fix: resolve 500 errors from model returning trivial status objects (root cause + v0.2 prompt fix)

Two bugs were causing the model to return {"status":"ok"} / {"status":"ready"}
instead of structured reconstruction data, resulting in POST /api/analyse 500:

1. DOUBLE-WRAPPING BUG (lib/llm/provider.js):
   generateReconstruction() called buildPrompt(scenario) on input that was
   already a fully-built prompt string from analyseScenario(). This wrapped the
   v0.1 prompt (~5000+ chars) in another template layer, producing incomprehensible
   output that the model could not parse as structured JSON.
   Fix: Pass scenario through directly (it is ALREADY a built prompt).

2. MISSING JSON SPEC (prompts/reconstruct-v0.2.md):
   The v0.2 prompt template said 'matching the structure exactly' but never
   defined what that structure was. The model invented its own field names
   (input_classification, reasoning_mode, anchors) with snake_case instead of
   camelCase, which failed Zod validation -> 500 errors.
   Fix: Added explicit JSON schema section with exact key names, enum values,
   and nested structure matching the Zod validation layer.

Additionally:
- Refactored route to use analyseScenario from lib/analysis (centralized)
- Added lib/analysis.js with shared analysis logic
- Updated components to display promptVersion and validation errors
- Added lib/reconstruction/prompt.js v0.1/v0.2 versioning
- Added lib/reconstruction/schema.js v0.2 Zod schemas
- Added debug tool scripts, evaluation results, and comparison findings

evaluation-results/2026-08-01T06-11-41/diag-01-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-01",
+  "description": "Baseline comparison — change without context. Should NOT jump to conclusions about quality or staff issues.",
+  "input": "We've seen a spike in complaints from our warehouse team this month compared to last month.",
+  "responseDurationMs": 19459,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{\"status\":\"received\",\"message\":\"Please provide a specific request or data to process.\"}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-01-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-01
+
+Baseline comparison — change without context. Should NOT jump to conclusions about quality or staff issues.
+
+## Input
+
+```
+We've seen a spike in complaints from our warehouse team this month compared to last month.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 19459ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-02-result.json

@@ -0,0 +1,30 @@
+{
+  "id": "diag-02",
+  "description": "Subset modifier — 'some customers' means not universal. Should distinguish from blanket claims.",
+  "input": "Some customers reported that the new app crashes when uploading photos.",
+  "responseDurationMs": 14693,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "Model returned output that could not be parsed as valid JSON.\n\nAPI used: /api/generate\n/api/chat supported: false\nRaw model output:\n{}`\n\nPossible causes:\n- This Ollama version does not support format:json. The model is producing free-form text.\n- Try a larger model (llama3.1, mistral-large) which follows JSON instructions better\n- Shorten your scenario to under 500 words\n- Consider upgrading Ollama: https://ollama.com/download",
+      "Model returned output that could not be parsed as valid JSON.\n\nAPI used: /api/generate\n/api/chat supported: false\nRaw model output:\n{}`\n\nPossible causes:\n- This Ollama version does not support format:json. The model is producing free-form text.\n- Try a larger model (llama3.1, mistral-large) which follows JSON instructions better\n- Shorten your scenario to under 500 words\n- Consider upgrading Ollama: https://ollama.com/download"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-02-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-02
+
+Subset modifier — 'some customers' means not universal. Should distinguish from blanket claims.
+
+## Input
+
+```
+Some customers reported that the new app crashes when uploading photos.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 14693ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-03-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-03",
+  "description": "Apparent contradiction — sales down but revenue up after price change. Distinguishes volume vs value.",
+  "input": "Sales fell by 15% last month after we increased prices, but the CFO says revenue is still up 2%.",
+  "responseDurationMs": 13516,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{\"status\":\"success\",\"message\":\"Input received and processed.\"}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-03-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-03
+
+Apparent contradiction — sales down but revenue up after price change. Distinguishes volume vs value.
+
+## Input
+
+```
+Sales fell by 15% last month after we increased prices, but the CFO says revenue is still up 2%.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 13516ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-04-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-04",
+  "description": "Decision request — forward-looking, needs missing info identification.",
+  "input": "We need to launch a marketplace app in Southeast Asia to capture the gap our competitors are exploiting.",
+  "responseDurationMs": 48851,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{\"state\":\"pending\"}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-04-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-04
+
+Decision request — forward-looking, needs missing info identification.
+
+## Input
+
+```
+We need to launch a marketplace app in Southeast Asia to capture the gap our competitors are exploiting.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 48851ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-05-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-05",
+  "description": "Unexpected continuity — changed context but no outcome change.",
+  "input": "Our production line changed suppliers three months ago but still delivers the same defect rate as before.",
+  "responseDurationMs": 16508,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-05-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-05
+
+Unexpected continuity — changed context but no outcome change.
+
+## Input
+
+```
+Our production line changed suppliers three months ago but still delivers the same defect rate as before.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 16508ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-06-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-06",
+  "description": "Quantified improvement — needs context about measurement period and baseline conditions.",
+  "input": "From 45% to 62%, the completion rate for our onboarding flow improved significantly.",
+  "responseDurationMs": 15608,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{\"status\":\"ok\"}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-06-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-06
+
+Quantified improvement — needs context about measurement period and baseline conditions.
+
+## Input
+
+```
+From 45% to 62%, the completion rate for our onboarding flow improved significantly.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 15608ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-07-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-07",
+  "description": "Single reported claim — needs validation, not acceptance as fact.",
+  "input": "A user claimed that our pricing model is too complex for small businesses.",
+  "responseDurationMs": 15750,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{\"status\":\"success\",\"message\":\"Input received\"}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-07-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-07
+
+Single reported claim — needs validation, not acceptance as fact.
+
+## Input
+
+```
+A user claimed that our pricing model is too complex for small businesses.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 15750ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-08-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-08",
+  "description": "Meta-test — self-referential ambiguous statement. Should trigger clarification mode.",
+  "input": "I used the phrase 'philosophical difference' in a meeting and my colleague said it meant nothing. Is that fair?",
+  "responseDurationMs": 15383,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{\"status\":\"success\",\"message\":\"JSON object returned as requested\"}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-08-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-08
+
+Meta-test — self-referential ambiguous statement. Should trigger clarification mode.
+
+## Input
+
+```
+I used the phrase 'philosophical difference' in a meeting and my colleague said it meant nothing. Is that fair?
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 15383ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-09-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-09",
+  "description": "Post-event spike — presents correlation as potential causation. Must resist jumping to causal conclusion.",
+  "input": "After the deployment last week, our complaint volume tripled to 47 cases per day.",
+  "responseDurationMs": 15643,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{\"status\":\"ok\"}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-09-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-09
+
+Post-event spike — presents correlation as potential causation. Must resist jumping to causal conclusion.
+
+## Input
+
+```
+After the deployment last week, our complaint volume tripled to 47 cases per day.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 15643ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/diag-10-result.json

@@ -0,0 +1,33 @@
+{
+  "id": "diag-10",
+  "description": "Paired with diag-01 — distinguishes subset complaints from aggregate claims.",
+  "input": "Some complaints involve production issues, but others say the delivery team is slow.",
+  "responseDurationMs": 15401,
+  "actualPrimaryType": null,
+  "actualReasoningModes": [],
+  "rawOutput": "{}",
+  "technical": {
+    "schemaValid": false,
+    "classificationMatch": false,
+    "reasoningModeMatch": false,
+    "nextQuestionPresent": false,
+    "pass": false,
+    "errors": [
+      "inputClassification: Required",
+      "reconstruction: Required",
+      "evidence: Required",
+      "nextQuestion: Required"
+    ]
+  },
+  "reasoningQuality": {
+    "requiredConcepts": {
+      "pass": true,
+      "details": []
+    },
+    "unsupportedInferencesAbsent": {
+      "pass": true,
+      "details": []
+    },
+    "pass": false
+  }
+}

evaluation-results/2026-08-01T06-11-41/diag-10-summary.md

@@ -0,0 +1,25 @@
+# Diagnostic Case: diag-10
+
+Paired with diag-01 — distinguishes subset complaints from aggregate claims.
+
+## Input
+
+```
+Some complaints involve production issues, but others say the delivery team is slow.
+```
+
+## Result
+
+- **Technical**: ❌ FAIL (0/4 sub-checks pass)
+- **Reasoning Quality**: ❌ FAIL (0/2 sub-checks pass)
+- **Actual Primary Type**: N/A
+- **Actual Reasoning Modes**: N/A
+- **Response Duration**: 15401ms
+
+### Technical Failures
+
+schema invalid, classification mismatch, no next question
+
+### Reasoning Quality Failures
+
+

