using System.Text.Json; using ClawdDotNet.Core.Api.Models; using ClawdDotNet.Core.Engine; using ClawdDotNet.Core.Tests.Infrastructure; using Shouldly; namespace ClawdDotNet.Core.Tests.Engine; public sealed class PromptCacheTests { // ═══════════════════════════════════════════════════════════ // Activation // ═══════════════════════════════════════════════════════════ [Theory] [InlineData("auto", "anthropic/claude-sonnet-4-5", true)] [InlineData("auto", "anthropic/claude-haiku-4.5", true)] [InlineData("auto", "openai/gpt-4o", false)] [InlineData("auto", "google/gemini-2.5-flash", false)] [InlineData("on", "openai/gpt-4o", true)] [InlineData("off", "anthropic/claude-sonnet-4-5", false)] [InlineData("OFF", "anthropic/claude-sonnet-4-5", false)] public void Activation_depends_on_setting_and_model(string setting, string model, bool expected) { PromptCache.IsEnabledFor(setting, model).ShouldBe(expected); } // ═══════════════════════════════════════════════════════════ // Placement of the breakpoints // ═══════════════════════════════════════════════════════════ [Fact] public void The_SystemPrompt_gets_a_breakpoint() { var messages = Conversation.Start("System").User("Frage").Build(); PromptCache.ApplyBreakpoints(messages); messages[0].Role.ShouldBe("system"); messages[0].CacheBreakpoint.ShouldBeTrue(); } [Fact] public void The_last_message_with_content_gets_a_rolling_breakpoint() { var messages = Conversation.Start().User("A").Assistant("B").User("C").Build(); PromptCache.ApplyBreakpoints(messages); messages[^1].CacheBreakpoint.ShouldBeTrue(); messages[^1].Content.ShouldBe("C"); } [Fact] public void An_assistant_message_without_content_carries_no_breakpoint() { // assistant with tool_calls has no text content and cannot carry a block. var messages = Conversation.Start().User("A").Build(); messages.Add(ChatMessage.AssistantWithToolCalls([ new ToolCall { Id = "c1", Function = new ToolCallFunction { Name = "T", Arguments = "{}" } } ])); PromptCache.ApplyBreakpoints(messages); messages[^1].CacheBreakpoint.ShouldBeFalse(); messages.Count(m => m.CacheBreakpoint).ShouldBeGreaterThan(0, "der System-Breakpoint muss bleiben"); } [Fact] public void At_most_two_breakpoints_are_set() { // Providers only allow a limited number — they must not accumulate. var messages = Conversation.Start().Repeat(10).Build(); PromptCache.ApplyBreakpoints(messages); messages.Count(m => m.CacheBreakpoint).ShouldBeLessThanOrEqualTo(2); } [Fact] public void Repeated_application_does_not_accumulate_breakpoints() { var messages = Conversation.Start().Repeat(3).Build(); PromptCache.ApplyBreakpoints(messages); messages.Add(ChatMessage.User("Noch eine Frage")); PromptCache.ApplyBreakpoints(messages); messages.Add(ChatMessage.User("Und noch eine")); PromptCache.ApplyBreakpoints(messages); messages.Count(m => m.CacheBreakpoint).ShouldBeLessThanOrEqualTo(2); messages[^1].CacheBreakpoint.ShouldBeTrue("der Breakpoint muss mitwandern"); } [Fact] public void An_empty_list_does_not_lead_to_an_error() { var messages = new List(); Should.NotThrow(() => PromptCache.ApplyBreakpoints(messages)); } // ═══════════════════════════════════════════════════════════ // Prefix stability — the decisive test // ═══════════════════════════════════════════════════════════ /// /// The cached prompt section must be identical to the character between two /// steps. A single timestamp in the system prompt would discard the cache at every step /// — the costs would stay unchanged without it being noticed anywhere. /// That is exactly what this test protects against. /// [Fact] public async Task The_prefix_stays_identical_across_all_steps() { var fixture = new EngineFixture().WithTool(FakeTool.Returning("ok")); var agent = fixture.AddAgent("agent-cache", "TestTool"); agent.Model = "anthropic/claude-sonnet-4-5"; agent.PromptCaching = "on"; // Eight tool steps, then a text answer. for (var i = 0; i < 8; i++) fixture.Client.RespondsWithToolCall("TestTool"); fixture.Client.RespondsWithText("Fertig"); await fixture.Engine.ChatAsync(agent, "Los", "test-instance", default); fixture.Client.ReceivedRequests.Count.ShouldBe(9); // The system message is the stable prefix — it must be serialized // byte-identically in every request. var systemPayloads = fixture.Client.ReceivedRequests .Select(r => JsonSerializer.Serialize(r.Messages[0])) .Distinct() .ToList(); systemPayloads.Count.ShouldBe(1, "der System-Prompt muss über alle Schritte hinweg identisch serialisiert werden:\n" + string.Join("\n", systemPayloads)); systemPayloads[0].ShouldContain("cache_control"); } [Fact] public async Task Without_caching_the_request_contains_no_cache_control() { var fixture = new EngineFixture().WithTool(FakeTool.Returning("ok")); var agent = fixture.AddAgent("agent-nocache", "TestTool"); agent.Model = "openai/gpt-4o"; agent.PromptCaching = "auto"; // so off for this model fixture.Client.RespondsWithText("Fertig"); await fixture.Engine.ChatAsync(agent, "Los", "test-instance", default); var json = JsonSerializer.Serialize(fixture.Client.ReceivedRequests[0].Messages); json.ShouldNotContain("cache_control"); } }