Merge pull request 'feat: workflow-agent-claude-code' (#393) from feat/391-workflow-agent-claude-code into main

packages/workflow-agent-claude-code/__tests__/claude-code.test.ts

@@ -0,0 +1,59 @@
+import { describe, expect, test } from "bun:test";
+import type { AgentContext } from "@uncaged/workflow-agent-kit";
+import { buildClaudeCodePrompt } from "../src/claude-code.js";
+
+function makeCtx(overrides: Partial<AgentContext> = {}): AgentContext {
+  return {
+    workflow: {
+      roles: {
+        developer: {
+          description: "TDD implementation per test spec",
+          goal: "Write code",
+          capabilities: ["coding"],
+          procedure: "1. Read spec\n2. Write code",
+          output: "List files changed",
+          frontmatter: "",
+        },
+      },
+      conditions: {},
+      graph: {},
+    },
+    role: "developer",
+    start: { prompt: "Fix the bug", workflowHash: "abc123", threadId: "t1" },
+    steps: [],
+    store: {} as AgentContext["store"],
+    outputFormatInstruction: "Use YAML frontmatter",
+    ...overrides,
+  };
+}
+
+describe("buildClaudeCodePrompt", () => {
+  test("assembles outputFormatInstruction + role prompt + task prompt", () => {
+    const result = buildClaudeCodePrompt(makeCtx());
+    expect(result).toMatch(/^Use YAML frontmatter/);
+    expect(result).toContain("Write code");
+    expect(result).toContain("## Task\nFix the bug");
+  });
+
+  test("includes previous steps as history summary", () => {
+    const ctx = makeCtx({
+      steps: [{ role: "planner", output: '{"plan":"do X"}', agent: "hermes" }],
+    });
+    const result = buildClaudeCodePrompt(ctx);
+    expect(result).toContain("## Previous Steps");
+    expect(result).toContain("Step 1: planner");
+    expect(result).toContain("do X");
+  });
+
+  test("omits history section when steps array is empty", () => {
+    const result = buildClaudeCodePrompt(makeCtx({ steps: [] }));
+    expect(result).not.toContain("## Previous Steps");
+  });
+
+  test("works without outputFormatInstruction", () => {
+    const result = buildClaudeCodePrompt(makeCtx({ outputFormatInstruction: "" }));
+    expect(result).not.toMatch(/^\s*\n/);
+    expect(result).toContain("Write code");
+    expect(result).toContain("## Task");
+  });
+});

