can1357
84ec8fba49
- Removed the legacy `parseEvalInput` parser module and `eval.lark`, eliminating `*** Cell` stream parsing. - Replaced eval tool arguments from single `input` strings to ordered `cells` arrays in tool calls and schema. - Updated execution to resolve language explicitly, map `py` to `python`, and apply timeout/reset defaults. - Removed backend sniffing and `ABORT_WARNING` suffix handling, then updated docs and tests to the new JSON cells format.
72 lines
2.6 KiB
TypeScript
72 lines
2.6 KiB
TypeScript
import { afterEach, describe, expect, it, vi } from "bun:test";
|
|
import { Settings } from "@oh-my-pi/pi-coding-agent/config/settings";
|
|
import * as evalIndex from "@oh-my-pi/pi-coding-agent/eval";
|
|
import * as pyKernel from "@oh-my-pi/pi-coding-agent/eval/py/kernel";
|
|
import type { ToolSession } from "@oh-my-pi/pi-coding-agent/tools";
|
|
import { EvalTool } from "@oh-my-pi/pi-coding-agent/tools/eval";
|
|
|
|
function makeSession(): ToolSession {
|
|
return {
|
|
cwd: "/tmp/eval-test",
|
|
hasUI: false,
|
|
getSessionFile: () => null,
|
|
getSessionSpawns: () => null,
|
|
settings: Settings.isolated(),
|
|
};
|
|
}
|
|
|
|
const mockResult = {
|
|
output: "ok",
|
|
exitCode: 0,
|
|
cancelled: false,
|
|
truncated: false,
|
|
artifactId: undefined,
|
|
totalLines: 1,
|
|
totalBytes: 2,
|
|
outputLines: 1,
|
|
outputBytes: 2,
|
|
displayOutputs: [],
|
|
};
|
|
|
|
describe("EvalTool language resolution", () => {
|
|
afterEach(() => {
|
|
vi.restoreAllMocks();
|
|
});
|
|
|
|
it("dispatches to js when fenced code declares ```js", async () => {
|
|
vi.spyOn(pyKernel, "checkPythonKernelAvailability").mockResolvedValue({ ok: true });
|
|
const jsExecuteSpy = vi.spyOn(evalIndex.jsBackend, "execute").mockResolvedValue(mockResult);
|
|
const pythonExecuteSpy = vi.spyOn(evalIndex.pythonBackend, "execute");
|
|
|
|
const tool = new EvalTool(makeSession());
|
|
await tool.execute("call-1", { cells: [{ language: "js", code: "```js one\nconst x = 1;\n```\n" }] });
|
|
|
|
expect(jsExecuteSpy).toHaveBeenCalledTimes(1);
|
|
expect(pythonExecuteSpy).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("dispatches to python when fenced code declares ```python", async () => {
|
|
const pythonExecuteSpy = vi.spyOn(evalIndex.pythonBackend, "execute").mockResolvedValue(mockResult);
|
|
vi.spyOn(evalIndex.pythonBackend, "isAvailable").mockResolvedValue(true);
|
|
const jsExecuteSpy = vi.spyOn(evalIndex.jsBackend, "execute");
|
|
|
|
const tool = new EvalTool(makeSession());
|
|
await tool.execute("call-2", { cells: [{ language: "js", code: "```python one\nprint('hi')\n```\n" }] });
|
|
|
|
expect(pythonExecuteSpy).toHaveBeenCalledTimes(1);
|
|
expect(jsExecuteSpy).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("auto-detects python via syntactic markers when fence is bare", async () => {
|
|
const pythonExecuteSpy = vi.spyOn(evalIndex.pythonBackend, "execute").mockResolvedValue(mockResult);
|
|
vi.spyOn(evalIndex.pythonBackend, "isAvailable").mockResolvedValue(true);
|
|
const jsExecuteSpy = vi.spyOn(evalIndex.jsBackend, "execute");
|
|
|
|
const tool = new EvalTool(makeSession());
|
|
await tool.execute("call-3", { cells: [{ language: "js", code: "def greet():\n print('hi')\ngreet()\n" }] });
|
|
|
|
expect(pythonExecuteSpy).toHaveBeenCalledTimes(1);
|
|
expect(jsExecuteSpy).not.toHaveBeenCalled();
|
|
});
|
|
});
|