Awesome/awesome-copilot
1
0
Fork 0
mirror of https://github.com/github/awesome-copilot.git synced 2026-03-23 09:35:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Align Copilot SDK documentation with permission handling requirements (#1107)

Browse Source 
* Apply permission handler requirements across Copilot SDK docs

Co-authored-by: jamesmontemagno <1676321+jamesmontemagno@users.noreply.github.com>
Agent-Logs-Url: https://github.com/jamesmontemagno/awesome-copilot/sessions/adf27a88-92f8-4ca6-b3fe-1204e3bb9963

* Polish permission update formatting in SDK examples

Co-authored-by: jamesmontemagno <1676321+jamesmontemagno@users.noreply.github.com>
Agent-Logs-Url: https://github.com/jamesmontemagno/awesome-copilot/sessions/adf27a88-92f8-4ca6-b3fe-1204e3bb9963

* Fix review comments on SDK permission handling PR

Address 5 review comments from PR #1103:

1. Fix invalid object literal syntax (stray comma) in resumeSession
   example in copilot-sdk-nodejs.instructions.md

2. Replace unused PermissionHandler import with actual usage in
   cookbook/copilot-sdk/python/recipe/ralph_loop.py (was using
   inline lambda instead)

3. Replace unused approveAll import with actual usage in
   cookbook/copilot-sdk/nodejs/recipe/ralph-loop.ts (was using
   inline handler instead)

4. Add missing PermissionHandler import to 4 Python code snippets
   in skills/copilot-sdk/SKILL.md that reference it without importing

5. Add missing approveAll import to 3 TypeScript code snippets
   in skills/copilot-sdk/SKILL.md that reference it without importing

* Refactor session creation to improve code formatting and consistency across SDK examples

* Fix formatting: split multi-property lines and put closing braces on own lines

Address review comments on PR #1107:
- Split OnPermissionRequest + Model onto separate lines in Go, C#, TypeScript
- Put closing }); on its own line consistently across all examples
- Fix indentation in SKILL.md Quick Start, CLI URL, Error Handling sections
- Fix cookbook Go multiple-sessions and error-handling formatting
- Fix ralph-loop.md TypeScript indentation

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: jamesmontemagno <1676321+jamesmontemagno@users.noreply.github.com>
This commit is contained in:
James Montemagno
2026-03-22 17:11:19 -07:00
committed by GitHub
parent 6d48c08215
commit 33f544c71d
48 changed files with 376 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
instructions/copilot-sdk-csharp.instructions.md
View File

