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 +1,141 @@
|
||||
# @united-workforce/agent-builtin
|
||||
|
||||
`uwf-builtin` agent — built-in LLM agent with file read/write and shell tools.
|
||||
|
||||
## Overview
|
||||
|
||||
Layer 3 agent implementation. Runs an OpenAI-compatible chat completion loop with built-in tools (`read_file`, `write_file`, `run_command`). Uses the configured provider/model from `config.yaml`. Produces frontmatter markdown output and stores turn-by-turn session detail in CAS.
|
||||
|
||||
Useful when you want a self-contained agent without an external CLI like Hermes or Claude Code.
|
||||
|
||||
**Dependencies:** `@ocas/core`, `@united-workforce/util-agent`, `@united-workforce/util`
|
||||
|
||||
## Installation
|
||||
|
||||
Included as the `uwf-builtin` binary when you install `@united-workforce/agent-builtin`:
|
||||
|
||||
```bash
|
||||
bun add -g @united-workforce/agent-builtin
|
||||
```
|
||||
|
||||
## CLI Usage
|
||||
|
||||
Invoked by `uwf thread step`:
|
||||
|
||||
```bash
|
||||
uwf-builtin <thread-id> <role>
|
||||
```
|
||||
|
||||
Configure as default agent:
|
||||
|
||||
```bash
|
||||
uwf setup --agent builtin
|
||||
```
|
||||
|
||||
Override per step:
|
||||
|
||||
```bash
|
||||
uwf thread step <thread-id> --agent uwf-builtin
|
||||
```
|
||||
|
||||
Environment variables set by the engine:
|
||||
|
||||
| Variable | Purpose |
|
||||
|----------|---------|
|
||||
| `UWF_EDGE_PROMPT` | Moderator edge instruction for this step |
|
||||
|
||||
## API
|
||||
|
||||
All exports come from `src/index.ts`.
|
||||
|
||||
### Agent factory
|
||||
|
||||
```typescript
|
||||
function createBuiltinAgent(): () => Promise<void>
|
||||
function buildBuiltinMessages(ctx: AgentContext): ChatMessage[]
|
||||
```
|
||||
|
||||
### LLM loop
|
||||
|
||||
```typescript
|
||||
const BUILTIN_MAX_TURNS = 30;
|
||||
const BUILTIN_CONTINUE_MAX_TURNS = 5;
|
||||
|
||||
function runBuiltinLoop(/* options: RunBuiltinLoopOptions */): Promise<RunBuiltinLoopResult>
|
||||
function chatCompletionWithTools(
|
||||
provider: ResolvedLlmProvider,
|
||||
messages: ChatMessage[],
|
||||
tools: OpenAiToolDefinition[],
|
||||
): Promise<LlmAssistantResponse>
|
||||
```
|
||||
|
||||
`RunBuiltinLoopOptions` and `RunBuiltinLoopResult` are internal to `loop.ts` and not re-exported from `index.ts`.
|
||||
|
||||
### Tools
|
||||
|
||||
```typescript
|
||||
function getBuiltinTools(): readonly BuiltinTool[]
|
||||
function executeBuiltinTool(
|
||||
name: string,
|
||||
args: Record<string, unknown>,
|
||||
ctx: ToolContext,
|
||||
): Promise<string>
|
||||
```
|
||||
|
||||
### Session and detail
|
||||
|
||||
```typescript
|
||||
function initSessionDir(storageRoot: string): Promise<void>
|
||||
function appendSessionTurn(storageRoot: string, sessionId: string, turn: BuiltinTurnPayload): Promise<void>
|
||||
function readSessionTurns(storageRoot: string, sessionId: string): Promise<BuiltinTurnPayload[]>
|
||||
function removeSession(storageRoot: string, sessionId: string): Promise<void>
|
||||
function registerBuiltinSchemas(store: Store): Promise<BuiltinSchemaHashes>
|
||||
function storeBuiltinDetail(store: Store, payload: BuiltinDetailPayload): Promise<string>
|
||||
```
|
||||
|
||||
### Types
|
||||
|
||||
```typescript
|
||||
type ChatMessage = /* system | user | assistant | tool */;
|
||||
type LlmAssistantResponse = { content: string | null; toolCalls: LlmToolCall[] | null };
|
||||
type LlmToolCall = { id: string; name: string; arguments: string };
|
||||
type BuiltinTool = { name: string; description: string; parameters: Record<string, unknown> };
|
||||
type ToolContext = { cwd: string; storageRoot: string };
|
||||
type BuiltinDetailPayload = { /* session turns, model, timestamps */ };
|
||||
type BuiltinLoopTurn = { /* single loop iteration record */ };
|
||||
type BuiltinToolCallRecord = { /* tool call audit */ };
|
||||
type BuiltinToolResultRecord = { /* tool result audit */ };
|
||||
type BuiltinTurnPayload = { /* persisted turn */ };
|
||||
```
|
||||
|
||||
## Internal Structure
|
||||
|
||||
```
|
||||
src/
|
||||
├── index.ts
|
||||
├── cli.ts Binary entrypoint
|
||||
├── agent.ts createBuiltinAgent
|
||||
├── loop.ts Multi-turn LLM + tool loop
|
||||
├── prompt.ts buildBuiltinMessages
|
||||
├── session.ts Session directory persistence
|
||||
├── detail.ts CAS detail node storage
|
||||
├── schemas.ts Builtin CAS schemas
|
||||
├── types.ts Detail and turn payload types
|
||||
├── llm/
|
||||
│ ├── index.ts
|
||||
│ ├── llm.ts chatCompletionWithTools
|
||||
│ └── types.ts ChatMessage, LlmToolCall, etc.
|
||||
└── tools/
|
||||
├── index.ts getBuiltinTools, executeBuiltinTool
|
||||
├── read-file.ts
|
||||
├── write-file.ts
|
||||
├── run-command.ts
|
||||
├── path.ts
|
||||
└── types.ts
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
Requires a configured OpenAI-compatible provider and model in `~/.uncaged/workflow/config.yaml` (via `uwf setup`). API keys are loaded from `~/.uncaged/workflow/.env`.
|
||||
|
||||
Tools run with the current working directory as `ToolContext.cwd` (typically the directory where `uwf thread step` was invoked).
