From 83c263e98e92c5a01b667aab00d5a2357fbffe2e Mon Sep 17 00:00:00 2001 From: Dmitry Ng <19asdek91@gmail.com> Date: Fri, 29 May 2026 00:06:47 +0300 Subject: [PATCH] feat(qwen): enhance agent configurations with thinking control parameters Updated the Qwen agent configuration to include `extra_body` parameters for thinking control across various models. Added `enable_thinking` and `preserve_thinking` options for reasoning agents, while utility agents have `enable_thinking` set to false. Adjusted the Qwen client initialization to support these new configurations. Updated test report to reflect changes in success rates and latencies. --- backend/pkg/providers/qwen/config.yml | 50 ++ backend/pkg/providers/qwen/qwen.go | 11 + examples/tests/qwen-report.md | 626 +++++++++++++------------- 3 files changed, 374 insertions(+), 313 deletions(-) diff --git a/backend/pkg/providers/qwen/config.yml b/backend/pkg/providers/qwen/config.yml index 96d00ce6..01810a47 100644 --- a/backend/pkg/providers/qwen/config.yml +++ b/backend/pkg/providers/qwen/config.yml @@ -1,8 +1,32 @@ +# Qwen (Alibaba Cloud DashScope) agent configuration. +# +# Strategy: qwen3.7-max (flagship) for critical reasoning, qwen3.6-plus (mid-tier +# multimodal Plus) for orchestration, qwen3.5-flash for cheap utility, qwen3-coder-* +# for code-specialized tasks (installer/coder). +# +# CRITICAL thinking control via extra_body (DashScope-specific, not OpenAI standard): +# - enable_thinking=false: utility agents (simple, simple_json, reflector, searcher, +# enricher) MUST set this explicitly. Qwen3.5/3.6/3.7 hybrid models have thinking +# ENABLED by default. Without disabling, reasoning_content leaks into content and +# corrupts short deterministic outputs (e.g. docker image selector returning the +# full chain-of-thought instead of just "vxcontrol/kali-linux"). +# - enable_thinking=true: reasoning agents (primary, assistant, generator, refiner, +# adviser, pentester) explicitly enable thinking. Redundant with hybrid defaults +# but defensive against future provider changes. +# - preserve_thinking=true: keeps reasoning_content from previous assistant turns +# in subsequent requests. Supported ONLY by qwen3.7-max and qwen3.6-plus families. +# Required for agent loops with tool calls to preserve reasoning continuity. +# Works together with WithPreserveReasoningContent() in qwen.go. +# - qwen3-coder-* (coder, installer) are NOT hybrid thinking models — no thinking +# control needed. + simple: model: "qwen3.5-flash" temperature: 0.6 n: 1 max_tokens: 8192 + extra_body: + enable_thinking: false price: input: 0.1 output: 0.4 @@ -14,6 +38,8 @@ simple_json: n: 1 max_tokens: 4096 json: true + extra_body: + enable_thinking: false price: input: 0.1 output: 0.4 @@ -24,6 +50,9 @@ primary_agent: temperature: 1.0 n: 1 max_tokens: 16384 + extra_body: + enable_thinking: true + preserve_thinking: true price: input: 0.5 output: 3.0 @@ -34,6 +63,9 @@ assistant: temperature: 1.0 n: 1 max_tokens: 16384 + extra_body: + enable_thinking: true + preserve_thinking: true price: input: 0.5 output: 3.0 @@ -44,6 +76,9 @@ generator: temperature: 1.0 n: 1 max_tokens: 32768 + extra_body: + enable_thinking: true + preserve_thinking: true price: input: 2.5 output: 7.5 @@ -54,6 +89,9 @@ refiner: temperature: 1.0 n: 1 max_tokens: 20480 + extra_body: + enable_thinking: true + preserve_thinking: true price: input: 2.5 output: 7.5 @@ -64,6 +102,9 @@ adviser: temperature: 1.0 n: 1 max_tokens: 8192 + extra_body: + enable_thinking: true + preserve_thinking: true price: input: 2.5 output: 7.5 @@ -74,6 +115,8 @@ reflector: temperature: 0.7 n: 1 max_tokens: 4096 + extra_body: + enable_thinking: false price: input: 0.1 output: 0.4 @@ -84,6 +127,8 @@ searcher: temperature: 0.7 n: 1 max_tokens: 4096 + extra_body: + enable_thinking: false price: input: 0.1 output: 0.4 @@ -94,6 +139,8 @@ enricher: temperature: 0.7 n: 1 max_tokens: 4096 + extra_body: + enable_thinking: false price: input: 0.1 output: 0.4 @@ -124,6 +171,9 @@ pentester: temperature: 0.8 n: 1 max_tokens: 16384 + extra_body: + enable_thinking: true + preserve_thinking: true price: input: 0.5 output: 3.0 diff --git a/backend/pkg/providers/qwen/qwen.go b/backend/pkg/providers/qwen/qwen.go index beee6f63..44ffd6f9 100644 --- a/backend/pkg/providers/qwen/qwen.go +++ b/backend/pkg/providers/qwen/qwen.go @@ -83,11 +83,22 @@ func New( return nil, err } + // Alibaba Cloud DashScope OpenAI-compatible API. Thinking is controlled via + // extra_body.enable_thinking (true/false) in the per-agent config — this is a + // DashScope-specific parameter, not OpenAI standard. Qwen3.5/3.6/3.7 hybrid + // models have thinking ENABLED by default, so utility agents must explicitly + // set enable_thinking=false or reasoning_content will be returned inline as + // part of content (corrupting outputs that expect short deterministic answers + // like docker image selection or descriptors). + // WithPreserveReasoningContent() is required for multi-turn with tool calls + // when preserve_thinking=true