Yehowshua/ZIm
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Have models indicate code locations in workflows using textual search, not symbol names (#17282)

Browse source 
Release Notes:

- N/A

---------

Co-authored-by: Antonio Scandurra <me@as-cii.com>
This commit is contained in:
Max Brunsfeld 2024-09-02 18:20:05 -07:00 • committed by GitHub
parent c63c2015a6
commit b41ddbd018
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 410 additions and 820 deletions
Download patch file Download diff file Expand all files Collapse all files

650
assets/prompts/edit_workflow.hbs
View file

@ -27,17 +27,17 @@ impl Person {
```
<edit>
<path>src/person.rs</path>
<operation>insert_before</operation>
<symbol>struct Person height</symbol>
<description>Add the age field</description>
<path>src/person.rs</path>
<operation>insert_before</operation>
<search>height: f32,</search>
<description>Add the age field</description>
</edit>
<edit>
<path>src/person.rs</path>
<operation>append_child</operation>
<symbol>impl Person</symbol>
<description>Add the age getter</description>
<path>src/person.rs</path>
<operation>insert_after</operation>
<search>impl Person {</search>
<description>Add the age getter</description>
</edit>
</step>
@ -45,15 +45,15 @@ impl Person {
First, each `<step>` must contain a written description of the change that should be made. The description should begin with a high-level overview, and can contain markdown code blocks as well. The description should be self-contained and actionable.
Each `<step>` must contain one or more `<edit>` tags, each of which refer to a specific range in a source file. Each `<edit>` tag must contain the following child tags:
After the description, each `<step>` must contain one or more `<edit>` tags, each of which refer to a specific range in a source file. Each `<edit>` tag must contain the following child tags:
### `<path>` (required)
This tag contains the path to the file that will be changed. It can be an existing path, or a path that should be created.
### `<symbol>` (optional)
### `<search>` (optional)
This tag contains the fully-qualified name of a symbol in the source file, e.g. `mod foo impl Bar pub fn baz` instead of just `fn baz`. If not provided, the new content will be inserted at the top of the file.
This tag contains a search string to locate in the source file, e.g. `pub fn baz() {`. If not provided, the new content will be inserted at the top of the file. Make sure to produce a string that exists in the source file and that isn't ambiguous. When there's ambiguity, add more lines to the search to eliminate it.
### `<description>` (required)
@ -62,110 +62,179 @@ This tag contains a single-line description of the edit that should be made at t
### `<operation>` (required)
This tag indicates what type of change should be made, relative to the given location. It can be one of the following:
- `update`: Rewrites the specified symbol entirely based on the given description.
- `update`: Rewrites the specified string entirely based on the given description.
- `create`: Creates a new file with the given path based on the provided description.
- `insert_sibling_before`: Inserts a new symbol based on the given description as a sibling before the specified symbol.
- `insert_sibling_after`: Inserts a new symbol based on the given description as a sibling after the specified symbol.
- `prepend_child`: Inserts a new symbol as a child of the specified symbol at the start.
- `append_child`: Inserts a new symbol as a child of the specified symbol at the end.
- `delete`: Deletes the specified symbol from the containing file.
- `insert_before`: Inserts new text based on the given description before the specified search string.
- `insert_after`: Inserts new text based on the given description after the specified search string.
- `delete`: Deletes the specified string from the containing file.
<guidelines>
- There's no need to describe *what* to do, just *where* to do it.
- Only reference locations that actually exist (unless you're creating a file).
- If creating a file, assume any subsequent updates are included at the time of creation.
- Don't create and then update a file. Always create new files in shot.
- Prefer updating symbols lower in the syntax tree if possible.
- Never include edits on a parent symbol and one of its children in the same edit block.
- Don't create and then update a file. Always create new files in one hot.
- Prefer multiple edits to smaller regions, as opposed to one big edit to a larger region.
- Don't produce edits that intersect each other. In that case, merge them into a bigger edit.
- Never nest an edit with another edit. Never include CDATA. All edits are leaf nodes.
- Descriptions are required for all edits except delete.
- When generating multiple edits, ensure the descriptions are specific to each individual operation.
- Avoid referring to the location in the description. Focus on the change to be made, not the location where it's made. That's implicit with the symbol you provide.
- Avoid referring to the search string in the description. Focus on the change to be made, not the location where it's made. That's implicit with the `search` string you provide.
- Don't generate multiple edits at the same location. Instead, combine them together in a single edit with a succinct combined description.
