Issue Station
Sign In
Tools hereToolbox

hermes - 💡(How to fix) Fix [Bug]: Context not being processed (Ollama local) [2 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#20180•Fetched 2026-05-06 06:38:14
View on GitHub
Comments
2
Participants
2
Timeline
11
Reactions
0
Author
ziipzaaapM16A4ziipzaaapM16A4
Participants
alt-glitchalt-glitchziipzaaapM16A4ziipzaaapM16A4
Timeline (top)
labeled ×4commented ×2renamed ×2closed ×1

Error Message

Additional Logs / Traceback (optional)

Root Cause

Root Cause Analysis (optional)

Code Example

I do not have memory between conversations, so I do not recall what secret number you might have told me previously.

Could you please remind me of the number?

---

Sorry i had to redact my user name out of the log logfiles are in the Bug Description

---
RAW_BUFFERClick to expand / collapse

Bug Description

Hello, I am using Hermes with Ollama (Local) as LLM Provider. But the LLM never did use the context that is beeing sent to ollama.

Hermes does sent it in its request but Ollama does not concider it. I tested this with Hermes in Docker and Locally installed. On my Docker Setup i even Captured the Network traffic between Ollama and Hermes to check if Hermes is sending it. When i use Ollama via CLI oder use OpenWeb UI and use the Ollama gateway the LLM responds to the context but not on any Hermes configuration i had.

If requested i can provide the hermes debug files from the docker hermes + ollama local setup too. It contains a wireshark pcapng log file On the Docker Hermes setup i used in addition the gemma4:31b to rule out a issues with the llm.

Report.txt agent.log

Steps to Reproduce

  1. Run Hermes Chat
  2. Prompt: hello. my secret number is 5796. please dont repeat it just say okay.
  3. Await Answer
  4. Prompt: what was my secret number i just told you about?

Expected Behavior

Something like: your secret number is 5796

Actual Behavior

I do not have memory between conversations, so I do not recall what secret number you might have told me previously.

Could you please remind me of the number?

Conversation History.txt

Affected Component

CLI (interactive chat), Gateway (Telegram/Discord/Slack/WhatsApp), Agent Core (conversation loop, context compression, memory)

Messaging Platform (if gateway-related)

No response

Debug Report

Sorry i had to redact my user name out of the log logfiles are in the Bug Description

Operating System

Nobara 43 (Fedora)

Python Version

3.14.3

Hermes Version

Hermes Agent v0.12.0 (2026.4.30) Project: /home/[REDACTED]/.hermes/hermes-agent Python: 3.11.15 OpenAI SDK: 2.32.0 Up to date

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

Issue seems to be with custom llm providers.

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 is likely due to Hermes not properly utilizing the context sent to Ollama, and a potential fix involves investigating the context handling in the Hermes-Ollama integration.

Guidance

  • Review the Hermes code to ensure it correctly sends and handles context when interacting with Ollama, focusing on the conversation loop and context compression components.
  • Verify that Ollama properly receives and processes the context by checking the network traffic capture (pcapng log file) and the agent.log for any relevant information.
  • Test the Ollama CLI and OpenWeb UI with the same context to confirm that the issue is specific to the Hermes integration.
  • Investigate the Hermes Agent v0.12.0 configuration and the OpenAI SDK: 2.32.0 to ensure compatibility and proper setup.

Example

No code snippet is provided due to the lack of specific code references in the issue.

Notes

The issue seems to be specific to the Hermes-Ollama integration, and the root cause analysis suggests a problem with custom LLM providers. However, without more information or code snippets, it's challenging to provide a definitive fix.

Recommendation

Apply workaround: Investigate and adjust the Hermes-Ollama integration to properly handle context, as the issue seems to be specific to this setup.

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…
#conversation history#logging issue#authentication issue#prompt issue#agent setup

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]: Context not being processed (Ollama local) [2 comments, 2 participants]