Fix documentation anomalies: incorrect API signatures, missing SDK links, wrong streaming patterns (#598)

## Summary

Systematic audit of all SDK documentation against actual source code
revealed **10 documentation anomalies** across 6 files. All fixes are
documentation-only — no source code changes.

## Changes by File

### Root `README.md`
| Fix | Before | After |
|-----|--------|-------|
| C# unload method name | `await model.Unload()` | `await
model.UnloadAsync()` |
| C# streaming missing parameter |
`CompleteChatStreamingAsync(messages)` |
`CompleteChatStreamingAsync(messages, CancellationToken.None)` |

### `sdk/cs/README.md`
| Fix | Before | After |
|-----|--------|-------|
| Non-existent factory methods (3 occurrences) |
`ChatMessage.FromUser("...")` / `ChatMessage.FromSystem("...")` | `new
ChatMessage { Role = "user", Content = "..." }` |
| Streaming property doesn't exist | `chunk.Choices?[0]?.Delta?.Content`
| `chunk.Choices?[0]?.Message?.Content` |
| Internal property used in public example |
`m.SelectedVariant.Info.DisplayName` | `m.Info.DisplayName` |

### `sdk/js/README.md`
| Fix | Before | After |
|-----|--------|-------|
| Streaming chunk access (2 occurrences) |
`chunk.choices?.[0]?.message?.content` |
`chunk.choices?.[0]?.delta?.content` |

### `sdk/python/README.md`
| Fix | Before | After |
|-----|--------|-------|
| Streaming pattern | Callback:
`client.complete_streaming_chat(messages, on_chunk)` | Generator: `for
chunk in client.complete_streaming_chat(messages):` |

### `sdk/rust/README.md`
| Fix | Before | After |
|-----|--------|-------|
| Non-existent trait | "All models implement the `IModel` trait" | "All
models are represented by the `Model` type" |
| Missing error variant | 8 variants listed | 9 variants (added
`Internal { reason }`) |
| Wrong license | "MIT" | "Microsoft Software License Terms" |

### `docs/README.md`
| Fix | Before | After |
|-----|--------|-------|
| Missing SDK references | Only C# and JS listed | Added Python and Rust
SDK links |

## Verification Method

Each fix was verified by reading the actual source code:
- C# `ChatMessage` constructor syntax confirmed in
`ChatCompletionsTests.cs`
- C# streaming `Message.Content` (not `Delta`) confirmed in
`ChatClient.cs` — both streaming and non-streaming return
`ChatCompletionCreateResponse`
- JS streaming `delta.content` confirmed in `chatClient.ts` JSDoc
- Python generator return confirmed in `chat_client.py:263-290`
- Rust `Model` struct confirmed in `lib.rs:16`; no trait exists
- Rust error variants confirmed in `error.rs:4-33`
- LICENSE file confirmed as Microsoft Software License Terms

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: baijumeswani <12852605+baijumeswani@users.noreply.github.com>
Co-authored-by: Baiju Meswani <baijumeswani@gmail.com>

Author: Copilot

README.md

@@ -157,13 +157,13 @@ The Foundry Local SDK makes it easy to integrate local AI models into your appli
         new() { Role = "user", Content = "What is the golden ratio?" } 
     };
 
-    await foreach (var chunk in chatClient.CompleteChatStreamingAsync(messages))
+    await foreach (var chunk in chatClient.CompleteChatStreamingAsync(messages, CancellationToken.None))
     {
         Console.Write(chunk.Choices[0].Message.Content);
     }
 
     // Unload the model when done
-    await model.Unload();
+    await model.UnloadAsync();
     ```
 
 </details>

docs/README.md

@@ -6,6 +6,8 @@ Documentation for Foundry Local can be found in the following resources:
 - SDK Reference:
     - [C# SDK Reference](../sdk/cs/README.md): This documentation provides detailed information about the C# SDK for Foundry Local, including API references, usage examples, and best practices for integrating Foundry Local into your applications.
     - [JavaScript SDK Reference](../sdk/js/README.md): This documentation offers detailed information about the JavaScript SDK for Foundry Local, including API references, usage examples, and best practices for integrating Foundry Local into your web applications.
+    - [Python SDK Reference](../sdk/python/README.md): This documentation provides detailed information about the Python SDK for Foundry Local, including API references, usage examples, and best practices for integrating Foundry Local into your Python applications.
+    - [Rust SDK Reference](../sdk/rust/README.md): This documentation provides detailed information about the Rust SDK for Foundry Local, including API references, usage examples, and best practices for integrating Foundry Local into your Rust applications.
 - [Foundry Local Lab](https://github.com/Microsoft-foundry/foundry-local-lab): This GitHub repository contains a lab designed to help you learn how to use Foundry Local effectively. It includes hands-on exercises, sample code, and step-by-step instructions to guide you through the process of setting up and using Foundry Local in various scenarios.
 
