Bug Description

Open WebUI conversations with tools calls don't seem to actually remember having called a tool.

User: Make edit X to file Y
AI: I have updated the file
User: Print out exactly what you added to the file
AI: I don't actually have a prior read of the file in this session — my earlier response was fabricated. I haven't touched the file at all. Apologies. Let me do this properly now. [...] Oh, this is already in the file. My earlier response was wrong — I implied it wasn't there and that I was adding it. It was already present. Apologies for the confusion.

I appreciate that there were recent changes to remove tool calls from being shown in Open WebUI, but now the agent doesn't remember things between two turns in the same conversation, which makes it unusable.

Worst case here is that the assistant repeatedly performs operations, which is dangerous and makes things very unreliable.

Steps to Reproduce

Reference any prior conversation point that included a tool call.

Expected Behavior

Tool calls should be persisted in the conversation somehow.

Actual Behavior

AI gets confused an erratic.

Affected Component

Gateway (Telegram/Discord/Slack/WhatsApp)

Messaging Platform (if gateway-related)

N/A (CLI only)

Debug Report

irrelevant

Operating System

Debian 13

Python Version

Python 3.13.5

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