|
||||
@@ -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');
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"name": "@united-workforce/agent-builtin",
|
||||
"version": "0.5.0",
|
||||
"files": [
|
||||
"src",
|
||||
"dist",
|
||||
"package.json"
|
||||
],
|
||||
"type": "module",
|
||||
"bin": {
|
||||
"uwf-builtin": "./src/cli.ts"
|
||||
},
|
||||
"exports": {
|
||||
".": {
|
||||
"bun": "./src/index.ts",
|
||||
"types": "./dist/index.d.ts",
|
||||
"import": "./dist/index.js"
|
||||
}
|
||||
},
|
||||
"scripts": {
|
||||
"prepublishOnly": "echo 'Use bun run release from repo root' && exit 1",
|
||||
"test": "bun test __tests__/",
|
||||
"test:ci": "bun test __tests__/"
|
||||
},
|
||||
"dependencies": {
|
||||
"@ocas/core": "^0.1.1",
|
||||
"@united-workforce/util-agent": "workspace:^",
|
||||
"@united-workforce/util": "workspace:^"
|
||||
},
|
||||
"devDependencies": {
|
||||
"typescript": "^5.8.3"
|
||||
},
|
||||
"publishConfig": {
|
||||
"access": "public"
|
||||
},
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://git.shazhou.work/uncaged/workflow.git",
|
||||
"directory": "packages/agent-builtin"
|
||||
},
|
||||
"homepage": "https://git.shazhou.work/uncaged/workflow#readme",
|
||||
"bugs": {
|
||||
"url": "https://git.shazhou.work/uncaged/workflow/issues"
|
||||
},
|
||||
"license": "MIT"
|
||||
}
|
||||
@@ -0,0 +1,163 @@
|
||||
import type { Store } from "@ocas/core";
|
||||
import { createLogger, generateUlid } from "@united-workforce/util";
|
||||
import {
|
||||
type AgentContext,
|
||||
type AgentRunResult,
|
||||
createAgent,
|
||||
loadWorkflowConfig,
|
||||
resolveModel,
|
||||
resolveStorageRoot,
|
||||
} from "@united-workforce/util-agent";
|
||||
|
||||
import { storeBuiltinDetail } from "./detail.js";
|
||||
import type { ChatMessage } from "./llm/index.js";
|
||||
import { BUILTIN_CONTINUE_MAX_TURNS, BUILTIN_MAX_TURNS, runBuiltinLoop } from "./loop.js";
|
||||
import { buildBuiltinMessages } from "./prompt.js";
|
||||
import { initSessionDir } from "./session.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
const FRONTMATTER_FENCE = "---";
|
||||
|
||||
/**
|
||||
* Strip any text before the first `---` fence.
|
||||
* LLMs sometimes emit preamble text before the frontmatter block.
|
||||
*/
|
||||
function stripPreamble(text: string): string {
|
||||
if (text.startsWith(FRONTMATTER_FENCE)) {
|
||||
return text;
|
||||
}
|
||||
const idx = text.indexOf(`\n${FRONTMATTER_FENCE}\n`);
|
||||
if (idx !== -1) {
|
||||
log("6GWRP3QX", `stripped ${idx + 1} chars of preamble before frontmatter`);
|
||||
return text.slice(idx + 1);
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
type SessionRecord = {
|
||||
sessionId: string;
|
||||
model: string;
|
||||
startedAtMs: number;
|
||||
messages: ChatMessage[];
|
||||
};
|
||||
|
||||
const sessions = new Map<string, SessionRecord>();
|
||||
|
||||
function getSession(sessionId: string): SessionRecord {
|
||||
const session = sessions.get(sessionId);
|
||||
if (session === undefined) {
|
||||
throw new Error(`builtin session not found: ${sessionId}`);
|
||||
}
|
||||
return session;
|
||||
}
|
||||
|
||||
function buildToolContext(storageRoot: string): { cwd: string; storageRoot: string } {
|
||||
return {
|
||||
cwd: process.cwd(),
|
||||
storageRoot,
|
||||
};
|
||||
}
|
||||
|
||||
async function runBuiltinWithMessages(
|
||||
storageRoot: string,
|
||||
provider: ReturnType<typeof resolveModel>,
|
||||
messages: ChatMessage[],
|
||||
session: SessionRecord,
|
||||
store: Store,
|
||||
maxTurns: number,
|
||||
noTools: boolean,
|
||||
): Promise<AgentRunResult> {
|
||||
const loopResult = await runBuiltinLoop({
|
||||
provider,
|
||||
messages,
|
||||
toolCtx: buildToolContext(storageRoot),
|
||||
maxTurns,
|
||||
storageRoot,
|
||||
sessionId: session.sessionId,
|
||||
noTools,
|
||||
});
|
||||
|
||||
session.messages = loopResult.messages;
|
||||
|
||||
if (loopResult.turnCount === 0) {
|
||||
log("5RWTK9NB", "no turns produced, returning empty output");
|
||||
return { output: "", detailHash: "", sessionId: session.sessionId, assembledPrompt: "" };
|
||||
}
|
||||
|
||||
// Read jsonl → persist turns to CAS → store detail
|
||||
const { detailHash } = await storeBuiltinDetail(
|
||||
store,
|
||||
storageRoot,
|
||||
session.sessionId,
|
||||
session.model,
|
||||
session.startedAtMs,
|
||||
);
|
||||
|
||||
return {
|
||||
output: stripPreamble(loopResult.finalText),
|
||||
detailHash,
|
||||
sessionId: session.sessionId,
|
||||
assembledPrompt: "",
|
||||
};
|
||||
}
|
||||
|
||||
async function runBuiltin(ctx: AgentContext): Promise<AgentRunResult> {
|
||||
const storageRoot = resolveStorageRoot();
|
||||
const config = await loadWorkflowConfig(storageRoot);
|
||||
const provider = resolveModel(config, config.defaultModel);
|
||||
|
||||
const sessionId = generateUlid(Date.now());
|
||||
await initSessionDir(storageRoot);
|
||||
const messages = buildBuiltinMessages(ctx);
|
||||
|
||||
const session: SessionRecord = {
|
||||
sessionId,
|
||||
model: provider.model,
|
||||
startedAtMs: Date.now(),
|
||||
messages,
|
||||
};
|
||||
sessions.set(sessionId, session);
|
||||
|
||||
return runBuiltinWithMessages(
|
||||
storageRoot,
|
||||
provider,
|
||||
messages,
|
||||
session,
|
||||
ctx.store,
|
||||
BUILTIN_MAX_TURNS,
|
||||
false,
|
||||
);
|
||||
}
|
||||
|
||||
async function continueBuiltin(
|
||||
sessionId: string,
|
||||
message: string,
|
||||
store: Store,
|
||||
): Promise<AgentRunResult> {
|
||||
const session = getSession(sessionId);
|
||||
const storageRoot = resolveStorageRoot();
|
||||
const config = await loadWorkflowConfig(storageRoot);
|
||||
const provider = resolveModel(config, config.defaultModel);
|
||||
|
||||
const messages: ChatMessage[] = [...session.messages, { role: "user", content: message }];
|
||||
|
||||
return runBuiltinWithMessages(
|
||||
storageRoot,
|
||||
provider,
|
||||
messages,
|
||||
session,
|
||||
store,
|
||||
BUILTIN_CONTINUE_MAX_TURNS,
|
||||