is set in extra_body for qwen3.7-max/qwen3.6-plus + // (other Qwen3 models do not support preserve_thinking). client, err := openai.New( openai.WithToken(cfg.QwenAPIKey), openai.WithModel(QwenAgentModel), openai.WithBaseURL(cfg.QwenServerURL), openai.WithHTTPClient(httpClient), + openai.WithPreserveReasoningContent(), ) if err != nil { return nil, err diff --git a/examples/tests/qwen-report.md b/examples/tests/qwen-report.md index 34b41008..56c2f14e 100644 --- a/examples/tests/qwen-report.md +++ b/examples/tests/qwen-report.md @@ -1,27 +1,27 @@ # LLM Agent Testing Report -Generated: Wed, 27 May 2026 23:05:00 UTC +Generated: Thu, 28 May 2026 16:06:51 UTC ## Overall Results | Agent | Model | Reasoning | Success Rate | Average Latency | |-------|-------|-----------|--------------|-----------------| -| simple | qwen3.5-flash | true | 23/23 (100.00%) | 3.014s | -| simple_json | qwen3.5-flash | true | 5/5 (100.00%) | 7.088s | -| primary_agent | qwen3.6-plus | true | 23/23 (100.00%) | 5.366s | -| assistant | qwen3.6-plus | true | 23/23 (100.00%) | 5.758s | -| generator | qwen3.7-max | true | 23/23 (100.00%) | 3.473s | -| refiner | qwen3.7-max | true | 23/23 (100.00%) | 3.352s | -| adviser | qwen3.7-max | true | 22/23 (95.65%) | 2.941s | -| reflector | qwen3.5-flash | true | 23/23 (100.00%) | 3.377s | -| searcher | qwen3.5-flash | true | 23/23 (100.00%) | 4.025s | -| enricher | qwen3.5-flash | true | 23/23 (100.00%) | 2.857s | -| coder | qwen3-coder-plus | true | 23/23 (100.00%) | 1.556s | -| installer | qwen3-coder-flash | true | 20/23 (86.96%) | 1.060s | -| pentester | qwen3.6-plus | true | 23/23 (100.00%) | 5.504s | +| simple | qwen3.5-flash | false | 23/23 (100.00%) | 1.194s | +| simple_json | qwen3.5-flash | false | 4/5 (80.00%) | 0.945s | +| primary_agent | qwen3.6-plus | true | 23/23 (100.00%) | 6.079s | +| assistant | qwen3.6-plus | true | 23/23 (100.00%) | 5.512s | +| generator | qwen3.7-max | true | 23/23 (100.00%) | 5.172s | +| refiner | qwen3.7-max | true | 23/23 (100.00%) | 5.455s | +| adviser | qwen3.7-max | true | 23/23 (100.00%) | 4.750s | +| reflector | qwen3.5-flash | true | 23/23 (100.00%) | 1.222s | +| searcher | qwen3.5-flash | true | 23/23 (100.00%) | 1.083s | +| enricher | qwen3.5-flash | true | 23/23 (100.00%) | 0.972s | +| coder | qwen3-coder-plus | true | 23/23 (100.00%) | 1.702s | +| installer | qwen3-coder-flash | true | 23/23 (100.00%) | 1.124s | +| pentester | qwen3.6-plus | true | 23/23 (100.00%) | 9.207s | -**Total**: 277/281 (98.58%) successful tests -**Overall average latency**: 3.587s +**Total**: 280/281 (99.64%) successful tests +**Overall average latency**: 3.575s ## Detailed Results @@ -31,38 +31,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 2.746s | | -| Text Transform Uppercase | ✅ Pass | 2.043s | | -| Count from 1 to 5 | ✅ Pass | 3.729s | | -| Math Calculation | ✅ Pass | 1.686s | | -| Basic Echo Function | ✅ Pass | 1.282s | | -| Streaming Simple Math Streaming | ✅ Pass | 1.606s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 2.200s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 0.928s | | +| Simple Math | ✅ Pass | 1.515s | | +| Text Transform Uppercase | ✅ Pass | 1.075s | | +| Count from 1 to 5 | ✅ Pass | 1.066s | | +| Math Calculation | ✅ Pass | 1.122s | | +| Basic Echo Function | ✅ Pass | 1.252s | | +| Streaming Simple Math Streaming | ✅ Pass | 0.603s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.569s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 0.800s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 1.163s | | -| Search Query Function | ✅ Pass | 1.264s | | -| Ask Advice Function | ✅ Pass | 1.232s | | -| Streaming Search Query Function Streaming | ✅ Pass | 0.884s | | -| Basic Context Memory Test | ✅ Pass | 2.803s | | -| Function Argument Memory Test | ✅ Pass | 0.750s | | -| Function Response Memory Test | ✅ Pass | 0.951s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 1.953s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 1.255s | | -| Penetration Testing Methodology | ✅ Pass | 7.005s | | -| Vulnerability Assessment Tools | ✅ Pass | 19.557s | | -| SQL Injection Attack Type | ✅ Pass | 2.703s | | -| Penetration Testing Framework | ✅ Pass | 5.521s | | -| Web Application Security Scanner | ✅ Pass | 4.520s | | -| Penetration Testing Tool Selection | ✅ Pass | 1.533s | | +| JSON Response Function | ✅ Pass | 1.795s | | +| Search Query Function | ✅ Pass | 1.148s | | +| Ask Advice Function | ✅ Pass | 1.347s | | +| Streaming Search Query Function Streaming | ✅ Pass | 0.834s | | +| Basic Context Memory Test | ✅ Pass | 0.655s | | +| Function Argument Memory Test | ✅ Pass | 1.019s | | +| Function Response Memory Test | ✅ Pass | 1.023s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 1.142s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 0.996s | | +| Penetration Testing Methodology | ✅ Pass | 2.497s | | +| Vulnerability Assessment Tools | ✅ Pass | 1.849s | | +| SQL Injection Attack Type | ✅ Pass | 0.552s | | +| Penetration Testing Framework | ✅ Pass | 1.971s | | +| Web Application Security Scanner | ✅ Pass | 1.461s | | +| Penetration Testing Tool Selection | ✅ Pass | 1.152s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 3.014s +**Average latency**: 1.194s --- @@ -72,15 +72,15 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Person Information JSON | ✅ Pass | 4.643s | | -| User Profile JSON | ✅ Pass | 5.759s | | -| Streaming Person Information JSON Streaming | ✅ Pass | 6.514s | | -| Project Information JSON | ✅ Pass | 7.046s | | -| Vulnerability Report Memory Test | ✅ Pass | 11.475s | | +| Project Information JSON | ✅ Pass | 0.751s | | +| User Profile JSON | ✅ Pass | 0.767s | | +| Person Information JSON | ✅ Pass | 1.137s | | +| Vulnerability Report Memory Test | ❌ Fail | 1.318s | got map\[string\]interface \{\}\{"$schema":"http://json\-schema\.org/draft\-07/schema\#", "properties":map\[string\]interface \{\}\{"open\_ports":\... | +| Streaming Person Information JSON Streaming | ✅ Pass | 0.747s | | -**Summary**: 5/5 (100.00%) successful tests +**Summary**: 4/5 (80.00%) successful tests -**Average latency**: 7.088s +**Average latency**: 0.945s --- @@ -90,38 +90,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 5.300s | | -| Text Transform Uppercase | ✅ Pass | 3.870s | | -| Math Calculation | ✅ Pass | 2.999s | | -| Count from 1 to 5 | ✅ Pass | 12.409s | | -| Basic Echo Function | ✅ Pass | 3.121s | | -| Streaming Simple Math Streaming | ✅ Pass | 4.737s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 4.527s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 4.412s | | +| Simple Math | ✅ Pass | 5.447s | | +| Text Transform Uppercase | ✅ Pass | 5.747s | | +| Count from 1 to 5 | ✅ Pass | 6.848s | | +| Math Calculation | ✅ Pass | 3.912s | | +| Basic Echo Function | ✅ Pass | 2.791s | | +| Streaming Simple Math Streaming | ✅ Pass | 4.355s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 5.205s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 2.995s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 2.506s | | -| Search Query Function | ✅ Pass | 2.580s | | -| Ask Advice Function | ✅ Pass | 3.013s | | -| Streaming Search Query Function Streaming | ✅ Pass | 2.157s | | -| Basic Context Memory Test | ✅ Pass | 4.461s | | -| Function Argument Memory Test | ✅ Pass | 4.159s | | -| Function Response Memory Test | ✅ Pass | 6.988s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 5.212s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 3.572s | | -| Penetration Testing Methodology | ✅ Pass | 11.000s | | -| Vulnerability Assessment Tools | ✅ Pass | 11.996s | | -| SQL Injection Attack Type | ✅ Pass | 5.396s | | -| Penetration Testing Framework | ✅ Pass | 11.164s | | -| Web Application Security Scanner | ✅ Pass | 4.543s | | -| Penetration Testing Tool Selection | ✅ Pass | 3.287s | | +| JSON Response Function | ✅ Pass | 4.066s | | +| Search Query Function | ✅ Pass | 2.232s | | +| Ask Advice Function | ✅ Pass | 2.860s | | +| Streaming Search Query Function Streaming | ✅ Pass | 2.094s | | +| Basic Context Memory Test | ✅ Pass | 4.240s | | +| Function Argument Memory Test | ✅ Pass | 2.635s | | +| Function Response Memory Test | ✅ Pass | 9.775s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 7.318s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 4.524s | | +| Penetration Testing Methodology | ✅ Pass | 13.685s | | +| Vulnerability Assessment Tools | ✅ Pass | 12.372s | | +| SQL Injection Attack Type | ✅ Pass | 11.677s | | +| Penetration Testing Framework | ✅ Pass | 12.500s | | +| Web Application Security Scanner | ✅ Pass | 9.014s | | +| Penetration Testing Tool Selection | ✅ Pass | 3.509s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 5.366s +**Average latency**: 6.079s --- @@ -131,38 +131,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 5.339s | | -| Text Transform Uppercase | ✅ Pass | 5.104s | | -| Count from 1 to 5 | ✅ Pass | 5.229s | | -| Math Calculation | ✅ Pass | 4.509s | | -| Basic Echo Function | ✅ Pass | 3.068s | | -| Streaming Simple Math Streaming | ✅ Pass | 4.267s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 4.656s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 2.860s | | +| Simple Math | ✅ Pass | 4.896s | | +| Text Transform Uppercase | ✅ Pass | 4.750s | | +| Count from 1 to 5 | ✅ Pass | 5.467s | | +| Math Calculation | ✅ Pass | 3.192s | | +| Basic Echo Function | ✅ Pass | 2.627s | | +| Streaming Simple Math Streaming | ✅ Pass | 3.657s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 4.401s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 5.018s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 3.200s | | -| Search Query Function | ✅ Pass | 1.780s | | -| Ask Advice Function | ✅ Pass | 2.841s | | -| Streaming Search Query Function Streaming | ✅ Pass | 2.020s | | -| Basic Context Memory Test | ✅ Pass | 5.116s | | -| Function Argument Memory Test | ✅ Pass | 3.908s | | -| Function Response Memory Test | ✅ Pass | 4.534s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 