Files

T

xiaoju 53fa4d8972 fix(agent-claude-code): handle missing result line gracefully

Handle the case where Claude Code exits without producing a result line
(timeout, OOM, signal kill). Previously returned null and threw an error;
now returns incomplete result with best-effort output extraction.

Changes:
- Add "incomplete" as new ClaudeCodeResultSubtype value
- Extract output from last assistant turn when no result line exists
- Enhanced error messages distinguish incomplete vs unparseable output
- Store incomplete results in CAS with appropriate metadata
- Add 10 comprehensive test cases for incomplete result handling

Fixes #574

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-05-30 05:37:09 +00:00

__tests__

fix(agent-claude-code): handle missing result line gracefully

2026-05-30 05:37:09 +00:00

src

fix(agent-claude-code): handle missing result line gracefully

2026-05-30 05:37:09 +00:00

package.json

chore: normalize to bun monorepo conventions

2026-05-28 08:02:52 +00:00

README.md

refactor: rename workflow-agent-kit → workflow-util-agent, merge workflow-moderator into cli-workflow

2026-05-25 10:51:16 +00:00

tsconfig.json

refactor: rename workflow-agent-kit → workflow-util-agent, merge workflow-moderator into cli-workflow

2026-05-25 10:51:16 +00:00

vitest.config.ts

chore: normalize to bun monorepo conventions

2026-05-28 08:02:52 +00:00

README.md

@uncaged/workflow-agent-claude-code

uwf-claude-code agent — spawns the Claude Code CLI and captures session detail.

Overview

Layer 3 agent implementation. Spawns the claude CLI with a composed system prompt (role definition, task, prior steps, edge prompt). Parses stream or JSON stdout, caches session IDs for multi-turn continuation, and stores raw output plus structured detail in CAS.

Dependencies: @uncaged/json-cas, @uncaged/workflow-util-agent

Installation

Included as the uwf-claude-code binary when you install @uncaged/workflow-agent-claude-code:

bun add -g @uncaged/workflow-agent-claude-code

Requires the claude CLI on PATH.

CLI Usage

Invoked by uwf thread step:

uwf-claude-code <thread-id> <role>

Configure or override the agent:

uwf setup --agent claude-code
uwf thread step <thread-id> --agent uwf-claude-code

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

function createClaudeCodeAgent(): () => Promise<void>
function buildClaudeCodePrompt(ctx: AgentContext): string

Session detail

function parseClaudeCodeStreamOutput(stdout: string): ClaudeCodeParsedResult | null
function parseClaudeCodeJsonOutput(stdout: string): ClaudeCodeParsedResult | null
function storeClaudeCodeDetail(
  store: Store,
  parsed: ClaudeCodeParsedResult,
  sessionId: string,
): Promise<string>
function storeClaudeCodeRawOutput(store: Store, rawOutput: string): Promise<string>

Usage (library)

import { createClaudeCodeAgent, buildClaudeCodePrompt } from "@uncaged/workflow-agent-claude-code";

const main = createClaudeCodeAgent();
void main();

Internal Structure

src/
├── index.ts
├── cli.ts              Binary entrypoint
├── claude-code.ts      createClaudeCodeAgent, buildClaudeCodePrompt, spawn logic
├── session-detail.ts   Parse stdout, store CAS detail nodes
├── schemas.ts          Claude Code detail CAS schemas
└── types.ts            ClaudeCodeParsedResult, message shapes

Configuration

Uses session caching from @uncaged/workflow-util-agent (getCachedSessionId / setCachedSessionId). No separate config file — relies on the Claude Code CLI's own authentication.

Maximum turns per invocation: 90 (constant in claude-code.ts).