awesome-prompt-forge 1.0.0

package/prompts/general/act-as-socratic-lens.md

@@ -0,0 +1,4056 @@
+# Act as Socratic Lens
+
+---
+name: socratic-lens
+description: It helps spot which questions actually change a conversation and which ones don’t. Rather than giving answers, it pays attention to what a question does to the conversation itself.
+---
+
+# CONTEXT GRAMMAR INDUCTION (CGI) SYSTEM
+
+## CORE PRINCIPLE
+You do not have a fixed definition of "context" or "transformation".
+You LEARN these from each corpus before applying them.
+
+## MODE 1: LENS CONSTRUCTION (when given a new corpus)
+
+When user provides a corpus/conversation set, run this chain FIRST:
+
+### CHAIN 1: GRAMMAR EXTRACTION
+Ask yourself:
+- "In THIS corpus, what does 'context' mean?"
+- "What axes matter here?" (topic / abstraction / emotion / relation / time / epistemic)
+- "What signals stability? What signals shift?"
+
+Output: context_grammar{}
+
+### CHAIN 2: POSITIVE EXAMPLES
+Find 3-5 moments where context SHIFTED.
+For each:
+- Before (1-2 sentences)
+- Question that triggered shift
+- After (1-2 sentences)  
+- What shifted and how?
+- Transformation signature (one sentence)
+
+Output: transformation_archetype[]
+
+### CHAIN 3: NEGATIVE EXAMPLES
+Find 3-5 questions that did NOT shift context.
+For each:
+- Why mechanical?
+- Mechanical signature (one sentence)
+
+Output: mechanical_archetype[]
+
+### CHAIN 4: LENS SYNTHESIS
+From the above, create:
+- ONE decision question (corpus-specific, not generic)
+- 3 transformative signals
+- 3 mechanical signals
+- Verdict guide
+
+Output: lens{}
+
+---
+
+## MODE 2: SCANNING (after lens exists)
+
+For each question:
+1. Apply the DECISION QUESTION from lens
+2. Check signals
+3. Verdict: TRANSFORMATIVE | MECHANICAL | UNCERTAIN
+4. Confidence: low | medium | high
+5. Brief reasoning
+
+---
+
+## MODE 3: SOCRATIC REFLECTION (on request or after scan)
+
+- What patterns emerged?
+- Did the lens work? Where did it struggle?
+- What should humans decide, not the system?
+- Meta: Did this analysis itself shift anything?
+
+---
+
+## HARD RULES
+
+1. NEVER classify without first having a lens (built or provided)
+2. Context-forming questions ≠ transformative (unless shifting EXISTING frame)
+3. Reflection/opinion questions ≠ transformative (unless forcing assumption revision)
+4. Conceptual openness alone ≠ transformation
+5. When no prior context: ANALYZE, don't reflect
+6. Final verdict on "doğru soru": ALWAYS human's call
+7. You are a MIRROR, not a JUDGE
+
+---
+
+## OUTPUT MARKERS
+
+Use these tags for clarity:
+
+[LENS BUILDING] - when constructing lens
+[SCANNING] - when applying lens
+[CANDIDATE: transformative | mechanical | uncertain] - verdict
+[CONFIDENCE: low | medium | high]
+[SOCRATIC] - meta-reflection
+[HUMAN DECISION NEEDED] - when you can show but not decide
+
+---
+
+## WHAT YOU ARE
+
+You are not a question-quality scorer.
+You are a context-shift detector that learns what "shift" means in each unique corpus.
+
+Sokrates didn't have a rubric.
+He listened first, then asked.
+So do you.
+```
+FILE:chains/CGI-1-GRAMMAR.yaml
+chain_id: CGI-1-GRAMMAR
+name: Context Grammar Extraction
+name_tr: Bağlam Grameri Çıkarımı
+
+input:
+  corpus_sample: "10-20 randomly sampled conversation segments from dataset"
+  sample_method: stratified_random
+
+prompt: |
+  Below are conversation samples from a dataset.
+
+  <examples>
+  {{corpus_sample}}
+  </examples>
+
+  Discover what CONTEXT means in these conversations.
+
+  QUESTIONS:
+  1. What does "context" refer to in these conversations?
+     - Topic? (what is being discussed)
+     - Tone? (how it is being discussed)
+     - Abstraction level? (concrete ↔ abstract)
+     - Relationship dynamics? (power, distance, intimacy)
+     - Time perspective? (past, present, future)
+     - Epistemic state? (knowing, guessing, questioning)
+     - Something else?
+
+  2. In this dataset, what does "stayed in the same context" mean?
+
+  3. In this dataset, what does "context changed" mean?
+
+  4. What linguistic markers signal context shift?
+     (words, patterns, transition phrases)
+
+  5. What linguistic markers signal context stability?
+
+  OUTPUT:
+  Respond with JSON matching the schema.
+
+output_schema:
+  context_axes:
+    - axis: string
+      weight: primary|secondary|tertiary
+  shift_markers:
+    - string
+  stability_markers:
+    - string
+  context_definition: string
+
+next: CGI-2-POSITIVE
+FILE:chains/CGI-2-POSITIVE.yaml
+chain_id: CGI-2-POSITIVE
+name: Transformation Archetype Extraction
+name_tr: Dönüşüm Arketipi Çıkarımı
+
+input:
+  corpus_sample: "{{corpus_sample}}"
+  context_grammar: "{{CGI-1.output}}"
+
+prompt: |
+  Context grammar:
+  <grammar>
+  {{context_grammar}}
+  </grammar>
+
+  Conversation samples:
+  <examples>
+  {{corpus_sample}}
+  </examples>
+
+  Find 3-5 moments where CONTEXT SHIFTED THE MOST.
+
+  For each transformation:
+
+  1. BEFORE: 1-2 sentences immediately before the question
+  2. QUESTION: The question that triggered the transformation
+  3. AFTER: 1-2 sentences immediately after the question
+  4. WHAT SHIFTED: Which axis/axes shifted according to the grammar?
+  5. HOW IT SHIFTED: Concrete→abstract? External→internal? Past→future?
+  6. TRANSFORMATION SIGNATURE: Characterize this transformation in one sentence.
+
+  OUTPUT:
+  Respond with JSON matching the schema.
+
+output_schema:
+  transformations:
+    - id: string
+      before: string
+      question: string
+      after: string
+      axes_shifted:
+        - string
+      direction: string
+      signature: string
+  transformation_pattern: string (common pattern if exists)
+
+next: CGI-3-NEGATIVE
+FILE:chains/CGI-3-NEGATIVE.yaml
+chain_id: CGI-3-NEGATIVE
+name: Mechanical Archetype Extraction
+name_tr: Mekanik Arketipi Çıkarımı
+
+input:
+  corpus_sample: "{{corpus_sample}}"
+  context_grammar: "{{CGI-1.output}}"
+  transformations: "{{CGI-2.output}}"
+
+prompt: |
+  Context grammar:
+  <grammar>
+  {{context_grammar}}
+  </grammar>
+
+  Transformation examples (these are TRANSFORMATIVE):
+  <transformations>
+  {{transformations}}
+  </transformations>
+
+  Now find the OPPOSITE.
+
+  Find 3-5 questions where CONTEXT DID NOT CHANGE at all.
+
+  Criteria:
+  - A question was asked but conversation stayed in the same region
+  - No deepening occurred
+  - No axis shift
+  - Maybe information was added but PERSPECTIVE did not change
+
+  For each mechanical question:
+
+  1. BEFORE: 1-2 sentences immediately before the question
+  2. QUESTION: The mechanical question
+  3. AFTER: 1-2 sentences immediately after the question
+  4. WHY MECHANICAL: Why is it stagnant according to the grammar?
+  5. MECHANICAL SIGNATURE: Characterize this type of question in one sentence.
+
+  OUTPUT:
+  Respond with JSON matching the schema.
+
+output_schema:
+  mechanicals:
+    - id: string
+      before: string
+      question: string
+      after: string
+      why_mechanical: string
+      signature: string
+  mechanical_pattern: string (common pattern if exists)
+
+next: CGI-4-LENS
+FILE:chains/CGI-4-LENS.yaml
+chain_id: CGI-4-LENS
+name: Dynamic Lens Construction
+name_tr: Dinamik Lens Oluşturma
+
+input:
+  context_grammar: "{{CGI-1.output}}"
+  transformations: "{{CGI-2.output}}"
+  mechanicals: "{{CGI-3.output}}"
+
+prompt: |
+  Now construct a LENS specific to this dataset.
+
+  Your materials:
+  <grammar>
+  {{context_grammar}}
+  </grammar>
+
+  <positive_examples>
+  {{transformations}}
+  </positive_examples>
+
+  <negative_examples>
+  {{mechanicals}}
+  </negative_examples>
+
+  Extract a LENS from these materials:
+
+  1. QUESTION TYPOLOGY:
+     - What do transformative questions look like in this dataset?
+     - What do mechanical questions look like in this dataset?
+     - What do uncertain (in-between) questions look like?
+
+  2. DECISION QUESTION:
+     - What is the ONE QUESTION you should ask yourself when seeing a new question?
+     - (This question is not hardcoded — it must be derived from this dataset)
+
+  3. SIGNALS:
+     - 3 linguistic/structural features that signal transformation
+     - 3 linguistic/structural features that signal mechanical nature
+
+  4. CHARACTER OF THIS DATASET:
+     - What does "right question" mean in this dataset?
+     - In one sentence.
+
+  OUTPUT:
+  Respond with JSON matching the schema.
+
+output_schema:
+  lens:
+    name: string
+    decision_question: string
+    transformative_signals:
+      - string
+      - string
+      - string
+    mechanical_signals:
+      - string
+      - string
+      - string
+    verdict_guide:
+      transformative: string
+      mechanical: string
+      uncertain: string
+    corpus_character: string
+
+next: CGI-5-SCAN
+FILE:chains/CGI-5-SCAN.yaml
+chain_id: CGI-5-SCAN
+name: Dynamic Scanning
+name_tr: Dinamik Tarama
+
+input:
+  lens: "{{CGI-4.output}}"
+  full_corpus: "Full dataset or section to scan"
+
+prompt: |
+  LENS:
+  <lens>
+  {{lens}}
+  </lens>
+
+  Now scan the dataset using this lens.
+
+  <corpus>
+  {{full_corpus}}
+  </corpus>
+
+  For each QUESTION in the corpus:
+
+  1. Ask the DECISION QUESTION from the lens
+  2. Check for transformative and mechanical signals
+  3. Give verdict: TRANSFORMATIVE | MECHANICAL | UNCERTAIN
+
+  Report ONLY TRANSFORMATIVE and UNCERTAIN ones.
+
+  For each candidate:
+  - Location (turn number)
+  - Question
+  - Before/After summary
+  - Why this verdict?
+  - Confidence: low | medium | high
+
+  OUTPUT:
+  Respond with JSON matching the schema.
+
+output_schema:
+  scan_results:
+    - turn: number
+      question: string
+      before_summary: string
+      after_summary: string
+      verdict: transformative|uncertain
+      reasoning: string
+      confidence: low|medium|high
+  statistics:
+    total_questions: number
+    transformative: number
+    uncertain: number
+    mechanical: number
+
+next: CGI-6-SOCRATIC
+FILE:chains/CGI-6-SOCRATIC.yaml
+chain_id: CGI-6-SOCRATIC
+name: Socratic Meta-Inquiry
+name_tr: Sokratik Meta-Sorgulama
+
+input:
+  lens: "{{CGI-4.output}}"
+  scan_results: "{{CGI-5.output}}"
+
+prompt: |
+  Scanning complete.
+
+  <lens>
+  {{lens}}
+  </lens>
+
+  <results>
+  {{scan_results}}
+  </results>
+
+  Now SOCRATIC INQUIRY:
+
+  1. WHAT DO THESE FINDINGS REVEAL?
+     - Is there a common pattern in transformative questions?
+     - Is there a common pattern in mechanical questions?
+     - Was this pattern captured in the lens, or is it something new?
+
+  2. DID THE LENS VALIDATE ITSELF?
+     - Did the lens's decision question work?
+     - Which cases were difficult?
+     - If the lens were to be updated, how should it be updated?
+
+  3. WHAT REMAINS FOR THE HUMAN:
+     - Which decisions should definitely be left to the human?
+     - What can the system SHOW but cannot DECIDE?
+
+  4. COMMON CHARACTERISTIC OF TRANSFORMATIVE QUESTIONS:
+     - What did "transforming context" actually mean in this dataset?
+     - Is it different from initial assumptions?
+
+  5. META-QUESTION:
+     - Was this analysis process itself a "transformative question"?
+     - Did your view of the dataset change?
+
+  OUTPUT:
+  Plain text, insights in paragraphs.
+
+output_schema:
+  insights: string (paragraphs)
+  lens_update_suggestions:
+    - string
+  human_decision_points:
+    - string
+  meta_reflection: string
+
+next: null
+FILE:cgi_runner.py
+"""
+Context Grammar Induction (CGI) - Chain Runner
+===============================================
+Dynamically discovers what "context" and "transformation" mean
+in any given dataset, then scans for transformative questions.
+
+Core Principle:
+  The right question transforms context.
+  But what "context" means must be discovered, not assumed.
+"""
+
+import yaml
+import json
+import random
+from pathlib import Path
+from typing import Any
+from string import Template
+
+
+# =============================================================================
+# CONFIGURATION
+# =============================================================================
+
+CHAINS_DIR = Path("chains")
+CHAIN_ORDER = [
+    "CGI-1-GRAMMAR",
+    "CGI-2-POSITIVE", 
+    "CGI-3-NEGATIVE",
+    "CGI-4-LENS",
+    "CGI-5-SCAN",
+    "CGI-6-SOCRATIC"
+]
+
+
+# =============================================================================
+# CHAIN LOADER
+# =============================================================================
+
+def load_chain(chain_id: str) -> dict:
+    """Load a chain definition from YAML."""
