asepharyana cf1ec25c71 fix(chatbot): disable thinking + use non-streaming LLM call ...

- Set stream:false on the /chat/completions request so the bot gets one
  complete response instead of an SSE token stream.
- Add reasoning_effort:"none" to suppress extended-thinking/reasoning tokens
  (ignored by non-reasoning models like gemini-flash-lite).
- Add parseResponse(): handles both the JSON object 9router returns for
  stream:false and the SSE text it may still emit, delegating SSE to parseSse.
  Verified live: omniroute returns 200 application/json with message.content.

2026-08-16 17:08:29 +07:00

..

scripts

fix(build): make oRPC/tRPC dist runnable under node ESM (deploy crashloop)

2026-08-16 14:45:02 +07:00

src

fix(chatbot): disable thinking + use non-streaming LLM call

2026-08-16 17:08:29 +07:00

tests

style: fix Biome dead-code warnings from oRPC migration (CI lint gate)

2026-08-16 14:51:47 +07:00

ARCHITECTURE.md

docs: sync remaining md (AGENTS, ARCHITECTURE, READMEs to 4001/4009, Nix)

2026-08-02 16:42:57 +07:00

package.json

fix(build): make oRPC/tRPC dist runnable under node ESM (deploy crashloop)

2026-08-16 14:45:02 +07:00

pnpm-lock.yaml

fix(build): make oRPC/tRPC dist runnable under node ESM (deploy crashloop)

2026-08-16 14:45:02 +07:00

tsconfig.json

chore(backend): switch moduleResolution to bundler and remove baseUrl from tsconfig

2026-06-02 19:14:50 +07:00

vitest.config.ts

fix(test): repair placeholder tests referencing deleted @bete/shared package

2026-08-01 22:08:54 +07:00