file format eval

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

@@ -590,7 +590,7 @@
 
 $`## DIFF file format
 
-The DIFF format should be used to generate diff changes on large files: 
+The DIFF format should be used to generate diff changes on large files with small number of changes: 
 
 - existing lines must start with their original line number: [<line number>] <line>
 - deleted lines MUST start with - followed by the line number: - [<line number>] <deleted line>
@@ -608,7 +608,7 @@
 - only emit a couple unmodified lines before and after the changes
 - keep the diffs AS SMALL AS POSSIBLE
 - when reading files, ask for line numbers
-- minimize the number of unmodified lines
+- minimize the number of unmodified lines. DO NOT EMIT MORE THEN 2 UNMODIFIED LINES BEFORE AND AFTER THE CHANGES. Otherwise use the FILE file format.
 
 - do NOT generate diff for files that have no changes
 - do NOT emit diff if lines are the same
@@ -620,39 +620,43 @@
 
 ### Examples:
 
 FOLLOW THE SYNTAX PRECISLY. THIS IS IMPORTANT.
 DIFF ./file.ts:
 \`\`\`diff
-[original line number]  <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 - [original line number] <deleted line>
 + <added line>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
 DIFF ./file2.ts:
 \`\`\`diff
-[original line number]   <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 - [original line number] <deleted line>
 - [original line number] <delete line 2>
 + <added line>
 + <added line 2>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
 DIFF ./file3.ts:
 \`\`\`diff
-[original line number]   <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 + <added line>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
 DIFF ./file4.ts:
 \`\`\`diff
-[original line number]   <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 - [original line number] <deleted line>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
+## Choosing what file format to use
+
+- If the file content is large (> 50 lines) and the changes are small, use the DIFF format.
+- In all other cases, use the FILE file format.
 `
 
 `````
@@ -688,9 +692,9 @@
 })
 
 const folder = env.vars["outputFolder"] || "."
-$`## Files
+$`## FILE file format
 
-When generating or updating files you will use the following syntax:`
+When generating or updating files you should use the FILE file syntax preferrably:`
 
 def(`File ${folder}/file1.ts`, `What goes in\n${folder}/file1.ts.`, {
     language: "typescript",
@@ -705,9 +709,24 @@
     language: "markdown",
 })
 
+$`You MUST specify a start_line and end_line to only update a specific part of a file:
+
+FILE ${folder}/file1.py:
+\`\`\`python start_line=15 end_line=20
+Replace line range 15-20 in \n${folder}/file1.py
+\`\`\`
+
+FILE ${folder}/file1.py:
+\`\`\`python start_line=30 end_line=35
+Replace line range 30-35 in \n${folder}/file1.py
+\`\`\`
+
+`
+
 $`- Make sure to use precisely \`\`\` to guard file code sections.
 - Always sure to use precisely \`\`\`\`\` to guard file markdown sections.
-- Use full path of filename in code section header.`
+- Use full path of filename in code section header.
+- Use start_line, end_line for large files with small updates`
 if (folder !== ".")
     $`When generating new files, place files in folder "${folder}".`
 $`- If a file does not have changes, do not regenerate.

packages/core/src/genaisrc/system.diff.genai.js

@@ -5,7 +5,7 @@ system({
 
 $`## DIFF file format
 
-The DIFF format should be used to generate diff changes on large files: 
+The DIFF format should be used to generate diff changes on large files with small number of changes: 
 
 - existing lines must start with their original line number: [<line number>] <line>
 - deleted lines MUST start with - followed by the line number: - [<line number>] <deleted line>
@@ -23,7 +23,7 @@ The DIFF format should be used to generate diff changes on large files:
 - only emit a couple unmodified lines before and after the changes
 - keep the diffs AS SMALL AS POSSIBLE
 - when reading files, ask for line numbers
-- minimize the number of unmodified lines
+- minimize the number of unmodified lines. DO NOT EMIT MORE THEN 2 UNMODIFIED LINES BEFORE AND AFTER THE CHANGES. Otherwise use the FILE file format.
 
 - do NOT generate diff for files that have no changes
 - do NOT emit diff if lines are the same
@@ -38,34 +38,38 @@ The DIFF format should be used to generate diff changes on large files:
 FOLLOW THE SYNTAX PRECISLY. THIS IS IMPORTANT.
 DIFF ./file.ts:
 \`\`\`diff
-[original line number]  <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 - [original line number] <deleted line>
 + <added line>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
 DIFF ./file2.ts:
 \`\`\`diff
-[original line number]   <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 - [original line number] <deleted line>
 - [original line number] <delete line 2>
 + <added line>
 + <added line 2>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
 DIFF ./file3.ts:
 \`\`\`diff
-[original line number]   <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 + <added line>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
 DIFF ./file4.ts:
 \`\`\`diff
-[original line number]   <2 lines before changes (not the whole file)>
+[original line number]  line before changes
 - [original line number] <deleted line>
-[original line number]   <2 lines after changes (not the whole file)>
+[original line number]  line after changes
 \`\`\`
 
+## Choosing what file format to use
+
+- If the file content is large (> 50 lines) and the changes are small, use the DIFF format.
+- In all other cases, use the FILE file format.
 `

packages/core/src/genaisrc/system.files.genai.mjs