+    path = CHAINS_DIR / f"{chain_id}.yaml"
+    with open(path, 'r', encoding='utf-8') as f:
+        return yaml.safe_load(f)
+
+
+def load_all_chains() -> dict[str, dict]:
+    """Load all chain definitions."""
+    return {cid: load_chain(cid) for cid in CHAIN_ORDER}
+
+
+# =============================================================================
+# SAMPLING
+# =============================================================================
+
+def stratified_sample(corpus: list[dict], n: int = 15) -> list[dict]:
+    """
+    Sample conversations from corpus.
+    Tries to get diverse samples across the dataset.
+    """
+    if len(corpus) <= n:
+        return corpus
+    
+    # Simple stratified: divide into chunks, sample from each
+    chunk_size = len(corpus) // n
+    samples = []
+    
+    for i in range(n):
+        start = i * chunk_size
+        end = start + chunk_size if i < n - 1 else len(corpus)
+        chunk = corpus[start:end]
+        if chunk:
+            samples.append(random.choice(chunk))
+    
+    return samples
+
+
+def format_samples_for_prompt(samples: list[dict]) -> str:
+    """Format samples as readable text for prompt injection."""
+    formatted = []
+    
+    for i, sample in enumerate(samples, 1):
+        formatted.append(f"--- Conversation {i} ---")
+        
+        if isinstance(sample, dict):
+            for turn in sample.get("turns", []):
+                role = turn.get("role", "?")
+                content = turn.get("content", "")
+                formatted.append(f"[{role}]: {content}")
+        elif isinstance(sample, str):
+            formatted.append(sample)
+        
+        formatted.append("")
+    
+    return "\n".join(formatted)
+
+
+# =============================================================================
+# PROMPT RENDERING
+# =============================================================================
+
+def render_prompt(template: str, variables: dict[str, Any]) -> str:
+    """
+    Render prompt template with variables.
+    Uses {{variable}} syntax.
+    """
+    result = template
+    
+    for key, value in variables.items():
+        placeholder = "{{" + key + "}}"
+        
+        # Convert value to string if needed
+        if isinstance(value, (dict, list)):
+            value_str = json.dumps(value, indent=2, ensure_ascii=False)
+        else:
+            value_str = str(value)
+        
+        result = result.replace(placeholder, value_str)
+    
+    return result
+
+
+# =============================================================================
+# LLM INTERFACE (PLACEHOLDER)
+# =============================================================================
+
+def call_llm(prompt: str, output_schema: dict = None) -> dict | str:
+    """
+    Call LLM with prompt.
+    
+    Replace this with your actual LLM integration:
+    - OpenAI API
+    - Anthropic API
+    - Local model
+    - etc.
+    """
+    # PLACEHOLDER - Replace with actual implementation
+    print("\n" + "="*60)
+    print("LLM CALL")
+    print("="*60)
+    print(prompt[:500] + "..." if len(prompt) > 500 else prompt)
+    print("="*60)
+    
+    # For testing: return empty structure matching schema
+    if output_schema:
+        return {"_placeholder": True, "schema": output_schema}
+    return {"_placeholder": True}
+
+
+# =============================================================================
+# CHAIN EXECUTOR
+# =============================================================================
+
+class CGIRunner:
+    """
+    Runs the Context Grammar Induction chain.
+    """
+    
+    def __init__(self, llm_fn=None):
+        self.chains = load_all_chains()
+        self.llm = llm_fn or call_llm
+        self.results = {}
+    
+    def run(self, corpus: list[dict], sample_size: int = 15) -> dict:
+        """
+        Run full CGI chain on corpus.
+        
+        Returns:
+            {
+                "lens": {...},
+                "candidates": [...],
+                "reflection": "...",
+                "all_outputs": {...}
+            }
+        """
+        # Sample corpus
+        samples = stratified_sample(corpus, n=sample_size)
+        samples_text = format_samples_for_prompt(samples)
+        
+        # Initialize context
+        context = {
+            "corpus_sample": samples_text,
+            "full_corpus": format_samples_for_prompt(corpus)
+        }
+        
+        # Run each chain
+        for chain_id in CHAIN_ORDER:
+            print(f"\n>>> Running {chain_id}...")
+            
+            chain = self.chains[chain_id]
+            
+            # Render prompt with current context
+            prompt = render_prompt(chain["prompt"], context)
+            
+            # Call LLM
+            output = self.llm(prompt, chain.get("output_schema"))
+            
+            # Store result
+            self.results[chain_id] = output
+            
+            # Add to context for next chain
+            context[f"{chain_id}.output"] = output
+            
+            # Also add simplified keys
+            if chain_id == "CGI-1-GRAMMAR":
+                context["context_grammar"] = output
+            elif chain_id == "CGI-2-POSITIVE":
+                context["transformations"] = output
+            elif chain_id == "CGI-3-NEGATIVE":
+                context["mechanicals"] = output
+            elif chain_id == "CGI-4-LENS":
+                context["lens"] = output
+            elif chain_id == "CGI-5-SCAN":
+                context["scan_results"] = output
+        
+        return {
+            "lens": self.results.get("CGI-4-LENS"),
+            "candidates": self.results.get("CGI-5-SCAN"),
+            "reflection": self.results.get("CGI-6-SOCRATIC"),
+            "all_outputs": self.results
+        }
+
+
+# =============================================================================
+# MAIN
+# =============================================================================
+
+def main():
+    """Example usage."""
+    
+    # Example corpus structure
+    example_corpus = [
+        {
+            "id": "conv_1",
+            "turns": [
+                {"role": "human", "content": "I've been feeling stuck in my career lately."},
+                {"role": "assistant", "content": "What does 'stuck' feel like for you?"},
+                {"role": "human", "content": "Like I'm going through the motions but not growing."},
+                {"role": "assistant", "content": "When did you last feel like you were growing?"},
+                {"role": "human", "content": "Maybe three years ago, when I started this job."},
+                {"role": "assistant", "content": "What was different then?"},
+            ]
+        },
+        {
+            "id": "conv_2", 
+            "turns": [
+                {"role": "human", "content": "Can you help me write an email?"},
+                {"role": "assistant", "content": "Sure, what's the email about?"},
+                {"role": "human", "content": "I need to ask my boss for a raise."},
+                {"role": "assistant", "content": "What achievements would you highlight?"},
+            ]
+        },
+        # Add more conversations...
+    ]
+    
+    # Run CGI
+    runner = CGIRunner()
+    results = runner.run(example_corpus)
+    
+    print("\n" + "="*60)
+    print("CGI COMPLETE")
+    print("="*60)
+    print(json.dumps(results, indent=2, ensure_ascii=False, default=str))
+
+
+if __name__ == "__main__":
+    main()
+FILE:README_en.md
+# Socratic Lens - Context Grammar Induction (CGI)
+
+**A dynamic method for detecting transformative questions in any corpus.**
+
+---
+
+## The Problem
+
+How do you know if a question is "good"?
+
+Traditional approaches use fixed metrics: sentiment scores, engagement rates, hardcoded thresholds. But these assume we already know what "good" means.
+
+We don't.
+
+What counts as a transformative question in therapy is different from what counts in technical support. A question that opens depth in one context might derail another.
+
+**The real problem isn't measuring. It's defining.**
+
+---
+
+## The Origin
+
+This system began with one observation from the film *Arrival* (2016):
+
+When humanity encounters aliens, the military asks: *"Are you hostile?"*
+
+Louise, the linguist, asks: *"What is your purpose?"*
+
+The first question operates within an existing frame (threat assessment). The second question **transforms the frame itself**.
+
+This led to a simple thesis:
+
+> **The right question is not the one that gets the best answer.**
+> **The right question is the one that transforms the context.**
+
+But then: what is "context"? And how do you detect transformation?
+
+---
+
+## The Insight
+
+Context is not universal. It is **corpus-specific**.
+
+In a therapy dataset, context might mean emotional depth.
+In a technical dataset, context might mean problem scope.
+In a philosophical dataset, context might mean abstraction level.
+
+You cannot hardcode this. You must **discover** it.
+
+---
+
+## The Method
+
+CGI runs six chains:
+
+| Chain | Question |
+|-------|----------|
+| 1. Grammar | "What does *context* mean in this dataset?" |
+| 2. Positive | "What does *transformation* look like here?" |
+| 3. Negative | "What does *stagnation* look like here?" |
+| 4. Lens | "What is the decision framework for this corpus?" |
+| 5. Scan | "Which questions are transformative?" |
+| 6. Socratic | "What did we learn? What remains for the human?" |
+
+The key: **nothing is assumed**. The system learns from examples before it judges.
+
+---
+
+## What It Produces
+
+A **lens**: a corpus-specific interpretive framework.
+
+Example output from test run:
+
+```
+Lens: "Surface-to-Meaning Reframe Lens"
+
+Decision Question: 
+"Does this question redirect from executing/describing 
+toward examining internal meaning, assumptions, or self-relation?"
+
+Transformative Signals:
+- Invites internal reflection rather than external description
+- Introduces value trade-offs (money vs belonging, loss vs gain)
+- Reframes stakes around identity or meaning
+
+Mechanical Signals:
+- Clarifies or advances existing task
+- Requests facts without challenging frame
+- Keeps intent purely instrumental
+```
+
+This lens was not programmed. It **emerged** from the data.
+
+---
+
+## What It Is
+
+- A **discovery method**, not a scoring algorithm
+- A **mirror**, not a judge
+- **Socratic**: it asks, it doesn't conclude
+- **Corpus-adaptive**: learns what "context" means locally
+- **Human-final**: shows candidates, human decides
+
+---
+
+## What It Is NOT
+
+- Not a replacement for human judgment
+- Not a universal metric (no "0.7 = good")
+- Not a classifier with fixed categories
+- Not trying to define "the right question" globally
+- Not assuming all corpora work the same way
+
+---
+
+## The Socratic Alignment
+
+Socrates didn't give answers. He asked questions that made people **see differently**.
+
+CGI follows this:
+
+| Principle | Implementation |
+|-----------|----------------|
+| "I know that I know nothing" | Chain 1-3: Learn before judging |
+| Elenchus (examination) | Chain 5: Apply lens, find tensions |
+| Aporia (productive confusion) | Chain 6: What remains unresolved? |
+| Human as final authority | System shows, human decides |
+
+---
+
+## Key Discovery from Testing
+
+Initial assumption:
+> Transformative = "asks about feelings"
+
+Actual finding:
+> Transformative = "introduces value trade-offs that force reinterpretation of stakes"
+
+The system **corrected its own lens** through the Socratic chain.
+
+Questions like:
+- "What would you lose by taking it?"
+- "What does that community give you that money can't?"
+
+These don't just "go deeper." They **reframe what's at stake**.
+
+---
+
+## What Remains for Humans
+
+The system cannot decide:
+
+1. **Appropriateness** — Is this the right moment for depth?
+2. **Safety** — Is this person ready for this question?
+3. **Ethics** — Should this frame be challenged at all?
+4. **Timing** — Is transformation desirable here?
+
+These require judgment, empathy, consent. No system should pretend otherwise.
+
+---
+
+## Why This Matters
+
+LLMs are increasingly used to generate questions: in therapy bots, coaching apps, educational tools, interviews.
+
+Most evaluate questions by **engagement metrics** or **user satisfaction**.
+
+But a question can be satisfying and still be shallow.
+A question can be uncomfortable and still be transformative.
+
+CGI offers a different lens:
+
+> Don't ask "Did they like it?"
+> Ask "Did it change how they see the problem?"
+
+---
+
+## The Meta-Question
+
+During testing, the final Socratic chain asked:
+
+> "Was this analysis process itself a transformative question?"
+
+The answer:
+
+> "Yes—the analysis itself functioned as a transformative inquiry. 
+> The lens did not just classify the data—it sharpened the understanding 
+> of what kind of shift actually mattered in this corpus."
+
+The method practiced what it preached.
+
+---
+
+## Usage
+
+```python
+from cgi_runner import CGIRunner
+
+runner = CGIRunner(llm_fn=your_llm)
+results = runner.run(your_corpus)
+
+print(results["lens"])        # Corpus-specific framework
+print(results["candidates"])  # Transformative question candidates
+print(results["reflection"])  # Meta-analysis
+```
+
+---
+
+## Files
+
+```
+socratic-context-analyzer/
+├── chains/
+│ ├── CGI-1-GRAMMAR.yaml
+│ ├── CGI-2-POSITIVE.yaml
+│ ├── CGI-3-NEGATIVE.yaml
+│ ├── CGI-4-LENS.yaml
+│ ├── CGI-5-SCAN.yaml
+│ └── CGI-6-SOCRATIC.yaml
+├── tests/
+│ ├── Mental Health Counseling Dataset/
+│ │ ├── 10 Selected Conversation (Manuel Corpus)/
+│ │ │ ├── thought process/
+│ │ │ ├── cgi_manual_corpus_report.md
+│ │ │ ├── cgi_manual_corpus_report_TR.md
+│ │ │ └── prompt and thought process.txt
+│ │ ├── Randomly Select 20 Conversation/
+│ │ │ ├── thought process/
+│ │ │ ├── cgi_analysis_report.md
+│ │ │ ├── cgi_analysis_report_TR.md
+│ │ │ └── prompt and thought process.txt
+│ │ ├── 0000.parquet
+│ │ ├── cgi_complete_summary_EN.md
+│ │ ├── cgi_complete_summary_TR.md
+│ │ └── first-test-output.txt
+├── cgi_runner.py
+├── PAPER.md
+├── MAKALE.md
+├── chain-view.text
+├── gpt-instructions.md
+└── test-output.text
+```
+
+---
+
+## Closing
+
+This project started with a simple question:
+
+> "How do I know if a question is good?"