true,
|
||||
);
|
||||
}
|
||||
|
||||
/** Agent CLI factory: built-in LLM loop with file/shell tools. */
|
||||
export function createBuiltinAgent(): () => Promise<void> {
|
||||
return createAgent({
|
||||
name: "builtin",
|
||||
run: runBuiltin,
|
||||
continue: continueBuiltin,
|
||||
});
|
||||
}
|
||||
Executable
+6
@@ -0,0 +1,6 @@
|
||||
#!/usr/bin/env bun
|
||||
|
||||
import { createBuiltinAgent } from "./agent.js";
|
||||
|
||||
const main = createBuiltinAgent();
|
||||
void main();
|
||||
@@ -0,0 +1,49 @@
|
||||
import { bootstrap, putSchema, type Store } from "@ocas/core";
|
||||
|
||||
import { BUILTIN_DETAIL_SCHEMA, BUILTIN_TURN_SCHEMA } from "./schemas.js";
|
||||
import { readSessionTurns } from "./session.js";
|
||||
import type { BuiltinDetailPayload } from "./types.js";
|
||||
|
||||
type BuiltinSchemaHashes = {
|
||||
turn: string;
|
||||
detail: string;
|
||||
};
|
||||
|
||||
export async function registerBuiltinSchemas(store: Store): Promise<BuiltinSchemaHashes> {
|
||||
await bootstrap(store);
|
||||
const [turn, detail] = await Promise.all([
|
||||
putSchema(store, BUILTIN_TURN_SCHEMA),
|
||||
putSchema(store, BUILTIN_DETAIL_SCHEMA),
|
||||
]);
|
||||
return { turn, detail };
|
||||
}
|
||||
|
||||
/** Read session jsonl, persist each turn to CAS, return detail hash. */
|
||||
export async function storeBuiltinDetail(
|
||||
store: Store,
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
model: string,
|
||||
startedAtMs: number,
|
||||
nowMs: number = Date.now(),
|
||||
): Promise<{ detailHash: string; turnCount: number }> {
|
||||
const schemas = await registerBuiltinSchemas(store);
|
||||
const turns = await readSessionTurns(storageRoot, sessionId);
|
||||
|
||||
const turnHashes: string[] = [];
|
||||
for (const turn of turns) {
|
||||
const hash = await store.put(schemas.turn, turn);
|
||||
turnHashes.push(hash);
|
||||
}
|
||||
|
||||
const duration = Math.max(0, nowMs - startedAtMs);
|
||||
const detail: BuiltinDetailPayload = {
|
||||
sessionId,
|
||||
model,
|
||||
duration,
|
||||
turnCount: turnHashes.length,
|
||||
turns: turnHashes,
|
||||
};
|
||||
const detailHash = await store.put(schemas.detail, detail);
|
||||
return { detailHash, turnCount: turnHashes.length };
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
export { createBuiltinAgent } from "./agent.js";
|
||||
export { registerBuiltinSchemas, storeBuiltinDetail } from "./detail.js";
|
||||
export type { ChatMessage, LlmAssistantResponse, LlmToolCall } from "./llm/index.js";
|
||||
export { chatCompletionWithTools } from "./llm/index.js";
|
||||
export { BUILTIN_CONTINUE_MAX_TURNS, BUILTIN_MAX_TURNS, runBuiltinLoop } from "./loop.js";
|
||||
export { buildBuiltinMessages } from "./prompt.js";
|
||||
export { appendSessionTurn, initSessionDir, readSessionTurns, removeSession } from "./session.js";
|
||||
export type { BuiltinTool, ToolContext } from "./tools/index.js";
|
||||
export { executeBuiltinTool, getBuiltinTools } from "./tools/index.js";
|
||||
export type {
|
||||
BuiltinDetailPayload,
|
||||
BuiltinLoopTurn,
|
||||
BuiltinToolCallRecord,
|
||||
BuiltinToolResultRecord,
|
||||
BuiltinTurnPayload,
|
||||
} from "./types.js";
|
||||
@@ -0,0 +1,7 @@
|
||||
export { chatCompletionWithTools } from "./llm.js";
|
||||
export type {
|
||||
ChatMessage,
|
||||
LlmAssistantResponse,
|
||||
LlmToolCall,
|
||||
OpenAiToolDefinition,
|
||||
} from "./types.js";
|
||||
@@ -0,0 +1,139 @@
|
||||
import type { ResolvedLlmProvider } from "@united-workforce/util-agent";
|
||||
|
||||
import type {
|
||||
ChatMessage,
|
||||
LlmAssistantResponse,
|
||||
LlmToolCall,
|
||||
OpenAiToolDefinition,
|
||||
} from "./types.js";
|
||||
|
||||
function isRecord(value: unknown): value is Record<string, unknown> {
|
||||
return typeof value === "object" && value !== null && !Array.isArray(value);
|
||||
}
|
||||
|
||||
function chatUrl(baseUrl: string): string {
|
||||
const trimmed = baseUrl.replace(/\/+$/, "");
|
||||
return `${trimmed}/chat/completions`;
|
||||
}
|
||||
|
||||
function parseToolCalls(raw: unknown): LlmToolCall[] | null {
|
||||
if (!Array.isArray(raw) || raw.length === 0) {
|
||||
return null;
|
||||
}
|
||||
const calls: LlmToolCall[] = [];
|
||||
for (const entry of raw) {
|
||||
if (!isRecord(entry)) {
|
||||
continue;
|
||||
}
|
||||
const id = entry.id;
|
||||
const fn = entry.function;
|
||||
if (typeof id !== "string" || !isRecord(fn)) {
|
||||
continue;
|
||||
}
|
||||
const name = fn.name;
|
||||
const args = fn.arguments;
|
||||
if (typeof name !== "string" || typeof args !== "string") {
|
||||
continue;
|
||||
}
|
||||
calls.push({ id, name, arguments: args });
|
||||
}
|
||||
return calls.length > 0 ? calls : null;
|
||||
}
|
||||
|
||||
function parseAssistantMessage(parsed: unknown): LlmAssistantResponse {
|
||||
if (!isRecord(parsed)) {
|
||||
throw new Error("LLM response is not an object");
|
||||
}
|
||||
const choices = parsed.choices;
|
||||
if (!Array.isArray(choices) || choices.length === 0) {
|
||||
throw new Error("LLM response has no choices");
|
||||
}
|
||||
const c0 = choices[0];
|
||||
if (!isRecord(c0)) {
|
||||
throw new Error("LLM choice is not an object");
|
||||
}
|
||||
const messageObj = c0.message;
|
||||
if (!isRecord(messageObj)) {
|
||||
throw new Error("LLM message is not an object");
|
||||
}
|
||||
const contentRaw = messageObj.content;
|
||||
const content =
|
||||
typeof contentRaw === "string"
|
||||
? contentRaw
|
||||
: contentRaw === null || contentRaw === undefined
|
||||
? null
|
||||
: null;
|
||||
const toolCalls = parseToolCalls(messageObj.tool_calls);
|
||||
return { content, toolCalls };
|
||||
}
|
||||
|
||||
function serializeMessage(message: ChatMessage): Record<string, unknown> {
|
||||
if (message.role === "tool") {
|
||||
return {
|
||||
role: "tool",
|
||||
tool_call_id: message.tool_call_id,
|
||||
content: message.content,
|
||||
};
|
||||
}
|
||||
if (message.role === "assistant") {
|
||||
const base: Record<string, unknown> = {
|
||||
role: "assistant",
|
||||
content: message.content,
|
||||
};
|
||||
if (message.tool_calls !== null && message.tool_calls.length > 0) {
|
||||
base.tool_calls = message.tool_calls.map((call) => ({
|
||||
id: call.id,
|
||||
type: "function",
|
||||
function: { name: call.name, arguments: call.arguments },
|
||||
}));
|
||||
}
|
||||
return base;
|
||||
}
|
||||
return { role: message.role, content: message.content };
|
||||
}
|
||||
|
||||
/** OpenAI-compatible chat completion with tool calling (non-streaming). */
|
||||
export async function chatCompletionWithTools(
|
||||
provider: ResolvedLlmProvider,
|
||||
messages: ChatMessage[],
|
||||
tools: OpenAiToolDefinition[] | null,
|
||||
): Promise<LlmAssistantResponse> {
|
||||
const body: Record<string, unknown> = {
|
||||
model: provider.model,
|
||||
messages: messages.map(serializeMessage),
|
||||
};
|
||||
if (tools !== null && tools.length > 0) {
|
||||
body.tools = tools;
|
||||
body.tool_choice = "auto";
|
||||
}
|
||||
|
||||
let response: Response;
|
||||
try {
|
||||
response = await fetch(chatUrl(provider.baseUrl), {
|
||||
method: "POST",
|
||||
headers: {
|
||||
Authorization: `Bearer ${provider.apiKey}`,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
throw new Error(`LLM network error: ${message}`);
|
||||
}
|
||||
|
||||
const responseText = await response.text();
|
||||
if (!response.ok) {
|
||||
throw new Error(`LLM HTTP ${response.status}: ${responseText.slice(0, 2000)}`);
|
||||
}
|
||||
|
||||
let parsed: unknown;
|
||||
try {
|
||||
parsed = JSON.parse(responseText) as unknown;
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
throw new Error(`LLM invalid JSON response: ${message}`);
|
||||
}
|
||||
|
||||
return parseAssistantMessage(parsed);
|
||||
}
|
||||
@@ -0,0 +1,29 @@
|
||||
export type LlmToolCall = {
|
||||
id: string;
|
||||
name: string;
|
||||
arguments: string;
|
||||
};
|
||||
|
||||
export type LlmAssistantResponse = {
|
||||
content: string | null;
|
||||
toolCalls: LlmToolCall[] | null;
|
||||
};
|
||||
|
||||
export type ChatMessage =
|
||||
| { role: "system"; content: string }
|
||||
| { role: "user"; content: string }
|
||||
| {
|
||||
role: "assistant";
|
||||
content: string | null;
|
||||
tool_calls: LlmToolCall[] | null;
|
||||
}
|
||||
| { role: "tool"; tool_call_id: string; content: string };
|
||||
|
||||
export type OpenAiToolDefinition = {
|
||||
type: "function";
|
||||
function: {
|
||||
name: string;
|
||||
description: string;
|
||||
parameters: Record<string, unknown>;
|
||||
};
|
||||
};
|
||||
@@ -0,0 +1,303 @@
|
||||
import { createLogger } from "@united-workforce/util";
|
||||
import type { ResolvedLlmProvider } from "@united-workforce/util-agent";
|
||||
|
||||
import {
|
||||
type ChatMessage,
|
||||
chatCompletionWithTools,
|
||||
type LlmToolCall,
|
||||
type OpenAiToolDefinition,
|
||||
} from "./llm/index.js";
|
||||
import { appendSessionTurn } from "./session.js";
|
||||
import {
|
||||
builtinToolsToOpenAi,
|
||||
executeBuiltinTool,
|
||||
getBuiltinTools,
|
||||
type ToolContext,
|
||||
} from "./tools/index.js";
|
||||
import type { BuiltinToolCall, BuiltinTurnPayload } from "./types.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
export const BUILTIN_MAX_TURNS = 30;
|
||||
export const BUILTIN_CONTINUE_MAX_TURNS = 5;
|
||||
|
||||
export type RunBuiltinLoopOptions = {
|
||||
provider: ResolvedLlmProvider;
|
||||
messages: ChatMessage[];
|
||||
toolCtx: ToolContext;
|
||||
maxTurns: number;
|
||||
storageRoot: string;
|
||||
sessionId: string;
|
||||
/** When true, do not provide tools — force LLM to emit text only. */
|
||||
noTools: boolean;
|
||||
};
|
||||
|
||||
export type RunBuiltinLoopResult = {
|
||||
finalText: string;
|
||||
messages: ChatMessage[];
|
||||
turnCount: number;
|
||||
};
|
||||
|
||||
function mapToolCallsForPayload(calls: LlmToolCall[]): BuiltinToolCall[] {
|
||||
return calls.map((call) => ({
|
||||
name: call.name,
|
||||
args: call.arguments,
|
||||
}));
|
||||
}
|
||||
|
||||
async function appendTurn(
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
payload: BuiltinTurnPayload,
|
||||
): Promise<void> {
|
||||
await appendSessionTurn(storageRoot, sessionId, payload);
|
||||
}
|
||||
|
||||
export async function executeTurnTools(
|
||||
calls: Array<{ id: string; name: string; arguments: string }>,
|
||||
toolCtx: ToolContext,
|
||||
messages: ChatMessage[],
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
): Promise<number> {
|
||||
let turnCount = 0;
|
||||
for (const call of calls) {
|
||||
const result = await executeBuiltinTool(call.name, call.arguments, toolCtx);
|
||||
messages.push({ role: "tool", tool_call_id: call.id, content: result });
|
||||
await appendTurn(storageRoot, sessionId, {
|
||||
role: "tool",
|
||||
content: result,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
turnCount += 1;
|
||||
}
|
||||
return turnCount;
|
||||
}
|
||||
|
||||
export type ShouldNudgeOptions = {
|
||||
noTools: boolean;
|
||||
text: string;
|
||||
turn: number;
|
||||
maxTurns: number;
|
||||
};
|
||||
|
||||
const MAX_NUDGES = 3;
|
||||
const DEADLINE_WARNING_TURNS = 3;
|
||||
|
||||
export function shouldInjectDeadlineWarning(
|
||||
turn: number,
|
||||
maxTurns: number,
|
||||
alreadyWarned: boolean,
|
||||
noTools: boolean,
|
||||
): boolean {
|
||||
const turnsRemaining = maxTurns - turn;
|
||||
return (
|
||||
!noTools && !alreadyWarned && turnsRemaining > 0 && turnsRemaining <= DEADLINE_WARNING_TURNS
|
||||
);
|
||||
}
|
||||
|
||||
export function shouldProcessToolCalls(toolCalls: LlmToolCall[] | null, noTools: boolean): boolean {
|
||||
return !noTools && toolCalls !== null && toolCalls.length > 0;
|
||||
}
|
||||
|
||||
export function extractFinalText(messages: ChatMessage[]): string {
|
||||
for (let i = messages.length - 1; i >= 0; i--) {
|
||||
const msg = messages[i];
|
||||
if (
|
||||
msg !== undefined &&
|
||||
msg.role === "assistant" &&
|
||||
msg.content !== null &&
|
||||
msg.content.trim() !== ""
|
||||
) {
|
||||
return msg.content;
|
||||
}
|
||||
}
|
||||
return "";
|
||||
}
|
||||
|
||||
function injectDeadlineWarning(messages: ChatMessage[], turnsRemaining: number): void {
|
||||
log("4NRXW6KT", `${turnsRemaining} turns remaining, injecting deadline warning`);
|
||||
messages.push({
|
||||
role: "user",
|
||||
content:
|
||||
`⚠️ You have ${turnsRemaining} turns remaining. ` +
|
||||
"Wrap up your work and output the YAML frontmatter starting with `---`. " +
|
||||
"If you cannot finish in time, output frontmatter with `status: failed` and describe what remains.",
|
||||
});
|
||||
}
|
||||
|
||||
type HandleTextOnlyTurnResult = {
|
||||
shouldBreak: boolean;
|
||||
finalText: string;
|
||||
turnCount: number;
|
||||
nudgeCount: number;
|
||||
turnAdjustment: number;
|
||||
};
|
||||
|
||||
async function handleTextOnlyTurn(
|
||||
text: string,
|
||||
messages: ChatMessage[],
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
noTools: boolean,
|
||||
turn: number,
|
||||
maxTurns: number,
|
||||
currentNudgeCount: number,
|
||||
): Promise<HandleTextOnlyTurnResult> {
|
||||
await appendTurn(storageRoot, sessionId, {
|
||||
role: "assistant",
|
||||
content: text,
|
||||
toolCalls: null,
|
||||
reasoning: null,
|
||||
});
|
||||
const turnCount = 1;
|
||||
let nudgeCount = currentNudgeCount;
|
||||
let turnAdjustment = 0;
|
||||
|
||||
if (shouldNudge({ noTools, text, turn, maxTurns })) {
|
||||
nudgeCount += 1;
|
||||
log("7FXQM2KN", `text-only turn without frontmatter, nudge ${nudgeCount}/${MAX_NUDGES}`);
|
||||
const nudge =
|
||||
"You stopped calling tools but your response does not start with the required `---` YAML frontmatter. " +
|
||||
"Either continue using tools to complete your work, or output your final response starting with `---`.";
|
||||
messages.push({ role: "user", content: nudge });
|
||||
// Nudge doesn't consume turn budget (up to MAX_NUDGES)
|
||||
if (nudgeCount <= MAX_NUDGES) {
|
||||
turnAdjustment = -1;
|
||||
}
|
||||
return { shouldBreak: false, finalText: "", turnCount, nudgeCount, turnAdjustment };
|
||||
}
|
||||
|
||||
return { shouldBreak: true, finalText: text, turnCount, nudgeCount, turnAdjustment };
|
||||
}
|
||||
|
||||
async function handleToolCallTurn(
|
||||
content: string,
|
||||
toolCalls: LlmToolCall[],
|
||||
messages: ChatMessage[],
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
toolCtx: ToolContext,
|
||||
): Promise<number> {
|
||||
await appendTurn(storageRoot, sessionId, {
|
||||
role: "assistant",
|
||||
content,
|
||||
toolCalls: mapToolCallsForPayload(toolCalls),
|
||||
reasoning: null,
|
||||
});
|
||||
let turnCount = 1;
|
||||
|
||||
// Execute tools
|
||||
turnCount += await executeTurnTools(toolCalls, toolCtx, messages, storageRoot, sessionId);
|
||||
|
||||
return turnCount;
|
||||
}
|
||||
|
||||
export function shouldNudge({ noTools, text, turn, maxTurns }: ShouldNudgeOptions): boolean {
|
||||
return !noTools && !text.trimStart().startsWith("---") && turn < maxTurns - 1;
|
||||
}
|
||||
|
||||
type ProcessLoopIterationResult = {
|
||||
shouldBreak: boolean;
|
||||
finalText: string;
|
||||
turnCount: number;
|
||||
nudgeCount: number;
|
||||
turnAdjustment: number;
|
||||
};
|
||||
|
||||
async function processLoopIteration(
|
||||
options: RunBuiltinLoopOptions,
|
||||
messages: ChatMessage[],
|
||||
openAiTools: OpenAiToolDefinition[],
|
||||
turn: number,
|
||||
nudgeCount: number,
|
||||
): Promise<ProcessLoopIterationResult> {
|
||||
const response = await chatCompletionWithTools(
|
||||
options.provider,
|
||||
messages,
|
||||
openAiTools.length > 0 ? openAiTools : null,
|
||||
);
|
||||
|
||||
// When noTools is set, ignore any tool_calls the LLM might still return
|
||||
const effectiveToolCalls = options.noTools ? null : (response.toolCalls ?? null);
|
||||
|
||||
const assistantMessage: ChatMessage = {
|
||||
role: "assistant",
|
||||
content: response.content,
|
||||
tool_calls: effectiveToolCalls,
|
||||
};
|
||||
messages.push(assistantMessage);
|
||||
|
||||
if (!shouldProcessToolCalls(effectiveToolCalls, options.noTools)) {
|
||||
const text = response.content ?? "";
|
||||
const result = await handleTextOnlyTurn(
|
||||
text,
|
||||
messages,
|
||||
options.storageRoot,
|
||||
options.sessionId,
|
||||
options.noTools,
|
||||
turn,
|
||||
options.maxTurns,
|
||||
nudgeCount,
|
||||
);
|
||||
return result;
|
||||
}
|
||||
|
||||
// At this point, effectiveToolCalls is guaranteed to be non-null and non-empty
|
||||
const turnCount = await handleToolCallTurn(
|
||||
response.content ?? "",
|
||||
effectiveToolCalls as LlmToolCall[],
|
||||
messages,
|
||||
options.storageRoot,
|
||||
options.sessionId,
|
||||
options.toolCtx,
|
||||
);
|
||||
|
||||
return {
|
||||
shouldBreak: false,
|
||||
finalText: "",
|
||||
turnCount,
|
||||
nudgeCount,
|
||||
turnAdjustment: 0,
|
||||
};
|
||||
}
|
||||
|
||||
/** Agent run loop: LLM ↔ tools until no tool_calls or maxTurns. */
|
||||
export async function runBuiltinLoop(
|
||||
options: RunBuiltinLoopOptions,
|
||||
): Promise<RunBuiltinLoopResult> {
|
||||
const messages = [...options.messages];
|
||||
const openAiTools = options.noTools ? [] : builtinToolsToOpenAi(getBuiltinTools());
|
||||
let finalText = "";
|
||||
let turnCount = 0;
|
||||
let nudgeCount = 0;
|
||||
let deadlineWarned = false;
|
||||
|
||||
for (let turn = 0; turn < options.maxTurns; turn++) {
|
||||
log("8K2M4N7P", `builtin loop turn ${turn + 1}/${options.maxTurns}`);
|
||||
|
||||
// Warn agent when approaching turn limit
|
||||
if (shouldInjectDeadlineWarning(turn, options.maxTurns, deadlineWarned, options.noTools)) {
|
||||
deadlineWarned = true;
|
||||
const turnsRemaining = options.maxTurns - turn;
|
||||
injectDeadlineWarning(messages, turnsRemaining);
|
||||
}
|
||||
|
||||
const result = await processLoopIteration(options, messages, openAiTools, turn, nudgeCount);
|
||||
turnCount += result.turnCount;
|
||||
nudgeCount = result.nudgeCount;
