refactor(cli): reduce cognitive complexity in thread.ts

Extract helper functions (resolveThreadId, getThreadHead, listThreadSteps,
displayStepDetails, displayThreadRead) to reduce nesting and improve
readability. Also adds test coverage for the refactored functions.

Fixes #446

.cursor/rules/sync-readme.mdc

@@ -0,0 +1,67 @@
+# Sync README
+
+When updating README.md files in this monorepo, follow these conventions.
+
+## Scope
+
+- Root `README.md` — project overview and navigation hub
+- Per-package `packages/*/README.md` — each package self-contained
+
+## Root README Structure
+
+The root README should have these sections in order:
+
+1. **Title and one-liner** — stateless workflow engine driven by single-step CLI
+2. **Overview** — 2-3 paragraphs explaining what it does and key concepts
+3. **Architecture** — dependency layer diagram (text-based)
+4. **Packages** — table with ALL packages from packages/ directory, columns: Package, Description, Type (cli/lib/agent/app)
+5. **Quick Start** — install, build, register workflow, start thread, run step
+6. **CLI Reference** — brief command list, detailed usage in cli-workflow README
+7. **Development** — bun install / build / check / test
+
+## Per-Package README Structure
+
+Each package README should have:
+
+1. **Title** — package name
+2. **One-line description** — matching package.json
+3. **Overview** — what it does, where it sits in the architecture, dependencies
+4. **Installation** — bun add (for libs) or "included as binary" (for cli/agents)
+5. **API** (lib packages) — all exports from src/index.ts with type signatures, grouped by category, minimal usage examples
+6. **CLI Usage** (cli/agent packages) — command reference with examples
+7. **Internal Structure** — brief src/ file organization
+8. **Configuration** (if applicable)
+
+## Execution Steps
+
+### Step 1: Gather current state
+For each package read:
+- package.json (name, version, description, dependencies, bin)
+- src/index.ts (public API exports)
+- Existing README.md (preserve hand-written content worth keeping)
+
+### Step 2: Update root README
+- Ensure ALL packages in packages/ directory are listed in the table
+- Update CLI command reference from uwf --help output
+- Keep Quick Start examples valid
+
+### Step 3: Write/update each package README
+- Follow the per-package structure
+- API section MUST match actual src/index.ts exports — never invent
+- For agent packages: document CLI binary name, how it is invoked
+- For lib packages: document exported types and functions
+- Internal structure: list actual files in src/
+
+### Step 4: Verify
+- All relative links work
+- Package names match package.json
+- No references to removed/renamed packages
+- bun run build still passes
+
+## Guidelines
+
+- Only document what src/index.ts actually exports
+- Root README summarizes, package READMEs go into detail
+- Verify CLI examples against actual commands
+- Preserve existing good prose when updating
+- English for all README content

packages/cli-workflow/src/__tests__/thread.test.ts

@@ -382,10 +382,6 @@ describe("cmdThreadStepDetails", () => {
       content: "done",
     });
   });
-
-  test("throws when step hash does not exist", async () => {
-    await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
-  });
 });
 
 // ── cmdThreadRead: ### Prompt deduplication ───────────────────────────────────
@@ -471,3 +467,181 @@ describe("cmdThreadRead ### Prompt deduplication", () => {
     expect(count).toBe(2);
   });
 });
+
+// ── cmdThreadRead: showStart / before / quota ─────────────────────────────────
+
+describe("cmdThreadRead start section / before / quota", () => {
+  async function makeSimpleThread(
+    uwf: UwfStore,
+    roles: string[],
+  ): Promise<{ startHash: CasRef; stepHashes: CasRef[] }> {
+    const uniqueRoles = [...new Set(roles)];
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "simple-wf",
+      description: "desc",
+      roles: Object.fromEntries(
+        uniqueRoles.map((r) => [
+          r,
+          {
+            description: r,
+            goal: `Goal for ${r}`,
+            capabilities: [],
+            procedure: "Do stuff.",
+            output: "Output.",
+            meta: "placeholder00" as CasRef,
+          },
+        ]),
+      ),
+      conditions: {},
+      graph: {},
+    });
+    const startHash = (await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Initial prompt",
+    })) as CasRef;
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    const stepHashes: CasRef[] = [];
+    let prev: CasRef | null = null;
+    for (const role of roles) {
+      const stepHash = (await uwf.store.put(uwf.schemas.stepNode, {
+        start: startHash,
+        prev,
+        role,
+        output: outputHash,
+        detail: null,
+        agent: "uwf-test",
+      })) as CasRef;
+      stepHashes.push(stepHash);
+      prev = stepHash;
+    }
+    return { startHash, stepHashes };
+  }
+
+  test("showStart=true includes # Thread header and ## Task section", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const { stepHashes } = await makeSimpleThread(uwf, ["roleA"]);
+    const threadId = "01JTEST0000000000000006" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[stepHashes.length - 1]! });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, true);
+    expect(markdown).toContain("# Thread");
+    expect(markdown).toContain("## Task");
+    expect(markdown).toContain("Initial prompt");
+  });
+
+  test("showStart=false with before=null still shows # Thread header (default behavior)", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const { stepHashes } = await makeSimpleThread(uwf, ["roleA"]);
+    const threadId = "01JTEST0000000000000007" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[stepHashes.length - 1]! });
+
+    // When before=null, the start section is always shown regardless of showStart
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+    expect(markdown).toContain("# Thread");
+    expect(markdown).toContain("## Task");
+  });
+
+  test("before filter: only steps before the given hash appear", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const { stepHashes } = await makeSimpleThread(uwf, ["roleA", "roleB", "roleC"]);
+    const [_hashA, hashB, hashC] = stepHashes as [CasRef, CasRef, CasRef];
+    const threadId = "01JTEST0000000000000008" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: hashC });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, hashB, false);
+    expect(markdown).toContain("roleA");
+    expect(markdown).not.toContain("roleB");
+    expect(markdown).not.toContain("roleC");
+  });
+
+  test("quota=1 limits output and includes skip hint", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const { stepHashes } = await makeSimpleThread(uwf, ["roleA", "roleB", "roleC"]);
+    const threadId = "01JTEST000000000000000A" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[stepHashes.length - 1]! });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, 1, null, false);
+    expect(markdown).toContain("earlier step");
+  });
+
+  test("all steps fit in quota: no skip hint", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const { stepHashes } = await makeSimpleThread(uwf, ["roleA"]);
+    const threadId = "01JTEST000000000000000B" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: stepHashes[0]! });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+    expect(markdown).not.toContain("earlier step");
+  });
+});
+
+// ── Tests that call process.exit must be last ─────────────────────────────────
+
+describe("cmdThreadStepDetails (process.exit tests - must be last)", () => {
+  test("throws when step hash does not exist", async () => {
+    await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
+  });
+
+  test("before with unknown hash rejects", async () => {
+    const _uwf = await makeUwfStore(tmpDir);
+    const casDir = join(tmpDir, "cas");
+    await mkdir(casDir, { recursive: true });
+    const store = createFsStore(casDir);
+    const schemas = await registerUwfSchemas(store);
+    const uwfStore: UwfStore = { storageRoot: tmpDir, store, schemas };
+
+    const workflowHash = await uwfStore.store.put(uwfStore.schemas.workflow, {
+      name: "wf2",
+      description: "",
+      roles: {
+        roleA: {
+          description: "r",
+          goal: "g",
+          capabilities: [],
+          procedure: "p",
+          output: "o",
+          meta: "placeholder00" as CasRef,
+        },
+      },
+      conditions: {},
+      graph: {},
+    });
+    const startHash = await uwfStore.store.put(uwfStore.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "p",
+    });
+    const outputHash = await uwfStore.store.put(uwfStore.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+    const stepHash = await uwfStore.store.put(uwfStore.schemas.stepNode, {
+      start: startHash,
+      prev: null,
+      role: "roleA",
+      output: outputHash,
+      detail: null,
+      agent: "uwf-test",
+    });
+    await saveThreadsIndex(tmpDir, { ["01JTEST000000000000000C" as ThreadId]: stepHash as CasRef });
+
+    await expect(
+      cmdThreadRead(
+        tmpDir,
+        "01JTEST000000000000000C" as ThreadId,
+        THREAD_READ_DEFAULT_QUOTA,
+        "unknownhash0" as CasRef,
+        false,
+      ),
+    ).rejects.toThrow();
+  });
+});

packages/cli-workflow/src/commands/thread.ts

@@ -462,49 +462,68 @@ function expandDeep(store: CasStore, hash: CasRef, visited?: Set<string>): unkno
   return expandValue(store, schema, node.payload, seen);
 }
 
+function expandCasRefField(store: CasStore, value: unknown, visited: Set<string>): unknown {
+  if (typeof value === "string") {
+    return expandDeep(store, value as CasRef, visited);
+  }
+  return value;
+}
+
+function expandAnyOfField(
+  store: CasStore,
+  schema: JSONSchema,
+  value: unknown,
+  visited: Set<string>,
+): unknown {
+  if (!Array.isArray(schema.anyOf)) return value;
+  for (const sub of schema.anyOf as JSONSchema[]) {
+    if (sub.format === "cas_ref" && typeof value === "string") {
+      return expandDeep(store, value as CasRef, visited);
+    }
+  }
+  return value;
+}
+
+function expandArrayField(
+  store: CasStore,
+  schema: JSONSchema,
+  value: unknown,
+  visited: Set<string>,
+): unknown {
+  if (!schema.items || !Array.isArray(value)) return value;
+  const itemSchema = schema.items as JSONSchema;
+  return (value as unknown[]).map((item) => expandValue(store, itemSchema, item, visited));
+}
+
+function expandObjectField(
+  store: CasStore,
+  schema: JSONSchema,
+  value: unknown,
+  visited: Set<string>,
+): unknown {
+  if (value === null || typeof value !== "object" || Array.isArray(value) || !schema.properties) {
+    return value;
+  }
+  const props = schema.properties as Record<string, JSONSchema>;
+  const obj = value as Record<string, unknown>;
+  const result: Record<string, unknown> = {};
+  for (const [key, val] of Object.entries(obj)) {
+    const propSchema = props[key];
+    result[key] = propSchema ? expandValue(store, propSchema, val, visited) : val;
+  }
+  return result;
+}
+
 function expandValue(
   store: CasStore,
   schema: JSONSchema,
   value: unknown,
   visited: Set<string>,
 ): unknown {
-  // If this field is a cas_ref, expand it
-  if (schema.format === "cas_ref") {
-    if (typeof value === "string") {
-      return expandDeep(store, value as CasRef, visited);
-    }
-    return value;
-  }
-
-  // anyOf (nullable refs)
-  if (Array.isArray(schema.anyOf)) {
-    for (const sub of schema.anyOf as JSONSchema[]) {
-      if (sub.format === "cas_ref" && typeof value === "string") {
-        return expandDeep(store, value as CasRef, visited);
-      }
-    }
-    return value;
-  }
-
-  // Array of cas_ref items
-  if (schema.type === "array" && schema.items && Array.isArray(value)) {
-    const itemSchema = schema.items as JSONSchema;
-    return (value as unknown[]).map((item) => expandValue(store, itemSchema, item, visited));
-  }
-
-  // Object with properties
-  if (value !== null && typeof value === "object" && !Array.isArray(value) && schema.properties) {
-    const props = schema.properties as Record<string, JSONSchema>;
-    const obj = value as Record<string, unknown>;
-    const result: Record<string, unknown> = {};
-    for (const [key, val] of Object.entries(obj)) {
-      const propSchema = props[key];
-      result[key] = propSchema ? expandValue(store, propSchema, val, visited) : val;
-    }
-    return result;
-  }
-
-  return value;
+  if (schema.format === "cas_ref") return expandCasRefField(store, value, visited);
+  if (Array.isArray(schema.anyOf)) return expandAnyOfField(store, schema, value, visited);
+  if (schema.type === "array") return expandArrayField(store, schema, value, visited);
+  return expandObjectField(store, schema, value, visited);
 }
 
 function collectOrderedSteps(
@@ -588,6 +607,85 @@ export function extractLastAssistantContent(uwf: UwfStore, detailRef: CasRef): s
   return null;
 }
 
