mirror of
https://github.com/badlogic/pi-mono.git
synced 2026-11-05 23:37:25 +00:00
e9c0ff4d84
src/next is src (the main export), src/next-node is src/node with short subpaths (/http, /workers, /plugins, /plugins/runtime, /app, /surfaces, /web, /react, /tui, /tui/launcher); the foundations get /json and /watch; Chord v1 moves to src/old (/old, /old/node) until p2 runs on v2; tests and docs move likewise (test/, docs/, test/old, docs/old). Durable and env import the foundations from their subpaths.
806 lines
31 KiB
TypeScript
806 lines
31 KiB
TypeScript
// `afterTool` runs on every result a tool task writes, also those the Harness decides without executing the tool
|
|
// (#11043).
|
|
|
|
import { mkdtemp, rm } from "node:fs/promises";
|
|
import { tmpdir } from "node:os";
|
|
import { join } from "node:path";
|
|
import type { JsonValue } from "@earendil-works/chord/json";
|
|
import {
|
|
type AssistantMessage,
|
|
fauxAssistantMessage,
|
|
fauxText,
|
|
fauxToolCall,
|
|
type ToolResultMessage,
|
|
} from "@earendil-works/pi-ai";
|
|
import {
|
|
defineTool,
|
|
type EntryRecord,
|
|
type Harness,
|
|
LiveDoc,
|
|
MemoryStorage,
|
|
type NestedToolExecutionResult,
|
|
ResetEntry,
|
|
ROOT_CONVERSATION_ID,
|
|
type Storage,
|
|
type TaskId,
|
|
type ToolExecutionResult,
|
|
type ToolHookCall,
|
|
type ToolRegistration,
|
|
ToolResultEntry,
|
|
ToolTask,
|
|
} from "@earendil-works/pi-durable";
|
|
import { bool, obj, opt, str } from "@earendil-works/pi-schema";
|
|
import { afterEach, describe, expect, it } from "vitest";
|
|
import { openNodeSqliteStorage } from "../src/storage/sqlite/node.ts";
|
|
import { commitWrites } from "../src/testing/commit-writes.ts";
|
|
import { allEntries, type ChatSetup, chatSetup, openChat, waitFor } from "./chat-support.ts";
|
|
import { addHooks, addTool } from "./harness-support.ts";
|
|
import { context } from "./session-support.ts";
|
|
import { aborted, deferred } from "./task-support.ts";
|
|
|
|
const directories = new Set<string>();
|
|
/** Storages of killed Harnesses, never closed by them: closed after each test. */
|
|
const killed = new Set<Storage>();
|
|
|
|
afterEach(async () => {
|
|
for (const storage of killed) await storage.close(context).catch(() => {});
|
|
killed.clear();
|
|
for (const directory of directories) await rm(directory, { recursive: true, force: true });
|
|
directories.clear();
|
|
});
|
|
|
|
async function sqlitePath(): Promise<string> {
|
|
const directory = await mkdtemp(join(tmpdir(), "pi-durable-tool-hooks-"));
|
|
directories.add(directory);
|
|
return join(directory, "session.sqlite");
|
|
}
|
|
|
|
/** Open a chat over the SQLite file at `path`; `kill()` simulates a crash: every later storage call hangs. */
|
|
async function open(path: string, setup: ChatSetup) {
|
|
const inner = await openNodeSqliteStorage(path);
|
|
let dead = false;
|
|
const storage = new Proxy(inner, {
|
|
get(target, property) {
|
|
const value = Reflect.get(target, property, target);
|
|
if (typeof value !== "function") return value;
|
|
return (...args: unknown[]) => (dead ? new Promise(() => {}) : value.apply(target, args));
|
|
},
|
|
});
|
|
const opened = await openChat(storage, setup);
|
|
opened.harness.resume();
|
|
const kill = (): void => {
|
|
dead = true;
|
|
killed.add(inner);
|
|
};
|
|
return { ...opened, kill };
|
|
}
|
|
|
|
/** Let deferred progress commits (`persistWithinMs: 0`) reach Storage before a crash. */
|
|
function stored(): Promise<void> {
|
|
return new Promise((resolve) => setTimeout(resolve, 50));
|
|
}
|
|
|
|
const Parameters = obj({ text: opt(str()) });
|
|
|
|
function tool(
|
|
name: string,
|
|
execute: ToolRegistration<typeof Parameters>["execute"],
|
|
extra: Partial<ToolRegistration<typeof Parameters>> = {},
|
|
): ToolRegistration<typeof Parameters> {
|
|
return defineTool({ name, description: name, parameters: Parameters, execute, ...extra });
|
|
}
|
|
|
|
function calls(...list: readonly (readonly [string, Record<string, JsonValue>, string])[]): AssistantMessage {
|
|
return fauxAssistantMessage(
|
|
list.map(([name, args, id]) => fauxToolCall(name, args, { id })),
|
|
{ stopReason: "toolUse" },
|
|
);
|
|
}
|
|
|
|
const DONE = fauxAssistantMessage([fauxText("done")]);
|
|
|
|
function results(entries: readonly EntryRecord[]): Map<string, ToolResultMessage> {
|
|
const messages = entries
|
|
.filter((entry) => ToolResultEntry.is(entry))
|
|
.map((entry) => entry.model![0] as ToolResultMessage);
|
|
return new Map(messages.map((message) => [message.toolCallId, message]));
|
|
}
|
|
|
|
function text(message: ToolResultMessage | undefined): string {
|
|
return (message?.content ?? []).map((item) => (item.type === "text" ? item.text : "")).join("|");
|
|
}
|
|
|
|
function codes(result: { readonly diagnostics?: readonly { readonly code?: string }[] }): (string | undefined)[] {
|
|
return (result.diagnostics ?? []).map((diagnostic) => diagnostic.code);
|
|
}
|
|
|
|
async function diagnosticsOf(entries: readonly EntryRecord[], callId: string): Promise<(string | undefined)[]> {
|
|
const entry = entries.find(
|
|
(each) => ToolResultEntry.is(each) && (each.model![0] as ToolResultMessage).toolCallId === callId,
|
|
);
|
|
return codes((entry?.data ?? {}) as { diagnostics?: { code?: string }[] });
|
|
}
|
|
|
|
type Seen = { readonly call: ToolHookCall; readonly result: ToolExecutionResult };
|
|
|
|
async function toolTaskId(harness: Harness, index = 0): Promise<TaskId> {
|
|
let id: TaskId | undefined;
|
|
await waitFor(async () => {
|
|
id = (await harness.snapshot(LiveDoc, ROOT_CONVERSATION_ID, context))?.tools?.[index]?.taskId;
|
|
return id !== undefined;
|
|
});
|
|
return id!;
|
|
}
|
|
|
|
describe("afterTool on results the call phase decides", () => {
|
|
// #11043
|
|
it("sees and replaces unavailable, invalid, and blocked results, with the raw arguments", async () => {
|
|
const setup = chatSetup();
|
|
let ran = 0;
|
|
const echo = tool("echo", async () => {
|
|
ran++;
|
|
return { output: [{ type: "text", text: "ran" }] };
|
|
});
|
|
addTool(setup.registry, echo);
|
|
addTool(
|
|
setup.registry,
|
|
tool("gone", async () => ({ output: [] })),
|
|
);
|
|
const seen: Seen[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
beforeTool: (call) => {
|
|
if (call.id === "block") return { block: "not today" };
|
|
if (call.id === "rewrite") return { arguments: { text: { not: "a string" } } };
|
|
return undefined;
|
|
},
|
|
afterTool: (call, result) => {
|
|
seen.push({ call, result });
|
|
return { ...result, output: [{ type: "text", text: `hooked ${call.id}` }], details: { by: "hook" } };
|
|
},
|
|
});
|
|
let root!: Awaited<ReturnType<typeof openChat>>["root"];
|
|
setup.faux.setResponses([
|
|
async () => {
|
|
// The tool is offered but no longer resolves when its task runs.
|
|
await root.configure({ tools: [echo] }, context);
|
|
return calls(
|
|
["gone", {}, "unavailable"],
|
|
["echo", { text: { not: "a string" } }, "invalid"],
|
|
["echo", { text: "x" }, "rewrite"],
|
|
["echo", {}, "block"],
|
|
);
|
|
},
|
|
DONE,
|
|
]);
|
|
const opened = await openChat(new MemoryStorage(), setup);
|
|
root = opened.root;
|
|
const settled = await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(settled.status).toBe("done");
|
|
expect(ran).toBe(0);
|
|
const byId = new Map(seen.map((each) => [each.call.id, each]));
|
|
expect([...byId.keys()].sort()).toEqual(["block", "invalid", "rewrite", "unavailable"]);
|
|
expect(codes(byId.get("unavailable")!.result)).toEqual(["tool_unavailable"]);
|
|
expect(codes(byId.get("invalid")!.result)).toEqual(["invalid_arguments"]);
|
|
expect(codes(byId.get("rewrite")!.result)).toEqual(["invalid_arguments"]);
|
|
expect(codes(byId.get("block")!.result)).toEqual(["blocked"]);
|
|
// Hooks see the call as the model made it, also when it is invalid or `beforeTool` rewrote it.
