Upload folder using huggingface_hub

.gitattributes

@@ -58,3 +58,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 # Video files - compressed
 *.mp4 filter=lfs diff=lfs merge=lfs -text
 *.webm filter=lfs diff=lfs merge=lfs -text
+candidate_data.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,198 @@
+---
+license: apache-2.0
+task_categories:
+  - question-answering
+language:
+  - en
+tags:
+  - agent-benchmark
+  - tool-use
+  - recruiting
+  - bpo
+size_categories:
+  - 10K<n<100K
+---
+
+# BPO Benchmark Dataset
+
+Evaluation dataset for AI agents using recruiting analytics APIs. This benchmark tests an agent's ability to use tool APIs to answer questions about BPO (Business Process Outsourcing) recruiting data.
+
+## Dataset Structure
+
+### Files
+
+- **candidate_data.parquet** (1.8 MB): 64k synthetic candidate records with recruiting funnel data
+- **candidate_data.csv** (13.5 MB): Same data in CSV format for human inspection
+- **tasks.json** (26 KB): 26 core evaluation tasks with ground truth
+- **tasks_type_mismatch.json**: 3 tasks testing agent handling of unexpected data types
+- **tasks_http_errors.json**: 4 tasks testing agent handling of HTTP error codes
+- **tasks_schema_violations.json**: 4 tasks testing agent handling of schema violations
+- **tasks_edge_cases.json**: 5 tasks testing agent handling of edge cases (large payloads, Unicode, deep nesting)
+- **tasks_undocumented.json**: 3 tasks testing agent handling of undocumented API behaviors
+- **large_response_fixture.json**: Fixture data for the oversized-payload edge case test
+
+### Candidate Data Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `candidate_id` | string | Unique candidate identifier |
+| `requisition_id` | string | Job requisition ID (e.g., "05958BR") |
+| `requisition_template_id` | string | Template for similar requisitions |
+| `source_name` | string | Sourcing channel (LinkedIn, Dice, GitHub, etc.) |
+| `applied_at` | datetime | Application timestamp |
+| `reviewed` | bool | Whether candidate was reviewed |
+| `sla_met` | bool | Whether SLA was met for review |
+| `interviewed` | bool | Whether candidate was interviewed |
+| `offer_extended` | bool | Whether offer was extended |
+| `offer_accepted` | bool | Whether offer was accepted |
+| `hired` | bool | Whether candidate was hired |
+| `hire_date` | datetime | Date of hire (if hired) |
+| `skills` | list | Candidate skills list |
+| `department` | string | Job department |
+| `seniority_level` | string | Job seniority level |
+
+### Task Format
+
+Each task in `tasks.json` has:
+
+```json
+{
+  "name": "task_1",
+  "description": "Task description and explanation",
+  "intent": "The question to answer",
+  "difficulty": "easy|medium|hard",
+  "expected_output": {
+    "response": "Expected answer text",
+    "keywords": ["keyword1", "keyword2|alternative"],
+    "tool_calls": [{"name": "api_endpoint", "args": {}}]
+  }
+}
+```
+
+Keywords support OR matching with `|` separator.
+
+## API Endpoints
+
+The benchmark includes 32 API endpoints (13 core + 19 error-prone).
+
+### Core Endpoints (13)
+
+#### Candidate Source APIs (7)
+1. `candidate_source_sla_per_source` - SLA performance by source
+2. `candidate_source_total_hires_by_source` - Hire counts by source
+3. `candidate_source_candidate_volume_by_source` - Candidate volume metrics
+4. `candidate_source_funnel_conversion_by_source` - Funnel conversion rates
+5. `candidate_source_metadata_and_timeframe` - Data timeframe and metadata
+6. `candidate_source_definitions_and_methodology` - Metric definitions
+7. `candidate_source_source_recommendation_summary` - Source recommendations
+
+#### Skills APIs (6)
+8. `skills_skill_analysis` - Skill statistics and correlations
+9. `skills_skill_impact_fill_rate` - Skill impact on fill rate
+10. `skills_skill_impact_sla` - Skill impact on SLA
+11. `skills_skill_relevance_justification` - Skill relevance explanation
+12. `skills_successful_posting_criteria` - Success criteria thresholds
+13. `skills_data_sources_used` - Data sources and models used
+
+### Error-Prone Endpoints (19)
+
+These endpoints intentionally exhibit problematic behaviors to test agent resilience and error handling.
+
+#### Type Mismatch (3)
+14. `skills_skill_summary` - Returns plain string instead of JSON
+15. `candidate_source_source_sla_score` - Returns numeric float instead of structured response
+16. `candidate_source_inactive_sources` - Returns boolean or list depending on data state
+
+#### HTTP Errors (4)
+17. `candidate_source_candidate_pipeline_status` - Intermittently returns 404
+18. `candidate_source_source_sla_check` - Returns 500 Internal Server Error
+19. `candidate_source_funnel_status` - Returns 503 Service Unavailable
+20. `candidate_source_bulk_source_data` - Returns 429 Too Many Requests
+
+#### Schema Violations (4)
+21. `skills_model_registry` - No output schema; returns untyped dict
+22. `skills_skill_lookup` - Returns extra undeclared fields
+23. `candidate_source_source_metrics_lite` - Randomly omits required fields
+24. `candidate_source_volume_report` - Returns wrong field types (strings for numbers)
+
+#### Edge Cases (5)
+25. `candidate_source_full_candidate_details` - Oversized payload (~1MB)
+26. `candidate_source_source_directory` - Unicode and special characters
+27. `skills_skill_deep_analysis` - Deeply nested JSON (5+ levels)
+28. `candidate_source_sla_extended` - Unexpected extra fields
+29. `skills_analyze_skill_match` - Mismatched schema vs documentation
+
+#### Undocumented Behaviors (3)
+30. `candidate_source_requisition_details` - Non-standard error format
+31. `candidate_source_list_all_sources` - Undocumented pagination
+32. `candidate_source_batch_metrics` - Undocumented rate limiting headers
+
+## Usage
+
+### With the Evaluation Space
+
+The easiest way to use this dataset is through the evaluation Space:
+
+[ibm-research/bpo-benchmark-eval](https://huggingface.co/spaces/ibm-research/bpo-benchmark-eval)
+
+### Programmatic Access
+
+```python
+from huggingface_hub import hf_hub_download
+import pandas as pd
+import json
+
+repo = "ibm-research/bpo-benchmark"
+
+# Download candidate data
+parquet_path = hf_hub_download(repo, "candidate_data.parquet", repo_type="dataset")
+
+# Download all task suites
+task_files = [
+    "tasks.json",
+    "tasks_type_mismatch.json",
+    "tasks_http_errors.json",
+    "tasks_schema_violations.json",
+    "tasks_edge_cases.json",
+    "tasks_undocumented.json",
+]
+task_paths = {
+    f: hf_hub_download(repo, f, repo_type="dataset")
+    for f in task_files
+}
+
+# Load data
+df = pd.read_parquet(parquet_path)
+with open(task_paths["tasks.json"]) as f:
+    core_tasks = json.load(f)
+
+print(f"Loaded {len(df)} candidates")
+print(f"Loaded {len(core_tasks[0]['test_cases'])} core tasks")
+print(f"Task suites: {list(task_paths.keys())}")
+```
+
+## Statistics
+
+- **Candidates**: 64,000 records
+- **Requisitions**: 1,047 unique
+- **Sourcing Channels**: 7 (LinkedIn, Dice, GitHub, Indeed, Referral, CyberSec Jobs, Company Website)
+- **Total API Endpoints**: 32 (13 core + 19 error-prone)
+- **Core Evaluation Tasks**: 26 (Easy: 20, Medium: 3, Hard: 3)
+- **Error-Prone Tasks**: 19 (Type Mismatch: 3, HTTP Errors: 4, Schema Violations: 4, Edge Cases: 5, Undocumented: 3)
+- **Total Tasks**: 45
+- **Time Range**: Oct 2023 - Mar 2025
+
+## License
+
+Apache 2.0
+
+## Citation
+
+```bibtex
+@misc{bpo-benchmark,
+  title={BPO Benchmark: Agent Evaluation for Recruiting Analytics},
+  year={2025},
+  publisher={HuggingFace},
+  url={https://huggingface.co/datasets/ibm-research/bpo-benchmark}
+}
+```

candidate_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12f5c73b7a0a8613cbf52803fbc391d55874a9de1fd85f180b51a0e8a6a70f2
+size 13505237

candidate_data.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f2e8e859259f6ff0c5dd017f630d0df2490d298775647ab5882350fe80c6e5
+size 1802852

tasks.json

@@ -0,0 +1,1291 @@
+[
+  {
+    "name": "bpo-benchmark",
+    "user_info": [],
+    "test_cases": [
+      {
+        "name": "task_1",
+        "description": "Lists sources ranked by SLA success rate. | Explanation: CyberSec Jobs was identified as the lowest-performing source because its SLA success rate is 67 %, well below Dice (80 %), LinkedIn (79 %), GitHub (78 %), and the other sources returned by the API.",
+        "intent": "For requisition 05958BR, which source has the lowest SLA performance?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "CyberSec Jobs with 67%",
+          "keywords": [
+            "CyberSec Jobs",
+            "67%|67 %|67"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_sla_per_source",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_sla_per_source",
+              "result": {
+                "metrics": [
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "sla_percentage": 67
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "sla_percentage": 86
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "sla_percentage": 90
+                  },
+                  {
+                    "source_name": "Dice",
+                    "sla_percentage": 95
+                  },
+                  {
+                    "source_name": "Internal",
+                    "sla_percentage": 95
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "sla_percentage": 95
+                  },
+                  {
+                    "source_name": "Referral",
+                    "sla_percentage": 95
+                  }
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_2",
+        "description": "Asks for the missing requisition id. | Explanation: The query lacks a requisition ID which is required for the API call.",
+        "intent": "What's the percentage of hires and the total hires per source?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Can you share the requisition ID (e.g., 05958BR or 05959BR)?",
+          "keywords": [
+            "requisition|req",
+            "ID|id|identifier",