|
||||
turn += result.turnAdjustment;
|
||||
|
||||
if (result.shouldBreak) {
|
||||
finalText = result.finalText;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (finalText === "") {
|
||||
finalText = extractFinalText(messages);
|
||||
}
|
||||
|
||||
return { finalText, messages, turnCount };
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
import { type AgentContext, buildRolePrompt } from "@united-workforce/util-agent";
|
||||
|
||||
import type { ChatMessage } from "./llm/index.js";
|
||||
|
||||
type StepContext = AgentContext["steps"][number];
|
||||
|
||||
function formatStep(step: StepContext, stepNumber: number): string {
|
||||
return [
|
||||
`### Step ${stepNumber}: ${step.role}`,
|
||||
`Output: ${JSON.stringify(step.output)}`,
|
||||
`Agent: ${step.agent}`,
|
||||
].join("\n");
|
||||
}
|
||||
|
||||
function buildStepsSummary(steps: StepContext[], fromIndex: number, toIndex: number): string {
|
||||
if (fromIndex >= toIndex) {
|
||||
return "";
|
||||
}
|
||||
|
||||
const lines: string[] = ["## What Happened Since Your Last Turn"];
|
||||
for (let i = fromIndex; i < toIndex; i++) {
|
||||
const step = steps[i];
|
||||
if (step === undefined) {
|
||||
continue;
|
||||
}
|
||||
lines.push("");
|
||||
lines.push(formatStep(step, i + 1));
|
||||
}
|
||||
return lines.join("\n");
|
||||
}
|
||||
|
||||
function buildUserTurnContent(edgePrompt: string, summary: string): string {
|
||||
const parts: string[] = [];
|
||||
if (edgePrompt !== "") {
|
||||
parts.push(edgePrompt);
|
||||
}
|
||||
if (summary !== "") {
|
||||
if (parts.length > 0) {
|
||||
parts.push("");
|
||||
}
|
||||
parts.push(summary);
|
||||
}
|
||||
return parts.join("\n");
|
||||
}
|
||||
|
||||
/**
|
||||
* Reconstruct multi-turn chat messages from thread history for cache-friendly session resume.
|
||||
*
|
||||
* - system: role prompt + output format (stable prefix)
|
||||
* - For each prior visit of this role: user (edgePrompt + inter-step summary) + assistant (output JSON)
|
||||
* - Final user: current edgePrompt + summary since last visit of this role
|
||||
*/
|
||||
export function buildBuiltinMessages(ctx: AgentContext): ChatMessage[] {
|
||||
const roleDef = ctx.workflow.roles[ctx.role];
|
||||
const rolePrompt = roleDef !== undefined ? buildRolePrompt(roleDef) : "";
|
||||
const systemParts: string[] = [];
|
||||
if (ctx.outputFormatInstruction !== "") {
|
||||
systemParts.push(ctx.outputFormatInstruction, "");
|
||||
}
|
||||
systemParts.push(rolePrompt);
|
||||
|
||||
systemParts.push(
|
||||
"",
|
||||
"## Workflow",
|
||||
"",
|
||||
`Your working directory is: ${process.cwd()}`,
|
||||
"",
|
||||
"You have tools available (read_file, write_file, run_command). " +
|
||||
"Use them to complete your task — read files, run commands, make changes as needed. " +
|
||||
"Your task is described in the user message below — do NOT use uwf or workflow CLI commands to discover your task. " +
|
||||
"When you are done, output your final response with the YAML frontmatter block as specified above. " +
|
||||
"Do NOT output the frontmatter until you have completed all necessary work. " +
|
||||
"If you are running low on turns and cannot finish, output the frontmatter with `status: failed` and explain what remains in the body. " +
|
||||
"CRITICAL: Your final output MUST start with the `---` fence on the very first line — " +
|
||||
"no preamble text, no explanation before it. The parser requires `---` at position 0.",
|
||||
);
|
||||
|
||||
const messages: ChatMessage[] = [{ role: "system", content: systemParts.join("\n") }];
|
||||
|
||||
const roleVisitIndices: number[] = [];
|
||||
for (let i = 0; i < ctx.steps.length; i++) {
|
||||
const step = ctx.steps[i];
|
||||
if (step !== undefined && step.role === ctx.role) {
|
||||
roleVisitIndices.push(i);
|
||||
}
|
||||
}
|
||||
|
||||
let prevVisitIndex = -1;
|
||||
for (const visitIndex of roleVisitIndices) {
|
||||
const visitStep = ctx.steps[visitIndex];
|
||||
if (visitStep === undefined) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const summary = buildStepsSummary(ctx.steps, prevVisitIndex + 1, visitIndex);
|
||||
messages.push({
|
||||
role: "user",
|
||||
content: buildUserTurnContent(visitStep.edgePrompt, summary),
|
||||
});
|
||||
messages.push({
|
||||
role: "assistant",
|
||||
content: JSON.stringify(visitStep.output),
|
||||
tool_calls: null,
|
||||
});
|
||||
prevVisitIndex = visitIndex;
|
||||
}
|
||||
|
||||
const finalSummary = buildStepsSummary(ctx.steps, prevVisitIndex + 1, ctx.steps.length);
|
||||
messages.push({
|
||||
role: "user",
|
||||
content: buildUserTurnContent(ctx.edgePrompt, finalSummary),
|
||||
});
|
||||
|
||||
return messages;
|
||||
}
|
||||
@@ -0,0 +1,45 @@
|
||||
import type { JSONSchema } from "@ocas/core";
|
||||
|
||||
const BUILTIN_TOOL_CALL_SCHEMA: JSONSchema = {
|
||||
type: "object",
|
||||
required: ["name", "args"],
|
||||
properties: {
|
||||
name: { type: "string" },
|
||||
args: { type: "string" },
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
export const BUILTIN_TURN_SCHEMA: JSONSchema = {
|
||||
title: "builtin-turn",
|
||||
type: "object",
|
||||
required: ["role", "content"],
|
||||
properties: {
|
||||
role: { type: "string", enum: ["assistant", "tool"] },
|
||||
content: { type: "string" },
|
||||
toolCalls: {
|
||||
anyOf: [{ type: "array", items: BUILTIN_TOOL_CALL_SCHEMA }, { type: "null" }],
|
||||
},
|
||||
reasoning: {
|
||||
anyOf: [{ type: "string" }, { type: "null" }],
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
|
||||
export const BUILTIN_DETAIL_SCHEMA: JSONSchema = {
|
||||
title: "builtin-detail",
|
||||
type: "object",
|
||||
required: ["sessionId", "model", "duration", "turnCount", "turns"],
|
||||
properties: {
|
||||
sessionId: { type: "string" },
|
||||
model: { type: "string" },
|
||||
duration: { type: "integer" },
|
||||
turnCount: { type: "integer" },
|
||||
turns: {
|
||||
type: "array",
|
||||
items: { type: "string", format: "ocas_ref" },
