🔧 Update changelog formats, tests, and poetry lines

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

@@ -505,11 +505,12 @@ Generate changelog formatter edits
 `````js wrap title="system.changelog"
 system({
     title: "Generate changelog formatter edits",
-    lineNumbers: true
+    lineNumbers: true,
 })
 
+$`## CHANGELOG file format
 
-$`For partial updates of files, return one or more ChangeLogs (CLs) formatted as follows. Each CL must contain
+For partial updates of large files, return one or more ChangeLogs (CLs) formatted as follows. Each CL must contain
 one or more code snippet changes for a single file. There can be multiple CLs for a single file.
 Each CL must start with a description of its changes. The CL must then list one or more pairs of
 (OriginalCode, ChangedCode) code snippets. In each such pair, OriginalCode must list all consecutive
@@ -519,7 +520,8 @@ lines of code (again including the same few lines before and after the changes).
 OriginalCode and ChangedCode must start at the same source code line number N. Each listed code line,
 in both the OriginalCode and ChangedCode snippets, must be prefixed with [N] that matches the line
 index N in the above snippets, and then be prefixed with exactly the same whitespace indentation as
-the original snippets above. See also the following examples of the expected response format.
+the original snippets above. Each OriginalCode must be paired with ChangedCode. Do NOT add multiple ChangedCode per OriginalCode.
+See also the following examples of the expected response format.
 
 CHANGELOG:
 \`\`\`\`\`changelog
@@ -553,7 +555,14 @@ OriginalCode@23-23:
 ChangedCode@23-23:
 [23] <white space> <changed code line>
 \`\`\`\`\`
+
+## Choosing what file format to use
+
+- If the file content is small (< 20 lines), use the full FULL format.
+- If the file content is large (> 50 lines), use CHANGELOG format.
+- If the file content IS VERY LARGE, ALWAYS USE CHANGELOG to save tokens.
 `
+
 `````
 
 

packages/core/src/changelog.test.ts

@@ -259,4 +259,24 @@ ChangedCode@105-107:
         console.log(res)
         assert.equal(res[0].filename, "src/edits/su/fib.ts")
     })
+
+    test("unbalancred fences", () => {
+        const source = `\`\`\`\`\`changelog
+ChangeLog:1@src/edits/bigfibs/fib.py
+Description: Implemented new_function, removed comments and empty lines.
+OriginalCode@48-51:
+[48] def new_function(sum):
+[49]     # TODO
+[50]     return 0
+[51]     # return (10 - (sum % 10)) % 10;
+ChangedCode@48-50:
+[48] def new_function(sum):
+[49]     return (10 - (sum % 10)) % 10
+[50] 
+\`\`\`
+`
+        const res = parseChangeLogs(source)
+        console.log(res)
+        assert.equal(res[0].filename, "src/edits/bigfibs/fib.py")
+    })
 })

packages/core/src/changelog.ts

@@ -3,6 +3,8 @@
  * A changelog describes changes between original and modified code segments.
  */
 
+import { unfence } from "./fence"
+
 // Represents a chunk of code with a start and end line and its content.
 export interface ChangeLogChunk {
     start: number // Starting line number
@@ -31,19 +33,26 @@ export interface ChangeLog {
  * @returns An array of parsed ChangeLog objects.
  */
 export function parseChangeLogs(source: string): ChangeLog[] {
-    const lines = source.split("\n")
+    const lines = unfence(source, "changelog").split("\n")
     const changelogs: ChangeLog[] = []
 
     // Process each line to extract changelog information.
     while (lines.length) {
         if (!lines[0].trim()) {
             lines.shift()
-            continue // Skip empty lines
+            continue
+        }
+
+        // each back ticks
+        if (/^[\`\.]{3,}/.test(lines[0])) {
+            lines.shift()
+            continue
         }
 
         // Parse the ChangeLog header line.
-        let m = /^ChangeLog:\s*(?<index>\d+)@(?<file>.*)$/i.exec(lines[0])
-        if (!m) throw new Error("missing ChangeLog header in " + lines[0])
+        let m = /^ChangeLog:\s*(?<index>\d+)@(?<file>.*)\s*$/i.exec(lines[0])
+        if (!m)
+            throw new Error("missing ChangeLog header in |" + lines[0] + "|")
         const changelog: ChangeLog = {
             index: parseInt(m.groups.index),
             filename: m.groups.file.trim(),
@@ -66,6 +75,14 @@ export function parseChangeLogs(source: string): ChangeLog[] {
                 lines.shift()
                 continue
             }
+
+            // each back ticks
+            if (/^[\`\.]{3,}/.test(lines[0])) {
+                // somehow we have finished this changed
+                lines.shift()
+                continue
+            }
+
             // Attempt to parse a change.
             const change = parseChange()
             if (change) changelog.changes.push(change)
@@ -89,7 +106,8 @@ export function parseChangeLogs(source: string): ChangeLog[] {
 
         lines.shift()
         const changed = parseChunk(m)
-        return <ChangeLogChange>{ original, changed }
+        const res = <ChangeLogChange>{ original, changed }
+        return res
     }
 
     // Parses a chunk of code from the changelog.

