feat(kernel-language-model-service): Add language model client#876
Open
feat(kernel-language-model-service): Add language model client#876
Conversation
grypez
force-pushed
the
grypez/language-model-client
branch
from
f2a4ffd to
e3cf0b3
Compare
Contributor
grypez
force-pushed
the
grypez/language-model-client
branch
from
e3cf0b3 to
5296cb9
Compare
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
Contributor
Author
|
@cursoragent review this PR for inconsistencies across docstrings, documentation and naming conventions |
|
Unable to authenticate your request. Please make sure to connect your GitHub account to Cursor. Go to Cursor |
Add @ocap/kernel-language-model-service — a new package that bridges the kernel with OpenAI-compatible language model backends. Core types and kernel service: - ChatParams / ChatResult / ChatService types for request/response shapes - makeKernelLanguageModelService: registers a kernel service object that dispatches chat calls to a provided chat function - LANGUAGE_MODEL_SERVICE_NAME constant Backends: - Open /v1 backend with SSE streaming (makeOpenV1NodejsService) - Ollama Node.js backend (OllamaNodejsService) Client API: - makeChatClient: returns an OpenAI-SDK-compatible client object that routes chat.completions.create() calls through a CapTP ChatService - makeSampleClient: convenience wrapper for single-token sampling Test utilities: - makeMockOpenV1Fetch: deterministic SSE mock for unit/integration tests Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add an integration test and e2e test that exercise the full kernel → LMS service → Ollama round-trip via a bundled vat. - lms-chat-vat: bundled vat that sends a single chat message and logs the response, used to verify the round-trip through the kernel - lms-chat.ts: shared test helper (runLmsChatKernelTest) - lms-chat.test.ts: uses a mock fetch — CI-safe, no network - lms-chat.e2e.test.ts: uses real fetch against local Ollama - agents.e2e.test.ts: json/repl agent e2e tests against local Ollama - test/suite.test.ts: pre-flight check that Ollama is running Lay out the package to match kernel-test: all vats, helpers, and test files live under src/; test/ holds only the Ollama pre-flight suite. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
grypez
force-pushed
the
grypez/language-model-client
branch
from
2dffa25 to
ea9f656
Compare
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, have a team admin enable autofix in the Cursor dashboard.
| chat: async (params: ChatParams) => service.chat(params), | ||
| sample: async (params: SampleParams) => service.sample(params), | ||
| }); | ||
| }; |
There was a problem hiding this comment.
New factory function exported but never reachable
Low Severity
makeOllamaNodejsKernelService is exported from ollama/nodejs.ts and its JSDoc says it's "for use with makeKernelLanguageModelService", but it is never re-exported from index.ts and has zero usages anywhere in the codebase. Consumers of the package have no path to this function through the public API.
Additional Locations (1)
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
1 participant
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.
feat(kernel-language-model-service): open v1 backend and vat clientsKernel service (
src/kernel-service.ts):makeKernelLanguageModelServicewraps achat(and optionalsample) function into a flat, hardened object suitable forkernel.registerKernelServiceObject(). Return values are plain data — no exos — so they cross the marshal boundary cleanly. Exported asLANGUAGE_MODEL_SERVICE_NAME = 'languageModelService'.Open /v1 backend (
src/open-v1/):OpenV1BaseServiceposts to/v1/chat/completionswith injectedfetch, supporting both single-response and SSE streaming modes.makeOpenV1NodejsServiceis the Node.js entry point (acceptsbaseUrland optionalapiKey).Ollama backend (
src/ollama/):OllamaNodejsServiceextends the Open /v1 base, defaulting tohttp://localhost:11434and adding amakeInstance({ model })factory.Vat clients (
src/client.ts):makeChatClientreturns an OpenAI-SDK-shaped object (client.chat.completions.create(...)) that routes calls through a CapTPChatServicereference viaE().makeSampleClientis the equivalent for raw token sampling.Test utilities (
src/test-utils/): Replaces the previous queue-based mock model withmakeMockOpenV1Fetch— a deterministic SSE mock that emits a configured sequence of token strings, keeping integration tests CI-safe and fast.makeMockSampleprovides the same for the sample path.Also updates
kernel-testto use the new chat/sample API: replaceslms-user-vat/lms-queue-vatwithlms-chat-vat/lms-sample-vatand the corresponding test files.test(kernel-test-local): kernel-LMS integration testsAdds two test variants that share a common
runLmsChatKernelTesthelper:lms-chat.test.ts(CI): injectsmakeMockOpenV1Fetch— no network, runs undertest:dev.lms-chat.e2e.test.ts(local): uses realfetchagainst a local Ollama instance, run viatest:e2e:local.Both launch a subcluster with
lms-chat-vatthrough the kernel, register the LMS kernel service, and assert that the vat logslms-chat response: Hello(or equivalent).Also adds
agents.e2e.test.ts(moved from the old layout) exercising json/repl agents end-to-end, andtest/suite.test.tsas an Ollama pre-flight check.Note
Medium Risk
Adds new kernel-exposed service surfaces (
chat/sample) plus an OpenAI-compatible HTTP backend with SSE parsing; correctness and type-safety around streaming/non-streaming behavior and marshal-safe hardening are the main risks. Also updates multiple integration tests and local e2e wiring, which may affect CI/local test stability.Overview
Adds a new language-model service API suitable for kernel registration and vat consumption.
makeKernelLanguageModelServiceexposes a hardened{ chat, sample }service under the canonicalLANGUAGE_MODEL_SERVICE_NAME, and new vat-side helpersmakeChatClient/makeSampleClientprovide OpenAI-style ergonomics while enforcing model selection.Introduces new backends and expands Ollama support. Adds an Open
/v1/chat/completionsNode.js backend (makeOpenV1NodejsService) with optional API key and SSE streaming support, and extends the Ollama service to supportchatand rawsample(generate withraw: true) plus amakeOllamaNodejsKernelServiceadapter.Reworks tests and test utilities around the new API. Replaces the queue-based test LMS with
makeMockOpenV1FetchandmakeMockSample, adds unit coverage for the new clients/kernel service/Open v1 streaming, and updateskernel-testandkernel-test-localto run new chat/sample vat round-trip tests (including a local Ollama e2e path and updated build/runner config).Written by Cursor Bugbot for commit ea9f656. This will update automatically on new commits. Configure here.