Repository navigation
release(macos): ship the BGE GGUF in the Mac bundle; raise size budgets - #271
Merged
Merged
Conversation
…size budgets Owner decision 2026-10-06: Hermes keyed embedding retrieval on every OS. bundle-lite now bundles models/bge-base-en-v1.5-gguf/* (pinned digest fa9e1f6c..., on runtime-deps). Budgets raised for the GGUF and the embedded corpus: dmg 700 MB, app.tar.gz 710 MB, app 1.2 GB, models 725 MB, knowledge-corpus 250 MB; re-measure and tighten at the build. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018wWZZ8GRVU9USh3kKQHsFe
This was referenced Oct 6, 2026
BerryManifold
approved these changes
Oct 6, 2026
BerryManifold
left a comment
BerryManifold
left a comment
Contributor
There was a problem hiding this comment.
Reviewed the macOS BGE GGUF bundle inclusion and explicit size-budget updates. Checks are green; approved for the release branch.
Matr0xshka
approved these changes
Oct 6, 2026
Matr0xshka
left a comment
Matr0xshka
left a comment
Contributor
There was a problem hiding this comment.
Reviewed the macOS BGE GGUF bundle inclusion and explicit size-budget updates. Checks are green; approved for the release branch.
7 of 10 tasks
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Owner decision 2026-10-06: the macOS DMG ships the BGE embedding GGUF so Hermes uses keyed embedding retrieval on every OS (Linux/Windows got it in #270). The GGUF (pinned
fa9e1f6c…eaee) is now onruntime-deps.tauri.bundle-lite.conf.json: bundlesmodels/bge-base-en-v1.5-gguf/*;embed_serve_testsnow checks bundle-lite too.release/budgets.json: dmg 455 → 700 MB, app.tar.gz 460 → 710 MB, app 938 MB → 1.2 GB, resources/models 483 → 725 MB, resources/knowledge-corpus 110 → 250 MB (embedded vectors). Re-measured and tightened at the v0.5.0 build (D2).scripts/size-budget.test.mjspins the new values (raising a budget stays a visible, reviewed change).Checks: embed_serve tests 9/9, vitest 2234 passed, fmt clean.
🤖 Generated with Claude Code
https://claude.ai/code/session_018wWZZ8GRVU9USh3kKQHsFe