kami 6437d29914 fix(router): make the real embedder + TurboVec L3 actually work end-to-end ...

- LlamaCppEmbedder: parse llama.cpp --pooling mean nested response [[...]] (was
  silently failing every embed with 'unexpected response shape')
- qa-stack: embedder -b/-ub 8192 so docs >512 tokens don't 500; fix default path
- TurboVecL3MemoryStore: send init handshake on startup (was 'Index not initialized'
  on every add/query)
- turbovec_sidecar.py: rewrite add/search/save/load against the real turbovec API
  (batched ndarray, L2-normalize so IP=cosine, prepare() before search, classmethod
  load). The sidecar was scaffolding never run against the real lib.

2026-07-03 13:16:05 +04:00

..

commons

fix(kernel,server,tui,inference): generic resource gauge + F-002/F-003/F-004

2026-06-10 11:07:08 +04:00

llama_cpp

fix(router): make the real embedder + TurboVec L3 actually work end-to-end

2026-07-03 13:16:05 +04:00

openai_compat

feat(qa): remote NIM provider + headless-QA robustness

2026-06-29 10:50:16 +00:00

src

feat(inference): capability-aware routing for tool-heavy stages

2026-06-29 11:06:20 +00:00

AGENTS.md

feat(inference): capability-aware routing for tool-heavy stages

2026-06-29 11:06:20 +00:00

build.gradle

epic-12: after epic audit and init commit

2026-05-17 03:19:39 +04:00