refactor: align package folder names with npm package names
CI / check (pull_request) Failing after 8m30s
CI / check (pull_request) Failing after 8m30s
Rename packages/ subdirectories to match their @united-workforce/* scope: cli-workflow → cli workflow-agent-builtin → agent-builtin workflow-agent-claude-code → agent-claude-code workflow-agent-hermes → agent-hermes workflow-dashboard → dashboard workflow-protocol → protocol workflow-util-agent → util-agent workflow-util → util Updated all tsconfig references, scripts, and active docs. Historical docs (docs/plans/, docs/superpowers/) left as-is. Closes #21
This commit is contained in:
@@ -0,0 +1,16 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
|
||||
import type { LlmToolCall } from "../src/llm/types.js";
|
||||
|
||||
/** Mirror OpenAI response shape for parser coverage via chatCompletionWithTools integration later. */
|
||||
describe("LlmToolCall shape", () => {
|
||||
test("tool call record fields", () => {
|
||||
const call: LlmToolCall = {
|
||||
id: "call_1",
|
||||
name: "read_file",
|
||||
arguments: '{"path":"README.md"}',
|
||||
};
|
||||
expect(call.name).toBe("read_file");
|
||||
expect(JSON.parse(call.arguments)).toEqual({ path: "README.md" });
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,256 @@
|
||||
import { beforeEach, describe, expect, mock, test } from "bun:test";
|
||||
|
||||
const mockChatCompletionWithTools = mock(async () => ({
|
||||
content: "---\nstatus: done\n---",
|
||||
toolCalls: [],
|
||||
}));
|
||||
const mockAppendSessionTurn = mock(async () => {});
|
||||
const mockExecuteBuiltinTool = mock(async () => "tool-result");
|
||||
|
||||
mock.module("../src/llm/index.js", () => ({
|
||||
chatCompletionWithTools: mockChatCompletionWithTools,
|
||||
}));
|
||||
mock.module("../src/session.js", () => ({
|
||||
appendSessionTurn: mockAppendSessionTurn,
|
||||
}));
|
||||
mock.module("../src/tools/index.js", () => ({
|
||||
builtinToolsToOpenAi: () => [],
|
||||
executeBuiltinTool: mockExecuteBuiltinTool,
|
||||
getBuiltinTools: () => [],
|
||||
}));
|
||||
|
||||
import {
|
||||
executeTurnTools,
|
||||
extractFinalText,
|
||||
runBuiltinLoop,
|
||||
shouldInjectDeadlineWarning,
|
||||
shouldNudge,
|
||||
shouldProcessToolCalls,
|
||||
} from "../src/loop.js";
|
||||
|
||||
const fakeProvider = {} as any;
|
||||
const fakeToolCtx = {} as any;
|
||||
|
||||
function makeOptions(overrides: Partial<Parameters<typeof runBuiltinLoop>[0]> = {}) {
|
||||
return {
|
||||
provider: fakeProvider,
|
||||
messages: [{ role: "system" as const, content: "sys" }],
|
||||
toolCtx: fakeToolCtx,
|
||||
maxTurns: 5,
|
||||
storageRoot: "/tmp",
|
||||
sessionId: "sess",
|
||||
noTools: false,
|
||||
...overrides,
|
||||
};
|
||||
}
|
||||
|
||||
beforeEach(() => {
|
||||
mockChatCompletionWithTools.mockReset();
|
||||
mockAppendSessionTurn.mockReset();
|
||||
mockExecuteBuiltinTool.mockReset();
|
||||
});
|
||||
|
||||
describe("shouldNudge", () => {
|
||||
test("2.1 returns true when all conditions met", () => {
|
||||
expect(shouldNudge({ noTools: false, text: "some text", turn: 0, maxTurns: 5 })).toBe(true);
|
||||
});
|
||||
test("2.2 returns false when noTools=true", () => {
|
||||
expect(shouldNudge({ noTools: true, text: "some text", turn: 0, maxTurns: 5 })).toBe(false);
|
||||
});
|
||||
test("2.3 returns false when text starts with ---", () => {
|
||||
expect(shouldNudge({ noTools: false, text: "---\nstatus: done", turn: 0, maxTurns: 5 })).toBe(
|
||||
false,
|
||||
);
|
||||
});
|
||||
test("2.4 returns false on last turn", () => {
|
||||
expect(shouldNudge({ noTools: false, text: "some text", turn: 4, maxTurns: 5 })).toBe(false);
|
||||
});
|
||||
test("2.5 returns true on second-to-last turn", () => {
|
||||
expect(shouldNudge({ noTools: false, text: "some text", turn: 3, maxTurns: 5 })).toBe(true);
|
||||
});
|
||||
test("2.6 leading whitespace before --- suppresses nudge", () => {
|
||||
expect(shouldNudge({ noTools: false, text: " ---\nstatus: done", turn: 0, maxTurns: 5 })).toBe(
|
||||
false,
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe("executeTurnTools", () => {
|
||||
test("4.1 executes each tool call and pushes tool result messages", async () => {
|
||||
mockExecuteBuiltinTool.mockResolvedValue("result");
|
||||
const messages: any[] = [];
|
||||
const calls = [
|
||||
{ id: "c1", name: "tool_a", arguments: "{}" },
|
||||
{ id: "c2", name: "tool_b", arguments: "{}" },
|
||||
];
|
||||
const count = await executeTurnTools(calls, fakeToolCtx, messages, "/tmp", "sess");
|
||||
expect(messages.length).toBe(2);
|
||||
expect(messages[0].role).toBe("tool");
|
||||
expect(messages[1].role).toBe("tool");
|
||||
expect(count).toBe(2);
|
||||
});
|
||||
test("4.2 tool result content matches executeBuiltinTool return value", async () => {
|
||||
mockExecuteBuiltinTool.mockResolvedValue("result-A");
|
||||
const messages: any[] = [];
|
||||
await executeTurnTools(
|
||||
[{ id: "c1", name: "read_file", arguments: "{}" }],
|
||||
fakeToolCtx,
|
||||
messages,
|
||||
"/tmp",
|
||||
"sess",
|
||||
);
|
||||
expect(messages[0].content).toBe("result-A");
|
||||
});
|
||||
});
|
||||
|
||||
describe("runBuiltinLoop integration", () => {
|
||||
test("3.1 single text-only response returns finalText immediately", async () => {
|
||||
mockChatCompletionWithTools.mockResolvedValue({
|
||||
content: "---\nstatus: done\n---",
|
||||
toolCalls: [],
|
||||
});
|
||||
const result = await runBuiltinLoop(makeOptions());
|
||||
expect(result.finalText).toBe("---\nstatus: done\n---");
|
||||
expect(result.turnCount).toBe(1);
|
||||
});
|
||||
test("3.2 noTools=true suppresses tool calls", async () => {
|
||||
mockChatCompletionWithTools.mockResolvedValue({
|
||||
content: "ok",
|
||||
toolCalls: [{ id: "c1", name: "read_file", arguments: "{}" }],
|
||||
});
|
||||
const result = await runBuiltinLoop(makeOptions({ noTools: true }));
|
||||
expect(result.finalText).toBe("ok");
|
||||
expect(result.turnCount).toBe(1);
|
||||
});
|
||||
test("3.3 tool call followed by text response", async () => {
|
||||
mockChatCompletionWithTools
|
||||
.mockResolvedValueOnce({
|
||||
content: null,
|
||||
toolCalls: [{ id: "c1", name: "read_file", arguments: "{}" }],
|
||||
})
|
||||
.mockResolvedValueOnce({ content: "---\nstatus: done\n---", toolCalls: [] });
|
||||
mockExecuteBuiltinTool.mockResolvedValue("file contents");
|
||||
const result = await runBuiltinLoop(makeOptions());
|
||||
expect(result.finalText).toBe("---\nstatus: done\n---");
|
||||
expect(result.turnCount).toBe(3);
|
||||
});
|
||||
test("3.4 nudge cycle inserts nudge message", async () => {
|
||||
mockChatCompletionWithTools
|
||||
.mockResolvedValueOnce({ content: "I am thinking", toolCalls: [] })
|
||||
.mockResolvedValueOnce({ content: "---\nstatus: done\n---", toolCalls: [] });
|
||||
const result = await runBuiltinLoop(makeOptions());
|
||||
expect(result.finalText).toBe("---\nstatus: done\n---");
|
||||
const nudgeMsg = result.messages.find(
|
||||
(m) =>
|
||||
m.role === "user" && typeof m.content === "string" && m.content.includes("frontmatter"),
|
||||
);
|
||||
expect(nudgeMsg).toBeDefined();
|
||||
});
|
||||
test("3.5 maxTurns exhaustion falls back to last assistant content", async () => {
|
||||
mockChatCompletionWithTools.mockResolvedValue({ content: "still thinking", toolCalls: [] });
|
||||
const result = await runBuiltinLoop(makeOptions({ maxTurns: 3 }));
|
||||
expect(result.finalText).toBe("still thinking");
|
||||
});
|
||||
test("3.6 original messages array is not mutated", async () => {
|
||||
mockChatCompletionWithTools.mockResolvedValue({
|
||||
content: "---\nstatus: done\n---",
|
||||
toolCalls: [],
|
||||
});
|
||||
const original = [{ role: "system" as const, content: "sys" }];
|
||||
await runBuiltinLoop(makeOptions({ messages: original }));
|
||||
expect(original.length).toBe(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe("shouldInjectDeadlineWarning", () => {
|
||||
test("5.1 returns true when turn count reaches warning threshold and not yet warned", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, false, false)).toBe(true);
|
||||
});
|
||||
test("5.2 returns false when already warned", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, true, false)).toBe(false);
|
||||
});
|
||||
test("5.3 returns false when noTools is true", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, false, true)).toBe(false);
|
||||
});
|
||||
test("5.4 returns false when turns remaining > DEADLINE_WARNING_TURNS", () => {
|
||||
expect(shouldInjectDeadlineWarning(5, 10, false, false)).toBe(false);
|
||||
});
|
||||
test("5.5 returns true when exactly at warning threshold", () => {
|
||||
expect(shouldInjectDeadlineWarning(7, 10, false, false)).toBe(true);
|
||||
});
|
||||
test("5.6 returns false when turns remaining is 0", () => {
|
||||
expect(shouldInjectDeadlineWarning(10, 10, false, false)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("shouldProcessToolCalls", () => {
|
||||
test("6.1 returns true when toolCalls present and noTools=false", () => {
|
||||
expect(shouldProcessToolCalls([{ id: "x", name: "read", arguments: "{}" }], false)).toBe(true);
|
||||
});
|
||||
test("6.2 returns false when toolCalls is null", () => {
|
||||
expect(shouldProcessToolCalls(null, false)).toBe(false);
|
||||
});
|
||||
test("6.3 returns false when toolCalls is empty array", () => {
|
||||
expect(shouldProcessToolCalls([], false)).toBe(false);
|
||||
});
|
||||
test("6.4 returns false when noTools=true", () => {
|
||||
expect(shouldProcessToolCalls([{ id: "x", name: "read", arguments: "{}" }], true)).toBe(false);
|
||||
});
|
||||
test("6.5 returns true when multiple tool calls present", () => {
|
||||
expect(
|
||||
shouldProcessToolCalls(
|
||||
[
|
||||
{ id: "x1", name: "read", arguments: "{}" },
|
||||
{ id: "x2", name: "write", arguments: "{}" },
|
||||
],
|
||||
false,
|
||||
),
|
||||
).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe("extractFinalText", () => {
|
||||
test("7.1 returns last assistant message content", () => {
|
||||
const messages = [
|
||||
{ role: "system" as const, content: "sys", tool_calls: null },
|
||||
{ role: "assistant" as const, content: "first", tool_calls: null },
|
