Harvmaster/autocomplete-model
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity
11 Commits 1 Branch 6 Tags
main
Commit Graph
4 Commits
Author SHA1 Message Date
HarvmasterandClaude Opus 5.5 5c99f011e8 Next-edit: treat empty model output as no-edit
ci / build (push) Canceled after 0s
Details 
llama-server leaves special tokens out of content, so the NO_EDIT token arrives as an
empty string. The daemon treated that as a rewrite of the region to nothing (Tab would
have deleted the region). shared/nextedit.ts parseNextEditOutput() is now used by the
daemon and the eval.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J39imRDT8L7xYbWzsVWd8A
 2026-10-04 00:15:11 +00:00
HarvmasterandClaude Opus 5.5 f92341d1a2 shared/nextedit: trim before-context in a few encodes instead of one per line
ci / build (push) Canceled after 0s
Details 
Same output on 397/398 test prompts, ~6x faster prompt building (daemon and export).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J39imRDT8L7xYbWzsVWd8A
 2026-10-03 18:17:56 +00:00
HarvmasterandClaude Opus 5.5 87d3c3c3bf Extension 0.6.0: next-edit, token healing, TS errors context, cursor-move, prewarm
ci / build (push) Canceled after 0s
Details 
- shared/nextedit.ts: next-edit prompt format (region rewrite or NO_EDIT, Qwen spare special tokens)
- shared/diagnostics.ts: TS errors near the cursor as context; symbols format 2 adds namespace imports
- shared/prompt.ts: token healing (cut the half-typed word, force it via grammar), errors header section
- daemon: model profiles carry contextFormat/errors/members/nextEdit; /v1/next-edit with edit-burst
  tracking; /v1/prewarm; /v1/debug/last; token healing on by default
- extension: next-edit decorations (Tab apply / Esc dismiss), suggest on cursor move, prewarm on focus,
  Show Last Prompt, update check against releases, diagnostics in the edit recorder
- models/README: training-data attribution; release script profiles for stage-d/stage-e
- .gitea/workflows/ci.yml: build + test, publish release on vscode-v* tags (needs a runner + RELEASE_TOKEN)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J39imRDT8L7xYbWzsVWd8A
 2026-10-03 17:21:38 +00:00
HarvmasterandClaude Opus 5.5 fa8f775779 Restructure into a monorepo: models, VS Code extension, daemon, shared 
- models/: GGUFs (Git LFS), manifest.json, model card, Apache-2.0 LICENSE + NOTICE
- extensions/vscode/: the Local Autocomplete extension (v0.5.0, publisher harvmaster)
- daemon/: acd completion daemon (bundled into the extension; also runs standalone)
- shared/: prompt layout + symbol extraction shared with the training pipeline
- scripts/: make-model-release.mjs, publish-extension-release.mjs (Gitea releases)
- README with quick start, settings, architecture, build and release instructions;
  MIT license for code; CHANGELOG

The default model manifest URL moves to models/manifest.json.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-03 15:37:19 +00:00