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

Use fuzzy-matching to locate symbols when resolving edit steps (#15447)

Browse source 
Release Notes:

- N/A

---------

Co-authored-by: Nathan <nathan@zed.dev>
This commit is contained in:
Antonio Scandurra 2024-07-29 20:21:19 +02:00 • committed by GitHub
parent 5e1aa898d4
commit 2b871a631a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 330 additions and 131 deletions
Download patch file Download diff file Expand all files Collapse all files

375
assets/prompts/operations.md
View file

@ -6,7 +6,7 @@ Guidelines:
- Don't create and then update a file.
- We'll create it in one shot.
- Prefer updating symbols lower in the syntax tree if possible.
- Never include operations on a parent symbol and one of its children in the same <operations> block.
- Never include operations on a parent symbol and one of its children in the same operations block.
- Never nest an operation with another operation or include CDATA or other content. All operations are leaf nodes.
- Include a description attribute for each operation with a brief, one-line description of the change to perform.
- Descriptions are required for all operations except delete.
@ -14,66 +14,73 @@ Guidelines:
- 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.
- Don't generate multiple operations at the same location. Instead, combine them together in a single operation with a succinct combined description.
The available operation types are:
1. <update>: Modify an existing symbol in a file.
2. <create_file>: Create a new file.
3. <insert_sibling_after>: Add a new symbol as sibling after an existing symbol in a file.
4. <append_child>: Add a new symbol as the last child of an existing symbol in a file.
5. <prepend_child>: Add a new symbol as the first child of an existing symbol in a file.
6. <delete>: Remove an existing symbol from a file. The `description` attribute is invalid for delete, but required for other ops.
All operations *require* a path.
Operations that *require* a symbol: <update>, <insert_sibling_after>, <delete>
Operations that don't allow a symbol: <create>
Operations that have an *optional* symbol: <prepend_child>, <append_child>
Example 1:
User:
```rs src/rectangle.rs
struct Rectangle {
width: f64,
height: f64,
}
```rs src/rectangle.rs
struct Rectangle {
width: f64,
height: f64,
}
impl Rectangle {
fn new(width: f64, height: f64) -> Self {
Rectangle { width, height }
}
}
```
impl Rectangle {
fn new(width: f64, height: f64) -> Self {
Rectangle { width, height }
}
}
```
Symbols for src/rectangle.rs:
- struct Rectangle
- impl Rectangle
- impl Rectangle fn new
<step>Add new methods 'calculate_area' and 'calculate_perimeter' to the Rectangle struct</step>
<step>Implement the 'Display' trait for the Rectangle struct</step>
<step>Add new methods 'calculate_area' and 'calculate_perimeter' to the Rectangle struct</step>
<step>Implement the 'Display' trait for the Rectangle struct</step>
What are the operations for the step: <step>Add a new method 'calculate_area' to the Rectangle struct</step>
What are the operations for the step: <step>Add a new method 'calculate_area' to the Rectangle struct</step>
Assistant (wrong):
<operations>
<append_child path="src/shapes.rs" symbol="impl Rectangle" description="Add calculate_area method" />
<append_child path="src/shapes.rs" symbol="impl Rectangle" description="Add calculate_perimeter method" />
</operations>
A (wrong):
{
"operations": [
{
"kind": "AppendChild",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Add calculate_area method"
},
{
"kind": "AppendChild",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Add calculate_perimeter method"
}
]
}
This demonstrates what NOT to do. NEVER append multiple children at the same location.
Assistant (corrected):
<operations>
<append_child path="src/shapes.rs" symbol="impl Rectangle" description="Add calculate area and perimeter methods" />
</operations>
A (corrected):
{
"operations": [
{
"kind": "AppendChild",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Add calculate area and perimeter methods"
}
]
}
User:
What are the operations for the step: <step>Implement the 'Display' trait for the Rectangle struct</step>
Assistant:
<operations>
<insert_sibling_after path="src/shapes.rs" symbol="impl Rectangle" description="Implement Display trait for Rectangle"/>
</operations>
A:
{
"operations": [
{
"kind": "InsertSiblingAfter",
"path": "src/shapes.rs",
"symbol": "impl Rectangle",
"description": "Implement Display trait for Rectangle"
}
]
}
Example 2:
@ -96,32 +103,36 @@ impl User {
}
```
Symbols for src/user.rs:
- struct User
- struct User pub name
- struct User age
- struct User email
- impl User
- impl User fn new
- impl User pub fn print_info
<step>Update the 'print_info' method to use formatted output</step>
<step>Remove the 'email' field from the User struct</step>
What are the operations for the step: <step>Update the 'print_info' method to use formatted output</step>
Assistant:
<operations>
<update path="src/user.rs" symbol="impl User fn print_info" description="Use formatted output" />
</operations>
A:
{
"operations": [
{
"kind": "Update",
"path": "src/user.rs",
"symbol": "impl User pub fn print_info",
"description": "Use formatted output"
}
]
}
User:
What are the operations for the step: <step>Remove the 'email' field from the User struct</step>
Assistant:
<operations>
<delete path="src/user.rs" symbol="struct User email" description="Remove the email field" />
</operations>
A:
{
"operations": [
{
"kind": "Delete",
"path": "src/user.rs",
"symbol": "struct User email"
}
]
}
Example 3:
@ -144,32 +155,36 @@ impl Vehicle {
}
```
Symbols for src/vehicle.rs:
- struct Vehicle
- struct Vehicle make
- struct Vehicle model
- struct Vehicle year
- impl Vehicle
- impl Vehicle fn new
- impl Vehicle fn print_year
<step>Add a 'use std::fmt;' statement at the beginning of the file</step>
<step>Add a new method 'start_engine' in the Vehicle impl block</step>
What are the operations for the step: <step>Add a 'use std::fmt;' statement at the beginning of the file</step>
Assistant:
<operations>
<prepend_child path="src/vehicle.rs" description="Add 'use std::fmt' statement" />
</operations>
A:
{
"operations": [
{
"kind": "PrependChild",
"path": "src/vehicle.rs",
"description": "Add 'use std::fmt' statement"
}
]
}
User:
What are the operations for the step: <step>Add a new method 'start_engine' in the Vehicle impl block</step>
Assistant:
<operations>
<insert_sibling_after path="src/vehicle.rs" symbol="impl Vehicle fn new" description="Add start_engine method"/>
</operations>
A:
{
"operations": [
{
"kind": "InsertSiblingAfter",
"path": "src/vehicle.rs",
"symbol": "impl Vehicle fn new",
"description": "Add start_engine method"
}
]
}
Example 4:
@ -198,44 +213,188 @@ impl Employee {
}
```
Symbols for src/employee.rs:
- struct Employee
- struct Employee name
- struct Employee position
- struct Employee salary
- struct Employee department
- impl Employee
- impl Employee fn new
- impl Employee fn print_details
- impl Employee fn give_raise
<step>Make salary an f32</step>
What are the operations for the step: <step>Make salary an f32</step>
A (wrong):
<operations>
<update path="src/employee.rs" symbol="struct Employee" description="Change the type of salary to an f32" />
<update path="src/employee.rs" symbol="struct Employee salary" description="Change the type to an f32" />
</operations>
{
"operations": [
{
"kind": "Update",
"path": "src/employee.rs",
"symbol": "struct Employee",
"description": "Change the type of salary to an f32"
},
{
"kind": "Update",
"path": "src/employee.rs",
"symbol": "struct Employee salary",
"description": "Change the type to an f32"
}
]
}
This example demonstrates what not to do. `struct Employee salary` is a child of `struct Employee`.
A (corrected):
<operations>
<update path="src/employee.rs" symbol="struct Employee salary" description="Change the type to an f32" />
</operations>
{
"operations": [
{
"kind": "Update",
"path": "src/employee.rs",
"symbol": "struct Employee salary",
"description": "Change the type to an f32"
}
]
}
User:
What are the correct operations for the step: <step>Remove the 'department' field and update the 'print_details' method</step>
What are the correct operations for the step: <step>Remove the 'department' field and update the 'print_details' method</step>
A:
<operations>
<delete path="src/employee.rs" symbol="struct Employee department" />
<update path="src/employee.rs" symbol="impl Employee fn print_details" description="Don't print the 'department' field" />
</operations>
{
"operations": [
{
"kind": "Delete",
"path": "src/employee.rs",
"symbol": "struct Employee department"
},
{
"kind": "Update",
"path": "src/employee.rs",
"symbol": "impl Employee fn print_details",
"description": "Don't print the 'department' field"
}
]
}
Now generate the operations for the following step.
Output only valid XML containing valid operations with their required attributes.
NEVER output code or any other text inside <operation> tags. If you do, you will replaced with another model.
Your response *MUST* begin with <operations> and end with </operations>:
Example 5:
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() }
}
}
```
<step>Add a 'level' field to Player and update the 'new' method</step>
A:
{
"operations": [
{
"kind": "InsertSiblingAfter",
"path": "src/game.rs",
"symbol": "struct Player pub score",
"description": "Add level field to Player"
},
{
"kind": "Update",
"path": "src/game.rs",
"symbol": "impl Player pub fn new",
"description": "Initialize level in new method"
}
]
}
Example 6:
User:
```rs src/config.rs
use std::collections::HashMap;
struct Config {
settings: HashMap<String, String>,
}
impl Config {
fn new() -> Self {
Config { settings: HashMap::new() }
}
}
```
<step>Add a 'load_from_file' method to Config and import necessary modules</step>
A:
{
"operations": [
{
"kind": "PrependChild",
"path": "src/config.rs",
"description": "Import std::fs and std::io modules"
},
{
"kind": "AppendChild",
"path": "src/config.rs",
"symbol": "impl Config",
"description": "Add load_from_file method"
}
]
}
Example 7:
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, &[])
}
}
```
<step>Add error handling to the 'query' method and create a custom error type</step>
A:
{
"operations": [
{
"kind": "PrependChild",
"path": "src/database.rs",
"description": "Import necessary error handling modules"
},
{
"kind": "InsertSiblingBefore",
"path": "src/database.rs",
"symbol": "pub(crate) struct Database",
"description": "Define custom DatabaseError enum"
},
{
"kind": "Update",
"path": "src/database.rs",
"symbol": "impl Database async fn query",
"description": "Implement error handling in query method"
}
]
}
Now generate the operations for the following step: