Files
pygienium/tests/agent-runner.test.ts
Michael Freno 8768f9de97
Some checks failed
port-to-omp / port (push) Failing after 2s
fix: sub-agent hang/crash stranding runs mid-phase with no save
A stalled sub-agent (provider stream never settling after the final tool
call, or a throwing session-event listener recursing through the SDK's
run-failure path to stack overflow) left the phase stuck in_progress with
no state save, no error, and no completion message — observed twice in
freno-dev, both times after comments wrote findings.md.

- agent-runner: 60-min settle watchdog on every agent phase
  (PYGIENIUM_AGENT_TIMEOUT_MS, env-tunable); timeout disposes the session
  and fails the phase loudly with a /pygienium-resume hint instead of
  hanging the check-runner's await forever.
- agent-runner: applySessionEvent — the session.subscribe listener can no
  longer throw into the SDK event pipeline (guards for partial/malformed
  events, optional-chained message_update, throwing chat forwarder).
- comments: scan no longer regenerates the full report as its final
  message (findings.md is the source of truth); fix phase reads
  findings.md with embedded fallback.
- check-runner: failing state-save inside the catch path can't double-
  fault or escape as an unhandled rejection; completion posting is
  best-effort.
- tests: watchdog timeout test, comments task-text regression tests,
  applySessionEvent malformed-shape unit tests. 146 pass, tsc clean.
- README: document PYGIENIUM_AGENT_TIMEOUT_MS.
2026-08-11 08:47:12 -04:00

138 lines
3.9 KiB
TypeScript

/**
* agent-runner.test.ts — unit tests for the session event accumulator.
*
* `applySessionEvent` runs synchronously inside the SDK's event pipeline; a
* throw there crashes the host (the SDK's run-failure path re-emits events
* through the same callback → stack overflow), stranding run-state at the
* phase boundary. These tests pin the handler to never throw on the partial /
* malformed event shapes streaming sessions actually emit.
*/
import { describe, expect, it } from "bun:test";
import {
applySessionEvent,
type SessionEventAccumulator,
} from "../src/agent-runner.js";
import type { AgentSessionEvent } from "@earendil-works/pi-coding-agent";
function fresh(): SessionEventAccumulator {
return { text: "" };
}
/** Build a typed-as-unknown event so malformed shapes compile in tests. */
function event(shape: unknown): AgentSessionEvent {
return shape as AgentSessionEvent;
}
describe("applySessionEvent", () => {
it("accumulates text_delta stream events in order", () => {
const acc = fresh();
applySessionEvent(
acc,
event({
type: "message_update",
assistantMessageEvent: { type: "text_delta", delta: "foo" },
}),
);
applySessionEvent(
acc,
event({
type: "message_update",
assistantMessageEvent: { type: "text_delta", delta: "bar" },
}),
);
expect(acc.text).toBe("foobar");
});
it("does not throw on a message_update with no assistantMessageEvent", () => {
const acc = fresh();
expect(() =>
applySessionEvent(acc, event({ type: "message_update" })),
).not.toThrow();
expect(acc.text).toBe("");
});
it("does not throw on a message_update with an unknown event shape", () => {
const acc = fresh();
expect(() => applySessionEvent(acc, event({ type: "bogus_event" }))).not.toThrow();
expect(() => applySessionEvent(acc, event(null))).not.toThrow();
expect(() => applySessionEvent(acc, event(undefined))).not.toThrow();
expect(acc.text).toBe("");
});
it("captures full text + stopReason from message_end when nothing streamed", () => {
const acc = fresh();
applySessionEvent(
acc,
event({
type: "message_end",
message: {
role: "assistant",
stopReason: "stop",
content: [{ type: "text", text: "full report" }],
},
}),
);
expect(acc.text).toBe("full report");
expect(acc.stopReason).toBe("stop");
});
it("does not throw on a message_end with no message", () => {
const acc = fresh();
expect(() => applySessionEvent(acc, event({ type: "message_end" }))).not.toThrow();
expect(acc.text).toBe("");
});
it("records an errorMessage surfaced on the final message", () => {
const acc = fresh();
applySessionEvent(
acc,
event({
type: "message_end",
message: { role: "assistant", errorMessage: "upstream 529" },
}),
);
expect(acc.errorMessage).toBe("upstream 529");
});
it("forwards stream-driving events and swallows a throwing forwarder", () => {
const originalError = console.error;
console.error = () => {};
try {
const forwarded: string[] = [];
const forward = (ev: AgentSessionEvent) => {
forwarded.push(ev.type);
if (ev.type === "tool_execution_end") throw new Error("renderer boom");
};
const acc = fresh();
applySessionEvent(
acc,
event({ type: "tool_execution_start", toolName: "bash" }),
forward,
);
applySessionEvent(
acc,
event({ type: "tool_execution_end", toolName: "bash" }),
forward,
);
expect(forwarded).toEqual(["tool_execution_start", "tool_execution_end"]);
} finally {
console.error = originalError;
}
});
it("does not forward non-stream-driving events", () => {
const forwarded: string[] = [];
const acc = fresh();
applySessionEvent(
acc,
event({ type: "message_update", assistantMessageEvent: { type: "text_delta", delta: "x" } }),
(ev) => forwarded.push(ev.type),
);
applySessionEvent(acc, event({ type: "agent_settled" }), (ev) =>
forwarded.push(ev.type),
);
expect(forwarded).toEqual([]);
expect(acc.text).toBe("x");
});
});