 ## Supported Capabilities

sdk/cs/README.md

@@ -126,7 +126,7 @@ await model.LoadAsync();
 var chatClient = await model.GetChatClientAsync();
 var response = await chatClient.CompleteChatAsync(new[]
 {
-    ChatMessage.FromUser("Why is the sky blue?")
+    new ChatMessage { Role = "user", Content = "Why is the sky blue?" }
 });
 
 Console.WriteLine(response.Choices![0].Message.Content);
@@ -159,7 +159,7 @@ var catalog = await FoundryLocalManager.Instance.GetCatalogAsync();
 // List all available models
 var models = await catalog.ListModelsAsync();
 foreach (var m in models)
-    Console.WriteLine($"{m.Alias} — {m.SelectedVariant.Info.DisplayName}");
+    Console.WriteLine($"{m.Alias} — {m.Info.DisplayName}");
 
 // Get a specific model by alias
 var model = await catalog.GetModelAsync("phi-3.5-mini")
@@ -214,8 +214,8 @@ var chatClient = await model.GetChatClientAsync();
 
 var response = await chatClient.CompleteChatAsync(new[]
 {
-    ChatMessage.FromSystem("You are a helpful assistant."),
-    ChatMessage.FromUser("Explain async/await in C#.")
+    new ChatMessage { Role = "system", Content = "You are a helpful assistant." },
+    new ChatMessage { Role = "user", Content = "Explain async/await in C#." }
 });
 
 Console.WriteLine(response.Choices![0].Message.Content);
@@ -229,9 +229,9 @@ Use `IAsyncEnumerable` for token-by-token output:
 using var cts = new CancellationTokenSource();
 
 await foreach (var chunk in chatClient.CompleteChatStreamingAsync(
-    new[] { ChatMessage.FromUser("Write a haiku about .NET") }, cts.Token))
+    new[] { new ChatMessage { Role = "user", Content = "Write a haiku about .NET" } }, cts.Token))
 {
-    Console.Write(chunk.Choices?[0]?.Delta?.Content);
+    Console.Write(chunk.Choices?[0]?.Message?.Content);
 }
 ```
 

sdk/js/README.md

@@ -111,7 +111,7 @@ console.log('\nTesting streaming completion...');
 for await (const chunk of chatClient.completeStreamingChat(
     [{ role: 'user', content: 'Write a short poem about programming.' }]
 )) {
-    const content = chunk.choices?.[0]?.message?.content;
+    const content = chunk.choices?.[0]?.delta?.content;
     if (content) {
         process.stdout.write(content);
     }
@@ -198,7 +198,7 @@ For real-time output, use streaming:
 for await (const chunk of chatClient.completeStreamingChat(
     [{ role: 'user', content: 'Write a short poem about programming.' }]
 )) {
-    const content = chunk.choices?.[0]?.message?.content;
+    const content = chunk.choices?.[0]?.delta?.content;
     if (content) {
         process.stdout.write(content);
     }

sdk/python/README.md

@@ -232,12 +232,9 @@ print(result.choices[0].message.content)  # "42"
 # Streaming chat
 messages = [{"role": "user", "content": "Tell me a joke"}]
 
-def on_chunk(chunk):
-    delta = chunk.choices[0].delta
-    if delta and delta.content:
-        print(delta.content, end="", flush=True)
-
-client.complete_streaming_chat(messages, on_chunk)
+for chunk in client.complete_streaming_chat(messages):
+    if chunk.choices[0].delta.content:
+        print(chunk.choices[0].delta.content, end="", flush=True)
 
 # Unload when done
 model.unload()

sdk/rust/README.md

@@ -175,7 +175,7 @@ let loaded = catalog.get_loaded_models().await?;
 
 ### Model Lifecycle
 
-Each model may have multiple variants (different quantizations, hardware targets). The SDK auto-selects the best available variant, preferring cached versions. All models implement the `IModel` trait.
+Each model may have multiple variants (different quantizations, hardware targets). The SDK auto-selects the best available variant, preferring cached versions. All models are represented by the `Model` type.
 
 ```rust
 let model = catalog.get_model("phi-3.5-mini").await?;
@@ -445,6 +445,7 @@ match manager.catalog().get_model("nonexistent").await {
 | `Serialization(serde_json::Error)` | JSON serialization/deserialization failed |
 | `Validation { reason }` | A validation check on user-supplied input failed |
 | `Io(std::io::Error)` | An I/O error occurred |
+| `Internal { reason }` | An internal SDK error (e.g. poisoned lock) |
 
 ## Configuration
 
@@ -520,4 +521,4 @@ cargo run -p native-chat-completions
 
 ## License
 
-MIT — see [LICENSE](../../LICENSE) for details.
+Microsoft Software License Terms — see [LICENSE](../../LICENSE) for details.