Issue Station
Sign In
Tools hereToolbox

hermes - 💡(How to fix) Fix [Bug]: The model takes over 3 minutes to answer a simple question.

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…

Error Message

Additional Logs / Traceback (optional)

Root Cause

Root Cause Analysis (optional)

Code Example

Report       https://paste.rs/YUZFT
  agent.log    https://paste.rs/3XMIf
  gateway.log  https://paste.rs/JfQPB

---
RAW_BUFFERClick to expand / collapse

Bug Description

The model takes over 3 minutes to respond to a simple question. I changed the opencode key and updated hermes. After that, problems started, in addition to the already mentioned issue with kimi models. Some Telegram commands became slow, such as new session and /model and repose time became very slow. CLI is also slow.

Steps to Reproduce

I changed the opencode key and updated hermes.

Expected Behavior

2026-05-25 16:42:54,205 INFO [20260525_164106_a004ab] agent.conversation_loop: conversation turn: session=20260525_164106_a004ab model=mimo-v2.5-pro provider=opencode-go platform=cli history=4 msg='hi' 2026-05-25 16:42:54,270 INFO run_agent: OpenAI client created (chat_completion_stream_request, shared=False) thread=Thread-13 (_call):139697451939520 provider=opencode-go base_url=https://opencode.ai/zen/go/v1 model=mimo-v2.5-pro 2026-05-25 16:43:00,601 INFO run_agent: OpenAI client closed (stream_request_complete, shared=False, tcp_force_closed=0) thread=Thread-13 (_call):139697451939520 provider=opencode-go base_url=https://opencode.ai/zen/go/v1 model=mimo-v2.5-pro 2026-05-25 16:43:00,602 INFO [20260525_164106_a004ab] agent.conversation_loop: API call #3: model=mimo-v2.5-pro provider=opencode-go in=16970 out=29 total=16999 latency=6.4s cache=16896/16970 (100%) 2026-05-25 16:43:00,619 INFO [20260525_164106_a004ab] agent.conversation_loop: Turn ended: reason=text_response(finish_reason=stop) model=mimo-v2.5-pro api_calls=1/90 budget=1/90 tool_turns=0 last_msg_role=assistant response_len=90 session=20260525_164106_a004ab

Actual Behavior

2026-05-25 13:34:27,222 INFO run_agent: Loaded environment variables from /root/.hermes/.env 2026-05-25 13:34:27,650 INFO run_agent: OpenAI client created (agent_init, shared=True) thread=Thread-3 (process_loop):139874938123968 provider=opencode-go base_url=https://opencode.ai/zen/go/v1 model=mimo-v2.5-pro 2026-05-25 13:34:48,035 INFO [20260525_133423_8856ab] agent.conversation_loop: conversation turn: session=20260525_133423_8856ab model=mimo-v2.5-pro provider=opencode-go platform=cli history=0 msg='hi' 2026-05-25 13:34:48,109 INFO run_agent: OpenAI client created (chat_completion_stream_request, shared=False) thread=Thread-5 (_call):139874907702976 provider=opencode-go base_url=https://opencode.ai/zen/go/v1 model=mimo-v2.5-pro 2026-05-25 13:35:05,363 INFO gateway.memory_monitor: [MEMORY] rss=200MB gc=(230, 11, 9) threads=6 uptime=900s 2026-05-25 13:36:52,583 INFO run_agent: OpenAI client closed (stream_request_complete, shared=False, tcp_force_closed=0) thread=Thread-5 (_call):139874907702976 provider=opencode-go base_url=https://opencode.ai/zen/go/v1 model=mimo-v2.5-pro 2026-05-25 13:36:52,583 INFO [20260525_133423_8856ab] agent.conversation_loop: API call #1: model=mimo-v2.5-pro provider=opencode-go in=18809 out=33 total=18842 latency=124.5s cache=18752/18809 (100%) 2026-05-25 13:37:32,945 INFO [20260525_133423_8856ab] agent.conversation_loop: Turn ended: reason=text_response(finish_reason=stop) model=mimo-v2.5-pro api_calls=1/90 budget=1/90 tool_turns=0 last_msg_role=assistant response_len=30 session=20260525_133423_8856ab 2026-05-25 13:37:33,135 INFO agent.auxiliary_client: Auxiliary auto-detect: using main provider opencode-go (mimo-v2.5-pro) 2026-05-25 13:37:33,135 INFO agent.auxiliary_client: Auxiliary title_generation: using auto (mimo-v2.5-pro) at https://opencode.ai/zen/go/v1

Affected Component

CLI (interactive chat)

Messaging Platform (if gateway-related)

Telegram

Debug Report

Report       https://paste.rs/YUZFT
  agent.log    https://paste.rs/3XMIf
  gateway.log  https://paste.rs/JfQPB

Operating System

Ubuntu 24.04

Python Version

3.11.15

Hermes Version

Hermes Agent v0.14.0 (2026.5.16) Project: /usr/local/lib/hermes-agent Python: 3.11.15 OpenAI SDK: 2.24.0 Up to date

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

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