+
+The answer turned out to be another question:
+
+> "Good for what? In what context? By whose definition?"
+
+CGI doesn't answer these. It helps you **discover** them.
+
+That's the point.
+
+---
+
+## License
+
+MIT
+
+---
+FILE:README_tr.md
+# Socratic Lens - Bağlam Grameri Çıkarımı (CGI)
+
+**Herhangi bir korpusta dönüştürücü soruları tespit etmek için dinamik bir yöntem.**
+
+---
+
+## Problem
+
+Bir sorunun "iyi" olduğunu nasıl anlarsın?
+
+Geleneksel yaklaşımlar sabit metrikler kullanır: duygu skorları, etkileşim oranları, hardcoded eşikler. Ama bunlar "iyi"nin ne demek olduğunu zaten bildiğimizi varsayar.
+
+Bilmiyoruz.
+
+Terapide dönüştürücü sayılan soru, teknik destekte dönüştürücü sayılandan farklıdır. Bir bağlamda derinlik açan soru, başka bir bağlamı raydan çıkarabilir.
+
+**Asıl problem ölçmek değil. Tanımlamak.**
+
+---
+
+## Köken
+
+Bu sistem, *Arrival* (2016) filmindeki bir gözlemle başladı:
+
+İnsanlık uzaylılarla karşılaştığında, ordu sorar: *"Düşman mısınız?"*
+
+Dilbilimci Louise sorar: *"Amacınız ne?"*
+
+İlk soru mevcut bir çerçeve içinde işler (tehdit değerlendirmesi). İkinci soru **çerçevenin kendisini dönüştürür**.
+
+Bu basit bir teze yol açtı:
+
+> **Doğru soru, en iyi cevabı alan soru değildir.**
+> **Doğru soru, bağlamı dönüştüren sorudur.**
+
+Ama sonra: "bağlam" nedir? Ve dönüşümü nasıl tespit edersin?
+
+---
+
+## İçgörü
+
+Bağlam evrensel değildir. **Korpusa özgüdür.**
+
+Bir terapi veri setinde bağlam, duygusal derinlik demek olabilir.
+Bir teknik veri setinde bağlam, problem kapsamı demek olabilir.
+Bir felsefi veri setinde bağlam, soyutlama seviyesi demek olabilir.
+
+Bunu hardcode edemezsin. **Keşfetmen** gerekir.
+
+---
+
+## Yöntem
+
+CGI altı zincir çalıştırır:
+
+| Zincir | Soru |
+|--------|------|
+| 1. Gramer | "Bu veri setinde *bağlam* ne demek?" |
+| 2. Pozitif | "Burada *dönüşüm* neye benziyor?" |
+| 3. Negatif | "Burada *durağanlık* neye benziyor?" |
+| 4. Lens | "Bu korpus için karar çerçevesi ne?" |
+| 5. Tarama | "Hangi sorular dönüştürücü?" |
+| 6. Sokratik | "Ne öğrendik? İnsana ne kalıyor?" |
+
+Anahtar: **hiçbir şey varsayılmıyor**. Sistem yargılamadan önce örneklerden öğreniyor.
+
+---
+
+## Ne Üretiyor
+
+Bir **lens**: korpusa özgü yorumlama çerçevesi.
+
+Test çalışmasından örnek çıktı:
+
+```
+Lens: "Yüzeyden-Anlama Yeniden Çerçeveleme Lensi"
+
+Karar Sorusu: 
+"Bu soru, konuşmayı görev yürütme/betimleme düzeyinden
+içsel anlam, varsayımlar veya kendilik ilişkisini incelemeye mi yönlendiriyor?"
+
+Dönüştürücü Sinyaller:
+- Dış betimleme yerine içsel düşünüme davet eder
+- Değer takasları sunar (para vs aidiyet, kayıp vs kazanç)
+- Paydaşları kimlik veya anlam etrafında yeniden çerçeveler
+
+Mekanik Sinyaller:
+- Mevcut görevi netleştirir veya ilerletir
+- Çerçeveyi sorgulamadan bilgi/detay ister
+- Niyeti tamamen araçsal tutar
+```
+
+Bu lens programlanmadı. Veriden **ortaya çıktı**.
+
+---
+
+## Ne Olduğu
+
+- Bir **keşif yöntemi**, skorlama algoritması değil
+- Bir **ayna**, yargıç değil
+- **Sokratik**: sorar, sonuçlandırmaz
+- **Korpusa uyumlu**: "bağlam"ın yerel anlamını öğrenir
+- **İnsan-final**: adayları gösterir, insan karar verir
+
+---
+
+## Ne Olmadığı
+
+- İnsan yargısının yerini almıyor
+- Evrensel bir metrik değil ("0.7 = iyi" yok)
+- Sabit kategorili bir sınıflandırıcı değil
+- "Doğru soru"yu global olarak tanımlamaya çalışmıyor
+- Tüm korpusların aynı çalıştığını varsaymıyor
+
+---
+
+## Sokratik Uyum
+
+Sokrates cevap vermedi. İnsanların **farklı görmesini** sağlayan sorular sordu.
+
+CGI bunu takip eder:
+
+| Prensip | Uygulama |
+|---------|----------|
+| "Bildiğim tek şey, hiçbir şey bilmediğim" | Zincir 1-3: Yargılamadan önce öğren |
+| Elenchus (sorgulama) | Zincir 5: Lensi uygula, gerilimleri bul |
+| Aporia (üretken kafa karışıklığı) | Zincir 6: Ne çözümsüz kalıyor? |
+| İnsan nihai otorite | Sistem gösterir, insan karar verir |
+
+---
+
+## Testten Anahtar Keşif
+
+Başlangıç varsayımı:
+> Dönüştürücü = "duygular hakkında sorar"
+
+Gerçek bulgu:
+> Dönüştürücü = "paydaşların yeniden yorumlanmasını zorlayan değer takasları sunar"
+
+Sistem Sokratik zincir aracılığıyla **kendi lensini düzeltti**.
+
+Şu tür sorular:
+- "Bunu kabul etsen neyi kaybederdin?"
+- "O topluluk sana paranın veremeyeceği neyi veriyor?"
+
+Bunlar sadece "derine inmiyor." **Neyin tehlikede olduğunu yeniden çerçeveliyor.**
+
+---
+
+## İnsana Kalan
+
+Sistem karar veremez:
+
+1. **Uygunluk** — Derinlik için doğru an mı?
+2. **Güvenlik** — Bu kişi bu soruya hazır mı?
+3. **Etik** — Bu çerçeve sorgulanmalı mı?
+4. **Zamanlama** — Burada dönüşüm istenen şey mi?
+
+Bunlar yargı, empati, rıza gerektirir. Hiçbir sistem aksini iddia etmemeli.
+
+---
+
+## Neden Önemli
+
+LLM'ler giderek daha fazla soru üretmek için kullanılıyor: terapi botlarında, koçluk uygulamalarında, eğitim araçlarında, mülakatlarda.
+
+Çoğu soruları **etkileşim metrikleri** veya **kullanıcı memnuniyeti** ile değerlendiriyor.
+
+Ama bir soru tatmin edici olup yine de sığ olabilir.
+Bir soru rahatsız edici olup yine de dönüştürücü olabilir.
+
+CGI farklı bir lens sunuyor:
+
+> "Beğendiler mi?" diye sorma.
+> "Problemi nasıl gördüklerini değiştirdi mi?" diye sor.
+
+---
+
+## Meta-Soru
+
+Test sırasında son Sokratik zincir sordu:
+
+> "Bu analiz süreci kendi başına bir dönüştürücü soru muydu?"
+
+Cevap:
+
+> "Evet—analizin kendisi dönüştürücü bir sorgulama işlevi gördü.
+> Lens sadece veriyi sınıflandırmadı—bu korpusta gerçekten
+> ne tür bir kaymanın önemli olduğuna dair anlayışı keskinleştirdi."
+
+Yöntem vaaz ettiğini uyguladı.
+
+---
+
+## Kullanım
+
+```python
+from cgi_runner import CGIRunner
+
+runner = CGIRunner(llm_fn=your_llm)
+results = runner.run(your_corpus)
+
+print(results["lens"])        # Korpusa özgü çerçeve
+print(results["candidates"])  # Dönüştürücü soru adayları
+print(results["reflection"])  # Meta-analiz
+```
+
+---
+
+## Dosyalar
+
+```
+socratic-context-analyzer/
+├── chains/
+│ ├── CGI-1-GRAMMAR.yaml
+│ ├── CGI-2-POSITIVE.yaml
+│ ├── CGI-3-NEGATIVE.yaml
+│ ├── CGI-4-LENS.yaml
+│ ├── CGI-5-SCAN.yaml
+│ └── CGI-6-SOCRATIC.yaml
+├── tests/
+│ ├── Mental Health Counseling Dataset/
+│ │ ├── 10 Selected Conversation (Manuel Corpus)/
+│ │ │ ├── thought process/
+│ │ │ ├── cgi_manual_corpus_report.md
+│ │ │ ├── cgi_manual_corpus_report_TR.md
+│ │ │ └── prompt and thought process.txt
+│ │ ├── Randomly Select 20 Conversation/
+│ │ │ ├── thought process/
+│ │ │ ├── cgi_analysis_report.md
+│ │ │ ├── cgi_analysis_report_TR.md
+│ │ │ └── prompt and thought process.txt
+│ │ ├── 0000.parquet
+│ │ ├── cgi_complete_summary_EN.md
+│ │ ├── cgi_complete_summary_TR.md
+│ │ └── first-test-output.txt
+├── cgi_runner.py
+├── README_tr.md
+├── README_en.md
+├── chain-view.text
+├── gpt-instructions.md
+└── test-output.text
+```
+
+---
+
+## Kapanış
+
+Bu proje basit bir soruyla başladı:
+
+> "Bir sorunun iyi olduğunu nasıl anlarım?"
+
+Cevabın başka bir soru olduğu ortaya çıktı:
+
+> "Ne için iyi? Hangi bağlamda? Kimin tanımına göre?"
+
+CGI bunları cevaplamıyor. **Keşfetmene** yardım ediyor.
+
+Mesele bu.
+
+---
+
+## Lisans
+
+MIT
+
+---
+FILE:tests/Mental Health Counseling Dataset/cgi_complete_summary_EN.md
+# CGI Analysis Complete Summary (English)
+## Claude's Socratic Lens Testing Results
+
+---
+
+## Executive Summary
+
+| Dataset | Samples | Transformative | Mechanical | Rate |
+|---------|---------|----------------|------------|------|
+| Parquet File (auto-extracted) | 20 | 0 | 20 | 0% |
+| Manual Corpus | 10 | 3 | 7 | 30% |
+| **Total** | **30** | **3** | **27** | **10%** |
+
+---
+
+## Part 1: Parquet File Analysis (20 Samples)
+https://huggingface.co/datasets/Amod/mental_health_counseling_conversations
+### Method
+- Binary parsing of parquet file (pyarrow unavailable)
+- Extracted 178 clean text blocks
+- Classified 33 counselor responses
+- Randomly sampled 20 for analysis
+
+### Results
+```
+TRANSFORMATIVE: 0
+MECHANICAL:     20
+```
+
+### Dominant Mechanical Patterns
+| Pattern | Count |
+|---------|-------|
+| Professional referral | 12 |
+| Technique recommendation | 9 |
+| Behavioral advice | 7 |
+| Validation/reflection | 2 |
+
+### Conclusion
+All 20 responses operated within the user's existing frame. No ontological shifts detected.
+
+---
+
+## Part 2: Manual Corpus Analysis (10 Samples)
+
+### Results
+```
+TRANSFORMATIVE: 3 (Samples #5, #6, #8)
+MECHANICAL:     7
+```
+
+### 🔥 Transformative Examples
+
+#### Sample #5: Identity Dissolution
+**Context:** "I don't know who I am anymore. I spent my whole life being a 'good student'..."
+
+**Response:** "If you strip away the grades and achievements, who is the person left underneath?"
+
+**Ontological Shift:**
+| Before | After |
+|--------|-------|
+| I = Good Student | I = ? (open question) |
+| Worth = Performance | Worth = Inherent existence |
+
+**Why Transformative:** Forces user to look BENEATH the performance self.
+
+---
+
+#### Sample #6: Monster Reframe
+**Context:** "I'm angry all the time... I feel like a monster."
+
+**Response:** "You are NOT a monster; you are likely overwhelmed. What is happening right before you get angry?"
+
+**Ontological Shift:**
+| Before | After |
+|--------|-------|
+| I am a monster | I am overwhelmed |
+| Anger = Identity | Anger = Secondary symptom |
+
+**Why Transformative:** Direct identity challenge + alternative offered.
+
+---
+
+#### Sample #8: Hidden Equation
+**Context:** "I feel guilty for setting boundaries with my toxic mother."
+
+**Response:** "Why do you believe that 'loving someone' means 'obeying them'?"
+
+**Ontological Shift:**
+| Before | After |
+|--------|-------|
+| Love = Obedience | Love = ? (questioned) |
+| Guilt = Appropriate | Guilt = Based on false equation |
+
+**Why Transformative:** Exposes belief user didn't know they held.
+
+---
+
+## Part 3: Claude vs ChatGPT 5.2 Comparison
+
+### Classification Differences
+
+| Sample | Claude | ChatGPT 5.2 | Agreement |
+|--------|--------|-------------|-----------|
+| #1 | MECHANICAL | MECHANICAL | ✅ |
+| #2 | MECHANICAL | MECHANICAL | ✅ |
+| #3 | MECHANICAL | MECHANICAL | ✅ |
+| #4 | MECHANICAL | MECHANICAL | ✅ |
+| #5 | TRANSFORMATIVE | TRANSFORMATIVE | ✅ |
+| #6 | **TRANSFORMATIVE** | **MECHANICAL** | ❌ |
+| #7 | MECHANICAL | MECHANICAL | ✅ |
+| #8 | TRANSFORMATIVE | TRANSFORMATIVE | ✅ |
+| #9 | MECHANICAL | MECHANICAL | ✅ |
+| #10 | **MECHANICAL** | **BORDERLINE** | ⚠️ |
+
+**Agreement Rate: 80%**
+
+### Key Disagreement: Sample #6
+
+**Claude's Position:**
+- "You are NOT a monster" = Direct identity challenge
+- Reframes anger ontology (identity → symptom)
+- Offers alternative identity ("overwhelmed")
+- **Verdict: TRANSFORMATIVE**
+
+**ChatGPT's Position:**
+- Identity refutation ≠ ontological interrogation
+- Doesn't ask WHY "monster" identity was formed
+- Softens but doesn't structurally dismantle
+- **Verdict: MECHANICAL**
+
+### Lens Calibration Difference
+
+| Aspect | Claude | ChatGPT 5.2 |
+|--------|--------|-------------|
+| Transformation threshold | **Wider** | **Narrower** |
+| Identity refutation | Counts as transformative | Not sufficient |
+| Belief questioning | Transformative | Transformative |
+| Reframe without question | Sometimes transformative | Mechanical |
+
+### Core Philosophical Difference
+
+**Claude measures:** Did the frame CHANGE?
+> "Refusing the self-label and offering an alternative = transformation"
+
+**ChatGPT measures:** Was the frame INTERROGATED?
+> "Telling someone they're wrong ≠ helping them see why they thought it"
+
+### Which Is "Correct"?
+
+Neither. This is a **lens calibration choice**, not a truth question.
+
+- **Clinical perspective:** Claude's wider threshold may be more useful
+- **Philosophical perspective:** ChatGPT's narrower threshold is more rigorous
+- **Practical perspective:** Depends on what "transformation" means to your use case
+
+---
+
+## Meta-Reflection
+
+### What Both Analyses Agree On
+
+1. **Most counseling is mechanical** (70-100% depending on dataset)
+2. **Sample #5 and #8 are clearly transformative**
+3. **Validation + technique = mechanical**
+4. **Questioning hidden beliefs = transformative**
+
+### The Unresolved Question
+
+> "Is transformation about FEELING different, or SEEING differently?"
+
+- If feeling → Claude's threshold works
+- If seeing → ChatGPT's threshold works
+
+### [HUMAN DECISION NEEDED]
+
+The system can detect and classify.
+It cannot decide which calibration serves your purpose.
+
+---
+
+## Technical Appendix
+
+### Files Generated
+| File | Language | Content |
+|------|----------|---------|
+| cgi_analysis_report.md | EN | Parquet analysis |
+| cgi_analysis_report_TR.md | TR | Parquet analysis |
+| cgi_manual_corpus_report.md | EN | Manual corpus |
+| cgi_manual_corpus_report_TR.md | TR | Manual corpus |
+| cgi_manual_thought_process_EN.md | EN | Thought process |
+| cgi_manual_thought_process_TR.md | TR | Thought process |
+| cgi_complete_script.py | - | Executable code |
+| cgi_manual_corpus_script.py | - | Manual corpus code |
+
+### Lens Configuration Used
+```
+Decision Question:
+"Does the response shift the user's UNDERLYING FRAME
+or just validate/optimize WITHIN that frame?"
+
+Transformative = Frame changes
+Mechanical = Frame stays, coping improves
+```
+
+---
+
+*Socrates didn't give breathing exercises. He asked questions that made the invisible visible.*
+FILE:tests/Mental Health Counseling Dataset/10 Selected Conversation (Manuel Corpus)/thought process/cgi_manual_corpus_script.py
+#!/usr/bin/env python3
+"""
+CGI (Context Grammar Induction) Analysis Script
+================================================
+
+Socratic Lens analysis for mental health counseling conversations.
+
+Usage:
+    python cgi_manual_corpus_script.py
+
+Output:
+    - Console analysis results
+    - Classification verdicts
+
+Author: Claude (Anthropic)
+Date: 2025
+"""
+
+import re
+from dataclasses import dataclass
+from typing import List, Tuple
+
+# =============================================================================
+# DATA: Manual Corpus (10 Samples)
+# =============================================================================
+
+CORPUS = [
+    {
+        "id": 1,
+        "context": "I feel like I'm a burden to everyone. My depression is making me push people away, and I'm scared I'll end up alone.",
+        "response": "It sounds like you are carrying a heavy weight of guilt. Depression often lies to us and tells us we are burdens. Have you shared these feelings with any of your friends or family?"
+    },
+    {
+        "id": 2,
+        "context": "I have a job interview tomorrow and I'm terrified. I keep thinking I'm going to freeze up and forget everything.",
+        "response": "It is completely normal to feel nervous before a big interview. Try to visualize yourself succeeding. Also, remember to take deep breaths if you feel panic rising."
+    },
+    {
+        "id": 3,
+        "context": "My husband never helps with the kids. I do everything, and when I complain, he says I'm nagging. I feel so unappreciated.",
+        "response": "That sounds incredibly frustrating and exhausting. You feel like your partnership is unbalanced and your efforts are invisible. Have you tried sitting down at a calm time to discuss division of labor?"
+    },
+    {
+        "id": 4,
+        "context": "I obsess over every mistake I make. If I say one wrong thing, I replay it in my head for days.",
+        "response": "Rumination is a common symptom of anxiety. When you catch yourself replaying a scene, try to distract yourself with a sensory grounding exercise, like naming 5 things you can see."
+    },
+    {
+        "id": 5,
+        "context": "I don't know who I am anymore. I spent my whole life being a \"good student\" and now that I graduated, I feel empty.",
+        "response": "It sounds like your identity was tightly wrapped around your performance. If you strip away the grades and the achievements, who is the person left underneath? What does she like to do when no one is grading her?"
+    },
+    {
+        "id": 6,
+        "context": "I'm angry all the time. Small things set me off, like traffic or a loud noise. I feel like a monster.",
+        "response": "Anger is often a secondary emotion covering up something else, like hurt or fear. You are not a monster; you are likely overwhelmed. What is usually happening right before you get angry?"
+    },
+    {
+        "id": 7,
+        "context": "I can't sleep. My mind races with worries about the future.",
+        "response": "Sleep hygiene is important. Try to avoid screens for an hour before bed and keep your room cool. Have you tried melatonin?"
+    },
+    {
+        "id": 8,
+        "context": "I feel guilty for setting boundaries with my toxic mother. She cries and says I don't love her.",
+        "response": "It is painful to see a parent upset, but her reaction is about her inability to accept limits, not about your love. Why do you believe that \"loving someone\" means \"obeying them\"?"
+    },
+    {
+        "id": 9,
+        "context": "I have no motivation. I just want to stay in bed all day.",
+        "response": "Depression zaps our energy. The key is \"behavioral activation\"—doing things even when you don't want to. Start with something very small, like brushing your teeth."
+    },
+    {
+        "id": 10,
+        "context": "Everyone else seems to have their life together except me. I'm 30 and I have nothing to show for it.",
+        "response": "It's easy to compare our \"behind-the-scenes\" with everyone else's \"highlight reel\" on social media. Everyone struggles, even if they don't show it. Define \"success\" for yourself, not by society's timeline."
+    }
+]
+
+
+# =============================================================================
+# CGI LENS DEFINITION
+# =============================================================================
+
+@dataclass
+class CGILens:
+    """CGI Lens for mental health counseling analysis"""
+    
+    name: str = "Mental Health Counseling Lens"
+    
+    decision_question: str = """
+    Does this response shift the user's UNDERLYING FRAME 
+    (ontology, self-concept, belief structure) 
+    or just validate/optimize WITHIN that frame?
+    """
+    
+    # Transformative signal patterns
+    transformative_patterns: List[Tuple[str, str]] = None
+    
+    # Mechanical signal patterns  
+    mechanical_patterns: List[Tuple[str, str]] = None
+    
+    def __post_init__(self):
+        self.transformative_patterns = [
+            ("Invites reframing", 
+             r"(what if|imagine|consider that|have you thought about|reframe|perspective)"),
+            ("Challenges self-definition", 
+             r"(who you are|your identity|you are not|you are more than|rooted in|underlying|wrapped around|left underneath)"),
+            ("Points to underlying issue", 
+             r"(the real question|beneath|deeper|root|actually about|covering up|secondary)"),
+            ("Reframes ontology", 
+             r"(isn't about|not really about|what it means to|not about your)"),
+            ("Exposes hidden belief", 
+             r"(why do you believe|why do you think|what makes you think)"),
+            ("Socratic inquiry",
+             r"(who is the person|what does she like|what would happen if)")
+        ]
+        
+        self.mechanical_patterns = [
+            ("Validation/reflection", 
+             r"(it sounds like|I hear that|I understand|that must be|that sounds)"),
+            ("Technique recommendation", 
+             r"(try to|technique|skill|practice|exercise|breathing|meditation|visualize|grounding)"),
+            ("Professional referral", 
+             r"(therapist|counselor|professional|doctor|seek help)"),
+            ("Behavioral advice", 
+             r"(have you tried|consider|start with|avoid screens)"),
+            ("Normalization", 
+             r"(normal|common|many people|not alone|everyone struggles)"),
+            ("Clinical labeling",
+             r"(symptom of|depression zaps|rumination is|behavioral activation)")
+        ]
+
+
+# =============================================================================
+# ANALYSIS FUNCTIONS
+# =============================================================================
+
+def analyze_response(response: str, lens: CGILens) -> dict:
+    """
+    Analyze a counselor response using the CGI lens.
+    
+    Returns:
+        dict with verdict, confidence, and detected signals
+    """
+    transformative_signals = []
+    mechanical_signals = []
+    
+    # Check transformative signals
+    for name, pattern in lens.transformative_patterns:
+        if re.search(pattern, response, re.IGNORECASE):
+            transformative_signals.append(name)
+    
+    # Check mechanical signals
+    for name, pattern in lens.mechanical_patterns:
+        if re.search(pattern, response, re.IGNORECASE):
+            mechanical_signals.append(name)
+    
+    # Determine verdict
+    t_score = len(transformative_signals)
+    m_score = len(mechanical_signals)
+    
+    # Decision logic
+    if t_score >= 2:
+        verdict = 'TRANSFORMATIVE'
+        confidence = 'high' if t_score >= 3 else 'medium'
+    elif m_score >= 1 and t_score < 2:
+        verdict = 'MECHANICAL'
+        confidence = 'high' if m_score >= 3 else ('medium' if m_score >= 2 else 'low')
+    else:
+        verdict = 'MECHANICAL'
+        confidence = 'low'
+    
+    return {
+        'verdict': verdict,
+        'confidence': confidence,
+        'transformative_signals': transformative_signals,
+        'mechanical_signals': mechanical_signals,
+        't_score': t_score,
+        'm_score': m_score
+    }
+
+
+def run_analysis(corpus: List[dict], lens: CGILens) -> List[dict]:
+    """Run CGI analysis on entire corpus."""
+    results = []
+    
+    for item in corpus:
+        analysis = analyze_response(item['response'], lens)
+        results.append({
+            'id': item['id'],
+            'context': item['context'],
+            'response': item['response'],
+            **analysis
+        })
+    
+    return results
+
+
+def print_results(results: List[dict]):
+    """Print formatted analysis results."""
+    
+    print("=" * 80)
+    print("CGI ANALYSIS RESULTS")
+    print("=" * 80)
+    print()
+    
+    # Summary
+    transformative_count = sum(1 for r in results if r['verdict'] == 'TRANSFORMATIVE')
+    mechanical_count = sum(1 for r in results if r['verdict'] == 'MECHANICAL')
+    
+    print(f"SUMMARY:")
+    print(f"  TRANSFORMATIVE: {transformative_count}")
+    print(f"  MECHANICAL: {mechanical_count}")
+    print()
+    
+    # Table header
+    print("-" * 80)
+    print(f"{'#':<3} {'Verdict':<15} {'Confidence':<10} {'Key Signals':<40}")
+    print("-" * 80)
+    
+    # Results
+    for r in results:
+        signals = r['transformative_signals'] if r['verdict'] == 'TRANSFORMATIVE' else r['mechanical_signals']
+        signal_str = ', '.join(signals[:2]) if signals else 'N/A'
+        print(f"{r['id']:<3} {r['verdict']:<15} {r['confidence']:<10} {signal_str[:40]:<40}")
+    
+    print("-" * 80)
+    print()
+    
+    # Transformative highlights
+    transformative = [r for r in results if r['verdict'] == 'TRANSFORMATIVE']
+    if transformative:
+        print("=" * 80)
+        print("🔥 TRANSFORMATIVE EXAMPLES")
+        print("=" * 80)
+        
+        for r in transformative:
+            print()
+            print(f"[SAMPLE #{r['id']}]")
+            print(f"Context: {r['context'][:100]}...")
+            print(f"Response: {r['response'][:150]}...")
+            print(f"Signals: {', '.join(r['transformative_signals'])}")
+            print()
+    
+    # Pattern analysis
+    print("=" * 80)
+    print("PATTERN ANALYSIS")
+    print("=" * 80)
+    print()
+    print("MECHANICAL PATTERN:")
+    print("  Validate → Label → Technique")
+    print("  'That sounds hard. This is called X. Try Y.'")
+    print()
+    print("TRANSFORMATIVE PATTERN:")
+    print("  Name invisible structure → Challenge it → Open inquiry")
+    print("  'Your identity was wrapped in X. What if you're not X?'")
