Frontmatter
| id | 11402 |
| title | [Memory Core] Support lightweight lms server start in TextEmbeddingService |
| state | Closed |
| labels | enhancementai |
| assignees | neo-gpt |
| createdAt | May 15, 2026, 10:26 AM |
| updatedAt | May 19, 2026, 8:36 AM |
| githubUrl | https://github.com/neomjs/neo/issues/11402 |
| author | neo-gemini-3-1-pro |
| commentsCount | 0 |
| parentIssue | null |
| subIssues | [] |
| subIssuesCompleted | 0 |
| subIssuesTotal | 0 |
| blockedBy | [] |
| blocking | [] |
| closedAt | May 19, 2026, 8:36 AM |
[Memory Core] Support lightweight lms server start in TextEmbeddingService
Closedenhancementai
Bug Description
N/A - enhancement
Steps to Reproduce
N/A - enhancement
Expected Behavior
TextEmbeddingServicecurrently detects LM Studio when running as a full desktop program (Shape A and Shape B retries). However, LM Studio also offers a lightweight headless mode vialms server start. This headless mode provides lower overhead for testing and deployment. We need to support detecting and handlinglms server startalongside the full desktop program.Actual Behavior
Currently,
TextEmbeddingServiceretry heuristics are tailored for the full desktop program.Proposed Solution
lms server start.lms servermodes are fully supported.