- Always ensure imports are added if you're referencing symbols that are not in scope. To manipulate imports, produce an edit where the `"symbol"` key is set to `"#imports"`
- Always ensure imports are added if you're referencing symbols that are not in scope.
</guidelines>
Here are some concrete examples.
<example language="rust">
<example>
<message role="user">
```rs src/rectangle.rs
struct Rectangle {
```rs src/shapes.rs
pub mod rectangle;
pub mod circle;
```
```rs src/shapes/rectangle.rs
pub struct Rectangle {
width: f64,
height: f64,
}
impl Rectangle {
fn new(width: f64, height: f64) -> Self {
pub fn new(width: f64, height: f64) -> Self {
Rectangle { width, height }
}
}
```
We need to add methods to calculate the area and perimeter of the rectangle. Can you help with that?
```rs src/shapes/circle.rs
pub struct Circle {
radius: f64,
}
impl Circle {
pub fn new(radius: f64) -> Self {
Circle { radius }
}
}
```
Update all shapes to store their origin as an (x, y) tuple and implement Display.
</message>
<message role="assistant">
We'll need to update both the rectangle and circle modules.
<step>
Add methods to calculate the area and perimeter of the rectangle
Add origin fields to both shape types.
```rust
impl Rectangle {
// existing methods...
struct Rectangle {
// existing fields ...
origin: (f64, f64),
}
```
fn calculate_area(&self) -> f64 {
self.width * self.height
}
fn calculate_perimeter(&self) -> f64 {
2.0 * (self.width + self.height)
}
```rust
struct Circle {
// existing fields ...
origin: (f64, f64),
}
```
<edit>
<path>src/rectangle.rs</path>
<operation>append_child</operation>
<symbol>impl Rectangle</symbol>
<description>Add calculate_area and calculate_perimeter methods</description>
<path>src/shapes/rectangle.rs</path>
<operation>insert_before</operation>
<search>
width: f64,
height: f64,
</search>
<description>Add the origin field to Rectangle</description>
</edit>
<edit>
<path>src/shapes/circle.rs</path>
<operation>insert_before</operation>
<search>
radius: f64,
</search>
<description>Add the origin field to Circle</description>
</edit>
<step>
Update both shape's constructors to take an origin.
<edit>
<path>src/shapes/rectangle.rs</path>
<operation>update</operation>
<search>
fn new(width: f64, height: f64) -> Self {
Rectangle { width, height }
}
</search>
<description>Update the Rectangle new function to take an origin</description>
</edit>
<edit>
<path>src/shapes/circle.rs</path>
<operation>update</operation>
<search>
fn new(radius: f64) -> Self {
Circle { radius }
}
</search>
<description>Update the Circle new function to take an origin</description>
</edit>
</step>
<step>
Implement the Display trait for the Rectangle struct
```rust
use std::fmt;
impl fmt::Display for Rectangle {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "Rectangle: {}x{}", self.width, self.height)
}
}
```
Implement Display for both shapes
<edit>
<path>src/rectangle.rs</path>
<operation>insert_sibling_after</operation>
<symbol>impl Rectangle</symbol>
<description>Implement Display trait for Rectangle</description>
<path>src/shapes/rectangle.rs</path>
<operation>insert_before</operation>
<search>
struct Rectangle {
</search>
<description>Add an import for the `std::fmt` module</description>
</edit>
<edit>
<path>src/rectangle.rs</path>
<operation>append_child</operation>
<symbol>#imports</symbol>
<description>Add use statement for fmt</description>
<path>src/shapes/rectangle.rs</path>
<operation>insert_after</operation>
<search>
Rectangle { width, height }
}
}
</search>
<description>Add a Display implementation for Rectangle</description>
</edit>
<edit>
<path>src/shapes/circle.rs</path>
<operation>insert_before</operation>
<search>
struct Circle {
</search>
<description>Add an import for the `std::fmt` module</description>
</edit>
<edit>
<path>src/shapes/circle.rs</path>
<operation>insert_after</operation>
<search>
Circle { radius }
}
}
</search>
<description>Add a Display implementation for Circle</description>
</edit>
</step>
</message>
</example>
<example language="rust">
<example number=2>
<message role="user">
```rs src/user.rs
struct User {
pub name: String,
@ -202,10 +271,14 @@ impl User {
```
<edit>
<path>src/user.rs</path>
<operation>update</operation>
<symbol>impl User pub fn print_info</symbol>
<description>Print all the user information</description>
<path>src/user.rs</path>
<operation>update</operation>
<search>
pub fn print_info(&self) {
todo!()
}
</search>
<description>Print all the user information</description>
</edit>
</step>
@ -213,442 +286,25 @@ impl User {
Remove the 'email' field from the User struct
<edit>
<path>src/user.rs</path>
<operation>delete</operation>
<symbol>struct User email</symbol>
<path>src/user.rs</path>
<operation>delete</operation>
<search>
email: String,
</search>
</edit>
<edit>
<path>src/user.rs</path>
<operation>update</operation>
<symbol>impl User fn new</symbol>
<description>Remove email parameter from new method</description>
</edit>
</step>
</message>
</example>
<example language="rust">
<message role="user">
```rs src/vehicle.rs
struct Vehicle {
make: String,
model: String,
year: u32,
<path>src/user.rs</path>
<operation>update</operation>
<symbol>
fn new(name: String, age: u32, email: String) -> Self {
User { name, age, email }
}
impl Vehicle {
fn new(make: String, model: String, year: u32) -> Self {
Vehicle { make, model, year }
}
fn print_year(&self) {
println!("Year: {}", self.year);
}
}
```
Let's add a `start_engine` method for the vehicle and print how long it takes to start it.
</message>
<message role="assistant">
<step>
Add a 'use std::time::Instant;' statement at the beginning of the file
<edit>
<path>src/vehicle.rs</path>
<operation>prepend_child</operation>
<symbol>#imports</symbol>
<description>Add use statement for std::time::Instant</description>
</edit>
</step>
<step>
Add a new method 'start_engine' in the Vehicle impl block
```rust
impl Vehicle {
// ... existing methods ...
fn start_engine(&self) {
let t0 = Instant::now();
println!("Starting the engine of {} {} {}. Took: {:?}",
self.year, self.make, self.model, t0.elapsed());
}
}
```
<edit>
<path>src/vehicle.rs</path>
<operation>append_child</operation>
<symbol>impl Vehicle</symbol>
<description>Add start_engine method</description>
</symbol>
<description>Remove email parameter from new method</description>
</edit>
</step>
</message>
</example>
<example language="rust">
<message role="user">
```rs src/employee.rs
struct Employee {
name: String,
position: String,
salary: u32,
department: String,
}
impl Employee {
fn new(name: String, position: String, salary: u32, department: String) -> Self {
Employee { name, position, salary, department }
}
fn print_details(&self) {
println!("Name: {}, Position: {}, Salary: {}, Department: {}",
self.name, self.position, self.salary, self.department);
}
fn give_raise(&mut self, amount: u32) {
self.salary += amount;
}
}
```
Let's turn the salary field into an f32. Also, let's delete the department field.
</message>
<message role="assistant">
<step>
Make salary an f32
```rust
struct Employee {
name: String,
position: String,
salary: f32,
department: String,
}
impl Employee {
fn new(name: String, position: String, salary: f32, department: String) -> Self {
Employee { name, position, salary, department }
}
// ... other methods ...
fn give_raise(&mut self, amount: f32) {
self.salary += amount;
}
}
```
<edit>
<path>src/employee.rs</path>
<operation>update</operation>
<symbol>struct Employee salary</symbol>
<description>Change salary type to f32</description>
</edit>
<edit>
<path>src/employee.rs</path>
<operation>update</operation>
<symbol>impl Employee fn new</symbol>
<description>Update new method to use f32 for salary</description>
</edit>
<edit>
<path>src/employee.rs</path>
<operation>update</operation>
<symbol>impl Employee fn give_raise</symbol>
<description>Update give_raise method to use f32 for amount</description>
</edit>
</step>
<step>
Remove the 'department' field and update the 'print_details' method
```rust
struct Employee {
name: String,
position: String,
salary: f32,
}
impl Employee {
fn new(name: String, position: String, salary: f32) -> Self {
Employee { name, position, salary }
}
fn print_details(&self) {
println!("Name: {}, Position: {}, Salary: {}",
self.name, self.position, self.salary);
}
// ... other methods ...
}
```
<edit>
<path>src/employee.rs</path>
<operation>delete</operation>
<symbol>struct Employee department</symbol>
</edit>
<edit>
<path>src/employee.rs</path>
<operation>update</operation>
<symbol>impl Employee fn new</symbol>
<description>Remove department parameter from new method</description>
</edit>
<edit>
<path>src/employee.rs</path>
<operation>update</operation>
<symbol>impl Employee fn print_details</symbol>
<description>Remove department from print_details method</description>
</edit>
</step>
</message>
</example>
<example language="rust">
<message role="user">
```rs src/game.rs
struct Player {
name: String,
health: i32,
pub score: u32,
}
impl Player {
pub fn new(name: String) -> Self {
Player { name, health: 100, score: 0 }
}
}
struct Game {
players: Vec<Player>,
}
impl Game {
fn new() -> Self {
Game { players: Vec::new() }
}
}
```
Introduce a level field.