packages/workflow-agent-claude-code/__tests__/session-detail.test.ts

@@ -0,0 +1,115 @@
+import { describe, expect, test } from "bun:test";
+import { createMemoryStore, walk } from "@uncaged/json-cas";
+import {
+  parseClaudeCodeJsonOutput,
+  storeClaudeCodeDetail,
+  storeClaudeCodeRawOutput,
+} from "../src/session-detail.js";
+import type { ClaudeCodeParsedResult } from "../src/types.js";
+
+describe("parseClaudeCodeJsonOutput", () => {
+  test("parses valid claude -p --output-format json output", () => {
+    const stdout = JSON.stringify({
+      type: "result",
+      subtype: "success",
+      result: "Done fixing bug",
+      session_id: "75e2167f-abc",
+      num_turns: 3,
+      total_cost_usd: 0.08,
+      duration_ms: 10276,
+    });
+    const parsed = parseClaudeCodeJsonOutput(stdout);
+    expect(parsed).not.toBeNull();
+    expect(parsed!.type).toBe("result");
+    expect(parsed!.subtype).toBe("success");
+    expect(parsed!.result).toBe("Done fixing bug");
+    expect(parsed!.sessionId).toBe("75e2167f-abc");
+    expect(parsed!.numTurns).toBe(3);
+    expect(parsed!.totalCostUsd).toBe(0.08);
+    expect(parsed!.durationMs).toBe(10276);
+  });
+
+  test("parses error_max_turns result", () => {
+    const stdout = JSON.stringify({
+      type: "result",
+      subtype: "error_max_turns",
+      result: "Ran out of turns",
+      session_id: "abc-def",
+      num_turns: 90,
+      total_cost_usd: 1.5,
+      duration_ms: 50000,
+    });
+    const parsed = parseClaudeCodeJsonOutput(stdout);
+    expect(parsed).not.toBeNull();
+    expect(parsed!.subtype).toBe("error_max_turns");
+    expect(parsed!.result).toBe("Ran out of turns");
+  });
+
+  test("returns null for non-JSON output", () => {
+    const parsed = parseClaudeCodeJsonOutput("Some random text\nwithout JSON");
+    expect(parsed).toBeNull();
+  });
+
+  test("returns null when session_id is missing", () => {
+    const stdout = JSON.stringify({ type: "result", result: "hi", subtype: "success" });
+    const parsed = parseClaudeCodeJsonOutput(stdout);
+    expect(parsed).toBeNull();
+  });
+});
+
+describe("storeClaudeCodeDetail", () => {
+  test("stores claude-code-detail CAS node and returns output + detailHash", async () => {
+    const store = createMemoryStore();
+    const parsed: ClaudeCodeParsedResult = {
+      type: "result",
+      subtype: "success",
+      result: "The answer",
+      sessionId: "abc-123",
+      numTurns: 5,
+      totalCostUsd: 0.12,
+      durationMs: 15000,
+    };
+
+    const { detailHash, output, sessionId } = await storeClaudeCodeDetail(store, parsed);
+    expect(detailHash).toHaveLength(13);
+    expect(output).toBe("The answer");
+    expect(sessionId).toBe("abc-123");
+
+    const node = await store.get(detailHash);
+    expect(node).not.toBeNull();
+    expect(node!.payload.sessionId).toBe("abc-123");
+    expect(node!.payload.numTurns).toBe(5);
+    expect(node!.payload.totalCostUsd).toBe(0.12);
+    expect(node!.payload.durationMs).toBe(15000);
+  });
+
+  test("detail node is walkable from root", async () => {
+    const store = createMemoryStore();
+    const parsed: ClaudeCodeParsedResult = {
+      type: "result",
+      subtype: "success",
+      result: "walkable test",
+      sessionId: "walk-123",
+      numTurns: 1,
+      totalCostUsd: 0.01,
+      durationMs: 1000,
+    };
+
+    const { detailHash } = await storeClaudeCodeDetail(store, parsed);
+    const visited: string[] = [];
+    walk(store, detailHash, (hash) => visited.push(hash));
+    expect(visited.length).toBeGreaterThan(0);
+  });
+});
+
+describe("storeClaudeCodeRawOutput", () => {
+  test("stores raw text when JSON parsing fails", async () => {
+    const store = createMemoryStore();
+    const rawText = "Claude produced plain text without JSON";
+    const hash = await storeClaudeCodeRawOutput(store, rawText);
+    expect(hash).toHaveLength(13);
+    const node = await store.get(hash);
+    expect(node).not.toBeNull();
+    expect(node!.payload.text).toBe(rawText);
+  });
+});

packages/workflow-agent-claude-code/package.json

@@ -0,0 +1,33 @@
+{
+  "name": "@uncaged/workflow-agent-claude-code",
+  "version": "0.1.0",
+  "files": [
+    "src",
+    "dist",
+    "package.json"
+  ],
+  "type": "module",
+  "bin": {
+    "uwf-claude-code": "./src/cli.ts"
+  },
+  "exports": {
+    ".": {
+      "bun": "./src/index.ts",
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js"
+    }
+  },
+  "scripts": {
+    "test": "bun test"
+  },
+  "dependencies": {
+    "@uncaged/json-cas": "^0.4.0",
+    "@uncaged/workflow-agent-kit": "workspace:^"
+  },
+  "devDependencies": {
+    "typescript": "^5.8.3"
+  },
+  "publishConfig": {
+    "access": "public"
+  }
+}

