Merge pull request 'fix(agent-claude-code): handle missing result line gracefully' (#576) from fix/574-silent-fail-handling into main

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

@@ -301,6 +301,179 @@ describe("storeClaudeCodeDetail", () => {
   });
 });
 
+describe("parseClaudeCodeStreamOutput — incomplete output (no result line)", () => {
+  test("Test 1.1: parses stream with turns but no result line", () => {
+    const lines = [
+      JSON.stringify({
+        type: "system",
+        subtype: "init",
+        session_id: "sess-incomplete-1",
+        model: "claude-sonnet-4.5",
+      }),
+      JSON.stringify({
+        type: "assistant",
+        message: {
+          role: "assistant",
+          content: [{ type: "text", text: "Starting work..." }],
+        },
+      }),
+      JSON.stringify({
+        type: "assistant",
+        message: {
+          role: "assistant",
+          content: [{ type: "text", text: "This is the last assistant message." }],
+        },
+      }),
+    ];
+    const stdout = lines.join("\n");
+    const parsed = parseClaudeCodeStreamOutput(stdout);
+
+    expect(parsed).not.toBeNull();
+    expect(parsed!.subtype).toBe("incomplete");
+    expect(parsed!.result).toBe("This is the last assistant message.");
+    expect(parsed!.sessionId).toBe("sess-incomplete-1");
+    expect(parsed!.model).toBe("claude-sonnet-4.5");
+    expect(parsed!.turns).toHaveLength(2);
+    expect(parsed!.stopReason).toBe("incomplete_no_result_line");
+    expect(parsed!.numTurns).toBe(2);
+    expect(parsed!.durationMs).toBe(0);
+    expect(parsed!.totalCostUsd).toBe(0);
+  });
+
+  test("Test 1.2: parses stream with no turns and no result line", () => {
+    const lines = [
+      JSON.stringify({
+        type: "system",
+        session_id: "sess-no-turns",
+        model: "claude-opus-4",
+      }),
+    ];
+    const stdout = lines.join("\n");
+    const parsed = parseClaudeCodeStreamOutput(stdout);
+
+    expect(parsed).not.toBeNull();
+    expect(parsed!.subtype).toBe("incomplete");
+    expect(parsed!.result).toBe("");
+    expect(parsed!.sessionId).toBe("sess-no-turns");
+    expect(parsed!.model).toBe("claude-opus-4");
+    expect(parsed!.turns).toHaveLength(0);
+    expect(parsed!.stopReason).toBe("incomplete_no_result_line");
+  });
+
+  test("Test 1.3: returns null for completely empty output", () => {
+    const parsed1 = parseClaudeCodeStreamOutput("");
+    expect(parsed1).toBeNull();
+
+    const parsed2 = parseClaudeCodeStreamOutput("   \n  \n  ");
+    expect(parsed2).toBeNull();
+  });
+
+  test("Test 1.4: returns null for malformed JSON lines only", () => {
+    const stdout = "not json\n{broken json\n[invalid";
+    const parsed = parseClaudeCodeStreamOutput(stdout);
+    expect(parsed).toBeNull();
+  });
+
+  test("Test 6.1: extracts from last assistant text-only turn", () => {
+    const lines = [
+      JSON.stringify({ type: "system", session_id: "s1", model: "test" }),
+      JSON.stringify({
+        type: "assistant",
+        message: { role: "assistant", content: [{ type: "text", text: "First message" }] },
+      }),
+      JSON.stringify({
+        type: "assistant",
+        message: { role: "assistant", content: [{ type: "text", text: "Last message" }] },
+      }),
+    ];
