Add prompty parser

.vscode/extensions.json

@@ -10,6 +10,7 @@
         "tldraw-org.tldraw-vscode",
         "bierner.emojisense",
         "github.vscode-pull-request-github",
-        "ms-toolsai.prompty"
+        "ms-toolsai.prompty",
+        "unifiedjs.vscode-mdx"
     ]
 }

docs/src/content/docs/guides/auto-git-commit-message.mdx

@@ -13,7 +13,7 @@
 The script acts as a regular node.js automation script and uses [runPrompt](/genaiscript/reference/scripts/inner-prompts)
 to issue calls to the LLM and ask the user to confirm the generated text.
 
-## 🔍 **Explaining the Script**
+## Explaining the Script
 
 First, we check if there are any staged changes in the Git repository:
 
@@ -24,7 +24,7 @@
 If no changes are staged, we ask the user if they want to stage all changes. If the user confirms, we stage all changes. Otherwise, we bail out.
 
 ```ts
-const stage = await host.confirm("No staged changes. Stage all changes?", { 
+const stage = await host.confirm("No staged changes. Stage all changes?", {
     default: true,
 })
 if (stage) {
@@ -70,8 +70,7 @@
 
 ```ts
 if (choice === "edit") {
-    message = await host.input("Edit commit message",
-        { required: true })
+    message = await host.input("Edit commit message", { required: true })
     choice = "commit"
 }
 ```
@@ -84,7 +83,7 @@
 }
 ```
 
-## 🚀 **Running the Script**
+## Running the Script
 
 You can run this script using the [CLI](/genaiscript/reference/cli).
 
@@ -96,8 +95,11 @@
 
 ```json '"gcm": "genaiscript run gcm"'
 {
+    "devDependencies": {
+        "genaiscript": "*"
+    },
     "scripts": {
-        "gcm": "npx --yes genaiscript run gcm"
+        "gcm": "genaiscript run gcm"
     }
 }
 ```
@@ -108,7 +110,35 @@
 npm run gcm
 ```
 
+## Using git hooks
+
+You can also attach to the [commit-msg](https://git-scm.com/docs/githooks#_commit_msg) git hook to run the message generation on demand.
+Using the [huksy](https://typicode.github.io/husky/) framework, we can register the execution
+of genaiscript in the `.husky/commit-msg` file.
+
+The `commit-msg` hook receives a file location where the message is stored. We pass this parameter to the script
+so that it gets populated in the `env.files` variable.
+
+```bash title=".husky/commit-msg"
+npx --yes genaiscript run commit-msg "$1"
+```
+
+In the script, we check if the content of the file already has a user message, otherwize generate a new message.
+
+```js title="commit-msg.genai.mts"
+const msg = env.files[0] // file created by git to hold the message
+const msgContent = msg.content // check if the user added any message
+    ?.split(/\n/g)
+    .filter((l) => l && !/^#/.test(l)) // filter out comments
+    .join("\n")
+if (msgContent) cancel("commit message already exists")
+
+...
+
+await host.writeText(msg.filename, message)
+```
+
 ## Acknowledgements
 
-This script was inspired from Karpathy's 
+This script was inspired from Karpathy's
 [commit message generator](https://gist.github.com/karpathy/1dd0294ef9567971c1e4348a90d69285).

docs/src/content/docs/reference/cli/commands.md

@@ -2,10 +2,11 @@
 title: Commands
 description: List of all CLI commands
 sidebar:
-  order: 100
+    order: 100
 ---
 
 <!-- autogenerated, do not edit -->
+
 A full list of the CLI command and its respective help text.
 
 ## `run`
@@ -308,7 +309,8 @@
   code <file> [query]          Parse code using tree sitter and executes a
                                query
   tokens [options] <files...>  Count tokens in a set of files
   jsonl2json                   Converts JSONL files to a JSON file
+  prompty <file...>            Converts .prompty files to genaiscript
 ```
 
 ### `parse fence`
@@ -388,7 +390,21 @@
 Options:
   -h, --help  display help for command
 ```
 
+### `parse prompty`
+
+```
+Usage: genaiscript parse prompty [options] <file...>
+
+Converts .prompty files to genaiscript
+
+Arguments:
+  file        input JSONL files
+
+Options:
+  -h, --help  display help for command
+```
+
 ## `workspace`
 
 ```

genaisrc/test-gen.genai.mjs

@@ -1,18 +1,19 @@
 script({
+    model: "openai:gpt-4",
     title: "unit test generator",
     system: ["system", "system.typescript", "system.files"],
     tools: ["fs"],
 })
 
 const code = def("CODE", env.files)
 
-
 $`## Step 1
 
 For each file in ${code}, 
 generate a plan to test the source code in each file
 
-- use input test files from packages/sample/src/rag/*
+- generate self-contained tests as much as possible by inlining all necessary values
+- if needed, use input test files from packages/sample/src/rag/*
 - only generate tests for files in ${code}
 - update the existing test files (<code filename>.test.ts). keep old tests if possible.
 
@@ -41,7 +42,7 @@ ${fence('import test, { beforeEach, describe } from "node:test"', { language: "j
 
 Validate and fix test sources.
 
-Use 'run_test' tool to execute the generated test code and fix the test code to make tests pass.
+Call the 'run_test' tool to execute the generated test code and fix the test code to make tests pass.
 
