* path the model uses.
*/
export function createMockToolResponse(
toolName: string,
input: unknown,
text: string,
) {
const messageId = `msg_${Date.now()}`
const toolCallId = `call_${Date.now()}`
const textId = `text_${Date.now()}`
const events = [
{ type: "start", messageId },
{ type: "text-start", id: textId },
{ type: "text-delta", id: textId, delta: text },
{ type: "text-end", id: textId },
{ type: "tool-input-start", toolCallId, toolName },
{ type: "tool-input-available", toolCallId, toolName, input },
{ type: "finish" },
]
return (
events.map((e) => `data: ${JSON.stringify(e)}\n\n`).join("") +
"data: [DONE]\n\n"
)
}
/**
* Creates a text-only SSE response (no tool call)
*/
export function createTextOnlyResponse(text: string) {
const messageId = `msg_${Date.now()}`
const textId = `text_${Date.now()}`
const events = [
{ type: "start", messageId },
{ type: "text-start", id: textId },
{ type: "text-delta", id: textId, delta: text },
{ type: "text-end", id: textId },
{ type: "finish" },
]
return (
events.map((e) => `data: ${JSON.stringify(e)}\n\n`).join("") +
"data: [DONE]\n\n"
)
}
/**
* Creates a mock SSE response with a tool error
*/
export function createToolErrorResponse(text: string, errorMessage: string) {
const messageId = `msg_${Date.now()}`
const toolCallId = `call_${Date.now()}`
const textId = `text_${Date.now()}`
const events = [
{ type: "start", messageId },
{ type: "text-start", id: textId },
{ type: "text-delta", id: textId, delta: text },
{ type: "text-end", id: textId },
{ type: "tool-input-start", toolCallId, toolName: "display_diagram" },
{
type: "tool-input-available",
toolCallId,
toolName: "display_diagram",
input: { xml: "<invalid>" },
},
{ type: "tool-output-error", toolCallId, error: errorMessage },
{ type: "finish" },
]
return (
events.map((e) => `data: ${JSON.stringify(e)}\n\n`).join("") +
"data: [DONE]\n\n"
)
}