Skip to content

fix: make vision_analyze timeout configurable via config.yaml (salvage #2306)#2480

Merged
teknium1 merged 1 commit intomainfrom
hermes/hermes-5e6ebebb
Mar 22, 2026
Merged

fix: make vision_analyze timeout configurable via config.yaml (salvage #2306)#2480
teknium1 merged 1 commit intomainfrom
hermes/hermes-5e6ebebb

Conversation

@teknium1
Copy link
Copy Markdown
Contributor

Summary

Based on PR #2306. Reimplemented to use config.yaml instead of an env var (non-secrets belong in config).

Reads auxiliary.vision.timeout from config.yaml (default: 30s) and passes it to async_call_llm. Useful for slow local vision models that need more than 30 seconds.

auxiliary:
  vision:
    timeout: 120  # seconds

Changes

  • hermes_cli/config.py: added timeout: 30 to DEFAULT_CONFIG["auxiliary"]["vision"]
  • tools/vision_tools.py: reads timeout from config, passes to async_call_llm
  • website/docs/user-guide/configuration.md: documented in auxiliary config reference

Verification

  • Vision tests: 43/43 passed

Credit

Original idea from PR #2306.

Reads auxiliary.vision.timeout from config.yaml (default: 30s) and
passes it to async_call_llm. Useful for slow local vision models
that need more than 30 seconds.

Setting is in config.yaml (not .env) since it's not a secret:

  auxiliary:
    vision:
      timeout: 120

Based on PR #2306.
@teknium1 teknium1 merged commit 6435d69 into main Mar 22, 2026
1 of 2 checks passed
outsourc-e pushed a commit to outsourc-e/hermes-agent that referenced this pull request Mar 26, 2026
…search#2480)

Reads auxiliary.vision.timeout from config.yaml (default: 30s) and
passes it to async_call_llm. Useful for slow local vision models
that need more than 30 seconds.

Setting is in config.yaml (not .env) since it's not a secret:

  auxiliary:
    vision:
      timeout: 120

Based on PR NousResearch#2306.

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
aashizpoudel pushed a commit to aashizpoudel/hermes-agent that referenced this pull request Mar 30, 2026
…search#2480)

Reads auxiliary.vision.timeout from config.yaml (default: 30s) and
passes it to async_call_llm. Useful for slow local vision models
that need more than 30 seconds.

Setting is in config.yaml (not .env) since it's not a secret:

  auxiliary:
    vision:
      timeout: 120

Based on PR NousResearch#2306.

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants