Skip to content

feat: streamline model provider options and add inherit/local hints#1658

Merged
hijzy merged 2 commits into
MemTensor:mem-agent-0424from
syzsunshine219:test/hermes-plugin-0428
May 8, 2026
Merged

feat: streamline model provider options and add inherit/local hints#1658
hijzy merged 2 commits into
MemTensor:mem-agent-0424from
syzsunshine219:test/hermes-plugin-0428

Conversation

@syzsunshine219
Copy link
Copy Markdown
Collaborator

@syzsunshine219 syzsunshine219 commented May 8, 2026

Summary

  • Embedding providers: simplified to local / openai_compatible / gemini (removed cohere, voyage, mistral, anthropic — Anthropic has no embedding API)
  • Summarizer providers: added (inherit) option to reuse the agent's model; simplified to inherit / openai_compatible / gemini / anthropic
  • Skill Evolver providers: simplified to inherit / openai_compatible / gemini / anthropic
  • Added hint text when embedding uses local ("MiniLM-L6-v2, 384-dim, ~23 MB") and when summarizer/skill evolver uses (inherit)
  • Updated schema.ts to allow empty string provider for LLM inherit mode
  • Updated defaults.ts to default LLM provider to "" (inherit from agent)
  • Chinese and English i18n strings added

Test plan

  • Verified provider dropdowns show correct options in Settings UI
  • Verified local hint and inherit hint display correctly
  • Verified schema validation passes when saving with (inherit) provider
  • Ran full Hermes v2 intent-driven test suite (120 passed, no new regressions)
  • Confirmed embedding (bge-m3), summarizer, and skill evolver init correctly from logs

jiachengzhen and others added 2 commits May 8, 2026 14:23
The retrieval ranker's limit was the SUM of per-tier topK values
(e.g. topK={tier1:3,tier2:3,tier3:3} → limit=9), allowing merged
results to exceed the caller's expected total. Now searchMemory
enforces per-tier caps before returning hits, so topK=3 per tier
returns at most 3 results per tier instead of up to 9 total.

Fixes [BUG-2026-05-08] skill-type overflow in search results.

Co-authored-by: Cursor <cursoragent@cursor.com>
- Embedding: keep local/openai_compatible/gemini, remove cohere/voyage/mistral/anthropic
- Summarizer: add (inherit) option to reuse agent model, remove bedrock/host/local_only
- Skill Evolver: keep inherit/openai_compatible/gemini/anthropic, remove bedrock
- Add localHint for embedding (MiniLM-L6-v2 384-dim info) and inheritsLabel for summarizer
- Update schema.ts and defaults.ts to allow empty provider for LLM inherit mode

Co-authored-by: Cursor <cursoragent@cursor.com>
@hijzy hijzy merged commit 6e7ad22 into MemTensor:mem-agent-0424 May 8, 2026
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