# MentorAgent 1.3.0 release notes

> What MentorAgent 1.3.0 adds and fixes: actions turned on and off outside your code, tenants, any vector store, whole-conversation tests, and how to upgrade.

- URL: https://docs.mentoragent.net/release-notes/1-3-0
- Verified with: MentorAgent 1.3.0
- Last updated: 2026-11-14
- Packages: Novior.MentorAgent, Novior.MentorAgent.Abstractions, Novior.MentorAgent.Blazor, Novior.MentorAgent.Declarative, Novior.MentorAgent.Server

MentorAgent 1.3.0 was published on NuGet on 11 November 2026 (UTC). It is a minor version: it adds features and fixes defects, with no intended break. It also fixes a security defect of severity S1 in `/mentor/chat`: see [Security](https://docs.mentoragent.net/release-notes/1-3-0#security).

> **Warning:**
> **1.3.0 has a security defect in action policies, fixed in 1.3.1.** A policy that left an action out only at the offer could be bypassed (BUG-233). Upgrade to 1.3.1: see [its notes](https://docs.mentoragent.net/release-notes/1-3-1#security).

| Package | Version |
|---|---|
| [Novior.MentorAgent](https://www.nuget.org/packages/Novior.MentorAgent/1.3.0) | 1.3.0 |
| [Novior.MentorAgent.Abstractions](https://www.nuget.org/packages/Novior.MentorAgent.Abstractions/1.3.0) | 1.3.0 |
| [Novior.MentorAgent.Blazor](https://www.nuget.org/packages/Novior.MentorAgent.Blazor/1.3.0) | 1.3.0 |
| [Novior.MentorAgent.Declarative](https://www.nuget.org/packages/Novior.MentorAgent.Declarative/1.3.0) | 1.3.0 |
| [Novior.MentorAgent.Server](https://www.nuget.org/packages/Novior.MentorAgent.Server/1.3.0) | 1.3.0 |

The five packages require each other at exactly this version: upgrade them together. MentorAgent 1.3.0 runs on .NET 10. To upgrade, see [Upgrade from 1.2.0](https://docs.mentoragent.net/release-notes/1-3-0#upgrade-from-120).

## Highlights

- **[Turn actions on and off from outside your code](https://docs.mentoragent.net/release-notes/1-3-0#turn-actions-on-and-off-from-outside-your-code).** An action can be turned off in the code. A governor then decides at run time whether each action is on, which roles it needs, whether the user confirms it, and what the model reads about it.
- **[One instance for several tenants](https://docs.mentoragent.net/release-notes/1-3-0#one-instance-for-several-tenants).** Tell MentorAgent which company a request belongs to, and memory, rate limits, conversations, metrics and retrieval stay apart.
- **[A knowledge base on any vector store](https://docs.mentoragent.net/release-notes/1-3-0#a-knowledge-base-on-any-vector-store).** pgvector, Qdrant, Azure AI Search or an in-memory collection, with no source of your own to write.
- **[An announced action is checked](https://docs.mentoragent.net/release-notes/1-3-0#an-announced-action-is-checked).** When a reply says "I'm adding the note" and no tool ran, the agent gets one more chance to call it, or to say that it was not done.
- **[Whole conversations in your tests](https://docs.mentoragent.net/release-notes/1-3-0#whole-conversations-in-your-tests).** Run multi-turn conversations through the real agent, and check which tools each turn calls.
- **[A link from another site no longer runs a turn](https://docs.mentoragent.net/release-notes/1-3-0#security).** A security fix for `/mentor/chat` with cookie sign-in.