@@ -65,6 +65,7 @@ Use `SessionConfig` for configuration:
```csharp
await using var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "gpt-5",
Streaming = true,
Tools = [...],
@@ -89,7 +90,11 @@ await using var session = await client.CreateSessionAsync(new SessionConfig
### Resuming Sessions
```csharp
var session = await client.ResumeSessionAsync(sessionId, new ResumeSessionConfig { ... });
var session = await client.ResumeSessionAsync(sessionId, new ResumeSessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
// ...
});
```
### Session Operations
@@ -178,6 +183,7 @@ Set `Streaming = true` in SessionConfig:
```csharp
var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "gpt-5",
Streaming = true
});
@@ -236,6 +242,7 @@ using System.ComponentModel;
var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "gpt-5",
Tools = [
AIFunctionFactory.Create(
@@ -268,6 +275,7 @@ When Copilot invokes a tool, the client automatically:
```csharp
var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "gpt-5",
SystemMessage = new SystemMessageConfig
{
@@ -287,6 +295,7 @@ var session = await client.CreateSessionAsync(new SessionConfig
```csharp
var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "gpt-5",
SystemMessage = new SystemMessageConfig
{
@@ -336,8 +345,16 @@ await session.SendAsync(new MessageOptions
Sessions are independent and can run concurrently:
```csharp
var session1 = await client.CreateSessionAsync(new SessionConfig { Model = "gpt-5" });
var session2 = await client.CreateSessionAsync(new SessionConfig { Model = "claude-sonnet-4.5" });
var session1 = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "gpt-5",
});
var session2 = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "claude-sonnet-4.5",
});
await session1.SendAsync(new MessageOptions { Prompt = "Hello from session 1" });
await session2.SendAsync(new MessageOptions { Prompt = "Hello from session 2" });
@@ -350,6 +367,7 @@ Use custom API providers via `ProviderConfig`:
```csharp
var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Provider = new ProviderConfig
{
Type = "openai",
@@ -390,7 +408,7 @@ var state = client.State;
```csharp
try
{
var session = await client.CreateSessionAsync();
var session = await client.CreateSessionAsync(new SessionConfig { OnPermissionRequest = PermissionHandler.ApproveAll });
await session.SendAsync(new MessageOptions { Prompt = "Hello" });
}
catch (StreamJsonRpc.RemoteInvocationException ex)
@@ -433,7 +451,7 @@ ALWAYS use `await using` for automatic disposal:
```csharp
await using var client = new CopilotClient();
await using var session = await client.CreateSessionAsync();
await using var session = await client.CreateSessionAsync(new SessionConfig { OnPermissionRequest = PermissionHandler.ApproveAll });
// Resources automatically cleaned up
```
@@ -477,6 +495,7 @@ await client.StartAsync();
await using var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Model = "gpt-5"
});
@@ -501,7 +520,7 @@ await done.Task;
### Multi-Turn Conversation
```csharp
await using var session = await client.CreateSessionAsync();
await using var session = await client.CreateSessionAsync(new SessionConfig { OnPermissionRequest = PermissionHandler.ApproveAll });
async Task SendAndWait(string prompt)
{
@@ -532,6 +551,7 @@ await SendAndWait("What is its population?");
```csharp
var session = await client.CreateSessionAsync(new SessionConfig
{
OnPermissionRequest = PermissionHandler.ApproveAll,
Tools = [
AIFunctionFactory.Create(
([Description("User ID")] string userId) => {

34
instructions/copilot-sdk-go.instructions.md
View File

@@ -72,6 +72,7 @@ Use `SessionConfig` for configuration:
```go
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "gpt-5",
Streaming: true,
Tools: []copilot.Tool{...},
@@ -104,7 +105,7 @@ if err != nil {
### Resuming Sessions
```go
session, err := client.ResumeSession("session-id")
session, err := client.ResumeSession("session-id", &copilot.ResumeSessionConfig{OnPermissionRequest: copilot.PermissionHandler.ApproveAll})
// Or with options:
session, err := client.ResumeSessionWithOptions("session-id", &copilot.ResumeSessionConfig{ ... })
```
@@ -190,6 +191,7 @@ Set `Streaming: true` in SessionConfig:
```go
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "gpt-5",
Streaming: true,
})
@@ -243,6 +245,7 @@ Note: Final events (`AssistantMessage`, `AssistantReasoning`) are ALWAYS sent re
```go
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "gpt-5",
Tools: []copilot.Tool{
{
@@ -300,6 +303,7 @@ When Copilot invokes a tool, the client automatically:
```go
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "gpt-5",
SystemMessage: &copilot.SystemMessageConfig{
Mode: "append",
@@ -317,6 +321,7 @@ session, err := client.CreateSession(&copilot.SessionConfig{
```go
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "gpt-5",
SystemMessage: &copilot.SystemMessageConfig{
Mode: "replace",
@@ -361,8 +366,14 @@ session.Send(copilot.MessageOptions{
Sessions are independent and can run concurrently:
```go
session1, _ := client.CreateSession(&copilot.SessionConfig{Model: "gpt-5"})
session2, _ := client.CreateSession(&copilot.SessionConfig{Model: "claude-sonnet-4.5"})
session1, _ := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "gpt-5",
})
session2, _ := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "claude-sonnet-4.5",
})
session1.Send(copilot.MessageOptions{Prompt: "Hello from session 1"})
session2.Send(copilot.MessageOptions{Prompt: "Hello from session 2"})
@@ -374,6 +385,7 @@ Use custom API providers via `ProviderConfig`:
```go
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Provider: &copilot.ProviderConfig{
Type: "openai",
BaseURL: "https://api.openai.com/v1",
@@ -396,7 +408,9 @@ state := client.GetState()
### Standard Exception Handling
```go
session, err := client.CreateSession(&copilot.SessionConfig{})
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
})
if err != nil {
log.Fatalf("Failed to create session: %v", err)
}
@@ -447,7 +461,7 @@ if err := client.Start(); err != nil {
}
defer client.Stop()
session, err := client.CreateSession(nil)
session, err := client.CreateSession(&copilot.SessionConfig{OnPermissionRequest: copilot.PermissionHandler.ApproveAll})
if err != nil {
log.Fatal(err)
}
@@ -465,7 +479,7 @@ if err != nil {
log.Fatal(err)
}
session, err := client.CreateSession(nil)
session, err := client.CreateSession(&copilot.SessionConfig{OnPermissionRequest: copilot.PermissionHandler.ApproveAll})
if err != nil {
client.Stop()
log.Fatal(err)
@@ -504,7 +518,10 @@ if err := client.Start(); err != nil {
}
defer client.Stop()
session, err := client.CreateSession(&copilot.SessionConfig{Model: "gpt-5"})
session, err := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Model: "gpt-5",
})
if err != nil {
log.Fatal(err)
}
@@ -527,7 +544,7 @@ session.Send(copilot.MessageOptions{Prompt: "What is 2+2?"})
### Multi-Turn Conversation
```go
session, _ := client.CreateSession(nil)
session, _ := client.CreateSession(&copilot.SessionConfig{OnPermissionRequest: copilot.PermissionHandler.ApproveAll})
defer session.Destroy()
sendAndWait := func(prompt string) error {
@@ -588,6 +605,7 @@ type UserInfo struct {
}
session, _ := client.CreateSession(&copilot.SessionConfig{
OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
Tools: []copilot.Tool{
{
Name: "get_user",