||||
{ role: "assistant" as const, content: "last", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("last");
|
||||
});
|
||||
test("7.2 returns empty string when no assistant messages", () => {
|
||||
expect(extractFinalText([{ role: "system" as const, content: "sys", tool_calls: null }])).toBe(
|
||||
"",
|
||||
);
|
||||
});
|
||||
test("7.3 skips assistant messages with null content", () => {
|
||||
const messages = [
|
||||
{ role: "assistant" as const, content: "first", tool_calls: null },
|
||||
{
|
||||
role: "assistant" as const,
|
||||
content: null,
|
||||
tool_calls: [{ id: "x", name: "t", arguments: "{}" }],
|
||||
},
|
||||
{ role: "assistant" as const, content: "second", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("second");
|
||||
});
|
||||
test("7.4 skips assistant messages with empty content", () => {
|
||||
const messages = [
|
||||
{ role: "assistant" as const, content: "first", tool_calls: null },
|
||||
{ role: "assistant" as const, content: "", tool_calls: null },
|
||||
{ role: "user" as const, content: "nudge", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("first");
|
||||
});
|
||||
test("7.5 handles empty messages array", () => {
|
||||
expect(extractFinalText([])).toBe("");
|
||||
});
|
||||
test("7.6 handles messages with only user and system roles", () => {
|
||||
const messages = [
|
||||
{ role: "system" as const, content: "sys", tool_calls: null },
|
||||
{ role: "user" as const, content: "query", tool_calls: null },
|
||||
];
|
||||
expect(extractFinalText(messages)).toBe("");
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,21 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
import { resolve } from "node:path";
|
||||
import { resolvePath } from "../src/tools/path.js";
|
||||
|
||||
describe("resolvePath", () => {
|
||||
test("resolves relative paths against cwd", () => {
|
||||
const root = "/workspace/project";
|
||||
const resolved = resolvePath(root, "src/foo.ts");
|
||||
expect(resolved).toBe(resolve(root, "src/foo.ts"));
|
||||
});
|
||||
|
||||
test("resolves absolute paths as-is", () => {
|
||||
const resolved = resolvePath("/workspace", "/etc/hosts");
|
||||
expect(resolved).toBe("/etc/hosts");
|
||||
});
|
||||
|
||||
test("resolves parent traversal normally", () => {
|
||||
const resolved = resolvePath("/workspace/project", "../other/file.ts");
|
||||
expect(resolved).toBe(resolve("/workspace/project", "../other/file.ts"));
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,236 @@
|
||||
import { describe, expect, test } from "bun:test";
|
||||
|
||||
import type { AgentContext } from "@united-workforce/util-agent";
|
||||
|
||||
import { buildBuiltinMessages } from "../src/prompt.js";
|
||||
|
||||
function minimalContext(overrides: Partial<AgentContext> = {}): AgentContext {
|
||||
return {
|
||||
threadId: "00000000000000000000000000" as AgentContext["threadId"],
|
||||
role: "developer",
|
||||
store: {} as AgentContext["store"],
|
||||
workflow: {
|
||||
name: "test",
|
||||
description: "test workflow",
|
||||
roles: {
|
||||
developer: {
|
||||
description: "Developer role",
|
||||
goal: "Ship the fix",
|
||||
capabilities: ["file-edit"],
|
||||
procedure: "Edit files",
|
||||
output: "A patch",
|
||||
frontmatter: "schema-hash",
|
||||
},
|
||||
},
|
||||
conditions: {},
|
||||
graph: {},
|
||||
},
|
||||
start: { workflow: "wf-hash", prompt: "Fix the bug" },
|
||||