|
|
expect(byId.get("invalid")!.call.arguments).toEqual({ text: { not: "a string" } });
|
|
expect(byId.get("rewrite")!.call.arguments).toEqual({ text: "x" });
|
|
const entries = await allEntries(root);
|
|
const messages = results(entries);
|
|
for (const id of ["unavailable", "invalid", "rewrite", "block"]) {
|
|
const message = messages.get(id)!;
|
|
expect(message).toMatchObject({ isError: true, details: { by: "hook" } });
|
|
expect(text(message).startsWith(`hooked ${id}|<harness>`)).toBe(true);
|
|
}
|
|
await opened.harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("bounds a replacement output with the tool's limits, or the defaults for an unresolved tool", async () => {
|
|
const setup = chatSetup();
|
|
addTool(
|
|
setup.registry,
|
|
tool("small", async () => ({ output: [] }), { outputLimits: { maxBytes: 10 } }),
|
|
);
|
|
addHooks(setup.registry, ToolTask, {
|
|
beforeTool: () => ({ block: "no" }),
|
|
afterTool: (call, result) => ({
|
|
...result,
|
|
output: [{ type: "text", text: call.id === "c2" ? "x".repeat(100) : "y".repeat(60 * 1024) }],
|
|
}),
|
|
});
|
|
let root!: Awaited<ReturnType<typeof openChat>>["root"];
|
|
setup.faux.setResponses([
|
|
async () => {
|
|
await root.configure({ tools: [] }, context);
|
|
return calls(["small", {}, "c1"]);
|
|
},
|
|
DONE,
|
|
]);
|
|
const opened = await openChat(new MemoryStorage(), setup);
|
|
root = opened.root;
|
|
await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
await root.configure({ tools: null }, context);
|
|
setup.faux.setResponses([calls(["small", {}, "c2"]), DONE]);
|
|
await (await root.submit({ type: "input", content: "again" }, context)).wait(context);
|
|
const entries = await allEntries(root);
|
|
const messages = results(entries);
|
|
// Unresolved: the default 50 KB.
|
|
const unresolved = messages.get("c1")!.content[0];
|
|
expect(unresolved?.type === "text" && unresolved.text.length).toBe(50 * 1024);
|
|
expect(await diagnosticsOf(entries, "c1")).toEqual(["tool_unavailable", "truncated"]);
|
|
const bounded = messages.get("c2")!.content[0];
|
|
expect(bounded?.type === "text" && bounded.text).toBe("x".repeat(10));
|
|
expect(await diagnosticsOf(entries, "c2")).toEqual(["blocked", "truncated"]);
|
|
await opened.harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("lets a hook's terminate on a blocked call count toward the round", async () => {
|
|
const setup = chatSetup();
|
|
addTool(
|
|
setup.registry,
|
|
tool("echo", async () => ({ output: [], control: { terminate: true } })),
|
|
);
|
|
addHooks(setup.registry, ToolTask, {
|
|
beforeTool: (call) => (call.id === "c2" ? { block: "no" } : undefined),
|
|
afterTool: (_call, result) => ({ ...result, control: { terminate: true } }),
|
|
});
|
|
setup.faux.setResponses([calls(["echo", {}, "c1"], ["echo", {}, "c2"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
const settled = await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(settled.status).toBe("done");
|
|
// The round terminated: no second request.
