← All Test Cases

RAW-002

raw text

critical

Repetitions

Documents

Questions

Reasoning

DIRECT

raw-text blank-line newlines

📖 In Plain English

What this category tests

Are special characters preserved through ingest and retrieval?

How the test works

Documents contain tabs, Unicode, JSON snippets, literal newlines, and other tricky text. The test checks every character round-trips intact.

Why it matters

Knowledge often contains structured fragments (code, JSON, formulas) that must survive the brain's normalization.

⚙️ How a single rep runs

① Generate

Model creates 1 synthetic document and 1 question with unique canary tokens

→ Fresh content per run prevents memorization and proves real retrieval

② Ingest (MCP)

Model calls brain_ingest to store the 1 document

→ Tests the brain's storage and indexing pipeline

③ Query (MCP)

Model answers the question using brain retrieval tools (search, fetch, context_pack, etc.)

→ Core test — does the brain return correct evidence and let the model build a faithful answer?

④ Evaluate

Model judges the answer against ground truth (the document it generated in phase 1)

→ Produces a score 0–100 with detailed sub-scores (retrieval, fidelity, reasoning, etc.)

This rep is run 3 times per test run. A pass requires score ≥ 85 and no critical failures.

🔬 Technical Instructions (raw prompts sent to AI)

🔧 ① Setup Instructions 1162 chars

Generate a document with a blank line between two text lines. Ingest it.
Ask to return the raw document exactly.

Requirements:
- Content: "First line.\n\nThird line after blank." (two newlines = blank line between)
- Use fictional short sentences.
- source_id: KB-{{RUN}}-RAW-002-A-v1
- Question: "Return the raw content of document KB-{{RUN}}-RAW-002-A-v1 exactly, including blank lines."

Output ONLY this JSON:
{
  "run_id": "{{RUN}}",
  "test_id": "RAW-002",
  "repetition": {{REP}},
  "documents": [
    {"source_id": "KB-{{RUN}}-RAW-002-A-v1", "content": "<first line>.\n\n<third line>.", "title": "<title>", "version": 1}
  ],
  "questions": ["Return the raw content of document KB-{{RUN}}-RAW-002-A-v1 exactly, including any blank lines."],
  "expected_answers": [{
    "question_index": 0,
    "correct_answer": "<first line>.\n\n<third line>.",
    "required_source_ids": ["KB-{{RUN}}-RAW-002-A-v1"],
    "required_quote": "<first line>.\n\n<third line>.",
    "required_label": "DIRECT",
    "must_refuse": false,
    "notes": "The blank line (double newline) must be preserved. Merging into one line or removing the blank line is a failure."
  }]
}

▶ ② Execution Instructions 119 chars

Use ONLY MCP Knowledge Brain retrieval tools.
Question: {{QUESTION}}
Return ONLY this JSON:
{{REQUIRED_ANSWER_SCHEMA}}

⚖ ③ Judge Instructions 363 chars

Ground truth:
{{SETUP_CONTEXT_JSON}}

Tested AI answer:
{{EXEC_ANSWER_JSON}}

Check: both lines present and blank line between them preserved. If the two lines are merged or the blank line removed, that is a failure.
Critical failures: blank line lost, lines merged, only one line returned, hallucinated source_id.

Return ONLY this JSON:
{{JUDGE_RESULT_SCHEMA}}

Critical Failure Conditions

blank_line_lost
lines_merged
hallucinated_source_id

Recent Run History

2 runs

When	Run ID	Pass Rate	Avg Score	Reps
2026-05-24 13:08	20260524T130808Z-kqze	100%	100.0	1/1	View →
2026-05-24 11:37	20260524T113756Z-kduj	100%	100.0	1/1	View →

📄 Raw YAML cases/raw_text/RAW-002.yaml

schema_version: "1.0"
test_id: "RAW-002"
category: "raw_text"
severity: "critical"
repetitions: 3
reasoning_type: "DIRECT"
num_documents: 1
num_questions: 1
tags: ["raw-text", "blank-line", "newlines"]

setup_instructions: |
  Generate a document with a blank line between two text lines. Ingest it.
  Ask to return the raw document exactly.

  Requirements:
  - Content: "First line.\n\nThird line after blank." (two newlines = blank line between)
  - Use fictional short sentences.
  - source_id: KB-{{RUN}}-RAW-002-A-v1
  - Question: "Return the raw content of document KB-{{RUN}}-RAW-002-A-v1 exactly, including blank lines."

  Output ONLY this JSON:
  {
    "run_id": "{{RUN}}",
    "test_id": "RAW-002",
    "repetition": {{REP}},
    "documents": [
      {"source_id": "KB-{{RUN}}-RAW-002-A-v1", "content": "<first line>.\n\n<third line>.", "title": "<title>", "version": 1}
    ],
    "questions": ["Return the raw content of document KB-{{RUN}}-RAW-002-A-v1 exactly, including any blank lines."],
    "expected_answers": [{
      "question_index": 0,
      "correct_answer": "<first line>.\n\n<third line>.",
      "required_source_ids": ["KB-{{RUN}}-RAW-002-A-v1"],
      "required_quote": "<first line>.\n\n<third line>.",
      "required_label": "DIRECT",
      "must_refuse": false,
      "notes": "The blank line (double newline) must be preserved. Merging into one line or removing the blank line is a failure."
    }]
  }

execution_instructions: |
  Use ONLY MCP Knowledge Brain retrieval tools.
  Question: {{QUESTION}}
  Return ONLY this JSON:
  {{REQUIRED_ANSWER_SCHEMA}}

judge_instructions: |
  Ground truth:
  {{SETUP_CONTEXT_JSON}}

  Tested AI answer:
  {{EXEC_ANSWER_JSON}}

  Check: both lines present and blank line between them preserved. If the two lines are merged or the blank line removed, that is a failure.
  Critical failures: blank line lost, lines merged, only one line returned, hallucinated source_id.

  Return ONLY this JSON:
  {{JUDGE_RESULT_SCHEMA}}

critical_failures:
  - "blank_line_lost"
  - "lines_merged"
  - "hallucinated_source_id"