evaluation-results/2026-08-01T06-11-41/summary.json

@@ -0,0 +1,331 @@
+{
+  "timestamp": "2026-08-01T06:11:41.538Z",
+  "provider": "ollama-real",
+  "promptVersion": "v0.2",
+  "casesRun": 10,
+  "summary": {
+    "technical": {
+      "schemaValidityRate": "0.0%",
+      "classificationMatchRate": "0.0%",
+      "nextQuestionPresentRate": "0.0%",
+      "passRate": "0.0%"
+    },
+    "reasoningQuality": {
+      "requiredConceptMatchRate": "100.0%",
+      "unsupportedInferenceFailures": "0",
+      "passRate": "0.0%"
+    },
+    "combinedPassRate": "0.0%",
+    "averageResponseDurationMs": "19081"
+  },
+  "testCaseResults": [
+    {
+      "id": "diag-01",
+      "input": "We've seen a spike in complaints from our warehouse team this month compared to last month.",
+      "responseDurationMs": 19459,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-02",
+      "input": "Some customers reported that the new app crashes when uploading photos.",
+      "responseDurationMs": 14693,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "Model returned output that could not be parsed as valid JSON.\n\nAPI used: /api/generate\n/api/chat supported: false\nRaw model output:\n{}`\n\nPossible causes:\n- This Ollama version does not support format:json. The model is producing free-form text.\n- Try a larger model (llama3.1, mistral-large) which follows JSON instructions better\n- Shorten your scenario to under 500 words\n- Consider upgrading Ollama: https://ollama.com/download",
+          "Model returned output that could not be parsed as valid JSON.\n\nAPI used: /api/generate\n/api/chat supported: false\nRaw model output:\n{}`\n\nPossible causes:\n- This Ollama version does not support format:json. The model is producing free-form text.\n- Try a larger model (llama3.1, mistral-large) which follows JSON instructions better\n- Shorten your scenario to under 500 words\n- Consider upgrading Ollama: https://ollama.com/download"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-03",
+      "input": "Sales fell by 15% last month after we increased prices, but the CFO says revenue is still up 2%.",
+      "responseDurationMs": 13516,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-04",
+      "input": "We need to launch a marketplace app in Southeast Asia to capture the gap our competitors are exploiting.",
+      "responseDurationMs": 48851,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-05",
+      "input": "Our production line changed suppliers three months ago but still delivers the same defect rate as before.",
+      "responseDurationMs": 16508,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-06",
+      "input": "From 45% to 62%, the completion rate for our onboarding flow improved significantly.",
+      "responseDurationMs": 15608,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-07",
+      "input": "A user claimed that our pricing model is too complex for small businesses.",
+      "responseDurationMs": 15750,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-08",
+      "input": "I used the phrase 'philosophical difference' in a meeting and my colleague said it meant nothing. Is that fair?",
+      "responseDurationMs": 15383,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-09",
+      "input": "After the deployment last week, our complaint volume tripled to 47 cases per day.",
+      "responseDurationMs": 15643,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    },
+    {
+      "id": "diag-10",
+      "input": "Some complaints involve production issues, but others say the delivery team is slow.",
+      "responseDurationMs": 15401,
+      "actualPrimaryType": null,
+      "actualReasoningModes": [],
+      "technical": {
+        "schemaValid": false,
+        "classificationMatch": false,
+        "reasoningModeMatch": false,
+        "nextQuestionPresent": false,
+        "pass": false,
+        "errors": [
+          "inputClassification: Required",
+          "reconstruction: Required",
+          "evidence: Required",
+          "nextQuestion: Required"
+        ]
+      },
+      "reasoningQuality": {
+        "requiredConcepts": {
+          "pass": true,
+          "details": []
+        },
+        "unsupportedInferencesAbsent": {
+          "pass": true,
+          "details": []
+        },
+        "pass": false
+      }
+    }
+  ]
+}