@eigenpal/cli 0.23.18 → 0.23.20

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -132,7 +132,7 @@ eigenpal workflow step-type list --search <partial-match>
132
132
  ### Eval flakiness with `llm-judge`
133
133
 
134
134
  LLM-judge scores have variance. Stabilize: select a current model
135
- (`openai/gpt-6.1-sol`), keep its reasoning effort fixed, narrow the prompt to
135
+ (`openai/gpt-6.2-sol`), keep its reasoning effort fixed, narrow the prompt to
136
136
  one dimension per judge, run multiple experiments and average. Only set
137
137
  temperature when the model supports it; reasoning models may reject it.
138
138
 
@@ -301,7 +301,7 @@ process — `--out` writes the file directly from the server's storage.
301
301
 
302
302
  LLM-judge scores have variance. To reduce flake:
303
303
 
304
- - Select a current model (`openai/gpt-6.1-sol`) and keep its reasoning effort fixed.
304
+ - Select a current model (`openai/gpt-6.2-sol`) and keep its reasoning effort fixed.
305
305
  Re-run representative evaluations when changing models or when the provider updates it.
306
306
  - Keep `promptExtension` narrow — score one dimension per evaluator. Use
307
307
  multiple judges instead of one omnibus prompt.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@eigenpal/cli",
3
- "version": "0.23.18",
3
+ "version": "0.23.20",
4
4
  "description": "Eigenpal CLI — author and run document workflows from your terminal. Agent-ready.",
5
5
  "keywords": [
6
6
  "eigenpal",