teknium1 b84f9e410c feat: default reasoning effort from xhigh to medium ...

Reduces token usage and latency for most tasks by defaulting to
medium reasoning effort instead of xhigh. Users can still override
via config or CLI flag. Updates code, tests, example config, and docs.

2026-03-07 10:14:19 -08:00

..

developer-guide

feat: platform-conditional skill loading + Apple/macOS skills

2026-03-07 00:47:54 -08:00

getting-started

fix: allow self-hosted Firecrawl without API key + add self-hosting docs

2026-03-05 16:44:21 -08:00

reference

feat: add z.ai/GLM, Kimi/Moonshot, MiniMax as first-class providers

2026-03-06 18:55:18 -08:00

user-guide

feat: default reasoning effort from xhigh to medium

2026-03-07 10:14:19 -08:00

index.md

docs: rebrand messaging — 'the self-improving AI agent'

2026-03-06 04:34:06 -08:00