feat(provider): add Ollama Cloud configuration with multi-model support

- Add pre-built ollama-cloud.provider.yml with 7 cloud models for different agent types. - Include configuration file in Docker image (/opt/pentagi/conf/ollama-cloud.provider.yml). - Update README with Free Tier and Paid Tier Ollama Cloud setup instructions. - Document model assignments: nemotron-3-super, qwen3-coder-next, glm-5, minimax-m2.7, qwen3.5:397b, devstral-2:123b
2026-07-21 08:15:23 -04:00 · 2026-03-23 19:37:24 +03:00
parent 260a26cfd4
commit 3ce09b9832
5 changed files with 527 additions and 414 deletions
@@ -67,6 +67,7 @@
                // "-type", "qwen",
                "-config", "${workspaceFolder}/examples/configs/moonshot.provider.yml",
                // "-config", "${workspaceFolder}/examples/configs/deepseek.provider.yml",
+                // "-config", "${workspaceFolder}/examples/configs/ollama-cloud.provider.yml",
                // "-config", "${workspaceFolder}/examples/configs/ollama-llama318b.provider.yml",
                // "-config", "${workspaceFolder}/examples/configs/ollama-llama318b-instruct.provider.yml",
                // "-config", "${workspaceFolder}/examples/configs/ollama-qwq32b-fp16-tc.provider.yml",
@@ -132,6 +132,7 @@ COPY examples/configs/custom-openai.provider.yml /opt/pentagi/conf/
 COPY examples/configs/deepinfra.provider.yml /opt/pentagi/conf/
 COPY examples/configs/deepseek.provider.yml /opt/pentagi/conf/
 COPY examples/configs/moonshot.provider.yml /opt/pentagi/conf/
+COPY examples/configs/ollama-cloud.provider.yml /opt/pentagi/conf/
 COPY examples/configs/ollama-llama318b-instruct.provider.yml /opt/pentagi/conf/
 COPY examples/configs/ollama-llama318b.provider.yml /opt/pentagi/conf/
 COPY examples/configs/ollama-qwen332b-fp16-tc.provider.yml /opt/pentagi/conf/
@@ -1280,9 +1280,29 @@ OLLAMA_SERVER_API_KEY=your_ollama_cloud_api_key
 OLLAMA_SERVER_MODEL=gpt-oss:120b  # Example: OpenAI OSS 120B model
 ```

-**Paid Tier Setup (Multi-Model with Custom Configuration)**
+**Paid Tier Setup (Multi-Model with Pre-built Configuration)**

-For paid tiers supporting multiple concurrent models, use custom agent configuration:
+For paid tiers supporting multiple concurrent models, use the pre-built Ollama Cloud configuration:
+
+```bash
+# Using pre-built Ollama Cloud configuration (included in Docker image)
+OLLAMA_SERVER_URL=https://ollama.com
+OLLAMA_SERVER_API_KEY=your_ollama_cloud_api_key
+OLLAMA_SERVER_CONFIG_PATH=/opt/pentagi/conf/ollama-cloud.provider.yml
+```
+
+The pre-built `ollama-cloud.provider.yml` configuration includes optimized model assignments for all agent types:
+- **Simple/Assistant**: `nemotron-3-super:cloud` - Fast general-purpose model
+- **Primary Agent**: `qwen3-coder-next:cloud` - Advanced reasoning with high effort mode
+- **Coder/Pentester**: `qwen3-coder-next:cloud` - Specialized coding models
+- **Searcher**: `qwen3.5:397b-cloud` - Large context for information gathering
+- **Refiner/Refactor**: `glm-5:cloud` - High-quality text refinement
+- **Adviser/Enricher**: `minimax-m2.7:cloud` - Efficient advisory tasks
+- **Installer**: `devstral-2:123b-cloud` - Installation and setup tasks
+
+**Custom Configuration (Advanced)**
+
+To create your own agent configuration, mount a custom file from your host filesystem:

 ```bash
 # Using custom provider configuration
@@ -1294,20 +1314,18 @@ OLLAMA_SERVER_CONFIG_PATH=/opt/pentagi/conf/ollama.provider.yml
 PENTAGI_OLLAMA_SERVER_CONFIG_PATH=/path/on/host/my-ollama-config.yml
 ```

-The `PENTAGI_OLLAMA_SERVER_CONFIG_PATH` environment variable maps your host configuration file to `/opt/pentagi/conf/ollama.provider.yml` inside the container. Create a custom configuration file defining models for each agent type (simple, primary_agent, coder, etc.) and reference it using this variable.
+The `PENTAGI_OLLAMA_SERVER_CONFIG_PATH` environment variable maps your host configuration file to `/opt/pentagi/conf/ollama.provider.yml` inside the container.

 **Example custom configuration** (`my-ollama-config.yml`):

