ouyangbo/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 9 Packages Projects Releases Wiki Activity
35,829 Commits 1 Branch 0 Tags
main
Commit Graph

7 Commits

Author SHA1 Message Date
Teknium 48da317211 refactor(model-providers): tighten router/openrouter bodies, drop __future__ annotations (py>=3.11) 2026-09-02 21:58:26 -07:00
Teknium 40722b322c refactor(model-providers): pack keyword-only profile constructors (comments and multi-line values keep their lines) 2026-09-02 21:45:13 -07:00
Teknium 9338e21093 refactor(model-providers): compact reasoning-translation profiles (opencode, kimi, zai, minimax, nous, qwen, custom, upstage, nebius, meta-ai, deepseek, copilot, deepinfra, vertex, gemini), fold catalog tuples 2026-09-02 21:36:03 -07:00
Teknium 313b244e8f refactor(plugins/model-providers): reuse agent.reasoning_effort clamps, per-model dict tables, compact profiles 2026-09-02 13:30:28 -07:00
kshitijk4poor b954547e72 fix(nebius): route effort through canonical clamp_effort — hand-rolled map inverted the ladder 
Review finding on salvaged #28253: the hand-rolled mapping sent
ultra -> medium while xhigh -> high (stronger request, weaker wire
value). Declare NEBIUS_EFFORTS in agent/reasoning_effort.py and use
clamp_effort like the zai/kimi/tokenhub call sites; disable detection
stays ahead of the clamp since clamp_effort('none', ...) returns the
floor, not off. Adds a monotonicity regression test.
 2026-08-29 20:39:44 +05:30
amrrs 49f5b6a9b4 fix(nebius): request verbose model metadata 2026-08-29 20:39:44 +05:30
amrrs 13bad590f3 feat(providers): add Nebius Token Factory provider 2026-08-29 20:39:44 +05:30