Skip to content

docs: simplify sharing Ollama, vLLM and LM Studio through plugins - #1823

Merged
michaelneale merged 2 commits into
mainfrom
jimmy/plugin-provider-guide
Sep 12, 2026
Merged

michaelneale merged 2 commits into
mainfrom
jimmy/plugin-provider-guide

Conversation

@michaelneale

@michaelneale michaelneale commented Sep 12, 2026

Copy link
Copy Markdown
Collaborator

Summary

Make sharing an existing Ollama, vLLM or LM Studio server a short, explicit plugin workflow rather than a second runtime command:

Start the provider → install a compatible openai-endpoint → set its URL → mesh-llm serve.

  • New provider quick start with concrete Ollama/vLLM/LM Studio startup recipes and base URLs, plus guidance for other OpenAI-compatible servers.
  • One config block, model-list and completion checks, then client --join from a second machine.
  • FAQ covers no duplicate model download, provider lifecycle, endpoint sharing versus weight splitting, API keys, HTTP-only upstream forwarding, model readiness and command overrides.
  • Update Plugins, Config Models & Plugins, FAQ, Troubleshooting and sidebar navigation.
  • Correct the installer's “latest compatible” claim: it selects a platform archive, not a negotiated host/plugin protocol match.

Companion and rollout

Adapter repair: Mesh-LLM/openai-endpoint#3

Prefer merging the adapter first. Guide links to its compatibility/build instructions are pinned to the reviewed commit so they also work before merge. The adapter's source-build recipe selects its rescue branch; retain it until replaced with a durable release/main reference. Publishing a compatible adapter release is a separate required step—this documentation does not pretend catalog installs are repaired already.

Published adapter 0.1.2 speaks protocol 2 and cannot initialize on Mesh 0.76.0 (protocol 3). Older protocol-2 hosts need their compatible pin. No host code, protocol behavior, or runtime command changes in this PR.

Example

For a running local Ollama server, edit ~/.mesh-llm/config.toml:

[runtime]
mode = "on_demand"

[[plugin]]
name = "openai-endpoint"
url = "http://127.0.0.1:11434/v1"

Start mesh-llm serve, list http://127.0.0.1:9337/v1/models, and send a completion using an exact listed ID. Change only the URL for vLLM (:8000/v1) or LM Studio (:1234/v1).

Validation

  • Website npm run build: CLI inventory, Tailwind, Eleventy, Pagefind passed.
  • Full website browser test script npm run test:cli-explorer passed.
  • node --check website/src/_data/docs.js passed.
  • Checked rendered guide links/anchors from Plugins, FAQ, Config Models and Troubleshooting.
  • Parsed guide/adapter README TOML fences and checked Bash fence syntax.
  • Independent source/docs review completed; HTTPS forwarding limitation, installed metadata vs command override, and private-config assumptions incorporated.
  • git diff --check passed. Generated output is not committed; Rustdoc regeneration/full Mesh runtime build was not needed for these authored docs/navigation changes.

Limits

Recipes checked against provider documentation and host/adapter source, not live certification of each provider. Prior adapter validation used two official Mesh 0.76.0 processes on one Mac with an HTTP fixture, not two machines or real-model/streaming/auth recovery testing. Direct HTTPS upstream and upstream API-key injection are not supported by this URL-only recipe; docs keep unauthenticated providers loopback-only.

Summary by CodeRabbit

  • Documentation
    • Added a guide for connecting Ollama, vLLM, LM Studio, and other OpenAI-compatible endpoints through Mesh.
    • Updated plugin configuration examples, installation steps, compatibility requirements, and provider limitations.
    • Added FAQ entries covering model server behavior, client connections, and API-key handling.
    • Added troubleshooting guidance for endpoint health checks, completion testing, and protocol compatibility.
    • Added the external model endpoints guide to the Plugins navigation.

Document provider setup, private-mesh consumption, release compatibility and the HTTP/authentication limits without adding another runtime command.

Signed-off-by: Michael Neale <14976+michaelneale@users.noreply.github.com>
@coderabbitai

coderabbitai Bot commented Sep 12, 2026

Copy link
Copy Markdown
Contributor

Review Change StackReview Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Advanced

Run ID: 63bbf050-91da-4e79-ace5-332aacbccbd0

📥 Commits

Reviewing files that changed from the base of the PR and between 473cd9b and 2c2fcd5.

📒 Files selected for processing (2)
  • website/src/docs/pages/external-model-endpoints.md
  • website/src/docs/pages/plugins.md
🚧 Files skipped from review as they are similar to previous changes (1)
  • website/src/docs/pages/plugins.md

Included review availability: Your plan provides up to 8 included reviews per hour; 7 remain after this review.


📝 Walkthrough

Walkthrough

The documentation updates external endpoint setup, plugin configuration, adapter compatibility, navigation, FAQ entries, and troubleshooting guidance for Ollama, vLLM, LM Studio, and other OpenAI-compatible providers.

Changes

External model endpoint support

Layer / File(s) Summary
Provider setup guide
website/src/docs/pages/external-model-endpoints.md, website/src/_data/docs.js
Documents adapter 0.2.0 for Mesh 0.76.0, protocol-version pinning, installation commands, compatibility references, and navigation to the provider guide.
Configuration and compatibility workflow
website/src/docs/pages/config-models.md, website/src/docs/pages/plugins.md
Updates loopback endpoint examples, local adapter process guidance, supported providers, installation instructions, workflow steps, and protocol compatibility notes.
FAQ and troubleshooting guidance
website/src/docs/pages/faq.md, website/src/docs/pages/troubleshooting.md
Documents endpoint ownership, authentication limits, validation checks, health distinctions, and protocol mismatch resolution.

Priority: ⬇️ Low

Estimated code review effort: 2 (Simple) | ~10 minutes

Change: Other

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly and concisely describes the main documentation change: simplifying plugin-based sharing for Ollama, vLLM, and LM Studio.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 1…
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch jimmy/plugin-provider-guide

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

Comment @coderabbitai help to get the list of available commands.

i386
i386 previously approved these changes Sep 12, 2026

@i386 i386 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reviewed the docs diff in full — clear provider recipes, honest limitations (no direct https upstream, adapter control connection semantics), consistent nav/data updates. Second approval alongside i386; green CI.

Signed-off-by: Michael Neale <14976+michaelneale@users.noreply.github.com>
@michaelneale
michaelneale enabled auto-merge (squash) September 12, 2026 11:44
@michaelneale
michaelneale merged commit d484109 into main Sep 12, 2026
29 of 31 checks passed
@michaelneale
michaelneale deleted the jimmy/plugin-provider-guide branch September 12, 2026 11:52
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.

2 participants