Mintplex-Labs/anything-llm · error

No token context limit was set.

Error message

No token context limit was set.

What it means

Static LiteLLM.promptWindowLimit(_modelName): `const limit = process.env.LITE_LLM_MODEL_TOKEN_LIMIT || 4096; if (!limit || isNaN(Number(limit))) throw 'No token context limit was set.'`. The || 4096 fallback means a missing var can never trigger it; only a set-but-non-numeric value can (Number() → NaN). Used statically by AnythingLLM to size context windows before instantiation.

Solutions

1. Use a bare integer: LITE_LLM_MODEL_TOKEN_LIMIT=8192.
2. Strip units, commas, underscores, quotes, and comments from the value; check for hidden CRLF with cat -A .env.
3. Or delete the variable to accept the 4096 default.
4. Guard in CI: reject deploys where the var is set and fails ^\d+$.

Example fix

# before (.env)
LITE_LLM_MODEL_TOKEN_LIMIT=128k

# after (.env)
LITE_LLM_MODEL_TOKEN_LIMIT=131072

const raw = process.env.LITE_LLM_MODEL_TOKEN_LIMIT;
if (raw && !/^\d+$/.test(raw.trim())) throw new Error(`LITE_LLM_MODEL_TOKEN_LIMIT must be an integer, got ${JSON.stringify(raw)}`);
const ctx = LiteLLM.promptWindowLimit(model);

const isIntegerEnv = (v) => v == null || v === "" || /^\d+$/.test(String(v).trim());

When it happens

Trigger: Calling LiteLLM.promptWindowLimit(model) with LITE_LLM_MODEL_TOKEN_LIMIT set to something like '128k', '32_768', '131072 # claude', or a quoted number — anything Number() cannot parse. Integer strings, hex-free floats, and empty/unset values are all fine (empty/unset hit the 4096 fallback).

Common situations: Copying human-readable context sizes ('200k') from model spec sheets into .env; dotenv files with CRLF line endings leaving a trailing \r; secret-manager injection adding quotes around numeric values; deploy pipelines templating 'None' when the var is unconfigured.

Understand the failure class

Background: "is not a valid" / "Invalid ... value" environment variable errors: how libraries validate env vars and what to do when they reject yours — this error's family across 48 libraries.

Related errors

• No LocalAi token context limit was set.
• No token context limit was set.
• LiteLLM must have a valid base path to use for the api.
• LiteLLM must have a valid model set.
• KoboldCPP must have a valid base path to use for the api.

AI-assisted analysis of Mintplex-Labs/anything-llm@3aec848f28 (2026-08-18). Data as JSON: /api/errors/bd6807448fb594b0. Report an issue: GitHub.

Appendix: source

Thrown at server/utils/AiProviders/liteLLM/index.js:61

    if (!contextTexts || !contextTexts.length) return "";
    return (
      "\nContext:\n" +
      contextTexts
        .map((text, i) => {
          return `[CONTEXT ${i}]:\n${text}\n[END CONTEXT ${i}]\n\n`;
        })
        .join("")
    );
  }

  streamingEnabled() {
    return "streamGetChatCompletion" in this;
  }

  static promptWindowLimit(_modelName) {
    const limit = process.env.LITE_LLM_MODEL_TOKEN_LIMIT || 4096;
    if (!limit || isNaN(Number(limit)))
      throw new Error("No token context limit was set.");
    return Number(limit);
  }

  // Ensure the user set a value for the token limit
  // and if undefined - assume 4096 window.
  promptWindowLimit() {
    const limit = process.env.LITE_LLM_MODEL_TOKEN_LIMIT || 4096;
    if (!limit || isNaN(Number(limit)))
      throw new Error("No token context limit was set.");
    return Number(limit);
  }

  // Short circuit since we have no idea if the model is valid or not
  // in pre-flight for generic endpoints
  isValidChatCompletionModel(_modelName = "") {
    return true;
  }

View on GitHub (pinned to 3aec848f28)