hermes - 💡(How to fix) Fix [Bug]: Explicit local OpenAI-compatible config still resolves back to OpenRouter [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
NousResearch/hermes-agent#16623Fetched 2026-04-28 06:52:07
View on GitHub
Comments
1
Participants
2
Timeline
6
Reactions
0
Author
Timeline (top)
labeled ×5commented ×1

Error Message

Additional Logs / Traceback (optional)

Root Cause

Root Cause Analysis (optional)

RAW_BUFFERClick to expand / collapse

Bug Description

Hermes does not reliably stay on an explicitly configured local OpenAI-compatible provider and keeps resolving back to OpenRouter.

Steps to Reproduce

  1. Configure a local LM Studio OpenAI-compatible endpoint.
  2. Set Hermes to use that local provider/model.
  3. Start Hermes and send a message.
  4. Observe that Hermes resolves to OpenRouter instead of the local provider.

Expected Behavior

Hermes should stay on the explicitly configured local provider, or fail clearly if that provider is invalid.

Actual Behavior

Hermes resolves to OpenRouter instead, causing misleading authentication and provider errors.

Affected Component

CLI (interactive chat)

Messaging Platform (if gateway-related)

Discord, N/A (CLI only)

Operating System

Linux (OpenCloudOS on VPS)

Python Version

No response

Hermes Version

v0.11.0

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

No response

Proposed Fix (optional)

No response

Are you willing to submit a PR for this?

  • I'd like to fix this myself and submit a PR

extent analysis

TL;DR

Hermes may not be correctly configured to prioritize the local OpenAI-compatible provider over OpenRouter, leading to unexpected resolution.

Guidance

  • Verify that the local OpenAI-compatible endpoint is correctly configured and accessible, ensuring it can handle requests from Hermes.
  • Check the Hermes configuration files or environment variables to ensure that the local provider is explicitly set as the primary or default provider.
  • Review any relevant documentation for Hermes v0.11.0 to understand how provider priorities are handled, as this might be a version-specific issue.
  • Test the local provider directly (outside of Hermes) to confirm it's functioning as expected and can process requests without resolving to OpenRouter.

Example

No code example is provided due to the lack of specific technical details about the configuration or implementation.

Notes

The solution might depend on the specific configuration options available in Hermes v0.11.0 and how it handles provider priorities. Without more detailed logs or a clear understanding of the configuration, it's challenging to provide a precise fix.

Recommendation

Apply workaround: Given the information, the best course of action seems to be to carefully review and adjust the Hermes configuration to ensure it correctly prioritizes the local OpenAI-compatible provider. This approach allows for a targeted fix without assuming the presence of a newer version with the issue resolved.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

hermes - 💡(How to fix) Fix [Bug]: Explicit local OpenAI-compatible config still resolves back to OpenRouter [1 comments, 2 participants]