+            "missing|without|share|provide|required"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_3",
+        "description": "Shows each source's candidate volume and offer/hire success metrics for jobs similar to 05958BR. | Explanation: Candidate counts and percentages were taken from the candidate-volume API; hire counts and offer-acceptance rates were taken from the recommendation-summary API. The two tables were joined on \"source_name\", producing a combined view of volume and effectiveness for the three leading sources. | Note: Cross-references performance and volume per source. Requires joining APIs on 'source_name'.",
+        "intent": "For requisitions like 05958BR, which sources provided the most candidates, and how effective were they at converting to hires?",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "LinkedIn: 519 candidates (18%), 7 hires. Offer acceptance rate: 70%. Dice: 516 candidates (18%), 11 hires. Offer acceptance rate: 79%. GitHub: 468 candidates (16%), 10 hires. Offer acceptance rate: 77%.",
+          "keywords": [
+            "LinkedIn",
+            "Dice",
+            "GitHub",
+            "Offer acceptance rate",
+            "519",
+            "516",
+            "468",
+            "18%|18 %|18",
+            "70%|70 %|70",
+            "79%|79 %|79",
+            "77%|77 %|77",
+            "hires"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_candidate_volume_by_source",
+              "args": {}
+            },
+            {
+              "name": "candidate_source_source_recommendation_summary",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_candidate_volume_by_source",
+              "result": {
+                "job_id": "05958BR",
+                "total_candidate_volume": 2913,
+                "metrics": [
+                  {
+                    "source_name": "LinkedIn",
+                    "candidate_volume": 519,
+                    "percentage": 18
+                  },
+                  {
+                    "source_name": "Dice",
+                    "candidate_volume": 516,
+                    "percentage": 18
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "candidate_volume": 468,
+                    "percentage": 16
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "candidate_volume": 410,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "Internal",
+                    "candidate_volume": 400,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "Referral",
+                    "candidate_volume": 400,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "candidate_volume": 200,
+                    "percentage": 7
+                  }
+                ],
+                "heading": "For requisitions similar to 05958BR, there were 2913 candidates over the past three years. Here's how many candidates came from each source (with percentages from the total number):"
+              }
+            },
+            {
+              "name": "candidate_source_source_recommendation_summary",
+              "result": {
+                "total_requisitions": 40,
+                "metrics": [
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "jobs_filled_percentage": 2,
+                    "first_round_review_percentage": 80,
+                    "offer_acceptance_rate": 67,
+                    "total_hires": 3
+                  },
+                  {
+                    "source_name": "Dice",
+                    "jobs_filled_percentage": 2,
+                    "first_round_review_percentage": 11,
+                    "offer_acceptance_rate": 79,
+                    "total_hires": 11
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "jobs_filled_percentage": 2,
+                    "first_round_review_percentage": 76,
+                    "offer_acceptance_rate": 77,
+                    "total_hires": 10
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "jobs_filled_percentage": 0,
+                    "first_round_review_percentage": 77,
+                    "offer_acceptance_rate": 0,
+                    "total_hires": 0
+                  },
+                  {
+                    "source_name": "Internal",
+                    "jobs_filled_percentage": 2,
+                    "first_round_review_percentage": 74,
+                    "offer_acceptance_rate": 70,
+                    "total_hires": 5
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "jobs_filled_percentage": 2,
+                    "first_round_review_percentage": 75,
+                    "offer_acceptance_rate": 70,
+                    "total_hires": 7
+                  },
+                  {
+                    "source_name": "Referral",
+                    "jobs_filled_percentage": 2,
+                    "first_round_review_percentage": 70,
+                    "offer_acceptance_rate": 62,
+                    "total_hires": 4
+                  }
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_4",
+        "description": "Asks for the missing requisition id. | Explanation: The query lacks a requisition ID which is required for the API call.",
+        "intent": "Did Dice provide a good funnel conversion rate?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Can you share the requisition ID (e.g., 05958BR or 05959BR)?",
+          "keywords": [
+            "requisition|req",
+            "ID|id|identifier",
+            "missing|without|share|provide|required"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_5",
+        "description": "Asks for the missing requisition id. | Explanation: The query lacks a requisition ID which is required for the API call.",
+        "intent": "Should I include the skill Python? What is its impact on SLA, fill rate, and overall relevance?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Can you share the requisition ID (e.g., 05958BR or 05959BR)?",
+          "keywords": [
+            "requisition|req",
+            "ID|id|identifier",
+            "missing|without|share|provide|required"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_6",
+        "description": "Recommends top-performing sources by combining SLA success, candidate volume, and funnel effectiveness. | Explanation: Each source received a weighted score (50 % SLA success, 30 % candidate volume share, 20 % offer-conversion rate). Dice and LinkedIn tied for top SLA (100 %) and high volume; GitHub's best-in-class conversion (2.8 %) offset its 80 % SLA. Indeed scored 0 on SLA and offers, so it was excluded. | Note: This benchmark tests multi-criteria decision-making and cross-API synthesis.",
+        "intent": "What are the best sources to prioritize for 05959BR?",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "You should prioritize Dice, GitHub, and LinkedIn. Dice and LinkedIn both met SLA 100% of the time and brought in 18% of all candidates. Dice had a strong offer conversion rate (2.7%), and GitHub had the highest conversion (2.8%) despite slightly lower SLA. Indeed should be avoided due to 0% SLA and 0% offer conversion.",
+          "keywords": [
+            "Dice",
+            "GitHub",
+            "LinkedIn",
+            "SLA",
+            "Indeed"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_sla_per_source",
+              "args": {}
+            },
+            {
+              "name": "candidate_source_candidate_volume_by_source",
+              "args": {}
+            },
+            {
+              "name": "candidate_source_funnel_conversion_by_source",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_sla_per_source",
+              "result": {
+                "metrics": [
+                  {
+                    "source_name": "Indeed",
+                    "sla_percentage": 0
+                  },
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "sla_percentage": 70
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "sla_percentage": 80
+                  },
+                  {
+                    "source_name": "Internal",
+                    "sla_percentage": 85
+                  },
+                  {
+                    "source_name": "Dice",
+                    "sla_percentage": 100
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "sla_percentage": 100
+                  },
+                  {
+                    "source_name": "Referral",
+                    "sla_percentage": 100
+                  }
+                ]
+              }
+            },
+            {
+              "name": "candidate_source_candidate_volume_by_source",
+              "result": {
+                "job_id": "05959BR",
+                "total_candidate_volume": 2913,
+                "metrics": [
+                  {
+                    "source_name": "Dice",
+                    "candidate_volume": 525,
+                    "percentage": 18
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "candidate_volume": 525,
+                    "percentage": 18
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "candidate_volume": 465,
+                    "percentage": 16
+                  },
+                  {
+                    "source_name": "Internal",
+                    "candidate_volume": 403,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "candidate_volume": 400,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "Referral",
+                    "candidate_volume": 400,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "candidate_volume": 195,
+                    "percentage": 7
+                  }
+                ],
+                "heading": "For requisitions similar to 05959BR, there were 2913 candidates over the past three years. Here's how many candidates came from each source (with percentages from the total number):"
+              }
+            },
+            {
+              "name": "candidate_source_funnel_conversion_by_source",
+              "result": {
+                "job_id": "05959BR",
+                "metrics": [
