fix(#447): fix biome format in loop.test.ts

- Inject user message when 3 turns remain, telling agent to wrap up
- Prompt tells agent to use status:failed if it can't finish in time
- Prevents wasting all turns without producing any frontmatter output
- Remove stale test file from dogfood agent run

package.json

@@ -9,7 +9,7 @@
     "check": "bunx tsc --build && biome check . && bash scripts/lint-log-tags.sh",
     "typecheck": "bunx tsc --build",
     "format": "biome format --write .",
-    "test": "bun run --filter '*' test",
+    "test": "bun run --filter './packages/*' test",
     "changeset": "bunx changeset",
     "version": "bunx changeset version",
     "release": "bun run build && bun test && node scripts/publish-all.mjs"

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

@@ -266,12 +266,7 @@ describe("cmdThreadRead ### Content section", () => {
 
     expect(markdown).toContain("### Content");
     expect(markdown).toContain("The assistant response text");
-
-    const contentIdx = markdown.indexOf("### Content");
-    const outputIdx = markdown.indexOf("### Output");
-    expect(contentIdx).toBeGreaterThanOrEqual(0);
-    expect(outputIdx).toBeGreaterThanOrEqual(0);
-    expect(contentIdx).toBeLessThan(outputIdx);
+    expect(markdown).not.toContain("### Output");
   });
 
   test("omits ### Content when detail has no matching assistant turns", async () => {
@@ -314,7 +309,7 @@ describe("cmdThreadRead ### Content section", () => {
     const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
 
     expect(markdown).not.toContain("### Content");
-    expect(markdown).toContain("### Output");
+    expect(markdown).not.toContain("### Output");
   });
 });
 
@@ -392,3 +387,87 @@ describe("cmdThreadStepDetails", () => {
     await expect(cmdThreadStepDetails(tmpDir, "nonexistenth0" as CasRef)).rejects.toThrow();
   });
 });
+
+// ── cmdThreadRead: ### Prompt deduplication ───────────────────────────────────
+
+describe("cmdThreadRead ### Prompt deduplication", () => {
+  async function makeThreadWithRoles(uwf: UwfStore, roles: string[]): Promise<string> {
+    const roleMap: Record<string, unknown> = {};
+    for (const r of [...new Set(roles)]) {
+      roleMap[r] = {
+        description: r,
+        goal: `Goal for ${r}`,
+        capabilities: [],
+        procedure: "Do stuff.",
+        output: "Output.",
+        meta: "placeholder00" as CasRef,
+      };
+    }
+    const workflowHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "dedup-wf",
+      description: "desc",
+      roles: roleMap,
+      conditions: {},
+      graph: {},
+    });
+    const startHash = await uwf.store.put(uwf.schemas.startNode, {
+      workflow: workflowHash,
+      prompt: "Start",
+    });
+    const outputHash = await uwf.store.put(uwf.schemas.workflow, {
+      name: "out",
+      description: "",
+      roles: {},
+      conditions: {},
+      graph: {},
+    });
+
+    let prev: string | null = null;
+    let stepHash = "";
+    for (const role of roles) {
+      stepHash = await uwf.store.put(uwf.schemas.stepNode, {
+        start: startHash,
+        prev: prev as CasRef | null,
+        role,
+        output: outputHash,
+        detail: null,
+        agent: "uwf-test",
+      });
+      prev = stepHash;
+    }
+    return stepHash;
+  }
+
+  test("same consecutive role shows ### Prompt once", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const headHash = await makeThreadWithRoles(uwf, ["writer", "writer"]);
+    const threadId = "01JTEST0000000000000003" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: headHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+    const count = (markdown.match(/### Prompt/g) ?? []).length;
+    expect(count).toBe(1);
+  });
+
+  test("different consecutive roles each show ### Prompt", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const headHash = await makeThreadWithRoles(uwf, ["planner", "coder"]);
+    const threadId = "01JTEST0000000000000004" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: headHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+    const count = (markdown.match(/### Prompt/g) ?? []).length;
+    expect(count).toBe(2);
+  });
+
+  test("non-consecutive same role shows ### Prompt twice", async () => {
+    const uwf = await makeUwfStore(tmpDir);
+    const headHash = await makeThreadWithRoles(uwf, ["roleA", "roleB", "roleA"]);
+    const threadId = "01JTEST0000000000000005" as ThreadId;
+    await saveThreadsIndex(tmpDir, { [threadId]: headHash });
+
+    const markdown = await cmdThreadRead(tmpDir, threadId, THREAD_READ_DEFAULT_QUOTA, null, false);
+    const count = (markdown.match(/### Prompt/g) ?? []).length;
+    expect(count).toBe(2);
+  });
+});

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

@@ -655,11 +655,11 @@ 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 outputYaml = formatYaml(expandOutput(uwf, item.payload.output));
     const ts = new Date(item.timestamp)
       .toISOString()
       .replace("T", " ")
@@ -669,9 +669,10 @@ function formatThreadReadMarkdown(options: {
       `**Agent:** ${item.payload.agent} | **Time:** ${ts}`,
     ];
     const roleDef = workflow.roles[item.payload.role];
-    if (roleDef) {
+    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);
@@ -679,7 +680,6 @@ function formatThreadReadMarkdown(options: {
         stepLines.push("", "### Content", "", content);
       }
     }
-    stepLines.push("", "### Output", "", "```yaml", outputYaml, "```");
     parts.push(stepLines.join("\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/agent.ts

@@ -66,6 +66,7 @@ async function runBuiltinWithMessages(
   session: SessionRecord,
   store: Store,
   maxTurns: number,
+  noTools: boolean,
 ): Promise<AgentRunResult> {
   const loopResult = await runBuiltinLoop({
     provider,
@@ -74,6 +75,7 @@ async function runBuiltinWithMessages(
     maxTurns,
     storageRoot,
     sessionId: session.sessionId,
+    noTools,
   });
 
   session.messages = loopResult.messages;
@@ -119,6 +121,7 @@ async function runBuiltin(ctx: AgentContext): Promise<AgentRunResult> {
     session,
     ctx.store,
     BUILTIN_MAX_TURNS,
+    false,
   );
 }
 
@@ -141,6 +144,7 @@ async function continueBuiltin(
     session,
     store,
     BUILTIN_CONTINUE_MAX_TURNS,
+    true,
   );
 }
 

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

@@ -96,8 +96,17 @@ function serializeMessage(message: ChatMessage): Record<string, unknown> {
 export async function chatCompletionWithTools(
   provider: ResolvedLlmProvider,
   messages: ChatMessage[],
-  tools: OpenAiToolDefinition[],
+  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), {
@@ -106,12 +115,7 @@ export async function chatCompletionWithTools(
         Authorization: `Bearer ${provider.apiKey}`,
         "Content-Type": "application/json",
       },
-      body: JSON.stringify({
-        model: provider.model,
-        messages: messages.map(serializeMessage),
-        tools,
-        tool_choice: "auto",
-      }),
+      body: JSON.stringify(body),
     });
   } catch (cause) {
     const message = cause instanceof Error ? cause.message : String(cause);

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

@@ -23,6 +23,8 @@ export type RunBuiltinLoopOptions = {
   maxTurns: number;
   storageRoot: string;
   sessionId: string;
+  /** When true, do not provide tools — force LLM to emit text only. */
+  noTools: boolean;
 };
 
 export type RunBuiltinLoopResult = {
@@ -46,7 +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[],
@@ -68,70 +70,140 @@ async function executeTurnTools(
   return turnCount;
 }
 