8.970s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 7.041s | | -| Penetration Testing Methodology | ✅ Pass | 11.914s | | -| Vulnerability Assessment Tools | ✅ Pass | 17.492s | | -| SQL Injection Attack Type | ✅ Pass | 5.510s | | -| Penetration Testing Framework | ✅ Pass | 9.591s | | -| Penetration Testing Tool Selection | ✅ Pass | 2.796s | | -| Web Application Security Scanner | ✅ Pass | 10.669s | | +| JSON Response Function | ✅ Pass | 2.385s | | +| Search Query Function | ✅ Pass | 2.864s | | +| Ask Advice Function | ✅ Pass | 3.599s | | +| Streaming Search Query Function Streaming | ✅ Pass | 1.866s | | +| Basic Context Memory Test | ✅ Pass | 4.909s | | +| Function Argument Memory Test | ✅ Pass | 3.381s | | +| Function Response Memory Test | ✅ Pass | 4.146s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 5.778s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 5.842s | | +| Penetration Testing Methodology | ✅ Pass | 9.568s | | +| SQL Injection Attack Type | ✅ Pass | 6.860s | | +| Vulnerability Assessment Tools | ✅ Pass | 18.097s | | +| Penetration Testing Framework | ✅ Pass | 10.065s | | +| Web Application Security Scanner | ✅ Pass | 9.724s | | +| Penetration Testing Tool Selection | ✅ Pass | 3.665s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 5.758s +**Average latency**: 5.512s --- @@ -172,38 +172,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 3.289s | | -| Text Transform Uppercase | ✅ Pass | 2.103s | | -| Count from 1 to 5 | ✅ Pass | 4.641s | | -| Math Calculation | ✅ Pass | 1.319s | | -| Basic Echo Function | ✅ Pass | 1.852s | | -| Streaming Simple Math Streaming | ✅ Pass | 1.998s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 3.591s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 1.928s | | +| Simple Math | ✅ Pass | 5.569s | | +| Text Transform Uppercase | ✅ Pass | 4.279s | | +| Math Calculation | ✅ Pass | 2.508s | | +| Basic Echo Function | ✅ Pass | 2.450s | | +| Count from 1 to 5 | ✅ Pass | 13.152s | | +| Streaming Simple Math Streaming | ✅ Pass | 3.691s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 4.566s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 2.392s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 1.388s | | -| Search Query Function | ✅ Pass | 2.131s | | -| Ask Advice Function | ✅ Pass | 1.544s | | -| Streaming Search Query Function Streaming | ✅ Pass | 1.977s | | -| Basic Context Memory Test | ✅ Pass | 4.750s | | -| Function Argument Memory Test | ✅ Pass | 3.913s | | -| Function Response Memory Test | ✅ Pass | 4.594s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 3.141s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 3.417s | | -| Penetration Testing Methodology | ✅ Pass | 3.566s | | -| Vulnerability Assessment Tools | ✅ Pass | 15.497s | | -| SQL Injection Attack Type | ✅ Pass | 4.163s | | -| Penetration Testing Framework | ✅ Pass | 2.677s | | -| Web Application Security Scanner | ✅ Pass | 4.448s | | -| Penetration Testing Tool Selection | ✅ Pass | 1.928s | | +| JSON Response Function | ✅ Pass | 2.320s | | +| Search Query Function | ✅ Pass | 3.027s | | +| Ask Advice Function | ✅ Pass | 4.213s | | +| Streaming Search Query Function Streaming | ✅ Pass | 2.036s | | +| Basic Context Memory Test | ✅ Pass | 7.051s | | +| Function Argument Memory Test | ✅ Pass | 3.966s | | +| Function Response Memory Test | ✅ Pass | 7.543s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 3.481s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 4.203s | | +| Penetration Testing Methodology | ✅ Pass | 6.768s | | +| SQL Injection Attack Type | ✅ Pass | 4.673s | | +| Vulnerability Assessment Tools | ✅ Pass | 18.743s | | +| Penetration Testing Framework | ✅ Pass | 5.278s | | +| Web Application Security Scanner | ✅ Pass | 3.018s | | +| Penetration Testing Tool Selection | ✅ Pass | 4.024s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 3.473s +**Average latency**: 5.172s --- @@ -213,38 +213,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 4.088s | | -| Text Transform Uppercase | ✅ Pass | 3.518s | | -| Count from 1 to 5 | ✅ Pass | 4.139s | | -| Math Calculation | ✅ Pass | 1.941s | | -| Basic Echo Function | ✅ Pass | 1.601s | | -| Streaming Simple Math Streaming | ✅ Pass | 2.624s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 3.881s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 2.028s | | +| Simple Math | ✅ Pass | 4.724s | | +| Text Transform Uppercase | ✅ Pass | 4.732s | | +| Count from 1 to 5 | ✅ Pass | 8.230s | | +| Math Calculation | ✅ Pass | 2.684s | | +| Basic Echo Function | ✅ Pass | 2.505s | | +| Streaming Simple Math Streaming | ✅ Pass | 5.229s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 6.093s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 1.982s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 2.901s | | -| Search Query Function | ✅ Pass | 2.251s | | -| Ask Advice Function | ✅ Pass | 1.898s | | -| Streaming Search Query Function Streaming | ✅ Pass | 2.260s | | -| Basic Context Memory Test | ✅ Pass | 2.202s | | -| Function Argument