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "first_round_review_percentage": 80.5,
+                    "interview_rate": 18.5,
+                    "offer_acceptance_rate": 3.1
+                  },
+                  {
+                    "source_name": "Dice",
+                    "first_round_review_percentage": 76.0,
+                    "interview_rate": 9.9,
+                    "offer_acceptance_rate": 2.7
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "first_round_review_percentage": 72.0,
+                    "interview_rate": 16.6,
+                    "offer_acceptance_rate": 2.8
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "first_round_review_percentage": 72.2,
+                    "interview_rate": 14.8,
+                    "offer_acceptance_rate": 0.0
+                  },
+                  {
+                    "source_name": "Internal",
+                    "first_round_review_percentage": 76.9,
+                    "interview_rate": 19.6,
+                    "offer_acceptance_rate": 2.5
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "first_round_review_percentage": 70.1,
+                    "interview_rate": 21.0,
+                    "offer_acceptance_rate": 1.9
+                  },
+                  {
+                    "source_name": "Referral",
+                    "first_round_review_percentage": 74.5,
+                    "interview_rate": 20.5,
+                    "offer_acceptance_rate": 2.0
+                  }
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_7",
+        "description": "Asks for the missing requisition id. | Explanation: The query lacks a requisition ID which is required for the API call.",
+        "intent": "Out of these skills — Python, Quantum Physics, Cyber Engineering, Risk Analysis, Wireshark — which ones negatively affect SLA performance?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Can you share the requisition ID (e.g., 05958BR or 05959BR)?",
+          "keywords": [
+            "requisition|req",
+            "ID|id|identifier",
+            "missing|without|share|provide|required"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_8",
+        "description": "Returns the definition of the SLA metric for the given requisition. | Explanation: The definitions-and-methodology endpoint contains a JSON field \"sla\" holding the textual definition; the agent extracted that string verbatim. | Note: Tests the agent's ability to locate and return a specific definition.",
+        "intent": "How is the SLA metric defined for 05958BR?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "SLA is defined as 'Percentage of candidates reviewed within the defined SLA window (e.g., 48 hours)'.",
+          "keywords": [
+            "SLA",
+            "Percentage",
+            "reviewed",
+            "window"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "result": {
+                "job_id": "05958BR",
+                "definitions": {
+                  "sla": "Percentage of candidates reviewed within the defined SLA window (e.g., 48 hours)",
+                  "time_to_fill": "Average time from job posting to accepted offer",
+                  "success_rate": "Ratio of candidates who accepted offers out of those interviewed"
+                },
+                "calculation_notes": "Metrics are computed from 1047 requisitions over the last 1.4 years. Funnel stats are based on system timestamps and recruiter actions in ATS.",
+                "top_metrics_considered": [
+                  "SLA %",
+                  "First round review %",
+                  "Offer acceptance rate",
+                  "Candidate volume",
+                  "Total hires"
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_9",
+        "description": "Returns the number of requisitions used to compute the reported metrics. | Explanation: The methodology response includes a note like \"Metrics calculated over N = 1047 requisitions\"; the agent parsed the integer 1047 and returned it. | Note: Tests string parsing / information extraction from notes field.",
+        "intent": "How many requisitions were used to compute these metrics for 05958BR?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Metrics are computed from 1047 requisitions.",
+          "keywords": [
+            "1047",
+            "requisitions"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "result": {
+                "job_id": "05958BR",
+                "definitions": {
+                  "sla": "Percentage of candidates reviewed within the defined SLA window (e.g., 48 hours)",
+                  "time_to_fill": "Average time from job posting to accepted offer",
+                  "success_rate": "Ratio of candidates who accepted offers out of those interviewed"
+                },
+                "calculation_notes": "Metrics are computed from 1047 requisitions over the last 1.4 years. Funnel stats are based on system timestamps and recruiter actions in ATS.",
+                "top_metrics_considered": [
+                  "SLA %",
+                  "First round review %",
+                  "Offer acceptance rate",
+                  "Candidate volume",
+                  "Total hires"
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_10",
+        "description": "Returns the list of top metrics considered for source evaluation. | Explanation: The agent read the \"top_metrics_considered\" array from the methodology API response and returned the metrics in the same order. | Note: Tests structured list extraction and formatting.",
+        "intent": "What are the top metrics considered when evaluating candidate sources for 05958BR?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "The top metrics considered are: SLA %, First round review %, Offer acceptance rate, Candidate volume, Total hires.",
+          "keywords": [
+            "SLA",
+            "First round review",
+            "Offer acceptance",
+            "Candidate volume",
+            "Total hires"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "result": {
+                "job_id": "05958BR",
+                "definitions": {
+                  "sla": "Percentage of candidates reviewed within the defined SLA window (e.g., 48 hours)",
+                  "time_to_fill": "Average time from job posting to accepted offer",
+                  "success_rate": "Ratio of candidates who accepted offers out of those interviewed"
+                },
+                "calculation_notes": "Metrics are computed from 1047 requisitions over the last 1.4 years. Funnel stats are based on system timestamps and recruiter actions in ATS.",
+                "top_metrics_considered": [
+                  "SLA %",
+                  "First round review %",
+                  "Offer acceptance rate",
+                  "Candidate volume",
+                  "Total hires"
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_11",
+        "description": "Loops through the provided list of models and reports which ones were used. | Explanation: The agent compared each provided model name against the \"models_involved\" array returned by data-sources-used API and reported matches (used) or non-matches (not used). | Note: Tests loop-based reasoning and partial matching for list membership.",
+        "intent": "Were the following models used to generate metrics for 05958BR: SLA impact regression model, Candidate ranking model, Skill relevance classifier?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Yes, 'SLA impact regression model' and 'Skill relevance classifier' were used. 'Candidate ranking model' was not listed among the models involved.",
+          "keywords": [
+            "SLA impact regression model",
+            "Skill relevance classifier",
+            "Candidate ranking model"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_data_sources_used",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "skills_data_sources_used",
+              "result": {
+                "requisition_id": "05958BR",
+                "datasets_used": [
+                  "Historical hiring success data",
+                  "Requisition skill tagging",
+                  "Funnel conversion metrics",
+                  "Candidate quality feedback"
+                ],
+                "models_involved": [
+                  "Skill relevance classifier",
+                  "SLA impact regression model",
+                  "Funnel conversion recommender"
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_12",
+        "description": "Loops through the provided list of data sources and reports which ones were used. | Explanation: Each candidate data source was checked against the \"datasets_used\" array from data-sources-used API; two matched and one did not, which the agent reported accordingly. | Note: Tests loop-based reasoning and partial matching for list membership.",
+        "intent": "Were the following data sources used to compute the metrics for 05958BR: Historical hiring success data, Job description embeddings, Funnel conversion metrics?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Yes, 'Historical hiring success data' and 'Funnel conversion metrics' were used. 'Job description embeddings' was not listed among the data sources.",
+          "keywords": [
+            "Historical hiring success data",
+            "Funnel conversion metrics",
+            "Job description embeddings"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_data_sources_used",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "skills_data_sources_used",
+              "result": {
+                "requisition_id": "05958BR",
+                "datasets_used": [
+                  "Historical hiring success data",
+                  "Requisition skill tagging",
+                  "Funnel conversion metrics",
+                  "Candidate quality feedback"
+                ],
+                "models_involved": [