+function sliceBeforeHash(
+  candidates: OrderedStepItem[],
+  before: CasRef,
+  threadId: ThreadId,
+): OrderedStepItem[] {
+  const idx = candidates.findIndex((s) => s.hash === before);
+  if (idx === -1) {
+    fail(`step ${before} not found in thread ${threadId}`);
+  }
+  return candidates.slice(0, idx);
+}
+
+function selectByQuota(
+  candidates: OrderedStepItem[],
+  uwf: UwfStore,
+  quota: number,
+): { selected: OrderedStepItem[]; skippedCount: number } {
+  const selected: OrderedStepItem[] = [];
+  let totalChars = 0;
+  for (let i = candidates.length - 1; i >= 0; i--) {
+    const item = candidates[i];
+    if (item === undefined) continue;
+    const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
+    const blockLen = formatCompactStep(i + 1, item, outputYaml).length;
+    selected.unshift(item);
+    totalChars += blockLen;
+    if (totalChars > quota) break;
+  }
+  return { selected, skippedCount: candidates.length - selected.length };
+}
+
+function formatStepHeader(stepNum: number, item: OrderedStepItem): string {
+  const ts = new Date(item.timestamp)
+    .toISOString()
+    .replace("T", " ")
+    .replace(/\.\d+Z$/, "");
+  return [
+    `## Step ${stepNum}: ${item.payload.role} \`${item.hash}\``,
+    `**Agent:** ${item.payload.agent} | **Time:** ${ts}`,
+  ].join("\n");
+}
+
+function formatStepPrompt(
+  roleDef: WorkflowPayload["roles"][string] | undefined,
+  role: string,
+  shownPromptRoles: Set<string>,
+): string {
+  if (!roleDef || shownPromptRoles.has(role)) return "";
+  shownPromptRoles.add(role);
+  return ["", "", "### Prompt", "", roleDef.goal].join("\n");
+}
+
+function formatStepContent(uwf: UwfStore, item: OrderedStepItem): string {
+  if (!item.payload.detail) return "";
+  const content = extractLastAssistantContent(uwf, item.payload.detail);
+  if (content === null) return "";
+  return ["", "", "### Content", "", content].join("\n");
+}
+
+function formatStartSection(options: {
+  threadId: ThreadId;
+  workflowName: string;
+  workflowHash: CasRef;
+  prompt: string;
+  before: CasRef | null;
+  showStart: boolean;
+}): string {
+  if (options.before !== null && !options.showStart) return "";
+  return [
+    `# Thread \`${options.threadId}\``,
+    "",
+    `**Workflow:** ${options.workflowName} (\`${options.workflowHash}\`)`,
+    "",
+    "## Task",
+    "",
+    options.prompt,
+  ].join("\n");
+}
+
 function formatThreadReadMarkdown(options: {
   threadId: ThreadId;
   workflowName: string;
@@ -600,50 +698,16 @@ function formatThreadReadMarkdown(options: {
   before: CasRef | null;
   showStart: boolean;
 }): string {
-  const { ordered, uwf, workflow, quota, before, showStart } = options;
+  const { ordered, uwf, workflow, quota, before } = options;
 
-  // Determine which steps to consider
-  let candidates = ordered;
-  if (before !== null) {
-    const idx = candidates.findIndex((s) => s.hash === before);
-    if (idx === -1) {
-      fail(`step ${before} not found in thread ${options.threadId}`);
-    }
-    candidates = candidates.slice(0, idx);
-  }
+  const candidates = before !== null ? sliceBeforeHash(ordered, before, options.threadId) : ordered;
+  const { selected, skippedCount } = selectByQuota(candidates, uwf, quota);
 