Memory Test | ✅ Pass | 2.319s | | -| Function Response Memory Test | ✅ Pass | 4.750s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 2.590s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 3.847s | | -| Penetration Testing Methodology | ✅ Pass | 4.130s | | -| Vulnerability Assessment Tools | ✅ Pass | 12.315s | | -| SQL Injection Attack Type | ✅ Pass | 4.225s | | -| Penetration Testing Framework | ✅ Pass | 2.234s | | -| Web Application Security Scanner | ✅ Pass | 2.434s | | -| Penetration Testing Tool Selection | ✅ Pass | 2.917s | | +| JSON Response Function | ✅ Pass | 2.442s | | +| Search Query Function | ✅ Pass | 2.913s | | +| Ask Advice Function | ✅ Pass | 3.594s | | +| Streaming Search Query Function Streaming | ✅ Pass | 3.382s | | +| Basic Context Memory Test | ✅ Pass | 4.152s | | +| Function Argument Memory Test | ✅ Pass | 3.718s | | +| Function Response Memory Test | ✅ Pass | 5.162s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 4.590s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 4.049s | | +| Penetration Testing Methodology | ✅ Pass | 5.504s | | +| SQL Injection Attack Type | ✅ Pass | 5.041s | | +| Vulnerability Assessment Tools | ✅ Pass | 20.343s | | +| Penetration Testing Framework | ✅ Pass | 10.747s | | +| Web Application Security Scanner | ✅ Pass | 10.091s | | +| Penetration Testing Tool Selection | ✅ Pass | 3.551s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 3.352s +**Average latency**: 5.455s --- @@ -254,38 +254,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 3.094s | | -| Text Transform Uppercase | ✅ Pass | 3.196s | | -| Count from 1 to 5 | ✅ Pass | 3.210s | | -| Math Calculation | ✅ Pass | 2.542s | | -| Basic Echo Function | ✅ Pass | 1.431s | | -| Streaming Simple Math Streaming | ✅ Pass | 2.476s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 2.746s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 1.526s | | +| Simple Math | ✅ Pass | 3.761s | | +| Text Transform Uppercase | ✅ Pass | 6.663s | | +| Count from 1 to 5 | ✅ Pass | 8.046s | | +| Math Calculation | ✅ Pass | 2.987s | | +| Basic Echo Function | ✅ Pass | 2.306s | | +| Streaming Simple Math Streaming | ✅ Pass | 3.074s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 2.033s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 7.517s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 2.530s | | -| Search Query Function | ✅ Pass | 1.782s | | -| Ask Advice Function | ✅ Pass | 1.862s | | -| Streaming Search Query Function Streaming | ✅ Pass | 1.915s | | -| Basic Context Memory Test | ✅ Pass | 3.090s | | -| Function Argument Memory Test | ❌ Fail | 3.063s | expected text 'Go programming language' not found | -| Function Response Memory Test | ✅ Pass | 4.037s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 2.505s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 3.618s | | -| Penetration Testing Methodology | ✅ Pass | 2.493s | | -| Vulnerability Assessment Tools | ✅ Pass | 6.921s | | -| SQL Injection Attack Type | ✅ Pass | 3.418s | | -| Penetration Testing Framework | ✅ Pass | 4.994s | | -| Web Application Security Scanner | ✅ Pass | 1.890s | | -| Penetration Testing Tool Selection | ✅ Pass | 3.285s | | +| JSON Response Function | ✅ Pass | 1.833s | | +| Search Query Function | ✅ Pass | 2.622s | | +| Ask Advice Function | ✅ Pass | 3.735s | | +| Streaming Search Query Function Streaming | ✅ Pass | 1.859s | | +| Basic Context Memory Test | ✅ Pass | 4.274s | | +| Function Argument Memory Test | ✅ Pass | 5.488s | | +| Function Response Memory Test | ✅ Pass | 7.424s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 2.711s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 4.780s | | +| Penetration Testing Methodology | ✅ Pass | 6.058s | | +| Vulnerability Assessment Tools | ✅ Pass | 13.545s | | +| SQL Injection Attack Type | ✅ Pass | 3.451s | | +| Penetration Testing Framework | ✅ Pass | 5.348s | | +| Web Application Security Scanner | ✅ Pass | 6.648s | | +| Penetration Testing Tool Selection | ✅ Pass | 3.077s | | -**Summary**: 22/23 (95.65%) successful tests +**Summary**: 23/23 (100.00%) successful tests -**Average latency**: 2.941s +**Average latency**: 4.750s --- @@ -295,38 +295,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 3.446s | | -| Text Transform Uppercase | ✅ Pass | 2.472s | | -| Count from 1 to 5 | ✅ Pass | 3.109s | | -| Math Calculation | ✅ Pass | 2.244s | | -| Basic Echo Function | ✅ Pass | 1.191s | | -| Streaming Simple Math Streaming | ✅ Pass | 2.377s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 2.817s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 0.952s | | +| Simple Math | ✅ Pass | 1.664s | | +| Text Transform Uppercase | ✅ Pass | 0.999s | | +| Count from 1 to 5 | ✅ Pass | 0.706s | | +| Math Calculation | ✅ Pass | 0.808s | | +| Basic Echo Function | ✅ Pass | 1.256s | | +| Streaming Simple Math Streaming | ✅ Pass | 0.597s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.636s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 1.226s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 1.376s | | -| Search Query Function | ✅ Pass | 1.034s | | -| Ask Advice Function | ✅ Pass | 1.177s | | -| Streaming Search Query Function Streaming | ✅ Pass | 1.399s | | -| Basic Context Memory Test | ✅ Pass | 2.150s | | -| Function Argument Memory Test | ✅ Pass | 0.884s | | -| Function Response Memory Test | ✅ Pass | 0.900s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 2.927s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 1.201s | | -| Penetration Testing Methodology | ✅ Pass | 8.294s | | -| SQL Injection Attack Type | ✅ Pass | 2.431s | | -| Vulnerability Assessment Tools | ✅ Pass | 24.680s | | -| Penetration Testing Framework | ✅ Pass | 4.850s | | -| Web Application Security Scanner | ✅ Pass | 4.195s | | -| Penetration Testing Tool Selection | ✅ Pass | 1.546s | | +| JSON Response Function | ✅ Pass | 0.959s | | +| Search Query Function | ✅ Pass | 1.138s | | +| Ask Advice Function | ✅ Pass | 1.422s | | +| Streaming Search Query Function Streaming | ✅ Pass | 1.120s | | +| Basic Context Memory Test | ✅ Pass | 0.691s | | +| Function Argument Memory Test | ✅ Pass | 0.528s | | +| Function Response Memory Test | ✅ Pass | 0.553s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 1.283s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 1.122s | | +| Penetration Testing Methodology | ✅ Pass | 2.639s | | +| Vulnerability Assessment Tools | ✅ Pass | 2.019s | | +| SQL Injection Attack Type | ✅ Pass | 1.036s | | +| Penetration Testing Framework | ✅ Pass | 1.655s | | +| Web Application Security Scanner | ✅ Pass | 3.147s | | +| Penetration Testing Tool Selection | ✅ Pass | 0.902s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 3.377s +**Average latency**: 1.222s --- @@ -336,38 +336,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 3.959s | | -| Text Transform Uppercase | ✅ Pass | 1.535s | | -| Count from 1 to 5 | ✅ Pass | 3.085s | | -| Math Calculation | ✅ Pass | 1.883s | | -| Basic Echo Function | ✅ Pass | 1.491s | | -| Streaming Simple Math Streaming | ✅ Pass | 1.364s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.694s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 1.338s | | +| Simple Math | ✅ Pass | 1.541s | | +| Text Transform Uppercase | ✅ Pass | 0.541s | | +| Count from 1 to 5 | ✅ Pass | 0.660s | | +| Math Calculation | ✅ Pass | 0.556s | | +| Basic Echo Function | ✅ Pass | 0.701s | | +| Streaming Simple Math Streaming | ✅ Pass | 0.537s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.012s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 0.886s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 1.277s | | -| Search Query Function | ✅ Pass | 1.249s | | -| Ask Advice Function | ✅ Pass | 1.653s | | -| Streaming Search Query Function Streaming | ✅ Pass | 0.925s | | -| Basic Context Memory Test | ✅ Pass | 3.426s | | -| Function Argument Memory Test | ✅ Pass | 1.552s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 2.090s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 1.792s | | -| Function Response Memory Test | ✅ Pass | 22.405s | | -| Penetration Testing Methodology | ✅ Pass | 6.872s | | -| SQL Injection Attack Type | ✅ Pass | 2.512s | | -| Vulnerability Assessment Tools | ✅ Pass | 19.206s | | -| Penetration Testing Framework | ✅ Pass | 4.480s | | -| Web Application Security Scanner | ✅ Pass | 4.976s | | -| Penetration Testing Tool Selection | ✅ Pass | 1.793s | | +| JSON Response Function | ✅ Pass | 0.744s | | +| Search Query Function | ✅ Pass | 1.350s | | +| Ask Advice Function | ✅ Pass | 1.986s | | +| Streaming Search Query Function Streaming | ✅ Pass | 0.726s | | +| Basic Context Memory Test | ✅ Pass | 1.089s | | +| Function Argument Memory Test | ✅ Pass | 0.558s | | +| Function Response Memory Test | ✅ Pass | 0.620s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 1.284s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 0.607s | | +| Penetration Testing Methodology | ✅ Pass | 2.167s | | +| Vulnerability Assessment Tools | ✅ Pass | 1.673s | | +| SQL Injection Attack Type | ✅ Pass | 1.089s | | +| Penetration Testing Framework | ✅ Pass | 1.859s | | +| Web Application Security Scanner | ✅ Pass | 1.590s | | +| Penetration Testing Tool Selection | ✅ Pass | 1.127s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 4.025s +**Average latency**: 1.083s --- @@ -377,38 +377,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 1.626s | | -| Text Transform Uppercase | ✅ Pass | 2.623s | | -| Count from 1 to 5 | ✅ Pass | 2.794s | | -| Math Calculation | ✅ Pass | 1.657s | | -| Basic Echo Function | ✅ Pass | 1.406s | | -| Streaming Simple Math Streaming | ✅ Pass | 2.086s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 2.390s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 1.279s | | +| Simple Math | ✅ Pass | 0.582s | | +| Text Transform Uppercase | ✅ Pass | 1.107s | | +| Count from 1 to 5 | ✅ Pass | 0.693s | | +| Math Calculation | ✅ Pass | 0.516s | | +| Basic Echo Function | ✅ Pass | 0.700s | | +| Streaming Simple Math Streaming | ✅ Pass | 0.523s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.544s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 0.772s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 1.314s | | -| Search Query Function | ✅ Pass | 1.160s | | -| Ask Advice Function | ✅ Pass | 1.645s | | -| Streaming Search Query Function Streaming | ✅ Pass | 0.948s | | -| Basic Context Memory Test | ✅ Pass | 3.003s | | -| Function Argument Memory Test | ✅ Pass | 2.254s | | -| Function Response Memory Test | ✅ Pass | 4.521s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 2.225s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 1.494s | | -| Penetration Testing Methodology | ✅ Pass | 5.008s | | -| Vulnerability Assessment Tools | ✅ Pass | 11.717s | | -| SQL Injection Attack Type | ✅ Pass | 4.587s | | -| Penetration Testing Framework | ✅ Pass | 4.199s | | -| Web Application Security Scanner | ✅ Pass | 4.499s | | -| Penetration Testing Tool Selection | ✅ Pass | 1.261s | | +| JSON Response Function | ✅ Pass | 0.830s | | +| Search Query Function | ✅ Pass | 1.114s | | +| Ask Advice Function | ✅ Pass | 0.989s | | +| Streaming Search Query Function Streaming | ✅ Pass | 0.729s | | +| Basic Context Memory Test | ✅ Pass | 0.571s | | +| Function Argument Memory Test | ✅ Pass | 0.820s | | +| Function Response Memory Test | ✅ Pass | 0.683s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 1.762s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 1.029s | | +| Penetration Testing Methodology | ✅ Pass | 2.050s | | +| Vulnerability Assessment Tools | ✅ Pass | 1.990s | | +| SQL Injection Attack Type | ✅ Pass | 0.651s | | +| Penetration Testing Framework | ✅ Pass | 1.320s | | +| Web Application Security Scanner | ✅ Pass | 1.317s | | +| Penetration Testing Tool Selection | ✅ Pass | 1.060s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 2.857s +**Average latency**: 0.972s --- @@ -418,38 +418,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 0.873s | | -| Text Transform Uppercase | ✅ Pass | 0.824s | | -| Count from 1 to 5 | ✅ Pass | 0.953s | | -| Math Calculation | ✅ Pass | 0.842s | | -| Basic Echo Function | ✅ Pass | 1.514s | | -| Streaming Simple Math Streaming | ✅ Pass | 1.386s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.346s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 1.009s | | +| Simple Math | ✅ Pass | 1.889s | | +| Text Transform Uppercase | ✅ Pass | 1.323s | | +| Count from 1 to 5 | ✅ Pass | 0.900s | | +| Math Calculation | ✅ Pass | 1.026s | | +| Basic Echo Function | ✅ Pass | 1.016s | | +| Streaming Simple Math Streaming | ✅ Pass | 1.920s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.298s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 0.987s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 1.687s | | -| Search Query Function | ✅ Pass | 0.994s | | -| Ask Advice Function | ✅ Pass | 1.286s | | -| Streaming Search Query Function Streaming | ✅ Pass | 1.041s | | -| Basic Context Memory Test | ✅ Pass | 0.905s | | -| Function Argument Memory Test | ✅ Pass | 0.845s | | -| Function Response Memory Test | ✅ Pass | 0.806s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 2.240s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 0.862s | | -| Penetration Testing Methodology | ✅ Pass | 4.261s | | -| Vulnerability Assessment Tools | ✅ Pass | 3.398s | | -| SQL Injection Attack Type | ✅ Pass | 0.869s | | -| Penetration Testing Framework | ✅ Pass | 3.691s | | -| Web Application Security Scanner | ✅ Pass | 2.796s | | -| Penetration Testing Tool Selection | ✅ Pass | 1.349s | | +| JSON Response Function | ✅ Pass | 1.585s | | +| Search Query Function | ✅ Pass | 1.567s | | +| Ask Advice Function | ✅ Pass | 1.272s | | +| Streaming Search Query Function Streaming | ✅ Pass | 0.972s | | +| Basic Context Memory Test | ✅ Pass | 1.434s | | +| Function Argument Memory Test | ✅ Pass | 0.764s | | +| Function Response Memory Test | ✅ Pass | 1.068s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 1.771s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 0.781s | | +| Penetration Testing Methodology | ✅ Pass | 3.191s | | +| Vulnerability Assessment Tools | ✅ Pass | 3.556s | | +| SQL Injection Attack Type | ✅ Pass | 0.965s | | +| Penetration Testing Framework | ✅ Pass | 5.216s | | +| Web Application Security Scanner | ✅ Pass | 3.193s | | +| Penetration Testing Tool Selection | ✅ Pass | 1.441s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 1.556s +**Average latency**: 1.702s --- @@ -459,38 +459,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 1.007s | | -| Text Transform Uppercase | ✅ Pass | 0.566s | | -| Count from 1 to 5 | ✅ Pass | 1.100s | | -| Math Calculation | ✅ Pass | 1.011s | | -| Basic Echo Function | ❌ Fail | 0.727s | no tool calls found, expected at least 1 | -| Streaming Simple Math Streaming | ✅ Pass | 0.542s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.560s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 0.774s | | +| Simple Math | ✅ Pass | 0.558s | | +| Text Transform Uppercase | ✅ Pass | 0.527s | | +| Count from 1 to 5 | ✅ Pass | 0.651s | | +| Math Calculation | ✅ Pass | 0.965s | | +| Basic Echo Function | ✅ Pass | 1.248s | | +| Streaming Simple Math Streaming | ✅ Pass | 0.919s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.591s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 0.761s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 0.830s | | -| Search Query Function | ❌ Fail | 1.222s | no tool calls found, expected at least 1 | -| Ask Advice Function | ✅ Pass | 0.877s | | -| Streaming Search Query Function Streaming | ❌ Fail | 1.146s | no tool calls found, expected at least 1 | -| Basic Context Memory Test | ✅ Pass | 0.973s | | -| Function Argument Memory Test | ✅ Pass | 0.613s | | -| Function Response Memory Test | ✅ Pass | 0.583s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 1.826s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 0.625s | | -| Penetration Testing Methodology | ✅ Pass | 1.940s | | -| Vulnerability Assessment Tools | ✅ Pass | 3.151s | | -| SQL Injection Attack Type | ✅ Pass | 0.588s | | -| Penetration Testing Framework | ✅ Pass | 1.175s | | -| Web Application Security Scanner | ✅ Pass | 1.550s | | -| Penetration Testing Tool Selection | ✅ Pass | 0.973s | | +| JSON Response Function | ✅ Pass | 0.869s | | +| Search Query Function | ✅ Pass | 0.856s | | +| Ask Advice Function | ✅ Pass | 1.283s | | +| Streaming Search Query Function Streaming | ✅ Pass | 1.259s | | +| Basic Context Memory Test | ✅ Pass | 0.981s | | +| Function Argument Memory Test | ✅ Pass | 0.649s | | +| Function Response Memory Test | ✅ Pass | 1.007s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 1.940s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 1.070s | | +| Penetration Testing Methodology | ✅ Pass | 2.822s | | +| Vulnerability Assessment Tools | ✅ Pass | 2.937s | | +| SQL Injection Attack Type | ✅ Pass | 0.620s | | +| Penetration Testing Framework | ✅ Pass | 1.331s | | +| Web Application Security Scanner | ✅ Pass | 1.018s | | +| Penetration Testing Tool Selection | ✅ Pass | 0.972s | | -**Summary**: 20/23 (86.96%) successful tests +**Summary**: 23/23 (100.00%) successful tests -**Average latency**: 1.060s +**Average latency**: 1.124s --- @@ -500,38 +500,38 @@ Generated: Wed, 27 May 2026 23:05:00 UTC | Test | Result | Latency | Error | |------|--------|---------|-------| -| Simple Math | ✅ Pass | 4.527s | | -| Text Transform Uppercase | ✅ Pass | 4.599s | | -| Count from 1 to 5 | ✅ Pass | 5.743s | | -| Math Calculation | ✅ Pass | 3.509s | | -| Basic Echo Function | ✅ Pass | 4.851s | | -| Streaming Simple Math Streaming | ✅ Pass | 3.707s | | -| Streaming Count from 1 to 3 Streaming | ✅ Pass | 4.781s | | -| Streaming Basic Echo Function Streaming | ✅ Pass | 5.300s | | +| Simple Math | ✅ Pass | 3.761s | | +| Text Transform Uppercase | ✅ Pass | 4.980s | | +| Count from 1 to 5 | ✅ Pass | 6.066s | | +| Math Calculation | ✅ Pass | 5.125s | | +| Basic Echo Function | ✅ Pass | 4.145s | | +| Streaming Simple Math Streaming | ✅ Pass | 4.829s | | +| Streaming Count from 1 to 3 Streaming | ✅ Pass | 5.837s | | +| Streaming Basic Echo Function Streaming | ✅ Pass | 3.264s | | #### Advanced Tests | Test | Result | Latency | Error | |------|--------|---------|-------| -| JSON Response Function | ✅ Pass | 2.456s | | -| Search Query Function | ✅ Pass | 3.989s | | -| Ask Advice Function | ✅ Pass | 3.255s | | -| Streaming Search Query Function Streaming | ✅ Pass | 2.430s | | -| Basic Context Memory Test | ✅ Pass | 4.780s | | -| Function Argument Memory Test | ✅ Pass | 5.338s | | -| Function Response Memory Test | ✅ Pass | 2.911s | | -| Penetration Testing Memory with Tool Call | ✅ Pass | 5.094s | | -| Cybersecurity Workflow Memory Test | ✅ Pass | 6.163s | | -| Penetration Testing Methodology | ✅ Pass | 12.475s | | -| Vulnerability Assessment Tools | ✅ Pass | 11.406s | | -| SQL Injection Attack Type | ✅ Pass | 6.216s | | -| Penetration Testing Framework | ✅ Pass | 11.490s | | -| Web Application Security Scanner | ✅ Pass | 8.229s | | -| Penetration Testing Tool Selection | ✅ Pass | 3.336s | | +| JSON Response Function | ✅ Pass | 2.894s | | +| Search Query Function | ✅ Pass | 3.922s | | +| Ask Advice Function | ✅ Pass | 3.311s | | +| Streaming Search Query Function Streaming | ✅ Pass | 2.728s | | +| Basic Context Memory Test | ✅ Pass | 4.075s | | +| Function Argument Memory Test | ✅ Pass | 5.545s | | +| Function Response Memory Test | ✅ Pass | 10.448s | | +| Penetration Testing Memory with Tool Call | ✅ Pass | 5.993s | | +| Cybersecurity Workflow Memory Test | ✅ Pass | 3.695s | | +| Penetration Testing Methodology | ✅ Pass | 9.881s | | +| Vulnerability Assessment Tools | ✅ Pass | 10.935s | | +| Penetration Testing Framework | ✅ Pass | 12.705s | | +| Web Application Security Scanner | ✅ Pass | 8.109s | | +| Penetration Testing Tool Selection | ✅ Pass | 2.886s | | +| SQL Injection Attack Type | ✅ Pass | 86.622s | | **Summary**: 23/23 (100.00%) successful tests -**Average latency**: 5.504s +**Average latency**: 9.207s ---