[pull] main from paralleldrive:main

README.md

@@ -13,6 +13,7 @@ All sufficiently advanced language models understand it without any special prom
 - **Referential omnipotence.** You do not need to explicitly define most functions. The AI will infer them for you.
 - **Functions and function composition** with the `|>` operator.
 - **Mermaid diagrams** for visualizing complex topics like architecture, flow control, and sequence descriptions.
+- **Options** for customizing the behavior of your program. See the [example](examples/reflective-thought-composition.sudo).
 
 ## Why SudoLang?
 

examples/learn-sudolang.sudo

@@ -65,6 +65,16 @@ Foo {
 }
 ```
 
+## Options
+
+SudoLang supports various options to customize the behavior of your program. These options can be specified using the `Options` keyword in the SudoLang prompt. Here are some examples:
+
+```SudoLang
+Options {
+  depth: 1..10|String
+}
+```
+
 Because it's an LLM, many functions can be automagically inferred. Just call a function with a descriptive name without defining it, and it will usually work.
 
 ---

examples/reflective-thought-composition.readme.md

@@ -13,6 +13,9 @@ The module uses emojis to visually represent different phases of the thinking pr
 * ⚖️ **Evaluation** - Consider options
 * 💬 **Response** - Consolidate previous insights, integrate, synthesize, and return a well-rounded response
 
+## Options
+
+The RTC module supports various options to customize the AI's responses. Use the `/help` command for details.
 
 ## Installation
 

sudolang.sudo.md

@@ -18,6 +18,7 @@ SudoLang is designed to be understood by LLMs without any special prompting. **A
 - **Semantic Pattern Matching**. AI can infer program states intelligently and match patterns like `(post contains harmful content) => explain(content policy)`.
 - **Referential omnipotence.** You do not need to explicitly define most functions. The AI will infer them for you.
 - **Mermaid diagrams** for visualizing complex topics like architecture, flow control, and sequence descriptions.
+- **Options** for customizing the behavior of your program. See the [example](examples/reflective-thought-composition.sudo).
 
 ### Markdown
 
@@ -315,6 +316,44 @@ graph LR
     Oven -->|Non-linear transformation| Cake
 ```
 
+## Options
+
+SudoLang supports various options to customize the behavior of your program. These options can be specified using the `Options` keyword in the SudoLang prompt. Here are some examples:
+
+```SudoLang
+Options {
+  depth: 1..10|String
+}
+```
+
+### Depth Parameter
+
+The depth parameter controls the level of detail in the AI's response. You can specify a numeric value or a descriptive string. Here are some examples:
+
+```SudoLang
+Why is the sky blue? -depth 1
+```
+
+This will result in a simple, short answer. If you want more depth, try:
+
+```SudoLang
+Why is the sky blue? -depth 10
+```
+
+You can also use descriptive strings for the depth parameter:
+
+```SudoLang
+Why is the sky blue? -depth kindergarten
+```
+
+Or
+
+```SudoLang
+Why is the sky blue? -depth PhD
+```
+
+For more details, see the [example](examples/reflective-thought-composition.sudo).
+
 ## Implicit LLM Capabilities
 
 SudoLang is a very expressive way to express traditional programming concepts. However, SudoLang also has access to the full inference capabilities of your favorite LLM. It is capable of much more than what is described here. Here are some of the capabilities that are not explicitly described in the language specification. An LLM running SudoLang can: