From c8114ef1ab8ad7e4f6e2410991b2a20f5d924640 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Fri, 23 Jan 2026 17:20:33 +0000
Subject: [PATCH 1/3] Initial plan


From 32b76be8902242c0339310e11350877d2f0a6757 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Fri, 23 Jan 2026 17:22:39 +0000
Subject: [PATCH 2/3] Add image support documentation to all SDK READMEs

Co-authored-by: friggeri <106686+friggeri@users.noreply.github.com>
---
 dotnet/README.md | 25 +++++++++++++++++++++++++
 go/README.md     | 24 ++++++++++++++++++++++++
 nodejs/README.md | 22 ++++++++++++++++++++++
 python/README.md | 22 ++++++++++++++++++++++
 4 files changed, 93 insertions(+)

diff --git a/dotnet/README.md b/dotnet/README.md
index a3d4076b..5ac20b21 100644
--- a/dotnet/README.md
+++ b/dotnet/README.md
@@ -200,6 +200,31 @@ session.On(evt =>
 });
 ```
 
+## Image Support
+
+The SDK supports image attachments via the `Attachments` parameter. You can attach images by providing their file path:
+
+```csharp
+await session.SendAsync(new MessageOptions
+{
+    Prompt = "What's in this image?",
+    Attachments = new List<UserMessageDataAttachmentsItem>
+    {
+        new UserMessageDataAttachmentsItem
+        {
+            Type = UserMessageDataAttachmentsItemType.File,
+            Path = "/path/to/image.jpg"
+        }
+    }
+});
+```
+
+Supported image formats include JPG, PNG, GIF, and other common image types. The agent's `view` tool can also read images directly from the filesystem, so you can also ask questions like:
+
+```csharp
+await session.SendAsync(new MessageOptions { Prompt = "What does the most recent jpg in this directory portray?" });
+```
+
 ## Streaming
 
 Enable streaming to receive assistant response chunks as they're generated:
diff --git a/go/README.md b/go/README.md
index 1a1c0f87..b57fc3c9 100644
--- a/go/README.md
+++ b/go/README.md
@@ -112,6 +112,30 @@ func main() {
 
 - `Bool(v bool) *bool` - Helper to create bool pointers for `AutoStart`/`AutoRestart` options
 
+## Image Support
+
+The SDK supports image attachments via the `Attachments` field in `MessageOptions`. You can attach images by providing their file path:
+
+```go
+_, err = session.Send(copilot.MessageOptions{
+    Prompt: "What's in this image?",
+    Attachments: []copilot.Attachment{
+        {
+            Type: "file",
+            Path: "/path/to/image.jpg",
+        },
+    },
+})
+```
+
+Supported image formats include JPG, PNG, GIF, and other common image types. The agent's `view` tool can also read images directly from the filesystem, so you can also ask questions like:
+
+```go
+_, err = session.Send(copilot.MessageOptions{
+    Prompt: "What does the most recent jpg in this directory portray?",
+})
+```
+
 ### Tools
 
 Expose your own functionality to Copilot by attaching tools to a session.
diff --git a/nodejs/README.md b/nodejs/README.md
index dea3b3ea..97d51304 100644
--- a/nodejs/README.md
+++ b/nodejs/README.md
@@ -183,6 +183,28 @@ Sessions emit various events during processing:
 
 See `SessionEvent` type in the source for full details.
 
+## Image Support
+
+The SDK supports image attachments via the `attachments` parameter. You can attach images by providing their file path:
+
+```typescript
+await session.send({
+    prompt: "What's in this image?",
+    attachments: [
+        {
+            type: "file",
+            path: "/path/to/image.jpg",
+        },
+    ],
+});
+```
+
+Supported image formats include JPG, PNG, GIF, and other common image types. The agent's `view` tool can also read images directly from the filesystem, so you can also ask questions like:
+
+```typescript
+await session.send({ prompt: "What does the most recent jpg in this directory portray?" });
+```
+
 ## Streaming
 
 Enable streaming to receive assistant response chunks as they're generated:
diff --git a/python/README.md b/python/README.md
index 3fc1300d..40939b22 100644
--- a/python/README.md
+++ b/python/README.md
@@ -155,6 +155,28 @@ session = await client.create_session({
 
 The SDK automatically handles `tool.call`, executes your handler (sync or async), and responds with the final result when the tool completes.
 
+## Image Support
+
+The SDK supports image attachments via the `attachments` parameter. You can attach images by providing their file path:
+
+```python
+await session.send({
+    "prompt": "What's in this image?",
+    "attachments": [
+        Attachment(
+            type="file",
+            path="/path/to/image.jpg"
+        )
+    ]
+})
+```
+
+Supported image formats include JPG, PNG, GIF, and other common image types. The agent's `view` tool can also read images directly from the filesystem, so you can also ask questions like:
+
+```python
+await session.send({"prompt": "What does the most recent jpg in this directory portray?"})
+```
+
 ## Streaming
 
 Enable streaming to receive assistant response chunks as they're generated:

From a874145c95cdc9333ae7847c0ff230677ea43d9b Mon Sep 17 00:00:00 2001
From: Adrien Friggeri <adrien@friggeri.net>
Date: Fri, 23 Jan 2026 12:11:27 -0700
Subject: [PATCH 3/3] Update python/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 python/README.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/python/README.md b/python/README.md
index 40939b22..a12ff423 100644
--- a/python/README.md
+++ b/python/README.md
@@ -163,10 +163,10 @@ The SDK supports image attachments via the `attachments` parameter. You can atta
 await session.send({
     "prompt": "What's in this image?",
     "attachments": [
-        Attachment(
-            type="file",
-            path="/path/to/image.jpg"
-        )
+        {
+            "type": "file",
+            "path": "/path/to/image.jpg",
+        }
     ]
 })
 ```