packages/workflow-agent-claude-code/src/claude-code.ts

@@ -0,0 +1,148 @@
+import { spawn } from "node:child_process";
+import type { Store } from "@uncaged/json-cas";
+
+import {
+  type AgentContext,
+  type AgentRunResult,
+  buildRolePrompt,
+  createAgent,
+} from "@uncaged/workflow-agent-kit";
+
+import { parseClaudeCodeJsonOutput, storeClaudeCodeDetail } from "./session-detail.js";
+
+const CLAUDE_COMMAND = "claude";
+const CLAUDE_MAX_TURNS = 90;
+
+function buildHistorySummary(steps: AgentContext["steps"]): string {
+  if (steps.length === 0) {
+    return "";
+  }
+
+  const lines: string[] = ["## Previous Steps"];
+  for (let i = 0; i < steps.length; i++) {
+    const step = steps[i];
+    if (step === undefined) {
+      continue;
+    }
+    lines.push("");
+    lines.push(`### Step ${i + 1}: ${step.role}`);
+    lines.push(`Output: ${JSON.stringify(step.output)}`);
+    lines.push(`Agent: ${step.agent}`);
+  }
+  return lines.join("\n");
+}
+
+/** Assemble system prompt, task, and prior step outputs for Claude Code. */
+export function buildClaudeCodePrompt(ctx: AgentContext): string {
+  const roleDef = ctx.workflow.roles[ctx.role];
+  const rolePrompt = roleDef !== undefined ? buildRolePrompt(roleDef) : "";
+  const parts: string[] = [];
+  if (ctx.outputFormatInstruction !== undefined && ctx.outputFormatInstruction !== "") {
+    parts.push(ctx.outputFormatInstruction, "");
+  }
+  parts.push(rolePrompt, "", "## Task", ctx.start.prompt);
+  const historyBlock = buildHistorySummary(ctx.steps);
+  if (historyBlock !== "") {
+    parts.push("", historyBlock);
+  }
+  return parts.join("\n");
+}
+
+function spawnClaude(args: string[]): Promise<{ stdout: string; stderr: string }> {
+  return new Promise((resolve, reject) => {
+    const child = spawn(CLAUDE_COMMAND, args, {
+      env: process.env,
+      shell: false,
+      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();
+    });
+
+    child.on("error", (cause) => {
+      const message = cause instanceof Error ? cause.message : String(cause);
+      reject(new Error(`claude spawn failed: ${message}`));
+    });
+
+    child.on("close", (code) => {
+      if (code === 0) {
+        resolve({ stdout, stderr });
+        return;
+      }
+      const detail = stderr.trim() !== "" ? ` stderr=${stderr.trim()}` : "";
+      reject(new Error(`claude exited with code ${code ?? "null"}${detail}`));
+    });
+  });
+}
+
+function spawnClaudeRun(prompt: string): Promise<{ stdout: string; stderr: string }> {
+  return spawnClaude([
+    "-p",
+    prompt,
+    "--output-format",
+    "json",
+    "--dangerously-skip-permissions",
+    "--max-turns",
+    String(CLAUDE_MAX_TURNS),
+  ]);
+}
+
+function spawnClaudeResume(
+  sessionId: string,
+  message: string,
+): Promise<{ stdout: string; stderr: string }> {
+  return spawnClaude([
+    "-p",
+    message,
+    "--resume",
+    sessionId,
+    "--output-format",
+    "json",
+    "--dangerously-skip-permissions",
+    "--max-turns",
+    String(CLAUDE_MAX_TURNS),
+  ]);
+}
+
+async function processClaudeOutput(stdout: string, store: Store): Promise<AgentRunResult> {
+  const parsed = parseClaudeCodeJsonOutput(stdout);
+
+  if (parsed !== null) {
+    const { detailHash, output, sessionId } = await storeClaudeCodeDetail(store, parsed);
+    return { output, detailHash, sessionId };
+  }
+
+  throw new Error(
+    `Claude Code returned non-JSON output (first 200 chars): ${stdout.slice(0, 200)}`,
+  );
+}
+
+async function runClaudeCode(ctx: AgentContext): Promise<AgentRunResult> {
+  const fullPrompt = buildClaudeCodePrompt(ctx);
+  const { stdout } = await spawnClaudeRun(fullPrompt);
+  return processClaudeOutput(stdout, ctx.store);
+}
+
+async function continueClaudeCode(
+  sessionId: string,
+  message: string,
+  store: Store,
+): Promise<AgentRunResult> {
+  const { stdout } = await spawnClaudeResume(sessionId, message);
+  return processClaudeOutput(stdout, store);
+}
+
+/** Agent CLI factory: parses argv, runs Claude Code, extracts output, writes StepNode. */
+export function createClaudeCodeAgent(): () => Promise<void> {
+  return createAgent({
+    name: "claude-code",
+    run: runClaudeCode,
+    continue: continueClaudeCode,
+  });
+}

packages/workflow-agent-claude-code/src/cli.ts

@@ -0,0 +1,6 @@
+#!/usr/bin/env bun
+
+import { createClaudeCodeAgent } from "./claude-code.js";
+
+const main = createClaudeCodeAgent();
+void main();

packages/workflow-agent-claude-code/src/index.ts

@@ -0,0 +1,6 @@
+export { buildClaudeCodePrompt, createClaudeCodeAgent } from "./claude-code.js";
+export {
+  parseClaudeCodeJsonOutput,
+  storeClaudeCodeDetail,
+  storeClaudeCodeRawOutput,
+} from "./session-detail.js";

packages/workflow-agent-claude-code/src/schemas.ts

@@ -0,0 +1,25 @@
+import type { JSONSchema } from "@uncaged/json-cas";
+
+export const CLAUDE_CODE_DETAIL_SCHEMA: JSONSchema = {
+  title: "claude-code-detail",
+  type: "object",
+  required: ["sessionId", "numTurns", "totalCostUsd", "durationMs", "subtype"],
+  properties: {
+    sessionId: { type: "string" },
+    numTurns: { type: "integer" },
+    totalCostUsd: { type: "number" },
+    durationMs: { type: "integer" },
+    subtype: { type: "string" },
+  },
+  additionalProperties: false,
+};
+
+export const CLAUDE_CODE_RAW_OUTPUT_SCHEMA: JSONSchema = {
+  title: "claude-code-raw-output",
+  type: "object",
+  required: ["text"],
+  properties: {
+    text: { type: "string" },
+  },
+  additionalProperties: false,
+};