steps: [],
|
||||
outputFormatInstruction: "---\nstatus: done\n---",
|
||||
edgePrompt: "Implement the fix described in the plan.",
|
||||
isFirstVisit: true,
|
||||
...overrides,
|
||||
};
|
||||
}
|
||||
|
||||
describe("buildBuiltinMessages", () => {
|
||||
test("system includes output format and role goal", () => {
|
||||
const messages = buildBuiltinMessages(minimalContext());
|
||||
const system = messages[0];
|
||||
expect(system?.role).toBe("system");
|
||||
if (system?.role === "system") {
|
||||
expect(system.content).toContain("status: done");
|
||||
expect(system.content).toContain("## Goal");
|
||||
expect(system.content).toContain("Ship the fix");
|
||||
}
|
||||
});
|
||||
|
||||
test("first visit produces system + single user message with edge prompt", () => {
|
||||
const messages = buildBuiltinMessages(minimalContext());
|
||||
expect(messages).toHaveLength(2);
|
||||
expect(messages[1]?.role).toBe("user");
|
||||
if (messages[1]?.role === "user") {
|
||||
expect(messages[1].content).toContain("Implement the fix");
|
||||
expect(messages[1].content).not.toContain("## What Happened Since Your Last Turn");
|
||||
}
|
||||
});
|
||||
|
||||
test("first visit with prior steps includes inter-step summary in final user message", () => {
|
||||
const messages = buildBuiltinMessages(
|
||||
minimalContext({
|
||||
steps: [
|
||||
{
|
||||
role: "planner",
|
||||
output: { plan: "step 1" },
|
||||
agent: "uwf-builtin",
|
||||
detail: "detail-hash",
|
||||
edgePrompt: "Create a plan.",
|
||||
},
|
||||
],
|
||||
}),
|
||||
);
|
||||
expect(messages).toHaveLength(2);
|
||||
const finalUser = messages[1];
|
||||
if (finalUser?.role === "user") {
|
||||
expect(finalUser.content).toContain("Implement the fix");
|
||||
expect(finalUser.content).toContain("## What Happened Since Your Last Turn");
|
||||
expect(finalUser.content).toContain("planner");
|
||||
}
|
||||
});
|
||||
|
||||
test("re-entry reconstructs prior user/assistant turns plus current user message", () => {
|
||||
const messages = buildBuiltinMessages(
|
||||
minimalContext({
|
||||
isFirstVisit: false,
|
||||
edgePrompt: "Fix the reviewer's feedback.",
|
||||
steps: [
|
||||
{
|
||||
role: "developer",
|
||||
output: { summary: "Initial fix" },
|
||||
agent: "uwf-builtin",
|
||||
detail: "detail-1",
|
||||
edgePrompt: "Implement the fix.",
|
||||
},
|
||||
{
|
||||
role: "reviewer",
|
||||
output: { approved: false, comments: "Missing tests" },
|
||||
agent: "uwf-builtin",
|
||||
detail: "detail-2",
|
||||
edgePrompt: "Review the implementation.",
|
||||
},
|
||||
],
|
||||
}),
|
||||
);
|
||||
|
||||
expect(messages).toHaveLength(4);
|
||||
expect(messages[0]?.role).toBe("system");
|
||||
expect(messages[1]?.role).toBe("user");
|
||||
expect(messages[2]?.role).toBe("assistant");
|
||||
expect(messages[3]?.role).toBe("user");
|
||||
|
||||
if (messages[1]?.role === "user") {
|
||||
expect(messages[1].content).toBe("Implement the fix.");
|
||||
}
|
||||
if (messages[2]?.role === "assistant") {
|
||||
expect(messages[2].content).toBe(JSON.stringify({ summary: "Initial fix" }));
|
||||
}
|
||||
if (messages[3]?.role === "user") {
|
||||
expect(messages[3].content).toContain("Fix the reviewer's feedback.");
|
||||
expect(messages[3].content).toContain("## What Happened Since Your Last Turn");
|
||||
expect(messages[3].content).toContain("reviewer");
|
||||
expect(messages[3].content).toContain("Missing tests");
|
||||
}
|
||||
});
|
||||
|
||||
test("prefix is stable across re-entry for LLM cache hits", () => {
|
||||
const firstVisitMessages = buildBuiltinMessages(
|
||||
minimalContext({
|
||||
edgePrompt: "Implement the fix.",
|
||||
steps: [],
|
||||
}),
|
||||
);
|
||||
|
||||
const reEntryMessages = buildBuiltinMessages(
|
||||
minimalContext({
|
||||
isFirstVisit: false,
|
||||
edgePrompt: "Fix the reviewer's feedback.",
|
||||
steps: [
|
||||
{
|
||||
role: "developer",
|
||||
output: { summary: "Initial fix" },
|
||||
agent: "uwf-builtin",
|
||||
detail: "detail-1",
|
||||
edgePrompt: "Implement the fix.",
|
||||
},
|
||||
{
|
||||
role: "reviewer",
|
||||
output: { approved: false },
|
||||
agent: "uwf-builtin",
|
||||
detail: "detail-2",
|
||||
edgePrompt: "Review the code.",
|
||||
},
|
||||
],
|
||||
}),
|
||||
);
|
||||
|
||||
expect(reEntryMessages[0]).toEqual(firstVisitMessages[0]);
|
||||
expect(reEntryMessages[1]).toEqual(firstVisitMessages[1]);
|
||||
expect(reEntryMessages[2]?.role).toBe("assistant");
|
||||
if (reEntryMessages[2]?.role === "assistant") {
|
||||
expect(reEntryMessages[2].content).toBe(JSON.stringify({ summary: "Initial fix" }));
|
||||
}
|
||||
expect(reEntryMessages[3]?.role).toBe("user");
|
||||
if (reEntryMessages[3]?.role === "user") {
|
||||
expect(reEntryMessages[3].content).toContain("Fix the reviewer's feedback.");
|
||||
}
|
||||
});
|
||||
|
||||
test("multiple prior visits emit one user/assistant pair per visit", () => {
|
||||
const messages = buildBuiltinMessages(
|
||||
minimalContext({
|
||||
isFirstVisit: false,
|
||||
edgePrompt: "Third round fix.",
|
||||
steps: [
|
||||
{
|
||||
role: "developer",
|
||||
output: { round: 1 },
|
||||
agent: "uwf-builtin",
|
||||
detail: "d1",
|
||||
edgePrompt: "First attempt.",
|
||||
},
|
||||
{
|
||||
role: "reviewer",
|
||||
output: { approved: false },
|
||||
agent: "uwf-builtin",
|
||||
detail: "d2",
|
||||
edgePrompt: "Review round 1.",
|
||||
},
|
||||
{
|
||||
role: "developer",
|
||||
output: { round: 2 },
|
||||
agent: "uwf-builtin",
|
||||
detail: "d3",
|
||||
edgePrompt: "Second attempt.",
|
||||
},
|
||||
{
|
||||
role: "reviewer",
|
||||
output: { approved: false },
|
||||
agent: "uwf-builtin",
|
||||
detail: "d4",
|
||||
edgePrompt: "Review round 2.",
|
||||
},
|
||||
],
|
||||
}),
|
||||
);
|
||||
|
||||
expect(messages).toHaveLength(6);
|
||||
expect(messages.map((m) => m.role)).toEqual([
|
||||
"system",
|
||||
"user",
|
||||
"assistant",
|
||||
"user",
|
||||
"assistant",
|
||||
"user",
|
||||
]);
|
||||
|
||||
if (messages[1]?.role === "user") {
|
||||
expect(messages[1].content).toBe("First attempt.");
|
||||
}
|
||||
if (messages[2]?.role === "assistant") {
|
||||
expect(messages[2].content).toBe(JSON.stringify({ round: 1 }));
|
||||
}
|
||||
if (messages[3]?.role === "user") {
|
||||
expect(messages[3].content).toContain("Second attempt.");
|
||||
expect(messages[3].content).toContain("reviewer");
|
||||
}
|
||||
if (messages[4]?.role === "assistant") {
|
||||
expect(messages[4].content).toBe(JSON.stringify({ round: 2 }));
|
||||
}
|
||||
if (messages[5]?.role === "user") {
|
||||
expect(messages[5].content).toContain("Third round fix.");
|
||||
expect(messages[5].content).toContain("### Step 4: reviewer");
|
||||
expect(messages[5].content).toContain('"approved":false');
|
||||
}
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user