 ```yaml
-simple:
-  model: "llama3.1:8b-instruct-q8_0"
-  temperature: 0.6
-  max_tokens: 4096
-
 primary_agent:
-  model: "gpt-oss:120b"
+  model: "qwen3-coder-next:cloud"
  temperature: 1.0
-  max_tokens: 16384
+  top_p: 0.9
+  max_tokens: 32768
+  reasoning:
+    effort: high

 coder:
  model: "qwen3-coder:32b"
@@ -0,0 +1,93 @@
+simple:
+  model: "nemotron-3-super:cloud"
+  temperature: 1
+  top_p: 0.9
+  n: 1
+  max_tokens: 65536
+
+simple_json:
+  model: "nemotron-3-super:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 65536
+  json: true
+
+primary_agent:
+  model: "qwen3-coder-next:cloud"
+  temperature: 1
+  top_p: 0.9
+  n: 1
+  max_tokens: 32768
+  reasoning:
+    effort: high
+
+assistant:
+  model: "nemotron-3-super:cloud"
+  temperature: 1
+  top_p: 0.9
+  n: 1
+  max_tokens: 65536
+
+generator:
+  model: "qwen3-coder-next:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 32768
+
+refiner:
+  model: "glm-5:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 65536
+
+adviser:
+  model: "minimax-m2.7:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 65536
+
+reflector:
+  model: "glm-5:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 65536
+
+searcher:
+  model: "qwen3.5:397b-cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 65536
+
+enricher:
+  model: "minimax-m2.7:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 65536
+
+coder:
+  model: "qwen3-coder-next:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 32768
+
+installer:
+  model: "devstral-2:123b-cloud"
+  temperature: 1
+  top_p: 0.9
+  n: 1
+  max_tokens: 65536
+
+pentester:
+  model: "qwen3-coder-next:cloud"
+  temperature: 1
+  top_p: 0.95
+  n: 1
+  max_tokens: 32768
@@ -1,537 +1,537 @@
 # LLM Agent Testing Report

-Generated: Thu, 05 Mar 2026 18:12:24 UTC
+Generated: Mon, 23 Mar 2026 16:29:35 UTC

 ## Overall Results

 | Agent | Model | Reasoning | Success Rate | Average Latency |
 |-------|-------|-----------|--------------|-----------------|
-| simple | gpt-oss:120b | false | 23/23 (100.00%) | 1.398s |
-| simple_json | gpt-oss:120b | false | 5/5 (100.00%) | 1.451s |
-| primary_agent | gpt-oss:120b | false | 22/23 (95.65%) | 1.343s |
-| assistant | gpt-oss:120b | false | 23/23 (100.00%) | 1.369s |
-| generator | gpt-oss:120b | false | 22/23 (95.65%) | 1.339s |
-| refiner | gpt-oss:120b | false | 23/23 (100.00%) | 1.285s |
-| adviser | gpt-oss:120b | false | 23/23 (100.00%) | 1.240s |
-| reflector | gpt-oss:120b | false | 23/23 (100.00%) | 1.229s |
-| searcher | gpt-oss:120b | false | 22/23 (95.65%) | 1.180s |
-| enricher | gpt-oss:120b | false | 22/23 (95.65%) | 1.281s |
-| coder | gpt-oss:120b | false | 23/23 (100.00%) | 1.218s |
-| installer | gpt-oss:120b | false | 23/23 (100.00%) | 1.260s |
-| pentester | gpt-oss:120b | false | 22/23 (95.65%) | 1.203s |
+| simple | nemotron-3-super:cloud | false | 22/23 (95.65%) | 22.627s |
+| simple_json | nemotron-3-super:cloud | false | 5/5 (100.00%) | 27.380s |
+| primary_agent | qwen3-coder-next:cloud | false | 23/23 (100.00%) | 4.101s |
+| assistant | nemotron-3-super:cloud | false | 23/23 (100.00%) | 22.773s |
+| generator | qwen3-coder-next:cloud | false | 23/23 (100.00%) | 2.348s |
+| refiner | glm-5:cloud | false | 23/23 (100.00%) | 7.964s |
+| adviser | minimax-m2.7:cloud | false | 23/23 (100.00%) | 3.990s |
+| reflector | glm-5:cloud | false | 23/23 (100.00%) | 9.201s |
+| searcher | qwen3.5:397b-cloud | false | 20/23 (86.96%) | 46.174s |
+| enricher | minimax-m2.7:cloud | false | 23/23 (100.00%) | 6.153s |
+| coder | qwen3-coder-next:cloud | false | 23/23 (100.00%) | 3.223s |
+| installer | devstral-2:123b-cloud | false | 23/23 (100.00%) | 8.049s |
+| pentester | qwen3-coder-next:cloud | false | 23/23 (100.00%) | 2.227s |

-**Total**: 276/281 (98.22%) successful tests
-**Overall average latency**: 1.282s
+**Total**: 277/281 (98.58%) successful tests
+**Overall average latency**: 11.851s

 ## Detailed Results

-### simple (gpt-oss:120b)
+### simple (nemotron-3-super:cloud)

 #### Basic Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Simple Math | ✅ Pass | 6.491s |  |
-| Text Transform Uppercase | ✅ Pass | 1.047s |  |
-| Count from 1 to 5 | ✅ Pass | 0.896s |  |
-| Math Calculation | ✅ Pass | 0.883s |  |
-| Basic Echo Function | ✅ Pass | 0.963s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.998s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.044s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.429s |  |
+| Simple Math | ✅ Pass | 2.444s |  |
+| Text Transform Uppercase | ✅ Pass | 10.749s |  |
+| Count from 1 to 5 | ✅ Pass | 19.076s |  |
+| Math Calculation | ✅ Pass | 6.549s |  |
+| Basic Echo Function | ✅ Pass | 16.980s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 18.192s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 8.274s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 10.723s |  |

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.137s |  |
-| Search Query Function | ✅ Pass | 1.015s |  |
-| Ask Advice Function | ✅ Pass | 1.187s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 0.969s |  |
-| Basic Context Memory Test | ✅ Pass | 1.158s |  |
-| Function Argument Memory Test | ✅ Pass | 1.198s |  |
-| Function Response Memory Test | ✅ Pass | 1.100s |  |
-| Penetration Testing Memory with Tool Call | ✅ Pass | 1.276s |  |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.169s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.275s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.485s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.718s |  |
-| Penetration Testing Framework | ✅ Pass | 1.261s |  |
-| Web Application Security Scanner | ✅ Pass | 1.225s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.212s |  |
+| JSON Response Function | ✅ Pass | 20.851s |  |
+| Search Query Function | ✅ Pass | 16.304s |  |
+| Ask Advice Function | ✅ Pass | 33.178s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 14.129s |  |
+| Basic Context Memory Test | ✅ Pass | 25.373s |  |
+| Function Argument Memory Test | ✅ Pass | 34.212s |  |
+| Function Response Memory Test | ✅ Pass | 22.402s |  |
+| Penetration Testing Memory with Tool Call | ❌ Fail | 39.672s | expected function 'generate\_report' not found in tool calls: expected function generate\_report not found in tool calls |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 14.158s |  |
+| Penetration Testing Methodology | ✅ Pass | 57.038s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 40.968s |  |
+| SQL Injection Attack Type | ✅ Pass | 9.713s |  |
+| Penetration Testing Framework | ✅ Pass | 65.247s |  |
+| Web Application Security Scanner | ✅ Pass | 15.760s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 18.418s |  |

-**Summary**: 23/23 (100.00%) successful tests
+**Summary**: 22/23 (95.65%) successful tests

-**Average latency**: 1.398s
+**Average latency**: 22.627s

 ---

-### simple_json (gpt-oss:120b)
+### simple_json (nemotron-3-super:cloud)

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Vulnerability Report Memory Test | ✅ Pass | 1.653s |  |
-| Person Information JSON | ✅ Pass | 1.338s |  |
-| Project Information JSON | ✅ Pass | 1.515s |  |
-| User Profile JSON | ✅ Pass | 1.588s |  |
-| Streaming Person Information JSON Streaming | ✅ Pass | 1.159s |  |
+| Vulnerability Report Memory Test | ✅ Pass | 30.553s |  |
+| Person Information JSON | ✅ Pass | 23.124s |  |
+| Project Information JSON | ✅ Pass | 25.124s |  |
+| User Profile JSON | ✅ Pass | 31.109s |  |
+| Streaming Person Information JSON Streaming | ✅ Pass | 26.988s |  |

 **Summary**: 5/5 (100.00%) successful tests

-**Average latency**: 1.451s
+**Average latency**: 27.380s

 ---

-### primary_agent (gpt-oss:120b)
+### primary_agent (qwen3-coder-next:cloud)

 #### Basic Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.896s |  |
-| Text Transform Uppercase | ✅ Pass | 1.101s |  |
-| Count from 1 to 5 | ✅ Pass | 1.103s |  |
-| Math Calculation | ✅ Pass | 1.249s |  |
-| Basic Echo Function | ✅ Pass | 1.002s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.870s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.200s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.312s |  |
+| Simple Math | ✅ Pass | 1.931s |  |
+| Text Transform Uppercase | ✅ Pass | 0.763s |  |
+| Count from 1 to 5 | ✅ Pass | 3.641s |  |
+| Math Calculation | ✅ Pass | 0.932s |  |
+| Basic Echo Function | ✅ Pass | 0.869s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 0.700s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.713s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 0.812s |  |