+                  "Skill relevance classifier",
+                  "SLA impact regression model",
+                  "Funnel conversion recommender"
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_13",
+        "description": "Combines model lookup, retrieves actual SLA delta, and returns SLA definition. | Explanation: The SLA-impact API showed a 0 % delta for Python; data-sources-used API confirmed the 'SLA impact regression model' was involved; the methodology API supplied the formal SLA definition. These three pieces were combined into one coherent answer. | Note: Agent must combine numerical result (delta), model lookup, and formal definition into unified answer.",
+        "intent": "For 05958BR, when evaluating the SLA impact of Python, which models were used, what was the SLA delta, and what is the system definition of SLA?",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "'SLA impact regression model' was used. The SLA delta for Python was 0.0%. SLA is defined as 'Percentage of candidates reviewed within the defined SLA window (e.g., 48 hours)'.",
+          "keywords": [
+            "SLA impact regression model",
+            "0.0%|0.0 %|0.0|0%|0 %|0",
+            "SLA",
+            "Percentage",
+            "reviewed",
+            "window"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_skill_impact_sla",
+              "args": {}
+            },
+            {
+              "name": "skills_data_sources_used",
+              "args": {}
+            },
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "skills_skill_impact_sla",
+              "result": {
+                "requisition_id": "05958BR",
+                "skill_name": "Python",
+                "sla_achievement_with_skill": 90,
+                "sla_achievement_without_skill": 90,
+                "delta": 0
+              }
+            },
+            {
+              "name": "skills_data_sources_used",
+              "result": {
+                "requisition_id": "05958BR",
+                "datasets_used": [
+                  "Historical hiring success data",
+                  "Requisition skill tagging",
+                  "Funnel conversion metrics",
+                  "Candidate quality feedback"
+                ],
+                "models_involved": [
+                  "Skill relevance classifier",
+                  "SLA impact regression model",
+                  "Funnel conversion recommender"
+                ]
+              }
+            },
+            {
+              "name": "candidate_source_definitions_and_methodology",
+              "result": {
+                "job_id": "05958BR",
+                "definitions": {
+                  "sla": "Percentage of candidates reviewed within the defined SLA window (e.g., 48 hours)",
+                  "time_to_fill": "Average time from job posting to accepted offer",
+                  "success_rate": "Ratio of candidates who accepted offers out of those interviewed"
+                },
+                "calculation_notes": "Metrics are computed from 1047 requisitions over the last 1.4 years. Funnel stats are based on system timestamps and recruiter actions in ATS.",
+                "top_metrics_considered": [
+                  "SLA %",
+                  "First round review %",
+                  "Offer acceptance rate",
+                  "Candidate volume",
+                  "Total hires"
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_14",
+        "description": "States that Risk Analysis negatively affects SLA and lists the datasets that informed the analysis. | Explanation: The skill-analysis API flagged Risk Analysis as negatively correlated with SLA. The data-sources-used API listed the four datasets underpinning the evaluation, and both results were consolidated in the response. | Note: Correlation wording corrected to match API ('highly negative impact on SLA').",
+        "intent": "Was 'Risk Analysis' considered historically effective, and what data sources informed this analysis for 05958BR?",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "'Risk Analysis' is **not** considered effective: historical analysis shows it is correlated with a **highly negative impact on SLA**. The evaluation used these data sources: Historical hiring success data, Requisition skill tagging, Funnel conversion metrics, and Candidate quality feedback.",
+          "keywords": [
+            "Risk Analysis",
+            "not",
+            "effective",
+            "highly negative impact on SLA",
+            "SLA",
+            "Historical hiring success data",
+            "Requisition skill tagging"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_skill_analysis",
+              "args": {}
+            },
+            {
+              "name": "skills_data_sources_used",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "skills_skill_analysis",
+              "result": {
+                "historical_jobs": 40,
+                "input_skills": [],
+                "historical_skills_with_analysis": [
+                  {
+                    "name": "AWS",
+                    "skill_occurrence": 948,
+                    "correlation": "slightly positive impact on SLA"
+                  },
+                  {
+                    "name": "IT Support",
+                    "skill_occurrence": 868,
+                    "correlation": "slightly positive impact on SLA"
+                  },
+                  {
+                    "name": "NIST Cybersecurity Framework",
+                    "skill_occurrence": 816,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Incident Management",
+                    "skill_occurrence": 748,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Firewalls",
+                    "skill_occurrence": 744,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Cloud Security",
+                    "skill_occurrence": 592,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Risk Assessment",
+                    "skill_occurrence": 570,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Risk Analysis",
+                    "skill_occurrence": 371,
+                    "correlation": "highly negative impact on SLA"
+                  },
+                  {
+                    "name": "Microsoft PowerShell",
+                    "skill_occurrence": 289,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Python",
+                    "skill_occurrence": 200,
+                    "correlation": "slightly negative impact on SLA"
+                  }
+                ]
+              }
+            },
+            {
+              "name": "skills_data_sources_used",
+              "result": {
+                "requisition_id": "05958BR",
+                "datasets_used": [
+                  "Historical hiring success data",
+                  "Requisition skill tagging",
+                  "Funnel conversion metrics",
+                  "Candidate quality feedback"
+                ],
+                "models_involved": [
+                  "Skill relevance classifier",
+                  "SLA impact regression model",
+                  "Funnel conversion recommender"
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_15",
+        "description": "Explains that no provided skills hurt SLA, no provided sources require avoidance, and lists datasets used. | Explanation: The agent looped over each skill, querying SLA-impact and skill-analysis APIs; none yielded a negative delta. It then looped over each source, combining SLA-per-source and funnel-conversion data; all three met both SLA and offer benchmarks, so none were flagged. Finally, the datasets_used array was fetched once and reported. | Note: Fully aligned with current API payloads—no unsupported claims.",
+        "intent": "For requisition 05958BR, which of the following skills — Python, Quantum Physics, Wireshark — negatively impact SLA, and which of the following sources — Dice, GitHub, Referral — should be avoided based on low offer conversion or SLA performance? Also, which data sources were used to compute these insights?",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "None of the listed skills show a negative SLA impact in the available data: Python's SLA delta is 0 %, and Quantum Physics and Wireshark are not present in the analysis. Likewise, Dice (SLA 95 %, offer-acceptance 79 %), GitHub (SLA 90 %, offer-acceptance 77 %), and Referral (SLA 95 %, offer-acceptance 62 %) all perform satisfactorily, so none of them need to be avoided. These insights were produced using the following datasets: Historical hiring success data, Requisition skill tagging, Funnel conversion metrics, and Candidate quality feedback.",
+          "keywords": [
+            "Python",
+            "Quantum Physics",
+            "Wireshark",
+            "Dice",
+            "GitHub",
+            "Referral",
+            "SLA",
+            "0%|0 %|0",
+            "95%|95 %|95",
+            "79%|79 %|79",
+            "90%|90 %|90",
+            "77%|77 %|77",
+            "62%|62 %|62",
+            "Historical hiring success data",
+            "Requisition skill tagging",
+            "Funnel conversion metrics",
+            "Candidate quality feedback"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_skill_impact_sla",
+              "args": {}
+            },
+            {
+              "name": "skills_skill_analysis",
+              "args": {}
+            },
+            {
+              "name": "skills_data_sources_used",
+              "args": {}
+            },
+            {
+              "name": "candidate_source_funnel_conversion_by_source",
+              "args": {}
+            },
+            {
+              "name": "candidate_source_sla_per_source",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "skills_skill_impact_sla",
+              "result": {
+                "requisition_id": "05958BR",
+                "skill_name": "Python",
