test(skills): add debug chat timing and isolation probes

2026-06-26 07:24:20 +00:00 · 2026-06-25 13:34:30 +08:00
parent 7e36869494
commit 9b0f5b36f3
10 changed files with 1501 additions and 22 deletions
@@ -0,0 +1,203 @@
+#!/usr/bin/env node
+
+import { spawn } from "node:child_process";
+import { mkdir, readFile, writeFile } from "node:fs/promises";
+import { dirname, resolve } from "node:path";
+import { env } from "node:process";
+import {
+  appendLine,
+  ensureEvidence,
+  evidencePaths,
+  loadEnvFiles,
+  redact,
+  writeResult,
+} from "./lib/langbot-e2e.mjs";
+
+const caseId = "ensure-fake-provider-cross-pipelines";
+const DEFAULT_PIPELINE_A_NAME = "Agent QA Fake Provider Debug Chat A";
+const DEFAULT_PIPELINE_B_NAME = "Agent QA Fake Provider Debug Chat B";
+
+await loadEnvFiles();
+const paths = evidencePaths(caseId);
+await ensureEvidence(paths);
+
+const writeEnv = process.argv.includes("--write-env");
+const envLocalPath = resolve("skills/.env.local");
+const pipelineAName = env.LANGBOT_FAKE_PROVIDER_PIPELINE_A_NAME || DEFAULT_PIPELINE_A_NAME;
+const pipelineBName = env.LANGBOT_FAKE_PROVIDER_PIPELINE_B_NAME || DEFAULT_PIPELINE_B_NAME;
+
+const result = {
+  source: "setup_automation",
+  case_id: caseId,
+  run_id: paths.runId,
+  status: "fail",
+  reason: "",
+  pipeline_a: {
+    name: pipelineAName,
+    id: "",
+    url: "",
+  },
+  pipeline_b: {
+    name: pipelineBName,
+    id: "",
+    url: "",
+  },
+  fake_provider: {
+    url: "",
+    base_url: "",
+    pid: null,
+  },
+  wrote_env: false,
+  evidence: {
+    console_log: paths.consoleLog,
+    automation_result_json: paths.automationResultJson,
+    result_json: paths.resultJson,
+  },
+  evidence_collected: ["api_diagnostic", "filesystem"],
+};
+
+try {
+  if (pipelineAName === pipelineBName) {
+    throw new Error("LANGBOT_FAKE_PROVIDER_PIPELINE_A_NAME and LANGBOT_FAKE_PROVIDER_PIPELINE_B_NAME must be different.");
+  }
+
+  const setupA = await runPipelineSetup(pipelineAName, "A");
+  const setupB = await runPipelineSetup(pipelineBName, "B");
+  result.pipeline_a = {
+    name: setupA.pipeline_name || pipelineAName,
+    id: setupA.pipeline_id || "",
+    url: setupA.pipeline_url || "",
+  };
+  result.pipeline_b = {
+    name: setupB.pipeline_name || pipelineBName,
+    id: setupB.pipeline_id || "",
+    url: setupB.pipeline_url || "",
+  };
+  result.fake_provider = {
+    url: setupB.fake_provider?.url || setupA.fake_provider?.url || "",
+    base_url: setupB.fake_provider?.base_url || setupA.fake_provider?.base_url || "",
+    pid: setupB.fake_provider?.pid ?? setupA.fake_provider?.pid ?? null,
+  };
+
+  if (!result.pipeline_a.url || !result.pipeline_b.url || !result.fake_provider.url) {
+    throw new Error("Cross-pipeline fake provider setup did not return both pipeline URLs and provider URL.");
+  }
+
+  if (writeEnv) {
+    await upsertEnvLocal(envLocalPath, {
+      LANGBOT_FAKE_PROVIDER_URL: result.fake_provider.url,
+      LANGBOT_FAKE_PROVIDER_BASE_URL: result.fake_provider.base_url,
+      LANGBOT_FAKE_PROVIDER_PID: result.fake_provider.pid ? String(result.fake_provider.pid) : "",
+      LANGBOT_FAKE_PROVIDER_PIPELINE_A_URL: result.pipeline_a.url,
+      LANGBOT_FAKE_PROVIDER_PIPELINE_A_NAME: result.pipeline_a.name,
+      LANGBOT_FAKE_PROVIDER_PIPELINE_B_URL: result.pipeline_b.url,
+      LANGBOT_FAKE_PROVIDER_PIPELINE_B_NAME: result.pipeline_b.name,
+    });
+    result.wrote_env = true;
+  }
+
+  result.status = "pass";
+  result.reason = "Fake provider cross-pipeline fixtures are configured.";
+} catch (error) {
+  result.status = looksLikeEnvIssue(error) ? "env_issue" : "fail";