## New features

### Turn actions on and off from outside your code

The code decides which methods are actions. Which actions are on for a customer, which roles they need, and whether they ask for a confirmation often change after a release. An administration console decides them. `[MentorAction(Enabled = false)]` turns an action off in the code. An `IMentorActionGovernor`, registered with `AddMentorActionGovernor<T>()`, answers for each action whether it is on, the roles it requires, whether the user confirms it, and the description the model reads. Each answer can be `null`, or `MentorConfirmationChoice.Code`, to keep what the code says.

```csharp title="ConsoleGovernor.cs"
public class CaseArchive
{
    // Shipped off: it runs only where the governor turns it on
    [MentorAction(Description = "Archives a closed support case",
        Enabled = false, RequiresConfirmation = true)]
    public string ArchiveCase(string caseNumber) =>
        $"Case {caseNumber} archived.";
}

public class ConsoleGovernor(IActionSettings settings)
    : IMentorActionGovernor
{
    // null: what the code says; false: off; true: on
    public ValueTask<bool?> IsEnabledAsync(
        MentorActionRequest request, CancellationToken cancellationToken)
        => settings.IsEnabledAsync(request.ToolName, cancellationToken);

    // null: the code's roles; an empty list: no role needed
    public ValueTask<IReadOnlyList<string>?> GetRequiredRolesAsync(
        MentorActionRequest request, CancellationToken cancellationToken)
        => settings.GetRolesAsync(request.ToolName, cancellationToken);

    // Code: what the code says; Required: ask; None: do not ask
    public ValueTask<MentorConfirmationChoice> GetConfirmationAsync(
        MentorActionRequest request, CancellationToken cancellationToken)
        => ValueTask.FromResult(MentorConfirmationChoice.Code);

    // null: the code's description
    public ValueTask<string?> GetDescriptionAsync(
        MentorActionRequest request, CancellationToken cancellationToken)
        => ValueTask.FromResult<string?>(null);
}
```

An action that is off is offered to no agent, no model reads about it, the MCP server does not list it and a call to it does not run. The governor is asked when a session builds its tools, on every `tools/list` of the MCP server, and before every call. A session keeps the tools that it was built with. Turning an action off applies at once, from its next call. Turning an action on applies from the next session. A confirmation that the governor adds applies from the next call, and a confirmation that it takes away applies from the next session.

A governor can widen what the code allows: turn on an action that ships off, require no role, or take a confirmation away. Whoever implements it holds that power, so check there what may be widened and with whose approval. A governor that throws, or does not answer within [`ActionPolicyTimeout`](https://docs.mentoragent.net/reference/options#actionpolicytimeout), stops the action. An application has one governor: a second registration throws. The A2A card follows only the code. The confirmation box keeps the description from the code.

The decisions say where an answer came from: `MentorActionDecision.RolesFromOutside` and `ConfirmationFromOutside`, and the new reason codes `disabled` and `governor-failed`.

### One instance for several tenants

An application that serves more than one company from one instance needs MentorAgent to keep each company apart. An `IMentorTenantResolver`, registered with `AddMentorTenantResolver<T>()`, names the [tenant](https://docs.mentoragent.net/reference/glossary#tenant) of each request. Your actions read it from `IMentorTenant.Id`.

```csharp title="ClaimTenantResolver.cs"
// The tenant is a claim of the signed-in user
public class ClaimTenantResolver : IMentorTenantResolver
{
    // null: the request is refused
    public ValueTask<string?> ResolveAsync(
        MentorTenantRequest request, CancellationToken cancellationToken)
        => ValueTask.FromResult(
            request.User?.FindFirst("tenant_id")?.Value);
}

// An action reads the tenant of the request
public class OrderActions(IMentorTenant tenant, IOrderStore store)
{
    [MentorAction(Description = "Counts the open orders",
        ReadOnly = true)]
    public Task<int> CountOpenOrders() =>
        store.CountOpenAsync(tenant.Id!);
}
```

With a resolver:

- **No request without a tenant.** A resolver that throws, or answers `null` or an empty text, refuses the request before the model or the action. A turn whose tenant is not the one its conversation began with is refused too.
- **Memory, rate limits and conversations are the tenant's own.** The key of the memory and of [`RateLimitPerUser`](https://docs.mentoragent.net/reference/options#ratelimitperuser) carries the tenant, and a session snapshot is restored for its tenant only.
- **Metrics name the tenant.** Every counter and the `mentor.turn` span have the `mentoragent.tenant` tag. The dashboard and `GET /mentor/admin/metrics` show the reader's tenant only.
- **Retrieval and logs know the tenant.** `MentorRagRequest.TenantId` gives a knowledge-base source the turn's tenant. MentorAgent filters nothing itself: the source returns that tenant's documents. Every log line of a turn is written in a scope with `mentoragent.tenant`.

