# NousResearch/hermes-agent · Vision preprocessing token limits and latency fixes

## Open now

- Nothing open on GitHub.

These issues and PRs address overly verbose vision preprocessing output, hardcoded max_tokens limits in auxiliary vision calls, and related latency problems. Work spans making max_tokens configurable via config.yaml, keeping preprocessing prompts concise, and routing improvements for multimodal models.

## TL;DR

- 10 member(s): 0 open issue(s), 3 closed issue(s), 0 open PR(s), 2 merged PR(s), 5 PR(s) closed without merging.
- A fix was merged to main in PR #75253. Verify it addresses your case.
- **Recommended:** read PR #75253 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `partially_resolved` · deciding PR(s): `pr-75253`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.17`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Closed / duplicate issues

- #10809: Default vision pre-process prompt generates overly long descriptions (~2000 chars), significantly slowing down image-bearing requests on local models
- #29590: \[Bug/Enhancement\] Hardcoded max_tokens and overly verbose prompt in vision_tools.py causes severe latency for reasoning models
- #34087: Make max_tokens configurable for aux vision calls

## Prior & competing PRs

- **#29600: fix(vision): honor auxiliary.vision.max_tokens from config in vision_tools**. closed without merge · fix tier `suggested`
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`
  - _suggested-tier fix detail withheld; re-request with `?tier=all` to include it._
- **#38004: fix: respect auxiliary.vision.max_tokens from config.yaml (#29590)**. closed without merge · fix tier `suggested`
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `db472f5df`
  - _suggested-tier fix detail withheld; re-request with `?tier=all` to include it._
- **#75253: fix(vision): stop capping aux vision output with hardcoded max_tokens**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`; implication `superseded`
  - files: `tests/tools/test_browser_console.py`, `tests/tools/test_video_analyze.py`, `tests/tools/test_vision_tools.py`, `tools/browser_tool.py`, `tools/vision_tools.py`
- **#81269: fix(gateway): keep auto vision preprocess concise (salvage #10852)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`; implication `superseded`
  - files: `contributors/emails/[redacted:email]`, `gateway/run.py`, `tests/gateway/test_vision_preprocess.py`
- **#10852: fix(gateway): keep auto vision preprocess concise**. closed without merge
  - maintainer direction: category `merged_via`; implication `superseded`; refs `#81269`, `#10809`, `#75253`
- **#28999: fix(gateway): retry auto-vision on transient failure (#28972)**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `fb403a3a730f2a4eab1cfc60ffe854f7ea7c4159`, `#56889`
- **#61187: Cap gateway vision preprocessing output**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#10852`, `#10809`, `#10852`

## Fix status

- Merged to main in PR #75253 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-08-15`.
- Subsystem: `agent`