+    const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
+    expect(parsed).not.toBeNull();
+    expect(parsed!.result).toBe("Last message");
+  });
+
+  test("Test 6.2: extracts from last assistant turn with tool calls", () => {
+    const lines = [
+      JSON.stringify({ type: "system", session_id: "s1", model: "test" }),
+      JSON.stringify({
+        type: "assistant",
+        message: {
+          role: "assistant",
+          content: [
+            { type: "text", text: "Text with tools" },
+            { type: "tool_use", name: "Bash", input: { command: "ls" } },
+          ],
+        },
+      }),
+    ];
+    const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
+    expect(parsed).not.toBeNull();
+    expect(parsed!.result).toBe("Text with tools");
+  });
+
+  test("Test 6.3: returns empty string when no assistant turns", () => {
+    const lines = [JSON.stringify({ type: "system", session_id: "s1", model: "test" })];
+    const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
+    expect(parsed).not.toBeNull();
+    expect(parsed!.result).toBe("");
+  });
+
+  test("Test 6.4: extracts from most recent assistant turn before tool_result", () => {
+    const lines = [
+      JSON.stringify({ type: "system", session_id: "s1", model: "test" }),
+      JSON.stringify({
+        type: "assistant",
+        message: { role: "assistant", content: [{ type: "text", text: "Before tool call" }] },
+      }),
+      JSON.stringify({
+        type: "user",
+        message: { role: "user", content: [{ type: "tool_result", content: "tool output" }] },
+      }),
+    ];
+    const parsed = parseClaudeCodeStreamOutput(lines.join("\n"));
+    expect(parsed).not.toBeNull();
+    expect(parsed!.result).toBe("Before tool call");
+  });
+});
+
+describe("storeClaudeCodeDetail — incomplete results", () => {
+  test("Test 4.1: stores incomplete result as detail", async () => {
+    const store = createMemoryStore();
+    const incompleteParsed: ClaudeCodeParsedResult = {
+      type: "result",
+      subtype: "incomplete",
+      result: "Partial output",
+      sessionId: "sess-incomplete",
+      numTurns: 2,
+      totalCostUsd: 0,
+      durationMs: 0,
+      model: "claude-sonnet-4.5",
+      stopReason: "incomplete_no_result_line",
+      usage: {
+        inputTokens: 0,
+        outputTokens: 0,
+        cacheReadInputTokens: 0,
+        cacheCreationInputTokens: 0,
+      },
+      turns: [
+        { index: 0, role: "assistant", content: "Turn 1", toolCalls: null },
+        { index: 1, role: "assistant", content: "Partial output", toolCalls: null },
+      ],
+    };
+
+    const { detailHash, output, sessionId } = await storeClaudeCodeDetail(store, incompleteParsed);
+
+    expect(detailHash).toHaveLength(13);
+    expect(output).toBe("Partial output");
+    expect(sessionId).toBe("sess-incomplete");
+
+    const node = await store.get(detailHash);
+    expect(node).not.toBeNull();
+    expect(node!.payload.subtype).toBe("incomplete");
+    expect(node!.payload.stopReason).toBe("incomplete_no_result_line");
+    expect(node!.payload.turns).toHaveLength(2);
+  });
+});
+
 describe("storeClaudeCodeRawOutput", () => {
   test("stores raw text when JSON parsing fails", async () => {
     const store = createMemoryStore();

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

@@ -48,7 +48,9 @@ export function buildClaudeCodePrompt(ctx: AgentContext): string {
   return parts.join("\n");
 }
 
-function spawnClaude(args: string[]): Promise<{ stdout: string; stderr: string }> {
+function spawnClaude(
+  args: string[],
+): Promise<{ stdout: string; stderr: string; exitCode: number | null }> {
   return new Promise((resolve, reject) => {
     const child = spawn(CLAUDE_COMMAND, args, {
       env: process.env,
@@ -72,7 +74,7 @@ function spawnClaude(args: string[]): Promise<{ stdout: string; stderr: string }
 
     child.on("close", (code) => {
       if (code === 0) {
-        resolve({ stdout, stderr });
+        resolve({ stdout, stderr, exitCode: code });
         return;
       }
       const detail = stderr.trim() !== "" ? ` stderr=${stderr.trim()}` : "";
@@ -81,7 +83,9 @@ function spawnClaude(args: string[]): Promise<{ stdout: string; stderr: string }
   });
 }
 
-function spawnClaudeRun(prompt: string): Promise<{ stdout: string; stderr: string }> {
+function spawnClaudeRun(
+  prompt: string,
+): Promise<{ stdout: string; stderr: string; exitCode: number | null }> {
   const args = [
     "-p",
     prompt,
@@ -101,7 +105,7 @@ function spawnClaudeRun(prompt: string): Promise<{ stdout: string; stderr: strin
 function spawnClaudeResume(
   sessionId: string,
   message: string,
-): Promise<{ stdout: string; stderr: string }> {
+): Promise<{ stdout: string; stderr: string; exitCode: number | null }> {
   const args = [
     "-p",
     message,
@@ -122,6 +126,8 @@ function spawnClaudeResume(
 
 async function processClaudeOutput(
   stdout: string,
+  stderr: string,
+  exitCode: number | null,
   store: Store,
   assembledPrompt: string,
 ): Promise<AgentRunResult> {
@@ -129,11 +135,25 @@ async function processClaudeOutput(
 
   if (parsed !== null) {
     const { detailHash, output, sessionId } = await storeClaudeCodeDetail(store, parsed);
+
+    // Log incomplete results for visibility
+    if (parsed.subtype === "incomplete") {
+      log(
+        "7NQW8R4P",
+        `Claude Code exited with incomplete output (no result line). Exit code: ${exitCode ?? "null"}, stderr: ${stderr.slice(0, 200)}`,
+      );
+    }
+
     return { output, detailHash, sessionId, assembledPrompt };
   }
 
+  // Truly unparseable output - provide enhanced error message
+  const exitInfo = exitCode !== null && exitCode !== 0 ? `Exit code: ${exitCode}\n` : "";
+  const stderrInfo = stderr.trim() !== "" ? `Stderr: ${stderr.slice(0, 200)}\n` : "";
+  const stdoutSnippet = stdout.slice(0, 200);
+
   throw new Error(
-    `Claude Code returned unparseable output (first 200 chars): ${stdout.slice(0, 200)}`,
+    `Claude Code exited without producing parseable output.\n${exitInfo}${stderrInfo}Stdout (first 200 chars): ${stdoutSnippet}`,
   );
 }
 
@@ -147,8 +167,8 @@ async function runClaudeCode(ctx: AgentContext): Promise<AgentRunResult> {
     const cachedSessionId = await getCachedSessionId("claude-code", ctx.threadId, ctx.role);
     if (cachedSessionId !== null) {
       try {
-        const { stdout } = await spawnClaudeResume(cachedSessionId, fullPrompt);
-        const result = await processClaudeOutput(stdout, ctx.store, fullPrompt);
+        const { stdout, stderr, exitCode } = await spawnClaudeResume(cachedSessionId, fullPrompt);
+        const result = await processClaudeOutput(stdout, stderr, exitCode, ctx.store, fullPrompt);
         if (result.sessionId !== undefined && result.sessionId !== "") {
           await setCachedSessionId("claude-code", ctx.threadId, ctx.role, result.sessionId);
         }
@@ -162,8 +182,8 @@ async function runClaudeCode(ctx: AgentContext): Promise<AgentRunResult> {
     }
   }
 
-  const { stdout } = await spawnClaudeRun(fullPrompt);
-  const result = await processClaudeOutput(stdout, ctx.store, fullPrompt);
+  const { stdout, stderr, exitCode } = await spawnClaudeRun(fullPrompt);
+  const result = await processClaudeOutput(stdout, stderr, exitCode, ctx.store, fullPrompt);
   if (result.sessionId !== undefined && result.sessionId !== "") {
     await setCachedSessionId("claude-code", ctx.threadId, ctx.role, result.sessionId);
   }
@@ -175,8 +195,8 @@ async function continueClaudeCode(
   message: string,
   store: Store,
 ): Promise<AgentRunResult> {
-  const { stdout } = await spawnClaudeResume(sessionId, message);
-  return processClaudeOutput(stdout, store, "");
+  const { stdout, stderr, exitCode } = await spawnClaudeResume(sessionId, message);
+  return processClaudeOutput(stdout, stderr, exitCode, store, "");
 }
 
 /** Agent CLI factory: parses argv, runs Claude Code, extracts output, writes StepNode. */

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

@@ -71,6 +71,7 @@ type ParseState = {
   turns: ClaudeCodeTurnPayload[];
   resultLine: Record<string, unknown> | null;
   model: string;
+  sessionId: string;
   turnIndex: number;
 };
 
@@ -78,6 +79,9 @@ function processSystemLine(parsed: Record<string, unknown>, state: ParseState):
   if (typeof parsed.model === "string") {
     state.model = parsed.model;
   }
+  if (typeof parsed.session_id === "string") {
+    state.sessionId = parsed.session_id;
+  }
 }
 
 function processAssistantLine(parsed: Record<string, unknown>, state: ParseState): void {
@@ -124,8 +128,52 @@ function processLine(line: string, state: ParseState): void {
   else if (type === "result") state.resultLine = parsed;
 }
 
+/**
+ * Extract output text from the last assistant turn.
+ * Used for best-effort extraction when no result line is present.
+ */
+function extractLastAssistantContent(turns: ClaudeCodeTurnPayload[]): string {
+  for (let i = turns.length - 1; i >= 0; i--) {
+    const turn = turns[i];
+    if (turn !== undefined && turn.role === "assistant" && turn.content !== "") {
+      return turn.content;
+    }
+  }
+  return "";
+}
+
 function assembleResult(state: ParseState): ClaudeCodeParsedResult | null {
-  if (state.resultLine === null) return null;
+  // Handle incomplete result (no result line)
+  if (state.resultLine === null) {
+    // Need at least a session_id from system line to be parseable
+    if (state.sessionId === "") {
+      return null;
+    }
+
+    // Best-effort extraction: get output from last assistant turn
+    const result = extractLastAssistantContent(state.turns);
+
+    return {
+      type: "result",
+      subtype: "incomplete",
+      result,
+      sessionId: state.sessionId,
+      numTurns: state.turns.length,
+      totalCostUsd: 0,
+      durationMs: 0,
+      model: state.model,
+      stopReason: "incomplete_no_result_line",
+      usage: {
+        inputTokens: 0,
+        outputTokens: 0,
+        cacheReadInputTokens: 0,
+        cacheCreationInputTokens: 0,
+      },
+      turns: state.turns,
+    };
+  }
+
+  // Handle complete result (has result line)
   const sessionId = state.resultLine.session_id;
   const result = state.resultLine.result;
   const subtype = state.resultLine.subtype;
@@ -159,7 +207,13 @@ function assembleResult(state: ParseState): ClaudeCodeParsedResult | null {
  */
 export function parseClaudeCodeStreamOutput(stdout: string): ClaudeCodeParsedResult | null {
   const lines = stdout.trim().split("\n");
-  const state: ParseState = { turns: [], resultLine: null, model: "", turnIndex: 0 };
+  const state: ParseState = {
+    turns: [],
+    resultLine: null,
+    model: "",
+    sessionId: "",
+    turnIndex: 0,
+  };
   for (const line of lines) {
     processLine(line, state);
   }

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

@@ -1,4 +1,4 @@
-export type ClaudeCodeResultSubtype = "success" | "error_max_turns" | "error_budget";
+export type ClaudeCodeResultSubtype = "success" | "error_max_turns" | "error_budget" | "incomplete";
 
 /** A single tool call within an assistant turn. */
 export type ClaudeCodeToolCall = {