Enhance token handling and refactor tool execution (#754)

* Add token handling improvements and error serialization to tool execution

* Refactor function to tool nomenclature, add token handling, and implement tool options.

* Add logWarn for error handling and adjust tracing in tool calls

* Refactor: Rename "functions" to "tools" in promptdom.ts for clarity

* Replace `writeText` with `assistant` function and update schema formatting across files.

* Add pricing data and cost calculation to GenerationStats with API integration

* Refactor cost calculation into `estimateCost` function for reuse.

* Add count parameter, increase token limits, and update cost rendering logic

docs/src/content/docs/reference/scripts/response-priming.md

@@ -1,59 +1,51 @@
 ---
 title: Response Priming
 sidebar:
-  order: 100
+    order: 100
 description: Learn how to prime LLM responses with specific syntax or format
-  using the writeText function in scripts.
+    using the writeText function in scripts.
 keywords: response priming, LLM syntax, script formatting, writeText function,
-  assistant message
+    assistant message
 genaiscript:
-  model: openai:gpt-3.5-turbo
-
+    model: openai:gpt-3.5-turbo
 ---
 
 It is possible to provide the start of the LLM response (`assistant` message) in the script.
 This allows to steer the answer of the LLM to a specify syntax or format.
 
-Use `writeText` with the `{assistant: true}` option to provide the assistant text.
+Use `assistant` function to provide the assistant text.
 
 ```js
 $`List 5 colors. Answer with a JSON array. Do not emit the enclosing markdown.`
 
 // help the LLM by starting the JSON array syntax
 // in the assistant response
-writeText(`[`, { assistant: true })
+assistant(`[`)
 ```
 
 <!-- genaiscript output start -->
 
 <details>
 <summary>👤 user</summary>
 
-
 ```markdown wrap
 List 5 colors. Answer with a JSON array. Do not emit the enclosing markdown.
 ```
 
-
 </details>
 
-
 <details open>
 <summary>🤖 assistant</summary>
 
-
 ```markdown wrap
 [
 ```
 
-
 </details>
 
-
 <details open>
 <summary>🤖 assistant</summary>
 
-
 ```markdown wrap
 "red",
 "blue",
@@ -63,13 +55,10 @@ List 5 colors. Answer with a JSON array. Do not emit the enclosing markdown.
 ]
 ```
 
-
 </details>
 
 <!-- genaiscript output end -->
 
-
-
 ### How does it work?
 
 Internally when invoking the LLM, an additional message is added to the query as if the LLM had generated this content.

docs/src/content/docs/reference/scripts/system.mdx

@@ -1043,6 +1043,10 @@ defTool(
                 enum: ["success", "failure"],
                 description: "Filter runs by completion status",
             },
+            count: {
+                type: "number",
+                description: "Number of runs to list. Default is 20.",
+            },
         },
     },
     async (args) => {
@@ -1053,6 +1057,7 @@ defTool(
         const res = await github.listWorkflowRuns(workflow_id, {
             branch,
             status,
+            count: 20,
         })
         return CSV.stringify(
             res.map(({ id, name, conclusion, head_sha }) => ({

packages/core/src/aici.ts

@@ -100,7 +100,7 @@ export async function renderAICI(functionName: string, root: PromptNode) {
         },
         // Unsupported node types
         image: notSupported("image"),
-        function: notSupported("function"),
+        tool: notSupported("tool"),
         assistant: notSupported("assistant"),
         schema: notSupported("schema"),
         // Capture output processors