can1357
24d58033bb
The eval agent() helper used `agent_type`/`return_handle` (snake_case) in
Python/Ruby/Julia and `agentType`/`returnHandle` (camelCase) in JS, forcing
the prelude docs to repeat every option twice ("JS same but camelcased").
Both are now single lowercase words identical across all four runtimes, and
`agent` matches the `task` tool's existing agent-selection parameter.
- Renamed across py/js/rb/jl preludes (signatures, forwarding, docstrings).
- Renamed the `__agent__` bridge wire protocol + `EvalAgentArgs` (`agentType`
→ `agent`, `returnHandle` → `handle`) so no prelude-side remap is needed.
- Updated prompt docs (workflow-notice.md, tools/eval.md), repo docs
(docs/tools/eval.md, docs/python-repl.md), and all bridge/prelude tests.
- CHANGELOG: Breaking Changes entry under [Unreleased].
67 lines
2.2 KiB
TypeScript
67 lines
2.2 KiB
TypeScript
import { afterEach, describe, expect, it, vi } from "bun:test";
|
|
import { Settings } from "@oh-my-pi/pi-coding-agent/config/settings";
|
|
import { runEvalAgent } from "@oh-my-pi/pi-coding-agent/eval/agent-bridge";
|
|
import type { LocalProtocolOptions } from "@oh-my-pi/pi-coding-agent/internal-urls";
|
|
import type { MCPManager } from "@oh-my-pi/pi-coding-agent/mcp";
|
|
import * as taskDiscovery from "@oh-my-pi/pi-coding-agent/task/discovery";
|
|
import * as taskExecutor from "@oh-my-pi/pi-coding-agent/task/executor";
|
|
import type { AgentDefinition, SingleResult } from "@oh-my-pi/pi-coding-agent/task/types";
|
|
import type { ToolSession } from "@oh-my-pi/pi-coding-agent/tools";
|
|
|
|
function createResult(): SingleResult {
|
|
return {
|
|
index: 0,
|
|
id: "0-Task",
|
|
agent: "task",
|
|
agentSource: "bundled",
|
|
task: "do work",
|
|
exitCode: 0,
|
|
output: "done",
|
|
stderr: "",
|
|
truncated: false,
|
|
durationMs: 1,
|
|
tokens: 0,
|
|
requests: 0,
|
|
};
|
|
}
|
|
|
|
describe("runEvalAgent", () => {
|
|
afterEach(() => {
|
|
vi.restoreAllMocks();
|
|
});
|
|
|
|
it("forwards session-scoped MCP and local protocol options", async () => {
|
|
const agent: AgentDefinition = {
|
|
name: "task",
|
|
description: "Task agent",
|
|
systemPrompt: "Handle task",
|
|
source: "bundled",
|
|
};
|
|
vi.spyOn(taskDiscovery, "discoverAgents").mockResolvedValue({ agents: [agent], projectAgentsDir: null });
|
|
const runSubprocessSpy = vi.spyOn(taskExecutor, "runSubprocess").mockResolvedValue(createResult());
|
|
|
|
const mcpManager = { sentinel: "mcp" } as unknown as MCPManager;
|
|
const localProtocolOptions: LocalProtocolOptions = {
|
|
getArtifactsDir: () => "/tmp/parent-artifacts",
|
|
getSessionId: () => "parent-session",
|
|
};
|
|
const session = {
|
|
cwd: "/tmp",
|
|
settings: Settings.isolated(),
|
|
getSessionSpawns: () => "*",
|
|
getSessionFile: () => null,
|
|
mcpManager,
|
|
localProtocolOptions,
|
|
getAgentId: () => "BridgeParent",
|
|
} as unknown as ToolSession;
|
|
|
|
await runEvalAgent({ prompt: "do work", agent: "task" }, { session });
|
|
|
|
expect(runSubprocessSpy).toHaveBeenCalledTimes(1);
|
|
const options = runSubprocessSpy.mock.calls[0]?.[0];
|
|
expect(options?.mcpManager).toBe(mcpManager);
|
|
expect(options?.localProtocolOptions).toBe(localProtocolOptions);
|
|
expect(options?.parentAgentId).toBe("BridgeParent");
|
|
});
|
|
});
|