# NousResearch/hermes-agent · Gemma 4 context length metadata fixes

## Open now

- Nothing open on GitHub.

These issues and pull requests address a bug where Gemma 4 models were incorrectly assigned an 8K context length instead of 256K. The fixes add or correct model metadata entries covering various naming conventions for Gemma 4, including Ollama-style naming.

## TL;DR

- 4 member(s): 0 open issue(s), 1 closed issue(s), 0 open PR(s), 1 merged PR(s), 2 PR(s) closed without merging.
- A fix was merged to main in PR #14198. Verify it addresses your case.
- **Recommended:** read PR #14198 (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: `resolved` · deciding PR(s): `pr-14198`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.50`: 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

- #12976: Bug: Gemma 4 models hardcoded with 8K context instead of 256K

## Prior & competing PRs

- **#14198: fix(model_metadata): add gemma-4 / gemma4 context-length entries**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `agent/model_metadata.py`, `scripts/release.py`
  - fix hunks:
  - `agent/model_metadata.py`

    ```diff
    @@ -133,6 +133,8 @@ def _strip_provider_prefix(model: str) -> str:
         # Google
         "gemini": 1048576,
         # Gemma (open models served via AI Studio)
    +    "gemma-4": 256000,  # Gemma 4 family
    +    "gemma4": 256000,  # Ollama-style naming (e.g. gemma4:31b-cloud)
         "gemma-4-31b": 256000,
         "gemma-3": 131072,
         "gemma": 8192,  # fallback for older gemma models
    ```
  - `scripts/release.py`

    ```diff
    @@ -343,6 +343,7 @@
         "[redacted:email]": "pinion05",
         "105142614+VTRiot@users.noreply.github.com": "VTRiot",
         "[redacted:email]": "iamagenius00",
    +    "89228157+Feranmi10@users.noreply.github.com": "Feranmi10",
     }
     
     
    ```
- **#13000: fix(model_metadata): add Ollama-style naming for Gemma 4 context length**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `#12976`
- **#14174: fix(model_metadata): add gemma-4 and gemma4 context length entries**. closed without merge
  - maintainer direction: category `merged_via`; implication `superseded`; refs `#14198`, `#12976`

## Fix status

- Merged to main in PR #14198 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-04-22`. This confirmation is old and may be out of date (a revert/reopen would not have invalidated it here); re-verify.