|
|
expect(setup.faux.state.callCount).toBe(1);
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("runs on nested invalid and blocked calls; the caller gets diagnostics and details, not output", async () => {
|
|
const setup = chatSetup();
|
|
addTool(
|
|
setup.registry,
|
|
tool("echo", async () => ({ output: [] })),
|
|
);
|
|
const nested: NestedToolExecutionResult[] = [];
|
|
addTool(
|
|
setup.registry,
|
|
tool("batch", async (_args, api, callContext) => {
|
|
nested.push(await api.executeTool("echo", { text: { not: "a string" } }, callContext));
|
|
nested.push(await api.executeTool("echo", { text: "secret" }, callContext));
|
|
nested.push(await api.executeTool("missing", {}, callContext));
|
|
return {};
|
|
}),
|
|
);
|
|
const seen: ToolHookCall[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
beforeTool: (call) => (call.arguments.text === "secret" ? { block: "no secrets" } : undefined),
|
|
afterTool: (call, result) => {
|
|
if (call.parent === undefined) return undefined;
|
|
seen.push(call);
|
|
return {
|
|
...result,
|
|
output: [{ type: "text", text: "dropped" }],
|
|
structuredOutput: { dropped: true },
|
|
details: { hooked: call.id },
|
|
diagnostics: [...(result.diagnostics ?? []), { severity: "info", code: "hooked", message: "seen" }],
|
|
};
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["batch", {}, "c1"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(seen.map((call) => call.id)).toEqual(["c1/1", "c1/2", "c1/3"]);
|
|
expect(seen.every((call) => call.parent?.callId === "c1")).toBe(true);
|
|
expect(nested.map((result) => [result.isError, codes(result)])).toEqual([
|
|
[true, ["invalid_arguments", "hooked"]],
|
|
[true, ["blocked", "hooked"]],
|
|
[true, ["tool_unavailable", "hooked"]],
|
|
]);
|
|
expect(nested.map((result) => result.details)).toEqual([
|
|
{ hooked: "c1/1" },
|
|
{ hooked: "c1/2" },
|
|
{ hooked: "c1/3" },
|
|
]);
|
|
// A Harness error result has no structured output, even when a hook supplies one.
|
|
expect(nested[1]!.structuredOutput).toBeUndefined();
|
|
expect(nested[2]!.structuredOutput).toBeUndefined();
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("gives a nested call a hook turns into a success its output as value, unless the tool has a schema", async () => {
|
|
const setup = chatSetup();
|
|
addTool(
|
|
setup.registry,
|
|
tool("plain", async () => ({ output: [] })),
|
|
);
|
|
addTool(
|
|
setup.registry,
|
|
tool("typed", async () => ({ output: [], structuredOutput: { ok: true } }), {
|
|
structuredOutputSchema: obj({ ok: bool() }),
|
|
}),
|
|
);
|
|
const nested: NestedToolExecutionResult[] = [];
|
|
addTool(
|
|
setup.registry,
|
|
tool("batch", async (_args, api, callContext) => {
|
|
nested.push(await api.executeTool("plain", {}, callContext));
|
|
nested.push(await api.executeTool("typed", {}, callContext));
|
|
return {};
|
|
}),
|
|
);
|
|
addHooks(setup.registry, ToolTask, {
|
|
beforeTool: (call) => (call.parent === undefined ? undefined : { block: "no" }),
|
|
afterTool: (call) =>
|
|
call.parent === undefined
|
|
? undefined
|
|
: { output: [{ type: "text", text: `fine ${call.name}` }], structuredOutput: { ok: false } },
|
|
});
|
|
setup.faux.setResponses([calls(["batch", {}, "c1"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(nested.map((result) => [result.isError, result.structuredOutput])).toEqual([
|
|
[false, "fine plain"],
|
|
[false, undefined],
|
|
]);
|
|
await harness.close(context);
|
|
});
|
|
});
|
|
|
|
describe("afterTool on results rebuilt from the slot", () => {
|
|
/** A tool that writes output, then blocks until its invocation is cancelled. */
|
|
function blocking(name: string, extra: Partial<ToolRegistration<typeof Parameters>> = {}) {
|
|
const started = deferred();
|
|
const state = { runs: 0 };
|
|
const registration = tool(
|
|
name,
|
|
async (_args, api, callContext) => {
|
|
state.runs++;
|
|
api.output(`${name} ${"o".repeat(40)}\n`);
|
|
await api.details({ run: state.runs }, callContext);
|
|
started.resolve();
|
|
return aborted(callContext.abortSignal!);
|
|
},
|
|
extra,
|
|
);
|
|
return { registration, started, state };
|
|
}
|
|
|
|
// #11043
|
|
it("runs on an interrupted call; a replaced output loses the slot's truncation diagnostic", async () => {
|
|
const path = await sqlitePath();
|
|
const setup = chatSetup();
|
|
setup.settings.progress = { outputIntervalMs: 0, persistWithinMs: 0 };
|
|
const limits = { outputLimits: { maxBytes: 10, retain: "tail" } } as const;
|
|
const work = blocking("work", limits);
|
|
const keep = blocking("keep", limits);
|
|
addTool(setup.registry, work.registration);
|
|
addTool(setup.registry, keep.registration);
|
|
const seen: Seen[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: (call, result) => {
|
|
seen.push({ call, result });
|
|
return call.name === "work" ? { ...result, output: [{ type: "text", text: "redacted" }] } : undefined;
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["work", {}, "c1"], ["keep", {}, "c2"]), DONE]);
|
|
let opened = await open(path, setup);
|
|
const id = (await opened.root.submit({ type: "input", content: "go" }, context)).id;
|
|
await work.started.promise;
|
|
await keep.started.promise;
|
|
await stored();
|
|
opened.kill();
|
|
|
|
opened = await open(path, setup);
|
|
expect((await (await opened.harness.submission(id, context))!.wait(context)).status).toBe("done");
|
|
expect(seen.map((each) => [each.call.id, codes(each.result)]).sort()).toEqual([
|
|
["c1", ["interrupted"]],
|
|
["c2", ["interrupted"]],
|
|
]);
|
|
const entries = await allEntries(opened.root);
|
|
const messages = results(entries);
|
|
expect(text(messages.get("c1")).startsWith("redacted|")).toBe(true);
|
|
expect(messages.get("c1")).toMatchObject({ isError: true, details: { run: 1 } });
|
|
expect(await diagnosticsOf(entries, "c1")).toEqual(["interrupted"]);
|
|
// The kept output keeps its truncation diagnostic, after the hooks' result.
|
|
expect(await diagnosticsOf(entries, "c2")).toEqual(["interrupted", "truncated"]);
|
|
await opened.harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("runs on an abort result, but not on the aborted results of calls that never started", async () => {
|
|
const setup = chatSetup();
|
|
setup.settings.toolExecution = "sequential";
|
|
const first = blocking("first");
|
|
addTool(setup.registry, first.registration);
|
|
addTool(
|
|
setup.registry,
|
|
tool("second", async () => ({ output: [] })),
|
|
);
|
|
const seen: Seen[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: (call, result) => {
|
|
seen.push({ call, result });
|
|
return { ...result, details: { hooked: true } };
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["first", {}, "c1"], ["second", {}, "c2"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
const submission = await root.submit({ type: "input", content: "go" }, context);
|
|
await first.started.promise;
|
|
await root.abort(context);
|
|
expect((await submission.wait(context)).status).toBe("unanswered");
|
|
expect(seen.map((each) => [each.call.id, codes(each.result)])).toEqual([["c1", ["aborted"]]]);
|
|
const messages = results(await allEntries(root));
|
|
expect(messages.get("c1")).toMatchObject({ isError: true, details: { hooked: true } });
|
|
expect(messages.get("c2")?.details).toBeUndefined();
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("reports a throwing hook on an abort result and settles the result as built", async () => {
|
|
const setup = chatSetup();
|
|
const work = blocking("work");
|
|
addTool(setup.registry, work.registration);
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: () => {
|
|
throw new Error("hook failed");
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["work", {}, "c1"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
const submission = await root.submit({ type: "input", content: "go" }, context);
|
|
await work.started.promise;
|
|
await root.abort(context);
|
|
expect((await submission.wait(context)).status).toBe("unanswered");
|
|
const entries = await allEntries(root);
|
|
expect(text(results(entries).get("c1")).startsWith(`work ${"o".repeat(40)}`)).toBe(true);
|
|
expect(await diagnosticsOf(entries, "c1")).toEqual(["aborted"]);
|
|
expect(setup.reports.map((error) => (error as Error).message)).toContain("hook failed");
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("settles an abort without the hooks in the abort handler's last attempt", async () => {
|
|
const path = await sqlitePath();
|
|
const setup = chatSetup();
|
|
setup.settings.restartLimit = 2;
|
|
setup.settings.progress = { outputIntervalMs: 0, persistWithinMs: 0 };
|
|
const work = blocking("work");
|
|
addTool(setup.registry, work.registration);
|
|
const seen: Seen[] = [];
|
|
const hanging = deferred();
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: async (call, result) => {
|
|
seen.push({ call, result });
|
|
hanging.resolve();
|
|
// Never returns: the host dies inside the hook.
|
|
return new Promise<undefined>(() => {});
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["work", {}, "c1"]), DONE]);
|
|
let opened = await open(path, setup);
|
|
const id = (await opened.root.submit({ type: "input", content: "go" }, context)).id;
|
|
await work.started.promise;
|
|
const taskId = await toolTaskId(opened.harness);
|
|
await stored();
|
|
void opened.root.abort(context).catch(() => {});
|
|
await hanging.promise;
|
|
opened.kill();
|
|
|
|
// One restart, at the limit minus one: the attempt the scheduler would fault when cut off runs no hooks.