 - this is important.
 `
@@ -55,8 +56,7 @@ defTool(
     },
     async (args) => {
         const { filename, source } = args
-        if (source)
-            await workspace.writeText(filename, source)
+        if (source) await workspace.writeText(filename, source)
         console.debug(`running test code ${filename}`)
         return host.exec(`node`, ["--import", "tsx", "--test", filename])
     }

packages/cli/src/cli.ts

@@ -13,6 +13,7 @@
     parseHTMLToText,
     parsePDF,
     parseTokens,
+    prompty2genaiscript,
 } from "./parse"
 import { compileScript, createScript, fixScripts, listScripts } from "./scripts"
 import { codeQuery } from "./codequery"
@@ -299,6 +300,11 @@
         .command("jsonl2json", "Converts JSONL files to a JSON file")
         .argument("<file...>", "input JSONL files")
         .action(jsonl2json)
+    parser
+        .command("prompty")
+        .description("Converts .prompty files to genaiscript")
+        .argument("<file...>", "input JSONL files")
+        .action(prompty2genaiscript)
 
     const workspace = program
         .command("workspace")

packages/cli/src/parse.ts

@@ -10,6 +10,7 @@
 import { YAMLStringify } from "../../core/src/yaml"
 import { resolveTokenEncoder } from "../../core/src/encoders"
 import { DEFAULT_MODEL } from "../../core/src/constants"
+import { promptyParse, promptyToGenAIScript } from "../../core/src/prompty"
 
 export async function parseFence(language: string, file: string) {
     const res = await parsePdf(file)
@@ -69,3 +70,15 @@
     }
     console.log(text)
 }
+
+export async function prompty2genaiscript(files: string[]) {
+    const fs = await expandFiles(files)
+    for (const f of fs) {
+        console.log(f)
+        const gf = replaceExt(f, ".genai.mts")
+        const content = await readText(f)
+        const doc = promptyParse(content)
+        const script = promptyToGenAIScript(doc)
+        await writeText(gf, script)
+    }
+}

packages/core/src/json5.ts

@@ -1,5 +1,5 @@
 /* eslint-disable curly */
-import { parse } from "json5"
+import { parse, stringify } from "json5"
 import { jsonrepair } from "jsonrepair"
 
 export function isJSONObjectOrArray(text: string) {
@@ -61,3 +61,5 @@ export function JSONLLMTryParse(s: string): any {
         s = s.replace(startRx, "").replace(endRx, "")
     return JSON5TryParse(s)
 }
+
+export const JSON5Stringify = stringify

packages/core/src/mustache.ts

@@ -18,7 +18,7 @@ export async function interpolateVariables(
 
     // remove prompty roles
     // https://github.com/microsoft/prompty/blob/main/runtime/prompty/prompty/parsers.py#L113C21-L113C77
-    content = content.replace(/^\s*(system|user):\s*$/gim, "\n")
+    content = content.replace(/^\s*(system|user|assistant)\s*:\s*$/gim, "\n")
 
     // remove xml tags
     // https://humanloop.com/docs/prompt-file-format

packages/core/src/prompty.test.ts

@@ -0,0 +1,75 @@
+import { promptyParse } from "./prompty"
+import { describe, test, beforeEach } from "node:test"
+import assert from "node:assert/strict"
+
+describe("promptyParse", () => {
+    test("correctly parses an empty markdown string", () => {
+        const result = promptyParse("")
+        assert.deepStrictEqual(result, {
+            frontmatter: {},
+            content: "",
+            messages: [],
+        })
+    })
+
+    test("correctly parses a markdown string without frontmatter", () => {
+        const content = "This is a sample content without frontmatter."
+        const result = promptyParse(content)
+        assert.deepStrictEqual(result, {
+            frontmatter: {},
+            content: content,
+            messages: [{ role: "system", content: content }],
+        })
+    })
+
+    test("correctly parses a markdown string with valid frontmatter", () => {
+        const markdownString = `---
+name: Test
+description: A test description
+version: 1.0.0
+authors:
+  - Author1
+  - Author2
+tags:
+  - tag1
+  - tag2
+sample:
+  key: value
+---
+# Heading
+Content below heading.`
+        const result = promptyParse(markdownString)
+        assert.deepStrictEqual(result.frontmatter, {
+            name: "Test",
+            description: "A test description",
+            version: "1.0.0",
+            authors: ["Author1", "Author2"],
+            tags: ["tag1", "tag2"],
+            sample: { key: "value" },
+        })
+        assert.strictEqual(result.content, "# Heading\nContent below heading.")
+    })
+
+    test("correctly parses a markdown string with content split into roles", () => {
+        const markdownContent = `user:
+User's message
+assistant:
+Assistant's reply
+user:
+Another message from the user`
+        const result = promptyParse(markdownContent)
+        assert.deepStrictEqual(result.messages, [
+            { role: "user", content: "User's message" },
+            { role: "assistant", content: "Assistant's reply" },
+            { role: "user", content: "Another message from the user" },
+        ])
+    })
+
+    test("correctly handles a markdown string with content but without roles", () => {
+        const markdownContent = `Just some content without specifying roles.`
+        const result = promptyParse(markdownContent)
+        assert.deepStrictEqual(result.messages, [
+            { role: "system", content: markdownContent },
+        ])
+    })
+})