+  result.reason = safeReason(error.message);
+} finally {
+  await writeResult(paths, result);
+  console.log(JSON.stringify(result, null, 2));
+}
+
+process.exit(result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1);
+
+function runPipelineSetup(pipelineName, label) {
+  return new Promise((resolvePromise, rejectPromise) => {
+    const child = spawn(process.execPath, ["scripts/e2e/ensure-fake-provider-pipeline.mjs"], {
+      cwd: resolve("."),
+      env: {
+        ...env,
+        LANGBOT_FAKE_PROVIDER_PIPELINE_NAME: pipelineName,
+        LANGBOT_FAKE_PROVIDER_FIRST_TOKEN_DELAY_MS: env.LANGBOT_FAKE_PROVIDER_FIRST_TOKEN_DELAY_MS || "25",
+        LANGBOT_FAKE_PROVIDER_CHUNK_DELAY_MS: env.LANGBOT_FAKE_PROVIDER_CHUNK_DELAY_MS || "10",
+        LANGBOT_FAKE_PROVIDER_CHUNK_COUNT: env.LANGBOT_FAKE_PROVIDER_CHUNK_COUNT || "0",
+        LANGBOT_FAKE_PROVIDER_FAIL_FIRST_N: "0",
+        LANGBOT_FAKE_PROVIDER_FAIL_EVERY_N: "0",
+        LANGBOT_FAKE_PROVIDER_FAULT_STATUS: env.LANGBOT_FAKE_PROVIDER_FAULT_STATUS || "500",
+        LANGBOT_FAKE_PROVIDER_FAIL_AFTER_FIRST_CHUNK: "false",
+        LANGBOT_FAKE_PROVIDER_DYNAMIC_RESPONSE: "true",
+      },
+      stdio: ["ignore", "pipe", "pipe"],
+    });
+
+    let stdout = "";
+    let stderr = "";
+    child.stdout.on("data", (chunk) => {
+      const text = chunk.toString();
+      stdout += text;
+      appendLine(paths.consoleLog, `[setup ${label} stdout] ${text.trimEnd()}`).catch(() => {});
+    });
+    child.stderr.on("data", (chunk) => {
+      const text = chunk.toString();
+      stderr += text;
+      appendLine(paths.consoleLog, `[setup ${label} stderr] ${text.trimEnd()}`).catch(() => {});
+    });
+    child.on("error", rejectPromise);
+    child.on("close", (code) => {
+      const parsed = parseJsonOutput(stdout);
+      if (code !== 0 || parsed.status !== "pass") {
+        rejectPromise(new Error(parsed.reason || stderr || `Fake provider pipeline setup ${label} exited with ${code}.`));
+        return;
+      }
+      resolvePromise(parsed);
+    });
+  });
+}
+
+function parseJsonOutput(text) {
+  const trimmed = String(text || "").trim();
+  if (!trimmed) return {};
+  try {
+    return JSON.parse(trimmed);
+  } catch {
+    const start = trimmed.indexOf("{");
+    const end = trimmed.lastIndexOf("}");
+    if (start >= 0 && end > start) {
+      try {
+        return JSON.parse(trimmed.slice(start, end + 1));
+      } catch {
+        return {};
+      }
+    }
+    return {};
+  }
+}
+
+async function upsertEnvLocal(path, updates) {
+  await mkdir(dirname(path), { recursive: true });
+  let text = "";
+  try {
+    text = await readFile(path, "utf8");
+  } catch {
+    text = "";
+  }
+  const lines = text.split(/\r?\n/);
+  const seen = new Set();
+  const next = lines.map((line) => {
+    const trimmed = line.trim();
+    const match = trimmed.match(/^([A-Z][A-Z0-9_]*)=/);
+    if (!match || updates[match[1]] === undefined) return line;
+    seen.add(match[1]);
+    return `${match[1]}=${updates[match[1]]}`;
+  });
+  for (const [key, value] of Object.entries(updates)) {
+    if (!seen.has(key)) next.push(`${key}=${value}`);
+  }
+  await writeFile(path, `${next.join("\n").replace(/\n+$/, "")}\n`, "utf8");
+}
+
+function looksLikeEnvIssue(error) {
+  const message = String(error?.message || error || "");
+  return /fetch failed|ECONNREFUSED|ENOTFOUND|LANGBOT_.*not configured|Could not read recovery_key|Backend did not respond/i.test(message);
+}
+
+function safeReason(value) {
+  return redact(String(value || "")).slice(0, 1000);
+}
@@ -28,6 +28,8 @@ const recentRequests = [];

