Issue Station
Sign In
Tools hereToolbox

hermes - 💡(How to fix) Fix [Bug]: Incorrect custom provider parsing [1 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#15516•Fetched 2026-04-26 05:26:56
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
1
Author
chinfengchinfeng
Participants
chinfengchinfeng
Timeline (top)
labeled ×4

Error Message

hermes-webui | ⚠️ API call failed (attempt 3/3): InternalServerError [HTTP 503] hermes-webui | 🔌 Provider: custom Model: gemma-4-31b-it hermes-webui | 🌐 Endpoint: http://192.168.1.101/v1 hermes-webui | 📝 Error: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj) hermes-webui | ⚠️ Max retries (3) exhausted — trying fallback... hermes-webui | ❌ API failed after 3 retries — HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj) hermes-webui | 💀 Final error: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)

Root Cause

Root Cause Analysis (optional)

Code Example

# config.yaml
model:
  default: "google/gemma-4-31b-it"
  provider: "custom"
  api_key: "my-api-key"
  base_url: "http://192.168.1.101/v1"

---

No response received: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)

---

# config.yaml
model:
  default: "google/gemma-4-31b-it"
  provider: "custom"
  api_key: "my-api-key"
  base_url: "http://192.168.1.101/v1"

---

No response received: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)

---

hermes-webui      | ⚠️  API call failed (attempt 3/3): InternalServerError [HTTP 503]
hermes-webui      |    🔌 Provider: custom  Model: gemma-4-31b-it
hermes-webui      |    🌐 Endpoint: http://192.168.1.101/v1
hermes-webui      |    📝 Error: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)
hermes-webui      | ⚠️ Max retries (3) exhausted — trying fallback...
hermes-webui      | ❌ API failed after 3 retries — HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)
hermes-webui      |    💀 Final error: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)

---
RAW_BUFFERClick to expand / collapse

Bug Description

When I use the following configuration with custom provider, it seems to automatically decompose the model's provider. It seems that the model configuration was broken down into Google Providers and the model name was truncated.

# config.yaml
model:
  default: "google/gemma-4-31b-it"
  provider: "custom"
  api_key: "my-api-key"
  base_url: "http://192.168.1.101/v1"

And got error:

No response received: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)

Steps to Reproduce

# config.yaml
model:
  default: "google/gemma-4-31b-it"
  provider: "custom"
  api_key: "my-api-key"
  base_url: "http://192.168.1.101/v1"

Expected Behavior

Normal response.

Actual Behavior

No response received: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)

Affected Component

CLI (interactive chat)

Messaging Platform (if gateway-related)

No response

Debug Report

hermes-webui      | ⚠️  API call failed (attempt 3/3): InternalServerError [HTTP 503]
hermes-webui      |    🔌 Provider: custom  Model: gemma-4-31b-it
hermes-webui      |    🌐 Endpoint: http://192.168.1.101/v1
hermes-webui      |    📝 Error: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)
hermes-webui      | ⚠️ Max retries (3) exhausted — trying fallback...
hermes-webui      | ❌ API failed after 3 retries — HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)
hermes-webui      |    💀 Final error: HTTP 503: No available channel for model gemma-4-31b-it under group default (distributor) (request id: 202604250452108487708688268d9d6HV283udj)

Operating System

ubuntu 24

Python Version

No response

Hermes Version

No response

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

The issue can be resolved by ensuring the custom provider is correctly configured to handle the model name and API endpoint.

Guidance

  • Verify that the base_url in the config.yaml file is correctly pointing to the API endpoint that can handle the model gemma-4-31b-it.
  • Check the custom provider implementation to ensure it does not truncate the model name or incorrectly decompose the model configuration.
  • Confirm that the API key my-api-key is valid and has the necessary permissions to access the model.
  • Review the debug report to ensure that the error message No available channel for model gemma-4-31b-it under group default (distributor) is not related to a temporary issue with the API endpoint.

Example

No code snippet is provided as the issue seems to be related to configuration and provider implementation.

Notes

The root cause of the issue is unclear, and more information about the custom provider implementation and the API endpoint would be necessary to provide a more detailed fix.

Recommendation

Apply workaround: Verify the custom provider configuration and implementation to ensure correct handling of the model name and API endpoint, as the issue seems to be related to the custom provider rather than a version-specific problem.

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…
#api#tool integration#LLM response#prompt template#agent execution

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]: Incorrect custom provider parsing [1 participants]