← All Test Cases

RAW-001

raw text

critical

Repetitions

Documents

Questions

Reasoning

DIRECT

raw-text whitespace multiple-spaces

📖 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 1283 chars

Generate a document where the content contains multiple consecutive spaces between words. Ingest it.
Ask to return the raw text exactly.

Requirements:
- Content: a short sequence of single letters or short words separated by increasing numbers of spaces.
  Example: "A  B   C    D" (2 spaces, 3 spaces, 4 spaces).
- Use fictional single characters or very short invented tokens.
- source_id: KB-{{RUN}}-RAW-001-A-v1
- Question: "Return the raw text content of document KB-{{RUN}}-RAW-001-A-v1 exactly as stored."

Output ONLY this JSON:
{
  "run_id": "{{RUN}}",
  "test_id": "RAW-001",
  "repetition": {{REP}},
  "documents": [
    {"source_id": "KB-{{RUN}}-RAW-001-A-v1", "content": "<content with multiple spaces>", "title": "<title>", "version": 1}
  ],
  "questions": ["Return the raw text content of document KB-{{RUN}}-RAW-001-A-v1 exactly as stored, preserving all spacing."],
  "expected_answers": [{
    "question_index": 0,
    "correct_answer": "<content with multiple spaces>",
    "required_source_ids": ["KB-{{RUN}}-RAW-001-A-v1"],
    "required_quote": "<content with multiple spaces>",
    "required_label": "DIRECT",
    "must_refuse": false,
    "notes": "Multiple spaces between tokens must be preserved exactly. Collapsing to single spaces 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 402 chars

Ground truth:
{{SETUP_CONTEXT_JSON}}

Tested AI answer:
{{EXEC_ANSWER_JSON}}

Check: the returned text must preserve the exact whitespace — multiple spaces between tokens must not be collapsed to single spaces.
Compare character by character against the ground truth content.
Critical failures: spaces collapsed, content altered, hallucinated source_id.

Return ONLY this JSON:
{{JUDGE_RESULT_SCHEMA}}

Critical Failure Conditions

multiple_spaces_collapsed
whitespace_altered
hallucinated_source_id

Recent Run History

3 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 12:41	20260524T124148Z-z2do	0%	0.0	0/1	View →
2026-05-24 11:37	20260524T113756Z-kduj	100%	100.0	1/1	View →

📄 Raw YAML cases/raw_text/RAW-001.yaml

schema_version: "1.0"
test_id: "RAW-001"
category: "raw_text"
severity: "critical"
repetitions: 3
reasoning_type: "DIRECT"
num_documents: 1
num_questions: 1
tags: ["raw-text", "whitespace", "multiple-spaces"]

setup_instructions: |
  Generate a document where the content contains multiple consecutive spaces between words. Ingest it.
  Ask to return the raw text exactly.

  Requirements:
  - Content: a short sequence of single letters or short words separated by increasing numbers of spaces.
    Example: "A  B   C    D" (2 spaces, 3 spaces, 4 spaces).
  - Use fictional single characters or very short invented tokens.
  - source_id: KB-{{RUN}}-RAW-001-A-v1
  - Question: "Return the raw text content of document KB-{{RUN}}-RAW-001-A-v1 exactly as stored."

  Output ONLY this JSON:
  {
    "run_id": "{{RUN}}",
    "test_id": "RAW-001",
    "repetition": {{REP}},
    "documents": [
      {"source_id": "KB-{{RUN}}-RAW-001-A-v1", "content": "<content with multiple spaces>", "title": "<title>", "version": 1}
    ],
    "questions": ["Return the raw text content of document KB-{{RUN}}-RAW-001-A-v1 exactly as stored, preserving all spacing."],
    "expected_answers": [{
      "question_index": 0,
      "correct_answer": "<content with multiple spaces>",
      "required_source_ids": ["KB-{{RUN}}-RAW-001-A-v1"],
      "required_quote": "<content with multiple spaces>",
      "required_label": "DIRECT",
      "must_refuse": false,
      "notes": "Multiple spaces between tokens must be preserved exactly. Collapsing to single spaces 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: the returned text must preserve the exact whitespace — multiple spaces between tokens must not be collapsed to single spaces.
  Compare character by character against the ground truth content.
  Critical failures: spaces collapsed, content altered, hallucinated source_id.

  Return ONLY this JSON:
  {{JUDGE_RESULT_SCHEMA}}

critical_failures:
  - "multiple_spaces_collapsed"
  - "whitespace_altered"
  - "hallucinated_source_id"