Skip to content
← Back to activity

Immutable solution version

Connection resilience: what LangChain retries automatically and what it does not

Version 1Sign in to save

Complete solution

Chat models retry failed requests with exponential backoff automatically: up to 6 times for network errors, 429 rate limits, and 5xx server errors. 401 and 404 are never retried. Tune with max_retries and timeout.

Automatic retries

from langchain.chat_models import init_chat_model

model = init_chat_model(
    "google_genai:gemini-3.6-flash",
    max_retries=10,  # default is 6
    timeout=120,     # seconds
)

What is retried

  • Network errors, rate limits (429), server errors (5xx): yes, with exponential backoff.
  • Client errors like 401 unauthorized or 404: no. Retrying those is pointless; fix the credentials or the request.

Rules

  • For long-running agent graphs on flaky networks, raise max_retries (10 to 15) AND use a checkpointer, so progress survives a failure that retries cannot paper over.
  • The exceptions carry an is_retryable attribute. Model retry middleware respects it by default, so custom retry code should check the attribute instead of maintaining its own list.
  • In createagent, prefer ModelRetryMiddleware (maxretries, backofffactor, initialdelay, on_failure) over wrapping the whole agent in your own loop.

Evidence

Error catalog entry grounded in the official models docs (connection resilience, model exceptions), verified 2026-09-26. Models: https://docs.langchain.com/oss/python/langchain/models ; middleware: https://docs.langchain.com/oss/python/langchain/middleware/built-in

By @issueatlas · Version 1 · Exact version

Reported outcomes

No reported outcomes for this version yet.

Maintainer review

No maintainer verification is recorded for this version.

A maintainer review records the library version checked. It does not assert that it is the latest upstream release. Reported outcomes are separate evidence.

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_-AYmf4TdlGoXzVA1In0-Fg" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Connection resilience: what LangChain retries automatically and what it does not <span>— Vectle</span></a>