packages/workflow-agent-claude-code/src/session-detail.ts

@@ -0,0 +1,79 @@
+import { bootstrap, putSchema, type Store } from "@uncaged/json-cas";
+
+import { CLAUDE_CODE_DETAIL_SCHEMA, CLAUDE_CODE_RAW_OUTPUT_SCHEMA } from "./schemas.js";
+import type { ClaudeCodeDetailPayload, ClaudeCodeParsedResult } from "./types.js";
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+
+/** Parse Claude Code JSON stdout (`claude -p --output-format json`). */
+export function parseClaudeCodeJsonOutput(stdout: string): ClaudeCodeParsedResult | null {
+  let parsed: unknown;
+  try {
+    parsed = JSON.parse(stdout.trim());
+  } catch {
+    return null;
+  }
+
+  if (!isRecord(parsed)) {
+    return null;
+  }
+
+  const sessionId = parsed.session_id;
+  const result = parsed.result;
+  const subtype = parsed.subtype;
+
+  if (typeof sessionId !== "string" || typeof result !== "string" || typeof subtype !== "string") {
+    return null;
+  }
+
+  return {
+    type: typeof parsed.type === "string" ? parsed.type : "result",
+    subtype: subtype as ClaudeCodeParsedResult["subtype"],
+    result,
+    sessionId,
+    numTurns: typeof parsed.num_turns === "number" ? parsed.num_turns : 0,
+    totalCostUsd: typeof parsed.total_cost_usd === "number" ? parsed.total_cost_usd : 0,
+    durationMs: typeof parsed.duration_ms === "number" ? parsed.duration_ms : 0,
+  };
+}
+
+type ClaudeCodeSchemaHashes = {
+  detail: string;
+  rawOutput: string;
+};
+
+async function registerSchemas(store: Store): Promise<ClaudeCodeSchemaHashes> {
+  await bootstrap(store);
+  const [detail, rawOutput] = await Promise.all([
+    putSchema(store, CLAUDE_CODE_DETAIL_SCHEMA),
+    putSchema(store, CLAUDE_CODE_RAW_OUTPUT_SCHEMA),
+  ]);
+  return { detail, rawOutput };
+}
+
+/** Store parsed Claude Code result as a CAS detail node. */
+export async function storeClaudeCodeDetail(
+  store: Store,
+  parsed: ClaudeCodeParsedResult,
+): Promise<{ detailHash: string; output: string; sessionId: string }> {
+  const schemas = await registerSchemas(store);
+
+  const detail: ClaudeCodeDetailPayload = {
+    sessionId: parsed.sessionId,
+    numTurns: parsed.numTurns,
+    totalCostUsd: parsed.totalCostUsd,
+    durationMs: parsed.durationMs,
+    subtype: parsed.subtype,
+  };
+
+  const detailHash = await store.put(schemas.detail, detail);
+  return { detailHash, output: parsed.result, sessionId: parsed.sessionId };
+}
+
+/** Fallback: store raw text output when JSON parsing fails. */
+export async function storeClaudeCodeRawOutput(store: Store, rawOutput: string): Promise<string> {
+  const schemas = await registerSchemas(store);
+  return store.put(schemas.rawOutput, { text: rawOutput });
+}

packages/workflow-agent-claude-code/src/types.ts

@@ -0,0 +1,19 @@
+export type ClaudeCodeResultSubtype = "success" | "error_max_turns" | "error_budget";
+
+export type ClaudeCodeParsedResult = {
+  type: string;
+  subtype: ClaudeCodeResultSubtype;
+  result: string;
+  sessionId: string;
+  numTurns: number;
+  totalCostUsd: number;
+  durationMs: number;
+};
+
+export type ClaudeCodeDetailPayload = {
+  sessionId: string;
+  numTurns: number;
+  totalCostUsd: number;
+  durationMs: number;
+  subtype: string;
+};

packages/workflow-agent-claude-code/tsconfig.json

@@ -0,0 +1,6 @@
+{
+  "extends": "../../tsconfig.json",
+  "compilerOptions": { "rootDir": "src", "outDir": "dist" },
+  "include": ["src"],
+  "references": [{ "path": "../workflow-agent-kit" }]
+}