ai-rulez 4.1.0 → 4.1.2

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.
Files changed (2) hide show
  1. package/README.md +14 -4
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -119,7 +119,7 @@ source = "https://github.com/company/ai-rules.git"
119
119
  merge_strategy = "local-override"
120
120
  ```
121
121
 
122
- **Per-agent reasoning effort** — Tune how hard Claude Code subagents think:
122
+ **Reasoning effort across providers** — Tune how hard each AI tool thinks:
123
123
  ```yaml
124
124
  # .ai-rulez/agents/security-reviewer.md
125
125
  ---
@@ -129,11 +129,21 @@ effort: high
129
129
  ---
130
130
  ```
131
131
  ```toml
132
- # .ai-rulez/config.yaml or config.toml — sets the default for agents that don't override
132
+ # .ai-rulez/config.yaml or config.toml
133
133
  [defaults]
134
- effort = "medium"
134
+ effort = "medium" # global default for every supported preset
135
+
136
+ [defaults.effort_by_preset]
137
+ codex = "high" # overrides the global default for Codex
138
+ claude = "xhigh" # …and for Claude
135
139
  ```
136
- Accepted values: `low`, `medium`, `high`, `xhigh`, `max`, `inherit`. Available levels depend on the model. Other presets ignore the field until they ship native support.
140
+ Accepted values: `low`, `medium`, `high`, `xhigh`, `max`, `inherit`. ai-rulez emits the right field per preset:
141
+ - **Claude** — `effort` in `.claude/agents/*.md` frontmatter (per-agent)
142
+ - **Codex** — `model_reasoning_effort` in `.codex/config.toml` (global)
143
+ - **Amp** — `amp.anthropic.effort` in `.amp/settings.json` (global)
144
+ - **Windsurf** — `reasoning_effort` in `.windsurf/agents/*.md` frontmatter (per-agent)
145
+
146
+ Each preset maps the value to its own vocabulary; tools without a documented config surface (Cursor, Copilot, Gemini, etc.) are silently skipped. See [docs/configuration.md](docs/configuration.md#defaults) for the full mapping table.
137
147
 
138
148
  **Installed Skills** — Pull reusable skills from external repos:
139
149
  ```toml
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ai-rulez",
3
- "version": "4.1.0",
3
+ "version": "4.1.2",
4
4
  "description": "Complete AI development workflow for 19+ tools. Ships with builtin rules, agents, and conventions. Generate native configs for Claude, Cursor, Copilot, Windsurf, Gemini, Codex and more from a single source.",
5
5
  "keywords": [
6
6
  "ai",