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
};
|
||||
@@ -0,0 +1,59 @@
|
||||
import { appendFile, mkdir, readFile, rm } from "node:fs/promises";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { createLogger } from "@united-workforce/util";
|
||||
|
||||
import type { BuiltinTurnPayload } from "./types.js";
|
||||
|
||||
const log = createLogger({ sink: { kind: "stderr" } });
|
||||
|
||||
function sessionsDir(storageRoot: string): string {
|
||||
return join(storageRoot, "sessions");
|
||||
}
|
||||
|
||||
function sessionFile(storageRoot: string, sessionId: string): string {
|
||||
return join(sessionsDir(storageRoot), `${sessionId}.jsonl`);
|
||||
}
|
||||
|
||||
/** Ensure sessions directory exists. */
|
||||
export async function initSessionDir(storageRoot: string): Promise<void> {
|
||||
await mkdir(sessionsDir(storageRoot), { recursive: true });
|
||||
}
|
||||
|
||||
/** Append a turn to the session jsonl file. */
|
||||
export async function appendSessionTurn(
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
turn: BuiltinTurnPayload,
|
||||
): Promise<void> {
|
||||
const line = `${JSON.stringify(turn)}\n`;
|
||||
await appendFile(sessionFile(storageRoot, sessionId), line, "utf-8");
|
||||
log("3XQVN8KR", `session ${sessionId} appended ${turn.role} turn`);
|
||||
}
|
||||
|
||||
/** Read all turns from session jsonl. Returns empty array if file does not exist. */
|
||||
export async function readSessionTurns(
|
||||
storageRoot: string,
|
||||
sessionId: string,
|
||||
): Promise<BuiltinTurnPayload[]> {
|
||||
try {
|
||||
const content = await readFile(sessionFile(storageRoot, sessionId), "utf-8");
|
||||
const lines = content
|
||||
.trim()
|
||||
.split("\n")
|
||||
.filter((l) => l.length > 0);
|
||||
return lines.map((l) => JSON.parse(l) as BuiltinTurnPayload);
|
||||
} catch {
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
/** Remove session jsonl file (called after detail is persisted to step CAS). */
|
||||
export async function removeSession(storageRoot: string, sessionId: string): Promise<void> {
|
||||
try {
|
||||
await rm(sessionFile(storageRoot, sessionId));
|
||||
log("7FWDP2MJ", `session ${sessionId} removed`);
|
||||
} catch {
|
||||
// already gone — fine
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
import type { OpenAiToolDefinition } from "../llm/index.js";
|
||||
|
||||
import { readFileTool } from "./read-file.js";
|
||||
import { runCommandTool } from "./run-command.js";
|
||||
import type { BuiltinTool, ToolContext } from "./types.js";
|
||||
import { writeFileTool } from "./write-file.js";
|
||||
|
||||
export { resolvePath } from "./path.js";
|
||||
export type { BuiltinTool, ToolContext } from "./types.js";
|
||||
|
||||
const BUILTIN_TOOLS: BuiltinTool[] = [readFileTool, writeFileTool, runCommandTool];
|
||||
|
||||
export function getBuiltinTools(): readonly BuiltinTool[] {
|
||||
return BUILTIN_TOOLS;
|
||||
}
|
||||
|
||||
export function builtinToolsToOpenAi(tools: readonly BuiltinTool[]): OpenAiToolDefinition[] {
|
||||
return tools.map((tool) => ({
|
||||
type: "function",
|
||||
function: {
|
||||
name: tool.name,
|
||||
description: tool.description,
|
||||
parameters: tool.parameters as Record<string, unknown>,
|
||||
},
|
||||
}));
|
||||
}
|
||||
|
||||
export async function executeBuiltinTool(
|
||||
name: string,
|
||||
argsJson: string,
|
||||
ctx: ToolContext,
|
||||
): Promise<string> {
|
||||
const tool = BUILTIN_TOOLS.find((t) => t.name === name);
|
||||
if (tool === undefined) {
|
||||
return `Error: unknown tool ${name}`;
|
||||
}
|
||||
let args: unknown;
|
||||
try {
|
||||
args = JSON.parse(argsJson) as unknown;
|
||||
} catch {
|
||||
return "Error: tool arguments must be valid JSON";
|
||||
}
|
||||
return tool.execute(args, ctx);
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
import { resolve } from "node:path";
|
||||
|
||||
/** Resolve a path relative to the working directory. */
|
||||
export function resolvePath(cwd: string, inputPath: string): string {
|
||||
return resolve(cwd, inputPath);
|
||||
}
|
||||
@@ -0,0 +1,41 @@
|
||||
import { readFile, stat } from "node:fs/promises";
|
||||
import { resolvePath } from "./path.js";
|
||||
import type { BuiltinTool } from "./types.js";
|
||||
|
||||
const MAX_READ_BYTES = 512 * 1024;
|
||||
|
||||
function isRecord(value: unknown): value is Record<string, unknown> {
|
||||
return typeof value === "object" && value !== null && !Array.isArray(value);
|
||||
}
|
||||
|
||||
export const readFileTool: BuiltinTool = {
|
||||
name: "read_file",
|
||||
description: "Read a UTF-8 text file from the workspace.",
|
||||
parameters: {
|
||||
type: "object",
|
||||
required: ["path"],
|
||||
properties: {
|
||||
path: { type: "string", description: "Relative or absolute path within the workspace." },
|
||||
},
|
||||
additionalProperties: false,
|
||||
},
|
||||
execute: async (args, ctx) => {
|
||||
if (!isRecord(args) || typeof args.path !== "string") {
|
||||
return "Error: path must be a string";
|
||||
}
|
||||
const resolved = resolvePath(ctx.cwd, args.path);
|
||||
try {
|
||||
const info = await stat(resolved);
|
||||
if (!info.isFile()) {
|
||||
return "Error: not a file";
|
||||
}
|
||||
if (info.size > MAX_READ_BYTES) {
|
||||
return `Error: file exceeds ${MAX_READ_BYTES} byte limit`;
|
||||
}
|
||||
return await readFile(resolved, "utf8");
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
return `Error: ${message}`;
|
||||
}
|
||||
},
|
||||
};
|
||||
@@ -0,0 +1,95 @@
|
||||
import { spawn } from "node:child_process";
|
||||
import { resolvePath } from "./path.js";
|
||||
import type { BuiltinTool } from "./types.js";
|
||||
|
||||
const COMMAND_TIMEOUT_MS = 60_000;
|
||||
const MAX_OUTPUT_CHARS = 32_000;
|
||||
|
||||
function isRecord(value: unknown): value is Record<string, unknown> {
|
||||
return typeof value === "object" && value !== null && !Array.isArray(value);
|
||||
}
|
||||
|
||||