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.080s |  |
-| Search Query Function | ✅ Pass | 0.969s |  |
-| Ask Advice Function | ✅ Pass | 1.030s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 1.482s |  |
-| Basic Context Memory Test | ✅ Pass | 1.174s |  |
-| Function Argument Memory Test | ✅ Pass | 1.106s |  |
-| Function Response Memory Test | ✅ Pass | 1.109s |  |
-| Penetration Testing Memory with Tool Call | ❌ Fail | 1.373s | expected function 'generate\_report' not found in tool calls: expected function generate\_report not found in tool calls |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 2.396s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.183s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.247s |  |
-| SQL Injection Attack Type | ✅ Pass | 3.982s |  |
-| Penetration Testing Framework | ✅ Pass | 1.473s |  |
-| Web Application Security Scanner | ✅ Pass | 1.145s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.395s |  |
-
-**Summary**: 22/23 (95.65%) successful tests
-
-**Average latency**: 1.343s
-
---
-
-### assistant (gpt-oss:120b)
-
-#### Basic Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.934s |  |
-| Text Transform Uppercase | ✅ Pass | 0.921s |  |
-| Count from 1 to 5 | ✅ Pass | 1.013s |  |
-| Math Calculation | ✅ Pass | 0.898s |  |
-| Basic Echo Function | ✅ Pass | 0.986s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.885s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.225s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.122s |  |
-
-#### Advanced Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 3.919s |  |
-| Search Query Function | ✅ Pass | 1.270s |  |
-| Ask Advice Function | ✅ Pass | 1.092s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 0.937s |  |
-| Basic Context Memory Test | ✅ Pass | 1.179s |  |
-| Function Argument Memory Test | ✅ Pass | 1.136s |  |
-| Function Response Memory Test | ✅ Pass | 1.183s |  |
-| Penetration Testing Memory with Tool Call | ✅ Pass | 1.503s |  |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.281s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.215s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.553s |  |
-| SQL Injection Attack Type | ✅ Pass | 3.831s |  |
-| Penetration Testing Framework | ✅ Pass | 1.037s |  |
-| Web Application Security Scanner | ✅ Pass | 1.120s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.230s |  |
-
-**Summary**: 23/23 (100.00%) successful tests
-
-**Average latency**: 1.369s
-
---
-
-### generator (gpt-oss:120b)
-
-#### Basic Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.884s |  |
-| Text Transform Uppercase | ✅ Pass | 1.102s |  |
-| Count from 1 to 5 | ✅ Pass | 0.958s |  |
-| Math Calculation | ✅ Pass | 1.046s |  |
-| Basic Echo Function | ✅ Pass | 1.050s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.896s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.128s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.024s |  |
-
-#### Advanced Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.522s |  |
-| Search Query Function | ✅ Pass | 1.082s |  |
-| Ask Advice Function | ✅ Pass | 1.034s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 1.040s |  |
-| Basic Context Memory Test | ✅ Pass | 1.403s |  |
-| Function Argument Memory Test | ✅ Pass | 1.079s |  |
-| Function Response Memory Test | ✅ Pass | 1.421s |  |
-| Penetration Testing Memory with Tool Call | ❌ Fail | 1.795s | expected function 'generate\_report' not found in tool calls: expected function generate\_report not found in tool calls |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.186s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.135s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.453s |  |
-| SQL Injection Attack Type | ✅ Pass | 4.510s |  |
-| Penetration Testing Framework | ✅ Pass | 1.658s |  |
-| Web Application Security Scanner | ✅ Pass | 1.139s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.239s |  |
-
-**Summary**: 22/23 (95.65%) successful tests
-
-**Average latency**: 1.339s
-
---
-
-### refiner (gpt-oss:120b)
-
-#### Basic Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.864s |  |
-| Text Transform Uppercase | ✅ Pass | 1.707s |  |
-| Count from 1 to 5 | ✅ Pass | 1.007s |  |
-| Math Calculation | ✅ Pass | 1.004s |  |
-| Basic Echo Function | ✅ Pass | 1.173s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 1.011s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.928s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.039s |  |
-
-#### Advanced Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.010s |  |
-| Search Query Function | ✅ Pass | 1.068s |  |
-| Ask Advice Function | ✅ Pass | 1.071s |  |
+| JSON Response Function | ✅ Pass | 0.959s |  |
+| Search Query Function | ✅ Pass | 0.933s |  |
+| Ask Advice Function | ✅ Pass | 33.999s |  |
 | Streaming Search Query Function Streaming | ✅ Pass | 0.998s |  |
-| Basic Context Memory Test | ✅ Pass | 1.102s |  |
-| Function Argument Memory Test | ✅ Pass | 1.199s |  |
-| Function Response Memory Test | ✅ Pass | 1.038s |  |
-| Penetration Testing Memory with Tool Call | ✅ Pass | 1.311s |  |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.178s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.379s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.752s |  |
-| SQL Injection Attack Type | ✅ Pass | 3.868s |  |
-| Penetration Testing Framework | ✅ Pass | 1.064s |  |
-| Web Application Security Scanner | ✅ Pass | 1.100s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.671s |  |
+| Basic Context Memory Test | ✅ Pass | 8.687s |  |
+| Function Argument Memory Test | ✅ Pass | 6.186s |  |
+| Function Response Memory Test | ✅ Pass | 2.615s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 1.527s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 4.732s |  |
+| Penetration Testing Methodology | ✅ Pass | 6.404s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 3.203s |  |
+| SQL Injection Attack Type | ✅ Pass | 2.766s |  |
+| Penetration Testing Framework | ✅ Pass | 8.059s |  |
+| Web Application Security Scanner | ✅ Pass | 1.546s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 1.339s |  |

 **Summary**: 23/23 (100.00%) successful tests

-**Average latency**: 1.285s
+**Average latency**: 4.101s

 ---

-### adviser (gpt-oss:120b)
+### assistant (nemotron-3-super:cloud)

 #### Basic Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Simple Math | ✅ Pass | 1.202s |  |
-| Text Transform Uppercase | ✅ Pass | 0.921s |  |
-| Count from 1 to 5 | ✅ Pass | 0.962s |  |
-| Math Calculation | ✅ Pass | 0.960s |  |
-| Basic Echo Function | ✅ Pass | 1.086s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.907s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.965s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 2.959s |  |
+| Simple Math | ✅ Pass | 13.460s |  |
+| Text Transform Uppercase | ✅ Pass | 8.769s |  |
+| Count from 1 to 5 | ✅ Pass | 6.944s |  |
+| Math Calculation | ✅ Pass | 31.133s |  |
+| Basic Echo Function | ✅ Pass | 10.710s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 16.396s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 7.617s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 13.783s |  |

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.101s |  |
-| Search Query Function | ✅ Pass | 1.005s |  |
-| Ask Advice Function | ✅ Pass | 1.049s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 1.083s |  |
-| Basic Context Memory Test | ✅ Pass | 1.114s |  |
-| Function Argument Memory Test | ✅ Pass | 1.035s |  |
-| Function Response Memory Test | ✅ Pass | 1.001s |  |
-| Penetration Testing Memory with Tool Call | ✅ Pass | 1.370s |  |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.135s |  |
-| Penetration Testing Methodology | ✅ Pass | 2.019s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.573s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.437s |  |
-| Penetration Testing Framework | ✅ Pass | 1.378s |  |
-| Web Application Security Scanner | ✅ Pass | 1.079s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.158s |  |
+| JSON Response Function | ✅ Pass | 20.992s |  |
+| Search Query Function | ✅ Pass | 13.170s |  |
+| Ask Advice Function | ✅ Pass | 17.042s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 18.533s |  |
+| Basic Context Memory Test | ✅ Pass | 23.059s |  |
+| Function Argument Memory Test | ✅ Pass | 25.397s |  |
+| Function Response Memory Test | ✅ Pass | 24.149s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 39.970s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 8.683s |  |
+| Penetration Testing Methodology | ✅ Pass | 63.505s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 34.659s |  |
+| SQL Injection Attack Type | ✅ Pass | 26.478s |  |
+| Penetration Testing Framework | ✅ Pass | 58.539s |  |
+| Web Application Security Scanner | ✅ Pass | 33.683s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 7.095s |  |

 **Summary**: 23/23 (100.00%) successful tests

-**Average latency**: 1.240s
+**Average latency**: 22.773s

 ---

-### reflector (gpt-oss:120b)
+### generator (qwen3-coder-next:cloud)

 #### Basic Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.834s |  |
-| Text Transform Uppercase | ✅ Pass | 1.040s |  |
-| Count from 1 to 5 | ✅ Pass | 1.190s |  |
-| Math Calculation | ✅ Pass | 0.915s |  |
-| Basic Echo Function | ✅ Pass | 1.050s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 1.076s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.197s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 0.925s |  |
+| Simple Math | ✅ Pass | 0.633s |  |
+| Text Transform Uppercase | ✅ Pass | 0.664s |  |
+| Count from 1 to 5 | ✅ Pass | 1.159s |  |
+| Math Calculation | ✅ Pass | 7.640s |  |
+| Basic Echo Function | ✅ Pass | 1.056s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 0.638s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.870s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 2.083s |  |

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.075s |  |
-| Search Query Function | ✅ Pass | 1.052s |  |
-| Ask Advice Function | ✅ Pass | 1.291s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 1.083s |  |
-| Basic Context Memory Test | ✅ Pass | 1.799s |  |
-| Function Argument Memory Test | ✅ Pass | 1.339s |  |
-| Function Response Memory Test | ✅ Pass | 0.996s |  |
-| Penetration Testing Memory with Tool Call | ✅ Pass | 2.745s |  |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.259s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.044s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.452s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.330s |  |
-| Penetration Testing Framework | ✅ Pass | 0.976s |  |
-| Web Application Security Scanner | ✅ Pass | 1.101s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.479s |  |
+| JSON Response Function | ✅ Pass | 0.946s |  |
+| Search Query Function | ✅ Pass | 0.880s |  |
+| Ask Advice Function | ✅ Pass | 1.013s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 0.946s |  |
+| Basic Context Memory Test | ✅ Pass | 1.315s |  |
+| Function Argument Memory Test | ✅ Pass | 0.722s |  |
+| Function Response Memory Test | ✅ Pass | 3.881s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 6.597s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 0.642s |  |
+| Penetration Testing Methodology | ✅ Pass | 9.073s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 3.598s |  |
+| SQL Injection Attack Type | ✅ Pass | 5.544s |  |
+| Penetration Testing Framework | ✅ Pass | 1.304s |  |
+| Web Application Security Scanner | ✅ Pass | 1.261s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 1.537s |  |

 **Summary**: 23/23 (100.00%) successful tests

-**Average latency**: 1.229s
+**Average latency**: 2.348s

 ---

-### searcher (gpt-oss:120b)
+### refiner (glm-5:cloud)

 #### Basic Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.910s |  |
-| Text Transform Uppercase | ✅ Pass | 1.046s |  |
-| Count from 1 to 5 | ✅ Pass | 0.902s |  |
-| Math Calculation | ✅ Pass | 1.029s |  |
-| Basic Echo Function | ✅ Pass | 1.376s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 1.394s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.670s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.105s |  |
+| Simple Math | ✅ Pass | 3.032s |  |
+| Text Transform Uppercase | ✅ Pass | 5.144s |  |
+| Count from 1 to 5 | ✅ Pass | 1.324s |  |
+| Math Calculation | ✅ Pass | 22.879s |  |
+| Basic Echo Function | ✅ Pass | 2.930s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 1.628s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 2.727s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 2.291s |  |

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.188s |  |
-| Search Query Function | ✅ Pass | 1.158s |  |
-| Ask Advice Function | ✅ Pass | 1.071s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 0.843s |  |
-| Basic Context Memory Test | ✅ Pass | 1.075s |  |
-| Function Argument Memory Test | ✅ Pass | 1.027s |  |
-| Function Response Memory Test | ✅ Pass | 1.038s |  |
-| Penetration Testing Memory with Tool Call | ❌ Fail | 1.625s | expected function 'generate\_report' not found in tool calls: expected function generate\_report not found in tool calls |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.159s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.303s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.499s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.109s |  |
-| Penetration Testing Framework | ✅ Pass | 1.128s |  |
-| Web Application Security Scanner | ✅ Pass | 1.189s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.284s |  |
-
-**Summary**: 22/23 (95.65%) successful tests
-
-**Average latency**: 1.180s
-
---
-
-### enricher (gpt-oss:120b)
-
-#### Basic Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| Simple Math | ✅ Pass | 1.643s |  |
-| Text Transform Uppercase | ✅ Pass | 0.776s |  |
-| Count from 1 to 5 | ✅ Pass | 1.023s |  |
-| Math Calculation | ✅ Pass | 1.061s |  |
-| Basic Echo Function | ✅ Pass | 0.918s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.944s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.206s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.036s |  |
-
-#### Advanced Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 0.993s |  |
-| Search Query Function | ✅ Pass | 0.981s |  |
-| Ask Advice Function | ✅ Pass | 2.644s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 0.904s |  |
-| Basic Context Memory Test | ✅ Pass | 1.120s |  |
-| Function Argument Memory Test | ✅ Pass | 1.211s |  |
-| Function Response Memory Test | ✅ Pass | 0.987s |  |
-| Penetration Testing Memory with Tool Call | ❌ Fail | 1.877s | expected function 'generate\_report' not found in tool calls: expected function generate\_report not found in tool calls |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.384s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.118s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.482s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.726s |  |
-| Penetration Testing Framework | ✅ Pass | 1.043s |  |
-| Web Application Security Scanner | ✅ Pass | 2.143s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.231s |  |
-
-**Summary**: 22/23 (95.65%) successful tests
-
-**Average latency**: 1.281s
-
---
-
-### coder (gpt-oss:120b)
-
-#### Basic Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.929s |  |
-| Text Transform Uppercase | ✅ Pass | 0.941s |  |
-| Count from 1 to 5 | ✅ Pass | 0.933s |  |
-| Math Calculation | ✅ Pass | 1.311s |  |
-| Basic Echo Function | ✅ Pass | 1.008s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.943s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.208s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.367s |  |
-
-#### Advanced Tests
-
-| Test | Result | Latency | Error |
-|------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.380s |  |
-| Search Query Function | ✅ Pass | 0.942s |  |
-| Ask Advice Function | ✅ Pass | 1.249s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 1.289s |  |
-| Basic Context Memory Test | ✅ Pass | 1.099s |  |
-| Function Argument Memory Test | ✅ Pass | 1.122s |  |
-| Function Response Memory Test | ✅ Pass | 0.967s |  |
-| Penetration Testing Memory with Tool Call | ✅ Pass | 1.401s |  |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.355s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.204s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.564s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.421s |  |
-| Penetration Testing Framework | ✅ Pass | 1.507s |  |
-| Web Application Security Scanner | ✅ Pass | 1.142s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.712s |  |
+| JSON Response Function | ✅ Pass | 2.312s |  |
+| Search Query Function | ✅ Pass | 1.351s |  |
+| Ask Advice Function | ✅ Pass | 1.539s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 1.405s |  |
+| Basic Context Memory Test | ✅ Pass | 5.605s |  |
+| Function Argument Memory Test | ✅ Pass | 2.879s |  |
+| Function Response Memory Test | ✅ Pass | 1.468s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 15.864s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 2.101s |  |
+| Penetration Testing Methodology | ✅ Pass | 16.016s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 24.194s |  |
+| SQL Injection Attack Type | ✅ Pass | 7.143s |  |
+| Penetration Testing Framework | ✅ Pass | 22.774s |  |
+| Web Application Security Scanner | ✅ Pass | 34.765s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 1.788s |  |

 **Summary**: 23/23 (100.00%) successful tests

-**Average latency**: 1.218s
+**Average latency**: 7.964s

 ---

-### installer (gpt-oss:120b)
+### adviser (minimax-m2.7:cloud)

 #### Basic Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.848s |  |
-| Text Transform Uppercase | ✅ Pass | 1.111s |  |
-| Count from 1 to 5 | ✅ Pass | 0.968s |  |
-| Math Calculation | ✅ Pass | 1.029s |  |
-| Basic Echo Function | ✅ Pass | 0.983s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 1.016s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.492s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 2.627s |  |
+| Simple Math | ✅ Pass | 2.791s |  |
+| Text Transform Uppercase | ✅ Pass | 1.907s |  |
+| Count from 1 to 5 | ✅ Pass | 5.236s |  |
+| Math Calculation | ✅ Pass | 4.146s |  |
+| Basic Echo Function | ✅ Pass | 1.855s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 2.809s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 3.696s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 7.184s |  |

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.052s |  |
-| Search Query Function | ✅ Pass | 0.978s |  |
-| Ask Advice Function | ✅ Pass | 1.163s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 2.407s |  |
-| Basic Context Memory Test | ✅ Pass | 1.079s |  |
-| Function Argument Memory Test | ✅ Pass | 1.316s |  |
-| Function Response Memory Test | ✅ Pass | 1.072s |  |
-| Penetration Testing Memory with Tool Call | ✅ Pass | 1.321s |  |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.255s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.210s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.539s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.214s |  |
-| Penetration Testing Framework | ✅ Pass | 0.828s |  |
-| Web Application Security Scanner | ✅ Pass | 1.242s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.221s |  |
+| JSON Response Function | ✅ Pass | 2.898s |  |
+| Search Query Function | ✅ Pass | 4.785s |  |
+| Ask Advice Function | ✅ Pass | 1.973s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 2.405s |  |
+| Basic Context Memory Test | ✅ Pass | 2.504s |  |
+| Function Argument Memory Test | ✅ Pass | 2.930s |  |
+| Function Response Memory Test | ✅ Pass | 2.279s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 3.874s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 2.765s |  |
+| Penetration Testing Methodology | ✅ Pass | 3.184s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 14.047s |  |
+| SQL Injection Attack Type | ✅ Pass | 5.317s |  |
+| Penetration Testing Framework | ✅ Pass | 5.817s |  |
+| Web Application Security Scanner | ✅ Pass | 4.591s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 2.773s |  |

 **Summary**: 23/23 (100.00%) successful tests

-**Average latency**: 1.260s
+**Average latency**: 3.990s

 ---

-### pentester (gpt-oss:120b)
+### reflector (glm-5:cloud)

 #### Basic Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| Simple Math | ✅ Pass | 0.922s |  |
-| Text Transform Uppercase | ✅ Pass | 1.372s |  |
-| Count from 1 to 5 | ✅ Pass | 1.114s |  |
-| Math Calculation | ✅ Pass | 0.914s |  |
-| Basic Echo Function | ✅ Pass | 1.084s |  |
-| Streaming Simple Math Streaming | ✅ Pass | 0.968s |  |
-| Streaming Count from 1 to 3 Streaming | ✅ Pass | 1.109s |  |
-| Streaming Basic Echo Function Streaming | ✅ Pass | 1.018s |  |
+| Simple Math | ✅ Pass | 18.770s |  |
+| Text Transform Uppercase | ✅ Pass | 3.024s |  |
+| Count from 1 to 5 | ✅ Pass | 1.798s |  |
+| Math Calculation | ✅ Pass | 2.176s |  |
+| Basic Echo Function | ✅ Pass | 4.612s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 2.214s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 17.066s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 1.913s |  |

 #### Advanced Tests

 | Test | Result | Latency | Error |
 |------|--------|---------|-------|
-| JSON Response Function | ✅ Pass | 1.243s |  |
-| Search Query Function | ✅ Pass | 1.003s |  |
-| Ask Advice Function | ✅ Pass | 0.941s |  |
-| Streaming Search Query Function Streaming | ✅ Pass | 0.879s |  |
-| Basic Context Memory Test | ✅ Pass | 1.544s |  |
-| Function Argument Memory Test | ✅ Pass | 1.132s |  |
-| Function Response Memory Test | ✅ Pass | 0.991s |  |
-| Penetration Testing Memory with Tool Call | ❌ Fail | 1.949s | expected function 'generate\_report' not found in tool calls: expected function generate\_report not found in tool calls |
-| Cybersecurity Workflow Memory Test | ✅ Pass | 1.581s |  |
-| Penetration Testing Methodology | ✅ Pass | 1.299s |  |
-| Vulnerability Assessment Tools | ✅ Pass | 1.353s |  |
-| SQL Injection Attack Type | ✅ Pass | 1.185s |  |
-| Penetration Testing Framework | ✅ Pass | 1.473s |  |
-| Web Application Security Scanner | ✅ Pass | 1.224s |  |
-| Penetration Testing Tool Selection | ✅ Pass | 1.355s |  |
+| JSON Response Function | ✅ Pass | 3.675s |  |
+| Search Query Function | ✅ Pass | 1.432s |  |
+| Ask Advice Function | ✅ Pass | 1.765s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 11.441s |  |
+| Basic Context Memory Test | ✅ Pass | 5.525s |  |
+| Function Argument Memory Test | ✅ Pass | 10.351s |  |
+| Function Response Memory Test | ✅ Pass | 3.459s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 7.899s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 2.117s |  |
+| Penetration Testing Methodology | ✅ Pass | 10.196s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 63.102s |  |
+| SQL Injection Attack Type | ✅ Pass | 4.516s |  |
+| Penetration Testing Framework | ✅ Pass | 17.855s |  |
+| Web Application Security Scanner | ✅ Pass | 9.839s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 6.867s |  |

-**Summary**: 22/23 (95.65%) successful tests
+**Summary**: 23/23 (100.00%) successful tests

-**Average latency**: 1.203s
+**Average latency**: 9.201s
+
+---
+
+### searcher (qwen3.5:397b-cloud)
+
+#### Basic Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| Simple Math | ✅ Pass | 1.317s |  |
+| Text Transform Uppercase | ✅ Pass | 1.459s |  |
+| Count from 1 to 5 | ✅ Pass | 3.248s |  |
+| Math Calculation | ✅ Pass | 1.474s |  |
+| Basic Echo Function | ✅ Pass | 2.060s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 1.405s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 2.521s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 0.976s |  |
+
+#### Advanced Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| JSON Response Function | ✅ Pass | 1.263s |  |
+| Search Query Function | ✅ Pass | 0.955s |  |
+| Ask Advice Function | ✅ Pass | 1.196s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 0.967s |  |
+| Basic Context Memory Test | ✅ Pass | 2.587s |  |
+| Function Argument Memory Test | ✅ Pass | 1.596s |  |
+| Function Response Memory Test | ✅ Pass | 1.408s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 2.083s |  |
+| Penetration Testing Methodology | ✅ Pass | 5.672s |  |
+| Penetration Testing Memory with Tool Call | ❌ Fail | 600.006s | Post "https://ollama\.com/api/chat?ts=1774282315": net/http: request canceled \(Client\.Timeout exceeded while awaiting headers\) |
+| SQL Injection Attack Type | ✅ Pass | 4.083s |  |
+| Vulnerability Assessment Tools | ❌ Fail | 391.303s | 500 Internal Server Error: Internal Server Error \(ref: 9d3370b7\-e2d2\-4086\-9f8b\-948f29fcd567\) |
+| Penetration Testing Framework | ❌ Fail | 30.619s | expected text 'exploitation' not found |
+| Web Application Security Scanner | ✅ Pass | 2.647s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 1.136s |  |
+
+**Summary**: 20/23 (86.96%) successful tests
+
+**Average latency**: 46.174s
+
+---
+
+### enricher (minimax-m2.7:cloud)
+
+#### Basic Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| Simple Math | ✅ Pass | 3.381s |  |
+| Text Transform Uppercase | ✅ Pass | 2.794s |  |
+| Count from 1 to 5 | ✅ Pass | 4.367s |  |
+| Math Calculation | ✅ Pass | 2.078s |  |
+| Basic Echo Function | ✅ Pass | 1.977s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 2.884s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 3.745s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 2.099s |  |
+
+#### Advanced Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| JSON Response Function | ✅ Pass | 1.883s |  |
+| Search Query Function | ✅ Pass | 3.617s |  |
+| Ask Advice Function | ✅ Pass | 1.873s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 2.564s |  |
+| Basic Context Memory Test | ✅ Pass | 1.803s |  |
+| Function Argument Memory Test | ✅ Pass | 2.661s |  |
+| Function Response Memory Test | ✅ Pass | 2.227s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 5.442s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 2.429s |  |
+| Penetration Testing Methodology | ✅ Pass | 5.753s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 70.743s |  |
+| SQL Injection Attack Type | ✅ Pass | 4.696s |  |
+| Penetration Testing Framework | ✅ Pass | 6.033s |  |
+| Web Application Security Scanner | ✅ Pass | 3.398s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 3.064s |  |
+
+**Summary**: 23/23 (100.00%) successful tests
+
+**Average latency**: 6.153s
+
+---
+
+### coder (qwen3-coder-next:cloud)
+
+#### Basic Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| Simple Math | ✅ Pass | 0.654s |  |
+| Text Transform Uppercase | ✅ Pass | 12.005s |  |
+| Count from 1 to 5 | ✅ Pass | 0.667s |  |
+| Math Calculation | ✅ Pass | 0.633s |  |
+| Basic Echo Function | ✅ Pass | 0.819s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 0.612s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.699s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 0.923s |  |
+
+#### Advanced Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| JSON Response Function | ✅ Pass | 4.229s |  |
+| Search Query Function | ✅ Pass | 0.873s |  |
+| Ask Advice Function | ✅ Pass | 1.075s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 1.897s |  |
+| Basic Context Memory Test | ✅ Pass | 1.072s |  |
+| Function Argument Memory Test | ✅ Pass | 1.312s |  |
+| Function Response Memory Test | ✅ Pass | 0.642s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 1.623s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 0.710s |  |
+| Penetration Testing Methodology | ✅ Pass | 15.597s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 12.591s |  |
+| SQL Injection Attack Type | ✅ Pass | 1.284s |  |
+| Penetration Testing Framework | ✅ Pass | 2.334s |  |
+| Web Application Security Scanner | ✅ Pass | 10.475s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 1.387s |  |
+
+**Summary**: 23/23 (100.00%) successful tests
+
+**Average latency**: 3.223s
+
+---
+
+### installer (devstral-2:123b-cloud)
+
+#### Basic Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| Simple Math | ✅ Pass | 0.698s |  |
+| Text Transform Uppercase | ✅ Pass | 0.738s |  |
+| Count from 1 to 5 | ✅ Pass | 0.793s |  |
+| Math Calculation | ✅ Pass | 0.709s |  |
+| Basic Echo Function | ✅ Pass | 0.842s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 1.028s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.740s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 158.484s |  |
+
+#### Advanced Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| JSON Response Function | ✅ Pass | 0.955s |  |
+| Search Query Function | ✅ Pass | 0.851s |  |
+| Ask Advice Function | ✅ Pass | 1.002s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 0.813s |  |
+| Basic Context Memory Test | ✅ Pass | 0.851s |  |
+| Function Argument Memory Test | ✅ Pass | 0.757s |  |
+| Function Response Memory Test | ✅ Pass | 0.761s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 1.261s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 0.730s |  |
+| Penetration Testing Methodology | ✅ Pass | 2.598s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 2.323s |  |
+| SQL Injection Attack Type | ✅ Pass | 1.026s |  |
+| Penetration Testing Framework | ✅ Pass | 4.639s |  |
+| Web Application Security Scanner | ✅ Pass | 1.504s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 1.016s |  |
+
+**Summary**: 23/23 (100.00%) successful tests
+
+**Average latency**: 8.049s
+
+---
+
+### pentester (qwen3-coder-next:cloud)
+
+#### Basic Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| Simple Math | ✅ Pass | 0.654s |  |
+| Text Transform Uppercase | ✅ Pass | 1.256s |  |
+| Count from 1 to 5 | ✅ Pass | 0.716s |  |
+| Math Calculation | ✅ Pass | 0.993s |  |
+| Basic Echo Function | ✅ Pass | 0.798s |  |
+| Streaming Simple Math Streaming | ✅ Pass | 0.657s |  |
+| Streaming Count from 1 to 3 Streaming | ✅ Pass | 0.658s |  |
+| Streaming Basic Echo Function Streaming | ✅ Pass | 1.956s |  |
+
+#### Advanced Tests
+
+| Test | Result | Latency | Error |
+|------|--------|---------|-------|
+| JSON Response Function | ✅ Pass | 1.019s |  |
+| Search Query Function | ✅ Pass | 0.841s |  |
+| Ask Advice Function | ✅ Pass | 8.525s |  |
+| Streaming Search Query Function Streaming | ✅ Pass | 7.950s |  |
+| Basic Context Memory Test | ✅ Pass | 10.081s |  |
+| Function Argument Memory Test | ✅ Pass | 0.815s |  |
+| Function Response Memory Test | ✅ Pass | 0.675s |  |
+| Penetration Testing Memory with Tool Call | ✅ Pass | 1.659s |  |
+| Cybersecurity Workflow Memory Test | ✅ Pass | 0.804s |  |
+| Penetration Testing Methodology | ✅ Pass | 1.960s |  |
+| Vulnerability Assessment Tools | ✅ Pass | 2.314s |  |
+| SQL Injection Attack Type | ✅ Pass | 1.424s |  |
+| Penetration Testing Framework | ✅ Pass | 1.673s |  |
+| Web Application Security Scanner | ✅ Pass | 1.148s |  |
+| Penetration Testing Tool Selection | ✅ Pass | 2.646s |  |
+
+**Summary**: 23/23 (100.00%) successful tests
+
+**Average latency**: 2.227s

 ---