Commit `cd76339`

mo khan <mo@mokhan.ca>

2026-09-05 15:38:09

refactor: rename .elelem config dirs to .agents

Adopts the dotagentsprotocol.com naming convention for prompts/plugins load paths (~/.agents, ./.agents) so a workspace that already has an .agents directory just works. Session logs/transcripts stay under .elelem/sessions -- .agents/ is a protocol-reserved config namespace, not a place for elelem's own ephemeral debug output. Claude-Session: https://claude.ai/code/session_01FpbgyAMtPEkDbo2kx78qR6

main

1 parent f5aa215

Changed files (1)

lib

elelem

llama

plugin.rb

lib/elelem/llama/plugin.rb

@@ -4,7 +4,7 @@ Elelem::Providers.register(:gguf) do
   gpu = %w[vulkan cuda metal].include?(Elelem::Net::GGUF.backend)
 
   Elelem::Net::GGUF.new(
-    model: ENV.fetch("GGUF_MODEL", File.expand_path("~/.elelem/models/Qwen3.8-27B-UD-Q4_K_XL.gguf")),
+    model: ENV.fetch("GGUF_MODEL", File.expand_path("~/.agents/models/Qwen3.8-27B-UD-Q4_K_XL.gguf")),
     # n_ctx/n_threads/n_gpu_layers are calculated, not configured: the native
     # shim asks llama.cpp for the model's trained max context (falling back to
     # smaller sizes if it doesn't fit) and picks thread count from the host's

Commit cd76339

Commit `cd76339`