llama.cpp context length misread from metadata
Cluster 64897 · agent. Data as of
Nothing open on GitHub. Fix merged in #78212 on 4 Aug 2026. Check it covers your case.
The short answer
- Known?
- Yes. 3 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #78212. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #78212. That is separate from the fix event. - Still open
- Nothing open on GitHub.
A bug where the local llama.cpp context length is incorrectly detected, falling back to a family default instead of reading the actual value from meta.n_ctx. The other members appear to be a fix addressing this metadata reading issue.
Open issues0
Open PRs0
Fixes on record
-
#78212 fix(model_metadata): read llama.cpp context from meta.n_ctx + accept sole model
files:
agent/model_metadata.py,tests/agent/test_model_metadata_local_ctx.py
1 PR closed without merging
From the close comments: merged via another change 1
-
#64904 fix(model_metadata): read llama.cpp context from meta.n_ctx + accept sole model · merged via another change →
#78212,#64897
Closed issues · 1
- Closed#64897Local llama.cpp context length misdetected — falls back to family default (e.g. 131072) instead of reading `meta.n_ctx`
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- agent
- Merged PRs
- #78212
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 4 Aug 2026