|
|
opened = await open(path, setup);
|
|
expect((await (await opened.harness.submission(id, context))!.wait(context)).status).toBe("unanswered");
|
|
expect(seen.map((each) => codes(each.result))).toEqual([["aborted"]]);
|
|
const entries = await allEntries(opened.root);
|
|
expect(text(results(entries).get("c1")).startsWith(`work ${"o".repeat(40)}`)).toBe(true);
|
|
expect(await diagnosticsOf(entries, "c1")).toEqual(["aborted"]);
|
|
expect((await opened.harness.getTask(taskId, context))?.state).toMatchObject({
|
|
status: "terminal",
|
|
outcome: { status: "aborted" },
|
|
});
|
|
await opened.harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("sees the held progress of an aborted call, and the result stores it", async () => {
|
|
const path = await sqlitePath();
|
|
const setup = chatSetup();
|
|
// Progress commits are held in memory until the result commit stores them.
|
|
setup.settings.progress = { outputIntervalMs: 0, persistWithinMs: 60_000 };
|
|
const work = blocking("work");
|
|
addTool(setup.registry, work.registration);
|
|
const seen: Seen[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: (call, result) => {
|
|
seen.push({ call, result });
|
|
return undefined;
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["work", {}, "c1"]), DONE]);
|
|
let opened = await open(path, setup);
|
|
const submission = await opened.root.submit({ type: "input", content: "go" }, context);
|
|
await work.started.promise;
|
|
await opened.root.abort(context);
|
|
expect((await submission.wait(context)).status).toBe("unanswered");
|
|
expect(seen).toHaveLength(1);
|
|
expect(seen[0]!.result).toMatchObject({ details: { run: 1 } });
|
|
expect(text({ content: seen[0]!.result.output } as ToolResultMessage)).toBe(`work ${"o".repeat(40)}\n`);
|
|
await opened.harness.close(context);
|
|
|
|
opened = await open(path, setup);
|
|
const message = results(await allEntries(opened.root)).get("c1");
|
|
expect(message).toMatchObject({ isError: true, details: { run: 1 } });
|
|
expect(text(message).startsWith(`work ${"o".repeat(40)}`)).toBe(true);
|
|
await opened.harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("runs on an abandoned nested call's result", async () => {
|
|
const path = await sqlitePath();
|
|
const setup = chatSetup();
|
|
const gated = deferred();
|
|
let gate = true;
|
|
addTool(
|
|
setup.registry,
|
|
tool("gated", async () => ({ output: [] })),
|
|
);
|
|
addTool(
|
|
setup.registry,
|
|
tool("batch", async (_args, api, callContext) => {
|
|
await api.executeTool("gated", {}, callContext);
|
|
return {};
|
|
}),
|
|
);
|
|
const seen: Seen[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
// Holds the nested call in its `call` phase, before intent, until the Harness closes.
|
|
beforeTool: async (call, _api, hookContext) => {
|
|
if (call.name !== "gated" || !gate) return undefined;
|
|
gated.resolve();
|
|
return aborted(hookContext.abortSignal!);
|
|
},
|
|
afterTool: (call, result) => {
|
|
if (call.parent === undefined) return undefined;
|
|
seen.push({ call, result });
|
|
return { ...result, details: { hooked: true } };
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["batch", {}, "c1"]), DONE]);
|
|
let opened = await open(path, setup);
|
|
const id = (await opened.root.submit({ type: "input", content: "go" }, context)).id;
|
|
await gated.promise;
|
|
await opened.harness.close(context);
|
|
gate = false;
|
|
|
|
opened = await open(path, setup);
|
|
expect((await (await opened.harness.submission(id, context))!.wait(context)).status).toBe("done");
|
|
expect(seen.map((each) => [each.call.id, codes(each.result)])).toEqual([["c1/1", ["abandoned"]]]);
|
|
await opened.harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("runs on a restart_limit result at the limit, and not once the hooks themselves were cut off", async () => {
|
|
const path = await sqlitePath();
|
|
const setup = chatSetup();
|
|
setup.settings.restartLimit = 1;
|
|
setup.settings.progress = { outputIntervalMs: 0, persistWithinMs: 0 };
|
|
const work = blocking("work");
|
|
addTool(setup.registry, work.registration);
|
|
const seen: Seen[] = [];
|
|
const hanging = deferred();
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: async (call, result) => {
|
|
seen.push({ call, result });
|
|
hanging.resolve();
|
|
// Never returns: the host dies inside the hook.