-  // Walk backward from newest, accumulating chars until quota exceeded
-  const selected: OrderedStepItem[] = [];
-  let totalChars = 0;
-  for (let i = candidates.length - 1; i >= 0; i--) {
-    const item = candidates[i];
-    if (item === undefined) continue;
-    const outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
-    const blockLen = formatCompactStep(i + 1, item, outputYaml).length;
-    selected.unshift(item);
-    totalChars += blockLen;
-    if (totalChars > quota) break;
-  }
-
-  const skippedCount = candidates.length - selected.length;
   const parts: string[] = [];
 
-  // Start section
-  if (before === null || showStart) {
-    parts.push(
-      [
-        `# Thread \`${options.threadId}\``,
-        "",
-        `**Workflow:** ${options.workflowName} (\`${options.workflowHash}\`)`,
-        "",
-        "## Task",
-        "",
-        options.prompt,
-      ].join("\n"),
-    );
-  }
+  const startSection = formatStartSection(options);
+  if (startSection !== "") parts.push(startSection);
 
-  // Skip hint
   if (skippedCount > 0 && selected.length > 0) {
     const firstSelected = selected[0];
     if (firstSelected !== undefined) {
@@ -653,34 +717,21 @@ function formatThreadReadMarkdown(options: {
     }
   }
 
-  // Step blocks
   const startIndex = candidates.length - selected.length;
   const shownPromptRoles = new Set<string>();
   for (let i = 0; i < selected.length; i++) {
     const item = selected[i];
     if (item === undefined) continue;
     const stepNum = startIndex + i + 1;
-    const ts = new Date(item.timestamp)
-      .toISOString()
-      .replace("T", " ")
-      .replace(/\.\d+Z$/, "");
-    const stepLines = [
-      `## Step ${stepNum}: ${item.payload.role} \`${item.hash}\``,
-      `**Agent:** ${item.payload.agent} | **Time:** ${ts}`,
-    ];
     const roleDef = workflow.roles[item.payload.role];
-    if (roleDef && !shownPromptRoles.has(item.payload.role)) {
-      const prompt = roleDef.goal;
-      stepLines.push("", "### Prompt", "", prompt);
-      shownPromptRoles.add(item.payload.role);
-    }
-    if (item.payload.detail) {
-      const content = extractLastAssistantContent(uwf, item.payload.detail);
-      if (content !== null) {
-        stepLines.push("", "### Content", "", content);
-      }
-    }
-    parts.push(stepLines.join("\n"));
+    const stepBlock = [
+      formatStepHeader(stepNum, item),
+      formatStepPrompt(roleDef, item.payload.role, shownPromptRoles),
+      formatStepContent(uwf, item),
+    ]
+      .filter((s) => s !== "")
+      .join("");
+    parts.push(stepBlock);
   }
 
   return parts.join("\n\n---\n\n");

packages/workflow-agent-builtin/__tests__/loop.test.ts

@@ -0,0 +1,156 @@
+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, runBuiltinLoop, shouldNudge } 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);
+  });
+});

packages/workflow-agent-builtin/src/loop.ts

@@ -48,7 +48,7 @@ async function appendTurn(
   await appendSessionTurn(storageRoot, sessionId, payload);
 }
 
-async function executeTurnTools(
+export async function executeTurnTools(
   calls: Array<{ id: string; name: string; arguments: string }>,
   toolCtx: ToolContext,
   messages: ChatMessage[],
@@ -70,6 +70,20 @@ async function executeTurnTools(
   return turnCount;
 }
 
+export type ShouldNudgeOptions = {
+  noTools: boolean;
+  text: string;
+  turn: number;
+  maxTurns: number;
+};
+
+const MAX_NUDGES = 3;
+const DEADLINE_WARNING_TURNS = 3;
+
+export function shouldNudge({ noTools, text, turn, maxTurns }: ShouldNudgeOptions): boolean {
+  return !noTools && !text.trimStart().startsWith("---") && turn < maxTurns - 1;
+}
+
 /** Agent run loop: LLM ↔ tools until no tool_calls or maxTurns. */
 export async function runBuiltinLoop(
   options: RunBuiltinLoopOptions,
@@ -78,23 +92,43 @@ export async function runBuiltinLoop(
   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
+    const turnsRemaining = options.maxTurns - turn;
+    if (!options.noTools && !deadlineWarned && turnsRemaining <= DEADLINE_WARNING_TURNS) {
+      deadlineWarned = true;
+      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.",
+      });
+    }
+
     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: response.toolCalls,
+      tool_calls: effectiveToolCalls,
     };
     messages.push(assistantMessage);
 
