Repository navigation
Sync Ollama model-projector (vision) bundles - #2
Merged
Merged
Conversation
ensevengg
added a commit
that referenced
this pull request
Nov 16, 2026
PRs #2 and #3 landed on their stacked parent branches instead of main, so this branch was written without them. Merge them in and apply this branch's import guarantees to multi-artifact records: - verify, transactionally replace, recover, copy-reuse and reclaim each artifact; record a file identity per artifact - keep a previous import tracked when a re-pull fails partway; the retry adopts files the failed attempt already verified - keep imports whose Ollama blob was deleted synced only while their recorded identity is unchanged (symlinks and edited files are stale) - sweep every leftover in copy-mode staging, since copy mode removes its aliases after each locked import - apply manifest size checks to projector blobs Validation: 281 passed on Python 3.12 including 27 sandboxed real-lms cases; 254 passed, 27 skipped on 3.13 and 3.14; Ruff, formatting, Pyright and distribution builds pass. Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Second PR of the stack (contains #1). Adds support for multi-artifact vision models — the gap where Ollama vision models like
llavaimported into LM Studio without their projector (mmproj) layer and silently lost vision capability.application/vnd.ollama.image.projector) layers; rejects, rather than partially syncs, unsupported shapes (multiple model/projector layers, adapter/draft/tensor layers).lms importper artifact; projector aliases use the LM Studio-recognizedmmproj-prefix; both files land in the same digest-keyeduser/reposo LM Studio pairs them.lms ls --jsonis polled (with retry) to confirm LM Studio actually indexed the model as vision-capable;statuscross-checks the same inventory (only when needed).sdl syncresumes instead of re-importing.sdl scanshows projector artifacts and their readiness; JSON output includes the artifact list.Design and compatibility were validated up front against primary sources (Ollama loader/layer-type sources,
lmsCLI source) and end-to-end on real LM Studio 0.4.23 — seedocs/research/multi-artifact-validation.mdand the retained registry fixture intests/fixtures/ollama/.Known trade-off
Re-pulling a vision model creates a new digest-keyed repo directory in LM Studio; the old bundle directory is orphaned there (prune only manages StudioLink staging aliases). Two follow-up bugs in this area are found and fixed by the audit in the next PR (#3).
Verification
Stack / merge order
stabilize-sync-lifecycle→mainstabilize-sync-lifecyclereliability-fixes→support-artifact-bundlesMerge in order; each PR contains the previous one.