|
|
return new Promise<undefined>(() => {});
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["work", {}, "c1"]), DONE]);
|
|
let opened = await open(path, setup);
|
|
const id = (await opened.root.submit({ type: "input", content: "go" }, context)).id;
|
|
await work.started.promise;
|
|
const taskId = await toolTaskId(opened.harness);
|
|
await stored();
|
|
opened.kill();
|
|
|
|
// Cut off once, at the limit: the task ends itself, and the hooks run on its result.
|
|
opened = await open(path, setup);
|
|
await hanging.promise;
|
|
expect(seen.map((each) => codes(each.result))).toEqual([["restart_limit"]]);
|
|
opened.kill();
|
|
|
|
// Past the limit: ends without the hooks.
|
|
opened = await open(path, setup);
|
|
expect((await (await opened.harness.submission(id, context))!.wait(context)).status).toBe("done");
|
|
expect(seen).toHaveLength(1);
|
|
expect(work.state.runs).toBe(1);
|
|
const entries = await allEntries(opened.root);
|
|
expect(await diagnosticsOf(entries, "c1")).toEqual(["restart_limit"]);
|
|
expect((await opened.harness.getTask(taskId, context))?.state).toMatchObject({
|
|
status: "terminal",
|
|
outcome: { status: "failed", error: { detail: { reason: "restart_limit" } } },
|
|
});
|
|
await opened.harness.close(context);
|
|
});
|
|
});
|
|
|
|
describe("calls to tools the request did not offer", () => {
|
|
// #11043
|
|
it("run afterTool inside their own tool task", async () => {
|
|
const setup = chatSetup();
|
|
const seen: { readonly id: string; readonly taskId: TaskId }[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: (call, result, api) => {
|
|
seen.push({ id: call.id, taskId: api.taskId });
|
|
return { ...result, output: [{ type: "text", text: "try another tool" }] };
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["ghost", {}, "c1"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(seen.map((each) => each.id)).toEqual(["c1"]);
|
|
expect(await harness.getTask(seen[0]!.taskId, context)).toMatchObject({
|
|
kind: "pi.tool",
|
|
input: { kind: "model", callId: "c1", unoffered: true },
|
|
});
|
|
const entries = await allEntries(root);
|
|
expect(text(results(entries).get("c1")).startsWith("try another tool|")).toBe(true);
|
|
expect(await diagnosticsOf(entries, "c1")).toEqual(["tool_unavailable"]);
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("count toward a round's terminate", async () => {
|
|
const setup = chatSetup();
|
|
addTool(
|
|
setup.registry,
|
|
tool("echo", async () => ({ output: [] })),
|
|
);
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: (_call, result) => ({ ...result, control: { terminate: true } }),
|
|
});
|
|
setup.faux.setResponses([calls(["echo", {}, "c1"], ["ghost", {}, "c2"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
const settled = await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(settled.status).toBe("done");
|
|
expect(setup.faux.state.callCount).toBe(1);
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("take their turn in a sequential round, and the last handoff in call order wins", async () => {
|
|
const setup = chatSetup();
|
|
setup.settings.toolExecution = "sequential";
|
|
const order: string[] = [];
|
|
for (const name of ["a", "b"]) {
|
|
addTool(
|
|
setup.registry,
|
|
tool(name, async () => {
|
|
order.push(name);
|
|
return { output: [] };
|
|
}),
|
|
);
|
|
}
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: (call, result) => {
|
|
order.push(`hook ${call.id}`);
|
|
return call.id === "c1" ? undefined : { ...result, control: { handoff: `from ${call.id}` } };
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["a", {}, "c1"], ["ghost", {}, "c2"], ["b", {}, "c3"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(order).toEqual(["a", "hook c1", "hook c2", "b", "hook c3"]);
|
|
const resets = (await allEntries(root)).filter((entry) => ResetEntry.is(entry));
|
|
expect(resets.map((entry) => (entry.model?.[0] as { content: string }).content)).toEqual(["from c3"]);
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("each get a tool task in a parallel round of only such calls", async () => {
|
|
const setup = chatSetup();
|
|
const seen: string[] = [];
|
|
addHooks(setup.registry, ToolTask, {
|
|
afterTool: (call) => {
|
|
seen.push(call.id);
|
|
return undefined;
|
|
},
|
|
});
|
|
setup.faux.setResponses([calls(["ghost", {}, "c1"], ["spirit", {}, "c2"], ["ghost", {}, "c3"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
const settled = await (await root.submit({ type: "input", content: "go" }, context)).wait(context);
|
|
expect(settled.status).toBe("done");
|
|
expect(seen.sort()).toEqual(["c1", "c2", "c3"]);
|
|
const entries = await allEntries(root);
|
|
for (const id of ["c1", "c2", "c3"]) expect(await diagnosticsOf(entries, id)).toEqual(["tool_unavailable"]);
|
|
// The round's results go to the next request.
|
|
expect(setup.faux.state.callCount).toBe(2);
|
|
await harness.close(context);
|
|
});
|
|
|
|
// #11043
|
|
it("keep their flag in a version 2 generation's sequential round, also one migrated from version 1", async () => {
|
|
for (const version of [2, 1]) {
|
|
const path = await sqlitePath();
|
|
const setup = chatSetup();
|
|
setup.settings.toolExecution = "sequential";
|
|
const started = deferred();
|
|
let runs = 0;
|
|
const a = tool(
|
|
"a",
|
|
async (_args, _api, callContext) => {
|
|
runs++;
|
|
if (runs > 1) return { output: [] };
|
|
started.resolve();
|
|
return aborted(callContext.abortSignal!);
|
|
},
|
|
{ replay: "safe" },
|
|
);
|
|
addTool(setup.registry, a);
|
|
addTool(
|
|
setup.registry,
|
|
tool("ghost", async () => ({ output: [{ type: "text", text: "ran" }] })),
|
|
);
|
|
setup.faux.setResponses([calls(["a", {}, "c1"], ["ghost", {}, "c2"]), DONE]);
|
|
let opened = await open(path, setup);
|
|
let root = opened.root;
|
|
// `ghost` is registered, but not offered to this request.
|
|
await root.configure({ tools: [a] }, context);
|
|
const id = (await root.submit({ type: "input", content: "go" }, context)).id;
|
|
await started.promise;
|
|
const live = (await opened.harness.snapshot(LiveDoc, ROOT_CONVERSATION_ID, context))!;
|
|
const generation = live.run!.taskId;
|
|
expect(live.tools?.map((slot) => [slot.callId, slot.unoffered])).toEqual([
|
|
["c1", undefined],
|
|
["c2", true],
|
|
]);
|
|
expect((await opened.harness.getTask(generation, context))?.version).toBe(2);
|
|
// The tools are offered when the round goes on: only the flag keeps `ghost` from running.
|
|
await root.configure({ tools: null }, context);
|
|
await opened.harness.close(context);
|
|
if (version === 1) {
|
|
const storage = await openNodeSqliteStorage(path);
|
|
const record = (await storage.task(generation, context))!;
|
|
await commitWrites(storage, [{ type: "task", value: { ...record, version: 1 } }], context);
|
|
await storage.close(context);
|
|
}
|
|
|
|
opened = await open(path, setup);
|
|
root = opened.root;
|
|
expect((await (await opened.harness.submission(id, context))!.wait(context)).status).toBe("done");
|
|
expect((await opened.harness.getTask(generation, context))?.version).toBe(2);
|
|
const entries = await allEntries(root);
|
|
expect(await diagnosticsOf(entries, "c2")).toEqual(["tool_unavailable"]);
|
|
expect(text(results(entries).get("c2"))).not.toContain("ran");
|
|
await opened.harness.close(context);
|
|
}
|
|
});
|
|
|
|
// #11043
|
|
it("settle unavailable, not aborted, when their sequential round is aborted before they start", async () => {
|
|
const setup = chatSetup();
|
|
setup.settings.toolExecution = "sequential";
|
|
const started = deferred();
|
|
addTool(
|
|
setup.registry,
|
|
tool("wait", async (_args, _api, callContext) => {
|
|
started.resolve();
|
|
return aborted(callContext.abortSignal!);
|
|
}),
|
|
);
|
|
setup.faux.setResponses([calls(["wait", {}, "c1"], ["ghost", {}, "c2"]), DONE]);
|
|
const { harness, root } = await openChat(new MemoryStorage(), setup);
|
|
const submission = await root.submit({ type: "input", content: "go" }, context);
|
|
await started.promise;
|
|
await root.abort(context);
|
|
expect((await submission.wait(context)).status).toBe("unanswered");
|
|
const entries = await allEntries(root);
|
|
expect(await diagnosticsOf(entries, "c1")).toEqual(["aborted"]);
|
|
expect(await diagnosticsOf(entries, "c2")).toEqual(["tool_unavailable"]);
|
|
await harness.close(context);
|
|
});
|
|
});
|