48
instructions/copilot-sdk-nodejs.instructions.md
View File

@@ -30,7 +30,7 @@ yarn add @github/copilot-sdk
### Basic Client Setup
```typescript
import { CopilotClient } from "@github/copilot-sdk";
import { CopilotClient, approveAll } from "@github/copilot-sdk";
const client = new CopilotClient();
await client.start();
@@ -74,6 +74,7 @@ Use `SessionConfig` for configuration:
```typescript
const session = await client.createSession({
onPermissionRequest: approveAll,
model: "gpt-5",
streaming: true,
tools: [...],
@@ -106,6 +107,7 @@ const session = await client.createSession({
```typescript
const session = await client.resumeSession("session-id", {
tools: [myNewTool],
onPermissionRequest: approveAll,
});
```
@@ -190,8 +192,9 @@ Set `streaming: true` in SessionConfig:
```typescript
const session = await client.createSession({
model: "gpt-5",
streaming: true,
onPermissionRequest: approveAll,
model: "gpt-5",
streaming: true,
});
```
@@ -243,7 +246,8 @@ Use `defineTool` for type-safe tool definitions:
import { defineTool } from "@github/copilot-sdk";
const session = await client.createSession({
model: "gpt-5",
onPermissionRequest: approveAll,
model: "gpt-5",
tools: [
defineTool({
name: "lookup_issue",
@@ -272,6 +276,7 @@ The SDK supports Zod schemas for parameters:
import { z } from "zod";
const session = await client.createSession({
onPermissionRequest: approveAll,
tools: [
defineTool({
name: "get_weather",
@@ -316,7 +321,8 @@ When Copilot invokes a tool, the client automatically:
```typescript
const session = await client.createSession({
model: "gpt-5",
onPermissionRequest: approveAll,
model: "gpt-5",
systemMessage: {
mode: "append",
content: `
@@ -333,7 +339,8 @@ const session = await client.createSession({
```typescript
const session = await client.createSession({
model: "gpt-5",
onPermissionRequest: approveAll,
model: "gpt-5",
systemMessage: {
mode: "replace",
content: "You are a helpful assistant.",
@@ -377,8 +384,14 @@ await session.send({
Sessions are independent and can run concurrently:
```typescript
const session1 = await client.createSession({ model: "gpt-5" });
const session2 = await client.createSession({ model: "claude-sonnet-4.5" });
const session1 = await client.createSession({
onPermissionRequest: approveAll,
model: "gpt-5",
});
const session2 = await client.createSession({
onPermissionRequest: approveAll,
model: "claude-sonnet-4.5",
});
await Promise.all([
session1.send({ prompt: "Hello from session 1" }),
@@ -392,6 +405,7 @@ Use custom API providers via `provider`:
```typescript
const session = await client.createSession({
onPermissionRequest: approveAll,
provider: {
type: "openai",
baseUrl: "https://api.openai.com/v1",
@@ -422,7 +436,7 @@ await client.deleteSession(sessionId);
```typescript
const lastId = await client.getLastSessionId();
if (lastId) {
const session = await client.resumeSession(lastId);
const session = await client.resumeSession(lastId, { onPermissionRequest: approveAll });
}
```
@@ -439,7 +453,7 @@ const state = client.getState();
```typescript
try {
const session = await client.createSession();
const session = await client.createSession({ onPermissionRequest: approveAll });
await session.send({ prompt: "Hello" });
} catch (error) {
console.error(`Error: ${error.message}`);
@@ -477,7 +491,7 @@ ALWAYS use try-finally or cleanup in a finally block:
const client = new CopilotClient();
try {
await client.start();
const session = await client.createSession();
const session = await client.createSession({ onPermissionRequest: approveAll });
try {
// Use session...
} finally {
@@ -507,7 +521,7 @@ async function withSession<T>(
client: CopilotClient,
fn: (session: CopilotSession) => Promise<T>,
): Promise<T> {
const session = await client.createSession();
const session = await client.createSession({ onPermissionRequest: approveAll });
try {
return await fn(session);
} finally {
@@ -542,13 +556,16 @@ await withClient(async (client) => {
### Simple Query-Response
```typescript
import { CopilotClient } from "@github/copilot-sdk";
import { CopilotClient, approveAll } from "@github/copilot-sdk";
const client = new CopilotClient();
try {
await client.start();
const session = await client.createSession({ model: "gpt-5" });
const session = await client.createSession({
onPermissionRequest: approveAll,
model: "gpt-5",
});
try {
await new Promise<void>((resolve) => {
session.on((event) => {
@@ -572,7 +589,7 @@ try {
### Multi-Turn Conversation
```typescript
const session = await client.createSession();
const session = await client.createSession({ onPermissionRequest: approveAll });
async function sendAndWait(prompt: string): Promise<void> {
await new Promise<void>((resolve, reject) => {
@@ -621,6 +638,7 @@ interface UserInfo {
}
const session = await client.createSession({
onPermissionRequest: approveAll,
tools: [
defineTool({
name: "get_user",

45
instructions/copilot-sdk-python.instructions.md
View File

@@ -30,7 +30,7 @@ uv add github-copilot-sdk
### Basic Client Setup
```python
from copilot import CopilotClient
from copilot import CopilotClient, PermissionHandler
import asyncio
async def main():
@@ -82,6 +82,7 @@ Use a dict for SessionConfig:
```python
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
"streaming": True,
"tools": [...],
@@ -113,6 +114,7 @@ session = await client.create_session({
```python
session = await client.resume_session("session-id", {
"on_permission_request": PermissionHandler.approve_all,
"tools": [my_new_tool]
})
```
@@ -195,6 +197,7 @@ Set `streaming: True` in SessionConfig:
```python
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
"streaming": True
})
@@ -248,6 +251,7 @@ async def fetch_issue(issue_id: str):
return {"id": issue_id, "status": "open"}
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
"tools": [
define_tool(
@@ -281,6 +285,7 @@ async def get_weather(args: WeatherArgs, inv):
return {"temperature": 72, "units": args.units}
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"tools": [
define_tool(
name="get_weather",
@@ -331,6 +336,7 @@ When Copilot invokes a tool, the client automatically:
```python
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
"system_message": {
"mode": "append",
@@ -348,6 +354,7 @@ session = await client.create_session({
```python
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
"system_message": {
"mode": "replace",
@@ -392,8 +399,14 @@ await session.send({
Sessions are independent and can run concurrently:
```python
session1 = await client.create_session({"model": "gpt-5"})
session2 = await client.create_session({"model": "claude-sonnet-4.5"})
session1 = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
})
session2 = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "claude-sonnet-4.5",
})
await asyncio.gather(
session1.send({"prompt": "Hello from session 1"}),
@@ -407,6 +420,7 @@ Use custom API providers via `provider`:
```python
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"provider": {
"type": "openai",
"base_url": "https://api.openai.com/v1",
@@ -436,7 +450,7 @@ await client.delete_session(session_id)
```python
last_id = await client.get_last_session_id()
if last_id:
session = await client.resume_session(last_id)
session = await client.resume_session(last_id, on_permission_request=PermissionHandler.approve_all)
```
### Checking Connection State
@@ -452,7 +466,7 @@ state = client.get_state()
```python
try:
session = await client.create_session()
session = await client.create_session(on_permission_request=PermissionHandler.approve_all)
await session.send({"prompt": "Hello"})
except Exception as e:
print(f"Error: {e}")
@@ -487,7 +501,7 @@ ALWAYS use async context managers for automatic cleanup:
```python
async with CopilotClient() as client:
async with await client.create_session() as session:
async with await client.create_session(on_permission_request=PermissionHandler.approve_all) as session:
# Use session...
await session.send({"prompt": "Hello"})
# Session automatically destroyed
@@ -500,7 +514,7 @@ async with CopilotClient() as client:
client = CopilotClient()
try:
await client.start()
session = await client.create_session()
session = await client.create_session(on_permission_request=PermissionHandler.approve_all)
try:
# Use session...
pass
@@ -529,12 +543,15 @@ finally:
### Simple Query-Response
```python
from copilot import CopilotClient
from copilot import CopilotClient, PermissionHandler
import asyncio
async def main():
async with CopilotClient() as client:
async with await client.create_session({"model": "gpt-5"}) as session:
async with await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
}) as session:
done = asyncio.Event()
def handler(event):
@@ -574,7 +591,7 @@ async def send_and_wait(session, prompt: str):
return result[0] if result else None
async with await client.create_session() as session:
async with await client.create_session(on_permission_request=PermissionHandler.approve_all) as session:
await send_and_wait(session, "What is the capital of France?")
await send_and_wait(session, "What is its population?")
```
@@ -583,7 +600,7 @@ async with await client.create_session() as session:
```python
# Use built-in send_and_wait for simpler synchronous interaction
async with await client.create_session() as session:
async with await client.create_session(on_permission_request=PermissionHandler.approve_all) as session:
response = await session.send_and_wait(
{"prompt": "What is 2+2?"},
timeout=60.0
@@ -616,6 +633,7 @@ async def get_user(args, inv) -> dict:
return asdict(user)
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"tools": [
define_tool(
name="get_user",
@@ -697,6 +715,7 @@ options: MessageOptions = {
await session.send(options)
config: SessionConfig = {
"on_permission_request": PermissionHandler.approve_all,
"model": "gpt-5",
"streaming": True
}
@@ -775,7 +794,9 @@ def copilot_tool(
def calculate(expression: str) -> float:
return eval(expression)
session = await client.create_session({"tools": [calculate]})
session = await client.create_session({
"on_permission_request": PermissionHandler.approve_all,
"tools": [calculate]})
```
## Python-Specific Features