fix(consult): record a tool call the tool never received

staging 手测 run 951a841e 第一次工具调用发出 tool.failed 后重试成功，但回执里
steps 只有 skill 与那次成功的 tool，stepBudget.used 为 2——失败的那次完全不存在。
客户端看见失败过一次，回执说没有，两边都查不到为什么。

工具的 inputSchema 是 strict 的，模型参数不合法时 Mastra 在调用 execute 之前就拒了，
于是工具体内一切都没跑：调用不计数、失败步不记录、连 chart-calculation 活动事件都没
发出（这也是本次定位的证据——失败那次没有任何 activity，重试那次有）。工具无法记录
一次它从未收到的调用。叠加两处：safeToolError 把非超时非取消的错误全塌成
calculation_failed，而即使失败落进工具体的 catch，consultationWorkflowFailureCode
对非 ConsultationWorkflowError 返回 undefined、append 处又写成可选省略，于是最需要
解释的那条记录恰好是唯一没有原因的记录。

改为在流层补记：流是唯一能观测到全部工具失败的位置，无论失败在 schema 这侧还是
execute 那侧，且它持有 startedAt 因而能给出时长。tool-error 分支比对「流已见的错误数」
与「state 里已有的失败 tool 步数」，只在前者更多时补一条，工具仍记录它能看见的失败，
两者不重复计。另新增 consultationToolFailureCode，令每个错误都解析出一个码。

failureCode 刻意仍不进公开回执：白名单与「the public receipt never carries the
internal failure classification」是刻意约束，workflow_rate_limited 这类后端内情不该
上线到客户端。原因走可观测日志的 toolCalls[].failureCode。客户端能看到「有一步失败」，
运维能在日志里看到为什么。

另记入 BUG-268 的线上实测值：单领域 referenceReads 两次均为 2，多领域为 0——不是
从不读方法，而是最需要方法的多领域路径一份都没打开。

Co-authored-by: Cursor <cursoragent@cursor.com>

frontend/tests/consultation-agentic-runtime.test.ts

@@ -9,6 +9,7 @@ import {
   canonicalDomainPlan,
   consultationModelStepTelemetry,
   consultationStepBudgetReceipt,
+  consultationToolFailureCode,
   createConsultationRuntimeHooks,
   createConsultationTools,
   createConsultationRuntimeState,
@@ -611,6 +612,75 @@ test("workflow failure codes classify transport and contract faults", () => {
   assert.equal(consultationWorkflowFailureCode(new Error("anything else")), undefined);
 });
 
+test("every tool failure resolves to a code, not an absent field", () => {
+  // The workflow classifier returns undefined for anything it does not own, and
+  // the append site omitted the field when it was undefined, so the failures
+  // raised inside the tool reached the log as the one record with no reason.
+  assert.equal(consultationToolFailureCode(new ConsultationWorkflowError("workflow_rate_limited", "x")), "workflow_rate_limited");
+  assert.equal(consultationToolFailureCode(new DOMException("stop", "AbortError")), "workflow_aborted");
+  assert.equal(consultationToolFailureCode(new Error("invalid_consultation_domain_plan")), "invalid_domain_plan");
+  assert.equal(consultationToolFailureCode(new Error("unsupported_consultation_domain")), "invalid_domain_plan");
+  assert.equal(consultationToolFailureCode(new Error("anything else")), "unexpected_error");
+  assert.equal(consultationToolFailureCode("not an error"), "unexpected_error");
+});
+
+test("a call rejected before the tool body runs still appears in the receipt", async () => {
+  // Observed on staging: the model's arguments were refused against the tool's
+  // strict input schema, so `execute` never ran. The client saw tool.failed
+  // while the receipt showed no failed step and the budget counted no call.
+  const state = createConsultationRuntimeState();
+  state.jyotishSkillLoaded = true;
+  appendConsultationRuntimeStep(state, { kind: "skill", name: "jyotish-vedic-astrology", status: "completed", durationMs: 370 });
+  async function* chunks() {
+    yield { type: "tool-call", payload: { toolCallId: "call-1", toolName: "run-jyotish-consultation" } };
+    yield { type: "tool-error", payload: { toolCallId: "call-1", toolName: "run-jyotish-consultation", error: new Error("bad arguments") } };
+  }
+  const response = streamAgentResponse({
+    runId: "run", requestId: "req", state, stream: chunks(), requireTool: true,
+    toolStatus: () => "blocked",
+    receipt: () => ({ ...receipt(state), steps: publicConsultationRuntimeSteps(state) }),
+    onError: () => {},
+  });
+  const events: unknown[] = [];
+  const parser = createNdjsonParser((event) => events.push(event));
+  parser.finish(await response.text());
+
+  const failedStep = state.steps.find((step) => step.kind === "tool" && step.status === "failed");
+  assert.equal(failedStep?.name, "run-jyotish-consultation");
+  assert.equal(failedStep?.failureCode, "tool_call_rejected");
+  assert.equal(consultationStepBudgetReceipt(state).used, 2);
+  // The client learns a step failed; the classification stays server-side.
+  const failed = events.find((event) => (event as { type?: string }).type === "run.failed") as {
+    receipt?: { steps: Array<{ status: string; name: string }> };
+  };
+  assert.deepEqual(failed.receipt?.steps.map((step) => step.status), ["completed", "failed"]);
+  assert.doesNotMatch(JSON.stringify(failed), /tool_call_rejected/);
+});
+
+test("a failure the tool already recorded is not recorded twice", async () => {
+  // The tool records what it can see, with the duration and cause it alone
+  // knows. The stream must only fill the gap, never double-count.
+  const state = createConsultationRuntimeState();
+  state.jyotishSkillLoaded = true;
+  appendConsultationRuntimeStep(state, {
+    kind: "tool", name: "run-jyotish-consultation", status: "failed", durationMs: 20936, failureCode: "workflow_queue_full",
+  });
+  async function* chunks() {
+    yield { type: "tool-call", payload: { toolCallId: "call-1", toolName: "run-jyotish-consultation" } };
+    yield { type: "tool-error", payload: { toolCallId: "call-1", toolName: "run-jyotish-consultation", error: new Error("boom") } };
+  }
+  const response = streamAgentResponse({
+    runId: "run", requestId: "req", state, stream: chunks(), requireTool: true,
+    toolStatus: () => "blocked",
+    receipt: () => ({ ...receipt(state), steps: publicConsultationRuntimeSteps(state) }),
+    onError: () => {},
+  });
+  await response.text();
+
+  assert.equal(state.steps.filter((step) => step.status === "failed").length, 1);
+  assert.equal(state.steps[0]?.failureCode, "workflow_queue_full");
+});
+
 test("the public receipt never carries the internal failure classification", () => {
   const state = createConsultationRuntimeState();
   appendConsultationRuntimeStep(state, {