 const server = createServer(async (request, response) => {
  const startedAt = Date.now();
+  const startedPerf = performance.now();
+  let requestRecord = null;
  const url = new URL(request.url || "/", `http://${request.headers.host || `${host}:${port}`}`);
  try {
    if (request.method === "GET" && url.pathname === "/healthz") {
@@ -98,13 +100,24 @@ const server = createServer(async (request, response) => {
      const requestId = `chatcmpl-langbot-fake-${requestCount}`;
      const shouldFail = requestCount <= config.fail_first_n
        || (config.fail_every_n > 0 && requestCount % config.fail_every_n === 0);
-      recordRequest({
+      const replyText = responseTextForBody(body);
+      requestRecord = recordRequest({
        id: requestId,
+        request_number: requestCount,
        path: url.pathname,
        stream: Boolean(body.stream),
        model: body.model || "",
        message_count: Array.isArray(body.messages) ? body.messages.length : 0,
        should_fail: shouldFail,
+        status: "running",
+        http_status: null,
+        expected_text: replyText,
+        response_text_preview: previewText(replyText),
+        started_at: new Date(startedAt).toISOString(),
+        started_epoch_ms: startedAt,
+        configured_first_token_delay_ms: config.first_token_delay_ms,
+        configured_chunk_delay_ms: config.chunk_delay_ms,
+        configured_chunk_count: config.chunk_count,
      });

      if (shouldFail) {
@@ -116,17 +129,21 @@ const server = createServer(async (request, response) => {
            code: "fake_provider_fault",
          },
        });
+        finishRequestRecord(requestRecord, startedPerf, {
+          status: "http_fault",
+          http_status: config.fault_status,
+        });
        return;
      }

-      const replyText = responseTextForBody(body);
-
      if (body.stream) {
        await streamCompletion(response, {
          requestId,
          model: body.model || modelName,
          content: replyText,
          failAfterFirstChunk: config.fail_after_first_chunk,
+          requestRecord,
+          startedPerf,
        });
      } else {
        await sleep(config.first_token_delay_ms + config.chunk_delay_ms);
@@ -135,6 +152,13 @@ const server = createServer(async (request, response) => {
          model: body.model || modelName,
          content: replyText,
        }));
+        markRequestTiming(requestRecord, "first_chunk", startedPerf);
+        markRequestTiming(requestRecord, "first_content_chunk", startedPerf);
+        requestRecord.content_chunk_count = 1;
+        finishRequestRecord(requestRecord, startedPerf, {
+          status: "ok",
+          http_status: 200,
+        });
      }
      return;
    }
@@ -146,6 +170,13 @@ const server = createServer(async (request, response) => {
      },
    });
  } catch (error) {
+    if (requestRecord) {
+      finishRequestRecord(requestRecord, startedPerf, {
+        status: "fake_provider_error",
+        http_status: 500,
+        error: error instanceof Error ? error.message : String(error),
+      });
+    }
    sendJson(response, 500, {
      error: {
        message: error instanceof Error ? error.message : String(error),
@@ -264,7 +295,14 @@ function completionPayload({ requestId, model, content }) {
  };
 }