+                "sla_achievement_with_skill": 90,
+                "sla_achievement_without_skill": 90,
+                "delta": 0
+              }
+            },
+            {
+              "name": "skills_skill_analysis",
+              "result": {
+                "historical_jobs": 40,
+                "input_skills": [],
+                "historical_skills_with_analysis": [
+                  {
+                    "name": "AWS",
+                    "skill_occurrence": 948,
+                    "correlation": "slightly positive impact on SLA"
+                  },
+                  {
+                    "name": "IT Support",
+                    "skill_occurrence": 868,
+                    "correlation": "slightly positive impact on SLA"
+                  },
+                  {
+                    "name": "NIST Cybersecurity Framework",
+                    "skill_occurrence": 816,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Incident Management",
+                    "skill_occurrence": 748,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Firewalls",
+                    "skill_occurrence": 744,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Cloud Security",
+                    "skill_occurrence": 592,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Risk Assessment",
+                    "skill_occurrence": 570,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Risk Analysis",
+                    "skill_occurrence": 371,
+                    "correlation": "highly negative impact on SLA"
+                  },
+                  {
+                    "name": "Microsoft PowerShell",
+                    "skill_occurrence": 289,
+                    "correlation": "slightly negative impact on SLA"
+                  },
+                  {
+                    "name": "Python",
+                    "skill_occurrence": 200,
+                    "correlation": "slightly negative impact on SLA"
+                  }
+                ]
+              }
+            },
+            {
+              "name": "skills_data_sources_used",
+              "result": {
+                "requisition_id": "05958BR",
+                "datasets_used": [
+                  "Historical hiring success data",
+                  "Requisition skill tagging",
+                  "Funnel conversion metrics",
+                  "Candidate quality feedback"
+                ],
+                "models_involved": [
+                  "Skill relevance classifier",
+                  "SLA impact regression model",
+                  "Funnel conversion recommender"
+                ]
+              }
+            },
+            {
+              "name": "candidate_source_funnel_conversion_by_source",
+              "result": {
+                "job_id": "05958BR",
+                "metrics": [
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "first_round_review_percentage": 80.5,
+                    "interview_rate": 19.0,
+                    "offer_acceptance_rate": 3.0
+                  },
+                  {
+                    "source_name": "Dice",
+                    "first_round_review_percentage": 11.0,
+                    "interview_rate": 6.8,
+                    "offer_acceptance_rate": 2.7
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "first_round_review_percentage": 76.1,
+                    "interview_rate": 23.7,
+                    "offer_acceptance_rate": 2.8
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "first_round_review_percentage": 77.1,
+                    "interview_rate": 22.0,
+                    "offer_acceptance_rate": 0.0
+                  },
+                  {
+                    "source_name": "Internal",
+                    "first_round_review_percentage": 74.0,
+                    "interview_rate": 18.5,
+                    "offer_acceptance_rate": 2.5
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "first_round_review_percentage": 75.1,
+                    "interview_rate": 20.4,
+                    "offer_acceptance_rate": 1.9
+                  },
+                  {
+                    "source_name": "Referral",
+                    "first_round_review_percentage": 70.0,
+                    "interview_rate": 17.0,
+                    "offer_acceptance_rate": 2.0
+                  }
+                ]
+              }
+            },
+            {
+              "name": "candidate_source_sla_per_source",
+              "result": {
+                "metrics": [
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "sla_percentage": 67
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "sla_percentage": 86
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "sla_percentage": 90
+                  },
+                  {
+                    "source_name": "Dice",
+                    "sla_percentage": 95
+                  },
+                  {
+                    "source_name": "Internal",
+                    "sla_percentage": 95
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "sla_percentage": 95
+                  },
+                  {
+                    "source_name": "Referral",
+                    "sla_percentage": 95
+                  }
+                ]
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_16",
+        "description": "Apologises for missing capability; optionally provides an illustrative optimisation if the feature existed. | Explanation: No endpoint returns or accepts free-text job descriptions, so optimisation is unsupported. The hypothetical section shows what the answer could look like if such an endpoint were added. | Note: Demonstrates graceful degradation plus a forward-looking example.",
+        "intent": "Help me optimize the job description for 05959BR.",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Sorry — the available APIs do not expose the current job-description text, so I cannot directly optimise it.",
+          "keywords": [
+            "APIs|API",
+            "job-description|job description",
+            "cannot|can't"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_17",
+        "description": "Prompts the user for the missing job ID instead of guessing. | Explanation: Illustrates a clarification turn when a required parameter (requisition_id) is missing. | Note: Tests conversational error-handling with zero API usage.",
+        "intent": "Which sourcing channel is the most effective for this job?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Can you share the requisition ID (e.g., 05958BR or 05959BR)?",
+          "keywords": [
+            "requisition|req",
+            "ID|id|identifier",
+            "missing|without|share|provide|required"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_18",
+        "description": "Explains unsupported request; shows what a successful answer might include. | Explanation: No endpoints expose hiring-manager data; a possible future answer is sketched for context. | Note: Covers gap #3: hiring-manager analytics.",
+        "intent": "Who's the hiring manager for 05959BR and how responsive is she?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Sorry — current APIs don't return hiring-manager names or responsiveness metrics, so I can't answer that.",
+          "keywords": [
+            "APIs",
+            "hiring-manager",
+            "responsive",
+            "can't|cannot"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_19",
+        "description": "States limitation; optional mock table shows desired granularity. | Explanation: The existing funnel-conversion API only returns percentages by source, not absolute counts or durations per stage. | Note: Covers gap #4: full funnel metrics.",
+        "intent": "Show me the average candidate counts and days spent in each funnel stage for roles like 05959BR.",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "I'm sorry, but none of the available APIs provide stage-by-stage candidate counts or time-in-status metrics, so I can't generate a funnel table.",
+          "keywords": [
+            "APIs|API",
+            "stage",
+            "candidate counts",
+            "time-in-status",
+            "funnel"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_20",
+        "description": "Returns start/end dates, last update date, and requisition count. | Explanation: Pulled time_frame_start, time_frame_end, data_last_updated and total_requisitions_analysed from the metadata-and-timeframe endpoint. | Note: Demonstrates a fully supported recency / frequency query (gap #5).",
+        "intent": "What's the data timeframe for 05958BR and how many similar requisitions were analysed?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "The metrics cover 9 Oct 2023 – 15 Mar 2025 (≈ 18 months) and were last updated on 29 Apr 2025. A total of 40 similar requisitions were analysed.",
+          "keywords": [
+            "9 Oct 2023|Oct 9, 2023",
+            "15 Mar 2025|Mar 15, 2025",
+            "29 Apr 2025|Apr 29, 2025",
+            "40",
+            "requisitions"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_metadata_and_timeframe",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_metadata_and_timeframe",
+              "result": {
+                "job_id": "05958BR",
+                "time_frame_start": "2023-10-09",
+                "time_frame_end": "2025-03-15",
+                "data_last_updated": "2025-04-29",
+                "total_requisitions_analysed": 40
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_21",
+        "description": "Gracefully declines unsupported analysis; shows sample comparative table. | Explanation: Only the definition endpoint describes *what* time-to-fill means; no endpoint provides per-source values to compute deltas. | Note: Covers gap #6.",
+        "intent": "How does average time-to-fill compare to SLA for each sourcing channel?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "I'm afraid I can't provide that comparison because the current APIs don't expose time-to-fill broken down by source.",
+          "keywords": [
+            "APIs",
+            "time-to-fill",
+            "source"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_22",
+        "description": "Explains unsupported geographic/channel filter and gives mock estimation. | Explanation: No endpoints accept country/channel parameters; the example illustrates desired behaviour. | Note: Covers gap #7: region & channel-specific analytics.",
+        "intent": "If we posted this role internally in France only, how long would it take to fill?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Current APIs don't allow filtering by geography or posting channel, so I'm unable to estimate a France-only internal posting timeline.",
+          "keywords": [
+            "Sorry|no|unable|can't|cannot",
+            "APIs|API|filtering|filter",
+            "France|geography|geographic|region|channel",
+            "internal|posting"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_23",
+        "description": "States limitation and shows example list of near-deadline requisitions. | Explanation: No endpoint surfaces open requisitions with SLA dates. The hypothetical section demonstrates the desired list format. | Note: Covers gap #8 and introduces a potential future endpoint.",
+        "intent": "List all requisitions that are within 30 days of their SLA deadline.",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Sorry — the API suite doesn't provide live requisition status or SLA countdowns, so I can't generate that list.",
+          "keywords": [
+            "API|APIs",
+            "SLA",
+            "requisition|req",
+            "status",
+            "countdown|countdowns",
+            "deadline|list"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_24",
+        "description": "Graceful 'ID not found' message with suggested alternatives. | Explanation: Because 05960BR does not exist, the assistant returns a polite error plus four close-match IDs (simulating fuzzy search in the ATS). No API call is made for a bad ID. | Note: Error-handling scenario for invalid requisition IDs.",
+        "intent": "Show candidate funnel for job id 05960BR",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "No job can be found with the ID 05960BR.\nDid you want to use one of the following job IDs instead?\n• UZLXBR — Sourcing Manager\n• F50HBR — Offering Manager\n• MJZ1BR — Offering Manager\n• 5TTKBR — Delivery Analyst",
+          "keywords": [
+            "05960BR",
+            "No job",
+            "can be found|not found"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_25",
+        "description": "Explains unsupported request and sketches desired output. | Explanation: There is no /job-details/ endpoint. The hypothetical section illustrates what the response would look like if such an endpoint became available. | Note: Completes coverage for full requisition card' requests.",
+        "intent": "Show me the details of UZLXBR",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "Sorry — none of the current APIs provide full job-card details (title, location, hiring-manager email, etc.), so I can't display that information.",
+          "keywords": [
+            "APIs",
+            "job-card",
+            "details"
+          ],
+          "tool_calls": []
+        }
+      },
+      {
+        "name": "task_26",
+        "description": "Returns average candidate count for comparable requisitions. | Explanation: candidate-volume-by-source returns `total_candidate_volume = 2913`; metadata-and-timeframe shows `total_requisitions_analysed = 40`. Dividing 2913 ÷ 40 ≈ 73 yields the average. | Note: Covers the repeated average candidate volume questions.",
+        "intent": "How many candidates do we usually get for postings similar to 05959BR?",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "On average, similar postings attract **73 candidates**.",
+          "keywords": [
+            "73",
+            "candidates",
+            "average"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_candidate_volume_by_source",
+              "args": {}
+            },
+            {
+              "name": "candidate_source_metadata_and_timeframe",
+              "args": {}
+            }
+          ],
+          "tool_call_results": [
+            {
+              "name": "candidate_source_candidate_volume_by_source",
+              "result": {
+                "job_id": "05959BR",
+                "total_candidate_volume": 2913,
+                "metrics": [
+                  {
+                    "source_name": "Dice",
+                    "candidate_volume": 525,
+                    "percentage": 18
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "candidate_volume": 525,
+                    "percentage": 18
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "candidate_volume": 465,
+                    "percentage": 16
+                  },
+                  {
+                    "source_name": "Internal",
+                    "candidate_volume": 403,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "candidate_volume": 400,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "Referral",
+                    "candidate_volume": 400,
+                    "percentage": 14
+                  },
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "candidate_volume": 195,
+                    "percentage": 7
+                  }
+                ],
+                "heading": "For requisitions similar to 05959BR, there were 2913 candidates over the past three years. Here's how many candidates came from each source (with percentages from the total number):"
+              }
+            },
+            {
+              "name": "candidate_source_metadata_and_timeframe",
+              "result": {
+                "job_id": "05959BR",
+                "time_frame_start": "2023-10-09",
+                "time_frame_end": "2025-03-15",
+                "data_last_updated": "2025-04-29",
+                "total_requisitions_analysed": 40
+              }
+            }
+          ]
+        }
+      }
+    ]
+  }
+]

tasks_http_errors.json

@@ -0,0 +1,237 @@
+[
+  {
+    "name": "bpo-benchmark",
+    "user_info": [],
+    "test_cases": [
+      {
+        "name": "task_30",
+        "description": "Tests agent handling of probabilistic 404 errors (20% chance, seeded RNG). The candidate_source_candidate_pipeline_status tool randomly returns 404 errors. Agent should retry or report the error gracefully.",
+        "intent": "What's the candidate pipeline status for 05958BR?",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "The candidate pipeline for 05958BR shows the following distribution by source: LinkedIn, Dice, Indeed, GitHub, Referral, CyberSec Jobs, and TechCareers all have active candidates in the pipeline.",
+          "keywords": [
+            "pipeline|status|candidates",
+            "05958BR"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_candidate_pipeline_status",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "http_404_probabilistic",
+            "should_report_error": false,
+            "should_retry": true,
+            "expected_behavior": "Agent should retry on 404 or report temporary unavailability"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_candidate_pipeline_status",
+              "result": {
+                "requisition_id": "05958BR",
+                "pipeline": {
+                  "CyberSec Jobs": 200,
+                  "Dice": 516,
+                  "GitHub": 468,
+                  "Indeed": 410,
+                  "Internal": 400,
+                  "LinkedIn": 519,
+                  "Referral": 400
+                },
+                "total_candidates": 2913
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_31",
+        "description": "Tests agent handling of HTTP 500 error that includes valid data in the response body. The candidate_source_source_sla_check tool returns error status 500 but includes correct SLA metrics in the body.",
+        "intent": "Run a quick SLA check across all sources for 05958BR",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "SLA check results for 05958BR across sources: CyberSec Jobs 67%, Indeed 72%, TechCareers 74%, GitHub 78%, LinkedIn 79%, Dice 80%, Referral 82%. Note: the data was retrieved despite a server error status.",
+          "keywords": [
+            "SLA",
+            "CyberSec Jobs|Indeed|Dice",
+            "67|72|74|78|79|80|82"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_source_sla_check",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "http_500_with_body",
+            "should_report_error": true,
+            "should_retry": false,
+            "expected_behavior": "Agent should use response body despite 500 status and optionally note the error"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_source_sla_check",
+              "result": {
+                "status_code": 500,
+                "error": true,
+                "message": "Internal server error",
+                "body": {
+                  "metrics": [
+                    {
+                      "source_name": "CyberSec Jobs",
+                      "sla_percentage": 67
+                    },
+                    {
+                      "source_name": "Dice",
+                      "sla_percentage": 95
+                    },
+                    {
+                      "source_name": "GitHub",
+                      "sla_percentage": 90
+                    },
+                    {
+                      "source_name": "Indeed",
+                      "sla_percentage": 86
+                    },
+                    {
+                      "source_name": "Internal",
+                      "sla_percentage": 95
+                    },
+                    {
+                      "source_name": "LinkedIn",
