Michal a432e9e19f feat(gate): terse selection prompt so a no-think model answers in ~2s ...

With the fast (no-think) route, gate-selection latency is now proportional to the
ANSWER length (a no-think model runs ~10-13 tok/s), not hidden thinking. A verbose
"reasoning" field pushed a selection to ~9s (over the 8s budget). Request compact
JSON with a <=8-word reasoning → ~2s (vs ~9s prose, or ~1.2s with no reasoning).
Validated live against vllm-fast (glm-4.6-reap-fast): 2.0s, valid selection JSON,
zero reasoning tokens.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-07-24 21:38:08 +01:00

..

src

feat(gate): terse selection prompt so a no-think model answers in ~2s

2026-07-24 21:38:08 +01:00

tests

feat(gate): route prompt-selection through mcpd's server Llm (credential tiering)

2026-07-24 12:43:48 +01:00

package.json

feat: HTTP-mode mcplocal container + mcpctl test mcp + token-auth preHandler

2026-04-17 01:21:42 +01:00

tsconfig.json

feat: implement v2 3-tier architecture (mcpctl → mcplocal → mcpd)

2026-02-22 11:42:06 +00:00

vitest.config.ts

feat: eager vLLM warmup and smart page titles in paginate stage

2026-03-03 19:07:39 +00:00

vitest.smoke.config.ts

feat: eager vLLM warmup and smart page titles in paginate stage

2026-03-03 19:07:39 +00:00