-async function streamCompletion(response, { requestId, model, content, failAfterFirstChunk: failMidStream }) {
+async function streamCompletion(response, {
+  requestId,
+  model,
+  content,
+  failAfterFirstChunk: failMidStream,
+  requestRecord,
+  startedPerf,
+}) {
  response.writeHead(200, {
    "content-type": "text/event-stream; charset=utf-8",
    "cache-control": "no-cache",
@@ -272,6 +310,7 @@ async function streamCompletion(response, { requestId, model, content, failAfter
  });

  await sleep(config.first_token_delay_ms);
+  markRequestTiming(requestRecord, "first_chunk", startedPerf);
  writeSse(response, {
    id: requestId,
    object: "chat.completion.chunk",
@@ -283,6 +322,8 @@ async function streamCompletion(response, { requestId, model, content, failAfter
  const chunks = splitContent(content);
  for (let index = 0; index < chunks.length; index += 1) {
    await sleep(config.chunk_delay_ms);
+    if (index === 0) markRequestTiming(requestRecord, "first_content_chunk", startedPerf);
+    requestRecord.content_chunk_count = (requestRecord.content_chunk_count || 0) + 1;
    writeSse(response, {
      id: requestId,
      object: "chat.completion.chunk",
@@ -291,6 +332,10 @@ async function streamCompletion(response, { requestId, model, content, failAfter
      choices: [{ index: 0, delta: { content: chunks[index] }, finish_reason: null }],
    });
    if (failMidStream && index === 0) {
+      finishRequestRecord(requestRecord, startedPerf, {
+        status: "mid_stream_disconnect",
+        http_status: 200,
+      });
      response.destroy(new Error("LangBot fake provider injected mid-stream disconnect"));
      return;
    }
@@ -312,6 +357,10 @@ async function streamCompletion(response, { requestId, model, content, failAfter
  });
  response.write("data: [DONE]\n\n");
  response.end();
+  finishRequestRecord(requestRecord, startedPerf, {
+    status: "ok",
+    http_status: 200,
+  });
 }

 function writeSse(response, payload) {
@@ -365,11 +414,48 @@ function flattenContent(content) {
 }

 function recordRequest(entry) {
-  recentRequests.push({
+  const item = {
    ...entry,
    at: new Date().toISOString(),
-  });
+    finished_at: null,
+    finished_epoch_ms: null,
+    duration_ms: null,
+    first_chunk_at: null,
+    first_chunk_epoch_ms: null,
+    first_chunk_ms: null,
+    first_content_chunk_at: null,
+    first_content_chunk_epoch_ms: null,
+    first_content_chunk_ms: null,
+    content_chunk_count: 0,
+  };
+  recentRequests.push(item);
  while (recentRequests.length > config.request_log_limit) recentRequests.shift();
+  return item;
+}
+
+function markRequestTiming(entry, key, startedPerf) {
+  if (!entry || entry[`${key}_at`]) return;
+  const now = Date.now();
+  entry[`${key}_at`] = new Date(now).toISOString();
+  entry[`${key}_epoch_ms`] = now;
+  entry[`${key}_ms`] = rounded(performance.now() - startedPerf);
+}
+
+function finishRequestRecord(entry, startedPerf, updates = {}) {
+  if (!entry || entry.finished_at) return;
+  const now = Date.now();
+  Object.assign(entry, updates);
+  entry.finished_at = new Date(now).toISOString();
+  entry.finished_epoch_ms = now;
+  entry.duration_ms = rounded(performance.now() - startedPerf);
+}
+
+function rounded(value) {
+  return Number(value.toFixed(3));
+}
+
+function previewText(value) {
+  return String(value || "").slice(0, 120);
 }

 function resetRequestState() {