Skip to content

feat(openclaw): enable memory-lancedb with fixed local embedding endpoint (#1300 phase 1) - #4451

Merged
dezren39 merged 1 commit into
mainfrom
queue/5001-1300-openclaw-lancedb
Nov 2, 2026
Merged

dezren39 merged 1 commit into
mainfrom
queue/5001-1300-openclaw-lancedb

Conversation

@dezren39

@dezren39 dezren39 commented Nov 2, 2026 •

Copy link
Copy Markdown
Member

Phase 1 of #1300 (queue task 5001, repo-health-code-pilot, worker repo-worker-code, Lane E). Phase 2 (fleet vector-store decision) is untouched and stays on #1300.

Plugin identity — verified against the catalog: the pinned nix-openclaw catalog (rev 4e5f4446, nix/generated/openclaw-runtime-plugins/memoryLancedb.nix) has memoryLancedb with id memory-lancedb, catalogSource = "official", package @openclaw/memory-lancedb v2026.10.7. That is the plugin enabled here.

Change (home/openclaw/default.nix, +52/−1):

  • runtimePlugins gains "memory-lancedb".
  • plugins.slots.memory = "memory-lancedb" (reversible: remove the slot line + plugin to fall back to the built-in memory backend) and a plugins.entries."memory-lancedb" entry: direct OpenAI-compatible embedding path, autoRecall = true, autoCapture = false.
  • Stable embedding endpoint: a new openclaw-embedding.service (systemd user unit) runs llama-server --embedding on the fixed loopback port 18791, reusing the llama.cpp b11669 binary and Qwen3-Embedding-0.6B-Q8_0.gguf already cached under ~/.cache/opencode by OpenCode's messaging embeddings (its own per-process servers use dynamic ports a static config cannot point at — the gap recorded on Roadmap: vector memory for OpenClaw (memory-lancedb now, fleet vector store later?) #1300). ConditionPathExists on the GGUF makes a cleared cache fail loudly. The gateway unit now starts After + Wants it.
  • Embedding config: baseUrl http://127.0.0.1:18791/v1, model Qwen3-Embedding-0.6B-Q8_0, dimensions = 1024, placeholder apiKey label (loopback server checks no key — same posture as the existing localProvider).

Verified this shift (laptop):

  • nix-instantiate --parse home/openclaw/default.nix — OK.
  • The exact binary + GGUF from the unit, started manually on 18791: POST /v1/embeddings returned a 1024-dimension vector with model Qwen3-Embedding-0.6B-Q8_0. Probe server stopped afterwards; port free.

Not yet done (why this is not merged yet): full module evaluation + the home-manager switch and the live gateway store/recall round-trip (openclaw plugins inspect memory-lancedb --runtime, openclaw ltm store/search) still need a low-load window — the laptop was at load ~136 from other fleet builds during this shift. Task 5001 is parked on that resume condition with this PR as the artifact.


Autofix with [code]smith
Open in [code]smith · Need help on this PR? Tag @codesmith-bot with what you need.

@dezren39
dezren39 requested a review from a team as a code owner November 2, 2026 16:26
@coderabbitai

coderabbitai Bot commented Nov 2, 2026

Copy link
Copy Markdown

Warning

Review limit reached

You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository.

Next included review available in 41 minutes.

Check out review usage here.

View limit details

Limit details: You’ve used the included review currently available.

Learn how review limits work.

Review configuration:

Run configuration
  • Source mode: Auto
  • Repository: Unavailable
  • Branch: Unavailable
  • File: No configuration file from this repository applied
  • Commit: Unavailable
  • Layers: defaults
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: a2e9db9c-91ea-4a78-80f2-eb93ac9328f1
Commits

Reviewing files that changed from the base of the PR and between 466cf98 and ecc757c.

Files selected for processing: 1
  • home/openclaw/default.nix
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

Share

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 2, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-02T16:28:30.804397Z ecc757c PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@dezren39
dezren39 merged commit b401d03 into main Nov 2, 2026
2 checks passed
@dezren39
dezren39 deleted the queue/5001-1300-openclaw-lancedb branch November 2, 2026 19:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant