mirror of
https://github.com/MindWorkAI/AI-Studio.git
synced 2026-09-27 00:53:37 +00:00
Share the checks that decide whether a tool can be offered
This commit is contained in:
parent
df257714f2
commit
38d4520e80
@ -0,0 +1,48 @@
|
||||
namespace AIStudio.Tools.ToolCallingSystem;
|
||||
|
||||
/// <summary>
|
||||
/// What keeps a tool from being offered to a model, if anything.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// A reason rather than a yes or no, because whoever asks has to say something different for each
|
||||
/// of them: a model which cannot use tools is a matter of the provider settings, a tool switched off
|
||||
/// by the organization is nothing the user can change, and missing settings are something they can
|
||||
/// fill in themselves.
|
||||
/// </remarks>
|
||||
public enum ToolOfferBlockReason
|
||||
{
|
||||
/// <summary>
|
||||
/// Nothing is in the way, the tool can be offered.
|
||||
/// </summary>
|
||||
NONE,
|
||||
|
||||
/// <summary>
|
||||
/// The organization switched tools off altogether.
|
||||
/// </summary>
|
||||
TOOLS_SWITCHED_OFF,
|
||||
|
||||
/// <summary>
|
||||
/// The selected model or its provider cannot use tools, or no provider is selected at all.
|
||||
/// </summary>
|
||||
MODEL_CANNOT_USE_TOOLS,
|
||||
|
||||
/// <summary>
|
||||
/// This installation does not know the tool, or the tool is not meant for this part of the app.
|
||||
/// </summary>
|
||||
NOT_AVAILABLE_HERE,
|
||||
|
||||
/// <summary>
|
||||
/// The organization switched this tool off.
|
||||
/// </summary>
|
||||
TOOL_SWITCHED_OFF,
|
||||
|
||||
/// <summary>
|
||||
/// A setting the tool cannot work without is missing or invalid.
|
||||
/// </summary>
|
||||
NOT_CONFIGURED,
|
||||
|
||||
/// <summary>
|
||||
/// The provider is not trusted enough for this tool.
|
||||
/// </summary>
|
||||
PROVIDER_CONFIDENCE_TOO_LOW,
|
||||
}
|
||||
@ -22,6 +22,14 @@ public sealed class ToolRegistry
|
||||
private readonly Dictionary<string, ToolDefinition> definitionsById = new(StringComparer.Ordinal);
|
||||
private readonly Dictionary<string, IToolImplementation> implementationsByKey = new(StringComparer.Ordinal);
|
||||
|
||||
/// <summary>
|
||||
/// What the checks of a single tool found.
|
||||
/// </summary>
|
||||
/// <param name="BlockReason">What keeps the tool from being offered, or none.</param>
|
||||
/// <param name="Implementation">The tool's implementation, once it was found.</param>
|
||||
/// <param name="MinimumConfidence">The confidence the tool requires and where that requirement came from, once it was read.</param>
|
||||
private readonly record struct ToolCheck(ToolOfferBlockReason BlockReason, IToolImplementation? Implementation, SettingsManager.ToolMinimumProviderConfidenceResolution? MinimumConfidence);
|
||||
|
||||
public ToolRegistry(
|
||||
IEnumerable<IToolImplementation> implementations,
|
||||
IEnumerable<IToolDefinitionSource> definitionSources,
|
||||
@ -370,36 +378,32 @@ public sealed class ToolRegistry
|
||||
var result = new List<(ToolDefinition, IToolImplementation)>(definitions.Count);
|
||||
foreach (var definition in definitions)
|
||||
{
|
||||
if (!this.settingsManager.IsToolActive(definition.Id))
|
||||
var check = await this.CheckToolAsync(definition, providerConfidence);
|
||||
if (check.MinimumConfidence is { } minimumConfidence)
|
||||
this.logger.LogDebug("Tool '{ToolId}' uses minimum provider confidence '{ConfidenceLevel}' from {Source}.", definition.Id, minimumConfidence.ConfidenceLevel, minimumConfidence.Source);
|
||||
|
||||
switch (check)
|
||||
{
|
||||
this.logger.LogDebug("Skipping tool '{ToolId}' because it is disabled by managed configuration.", definition.Id);
|
||||
continue;
|
||||
}
|
||||
|
||||
if (!this.implementationsByKey.TryGetValue(definition.ImplementationKey, out var implementation))
|
||||
{
|
||||
this.logger.LogWarning("Skipping tool '{ToolId}' because no implementation is registered.", definition.Id);
|
||||
continue;
|
||||
}
|
||||
|
||||
var configurationState = await this.toolSettingsService.GetConfigurationStateAsync(definition, implementation);
|
||||
if (!configurationState.IsConfigured)
|
||||
{
|
||||
this.logger.LogDebug("Skipping tool '{ToolId}' because it is not configured.", definition.Id);
|
||||
continue;
|
||||
}
|
||||
|
||||
var resolution = this.settingsManager.GetMinimumProviderConfidenceResolutionForTool(definition.Id, definition.MinimumProviderConfidence);
|
||||
var minimumToolConfidence = resolution.ConfidenceLevel;
|
||||
this.logger.LogDebug("Tool '{ToolId}' uses minimum provider confidence '{ConfidenceLevel}' from {Source}.", definition.Id, minimumToolConfidence, resolution.Source);
|
||||
|
||||
if (!ToolSelectionRules.IsProviderConfidenceAllowed(providerConfidence, minimumToolConfidence))
|
||||
{
|
||||
this.logger.LogInformation("Skipping tool '{ToolId}' because provider confidence '{ProviderConfidence}' is below the required minimum '{MinimumConfidence}'.", definition.Id, providerConfidence, minimumToolConfidence);
|
||||
continue;
|
||||
}
|
||||
|
||||
case { BlockReason: ToolOfferBlockReason.NONE, Implementation: { } implementation }:
|
||||
result.Add((definition, implementation));
|
||||
break;
|
||||
|
||||
case { BlockReason: ToolOfferBlockReason.TOOL_SWITCHED_OFF }:
|
||||
this.logger.LogDebug("Skipping tool '{ToolId}' because it is disabled by managed configuration.", definition.Id);
|
||||
break;
|
||||
|
||||
case { BlockReason: ToolOfferBlockReason.NOT_CONFIGURED }:
|
||||
this.logger.LogDebug("Skipping tool '{ToolId}' because it is not configured.", definition.Id);
|
||||
break;
|
||||
|
||||
case { BlockReason: ToolOfferBlockReason.PROVIDER_CONFIDENCE_TOO_LOW }:
|
||||
this.logger.LogInformation("Skipping tool '{ToolId}' because provider confidence '{ProviderConfidence}' is below the required minimum '{MinimumConfidence}'.", definition.Id, providerConfidence, check.MinimumConfidence?.ConfidenceLevel);
|
||||
break;
|
||||
|
||||
case { BlockReason: ToolOfferBlockReason.NOT_AVAILABLE_HERE }:
|
||||
this.logger.LogWarning("Skipping tool '{ToolId}' because no implementation is registered.", definition.Id);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
foreach (var selectedToolId in selectedToolIdSet.Where(selectedToolId => definitions.All(definition => !definition.Id.Equals(selectedToolId, StringComparison.Ordinal))))
|
||||
@ -407,4 +411,63 @@ public sealed class ToolRegistry
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Whether a tool can be offered to a provider in this component, and if not, what is in the way.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// Asks the same questions, in the same order, as the preparation of a request does, because
|
||||
/// whoever decides something on the tool's behalf must not come to another answer than the
|
||||
/// request will. The RAG process, for instance, leaves the searching of the data sources to
|
||||
/// Semantic Search only when this says it can be offered; checks of its own which forgot one
|
||||
/// of these would leave a chat without its data sources.<br/><br/>
|
||||
/// Two questions stay out. Whether the tool is selected is the caller's business, and whether
|
||||
/// the tool has anything to offer right now depends on the chat, so only the preparation of a
|
||||
/// request can answer it.
|
||||
/// </remarks>
|
||||
/// <param name="toolId">The tool to check.</param>
|
||||
/// <param name="provider">The provider the request would go to.</param>
|
||||
/// <param name="component">Where the request would come from.</param>
|
||||
/// <returns>ToolOfferBlockReason.NONE when nothing is in the way, otherwise the first obstacle found.</returns>
|
||||
public async Task<ToolOfferBlockReason> GetOfferBlockReasonAsync(string toolId, AIStudio.Settings.Provider provider, Components component)
|
||||
{
|
||||
if (!this.settingsManager.AreToolsEnabled())
|
||||
return ToolOfferBlockReason.TOOLS_SWITCHED_OFF;
|
||||
|
||||
if (!provider.GetToolCallingAvailability().IsAvailable)
|
||||
return ToolOfferBlockReason.MODEL_CANNOT_USE_TOOLS;
|
||||
|
||||
if (this.GetDefinition(toolId) is not { } definition || !definition.VisibleIn.IsVisibleIn(component))
|
||||
return ToolOfferBlockReason.NOT_AVAILABLE_HERE;
|
||||
|
||||
var providerConfidence = provider.UsedLLMProvider.GetConfidence(this.settingsManager).Level;
|
||||
return (await this.CheckToolAsync(definition, providerConfidence)).BlockReason;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Checks one tool on its own, apart from what applies to all tools of a request.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// Shared by the preparation of a request and by GetOfferBlockReasonAsync, so the two cannot
|
||||
/// drift apart. It reports rather than logs: the preparation of a request writes down why a
|
||||
/// tool was left out, while a question asked by the user interface on every render must not.
|
||||
/// </remarks>
|
||||
private async Task<ToolCheck> CheckToolAsync(ToolDefinition definition, ConfidenceLevel providerConfidence)
|
||||
{
|
||||
if (!this.settingsManager.IsToolActive(definition.Id))
|
||||
return new(ToolOfferBlockReason.TOOL_SWITCHED_OFF, null, null);
|
||||
|
||||
if (!this.implementationsByKey.TryGetValue(definition.ImplementationKey, out var implementation))
|
||||
return new(ToolOfferBlockReason.NOT_AVAILABLE_HERE, null, null);
|
||||
|
||||
var configurationState = await this.toolSettingsService.GetConfigurationStateAsync(definition, implementation);
|
||||
if (!configurationState.IsConfigured)
|
||||
return new(ToolOfferBlockReason.NOT_CONFIGURED, implementation, null);
|
||||
|
||||
var minimumConfidence = this.settingsManager.GetMinimumProviderConfidenceResolutionForTool(definition.Id, definition.MinimumProviderConfidence);
|
||||
if (!ToolSelectionRules.IsProviderConfidenceAllowed(providerConfidence, minimumConfidence.ConfidenceLevel))
|
||||
return new(ToolOfferBlockReason.PROVIDER_CONFIDENCE_TOO_LOW, implementation, minimumConfidence);
|
||||
|
||||
return new(ToolOfferBlockReason.NONE, implementation, minimumConfidence);
|
||||
}
|
||||
}
|
||||
193
app/Tests/Tools/ToolCalling/ToolRegistryOfferTests.cs
Normal file
193
app/Tests/Tools/ToolCalling/ToolRegistryOfferTests.cs
Normal file
@ -0,0 +1,193 @@
|
||||
using System.Text.Json;
|
||||
|
||||
using AIStudio.Provider;
|
||||
using AIStudio.Settings;
|
||||
using AIStudio.Tools;
|
||||
using AIStudio.Tools.Services;
|
||||
using AIStudio.Tools.ToolCallingSystem;
|
||||
|
||||
using Microsoft.Extensions.DependencyInjection;
|
||||
using Microsoft.Extensions.Logging.Abstractions;
|
||||
|
||||
namespace AIStudio.Tests.Tools.ToolCalling;
|
||||
|
||||
/// <summary>
|
||||
/// Checks that asking whether a tool can be offered gets the same answer as preparing a request.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// The RAG process leaves the searching of the data sources to Semantic Search only when the
|
||||
/// registry says the tool can be offered. If the question and the preparation of the request ever
|
||||
/// disagreed, a chat would end up searching nothing at all: the RAG process would stand back, and
|
||||
/// the request would offer no tool either. Each reason is therefore checked against both.<br/><br/>
|
||||
/// Not parallelizable, because the settings are reached through Program.SERVICE_PROVIDER, see below.
|
||||
/// </remarks>
|
||||
[TestFixture]
|
||||
[NonParallelizable]
|
||||
public sealed class ToolRegistryOfferTests
|
||||
{
|
||||
private const string TOOL_ID = "test_tool";
|
||||
private const string REQUIRED_SETTING = "endpoint";
|
||||
|
||||
private RustService rustService = null!;
|
||||
private SettingsManager settingsManager = null!;
|
||||
private ServiceProvider serviceProvider = null!;
|
||||
private IServiceProvider previousServiceProvider = null!;
|
||||
|
||||
[SetUp]
|
||||
public void CreateSettings()
|
||||
{
|
||||
// Only builds its HTTP clients. Nothing connects, as long as no tool reads a secret:
|
||||
this.rustService = new RustService("1", "unused");
|
||||
this.settingsManager = new SettingsManager(NullLogger<SettingsManager>.Instance, this.rustService);
|
||||
|
||||
// Self-hosted providers are trusted highly, all others moderately:
|
||||
this.settingsManager.ConfigurationData.Confidence.ConfidenceScheme = ConfidenceSchemes.TRUST_ALL;
|
||||
|
||||
//
|
||||
// The managed configuration asks for the settings through the application's service
|
||||
// provider rather than taking them as an argument, see ConfigMetaBase.SettingsManagerAccess.
|
||||
// Reading the tool's required confidence goes through it, so the settings of this test have
|
||||
// to be the ones found there, and only while this test runs:
|
||||
//
|
||||
this.previousServiceProvider = Program.SERVICE_PROVIDER;
|
||||
this.serviceProvider = new ServiceCollection().AddSingleton(this.settingsManager).BuildServiceProvider();
|
||||
Program.SERVICE_PROVIDER = this.serviceProvider;
|
||||
}
|
||||
|
||||
[TearDown]
|
||||
public void RestoreApplicationState()
|
||||
{
|
||||
Program.SERVICE_PROVIDER = this.previousServiceProvider;
|
||||
this.serviceProvider.Dispose();
|
||||
this.rustService.Dispose();
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task NothingInTheWay()
|
||||
{
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition()), ToolCapableProvider(), ToolOfferBlockReason.NONE, "A tool-capable, highly trusted provider and a tool which needs nothing.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task ToolsSwitchedOffAltogether()
|
||||
{
|
||||
this.settingsManager.ConfigurationData.Tools.EnableTools = false;
|
||||
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition()), ToolCapableProvider(), ToolOfferBlockReason.TOOLS_SWITCHED_OFF, "The organization turned all tools off.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task AModelWithoutTools()
|
||||
{
|
||||
var provider = ToolCapableProvider() with { CapabilityOverrides = new() { FunctionCalling = false } };
|
||||
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition()), provider, ToolOfferBlockReason.MODEL_CANNOT_USE_TOOLS, "The person said their model cannot call functions.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task NoProviderSelected()
|
||||
{
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition()), AIStudio.Settings.Provider.NONE, ToolOfferBlockReason.MODEL_CANNOT_USE_TOOLS, "Without a provider there is no model that could call a tool.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task AToolNotMeantForTheChat()
|
||||
{
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition(visibleInChat: false)), ToolCapableProvider(), ToolOfferBlockReason.NOT_AVAILABLE_HERE, "The tool belongs to the assistants only.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task AToolNobodyKnows()
|
||||
{
|
||||
var registry = this.CreateRegistry(Definition());
|
||||
|
||||
Assert.That(await registry.GetOfferBlockReasonAsync("unknown_tool", ToolCapableProvider(), AIStudio.Tools.Components.CHAT), Is.EqualTo(ToolOfferBlockReason.NOT_AVAILABLE_HERE));
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task AToolSwitchedOffByTheOrganization()
|
||||
{
|
||||
this.settingsManager.ConfigurationData.Tools.DisabledToolIds.Add(TOOL_ID);
|
||||
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition()), ToolCapableProvider(), ToolOfferBlockReason.TOOL_SWITCHED_OFF, "The organization turned this one tool off.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task AToolMissingASetting()
|
||||
{
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition(requiresSetting: true)), ToolCapableProvider(), ToolOfferBlockReason.NOT_CONFIGURED, "The tool cannot work without a setting nobody filled in.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task AProviderTrustedTooLittle()
|
||||
{
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition(minimumConfidence: ConfidenceLevel.HIGH)), LessTrustedProvider(), ToolOfferBlockReason.PROVIDER_CONFIDENCE_TOO_LOW, "The tool asks for high confidence, the provider has a moderate one.");
|
||||
}
|
||||
|
||||
[Test]
|
||||
public async Task ARaisedRequirementCountsAsWell()
|
||||
{
|
||||
this.settingsManager.SetMinimumProviderConfidenceForTool(TOOL_ID, ConfidenceLevel.HIGH, ConfidenceLevel.NONE);
|
||||
|
||||
await this.AssertBothAgree(this.CreateRegistry(Definition()), LessTrustedProvider(), ToolOfferBlockReason.PROVIDER_CONFIDENCE_TOO_LOW, "The tool asks for nothing itself, but its requirement was raised in the settings.");
|
||||
}
|
||||
|
||||
private async Task AssertBothAgree(ToolRegistry registry, AIStudio.Settings.Provider provider, ToolOfferBlockReason expected, string situation)
|
||||
{
|
||||
var reason = await registry.GetOfferBlockReasonAsync(TOOL_ID, provider, AIStudio.Tools.Components.CHAT);
|
||||
var providerConfidence = provider.UsedLLMProvider.GetConfidence(this.settingsManager).Level;
|
||||
var runnableTools = await registry.GetRunnableToolsAsync(provider, AIStudio.Tools.Components.CHAT, [TOOL_ID], providerConfidence, mayRunTools: true);
|
||||
|
||||
Assert.Multiple(() =>
|
||||
{
|
||||
Assert.That(reason, Is.EqualTo(expected), situation);
|
||||
Assert.That(runnableTools.Any(x => x.Definition.Id == TOOL_ID), Is.EqualTo(expected is ToolOfferBlockReason.NONE), "Preparing the request has to come to the same answer as asking beforehand.");
|
||||
});
|
||||
}
|
||||
|
||||
private ToolRegistry CreateRegistry(ToolDefinition definition)
|
||||
{
|
||||
var tool = new TestTool(definition);
|
||||
var toolSettingsService = new ToolSettingsService(this.settingsManager, this.rustService, NullLogger<ToolSettingsService>.Instance);
|
||||
return new ToolRegistry([tool], [new CodeToolDefinitionSource([tool])], this.settingsManager, toolSettingsService, NullLogger<ToolRegistry>.Instance);
|
||||
}
|
||||
|
||||
private static ToolDefinition Definition(ConfidenceLevel minimumConfidence = ConfidenceLevel.NONE, bool requiresSetting = false, bool visibleInChat = true) => new()
|
||||
{
|
||||
Id = TOOL_ID,
|
||||
ImplementationKey = TOOL_ID,
|
||||
MinimumProviderConfidence = minimumConfidence,
|
||||
VisibleIn = new() { Chat = visibleInChat },
|
||||
SettingsSchema = requiresSetting
|
||||
? ToolSettingsSchemaBuilder.Create().Required(REQUIRED_SETTING).Build()
|
||||
: ToolSettingsSchemaBuilder.Create().Build(),
|
||||
Function = new()
|
||||
{
|
||||
Name = TOOL_ID,
|
||||
DescriptionForLLM = "A tool for tests.",
|
||||
Parameters = ToolParameterSchemaBuilder.Create().Build(),
|
||||
},
|
||||
};
|
||||
|
||||
// Self-hosted, so highly trusted, and able to call functions no matter what the rules say:
|
||||
private static AIStudio.Settings.Provider ToolCapableProvider() => new(0, "self-hosted", "Self-hosted", LLMProviders.SELF_HOSTED, new Model("llama3.3:70b", null))
|
||||
{
|
||||
CapabilityOverrides = new() { FunctionCalling = true },
|
||||
};
|
||||
|
||||
private static AIStudio.Settings.Provider LessTrustedProvider() => new(1, "cloud", "Cloud", LLMProviders.OPEN_AI, new Model("gpt-5", null))
|
||||
{
|
||||
CapabilityOverrides = new() { FunctionCalling = true },
|
||||
};
|
||||
|
||||
private sealed class TestTool(ToolDefinition definition) : IToolImplementation
|
||||
{
|
||||
public string ImplementationKey => definition.ImplementationKey;
|
||||
|
||||
public ToolDefinition GetDefinition() => definition;
|
||||
|
||||
public IReadOnlySet<string> SensitiveTraceArgumentNames { get; } = new HashSet<string>(StringComparer.Ordinal);
|
||||
|
||||
public Task<ToolExecutionResult> ExecuteAsync(JsonElement arguments, ToolExecutionContext context, CancellationToken token = default) => Task.FromResult(new ToolExecutionResult());
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user