fix(cli): resolve embedding provider explicitly and surface lane status in sl search (#192)

* feat(cli): add tryUseManagedLocalEmbeddingsDaemon for read-only callers

* feat(cli): add resolveProjectEmbeddingProvider helper

* fix(cli): wire sl search through resolveProjectEmbeddingProvider so semantic lane works

* fix(cli): wire wiki/knowledge search through resolveProjectEmbeddingProvider

* feat(cli): surface embeddings-unavailable status when sl search returns empty

* refactor(cli): route admin reindex through resolveProjectEmbeddingProvider

* refactor: pass embeddingProvider into ingest/scan instead of resolving inside @ktx/context

* refactor(mcp): resolve embedding provider in CLI factory, pass into context ports

* refactor(context): delete MANAGED_SENTENCE_TRANSFORMERS_BASE_URL sentinel

* refactor(cli): delete sentinel-based managed-embeddings indirection

* chore: scrub stale managed-embeddings sentinel references from tests and smoke script

* chore: unexport unused EmbeddingResolutionMode alias

* fix(cli): force pathPrefix="" when targeting the managed embeddings daemon

The managed daemon serves /embeddings/compute directly. The default
pathPrefix in @ktx/llm is /api, so omitting sentenceTransformers from
ktx.yaml produced /api/embeddings/compute -> 404. The resolver now
sets pathPrefix='' explicitly when wiring the managed daemon URL,
matching what the daemon actually exposes.
This commit is contained in:
Andrey Avtomonov 2026-05-21 02:21:22 +02:00 committed by GitHub
parent 56a967278a
commit 9d92c79988
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
36 changed files with 750 additions and 442 deletions

View file

@ -1,7 +1,6 @@
import { mkdtemp, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { MANAGED_SENTENCE_TRANSFORMERS_BASE_URL } from '@ktx/context';
import { buildDefaultKtxProjectConfig, readKtxSetupState, type KtxProjectConfig } from '@ktx/context/project';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import { runKtxSetupRuntimeStep } from './setup-runtime.js';
@ -103,7 +102,6 @@ describe('runKtxSetupRuntimeStep', () => {
baseUrl: 'http://127.0.0.1:61234',
stdoutLog: join(tempDir, '.ktx', 'runtime', 'daemon.stdout.log'),
stderrLog: join(tempDir, '.ktx', 'runtime', 'daemon.stderr.log'),
env: { KTX_MANAGED_SENTENCE_TRANSFORMERS_BASE_URL: 'http://127.0.0.1:61234' },
}));
const config: KtxProjectConfig = {
...buildDefaultKtxProjectConfig(),
@ -113,7 +111,7 @@ describe('runKtxSetupRuntimeStep', () => {
backend: 'sentence-transformers',
model: 'all-MiniLM-L6-v2',
dimensions: 384,
sentenceTransformers: { base_url: MANAGED_SENTENCE_TRANSFORMERS_BASE_URL },
sentenceTransformers: { base_url: '' },
},
},
};