@@ -0,0 +1,46 @@
+system({
+    title: "File generation",
+    description: "Teaches the file format supported by GenAIScripts",
+})
+
+const folder = env.vars["outputFolder"] || "."
+$`## FILE file format
+
+When generating or updating files you should use the FILE file syntax preferrably:`
+
+def(`File ${folder}/file1.ts`, `What goes in\n${folder}/file1.ts.`, {
+    language: "typescript",
+})
+def(`File ${folder}/file1.js`, `What goes in\n${folder}/file1.js.`, {
+    language: "javascript",
+})
+def(`File ${folder}/file1.py`, `What goes in\n${folder}/file1.py.`, {
+    language: "python",
+})
+def(`File /path_to_file/file2.md`, `What goes in\n/path_to_file/file2.md.`, {
+    language: "markdown",
+})
+
+$`You MUST specify a start_line and end_line to only update a specific part of a file:
+
+FILE ${folder}/file1.py:
+\`\`\`python start_line=15 end_line=20
+Replace line range 15-20 in \n${folder}/file1.py
+\`\`\`
+
+FILE ${folder}/file1.py:
+\`\`\`python start_line=30 end_line=35
+Replace line range 30-35 in \n${folder}/file1.py
+\`\`\`
+
+`
+
+$`- Make sure to use precisely \`\`\` to guard file code sections.
+- Always sure to use precisely \`\`\`\`\` to guard file markdown sections.
+- Use full path of filename in code section header.
+- Use start_line, end_line for large files with small updates`
+if (folder !== ".")
+    $`When generating new files, place files in folder "${folder}".`
+$`- If a file does not have changes, do not regenerate.
+- Do NOT emit line numbers in file.
+- CSV files are inlined as markdown tables.`

packages/core/src/promptdom.ts

@@ -243,12 +243,14 @@
     while (dfence && body.includes(dfence)) {
         dfence += "`"
     }
+    const diffFormat = "" // body.length > 500 ? "preferred_diff_format=DIFF" : ""
     const res =
         (name ? name + ":\n" : "") +
         dfence +
         dtype +
         (file.filename ? ` file="${file.filename}"` : "") +
         (schema ? ` schema=${schema}` : "") +
+        diffFormat +
         "\n" +
         body +
         dfence +

packages/core/src/systems.ts

@@ -8,7 +8,7 @@
 /**
  * Function to resolve and return a list of systems based on the provided script and project.
  * This function analyzes the script options and JavaScript source code to determine applicable systems.
- * 
+ *
  * @param prj - The project object containing templates and other project-related data.
  * @param script - An object containing options for the prompt system, model options, and optionally JavaScript source code.
  * @returns An array of unique system IDs that are applicable based on the analysis.
@@ -45,6 +45,7 @@
         if (/\Wchangelog\W/i.test(jsSource)) systems.push("system.changelog")
         else if (/\Wfile\W/i.test(jsSource)) {
             systems.push("system.files")
+           // systems.push("system.diff")
             // Add file schema system if schema is used
             if (useSchema) systems.push("system.files_schema")
         }
@@ -82,7 +83,7 @@
 /**
  * Helper function to resolve tools in the project and return their system IDs.
  * Finds systems in the project associated with a specific tool.
- * 
+ *
  * @param prj - The project object containing templates and other project-related data.
  * @param tool - The tool ID to resolve systems for.
  * @returns An array of system IDs associated with the specified tool.
@@ -99,7 +100,7 @@
 /**
  * Function to resolve tools in the project based on provided systems and tools.
  * This function returns a list of tool objects with their IDs and descriptions.
- * 
+ *
  * @param prj - The project object containing templates and other project-related data.
  * @param systems - An array of system IDs to resolve tools for.
  * @param tools - An array of tool IDs to resolve tools for.

packages/sample/src/edits/edits_files_diff.genai.mts

@@ -14,3 +14,4 @@ script({
 })
 import { editTest } from "./fileedittest.mts"
 editTest()
+//$`Use DIFF for changes in src/edits/su/fib.ts`

packages/sample/src/edits/edits_tool.genai.mts

@@ -0,0 +1,58 @@
+script({
+    model: "large",
+    files: "src/edits/fibs/fib.*",
+    system: ["system"],
+    lineNumbers: true,
+    tests: [
+        {
+            files: "src/edits/fibs/fib.*",
+        },
+        {
+            files: "src/edits/bigfibs/fib.*",
+        },
+    ],
+})
+import { editTest } from "./fileedittest.mts"
+
+$`## File edits
+
+Use the 'file_edit' tool to update a file with new content. THIS IS IMPORTANT
+
+`
+
+editTest()
+
+defTool(
+    "file_edit",
+    "Updates a file with new content. If the file is large, use lineStart and lineEnd in multiple tool calls to split the update into multiple parts THIS IS VERY IMPORTANT.",
+    {
+        type: "object",
+        properties: {
+            filename: {
+                type: "string",
+                description:
+                    "The path of the file to update relative to the workspace root",
+            },
+            content: {
+                type: "string",
+                description:
+                    "The new content to write to the file. Preserve white space.",
+            },
+            lineStart: {
+                type: "number",
+                description: "The line number to start the edit",
+            },
+            lineEnd: {
+                type: "number",
+                description: "The line number to end the edit",
+            },
+        },
+        required: ["filename", "content"],
+    },
+    async (args) => {
+        const { context, filename, content, lineStart, lineEnd } = args
+        context.log(`${filename}#L${lineStart || ""}:${lineEnd || ""}`)
+        context.log(content)
+        return "ok"
+    }
+)