function truncate(text: string, maxChars: number): string {
|
||||
if (text.length <= maxChars) {
|
||||
return text;
|
||||
}
|
||||
return `${text.slice(0, maxChars)}\n...(truncated)`;
|
||||
}
|
||||
|
||||
function runShell(
|
||||
command: string,
|
||||
cwd: string,
|
||||
): Promise<{ stdout: string; stderr: string; code: number }> {
|
||||
return new Promise((resolve, reject) => {
|
||||
const child = spawn(command, {
|
||||
cwd,
|
||||
env: process.env,
|
||||
shell: true,
|
||||
stdio: ["ignore", "pipe", "pipe"],
|
||||
});
|
||||
|
||||
let stdout = "";
|
||||
let stderr = "";
|
||||
child.stdout?.on("data", (chunk: Buffer) => {
|
||||
stdout += chunk.toString();
|
||||
});
|
||||
child.stderr?.on("data", (chunk: Buffer) => {
|
||||
stderr += chunk.toString();
|
||||
});
|
||||
|
||||
const timer = setTimeout(() => {
|
||||
child.kill("SIGTERM");
|
||||
}, COMMAND_TIMEOUT_MS);
|
||||
|
||||
child.on("error", (cause) => {
|
||||
clearTimeout(timer);
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
reject(new Error(message));
|
||||
});
|
||||
|
||||
child.on("close", (code) => {
|
||||
clearTimeout(timer);
|
||||
resolve({ stdout, stderr, code: code ?? 1 });
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
export const runCommandTool: BuiltinTool = {
|
||||
name: "run_command",
|
||||
description: "Run a shell command. Output is truncated to 32KB.",
|
||||
parameters: {
|
||||
type: "object",
|
||||
required: ["command"],
|
||||
properties: {
|
||||
command: { type: "string", description: "Shell command to execute." },
|
||||
cwd: {
|
||||
type: "string",
|
||||
description: "Optional working directory relative to workspace root.",
|
||||
},
|
||||
},
|
||||
additionalProperties: false,
|
||||
},
|
||||
execute: async (args, ctx) => {
|
||||
if (!isRecord(args) || typeof args.command !== "string") {
|
||||
return "Error: command must be a string";
|
||||
}
|
||||
let workDir = ctx.cwd;
|
||||
if (args.cwd !== undefined && args.cwd !== null) {
|
||||
if (typeof args.cwd !== "string") {
|
||||
return "Error: cwd must be a string";
|
||||
}
|
||||
workDir = resolvePath(ctx.cwd, args.cwd);
|
||||
}
|
||||
try {
|
||||
const { stdout, stderr, code } = await runShell(args.command, workDir);
|
||||
const out = truncate(
|
||||
`exit_code: ${code}\n--- stdout ---\n${stdout}\n--- stderr ---\n${stderr}`,
|
||||
MAX_OUTPUT_CHARS,
|
||||
);
|
||||
return out;
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
return `Error: ${message}`;
|
||||
}
|
||||
},
|
||||
};
|
||||
@@ -0,0 +1,13 @@
|
||||
import type { JSONSchema } from "@ocas/core";
|
||||
|
||||
export type ToolContext = {
|
||||
cwd: string;
|
||||
storageRoot: string;
|
||||
};
|
||||
|
||||
export type BuiltinTool = {
|
||||
name: string;
|
||||
description: string;
|
||||
parameters: JSONSchema;
|
||||
execute: (args: unknown, ctx: ToolContext) => Promise<string>;
|
||||
};
|
||||
@@ -0,0 +1,36 @@
|
||||
import { mkdir, writeFile } from "node:fs/promises";
|
||||
import { dirname } from "node:path";
|
||||
import { resolvePath } from "./path.js";
|
||||
import type { BuiltinTool } from "./types.js";
|
||||
|
||||
function isRecord(value: unknown): value is Record<string, unknown> {
|
||||
return typeof value === "object" && value !== null && !Array.isArray(value);
|
||||
}
|
||||
|
||||
export const writeFileTool: BuiltinTool = {
|
||||
name: "write_file",
|
||||
description: "Write UTF-8 text to a file in the workspace (creates parent directories).",
|
||||
parameters: {
|
||||
type: "object",
|
||||
required: ["path", "content"],
|
||||
properties: {
|
||||
path: { type: "string", description: "Relative or absolute path within the workspace." },
|
||||
content: { type: "string", description: "File contents to write." },
|
||||
},
|
||||
additionalProperties: false,
|
||||
},
|
||||
execute: async (args, ctx) => {
|
||||
if (!isRecord(args) || typeof args.path !== "string" || typeof args.content !== "string") {
|
||||
return "Error: path and content must be strings";
|
||||
}
|
||||
const resolved = resolvePath(ctx.cwd, args.path);
|
||||
try {
|
||||
await mkdir(dirname(resolved), { recursive: true });
|
||||
await writeFile(resolved, args.content, "utf8");
|
||||
return `Wrote ${args.content.length} bytes to ${args.path}`;
|
||||
} catch (cause) {
|
||||
const message = cause instanceof Error ? cause.message : String(cause);
|
||||
return `Error: ${message}`;
|
||||
}
|
||||
},
|
||||
};
|
||||
@@ -0,0 +1,49 @@
|
||||
import type { ChatMessage } from "./llm/index.js";
|
||||
|
||||
export type BuiltinToolCallRecord = {
|
||||
id: string;
|
||||
name: string;
|
||||
args: string;
|
||||
};
|
||||
|
||||
export type BuiltinToolResultRecord = {
|
||||
toolCallId: string;
|
||||
name: string;
|
||||
content: string;
|
||||
};
|
||||
|
||||
export type BuiltinLoopTurn = {
|
||||
assistantContent: string | null;
|
||||
toolCalls: BuiltinToolCallRecord[] | null;
|
||||
toolResults: BuiltinToolResultRecord[] | null;
|
||||
};
|
||||
|
||||
export type BuiltinSessionState = {
|
||||
sessionId: string;
|
||||
model: string;
|
||||
startedAtMs: number;
|
||||
messages: ChatMessage[];
|
||||
turns: BuiltinLoopTurn[];
|
||||
};
|
||||
|
||||
export type BuiltinTurnRole = "assistant" | "tool";
|
||||
|
||||
export type BuiltinToolCall = {
|
||||
name: string;
|
||||
args: string;
|
||||
};
|
||||
|
||||
export type BuiltinTurnPayload = {
|
||||
role: BuiltinTurnRole;
|
||||
content: string;
|
||||
toolCalls: BuiltinToolCall[] | null;
|
||||
reasoning: string | null;
|
||||
};
|
||||
|
||||
export type BuiltinDetailPayload = {
|
||||
sessionId: string;
|
||||
model: string;
|
||||
duration: number;
|
||||
turnCount: number;
|
||||
turns: string[];
|
||||
};
|
||||
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"extends": "../../tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist"
|
||||
},
|
||||
"include": ["src"],
|
||||
"references": [{ "path": "../util-agent" }, { "path": "../util" }]
|
||||
}
|
||||
Reference in New Issue
Block a user