Bump OllamaSharp from 5.1.19 to 5.4.6

[dependabot]

Updated OllamaSharp from 5.1.19 to 5.4.6.

Release notes

Sourced from OllamaSharp's releases.

5.4.6

• Allow the model to do multiple tool calls sequentially when using the Chat class like first querying users and then getting details for a single user, for example.

5.4.5

• Allow setting thinking to strings in addition to true & false like "high"/"medium"/"low" for gpt-oss #​312

Thanks @​byronmcclain

5.4.4

• Update packages #​317

Thanks @​Joy-less

5.4.3

• Improve namespace handling in source generator #​318

Thanks @​Joy-less

5.4.2

• Respect a few recent Microsoft.Extensions.AI additions #​319

Thanks @​stephentoub

5.4.1

• Allow opting in to NativeAOT with a given JsonSerializerContext with known types #​316

5.3.12

• OllamaSharp dropping tool calls with gpt-oss #​306
• Use source-generation JSON for NativeAOT support #​297
• Keep tools after tool call #​308
• Update Microsoft.Extensions.AI packages to 9.9.0 #​314
• Forwarding Error content in McpClientTool #​304
• Fix tests Allows_Line_Breaks_In_Summary and ListRunningModels. #​309

Thanks @​byronmcclain, @​ZhaoYunxiong, @​2767mr, @​rogerbarreto, @​npp127 and @​AustinWise

5.3.11

5.3.10

5.3.9

5.3.8

5.3.7

5.3.6

• Improved environment variable handling with MCP tools #​303

---

Thanks @​npp127

5.3.5

• Updates Microsoft.Extensions.AI to 9.8.0 #​301

---

Thanks @​rogerbarreto

5.3.4

• Add ContextLength when listing loaded models #​291

---

Thanks @​mili-tan

5.3.3

• Fix boolean parameter handling in ToolSourceGenerator #​286
• Add support for ChatOptions.Instructions and ChatOptions.RawRepresentationFactory #​287

---

Thanks @​DillionLowry and @​stephentoub

5.3.1

• Add Message.ToolName #​284

---

Thanks @​mili-tan

5.2.10

• Maps thinking content from Microsoft.Extensions.AI as TextReasoningContent
• Adds a tool demo for Microsoft.Extensions.AI #​281

---

Thanks @​twenzel

5.2.9

• Add support for "Think" with Microsoft.Extensions.AI ChatOptions #​280

---

Thanks @​Jimex

5.2.8

Improved the source code generator for Ollama tools:

• supports line breaks in summaries (#​251)
• supports tools without namespace (#​262)
• won't cause warnings for missing XML documentation of the generator tool class (#​263)

---

Recap: Providing tools is as simple as implementing a method and decorating it with the OllamaTool attribute.

/// <summary>
/// Get the current weather for a city
/// </summary>
/// <param name="city">Name of the city</param>
[OllamaTool]
public static string GetWeather(string city) => $"It's cold at only 6°C in {city}.";

Make sure to add <GenerateDocumentationFile>true</GenerateDocumentationFile> to your project file to include the XML documentation when building.

See tool support for more information.

5.2.7

Improvements to the Chat class

• Adds support for multiple tool calls
• Adds an event OnThink that gets fired for thinking tokens if Think is set to true
• Adds an event OnToolCall that gets fired once the AI model wants to call a tool
• Adds an event OnToolResult that gets fired once a result is available for a tool call that the AI model requested

Demo Console:

• Prints tool calls as they happen in between messages from the AI model

5.2.6

The Chat class can now yield thoughts over OnThink(string) when thinking is allowed (Think=true) #​273.

You can easily experiment with this in the console demos by using the command /togglethink that switches the think mode from null → false → true → null ...

5.2.5

• Skip initializing Think property #​271
• Return typed MCP tools from GetFromMcpServers() #​260

5.2.4

• Add token usage to last value produced by IChatClient.GetStreamingResponseAsync() #​270

---

Thanks @​jmickeyd

5.2.3

• Update ModelContextProtocol to version 0.2.0-preview.3

---

Thanks @​RynFaulkner

5.2.2

• Make Chat.Think nullable, used for set null to do not parse <think> #​256 - thanks @​mili-tan

→ learn more about think in release 5.2.0

5.2.1

• Support think with Chat #​255

→ learn more about think in release 5.2.0

5.2.0

• Add support for think and thinking with Ollama 0.9 #​254 - thanks @​mili-tan

---

Important notes

The Think parameter controls whether the models are allowed to reason and how the reasoning tokens are handled.

Reasoning model	Marked "thinking" in Ollama library	Think=false	Think=true
Yes	Yes	Disables reasoning	Enables reasoning + Separates reasoning tokens in Message.Thinking
Yes	No	Reasoning stays enabled + Reasoning tags will appear as <think></think> in the models response	❌ Error: Model does not support thinking → Download the model again
No	No	No effect	❌ Error: Model does not support thinking

5.1.20

→ see 5.2.0

Commits viewable in compare view.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
• @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
• @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
• @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
• @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions