Issue Station
Sign In
Tools hereToolbox

hermes - ✅(Solved) Fix [Bug]: Multi Model for Profile don't work [1 pull requests, 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#14554•Fetched 2026-04-24 06:16:33
View on GitHub
Comments
0
Participants
1
Timeline
5
Reactions
0
Author
hqin2013hqin2013
Participants
hqin2013hqin2013
Timeline (top)
labeled ×4cross-referenced ×1

Error Message

Additional Logs / Traceback (optional)

Root Cause

Root Cause Analysis (optional)

Fix Action

Fixed

PR fix notes

PR #14584: fix(cli): use profile providers during model switch

Description (problem / solution / changelog)

Summary

  • load the active profile's providers: and compatible custom_providers: before every /model switch, not only when opening the picker
  • pass those provider definitions into switch_model() for argument-based model switches
  • add a CLI regression test covering /model deepseek with profile-scoped provider config

Testing

  • python3 -m pytest -o addopts='' tests/cli/test_cli_model_switch_profile_providers.py tests/hermes_cli/test_user_providers_model_switch.py -q

Closes #14554

Changed files

  • cli.py (modified, +8/-10)
  • tests/cli/test_cli_model_switch_profile_providers.py (added, +55/-0)

Code Example

✓ Model switched: deepseek/deepseek-chat-v3.1
    Provider: **OpenRouter**
    Context: 163,840 tokens
    Max output: 163,840 tokens
    Cost: $0.20/M in, $0.80/M out
    Capabilities: reasoning, tools, structured output, open weights
    (session only — add --global to persist)

---

Report     https://paste.rs/zFeDN
  agent.log  https://paste.rs/OxL59

---
RAW_BUFFERClick to expand / collapse

Bug Description

Multi models doesn't work in Profile

Steps to Reproduce

  1. Create profile iaa
  2. config model OpenRouter(both minimax and deepseek)
  3. config model MiniMax and DeepSeek (Direct API)
  4. set multi-model for profile iaa, default is MiniMax `model: default: MiniMax-M2.7 provider: minimax-cn base_url: https://api.minimaxi.com/anthropic providers: minimax: provider: minimax-cn api_key_env: MINIMAX_API_KEY base_url: https://api.minimaxi.com/anthropic model_name: MiniMax-M2.7 deepseek: provider: deepseek api_key_env: DEEPSEEK_API_KEY base_url: https://api.deepseek.com/v1 model_name: deepseek-chat fallback_providers:
  • provider: deepseek api_key_env: DEEPSEEK_API_KEY base_url: https://api.deepseek.com/v1 model_name: deepseek-chat credential_pool_strategies: {} `
  1. remove OpenRouter API KEY in .env file (option)
  2. change model in CLI: "/model deepseek" or "/model minimax", it tips:
  ✓ Model switched: deepseek/deepseek-chat-v3.1
    Provider: **OpenRouter**
    Context: 163,840 tokens
    Max output: 163,840 tokens
    Cost: $0.20/M in, $0.80/M out
    Capabilities: reasoning, tools, structured output, open weights
    (session only — add --global to persist)

it always use OpenRouter, not Deepseek or MiniMax direct

Expected Behavior

i can use any model in profile.

PS1: I use the same config in default profile, it works. PS2: I didn't config OpenRouter Model in default profile.

Actual Behavior

It always use OpenRouter, like it remember deepseek/opentouer should use openrouter

Affected Component

Configuration (config.yaml, .env, hermes setup)

Messaging Platform (if gateway-related)

N/A (CLI only)

Debug Report

Report     https://paste.rs/zFeDN
  agent.log  https://paste.rs/OxL59

Operating System

Debian 12

Python Version

Python: 3.11.15

Hermes Version

Hermes Agent v0.10.0 (2026.4.16)

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 reconfiguring the model settings to correctly use the intended providers, MiniMax and DeepSeek, instead of OpenRouter.

Guidance

  • Review the config.yaml file to ensure that the model and providers sections are correctly configured for the intended models, MiniMax and DeepSeek.
  • Verify that the OpenRouter model is not configured as a default or fallback provider for the profile.
  • Check the .env file to ensure that the API keys for MiniMax and DeepSeek are correctly set and that the OpenRouter API key is removed or commented out.
  • Test the model switching using the CLI command /model deepseek or /model minimax to ensure that the correct model is being used.

Example

No code snippet is provided as the issue is related to configuration and not code.

Notes

The issue seems to be related to the configuration of the models and providers in the config.yaml file. The fact that the same configuration works in the default profile suggests that the issue is specific to the profile being used.

Recommendation

Apply workaround: Reconfigure the model settings to correctly use the intended providers, MiniMax and DeepSeek, instead of OpenRouter. This is because the issue seems to be related to the configuration and not a version-specific bug.

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#cache error#pipeline error#runtime error#dependency conflict

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 - ✅(Solved) Fix [Bug]: Multi Model for Profile don't work [1 pull requests, 1 participants]