@librechat/agents 3.4.7 → 3.5.0

package/src/scripts/abort.ts

@@ -1,157 +0,0 @@
-/* eslint-disable no-console */
-// src/scripts/cli.ts
-import { config } from 'dotenv';
-config();
-import { HumanMessage, BaseMessage } from '@langchain/core/messages';
-import type * as t from '@/types';
-import { ChatModelStreamHandler, createContentAggregator } from '@/stream';
-import { ToolEndHandler } from '@/events';
-
-import { getArgs } from '@/scripts/args';
-import { Run } from '@/run';
-import { GraphEvents, Callback } from '@/common';
-import { getLLMConfig } from '@/utils/llmConfig';
-
-const conversationHistory: BaseMessage[] = [];
-
-async function testStandardStreaming(): Promise<void> {
-  const { userName, location, provider, currentDate } = await getArgs();
-  const { contentParts, aggregateContent } = createContentAggregator();
-  const controller = new AbortController();
-
-  const customHandlers = {
-    [GraphEvents.TOOL_END]: new ToolEndHandler(),
-    [GraphEvents.CHAT_MODEL_STREAM]: new ChatModelStreamHandler(),
-    [GraphEvents.ON_RUN_STEP_COMPLETED]: {
-      handle: (
-        event: GraphEvents.ON_RUN_STEP_COMPLETED,
-        data: t.StreamEventData
-      ): void => {
-        console.log('====== ON_RUN_STEP_COMPLETED ======');
-        aggregateContent({
-          event,
-          data: data as unknown as { result: t.ToolEndEvent },
-        });
-      },
-    },
-    [GraphEvents.ON_RUN_STEP]: {
-      handle: (
-        event: GraphEvents.ON_RUN_STEP,
-        data: t.StreamEventData
-      ): void => {
-        console.log('====== ON_RUN_STEP ======');
-        console.dir(data, { depth: null });
-        aggregateContent({ event, data: data as t.RunStep });
-      },
-    },
-    [GraphEvents.ON_RUN_STEP_DELTA]: {
-      handle: (
-        event: GraphEvents.ON_RUN_STEP_DELTA,
-        data: t.StreamEventData
-      ): void => {
-        console.log('====== ON_RUN_STEP_DELTA ======');
-        console.dir(data, { depth: null });
-        aggregateContent({ event, data: data as t.RunStepDeltaEvent });
-      },
-    },
-    [GraphEvents.ON_MESSAGE_DELTA]: {
-      handle: (
-        event: GraphEvents.ON_MESSAGE_DELTA,
-        data: t.StreamEventData
-      ): void => {
-        console.log('====== ON_MESSAGE_DELTA ======');
-        console.dir(data, { depth: null });
-        aggregateContent({ event, data: data as t.MessageDeltaEvent });
-      },
-    },
-    [GraphEvents.TOOL_START]: {
-      handle: (
-        _event: string,
-        data: t.StreamEventData,
-        metadata?: Record<string, unknown>
-      ): void => {
-        console.log('====== TOOL_START ======');
-      },
-    },
-  };
-
-  const llmConfig = getLLMConfig(provider);
-  const signal = controller.signal;
-  const run = await Run.create<t.IState>({
-    runId: 'test-run-id',
-    graphConfig: {
-      type: 'standard',
-      signal,
-      llmConfig,
-      tools: [],
-      instructions:
-        'You are a friendly AI assistant. Always address the user by their name.',
-      additional_instructions: `The user's name is ${userName} and they are located in ${location}.`,
-    },
-    customHandlers,
-  });
-
-  const config = {
-    configurable: {
-      provider,
-      thread_id: 'conversation-num-1',
-    },
-    signal,
-    streamMode: 'values',
-    version: 'v2' as const,
-  };
-
-  console.log('Test 1: Weather query (content parts test)');
-
-  const userMessage = `
-  Make a search for the weather in ${location} today, which is ${currentDate}.
-  Make sure to always refer to me by name, which is ${userName}.
-  After giving me a thorough summary, tell me a joke about the weather forecast we went over.
-  `;
-
-  conversationHistory.push(new HumanMessage(userMessage));
-
-  const inputs = {
-    messages: conversationHistory,
-  };
-
-  // Set a timeout to abort the operation after 5 seconds
-  setTimeout(() => {
-    controller.abort();
-    console.log('Operation aborted');
-    console.log('Current content parts:');
-    console.dir(contentParts, { depth: null });
-  }, 4000);
-
-  try {
-    const finalContentParts = await run.processStream(inputs, config);
-    const finalMessages = run.getRunMessages();
-    if (finalMessages) {
-      conversationHistory.push(...finalMessages);
-      console.dir(conversationHistory, { depth: null });
-    }
-    console.dir(finalContentParts, { depth: null });
-  } catch (error) {
-    if ((error as Error)?.name === 'AbortError') {
-      console.log('Operation was aborted');
-    } else {
-      console.error('An error occurred:', error);
-    }
-  }
-
-  console.log('\n\n====================\n\n');
-  console.dir(contentParts, { depth: null });
-}
-
-process.on('unhandledRejection', (reason, promise) => {
-  console.error('Unhandled Rejection at:', promise, 'reason:', reason);
-  console.log('Conversation history:');
-  process.exit(1);
-});
-
-testStandardStreaming().catch((err) => {
-  console.error(err);
-  console.log('Conversation history:');
-  console.dir(conversationHistory, { depth: null });
-  process.exit(1);
-});

package/src/scripts/activity-labels/captured.json

@@ -1,56 +0,0 @@
-[
-  {
-    "id": "sandbox-python-version",
-    "traceId": "eeab6f47000fe2a6aac76cde6bbc67fd",
-    "prompt": "Reasoning excerpts:\n- I'll work through each check methodically, running them one at a time and documenting what I find.\n\nTool calls:\n- run_tools_with_bash({\"code\":\"python3 --version\"}) → stdout:\nPython 3.14.4\n\nLabel:",
-    "productionLabel": "Confirmed Python 3.14.4 is installed"
-  },
-  {
-    "id": "mnt-data-write-test",
-    "traceId": "8ee41468850d42e5477af07759519e84",
-    "prompt": "Intent (assistant's last message): **Python version: 3.14.4**\n\nNow let's check if files in /mnt/data survive between calls.\n\nTool calls:\n- bash_tool({\"command\":\"echo \\\"hello from probe 1, written at $(date)\\\" > /mnt/data/persist_test.txt; cat /mnt/data/persist_test.txt\"}) → stdout:\nhello from probe 1, written at Wed Jul 29 11:30:09 AM UTC 2026\n\nLabel:",
-    "productionLabel": "Wrote test file to /mnt/data, confirmed persistence"
-  },
-  {
-    "id": "mnt-data-persistence",
-    "traceId": "64b318bd7251b66baccd75009d947682",
-    "prompt": "Intent (assistant's last message): **Python version: 3.14.4**\n\nNow let's check if files in /mnt/data survive between calls.\n\nReasoning excerpts:\n- I should make a second request to verify the behavior persists across multiple calls.\n\nTool calls:\n- bash_tool({\"command\":\"ls -la /mnt/data/persist_test.txt && cat /mnt/data/persist_test.txt\"}) → stdout:\n-rw------- 1 65534 65534 63 Jul 29 11:30 /mnt/data/persist_test.txt\nhello from probe 1, written at Wed Jul 29 11:30:09 AM UTC 2026\n\nLabel:",
-    "productionLabel": "Confirmed /mnt/data persists between tool calls"
-  },
-  {
-    "id": "mnt-data-tmpfs",
-    "traceId": "bff7f9766cc2916230403a04c47c92af",
-    "prompt": "Intent (assistant's last message): **Files in /mnt/data DO survive between calls** — the file I wrote in the previous, separate sandbox invocation is still there with its original content intact.\n\nNow let's check RAM and disk.\n\nTool calls:\n- bash_tool({\"command\":\"echo \\\"=== MEMORY ===\\\"; free -h; echo; echo \\\"=== DISK ===\\\"; df -h /mnt/data / /tmp 2>/dev/null\"}) → stdout:\n=== MEMORY ===\n\n=== DISK ===\nFilesystem      Size  Used Avail Use% Mounted on\ntmpfs           1.0G   32K  1.0G   1% /mnt/data\nnone             16M     0   16M   0% /\nnone             20M     0   20M   0% /tmp\n\nstderr:\nfree: Unable to create meminfo structure\nNote: /tmp files are same-call scratch only and were not persisted; use /mnt/data for files needed later.\n\nLabel:",
-    "productionLabel": "Confirmed /mnt/data is tmpfs with 1GB capacity"
-  },
-  {
-    "id": "cpu-meminfo-disk",
-    "traceId": "6faf26136e125c29fe0bae7ddd87c59e",
-    "prompt": "Intent (assistant's last message): `free` failed, let me try /proc/meminfo directly — and note disk is quite constrained (tmpfs-based, tiny root/tmp).\n\nTool calls:\n- bash_tool({\"command\":\"echo \\\"=== /proc/meminfo ===\\\"; cat /proc/meminfo 2>/dev/null | head -5\\necho\\necho \\\"=== nproc ===\\\"; nproc\\necho\\necho \\\"=== /proc/cpuinfo count ===\\\"; grep -c ^processor /proc/cpuinfo 2>/dev/null\\necho\\necho \\\"=== disk full df ===\\\"; df -h 2>/dev/null\"}) → stdout:\n=== /proc/meminfo ===\n\n=== nproc ===\n1\n\n=== /proc/cpuinfo count ===\n0\n\n=== disk full df ===\nFilesystem      Size  Used Avail Use% Mounted on\nnone             16M     0   16M   0% /\n/dev/vdc         16G  4.4G   11G  30% /usr\nnone             16M  4.0K   16M   1% /etc/hosts\ntmpfs            64M     0   64M   0% /dev/null\nnone             20M     0   20M   0% /tmp\ntmpfs           1.0G   32K  1.0G   1% /mnt/data\n\nLabel:",
-    "productionLabel": "Confirmed single CPU, /proc/meminfo empty, disk constrained with 16M root and 20M tmp"
-  },
-  {
-    "id": "rlimit-cgroup",
-    "traceId": "2797232991aa7e841081a6b6175bd62b",
-    "prompt": "Intent (assistant's last message): `/proc/meminfo` is empty/restricted, but I can check cgroup limits for a real memory figure.\n\nTool calls:\n- bash_tool({\"command\":\"echo \\\"=== cgroup memory limit ===\\\"\\nfor f in /sys/fs/cgroup/memory.max /sys/fs/cgroup/memory/memory.limit_in_bytes; do\\n  [ -f \\\"$f\\\" ] && echo \\\"$f: $(cat $f)\\\"\\ndone\\necho\\necho \\\"=== cgroup cpu ===\\\"\\nfor f in /sys/fs/cgroup/cpu.max /sys/fs/cgroup/cpu/cpu.cfs_quota_us; do\\n  [ -f \\\"$f\\\" ] && echo \\\"$f: $(cat $f)\\\"\\ndone\\necho\\npython3 -c \\\"import resource; print('soft/hard RLIMIT_AS:', resource.getrlimit(resource.RLIMIT_AS))\\\" 2>/dev/null\"}) → stdout:\n=== cgroup memory limit ===\n\n=== cgroup cpu ===\n\nsoft/hard RLIMIT_AS: (17179869184, 17179869184)\n\nLabel:",
-    "productionLabel": "Found RLIMIT_AS ceiling at 16GB, cgroup limits unavailable"
-  },
-  {
-    "id": "network-tools",
-    "traceId": "e813a6ee932da05d573ced56424265b8",
-    "prompt": "Intent (assistant's last message): No cgroup files readable, but RLIMIT_AS shows a **16 GiB address-space limit** — likely the effective memory ceiling. Now let's check network access.\n\nTool calls:\n- bash_tool({\"command\":\"echo \\\"=== ping ===\\\"; timeout 3 ping -c1 8.8.8.8 2>&1\\necho\\necho \\\"=== curl ===\\\"; timeout 5 curl -sS -o /dev/null -w \\\"HTTP_CODE:%{http_code}\\\\n\\\" https://www.google.com 2>&1\\necho\\necho \\\"=== curl example.com ===\\\"; timeout 5 curl -sS -o /dev/null -w \\\"HTTP_CODE:%{http_code}\\\\n\\\" http://example.com 2>&1\\necho\\necho \\\"=== DNS resolution ===\\\"; timeout 3 getent hosts google.com 2>&1\"}) → stdout:\n=== ping ===\ntimeout: failed to run command ‘ping’: No such file or directory\n\n=== curl ===\ntimeout: failed to run command ‘curl’: No such file or directory\n\n=== curl example.com ===\ntimeout: failed to run command ‘curl’: No such file or directory\n\n=== DNS resolution ===\n\nLabel:",
-    "productionLabel": "Network tools unavailable, DNS resolution failed"
-  },
-  {
-    "id": "dns-tcp",
-    "traceId": "d96b49502c4a0ecb4c9325c2e74b43bf",
-    "prompt": "Intent (assistant's last message): No curl/ping binaries — let me test connectivity directly via Python sockets/urllib instead.\n\nTool calls:\n- bash_tool({\"command\":\"python3 - <<'EOF'\\nimport socket, urllib.request, time\\n\\n# DNS test\\ntry:\\n    ip = socket.gethostbyname(\\\"example.com\\\")\\n    print(\\\"DNS resolution OK:\\\", ip)\\nexcept Exception as e:\\n    print(\\\"DNS resolution FAILED:\\\", repr(e))\\n\\n# raw TCP connect test\\ntry:\\n    s = socket.create_connection((\\\"8.8.8.8\\\", 53), timeout=4)\\n    print(\\\"TCP connect to 8.8.8.8:53 OK\\\")\\n    s.close()\\nexcept Exception as e:\\n    print(\\\"TCP connect FAILED:\\\", repr(e))\\n\\n# HTTP fetch test\\ntry:\\n    t0 = time.time()\\n    r = urllib.request.urlopen(\\\"http://example.com\\\", timeout=5)\\n    print(\\…) → stdout:\nDNS resolution FAILED: gaierror(-2, 'Name or service not known')\nTCP connect FAILED: PermissionError(1, 'Operation not permitted')\nHTTP fetch FAILED: URLError(gaierror(-3, 'Temporary failure in name resolution'))\n\nLabel:",
-    "productionLabel": "DNS and TCP connectivity both blocked or unavailable"
-  },
-  {
-    "id": "python-packages",
-    "traceId": "a6fcd0fd40b490285ced22c236023e2c",
-    "prompt": "Intent (assistant's last message): **No network access** — DNS resolution fails and raw TCP connections are blocked with a permission error. This sandbox is fully network-isolated.\n\nNow let's check for numpy/pandas/scipy/torch.\n\nTool calls:\n- bash_tool({\"command\":\"python3 - <<'EOF'\\nmods = [\\\"numpy\\\", \\\"pandas\\\", \\\"scipy\\\", \\\"torch\\\"]\\nfor m in mods:\\n    try:\\n        mod = __import__(m)\\n        ver = getattr(mod, \\\"__version__\\\", \\\"unknown\\\")\\n        print(f\\\"{m}: INSTALLED, version {ver}\\\")\\n    except ImportError as e:\\n        print(f\\\"{m}: NOT INSTALLED ({e})\\\")\\nEOF\"}) → stdout:\nnumpy: INSTALLED, version 2.4.6\npandas: INSTALLED, version 2.3.3\nscipy: INSTALLED, version 1.18.0\ntorch: NOT INSTALLED (No module named 'torch')\n\nLabel:",
-    "productionLabel": "Confirmed numpy, pandas, scipy installed; torch unavailable"
-  }
-]

package/src/scripts/activity-labels/checks.cjs

@@ -1,205 +0,0 @@
-/**
- * Mechanical label checks. These catch format violations and the two
- * measurable prose failures (register collapse via first-word tallies,
- * cross-batch redundancy via content-word overlap); commit-log READABILITY
- * still needs the human pass over results/latest.md.
- *
- * Ported from LibreChat #14527 with two divergences, both backport
- * candidates for LibreChat's scripts/activity-labels/checks.js: tool-echo
- * matching normalizes namespaced MCP names (see the candidate-set comment
- * below), and COUNT_ECHO also catches spelled-out counts.
- */
-const STOPWORDS = new Set([
-  'the',
-  'a',
-  'an',
-  'to',
-  'of',
-  'and',
-  'or',
-  'with',
-  'for',
-  'in',
-  'on',
-  'at',
-  'is',
-  'are',
-  'was',
-  'were',
-  'be',
-  'been',
-  'it',
-  'its',
-  'as',
-  'by',
-  'from',
-  'that',
-  'this',
-  'both',
-  'all',
-  'no',
-  'not',
-  'via',
-]);
-
-function words(label) {
-  return label.trim().split(/\s+/).filter(Boolean);
-}
-
-const SUFFIXES = [
-  'ations',
-  'ation',
-  'ence',
-  'ance',
-  'ings',
-  'ing',
-  'ed',
-  'es',
-  's',
-];
-
-/** Crude suffix stemmer so persists/persistence/persisted collide — enough
- *  for overlap detection; linguistic correctness is not the goal. */
-function stem(word) {
-  if (word.length < 5) {
-    return word;
-  }
-  for (const suffix of SUFFIXES) {
-    if (word.endsWith(suffix) && word.length - suffix.length >= 4) {
-      return word.slice(0, word.length - suffix.length);
-    }
-  }
-  return word;
-}
-
-function contentWords(label) {
-  return words(label.toLowerCase().replace(/[^a-z0-9/._-]+/g, ' '))
-    .filter((word) => !STOPWORDS.has(word))
-    .map(stem);
-}
-
-/** Payload tokens carry the informative delta between template-shaped
- *  labels: numbers, versions, paths, filenames. */
-function isPayload(word) {
-  return /\d/.test(word) || word.includes('/') || word.includes('.');
-}
-
-function jaccard(a, b) {
-  const setA = new Set(a);
-  const setB = new Set(b);
-  if (setA.size === 0 || setB.size === 0) {
-    return 0;
-  }
-  let intersection = 0;
-  for (const word of setA) {
-    if (setB.has(word)) {
-      intersection += 1;
-    }
-  }
-  return intersection / (setA.size + setB.size - intersection);
-}
-
-const GENERIC_OPENER = /^(ran|used|executed|called|invoked|performed)\b/i;
-/** Digits or the spelled-out counts a label-length line can fit — the
- *  instruction forbids counting calls either way. */
-const COUNT_ECHO =
-  /\b(\d+|one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve)\s+(tools?|commands?|calls?)\b/i;
-const DUP_THRESHOLD = 0.5;
-
-/**
- * @param label generated label text
- * @param entries the batch's tool entries (for tool-name echo detection)
- * @param previousLabels labels generated EARLIER in the same case chain,
- *   regardless of whether the variant saw them — redundancy is measured
- *   uniformly so continuity variants can be compared against blind ones.
- */
-function checkLabel(label, { entries = [], previousLabels = [] } = {}) {
-  const flags = [];
-  const wordList = words(label);
-  if (wordList.length < 4 || wordList.length > 9) {
-    flags.push(`len:${wordList.length}`);
-  }
-  if (/[.!?,;:]$/.test(label.trim())) {
-    flags.push('punct');
-  }
-  if (/^["'`]|["'`]$/.test(label.trim())) {
-    flags.push('quote');
-  }
-  if (/[*`]|^#|\[.*\]\(/.test(label)) {
-    flags.push('md');
-  }
-  if (GENERIC_OPENER.test(label.trim())) {
-    flags.push('opener');
-  }
-  const lower = label.toLowerCase();
-  for (const entry of entries) {
-    const name = String(entry.toolName ?? '').toLowerCase();
-    if (name.length <= 3) {
-      continue;
-    }
-    /** Namespaced MCP names (`mcp__github__search_repositories`) would
-     *  otherwise normalize their double underscores to double spaces and
-     *  never match a natural echo; collapse separator runs and also try
-     *  the post-namespace tail ("search repositories"). Only multi-char
-     *  candidates derived from the full name — never single middle
-     *  segments like "github", which are legitimate label subjects. */
-    const segments = name.split('__');
-    const tail = segments[segments.length - 1];
-    const candidates = new Set([
-      name,
-      name.replace(/_+/g, ' '),
-      tail,
-      tail.replace(/_/g, ' '),
-    ]);
-    let echoed = false;
-    for (const candidate of candidates) {
-      if (candidate.length > 3 && lower.includes(candidate)) {
-        echoed = true;
-        break;
-      }
-    }
-    if (echoed) {
-      flags.push(`tool-echo:${entry.toolName}`);
-      break;
-    }
-  }
-  if (COUNT_ECHO.test(label)) {
-    flags.push('count-echo');
-  }
-  /** Overlap splits into two flags: `restate` (high overlap, no payload
-   *  delta — the line adds nothing over a previous header; the production
-   *  2/3 and 7/8 failure) and `template` (high overlap but the differing
-   *  tokens are numbers/paths — same sentence frame, new information, e.g.
-   *  fib(1)→fib(2). Often fine, arguably better than synonym churn). */
-  const own = contentWords(label);
-  let maxOverlap = 0;
-  let worst = null;
-  for (const previous of previousLabels) {
-    const other = contentWords(previous);
-    const overlap = jaccard(own, other);
-    if (overlap > maxOverlap) {
-      maxOverlap = overlap;
-      worst = other;
-    }
-  }
-  if (maxOverlap > DUP_THRESHOLD && worst != null) {
-    const otherSet = new Set(worst);
-    const ownSet = new Set(own);
-    const differing = [
-      ...own.filter((word) => !otherSet.has(word)),
-      ...worst.filter((word) => !ownSet.has(word)),
-    ];
-    const informativeDelta = differing.some(isPayload);
-    flags.push(
-      `${informativeDelta ? 'template' : 'restate'}:${maxOverlap.toFixed(2)}`
-    );
-  }
-  return {
-    flags,
-    wordCount: wordList.length,
-    firstWord: wordList[0] ?? '',
-    maxOverlap,
-  };
-}
-
-module.exports = { checkLabel, contentWords, jaccard, words, stem };