-    if (response.toolCalls === null || response.toolCalls.length === 0) {
+    if (effectiveToolCalls === null || effectiveToolCalls.length === 0) {
       const text = response.content ?? "";
       await appendTurn(options.storageRoot, options.sessionId, {
         role: "assistant",
@@ -104,14 +138,17 @@ export async function runBuiltinLoop(
       });
       turnCount += 1;
 
-      // If tools are available but LLM stopped calling them without producing
-      // frontmatter, nudge it to continue working or output frontmatter.
-      if (!options.noTools && !text.trimStart().startsWith("---") && turn < options.maxTurns - 1) {
-        log("7FXQM2KN", "text-only turn without frontmatter, nudging LLM to continue");
+      if (shouldNudge({ noTools: options.noTools, text, turn, maxTurns: options.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) {
+          turn -= 1;
+        }
         continue;
       }
 
@@ -123,14 +160,14 @@ export async function runBuiltinLoop(
     await appendTurn(options.storageRoot, options.sessionId, {
       role: "assistant",
       content: response.content ?? "",
-      toolCalls: mapToolCallsForPayload(response.toolCalls),
+      toolCalls: mapToolCallsForPayload(effectiveToolCalls),
       reasoning: null,
     });
     turnCount += 1;
 
     // Execute tools
     turnCount += await executeTurnTools(
-      response.toolCalls,
+      effectiveToolCalls,
       options.toolCtx,
       messages,
       options.storageRoot,

packages/workflow-agent-builtin/src/prompt.ts

@@ -70,6 +70,7 @@ export function buildBuiltinMessages(ctx: AgentContext): ChatMessage[] {
       "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.",
   );

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

@@ -16,6 +16,7 @@ const log = createLogger({ sink: { kind: "stderr" } });
 
 const CLAUDE_COMMAND = "claude";
 const CLAUDE_MAX_TURNS = 90;
+const CLAUDE_MODEL = process.env["CLAUDE_MODEL"] ?? null;
 
 function buildHistorySummary(steps: AgentContext["steps"]): string {
   if (steps.length === 0) {
@@ -87,7 +88,7 @@ function spawnClaude(args: string[]): Promise<{ stdout: string; stderr: string }
 }
 
 function spawnClaudeRun(prompt: string): Promise<{ stdout: string; stderr: string }> {
-  return spawnClaude([
+  const args = [
     "-p",
     prompt,
     "--output-format",
@@ -96,14 +97,18 @@ function spawnClaudeRun(prompt: string): Promise<{ stdout: string; stderr: strin
     "--dangerously-skip-permissions",
     "--max-turns",
     String(CLAUDE_MAX_TURNS),
-  ]);
+  ];
+  if (CLAUDE_MODEL !== null) {
+    args.push("--model", CLAUDE_MODEL);
+  }
+  return spawnClaude(args);
 }
 
 function spawnClaudeResume(
   sessionId: string,
   message: string,
 ): Promise<{ stdout: string; stderr: string }> {
-  return spawnClaude([
+  const args = [
     "-p",
     message,
     "--resume",
@@ -114,7 +119,11 @@ function spawnClaudeResume(
     "--dangerously-skip-permissions",
     "--max-turns",
     String(CLAUDE_MAX_TURNS),
-  ]);
+  ];
+  if (CLAUDE_MODEL !== null) {
+    args.push("--model", CLAUDE_MODEL);
+  }
+  return spawnClaude(args);
 }
 
 async function processClaudeOutput(stdout: string, store: Store): Promise<AgentRunResult> {