Skip to content
Agents tracked: 502 Releases (7d): 613 Agent status: 4 with issuesSince last limit reset: Claude 7d · Codex 5d For AI agents: Markdown Updated Nov 18, 2026

LiteLLM known issues, errors and fixes

What LiteLLM users report right now: 0 open problems, 3 fixed and 2 answered questions, from its GitHub repository, written up by AgentGid. Workarounds and fix versions come only from official sources. Checked Nov 12, 2026.

← LiteLLM: pricing, features and usage · All user reports

Fixed Sep 3, 2026

Users report that OpenCode Go started rejecting requests sent through LiteLLM because they lacked the x-opencode-session header the service began to require in September. A merged pull request now forwards stable session IDs automatically.

Reported on GitHub · 53 👍

Security Fixed Oct 26, 2026

Users report that LiteLLM capped filelock below 4.0, which kept projects on a filelock version with three published CVEs and made security audits fail with no way to upgrade. A merged change now allows filelock 4.x.

Reported on GitHub · 12 👍

Fixed RequestAug 22, 2026

Users asked LiteLLM to lift its openai<3 dependency cap, which blocked installing it next to packages that need the OpenAI Python SDK 3.x. A maintainer said a merged change raised the bound to <4 and CI now tests both SDK 2 and SDK 3.

Reported on GitHub · 8 👍

Security Closed WorkaroundOct 21, 2026

Users report that the litellm 1.107.0 release on PyPI, and the Docker images tagged latest, main-latest and main-stable, shipped a credential stealer built from a lookalike repository. Maintainers handled it as a SEV-0 incident; PyPI removed 1.107.0 and the malicious Docker images were taken down.

Workaround: Pin an explicit, known-good version instead of floating tags; during the incident maintainers advised 1.106.2.

Reported on GitHub · 20 👍 · workaround source

Closed RequestAug 18, 2026

Users asked for the GPT-5.6 models (Sol, Terra, Luna) to be callable through the Amazon Bedrock Runtime path, with its geo and global cross-region routing, not only through Bedrock Mantle. A merged pull request added these cross-region inference profiles.

Reported on GitHub · 18 👍

Questions LiteLLM users ask

Answered from the official documentation.

How do I reset the usage and spend that LiteLLM Proxy has recorded so far?

The docs describe a POST /global/spend/reset endpoint, callable only with the master key, that sets spend to 0 for all API keys and teams while keeping the request logs in the spend logs table for auditing. For recurring reporting periods, budget_duration resets a budget automatically at the end of each period; without it a budget never resets.

Source · Source · Source · Where it was asked

Can one LiteLLM proxy send the same model name to different provider accounts depending on which team makes the call?

Yes. The docs describe per-team and per-project credential routing, where each account's credentials are stored in the credentials table and referenced from a team's model_config metadata. Requests are then routed by the team of the API key, without duplicating the model definition.

Source · Source · Where it was asked

Reports are users' accounts from public GitHub issues and discussions, not AgentGid tests. AgentGid writes each one in its own words; statuses, fix versions and workarounds come from the project's own pages, release notes and maintainers.