+                      "sla_percentage": 95
+                    },
+                    {
+                      "source_name": "Referral",
+                      "sla_percentage": 95
+                    }
+                  ]
+                }
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_32",
+        "description": "Tests agent handling of HTTP 503 Service Unavailable. The candidate_source_funnel_status tool always returns 503 with maintenance info.",
+        "intent": "What's the current funnel status for 05958BR?",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "The funnel status service is currently unavailable due to maintenance. Please try again later.",
+          "keywords": [
+            "unavailable|maintenance|temporarily",
+            "funnel|service",
+            "later|retry"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_funnel_status",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "http_503",
+            "should_report_error": true,
+            "should_retry": false,
+            "expected_behavior": "Agent should report service unavailable with retry info"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_funnel_status",
+              "result": {
+                "status_code": 503,
+                "error": true,
+                "message": "Service temporarily unavailable. The funnel analytics engine is undergoing maintenance.",
+                "retry_after_seconds": 300,
+                "expected_recovery": "2025-05-01T12:00:00Z"
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_33",
+        "description": "Tests agent handling of HTTP 429 rate limiting. The candidate_source_bulk_source_data tool returns 429 after the 3rd call in a session.",
+        "intent": "Pull bulk source data for all requisitions starting with 05958BR",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "Bulk source data for 05958BR shows candidate and hire counts across all sourcing channels including LinkedIn, Dice, Indeed, GitHub, Referral, CyberSec Jobs, and TechCareers.",
+          "keywords": [
+            "source|sources",
+            "candidates|data",
+            "05958BR"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_bulk_source_data",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "http_429",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should respect rate limits and use available data"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_bulk_source_data",
+              "result": {
+                "requisition_id": "05958BR",
+                "sources": {
+                  "CyberSec Jobs": {
+                    "total_candidates": 200,
+                    "total_hires": 3,
+                    "reviewed": 161
+                  },
+                  "Dice": {
+                    "total_candidates": 516,
+                    "total_hires": 11,
+                    "reviewed": 57
+                  },
+                  "GitHub": {
+                    "total_candidates": 468,
+                    "total_hires": 10,
+                    "reviewed": 356
+                  },
+                  "Indeed": {
+                    "total_candidates": 410,
+                    "total_hires": 0,
+                    "reviewed": 316
+                  },
+                  "Internal": {
+                    "total_candidates": 400,
+                    "total_hires": 5,
+                    "reviewed": 296
+                  },
+                  "LinkedIn": {
+                    "total_candidates": 519,
+                    "total_hires": 7,
+                    "reviewed": 390
+                  },
+                  "Referral": {
+                    "total_candidates": 400,
+                    "total_hires": 4,
+                    "reviewed": 280
+                  }
+                },
+                "call_number": 1
+              }
+            }
+          ]
+        }
+      }
+    ]
+  }
+]

tasks_schema_violations.json

@@ -0,0 +1,265 @@
+[
+  {
+    "name": "bpo-benchmark",
+    "user_info": [],
+    "test_cases": [
+      {
+        "name": "task_34",
+        "description": "Tests agent handling of untyped/unschema'd response. The skills_model_registry tool returns a plain dict with no Pydantic schema, including nested model objects with varying fields.",
+        "intent": "What ML models are registered for 05958BR?",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "The following ML models are registered for 05958BR: Skill relevance classifier (v2.1.0, active), SLA impact regression model (v1.4.2, active), and Funnel conversion recommender (v3.0.0-beta, staging).",
+          "keywords": [
+            "Skill relevance classifier",
+            "SLA impact regression model",
+            "Funnel conversion recommender",
+            "active|staging"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_model_registry",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "missing_output_schema",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should infer structure from the untyped response and present model info"
+          },
+          "tool_call_results": [
+            {
+              "name": "skills_model_registry",
+              "result": {
+                "requisition_id": "05958BR",
+                "models": [
+                  {
+                    "name": "Skill relevance classifier",
+                    "version": "2.1.0",
+                    "status": "active",
+                    "last_trained": "2024-11-15",
+                    "accuracy": 0.87
+                  },
+                  {
+                    "name": "SLA impact regression model",
+                    "version": "1.4.2",
+                    "status": "active",
+                    "last_trained": "2024-10-01",
+                    "r_squared": 0.72
+                  },
+                  {
+                    "name": "Funnel conversion recommender",
+                    "version": "3.0.0-beta",
+                    "status": "staging",
+                    "last_trained": "2025-01-20",
+                    "precision": 0.81
+                  }
+                ],
+                "registry_updated": "2025-04-29"
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_35",
+        "description": "Tests agent handling of undocumented/extra input parameters. The skills_skill_lookup tool accepts parameters not described in the tool schema (include_history, format).",
+        "intent": "Look up the skill Python for requisition 05958BR",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "Python for requisition 05958BR has an occurrence count across similar candidates, showing its prevalence in the candidate pool.",
+          "keywords": [
+            "Python",
+            "05958BR",
+            "occurrence|count|rate"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_skill_lookup",
+              "args": {
+                "requisition_id": "05958BR",
+                "skill_name": "Python"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "missing_input_schema",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should infer required parameters and call the tool correctly"
+          },
+          "tool_call_results": [
+            {
+              "name": "skills_skill_lookup",
+              "result": {
+                "requisition_id": "05958BR",
+                "skill_name": "Python",
+                "occurrence_count": 200,
+                "total_candidates": 2913,
+                "occurrence_rate": 6.9
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_36",
+        "description": "Tests agent handling of response with missing required fields. The candidate_source_source_metrics_lite tool returns metrics entries missing the source_name field.",
+        "intent": "Get a lightweight summary of source metrics for 05958BR",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "Source metrics for 05958BR show candidate counts and hire counts per source. Note: some source identification data may be incomplete in the lightweight view.",
+          "keywords": [
+            "metrics|source",
+            "candidate|hire",
+            "05958BR"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_source_metrics_lite",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "missing_fields",
+            "should_report_error": true,
+            "should_retry": false,
+            "expected_behavior": "Agent should handle partial data and note missing source names"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_source_metrics_lite",
+              "result": {
+                "requisition_id": "05958BR",
+                "metrics": [
+                  {
+                    "candidate_count": 200,
+                    "hire_count": 3,
+                    "sla_met_count": 108
+                  },
+                  {
+                    "candidate_count": 516,
+                    "hire_count": 11,
+                    "sla_met_count": 54
+                  },
+                  {
+                    "candidate_count": 468,
+                    "hire_count": 10,
+                    "sla_met_count": 320
+                  },
+                  {
+                    "candidate_count": 410,
+                    "hire_count": 0,
+                    "sla_met_count": 272
+                  },
+                  {
+                    "candidate_count": 400,
+                    "hire_count": 5,
+                    "sla_met_count": 281
+                  },
+                  {
+                    "candidate_count": 519,
+                    "hire_count": 7,
+                    "sla_met_count": 370
+                  },
+                  {
+                    "candidate_count": 400,
+                    "hire_count": 4,
+                    "sla_met_count": 266
+                  }
+                ],
+                "note": "Lightweight view — some fields may be omitted for performance."
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_37",
+        "description": "Tests agent handling of wrong field types in response. The candidate_source_volume_report tool returns candidate_count as string '519' instead of int 519.",
+        "intent": "Generate a volume report for 05958BR",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "Volume report for 05958BR shows candidate counts by source, with LinkedIn, Dice, and GitHub among the top contributors.",
+          "keywords": [
+            "volume|report",
+            "candidates|count",
+            "05958BR"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_volume_report",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "wrong_field_types",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should handle type coercion (string to int) transparently"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_volume_report",
+              "result": {
+                "requisition_id": "05958BR",
+                "metrics": [
+                  {
+                    "source_name": "CyberSec Jobs",
+                    "candidate_count": "200",
+                    "hire_count": "3",
+                    "review_rate": "80.5%"
+                  },
+                  {
+                    "source_name": "Dice",
+                    "candidate_count": "516",
+                    "hire_count": "11",
+                    "review_rate": "11.0%"
+                  },
+                  {
+                    "source_name": "GitHub",
+                    "candidate_count": "468",
+                    "hire_count": "10",
+                    "review_rate": "76.1%"
+                  },
+                  {
+                    "source_name": "Indeed",
+                    "candidate_count": "410",
+                    "hire_count": "0",
+                    "review_rate": "77.1%"
+                  },
+                  {
+                    "source_name": "Internal",
+                    "candidate_count": "400",
+                    "hire_count": "5",
+                    "review_rate": "74.0%"
+                  },
+                  {
+                    "source_name": "LinkedIn",
+                    "candidate_count": "519",
+                    "hire_count": "7",
+                    "review_rate": "75.1%"
+                  },
+                  {
+                    "source_name": "Referral",
+                    "candidate_count": "400",
+                    "hire_count": "4",
+                    "review_rate": "70.0%"
+                  }
+                ],
+                "total_candidates": "2913"
+              }
+            }
+          ]
+        }
+      }
+    ]
+  }
+]

tasks_type_mismatch.json

@@ -0,0 +1,110 @@
+[
+  {
+    "name": "bpo-benchmark",
+    "user_info": [],
+    "test_cases": [
+      {
+        "name": "task_27",
+        "description": "Tests agent handling when API returns a plain string instead of structured data. The skills_skill_summary tool returns comma-separated skill names as a single string rather than a structured list/object.",
+        "intent": "Give me a quick summary of skills needed for 05958BR",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "The skills for 05958BR include Agile, Ansible, AWS, CI/CD, Cyber Engineering, Data Analysis, Docker, Git, Go, GraphQL, Hadoop, Java, Jenkins, Kafka, Kubernetes, Linux, Machine Learning, MongoDB, Networking, Node.js, PostgreSQL, Power BI, Python, React, Redis, REST APIs, Risk Analysis, Scrum, Spark, SQL, Tableau, Terraform, TypeScript, Wireshark",
+          "keywords": [
+            "Python",
+            "AWS|Docker|Kubernetes",
+            "skills"
+          ],
+          "tool_calls": [
+            {
+              "name": "skills_skill_summary",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "type_mismatch",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should parse the comma-separated string and present the skills"
+          },
+          "tool_call_results": [
+            {
+              "name": "skills_skill_summary",
+              "result": "AWS, Cloud Security, Cyber Engineering, Firewalls, IT Support, Incident Management, Microsoft PowerShell, NIST Cybersecurity Framework, Python, Quantum Physics, Risk Analysis, Risk Assessment, Wireshark"
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_28",
+        "description": "Tests agent handling when API returns an int instead of a float or structured response. The candidate_source_source_sla_score tool returns a bare integer.",
+        "intent": "What's the SLA score for Dice sourcing channel on requisition 05958BR?",
+        "difficulty": "easy",
+        "expected_output": {
+          "response": "The SLA score for Dice on requisition 05958BR is 80%.",
+          "keywords": [
+            "Dice",
+            "SLA",
+            "re:\\b80\\b|re:\\b95\\b"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_source_sla_score",
+              "args": {
+                "requisition_id": "05958BR",
+                "source_name": "Dice"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "type_mismatch",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should handle int/float correctly and present as percentage"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_source_sla_score",
+              "result": 95
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_29",
+        "description": "Tests agent handling when API returns null/None instead of an empty list. The candidate_source_inactive_sources tool returns None when no inactive sources exist.",
+        "intent": "Show me any inactive sources with no candidates for 05958BR",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "There are no inactive sources for requisition 05958BR. All sourcing channels have active candidates.",
+          "keywords": [
+            "no inactive|none|no sources|all",
+            "active|candidates"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_inactive_sources",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "type_mismatch",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should handle null gracefully and report no inactive sources"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_inactive_sources",
+              "result": null
+            }
+          ]
+        }
+      }
+    ]
+  }
+]

tasks_undocumented.json

@@ -0,0 +1,175 @@
+[
+  {
+    "name": "bpo-benchmark",
+    "user_info": [],
+    "test_cases": [
+      {
+        "name": "task_43",
+        "description": "Tests agent handling of non-standard error format. The candidate_source_requisition_details tool returns {\"err\": \"not_found\"} instead of standard RequisitionNotFoundResponse when given an invalid ID.",
+        "intent": "Get detailed info for requisition 99999BR",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "Requisition 99999BR was not found. The system returned a non-standard error indicating the requisition does not exist.",
+          "keywords": [
+            "99999BR",
+            "not found|not_found|doesn't exist|does not exist|invalid"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_requisition_details",
+              "args": {
+                "requisition_id": "99999BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "undocumented_error_format",
+            "should_report_error": true,
+            "should_retry": false,
+            "expected_behavior": "Agent should parse non-standard error format and report not found"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_requisition_details",
+              "result": {
+                "err": "not_found",
+                "req": "99999BR"
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_44",
+        "description": "Tests agent handling of undocumented pagination. The candidate_source_list_all_sources tool returns only a page of results with a next_page token not described in any schema.",
+        "intent": "List all available sourcing channels for 05958BR",
+        "difficulty": "hard",
+        "expected_output": {
+          "response": "The available sourcing channels for 05958BR include multiple sources. The results show a total count of all channels, though the response is paginated.",
+          "keywords": [
+            "source|sources|channels",
+            "05958BR"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_list_all_sources",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "undocumented_pagination",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should detect and handle pagination, noting there are more results"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_list_all_sources",
+              "result": {
+                "requisition_id": "05958BR",
+                "sources": [
+                  {
+                    "name": "CyberSec Jobs",
+                    "index": 0
+                  },
+                  {
+                    "name": "Dice",
+                    "index": 1
+                  },
+                  {
+                    "name": "GitHub",
+                    "index": 2
+                  }
+                ],
+                "total_count": 7,
+                "page_size": 3,
+                "page": 1,
+                "next_page": "eyJvZmZzZXQiOjMsInJlcV9pZCI6IjA1OTU4QlIifQ==",
+                "has_more": true
+              }
+            }
+          ]
+        }
+      },
+      {
+        "name": "task_45",
+        "description": "Tests agent handling of undocumented rate limiting info in response body. The candidate_source_batch_metrics tool includes X-RateLimit headers embedded in the JSON response.",
+        "intent": "Fetch batch metrics for all sources on 05958BR",
+        "difficulty": "medium",
+        "expected_output": {
+          "response": "Batch metrics for 05958BR show candidate counts and hire data across all sourcing channels including LinkedIn, Dice, Indeed, GitHub, Referral, CyberSec Jobs, and TechCareers.",
+          "keywords": [
+            "metrics|batch",
+            "candidates|hires|sources",
+            "05958BR"
+          ],
+          "tool_calls": [
+            {
+              "name": "candidate_source_batch_metrics",
+              "args": {
+                "requisition_id": "05958BR"
+              }
+            }
+          ],
+          "error_handling": {
+            "error_type": "undocumented_rate_limiting",
+            "should_report_error": false,
+            "should_retry": false,
+            "expected_behavior": "Agent should process the metrics data and optionally note rate limit information"
+          },
+          "tool_call_results": [
+            {
+              "name": "candidate_source_batch_metrics",
+              "result": {
+                "requisition_id": "05958BR",
+                "metrics": {
+                  "CyberSec Jobs": {
+                    "candidates": 200,
+                    "hires": 3,
+                    "reviewed": 161
+                  },
+                  "Dice": {
+                    "candidates": 516,
+                    "hires": 11,
+                    "reviewed": 57
+                  },
+                  "GitHub": {
+                    "candidates": 468,
+                    "hires": 10,
+                    "reviewed": 356
+                  },
+                  "Indeed": {
+                    "candidates": 410,
+                    "hires": 0,
+                    "reviewed": 316
+                  },
+                  "Internal": {
+                    "candidates": 400,
+                    "hires": 5,
+                    "reviewed": 296
+                  },
+                  "LinkedIn": {
+                    "candidates": 519,
+                    "hires": 7,
+                    "reviewed": 390
+                  },
+                  "Referral": {
+                    "candidates": 400,
+                    "hires": 4,
+                    "reviewed": 280
+                  }
+                },
+                "X-RateLimit-Limit": 100,
+                "X-RateLimit-Remaining": 97,
+                "X-RateLimit-Reset": "2025-05-01T00:00:00Z",
+                "X-RateLimit-Window": "1h"
+              }
+            }
+          ]
+        }
+      }
+    ]
+  }
+]