Without a resolver there is one tenant, as before, and `IMentorTenant.Id` is `null`.

### A knowledge base on any vector store

For a collection of `Microsoft.Extensions.VectorData`, such as pgvector, Qdrant, Azure AI Search or an in-memory one, you no longer write an `IMentorRagSource`. Register the collection with `AddMentorVectorStoreRag`, and say which part of a record is the document:

```csharp title="Program.cs"
builder.Services.AddMentorVectorStoreRag(
    sp => sp.GetRequiredService<VectorStore>()
        .GetCollection<Guid, Doc>("docs"),
    new MentorVectorStoreRagOptions<Doc>
    {
        Content = d => d.Text,       // required
        Title = d => d.Title,
        SourceUrl = d => d.Url,
        // With a tenant resolver: the tenant's documents only
        Filter = request => d => d.Tenant == request.TenantId,
    });

builder.Services.AddMentorAgent(options =>
{
    options.UseRag = true;
    // options.EmbeddingGenerator = ...;
});
```

The options also give the title, the link and the metadata of a record, and `Filter` says which records a request may see, for example those of its tenant.

The source reads every score as a similarity, whatever the distance function of the collection. With `CosineDistance`, the Postgres default, it uses 1 minus the distance, so [`RagMinScore`](https://docs.mentoragent.net/reference/options#ragminscore) keeps the nearest documents. With a Euclidean, Manhattan or Hamming distance, or with no distance function, the registration fails at startup.

With `EmbeddingGenerator` set, the message is embedded once per turn, and routing, tool filtering and memory share that vector. The source can also have a generator of its own. Without either, the collection embeds the text itself.

### An announced action is checked

A model can end its reply with "I'm registering the note" and call nothing, or say that something is done when nothing ran (BUG-220). [`CheckAnnouncedActions`](https://docs.mentoragent.net/reference/options#checkannouncedactions) is on by default. After a turn in which no tool was called, a model checks whether the reply announces an action or reports one as done. If it does, the agent gets one more request in the same turn, with the same tools. That request tells the agent to call the tool now, or to say that it was not done. The reply already shown is not held back, and the call passes the same checks as any other.

The check costs a few hundred tokens after every reply that called no tool. It goes to [`ClassifierChatClient`](https://docs.mentoragent.net/reference/options#classifierchatclient), or to `ChatClient` without one, so a small model there keeps the cost down. It works on Path A with the history kept by MentorAgent, not with [`UseServiceManagedHistory`](https://docs.mentoragent.net/reference/options#useservicemanagedhistory) nor with a pre-built `Agent`.

### Whole conversations in your tests

`MentorEvaluator.RunAsync` sends each case to the model alone. `RunConversationsAsync` runs whole conversations through the agent itself, with its tools, roles, filters, knowledge base, memory and the history from one turn to the next. A turn can require tools, forbid others, set a token budget and a limit on the time to the first token, or expect a refusal.

```csharp title="ConversationTests.cs"
var report = await evaluator.RunConversationsAsync(
    [
        new EvalConversation("close a case",
        [
            new EvalTurn("What is the status of case C-1?")
            {
                ExpectTools = ["get_case_status"],
            },
            new EvalTurn("Close it, please.")
            {
                ExpectTools = ["close_case"],
                MaxTimeToFirstToken = TimeSpan.FromSeconds(3),
            },
        ]),
        new EvalConversation("out of scope",
        [
            new EvalTurn("Write me a poem about the sea")
            {
                ExpectRefusal = EvalRefusal.OutOfScope,
            },
        ]),
    ],
    new MentorEvalOptions
    {
        // Sign in a test user here: anonymous otherwise
        PrepareSession = (services, ct) => Task.CompletedTask,
        // Default: every confirmation is answered no
        // ApproveConfirmations = true,
        MaxTotalTokens = 20_000,
    });

foreach (var r in report.Results.Where(r => !r.Passed))
    output($"{r.Conversation} turn {r.Turn}: {r.Notes}");

report.ThrowIfFailed();
```

**Every confirmation is answered no by default: an evaluation does not write data on its own.** `MentorEvalOptions.ApproveConfirmations` answers yes, and `PrepareSession` sets the user or the page of the conversation before the first turn, for example to sign in a test user. Each conversation runs in a session of its own. See [Test without a model](https://docs.mentoragent.net/configure/test-without-model) for the tests that need no model.

### Other features

- **The rules of actions, by name.** `ACTION-RULES.md`, in the repository, lists the rules by which a method becomes an action, how actions are named, and how roles and confirmations add up. Each rule has a name that does not change and a test. A rule that comes in, changes or is retired is named in the release notes of its version. In 1.3.0 the governor and the agent sources bring eight new rules: `enabled.off-by-default`, `enabled.external-decides`, `surface.governor-session`, `roles.external-replace`, `confirm.external-decides`, `describe.external-replace`, `declarative.functions-match` and `declarative.no-hosted-tools`. Four rules now also cover the governor: `surface.mcp-withholds-gated`, `surface.card-ungated-only`, `roles.checked-before-confirmation` and `confirm.predicate-adds`. Every rule is in [How methods become actions](https://docs.mentoragent.net/concepts/action-rules).
- **An agent source says what it left out.** `IMentorAgentSource.LoadAsync` returns the agents and a `MentorAgentRejection` for each definition left out or tool taken away. An `IMentorAgentSourceObserver`, registered with `AddMentorAgentSourceObserver<T>()`, receives the report each time a coordinator is built. An existing source works unchanged.
- **Options you can change while the application runs.** `MentorRuntimeOptions.Changeable` lists them, and says whether a change counts from the next turn, such as `Language` or `ConfirmationTimeout`, or from the next session, such as `MentorshipLevel`. Every other option is read before the application starts.
- **"Not found in the documents".** With [`RagNoResultsNotice`](https://docs.mentoragent.net/reference/options#ragnoresultsnotice), off by default, the model is told when the knowledge-base search kept no document, so it does not answer from memory.
- **Failed searches are counted.** With [`EnableObservability`](https://docs.mentoragent.net/reference/options#enableobservability), a knowledge-base search that fails is counted on `mentoragent.rag_failures`, and each search has a `mentor.rag.search` span.
- **A source hears when the conversation changes.** `IMentorRagSource.OnConversationChangedAsync` tells a source that keeps state that the conversation was reset, restored or replaced.
- **The coordinator's sampling.** [`CoordinatorSampling`](https://docs.mentoragent.net/reference/options#coordinatorsampling) sets temperature, top-p, top-k, the output limit, the penalties and the seed on every request of the coordinator. A value that you leave unset keeps the provider's default.
- **A warmer start.** `WarmUpChatModel`, with [`WarmUpAtStartup`](https://docs.mentoragent.net/reference/options#warmupatstartup), sends the coordinator's model one small request at startup, so the first user does not wait for the connection or for a local model to load.
- **A provider that ignores a required tool call is reported.** Ollama ignores `tool_choice: "required"`, so [`RequireLookupForRecordQuestions`](https://docs.mentoragent.net/reference/options#requirelookupforrecordquestions) and [`RequireActionForChangeRequests`](https://docs.mentoragent.net/reference/options#requireactionforchangerequests) had no effect with it, and nothing said so. Now a warning says so, once per provider client.
- **A call to an action not offered is reported.** A call to an action that the agent was not given in the turn runs nothing, as before. An `IMentorActionObserver` now receives its decision, `Denied` with the reason code `not-offered`.
- **A project template.** The repository has a `dotnet new` template, `templates/mentoragent-blazor`: a Blazor Server helpdesk with three actions, roles, confirmations and a test project that runs whole conversations with a scripted model. It is installed from a clone of the repository, not from NuGet.