</message>
<message role="assistant">
<step>
Add a 'level' field to Player and update the 'new' method
```rust
struct Player {
name: String,
health: i32,
pub score: u32,
level: u8,
}
impl Player {
pub fn new(name: String) -> Self {
Player { name, health: 100, score: 0, level: 1 }
}
}
```
<edit>
<path>src/game.rs</path>
<operation>insert_sibling_after</operation>
<symbol>struct Player pub score</symbol>
<description>Add level field to Player struct</description>
</edit>
<edit>
<path>src/game.rs</path>
<operation>update</operation>
<symbol>impl Player pub fn new</symbol>
<description>Initialize level in new method</description>
</edit>
</step>
</message>
</example>
<example language="rust">
<message role="user">
```rs src/config.rs
use std::collections::HashMap;
struct Config {
settings: HashMap<String, String>,
}
impl Config {
fn new() -> Self {
Config { settings: HashMap::new() }
}
}
```
I want to load the configuration from a file.
</message>
<message role="assistant">
<step>
Add a 'load_from_file' method to Config and import necessary modules
```rust
use std::collections::HashMap;
use std::fs::File;
use std::io::{self, BufRead};
use std::path::Path;
struct Config {
settings: HashMap<String, String>,
}
impl Config {
fn new() -> Self {
Config { settings: HashMap::new() }
}
fn load_from_file<P: AsRef<Path>>(&mut self, path: P) -> io::Result<()> {
let file = File::open(path)?;
for line in io::BufReader::new(file).lines() {
let line = line?;
if let Some((key, value)) = line.split_once('=') {
self.settings.insert(key.trim().to_string(), value.trim().to_string());
}
}
Ok(())
}
}
```
<edit>
<path>src/config.rs</path>
<operation>append_child</operation>
<symbol>#imports</symbol>
<description>Import necessary modules for file operations</description>
</edit>
<edit>
<path>src/config.rs</path>
<operation>append_child</operation>
<symbol>impl Config</symbol>
<description>Add load_from_file method</description>
</edit>
</step>
</message>
</example>
<example language="rust">
<message role="user">
```rs src/database.rs
pub(crate) struct Database {
connection: Connection,
}
impl Database {
fn new(url: &str) -> Result<Self, Error> {
let connection = Connection::connect(url)?;
Ok(Database { connection })
}
async fn query(&self, sql: &str) -> Result<Vec<Row>, Error> {
self.connection.query(sql, &[])
}
}
```
I want to add error handling to this module.
</message>
<message role="assistant">
<step>
Add error handling to the 'query' method and create a custom error type
```rust
use std::fmt;
use std::error::Error as StdError;
#[derive(Debug)]
pub enum DatabaseError {
ConnectionError(String),
QueryError(String),
}
impl fmt::Display for DatabaseError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self {
DatabaseError::ConnectionError(msg) => write!(f, "Connection error: {}", msg),
DatabaseError::QueryError(msg) => write!(f, "Query error: {}", msg),
}
}
}
impl StdError for DatabaseError {}
// ...omitted code...
impl Database {
fn new(url: &str) -> Result<Self, DatabaseError> {
let connection = Connection::connect(url)
.map_err(|e| DatabaseError::ConnectionError(e.to_string()))?;
Ok(Database { connection })
}
async fn query(&self, sql: &str) -> Result<Vec<Row>, DatabaseError> {
self.connection.query(sql, &[])
.await
.map_err(|e| DatabaseError::QueryError(e.to_string()))
}
}
```
<edit>
<path>src/database.rs</path>
<operation>prepend_child</operation>
<symbol>#imports</symbol>
<description>Import necessary error handling modules</description>
</edit>
<edit>
<path>src/database.rs</path>
<operation>insert_sibling_before</operation>
<symbol>pub(crate) struct Database</symbol>
<description>Define custom DatabaseError enum</description>
</edit>
<edit>
<path>src/database.rs</path>
<operation>update</operation>
<symbol>impl Database fn new</symbol>
<description>Update new method to use DatabaseError</description>
</edit>
<edit>
<path>src/database.rs</path>
<operation>update</operation>
<symbol>impl Database async fn query</symbol>
<description>Update query method to use DatabaseError</description>
</edit>
</step>
</message>
</example>
You should think step by step. When possible, produce smaller, coherent logical steps as opposed to one big step that combines lots of heterogeneous edits.