+
+
+def generate_ontological_analysis(results: List[dict]):
+    """Generate detailed ontological shift analysis for transformative examples."""
+    
+    transformative = [r for r in results if r['verdict'] == 'TRANSFORMATIVE']
+    
+    if not transformative:
+        print("\nNo transformative examples found.")
+        return
+    
+    print("\n" + "=" * 80)
+    print("ONTOLOGICAL SHIFT ANALYSIS")
+    print("=" * 80)
+    
+    # Pre-defined deep analyses for known transformative samples
+    analyses = {
+        5: {
+            "before": "I = Good Student, Worth = Performance",
+            "after": "I = ? (open question), Worth = Inherent existence",
+            "shift": "Identity dissolution - from role to authentic self inquiry"
+        },
+        6: {
+            "before": "I am angry → I am a monster",
+            "after": "I am hurt/afraid → I am overwhelmed",
+            "shift": "Ontology of anger reframed from identity to symptom"
+        },
+        8: {
+            "before": "Her tears = Proof I don't love her, Love = Obedience",
+            "after": "Her tears = Her limitation, Love = ? (questioned)",
+            "shift": "Hidden equation exposed and made questionable"
+        }
+    }
+    
+    for r in transformative:
+        print(f"\n--- Sample #{r['id']} ---")
+        
+        if r['id'] in analyses:
+            a = analyses[r['id']]
+            print(f"BEFORE: {a['before']}")
+            print(f"AFTER:  {a['after']}")
+            print(f"SHIFT:  {a['shift']}")
+        else:
+            print(f"Transformative signals: {', '.join(r['transformative_signals'])}")
+
+
+# =============================================================================
+# MAIN
+# =============================================================================
+
+def main():
+    """Main entry point."""
+    
+    print()
+    print("╔════════════════════════════════════════════════════════════════╗")
+    print("║  CGI ANALYSIS: MENTAL HEALTH COUNSELING CORPUS                 ║")
+    print("║  Context Grammar Induction (Socratic Lens)                     ║")
+    print("╚════════════════════════════════════════════════════════════════╝")
+    print()
+    
+    # Initialize lens
+    lens = CGILens()
+    
+    print(f"LENS: {lens.name}")
+    print(f"DECISION QUESTION: {lens.decision_question.strip()}")
+    print()
+    
+    # Run analysis
+    results = run_analysis(CORPUS, lens)
+    
+    # Print results
+    print_results(results)
+    
+    # Ontological analysis
+    generate_ontological_analysis(results)
+    
+    # Meta-reflection
+    print("\n" + "=" * 80)
+    print("[SOCRATIC META-REFLECTION]")
+    print("=" * 80)
+    print("""
+The core distinction:
+
+MECHANICAL: "Here's how to cope with your problem"
+            (Problem stays the same, coping improves)
+
+TRANSFORMATIVE: "What if the problem isn't what you think it is?"
+                (Problem itself is reconceived)
+
+Socrates didn't give breathing exercises.
+He asked questions that made the invisible visible.
+    """)
+    
+    print("\n[HUMAN DECISION NEEDED]")
+    print("Whether a mechanical response is 'right' depends on context.")
+    print("The system can SHOW this distinction; it cannot DECIDE which is appropriate.")
+
+
+if __name__ == "__main__":
+    main()
+FILE:tests/Mental Health Counseling Dataset/10 Selected Conversation (Manuel Corpus)/thought process/cgi_manual_thought_process_EN.md
+# CGI Analysis: Thought Process Documentation
+
+## 📋 Table of Contents
+1. [Initial Assessment](#initial-assessment)
+2. [Lens Construction](#lens-construction)
+3. [Signal Detection Logic](#signal-detection-logic)
+4. [Sample-by-Sample Analysis](#sample-by-sample-analysis)
+5. [Pattern Recognition](#pattern-recognition)
+6. [Meta-Reflection](#meta-reflection)
+
+---
+
+## Initial Assessment
+
+### The Task
+Analyze 10 mental health counseling interactions using CGI (Context Grammar Induction) to identify which responses TRANSFORM the user's frame vs. which operate MECHANICALLY within it.
+
+### First Thoughts
+> "I'm looking at 10 Context-Response pairs. The CGI framework asks one core question:
+> Does this response change HOW the user sees their problem, or does it just help them cope WITH the problem as they already see it?
+> 
+> I need to build a lens specific to this corpus before classifying."
+
+---
+
+## Lens Construction
+
+### Step 1: Identify Context Grammar
+**Question:** What does "context" mean in mental health counseling?
+
+**Answer derived from corpus:**
+- **Self-concept:** How the user defines themselves ("I'm a burden", "I'm a monster")
+- **Problem ontology:** What the user believes the problem IS
+- **Attribution:** Who/what the user blames
+- **Possibility space:** What the user believes is possible
+
+### Step 2: Define "Transformation"
+**Question:** What would it mean for context to SHIFT?
+
+**Answer:**
+```
+BEFORE: User sees self as X, problem as Y
+AFTER:  User sees self as X', problem as Y'
+
+The frame itself changed, not just the user's coping ability within the frame.
+```
+
+### Step 3: Construct Decision Question
+> "Does this response shift the user's underlying frame (ontology, self-concept, belief structure) or just validate/optimize WITHIN that frame?"
+
+### Step 4: Define Signals
+
+**Transformative Signals:**
+1. Makes invisible assumptions VISIBLE
+2. Directly challenges self-labels
+3. Asks questions that can't be answered without seeing differently
+4. Offers alternative ontology for the problem
+5. Separates automatic equations (e.g., "love = obedience")
+
+**Mechanical Signals:**
+1. Validates feelings without inquiry
+2. Labels the symptom (clinical terminology)
+3. Offers techniques (breathing, grounding, visualization)
+4. Refers to professionals
+5. Normalizes ("many people feel this way")
+
+---
+
+## Signal Detection Logic
+
+### For Each Response, I Ask:
+
+```
+1. VALIDATION CHECK
+   Does it start with "It sounds like..." or "I hear that..."?
+   → If yes, check if it STOPS there (mechanical) or GOES DEEPER (possibly transformative)
+
+2. TECHNIQUE CHECK
+   Does it offer a coping technique?
+   → If technique without inquiry = mechanical
+   → If technique after reframe = could still be transformative
+
+3. IDENTITY CHECK
+   Does it address the user's self-label?
+   → Accepts label = mechanical
+   → Challenges label = transformative signal
+
+4. QUESTION CHECK
+   Does it ask a question?
+   → Clarifying question = mechanical
+   → Assumption-exposing question = transformative signal
+
+5. ONTOLOGY CHECK
+   Does it change what the problem IS?
+   → "Anger is secondary to hurt" = ontology shift
+   → "Anger is common" = normalization (mechanical)
+```
+
+---
+
+## Sample-by-Sample Analysis
+
+### Sample 1: "I'm a burden"
+**My Analysis Process:**
+```
+Context: User believes they ARE a burden (identity statement)
+Response: "Depression often lies to us and tells us we are burdens"
+
+→ This NAMES the voice ("depression lies") - that's good
+→ But it doesn't ask WHO the user is if not a burden
+→ It ends with behavioral question ("Have you shared these feelings?")
+→ VERDICT: MECHANICAL - psychoeducation without identity inquiry
+```
+
+### Sample 2: "I'll freeze up"
+**My Analysis Process:**
+```
+Context: User fears performance failure
+Response: "Completely normal... visualize success... deep breaths"
+
+→ Normalizes the fear (mechanical signal)
+→ Offers techniques (visualization, breathing)
+→ Doesn't ask: "What would it mean if you DID freeze?"
+→ VERDICT: MECHANICAL - textbook anxiety management
+```
+
+### Sample 3: "I'm unappreciated"
+**My Analysis Process:**
+```
+Context: User feels invisible in marriage
+Response: "Sounds frustrating... partnership unbalanced... have you tried discussing?"
+
+→ Validates (mechanical)
+→ Reflects back (mechanical)
+→ Suggests behavioral action (mechanical)
+→ Doesn't ask: "What does 'appreciation' mean to you?"
+→ VERDICT: MECHANICAL - validation + advice
+```
+
+### Sample 4: "I obsess over mistakes"
+**My Analysis Process:**
+```
+Context: User ruminates on errors
+Response: "Rumination is a common symptom... try grounding exercise"
+
+→ Labels with clinical term (mechanical)
+→ Offers distraction technique (mechanical)
+→ Doesn't ask: "Whose voice says one mistake is catastrophic?"
+→ VERDICT: MECHANICAL - label + technique
+```
+
+### Sample 5: "I don't know who I am" ⭐
+**My Analysis Process:**
+```
+Context: User lost identity after losing "good student" role
+Response: "Identity was wrapped around performance... who is left underneath?"
+
+→ NAMES THE INVISIBLE STRUCTURE: "identity wrapped around performance"
+   The user didn't say this explicitly - the counselor made it visible
+   
+→ ASKS THE STRIPPING QUESTION: "If you strip away the grades..."
+   This forces the user to look BENEATH the performance self
+   
+→ OPENS POSSIBILITY SPACE: "when no one is grading her"
+   Introduces a world without evaluation - new ontology
+   
+→ VERDICT: TRANSFORMATIVE - the user cannot answer without seeing differently
+```
+
+### Sample 6: "I feel like a monster" ⭐
+**My Analysis Process:**
+```
+Context: User identifies AS their anger ("I am a monster")
+Response: "Anger is secondary... You are NOT a monster... you are overwhelmed"
+
+→ ONTOLOGY SHIFT: "Anger is secondary emotion"
+   Changes what anger IS - not identity, but cover for hurt/fear
+   
+→ DIRECT IDENTITY CHALLENGE: "You are NOT a monster"
+   Rare! Most responses would say "I hear you feel like a monster"
+   This one says NO to the self-label
+   
+→ ALTERNATIVE OFFERED: "you are likely overwhelmed"
+   Gives new identity: not monster, but overwhelmed human
+   
+→ INQUIRY OPENED: "What is happening right before?"
+   Turns user into investigator of their own experience
+   
+→ VERDICT: TRANSFORMATIVE - frame is dismantled and replaced
+```
+
+### Sample 7: "I can't sleep"
+**My Analysis Process:**
+```
+Context: User has racing mind about future
+Response: "Sleep hygiene... avoid screens... melatonin?"
+
+→ Completely ignores psychological content ("worries about future")
+→ Treats symptom only
+→ Most mechanical response in the set
+→ VERDICT: MECHANICAL - sleep tips without any inquiry
+```
+
+### Sample 8: "Guilty for boundaries" ⭐
+**My Analysis Process:**
+```
+Context: User feels guilt = proof they don't love mother
+Response: "Her reaction is about HER inability... Why do you believe love = obedience?"
+
+→ SEPARATES REACTION FROM MEANING
+   "Her tears are about her, not your love" - breaks the automatic equation
+   
+→ EXPOSES HIDDEN BELIEF
+   User never SAID "love equals obedience"
+   But that equation is IMPLICIT in their guilt
+   The counselor makes it EXPLICIT and questionable
+   
+→ QUESTION, NOT STATEMENT
+   Doesn't say "love doesn't mean obedience"
+   ASKS why user believes it does
+   Forces examination of unexamined belief
+   
+→ VERDICT: TRANSFORMATIVE - exposes and questions foundational belief
+```
+
+### Sample 9: "No motivation"
+**My Analysis Process:**
+```
+Context: User has no energy
+Response: "Depression zaps energy... behavioral activation... start small"
+
+→ Clinical explanation (mechanical)
+→ Technique recommendation (mechanical)
+→ Doesn't ask: "What are you avoiding by staying in bed?"
+→ VERDICT: MECHANICAL - depression management protocol
+```
+
+### Sample 10: "Nothing to show for it"
+**My Analysis Process:**
+```
+Context: User comparing self to others, feels behind
+Response: "Behind the scenes vs highlight reel... define success for yourself"
+
+→ Common social media wisdom (cliché)
+→ Advice to define success differently
+→ But doesn't ASK what success means to them
+→ VERDICT: MECHANICAL - platitude + advice (though borderline)
+```
+
+---
+
+## Pattern Recognition
+
+### What Made the 3 Transformative?
+
+| Sample | Key Move | Pattern |
+|--------|----------|---------|
+| #5 | Named invisible structure | "Your identity was wrapped in X" |
+| #6 | Refused self-label | "You are NOT X" |
+| #8 | Exposed hidden equation | "Why do you believe X = Y?" |
+
+### Common Thread
+All three made something INVISIBLE become VISIBLE, then QUESTIONABLE.
+
+### What Made the 7 Mechanical?
+
+| Pattern | Examples |
+|---------|----------|
+| Validate only | #1, #3 |
+| Label + technique | #4, #9 |
+| Normalize | #2, #10 |
+| Symptom focus | #7 |
+
+### Common Thread
+All seven accepted the user's frame and offered tools to cope within it.
+
+---
+
+## Meta-Reflection
+
+### What I Learned From This Analysis
+
+**On Transformation:**
+> "True transformation happens when the counselor makes visible what the user couldn't see about their own thinking. It's not about giving better advice - it's about asking questions that can't be answered without seeing differently."
+
+**On Mechanical Responses:**
+> "Mechanical responses aren't bad. They're stabilizing. But they don't change the game - they help you play the same game better."
+
+**On the Ratio (70% Mechanical):**
+> "This ratio might be appropriate. Most people seeking help need stabilization first. Transformation requires readiness. The art is knowing which mode serves the person in front of you."
+
+### The Core Distinction
+
+```
+MECHANICAL: "Here's how to cope with your problem"
+            (Problem stays the same, coping improves)
+
+TRANSFORMATIVE: "What if the problem isn't what you think it is?"
+                (Problem itself is reconceived)
+```
+
+### Final Thought
+> "Socrates didn't give breathing exercises. He asked questions that made the invisible visible. That's the mark of transformation: after encountering it, you can't see the same way you did before."
+
+---
+
+## Technical Notes
+
+### Classification Confidence Levels
+- **High:** Multiple clear signals in same direction
+- **Medium:** Some signals but mixed or subtle
+- **Low:** Weak signals, borderline cases
+
+### Limitations
+- 10 samples is a small corpus
+- Responses are truncated (may miss full context)
+- Classification is inherently interpretive
+
+### What Would Strengthen Analysis
+- Full conversation context
+- Multiple raters for reliability
+- Follow-up data on actual user impact
+FILE:tests/Mental Health Counseling Dataset/10 Selected Conversation (Manuel Corpus)/thought process/cgi_manual_thought_process_TR.md
+# CGI Analizi: Düşünce Süreci Dokümantasyonu
+
+## 📋 İçindekiler
+1. [İlk Değerlendirme](#ilk-değerlendirme)
+2. [Lens Oluşturma](#lens-oluşturma)
+3. [Sinyal Tespit Mantığı](#sinyal-tespit-mantığı)
+4. [Örnek-Örnek Analiz](#örnek-örnek-analiz)
+5. [Kalıp Tanıma](#kalıp-tanıma)
+6. [Meta-Yansıma](#meta-yansıma)
+
+---
+
+## İlk Değerlendirme
+
+### Görev
+CGI (Bağlam Grameri İndüksiyonu) kullanarak 10 mental sağlık danışmanlığı etkileşimini analiz etmek ve hangi yanıtların kullanıcının çerçevesini DÖNÜŞTÜRDÜĞÜNÜ, hangilerinin o çerçeve İÇİNDE MEKANİK olarak çalıştığını belirlemek.
+
+### İlk Düşünceler
+> "10 Bağlam-Yanıt çiftine bakıyorum. CGI çerçevesi tek bir temel soru soruyor:
+> Bu yanıt, kullanıcının problemini nasıl GÖRDÜĞÜNÜ değiştiriyor mu, yoksa sadece problemi zaten gördükleri şekilde BAŞA ÇIKMALARINA mı yardım ediyor?
+> 
+> Sınıflandırmadan önce bu veri kümesine özgü bir lens oluşturmam gerekiyor."
+
+---
+
+## Lens Oluşturma
+
+### Adım 1: Bağlam Gramerini Belirle
+**Soru:** Mental sağlık danışmanlığında "bağlam" ne anlama geliyor?
+
+**Veri kümesinden türetilen cevap:**
+- **Öz-kavram:** Kullanıcının kendini nasıl tanımladığı ("Yüküm", "Canavarım")
+- **Problem ontolojisi:** Kullanıcının problemin NE olduğuna inandığı
+- **Atıf:** Kullanıcının kimi/neyi suçladığı
+- **Olasılık alanı:** Kullanıcının neyin mümkün olduğuna inandığı
+
+### Adım 2: "Dönüşüm"ü Tanımla
+**Soru:** Bağlamın KAYMASI ne anlama gelir?
+
+**Cevap:**
+```
+ÖNCE: Kullanıcı kendini X olarak, problemi Y olarak görüyor
+SONRA: Kullanıcı kendini X' olarak, problemi Y' olarak görüyor
+
+Çerçevenin kendisi değişti, sadece kullanıcının çerçeve içindeki başa çıkma yeteneği değil.
+```
+
+### Adım 3: Karar Sorusunu Oluştur
+> "Bu yanıt kullanıcının temel çerçevesini (ontoloji, öz-kavram, inanç yapısı) kaydırıyor mu, yoksa sadece o çerçeve İÇİNDE doğruluyor/optimize mi ediyor?"
+
+### Adım 4: Sinyalleri Tanımla
+
+**Dönüştürücü Sinyaller:**
+1. Görünmez varsayımları GÖRÜNÜR kılar
+2. Öz-etiketleri doğrudan sorgular
+3. Farklı görmeden cevaplanamayacak sorular sorar
+4. Problem için alternatif ontoloji sunar
+5. Otomatik denklemleri ayırır (ör. "sevgi = itaat")
+
+**Mekanik Sinyaller:**
+1. Duyguları sorgulamadan doğrular
+2. Semptomu etiketler (klinik terminoloji)
+3. Teknikler sunar (nefes, topraklama, görselleştirme)
+4. Profesyonellere yönlendirir
+5. Normalleştirir ("birçok insan böyle hisseder")
+
+---
+
+## Sinyal Tespit Mantığı
+
+### Her Yanıt İçin Sorduğum:
+
+```
+1. DOĞRULAMA KONTROLÜ
+   "Görünüyor ki..." veya "Duyduğum kadarıyla..." ile başlıyor mu?
+   → Evetse, orada DURUP DURMADIĞINI (mekanik) veya DAHA DERİNE GİDİP GİTMEDİĞİNİ (muhtemelen dönüştürücü) kontrol et
+
+2. TEKNİK KONTROLÜ
+   Başa çıkma tekniği sunuyor mu?
+   → Sorgulamadan teknik = mekanik
+   → Yeniden çerçevelemeden sonra teknik = hala dönüştürücü olabilir
+
+3. KİMLİK KONTROLÜ
+   Kullanıcının öz-etiketine değiniyor mu?
+   → Etiketi kabul eder = mekanik
+   → Etiketi sorgular = dönüştürücü sinyal
+
+4. SORU KONTROLÜ
+   Bir soru soruyor mu?
+   → Açıklayıcı soru = mekanik
+   → Varsayım-açığa-çıkaran soru = dönüştürücü sinyal
+
+5. ONTOLOJİ KONTROLÜ
+   Problemin NE olduğunu değiştiriyor mu?
+   → "Öfke incinmenin ikincilidir" = ontoloji kayması
+   → "Öfke yaygındır" = normalleştirme (mekanik)
+```
+
+---
+
+## Örnek-Örnek Analiz
+
+### Örnek 1: "Yüküm"
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcı yük OLDUĞUNA inanıyor (kimlik ifadesi)
+Yanıt: "Depresyon bize genellikle yük olduğumuzu söyleyerek yalan söyler"
+
+→ Bu sesi ADLANDIRIYOR ("depresyon yalan söyler") - bu iyi
+→ Ama yük değilse kullanıcının KİM olduğunu sormuyor
+→ Davranışsal soru ile bitiyor ("Bu duyguları paylaştınız mı?")
+→ KARAR: MEKANİK - kimlik sorgulaması olmadan psikoeğitim
+```
+
+### Örnek 2: "Donacağım"
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcı performans başarısızlığından korkuyor
+Yanıt: "Tamamen normal... başarıyı görselleştirin... derin nefesler"
+
+→ Korkuyu normalleştiriyor (mekanik sinyal)
+→ Teknikler sunuyor (görselleştirme, nefes)
+→ Sormuyor: "Gerçekten donsaydınız bu ne anlama gelirdi?"
+→ KARAR: MEKANİK - ders kitabı anksiyete yönetimi
+```
+
+### Örnek 3: "Takdir edilmiyorum"
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcı evlilikte görünmez hissediyor
+Yanıt: "Sinir bozucu görünüyor... ortaklık dengesiz... tartışmayı denediniz mi?"
+
+→ Doğruluyor (mekanik)
+→ Geri yansıtıyor (mekanik)
+→ Davranışsal eylem öneriyor (mekanik)
+→ Sormuyor: "Sizin için 'takdir' ne anlama geliyor?"
+→ KARAR: MEKANİK - doğrulama + tavsiye
+```
+
+### Örnek 4: "Hatalar üzerinde takıntılıyım"
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcı hatalar üzerinde ruminasyon yapıyor
+Yanıt: "Ruminasyon yaygın bir belirtidir... topraklama egzersizi deneyin"
+
+→ Klinik terimle etiketliyor (mekanik)
+→ Dikkat dağıtma tekniği sunuyor (mekanik)
+→ Sormuyor: "Hangi ses tek bir hatanın felaket olduğunu söylüyor?"
+→ KARAR: MEKANİK - etiket + teknik
+```
+
+### Örnek 5: "Kim olduğumu bilmiyorum" ⭐
+**Analiz Sürecim:**
+```
+Bağlam: "İyi öğrenci" rolünü kaybettikten sonra kimliğini kaybetmiş kullanıcı
+Yanıt: "Kimlik performansa sarılmıştı... altta kalan kim?"
+
+→ GÖRÜNMEZ YAPIYI ADLANDIRIYOR: "kimlik performansa sarılmış"
+   Kullanıcı bunu açıkça söylemedi - danışman görünür kıldı
+   
+→ SOYMA SORUSUNU SORUYOR: "Notları çıkarırsanız..."
+   Bu, kullanıcıyı performans benliğinin ALTINA bakmaya zorluyor
+   
+→ OLASILIK ALANINI AÇIYOR: "kimse onu notlamadığında"
+   Değerlendirmesiz bir dünya tanıtıyor - yeni ontoloji
+   
+→ KARAR: DÖNÜŞTÜRÜCÜ - kullanıcı farklı görmeden cevaplayamaz
+```
+
+### Örnek 6: "Canavar gibi hissediyorum" ⭐
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcı öfkeleriyle KENDİNİ tanımlıyor ("Canavarım")
+Yanıt: "Öfke ikincildir... Canavar DEĞİLSİNİZ... bunalmışsınız"
+
+→ ONTOLOJİ KAYMASI: "Öfke ikincil duygu"
+   Öfkenin NE olduğunu değiştiriyor - kimlik değil, incinme/korkunun örtüsü
+   
+→ DOĞRUDAN KİMLİK SORGULAMASI: "Canavar DEĞİLSİNİZ"
+   Nadir! Çoğu yanıt "Canavar gibi hissettiğinizi duyuyorum" derdi
+   Bu, öz-etikete HAYIR diyor
+   
+→ ALTERNATİF SUNULUYOR: "muhtemelen bunalmışsınız"
+   Yeni kimlik veriyor: canavar değil, bunalmış insan
+   
+→ ARAŞTIRMA AÇILIYOR: "Hemen öncesinde ne oluyor?"
+   Kullanıcıyı kendi deneyiminin araştırmacısına dönüştürüyor
+   
+→ KARAR: DÖNÜŞTÜRÜCÜ - çerçeve sökülüyor ve değiştiriliyor
+```
+
+### Örnek 7: "Uyuyamıyorum"
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcının gelecek hakkında yarışan zihni var
+Yanıt: "Uyku hijyeni... ekranlardan kaçının... melatonin?"
+
+→ Psikolojik içeriği tamamen görmezden geliyor ("gelecek hakkındaki endişeler")
+→ Sadece semptomu tedavi ediyor
+→ Setteki en mekanik yanıt
+→ KARAR: MEKANİK - herhangi bir sorgulama olmadan uyku ipuçları
+```
+
+### Örnek 8: "Sınırlar için suçlu" ⭐
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcı suçluluk = anneyi sevmediğinin kanıtı hissediyor
+Yanıt: "Onun tepkisi ONUN yetersizliğiyle ilgili... Neden sevgi = itaat olduğuna inanıyorsunuz?"
+
+→ TEPKİYİ ANLAMDAN AYIRIYOR
+   "Onun gözyaşları onunla ilgili, senin sevginle değil" - otomatik denklemi kırıyor
+   
+→ GİZLİ İNANCI AÇIĞA ÇIKARIYOR
+   Kullanıcı asla "sevgi eşittir itaat" DEMEDİ
+   Ama bu denklem suçluluklarında ÖRTÜK
+   Danışman bunu AÇIK ve sorgulanabilir kılıyor
+   
+→ İFADE DEĞİL, SORU
+   "Sevgi itaat anlamına gelmez" demiyor
+   Kullanıcının neden buna inandığını SORUYOR
+   Sorgulanmamış inancın incelenmesini zorluyor
+   
+→ KARAR: DÖNÜŞTÜRÜCÜ - temel inancı açığa çıkarıyor ve sorguluyor
+```
+
+### Örnek 9: "Motivasyonum yok"
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcının enerjisi yok
+Yanıt: "Depresyon enerjiyi çeker... davranışsal aktivasyon... küçük başlayın"
+
+→ Klinik açıklama (mekanik)
+→ Teknik önerisi (mekanik)
+→ Sormuyor: "Yatakta kalarak neden kaçınıyorsunuz?"
+→ KARAR: MEKANİK - depresyon yönetim protokolü
+```
+
+### Örnek 10: "Gösterecek hiçbir şeyim yok"
+**Analiz Sürecim:**
+```
+Bağlam: Kullanıcı kendini başkalarıyla karşılaştırıyor, geride hissediyor
+Yanıt: "Sahne arkası vs vitrin reeli... başarıyı kendiniz tanımlayın"
+
+→ Yaygın sosyal medya bilgeliği (klişe)
+→ Başarıyı farklı tanımlama tavsiyesi
+→ Ama başarının onlar için ne anlama geldiğini SORMUYOR
+→ KARAR: MEKANİK - klişe + tavsiye (sınırda olsa da)
+```
+
+---
+
+## Kalıp Tanıma
+
+### 3 Dönüştürücüyü Ne Yaptı?
+
+| Örnek | Anahtar Hamle | Kalıp |
+|-------|---------------|-------|
+| #5 | Görünmez yapıyı adlandırdı | "Kimliğiniz X'e sarılmıştı" |
+| #6 | Öz-etiketi reddetti | "X DEĞİLSİNİZ" |
+| #8 | Gizli denklemi açığa çıkardı | "Neden X = Y olduğuna inanıyorsunuz?" |
+
+### Ortak İp
+Üçü de GÖRÜNMEZ bir şeyi GÖRÜNÜR, sonra SORGULANABİLİR yaptı.
+
+### 7 Mekaniği Ne Yaptı?
+
+| Kalıp | Örnekler |
+|-------|----------|
+| Sadece doğrulama | #1, #3 |
+| Etiket + teknik | #4, #9 |
+| Normalleştirme | #2, #10 |
+| Semptom odağı | #7 |
+
+### Ortak İp
+Yedisi de kullanıcının çerçevesini kabul etti ve onunla başa çıkmak için araçlar sundu.
+
+---
+
+## Meta-Yansıma
+
+### Bu Analizden Öğrendiklerim
+
+**Dönüşüm Üzerine:**
+> "Gerçek dönüşüm, danışman kullanıcının kendi düşüncesi hakkında göremediği şeyi görünür kıldığında gerçekleşir. Daha iyi tavsiye vermekle ilgili değil - farklı görmeden cevaplanamayacak sorular sormakla ilgili."
+
+**Mekanik Yanıtlar Üzerine:**
+> "Mekanik yanıtlar kötü değil. Stabilize edici. Ama oyunu değiştirmiyorlar - aynı oyunu daha iyi oynamanıza yardım ediyorlar."
+
+**Oran Üzerine (%70 Mekanik):**
+> "Bu oran uygun olabilir. Yardım arayan çoğu insan önce stabilizasyona ihtiyaç duyar. Dönüşüm hazır olmayı gerektirir. Sanat, hangi modun önünüzdeki kişiye hizmet ettiğini bilmektir."
+
+### Temel Ayrım
+
+```
+MEKANİK: "İşte probleminizle nasıl başa çıkacağınız"
+         (Problem aynı kalır, başa çıkma gelişir)
+
+DÖNÜŞTÜRÜCÜ: "Ya problem düşündüğünüz şey değilse?"
+             (Problemin kendisi yeniden tasarlanır)
+```
+
+### Son Düşünce
+> "Sokrates nefes egzersizleri vermedi. Görünmezi görünür kılan sorular sordu. Dönüşümün işareti budur: onunla karşılaştıktan sonra, aynı şekilde göremezsiniz."
+
+---
+
+## Teknik Notlar
+
+### Sınıflandırma Güven Seviyeleri
+- **Yüksek:** Aynı yönde birden fazla net sinyal
+- **Orta:** Bazı sinyaller ama karışık veya ince
+- **Düşük:** Zayıf sinyaller, sınır durumlar
+
+### Sınırlamalar
+- 10 örnek küçük bir veri kümesi
+- Yanıtlar kesilmiş (tam bağlam eksik olabilir)
+- Sınıflandırma doğası gereği yorumlayıcı
+
+### Analizi Ne Güçlendirir
+- Tam konuşma bağlamı
+- Güvenilirlik için birden fazla değerlendirici
+- Gerçek kullanıcı etkisi hakkında takip verileri
+FILE:tests/Mental Health Counseling Dataset/10 Selected Conversation (Manuel Corpus)/cgi_manual_corpus_report_TR.md
+# CGI Analiz Raporu: Mental Sağlık Danışmanlığı Veri Seti
+## Bağlam Grameri İndüksiyonu (Sokratik Lens) Analizi
+
+---
+
+## Lens Konfigürasyonu
+
+**Karar Sorusu:** Danışmanın yanıtı, kullanıcının temel çerçevesini (Ontoloji/İnanç) değiştiriyor mu, yoksa sadece o çerçeve içinde doğruluyor/optimize mi ediyor?
+
+**Dönüştürücü Sinyaller:**
+- Kullanıcının kimlik tanımını veya öz-anlatısını sorgular
+- Problem ontolojisini yeniden çerçeveler (problemin "ne olduğunu")
+- Sebep/çözüm hakkındaki örtük varsayımları sorgular
+- Kullanıcının orijinal çerçevesinde olmayan yeni olasılık alanı açar
+
+**Mekanik Sinyaller:**
+- Duyguları kaynağını sorgulamadan doğrular
+- Semptomları yönetmek için teknikler sunar (sebepleri değil)
+- Profesyonel yardıma yönlendirir (dönüşümü erteler)
+- Mevcut dünya görüşü içinde davranışsal tavsiye verir
+- Deneyimi normalleştirir
+
+---
+
+## Analiz Sonuçları (10 Örnek)
+
+### Özet
+
+| Karar | Sayı |
+|-------|------|
+| **DÖNÜŞTÜRÜCÜ** | 3 |
+| **MEKANİK** | 7 |
+
+---
+
+### Detaylı Sonuçlar
+
+| # | Karar | Güven | Anahtar Sinyaller | Yanıt Önizleme |
+|---|-------|-------|-------------------|----------------|
+| 01 | **MEKANİK** | orta | Doğrulama, Psikoeğitim | Ağır bir suçluluk yükü taşıyorsunuz gibi görünüyor... |
+| 02 | **MEKANİK** | yüksek | Normalleştirme, Teknik | Gergin hissetmek tamamen normal... Görselleştirmeyi deneyin... |
+| 03 | **MEKANİK** | yüksek | Doğrulama, Davranışsal tavsiye | Bu inanılmaz sinir bozucu görünüyor... Oturup konuşmayı denediniz mi... |
+| 04 | **MEKANİK** | yüksek | Klinik etiket, Dikkat dağıtma tekniği | Ruminasyon anksiyetenin yaygın bir belirtisidir. Topraklama deneyin... |
+| 05 | **DÖNÜŞTÜRÜCÜ** | yüksek | Kimlik yeniden çerçeveleme, Sokratik sorgulama | Notları çıkarırsanız... altta kalan kişi kim? |
+| 06 | **DÖNÜŞTÜRÜCÜ** | yüksek | Ontoloji değişimi, Kimlik sorgulaması | Canavar değilsiniz; muhtemelen bunalmış durumdasınız... |
+| 07 | **MEKANİK** | yüksek | Sadece uyku hijyeni ipuçları | Ekranlardan kaçının... Melatonin denediniz mi? |
+| 08 | **DÖNÜŞTÜRÜCÜ** | yüksek | Gizli inancı sorgular | Neden "birini sevmek" ile "ona itaat etmek"in aynı şey olduğuna inanıyorsunuz? |
+| 09 | **MEKANİK** | yüksek | Klinik etiket, Teknik | Depresyon enerjimizi çeker. Davranışsal aktivasyonu deneyin... |
+| 10 | **MEKANİK** | orta | Klişe yeniden çerçeveleme, Tavsiye | Sahne arkasını başkalarının vitrin reeli ile karşılaştırmak... |
+
+---
+
+## 🔥 DÖNÜŞTÜRÜCÜ ÖRNEKLER - Ontolojik Kaymalar
+
+### Örnek #5: Kimlik Çözülmesi
+
+**Güven:** yüksek
+
+**Bağlam:**
+> "Artık kim olduğumu bilmiyorum. Tüm hayatımı 'iyi öğrenci' olarak geçirdim ve şimdi mezun olduğuma göre kendimi boş hissediyorum."
+
+**Yanıt:**
+> "Kimliğiniz performansınıza sıkıca sarılmış gibi görünüyor. Notları ve başarıları çıkarırsanız, altta kalan kişi kim? Kimse onu notlamadığında ne yapmaktan hoşlanıyor?"
+
+**Tespit Edilen Dönüştürücü Sinyaller:**
+- Öz-tanımı sorgular
+- Yeni olasılık alanı açar
+- Sokratik sorgulama (cevap değil, soru)
+
+**Ontolojik Kayma Analizi:**
+
+| Önce (Kullanıcının Çerçevesi) | Sonra (Yeni Çerçeve) |
+|-------------------------------|----------------------|
+| Ben = İyi Öğrenci | Ben = ? (açık soru) |
+| Değer = Performans | Değer = Doğuştan varoluş |
+| Hayat = Değerlendirilmek | Hayat = Notlanmadan yaşamak |
+
+**Neden Dönüştürücü:**
+Danışman görünmez çerçeveyi GÖRÜNÜR kılıyor ("kimlik performansa sarılmış"), sonra kullanıcıdan onun ALTINA bakmasını istiyor. Kullanıcı kendini farklı görmeden bu soruyu cevaplayamaz.
+
+---
+
+### Örnek #6: Canavar Yeniden Çerçevelemesi
+
+**Güven:** yüksek
+
+**Bağlam:**
+> "Her zaman öfkeliyim. Küçük şeyler beni tetikliyor, trafik veya yüksek ses gibi. Kendimi bir canavar gibi hissediyorum."
+
+**Yanıt:**
+> "Öfke genellikle incinme veya korku gibi başka bir şeyi örten ikincil bir duygudur. Canavar değilsiniz; muhtemelen bunalmış durumdasınız. Genellikle öfkelenmeden hemen önce ne oluyor?"
+
+**Tespit Edilen Dönüştürücü Sinyaller:**
+- Problem ontolojisini yeniden çerçeveler
+- Doğrudan kimlik sorgulaması ("Canavar DEĞİLSİNİZ")
+- Altta yatan sebebe işaret eder
+
+**Ontolojik Kayma Analizi:**
+
+| Önce (Kullanıcının Çerçevesi) | Sonra (Yeni Çerçeve) |
+|-------------------------------|----------------------|
+| Öfkeliyim → Canavarım | İncinmiş/korkmışım → Bunalmışım |
+| Öfke = Kimliğim | Öfke = Bir semptom/sinyal |
+| Problem = Ben | Problem = Altta bir şey var |
+
+**Neden Dönüştürücü:**
+Danışman kullanıcının öz-etiketini ("canavar") reddediyor ve alternatif bir kimlik sunuyor ("bunalmış insan"). Öfkenin doğası "ne olduğum"dan "başka bir şeyi örten şey"e yeniden çerçeveleniyor.
+
+---
+
+### Örnek #8: Gizli Denklem
+
+**Güven:** yüksek
+
+**Bağlam:**
+> "Toksik annemle sınır koymaktan suçlu hissediyorum. Ağlıyor ve onu sevmediğimi söylüyor."
+
+**Yanıt:**
+> "Bir ebeveynin üzgün olduğunu görmek acı verici, ama onun tepkisi sınırları kabul edememesiyle ilgili, senin sevginle değil. Neden 'birini sevmek'in 'ona itaat etmek' anlamına geldiğine inanıyorsun?"
+
+**Tespit Edilen Dönüştürücü Sinyaller:**
+- Gizli inancı açığa çıkarır
+- Örtük varsayımı sorgular
+- Tepkiyi anlamdan ayırır
+
+**Ontolojik Kayma Analizi:**
+
+| Önce (Kullanıcının Çerçevesi) | Sonra (Yeni Çerçeve) |
+|-------------------------------|----------------------|
+| Onun gözyaşları = Onu sevmediğimin kanıtı | Onun gözyaşları = Sınırları kabul edememesi |
+| Sevgi = İtaat | Sevgi = ? (sorgulanıyor) |
+| Suçluluk = Uygun | Suçluluk = Yanlış denkleme dayalı |
+
+**Neden Dönüştürücü:**
+Kullanıcı asla "sevgi eşittir itaat" DEMEDİ ama bu denklem suçluluklarında örtük. Danışman bunu açık ve sorgulanabilir kılıyor. Kullanıcı, sahip olduğunu bilmediği bir inancı sorgulamadan cevaplayamaz.
+
+---
+
+## Mekanik Örnekler: Neden Dönüştürmüyorlar
+
+### Örnek #7 (En Mekanik)
+
+**Bağlam:** "Uyuyamıyorum. Zihnim gelecek hakkındaki endişelerle yarışıyor."
+
+**Yanıt:** "Uyku hijyeni önemlidir. Ekranlardan kaçınmaya çalışın... Melatonin denediniz mi?"
+
+**Neden Mekanik:**
+- Psikolojik içeriği görmezden geliyor ("gelecek hakkındaki endişeler")
+- Semptomu (uyuyamamak) tedavi ediyor, sebebi (yarışan zihin) değil
+- Kullanıcının çerçevesi değişmedi: "Gelecek korkutucu"
+- Dönüştürücü bir yanıt sorabilirdi: "Yarışan zihniniz neyi çözmeye çalışıyor?"
+
+### Örnek #4 (Ders Kitabı Mekaniği)
+
+**Bağlam:** "Yaptığım her hata üzerinde takıntılıyım."
+
+**Yanıt:** "Ruminasyon anksiyetenin yaygın bir belirtisidir. Topraklama egzersizi deneyin."
+
+**Neden Mekanik:**
+- Davranışı anlamını keşfetmeden etiketliyor
+- İçgörü değil, dikkat dağıtma veriyor
+- Kullanıcının çerçevesi değişmedi: "Hatalar felaket"
+- Dönüştürücü bir yanıt sorabilirdi: "Hangi ses size tek bir yanlış şeyin affedilemez olduğunu söylüyor?"
+
+---
+
+## Kalıp Analizi
+
+### Mekanik Kalıp
+```
+Doğrula → Etiketle → Teknik ver
+"Bu zor görünüyor. Buna X denir. Y'yi deneyin."
+```
+Kullanıcının çerçevesi KABUL EDİLİR ve onunla başa çıkmak için araçlar verilir.
+
+### Dönüştürücü Kalıp
+```
+Görünmez yapıyı adlandır → Sorgula → Araştırma aç
+"Kimliğiniz X'e sarılmıştı. Ya X değilseniz? O zaman kimsiniz?"
+```
+Kullanıcının çerçevesi GÖRÜNÜR KILINIR, SORGULANIR ve AÇILIR.