+export type ShouldNudgeOptions = {
+  noTools: boolean;
+  text: string;
+  turn: number;
+  maxTurns: number;
+};
+
+export function shouldNudge({ noTools, text, turn, maxTurns }: ShouldNudgeOptions): boolean {
+  return !noTools && !text.trimStart().startsWith("---") && turn < maxTurns - 1;
+}
+
+async function handleTextTurn(
+  text: string,
+  turn: number,
+  noTools: boolean,
+  maxTurns: number,
+  storageRoot: string,
+  sessionId: string,
+  messages: ChatMessage[],
+): Promise<{ done: boolean; finalText: string }> {
+  await appendTurn(storageRoot, sessionId, {
+    role: "assistant",
+    content: text,
+    toolCalls: null,
+    reasoning: null,
+  });
+
+  if (shouldNudge({ noTools, text, turn, maxTurns })) {
+    log("7FXQM2KN", "text-only turn without frontmatter, nudging LLM to continue");
+    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 });
+    return { done: false, finalText: "" };
+  }
+
+  return { done: true, finalText: text };
+}
+
+async function handleToolTurn(
+  content: string,
+  toolCalls: LlmToolCall[],
+  toolCtx: ToolContext,
+  messages: ChatMessage[],
+  storageRoot: string,
+  sessionId: string,
+): Promise<number> {
+  await appendTurn(storageRoot, sessionId, {
+    role: "assistant",
+    content,
+    toolCalls: mapToolCallsForPayload(toolCalls),
+    reasoning: null,
+  });
+  return executeTurnTools(toolCalls, toolCtx, messages, storageRoot, sessionId);
+}
+
+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 "";
+}
+
+type LoopTurnResult = { done: boolean; finalText: string; extraTurns: number };
+
+async function runLoopTurn(
+  turn: number,
+  options: RunBuiltinLoopOptions,
+  messages: ChatMessage[],
+  openAiTools: ReturnType<typeof builtinToolsToOpenAi>,
+): Promise<LoopTurnResult> {
+  log("8K2M4N7P", `builtin loop turn ${turn + 1}/${options.maxTurns}`);
+  const response = await chatCompletionWithTools(
+    options.provider,
+    messages,
+    openAiTools.length > 0 ? openAiTools : null,
+  );
+
+  const effectiveToolCalls = options.noTools ? null : (response.toolCalls ?? null);
+  messages.push({ role: "assistant", content: response.content, tool_calls: effectiveToolCalls });
+
+  if (effectiveToolCalls === null || effectiveToolCalls.length === 0) {
+    const text = response.content ?? "";
+    const result = await handleTextTurn(
+      text,
+      turn,
+      options.noTools,
+      options.maxTurns,
+      options.storageRoot,
+      options.sessionId,
+      messages,
+    );
+    return { done: result.done, finalText: result.finalText, extraTurns: 0 };
+  }
+
+  const extra = await handleToolTurn(
+    response.content ?? "",
+    effectiveToolCalls,
+    options.toolCtx,
+    messages,
+    options.storageRoot,
+    options.sessionId,
+  );
+  return { done: false, finalText: "", extraTurns: extra };
+}
+
 /** 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 = builtinToolsToOpenAi(getBuiltinTools());
+  const openAiTools = options.noTools ? [] : builtinToolsToOpenAi(getBuiltinTools());
   let finalText = "";
   let turnCount = 0;
 
   for (let turn = 0; turn < options.maxTurns; turn++) {
-    log("8K2M4N7P", `builtin loop turn ${turn + 1}/${options.maxTurns}`);
-    const response = await chatCompletionWithTools(options.provider, messages, openAiTools);
-
-    const assistantMessage: ChatMessage = {
-      role: "assistant",
-      content: response.content,
-      tool_calls: response.toolCalls,
-    };
-    messages.push(assistantMessage);
-
-    if (response.toolCalls === null || response.toolCalls.length === 0) {
-      finalText = response.content ?? "";
-      await appendTurn(options.storageRoot, options.sessionId, {
-        role: "assistant",
-        content: response.content ?? "",
-        toolCalls: null,
-        reasoning: null,
-      });
-      turnCount += 1;
+    const result = await runLoopTurn(turn, options, messages, openAiTools);
+    turnCount += 1 + result.extraTurns;
+    if (result.done) {
+      finalText = result.finalText;
       break;
     }
-
-    // Assistant turn with tool calls
-    await appendTurn(options.storageRoot, options.sessionId, {
-      role: "assistant",
-      content: response.content ?? "",
-      toolCalls: mapToolCallsForPayload(response.toolCalls),
-      reasoning: null,
-    });
-    turnCount += 1;
-
-    // Execute tools
-    turnCount += await executeTurnTools(
-      response.toolCalls,
-      options.toolCtx,
-      messages,
-      options.storageRoot,
-      options.sessionId,
-    );
   }
 
   if (finalText === "" && messages.length > 0) {
-    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() !== ""
-      ) {
-        finalText = msg.content;
-        break;
-      }
-    }
+    finalText = extractFinalText(messages);
   }
 
   return { finalText, messages, turnCount };

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

@@ -63,10 +63,14 @@ export function buildBuiltinMessages(ctx: AgentContext): ChatMessage[] {
     "",
     "## 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.",
   );

packages/workflow-agent-kit/src/run.ts

@@ -121,6 +121,11 @@ export function createAgent(options: AgentOptions): () => Promise<void> {
 
     let agentResult = await runWithMessage("agent run failed", () => options.run(ctx));
 
+    // Preserve the primary detail from the first run — it contains the full
+    // tool-call turn history.  Continuation retries only fix frontmatter
+    // formatting and their 1-turn detail is not meaningful.
+    const primaryDetailHash = agentResult.detailHash;
+
     // Try to extract frontmatter; retry via continue if it fails
     let outputHash = await tryExtractOutput(agentResult.output, roleDef.frontmatter, ctx);
 
@@ -147,7 +152,7 @@ export function createAgent(options: AgentOptions): () => Promise<void> {
     const stepHash = await persistStep({
       ctx,
       outputHash,
-      detailHash: agentResult.detailHash,
+      detailHash: primaryDetailHash,
       agentName: agentLabel(options.name),
     });