## Improvements

- **A knowledge-base source that answers `null` fails at once.** The message says that a source that finds nothing returns an empty list, instead of a `NullReferenceException` later on. The turn goes on without documents, as before.
- **Declarative agents: functions that name no action are taken away.** In `Novior.MentorAgent.Declarative`, a `kind: function` entry that names no action of the session is removed from the agent with a warning. The name can be unknown, or the action can be off. Before, the agent had a function with nothing behind it: the model could call it, nothing ran, and nothing was logged.
- **A check of the public API.** At pack time, every package is checked against the public API of 1.2.0.
- **Description and tags on NuGet.** The packages say what MentorAgent is: AI agents in a .NET application under your rules. The tags of `Novior.MentorAgent`, `Novior.MentorAgent.Server` and `Novior.MentorAgent.Blazor` now include `ai-governance`, `governance`, `authorization`, `roles`, `approval` and `human-in-the-loop`, and the `mentor` tag is gone from all five packages.

## Fixes

Each defect has a severity from S1, the most severe, to S4: see [Versioning and support](https://docs.mentoragent.net/release-notes#versioning-and-support).

- **BUG-220 (S3):** with `HitlMode` set to `Blocking` and a Chat Completions client, the model could announce an action that asks for no confirmation, and end its reply without calling it. Now [`CheckAnnouncedActions`](https://docs.mentoragent.net/release-notes/1-3-0#an-announced-action-is-checked) gives it one more request to call the action, or to say that it was not done. On a sample application, with the check off 18 of 24 replies said a note was written when it was not; with it on, 23 of 24 notes were written.
- **BUG-110 (S3):** when a restored conversation was replaced by a new one, because the service no longer knew it, the knowledge-base search kept the recent messages of the conversation that was gone. Now they are cleared, as on a reset or a restore.
- **BUG-229 (S3):** a knowledge-base source that embeds the message with a model of its own could be handed the vector of `EmbeddingGenerator`, or routing, tool filtering and memory could be handed the vector of the source. It depended on which of them asked first in the turn. Now each embedding model gets its own vector, still computed once per turn.

The security fix is under [Security](https://docs.mentoragent.net/release-notes/1-3-0#security).

## Security

**BUG-230 (S1), in `Novior.MentorAgent.Server`.** `GET /mentor/chat` ran a turn for any request that the browser sent with the sign-in cookie. With cookie sign-in (`SameSite=Lax`), a link clicked on another site ran a turn as the signed-in user, with the question that the link's author chose. This happened even with `RequireAuthorization`.

Now `GET` and `POST /mentor/chat` answer `403` before the turn when the browser's Fetch Metadata says that another site started the request. That is the case when `Sec-Fetch-Site` is `cross-site` or `same-site`, and `Sec-Fetch-Mode` is not `cors`. A warning `chat.cross-site-refused` is logged, without the question. These requests work as before: calls from your own page, `cors` requests, and clients that send no Fetch Metadata (such as servers and mobile apps).

Two cases are left to your application: a `SameSite=None` sign-in cookie, and browsers that send no Fetch Metadata, such as Safari before 16.4. For them, add a check of your own, such as antiforgery tokens or a custom request header: see [Upgrade from 1.2.0](https://docs.mentoragent.net/release-notes/1-3-0#upgrade-from-120).

## Breaking changes

This version has no intended breaking change. Three changes of behavior are worth checking when you upgrade: [CheckAnnouncedActions](https://docs.mentoragent.net/release-notes/1-3-0#an-announced-action-is-checked) is on by default, `/mentor/chat` refuses requests that another site started, and declarative agents lose the functions that name no action. The steps are in [Upgrade from 1.2.0](https://docs.mentoragent.net/release-notes/1-3-0#upgrade-from-120).

## Deprecations

This version deprecates nothing.

## Dependency updates

| Package | From | To | Why |
|---|---|---|---|
| `Microsoft.Agents.AI` and `Microsoft.Agents.AI.Workflows` | 1.26.0 | 1.27.0 | The Agent Framework 1.27 line. Its two breaking changes are in parts MentorAgent does not use: `AddFoundryResponses` for hosted Foundry applications, and the redirect callbacks of `DefaultHttpRequestHandler`. |
| `Microsoft.Agents.AI.Declarative` (in `Novior.MentorAgent.Declarative`) | 1.26.0-rc1 | 1.27.0-rc1 | The same line. |
| `Microsoft.Extensions.VectorData.Abstractions` | (none) | 10.10.0 | New, for the vector store source. Agent Framework already brought it. |

The other dependencies are unchanged: `Microsoft.Extensions.AI` 10.11.0, `ModelContextProtocol` 2.3.0, `A2A` 1.0.0-preview3.

## Known issues

The defects that are still open in 1.3.0, with what to do about each one, are on the [Known issues](https://docs.mentoragent.net/reference/known-issues) page, together with the prerelease packages and the package versions to pin. The limits that are not defects are in [Known limitations](https://docs.mentoragent.net/reference/known-limitations).

## Upgrade from 1.2.0

1. **Upgrade the five packages together.** Each package requires the others at exactly its own version.
2. **Check `/mentor/chat` if a front end calls it from another site.** A request that another site started now gets `403`. Your own page and `cors` requests work as before. With a `SameSite=None` sign-in cookie, or for browsers without Fetch Metadata, add a check of your own: see [Security](https://docs.mentoragent.net/release-notes/1-3-0#security).
3. **Decide about `CheckAnnouncedActions`.** It is on by default, and costs a few hundred tokens after each reply that called no tool. Give [`ClassifierChatClient`](https://docs.mentoragent.net/reference/options#classifierchatclient) a small model, or set `CheckAnnouncedActions = false`.
4. **Check your declarative agents.** A `kind: function` entry that names no action of the session is now removed, and a warning names it. Fix the name, or remove the entry.
5. **Update the links you write by hand.** If a page links `MentorAgent.css` and `MentorAgent.js` itself, as the `index.html` of a [Blazor WebAssembly](https://docs.mentoragent.net/configure/blazor-webassembly#minimal-configuration) client or of a [.NET MAUI](https://docs.mentoragent.net/configure/maui#minimal-configuration) app does, change `?v=1.2.0` to `?v=1.3.0` in both links.
6. **If you use pgvector with Semantic Kernel.** `Microsoft.SemanticKernel.Connectors.PgVector` 1.74.0-preview is built on `Microsoft.Extensions.VectorData` 10.1. MentorAgent references version 10.10, and with it every search fails with `MissingMethodException`. Use `CommunityToolkit.VectorData.PgVector` instead.

If you upgrade from 1.1.0, first read [Upgrade from 1.1.0](https://docs.mentoragent.net/release-notes/1-2-0#upgrade-from-110) in the 1.2.0 notes.

## Full list of changes

Every entry of this version is in the [1.3.0 section of CHANGELOG.md](https://github.com/Novior-dev/MentorAgent/blob/main/CHANGELOG.md#130---2026-11-05), which is also the [release notes on NuGet](https://www.nuget.org/packages/Novior.MentorAgent/1.3.0#releasenotes-body-tab).

---

- Previous: [MentorAgent 1.3.1 release notes](https://docs.mentoragent.net/release-notes/1-3-1.md)
- Next: [MentorAgent 1.2.0 release notes](https://docs.mentoragent.net/release-notes/1-2-0.md)
