Files

T

xiaoju 2b8cd99100 fix(agent-claude-code): use buildContinuationPrompt for step context

Replace custom buildHistorySummary with shared buildContinuationPrompt
from workflow-agent-kit. This aligns claude-code agent with hermes agent:

- First visit: includes step content (within 32k quota)
- Re-entry: shows only steps since last visit (meta only, session has context)

Previously developer could not see reviewer's detailed feedback on
re-entry, only {"approved":false}. Now gets full review text.

Fixes #486

2026-05-25 02:01:57 +00:00

__tests__

fix(agent-claude-code): use buildContinuationPrompt for step context

2026-05-25 02:01:57 +00:00

src

fix(agent-claude-code): use buildContinuationPrompt for step context

2026-05-25 02:01:57 +00:00

package.json

feat(cli): add filtering and pagination to thread list command

2026-05-24 14:44:30 +00:00

README.md

docs: sync all README.md files with current codebase

2026-05-23 15:00:05 +00:00

tsconfig.json

feat: add workflow-agent-claude-code package

2026-05-22 18:38:18 +08:00

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-agent-kit

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-agent-kit (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).