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

@@ -1,10 +1,11 @@
 system({
     title: "Generate changelog formatter edits",
-    lineNumbers: true
+    lineNumbers: true,
 })
 
+$`## CHANGELOG file format
 
-$`For partial updates of files, return one or more ChangeLogs (CLs) formatted as follows. Each CL must contain
+For partial updates of large files, return one or more ChangeLogs (CLs) formatted as follows. Each CL must contain
 one or more code snippet changes for a single file. There can be multiple CLs for a single file.
 Each CL must start with a description of its changes. The CL must then list one or more pairs of
 (OriginalCode, ChangedCode) code snippets. In each such pair, OriginalCode must list all consecutive
@@ -14,7 +15,8 @@ lines of code (again including the same few lines before and after the changes).
 OriginalCode and ChangedCode must start at the same source code line number N. Each listed code line,
 in both the OriginalCode and ChangedCode snippets, must be prefixed with [N] that matches the line
 index N in the above snippets, and then be prefixed with exactly the same whitespace indentation as
-the original snippets above. See also the following examples of the expected response format.
+the original snippets above. Each OriginalCode must be paired with ChangedCode. Do NOT add multiple ChangedCode per OriginalCode.
+See also the following examples of the expected response format.
 
 CHANGELOG:
 \`\`\`\`\`changelog
@@ -48,4 +50,10 @@ OriginalCode@23-23:
 ChangedCode@23-23:
 [23] <white space> <changed code line>
 \`\`\`\`\`
-`
+
+## Choosing what file format to use
+
+- If the file content is small (< 20 lines), use the full FULL format.
+- If the file content is large (> 50 lines), use CHANGELOG format.
+- If the file content IS VERY LARGE, ALWAYS USE CHANGELOG to save tokens.
+`

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

@@ -4,9 +4,9 @@ system({
 })
 
 const folder = env.vars["outputFolder"] || "."
-$`## Files
+$`## FULL file format
 
-When generating or updating files you will use the following syntax:`
+When generating or updating files you may use the FULL file format:`
 
 def(`File ${folder}/file1.ts`, `What goes in\n${folder}/file1.ts.`, {
     language: "typescript",
@@ -23,7 +23,9 @@ def(`File /path_to_file/file2.md`, `What goes in\n/path_to_file/file2.md.`, {
 
 $`- 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.
+- do NOT use ## headers with filename
+`
 if (folder !== ".")
     $`When generating new files, place files in folder "${folder}".`
 $`- If a file does not have changes, do not regenerate.

packages/core/src/promptdom.ts

@@ -243,7 +243,12 @@ function renderDefNode(def: PromptDefNode): string {
     while (dfence && body.includes(dfence)) {
         dfence += "`"
     }
-    const diffFormat = "" // body.length > 500 ? "preferred_diff_format=DIFF" : ""
+    const diffFormat =
+        body.length > 500
+            ? " preferred_output_format=CHANGELOG "
+            : body.length < 200
+              ? " preferred_output_format=FILE "
+              : ""
     const res =
         (name ? name + ":\n" : "") +
         dfence +

packages/core/src/systems.ts

@@ -45,7 +45,7 @@ export function resolveSystems(
         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")
+            systems.push("system.changelog")
             // Add file schema system if schema is used
             if (useSchema) systems.push("system.files_schema")
         }

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

@@ -0,0 +1,9 @@
+import { editTest } from "./fileedittest.mts"
+script({
+    model: "large",
+    title: "system.diff test",
+    files: "src/edits/fibs/fib.*",
+    system: ["system", "system.files", "system.changelog"],
+})
+
+editTest()

packages/sample/src/edits/fileedittest.mts

@@ -2,14 +2,15 @@ export function editTest() {
     def("FILE", env.files)
 
     $`- Implement the functions with TODO.
-- Delete all comments
+- Delete all comments in the entire file. This is important.
 - Delete all empty lines
+- process all files, do NOT skip any
 `
 
     defOutputProcessor((output) => {
         const { fileEdits } = output
-        if (Object.keys(fileEdits).length !== env.files.length)
-            throw new Error("no file edits")
+        const fns = Object.keys(fileEdits)
+        if (!fns.length) throw new Error("no file edits")
         for (const [fn, fe] of Object.entries(fileEdits)) {
             const res = fe.after
             if (/^\s*(#|\/\/).*$/m.test(res)) {