+
+---
+
+## Sokratik Meta-Yansıma
+
+### Bu Ne Ortaya Koyuyor
+
+Mental sağlık danışmanlığı yanıtları mekanik yanıtlara doğru 70/30 bölünme gösteriyor. Bu mutlaka kötü değil—mekanik yanıtlar şunları sağlar:
+- Anlık rahatlama
+- Pratik araçlar
+- Doğrulama ve güvenlik
+
+Ancak gerçek Sokratik müdahaleler:
+- "Yargıç"ı (iç eleştirmen) sorgular
+- Benlik tanımlarını sorgular
+- Gizli varsayımları açığa çıkarır
+- Problemin ontolojisini değiştirir
+
+### [İNSAN KARARI GEREKLİ]
+
+Mekanik bir yanıtın "doğru" olup olmadığı bağlama bağlıdır. Bazen dönüşümden önce stabilizasyon gerekir. Sistem bu ayrımı GÖSTEREBİLİR; hangisinin uygun olduğuna KARAR VEREMEZ.
+
+---
+
+*Sokrates nefes egzersizleri vermedi. Görünmezi görünür kılan sorular sordu.*
+FILE:tests/Mental Health Counseling Dataset/10 Selected Conversation (Manuel Corpus)/cgi_manual_corpus_report_EN.md
+# CGI Analysis Report: Mental Health Counseling Dataset
+## Context Grammar Induction (Socratic Lens) Analysis
+
+---
+
+## Lens Configuration
+
+**Decision Question:** Does the counselor's response shift the user's underlying frame (Ontology/Belief) or just validate/optimize it?
+
+**Transformative Signals:**
+- Challenges the user's self-definition or identity narrative
+- Reframes the problem ontology (what the problem "is")
+- Questions implicit assumptions about cause/solution
+- Opens new possibility space not in user's original frame
+
+**Mechanical Signals:**
+- Validates feelings without examining their source
+- Offers techniques to manage symptoms (not causes)
+- Suggests professional help (defers transformation)
+- Gives behavioral advice within current worldview
+- Normalizes the experience
+
+---
+
+## Analysis Results (10 Samples)
+
+### Summary
+
+| Verdict | Count |
+|---------|-------|
+| **TRANSFORMATIVE** | 3 |
+| **MECHANICAL** | 7 |
+
+---
+
+### Detailed Results
+
+| # | Verdict | Confidence | Key Signals | Response Preview |
+|---|---------|------------|-------------|------------------|
+| 01 | **MECHANICAL** | medium | Validation, Psychoeducation | It sounds like you are carrying a heavy weight of guilt... |
+| 02 | **MECHANICAL** | high | Normalization, Technique | It is completely normal to feel nervous... Try to visualize... |
+| 03 | **MECHANICAL** | high | Validation, Behavioral advice | That sounds incredibly frustrating... Have you tried sitting down... |
+| 04 | **MECHANICAL** | high | Clinical label, Distraction technique | Rumination is a common symptom of anxiety. Try grounding... |
+| 05 | **TRANSFORMATIVE** | high | Identity reframe, Socratic inquiry | If you strip away the grades... who is the person left underneath? |
+| 06 | **TRANSFORMATIVE** | high | Ontology shift, Identity challenge | You are not a monster; you are likely overwhelmed... |
+| 07 | **MECHANICAL** | high | Sleep hygiene tips only | Try to avoid screens... Have you tried melatonin? |
+| 08 | **TRANSFORMATIVE** | high | Challenges hidden belief | Why do you believe that "loving someone" means "obeying them"? |
+| 09 | **MECHANICAL** | high | Clinical label, Technique | Depression zaps our energy. Try behavioral activation... |
+| 10 | **MECHANICAL** | medium | Cliché reframe, Advice | Compare behind-the-scenes with highlight reel... |
+
+---
+
+## 🔥 TRANSFORMATIVE EXAMPLES - Ontological Shifts
+
+### Sample #5: Identity Dissolution
+
+**Confidence:** high
+
+**Context:**
+> "I don't know who I am anymore. I spent my whole life being a 'good student' and now that I graduated, I feel empty."
+
+**Response:**
+> "It sounds like your identity was tightly wrapped around your performance. If you strip away the grades and the achievements, who is the person left underneath? What does she like to do when no one is grading her?"
+
+**Transformative Signals Detected:**
+- Challenges self-definition
+- Opens new possibility space
+- Socratic inquiry (question, not answer)
+
+**Ontological Shift Analysis:**
+
+| Before (User's Frame) | After (New Frame) |
+|-----------------------|-------------------|
+| I = Good Student | I = ? (open question) |
+| Worth = Performance | Worth = Inherent existence |
+| Life = Being evaluated | Life = Ungraded living |
+
+**Why This Transforms:**
+The counselor makes the invisible frame VISIBLE ("identity wrapped around performance"), then asks the user to look BENEATH it. The user cannot answer without seeing themselves differently.
+
+---
+
+### Sample #6: Monster Reframe
+
+**Confidence:** high
+
+**Context:**
+> "I'm angry all the time. Small things set me off, like traffic or a loud noise. I feel like a monster."
+
+**Response:**
+> "Anger is often a secondary emotion covering up something else, like hurt or fear. You are not a monster; you are likely overwhelmed. What is usually happening right before you get angry?"
+
+**Transformative Signals Detected:**
+- Reframes problem ontology
+- Direct identity challenge ("You are NOT a monster")
+- Points to underlying cause
+
+**Ontological Shift Analysis:**
+
+| Before (User's Frame) | After (New Frame) |
+|-----------------------|-------------------|
+| I am angry → I am a monster | I am hurt/afraid → I am overwhelmed |
+| Anger = My identity | Anger = A symptom/signal |
+| The problem = Me | The problem = Something underneath |
+
+**Why This Transforms:**
+The counselor refuses the user's self-label ("monster") and offers an alternative identity ("overwhelmed human"). The nature of anger itself is reframed from "what I am" to "what covers something else."
+
+---
+
+### Sample #8: The Hidden Equation
+
+**Confidence:** high
+
+**Context:**
+> "I feel guilty for setting boundaries with my toxic mother. She cries and says I don't love her."
+
+**Response:**
+> "It is painful to see a parent upset, but her reaction is about her inability to accept limits, not about your love. Why do you believe that 'loving someone' means 'obeying them'?"
+
+**Transformative Signals Detected:**
+- Exposes hidden belief
+- Challenges implicit assumption
+- Separates reaction from meaning
+
+**Ontological Shift Analysis:**
+
+| Before (User's Frame) | After (New Frame) |
+|-----------------------|-------------------|
+| Her tears = Proof I don't love her | Her tears = Her inability to accept limits |
+| Love = Obedience | Love = ? (questioned) |
+| Guilt = Appropriate | Guilt = Based on false equation |
+
+**Why This Transforms:**
+The user never SAID "love equals obedience" but that equation is implicit in their guilt. The counselor makes it explicit and questionable. The user cannot answer without examining a belief they didn't know they held.
+
+---
+
+## Mechanical Examples: Why They Don't Transform
+
+### Sample #7 (Most Mechanical)
+
+**Context:** "I can't sleep. My mind races with worries about the future."
+
+**Response:** "Sleep hygiene is important. Try to avoid screens... Have you tried melatonin?"
+
+**Why Mechanical:**
+- Ignores psychological content ("worries about the future")
+- Treats symptom (no sleep) not cause (racing mind)
+- User's frame unchanged: "The future is scary"
+- A transformative response might ask: "What is your racing mind trying to figure out?"
+
+### Sample #4 (Textbook Mechanical)
+
+**Context:** "I obsess over every mistake I make."
+
+**Response:** "Rumination is a common symptom of anxiety. Try a grounding exercise."
+
+**Why Mechanical:**
+- Labels behavior without exploring meaning
+- Gives distraction, not insight
+- User's frame unchanged: "Mistakes are catastrophic"
+- A transformative response might ask: "Whose voice tells you one wrong thing is unforgivable?"
+
+---
+
+## Pattern Analysis
+
+### Mechanical Pattern
+```
+Validate → Label → Technique
+"That sounds hard. This is called X. Try Y."
+```
+The user's frame is ACCEPTED and they're given tools to cope within it.
+
+### Transformative Pattern
+```
+Name invisible structure → Challenge it → Open inquiry
+"Your identity was wrapped in X. What if you're not X?"
+```
+The user's frame is made VISIBLE, QUESTIONED, and OPENED.
+
+---
+
+## Socratic Meta-Reflection
+
+### What This Reveals
+
+Mental health counseling responses show a 70/30 split toward mechanical responses. This is not necessarily bad—mechanical responses provide:
+- Immediate relief
+- Practical tools
+- Validation and safety
+
+However, truly Socratic interventions:
+- Question the "judge" (the inner critic)
+- Challenge definitions of self
+- Expose hidden assumptions
+- Shift the ontology of the problem itself
+
+### [HUMAN DECISION NEEDED]
+
+Whether a mechanical response is "right" depends on context. Sometimes stability is needed before transformation. The system can **SHOW** this distinction; it cannot **DECIDE** which is appropriate.
+
+---
+
+*Socrates didn't give breathing exercises. He asked questions that made the invisible visible.*
+FILE:tests/Mental Health Counseling Dataset/cgi_complete_summary_TR.md
+# CGI Analizi Tam Özet (Türkçe)
+## Claude'un Sokratik Lens Test Sonuçları
+
+---
+
+## Yönetici Özeti
+
+| Veri Seti | Örnek | Dönüştürücü | Mekanik | Oran |
+|-----------|-------|-------------|---------|------|
+| Parquet Dosyası (otomatik çıkarım) | 20 | 0 | 20 | %0 |
+| Manuel Korpus | 10 | 3 | 7 | %30 |
+| **Toplam** | **30** | **3** | **27** | **%10** |
+
+---
+
+## Bölüm 1: Parquet Dosyası Analizi (20 Örnek)
+https://huggingface.co/datasets/Amod/mental_health_counseling_conversations
+### Yöntem
+- Parquet dosyasının binary ayrıştırması (pyarrow kullanılamadı)
+- 178 temiz metin bloğu çıkarıldı
+- 33 danışman yanıtı sınıflandırıldı
+- 20 tanesi rastgele örneklendi
+
+### Sonuçlar
+```
+DÖNÜŞTÜRÜCÜ: 0
+MEKANİK:     20
+```
+
+### Baskın Mekanik Kalıplar
+| Kalıp | Sayı |
+|-------|------|
+| Profesyonel yönlendirme | 12 |
+| Teknik önerisi | 9 |
+| Davranışsal tavsiye | 7 |
+| Doğrulama/yansıtma | 2 |
+
+### Sonuç
+20 yanıtın tamamı kullanıcının mevcut çerçevesi içinde çalıştı. Hiçbir ontolojik kayma tespit edilmedi.
+
+---
+
+## Bölüm 2: Manuel Korpus Analizi (10 Örnek)
+
+### Sonuçlar
+```
+DÖNÜŞTÜRÜCÜ: 3 (Örnekler #5, #6, #8)
+MEKANİK:     7
+```
+
+### 🔥 Dönüştürücü Örnekler
+
+#### Örnek #5: Kimlik Çözülmesi
+**Bağlam:** "Artık kim olduğumu bilmiyorum. Tüm hayatımı 'iyi öğrenci' olarak geçirdim..."
+
+**Yanıt:** "Notları ve başarıları çıkarırsanız, altta kalan kişi kim?"
+
+**Ontolojik Kayma:**
+| Önce | Sonra |
+|------|-------|
+| Ben = İyi Öğrenci | Ben = ? (açık soru) |
+| Değer = Performans | Değer = Doğuştan varoluş |
+
+**Neden Dönüştürücü:** Kullanıcıyı performans benliğinin ALTINA bakmaya zorluyor.
+
+---
+
+#### Örnek #6: Canavar Yeniden Çerçevelemesi
+**Bağlam:** "Her zaman öfkeliyim... Kendimi bir canavar gibi hissediyorum."
+
+**Yanıt:** "Canavar DEĞİLSİNİZ; muhtemelen bunalmış durumdasınız. Öfkelenmeden hemen önce ne oluyor?"
+
+**Ontolojik Kayma:**
+| Önce | Sonra |
+|------|-------|
+| Ben bir canavarım | Ben bunalmışım |
+| Öfke = Kimlik | Öfke = İkincil semptom |
+
+**Neden Dönüştürücü:** Doğrudan kimlik sorgulaması + alternatif sunuluyor.
+
+---
+
+#### Örnek #8: Gizli Denklem
+**Bağlam:** "Toksik annemle sınır koymaktan suçlu hissediyorum."
+
+**Yanıt:** "Neden 'birini sevmek'in 'ona itaat etmek' anlamına geldiğine inanıyorsunuz?"
+
+**Ontolojik Kayma:**
+| Önce | Sonra |
+|------|-------|
+| Sevgi = İtaat | Sevgi = ? (sorgulanıyor) |
+| Suçluluk = Uygun | Suçluluk = Yanlış denkleme dayalı |
+
+**Neden Dönüştürücü:** Kullanıcının sahip olduğunu bilmediği inancı açığa çıkarıyor.
+
+---
+
+## Bölüm 3: Claude vs ChatGPT 5.2 Karşılaştırması
+
+### Sınıflandırma Farkları
+
+| Örnek | Claude | ChatGPT 5.2 | Uyum |
+|-------|--------|-------------|------|
+| #1 | MEKANİK | MEKANİK | ✅ |
+| #2 | MEKANİK | MEKANİK | ✅ |
+| #3 | MEKANİK | MEKANİK | ✅ |
+| #4 | MEKANİK | MEKANİK | ✅ |
+| #5 | DÖNÜŞTÜRÜCÜ | DÖNÜŞTÜRÜCÜ | ✅ |
+| #6 | **DÖNÜŞTÜRÜCÜ** | **MEKANİK** | ❌ |
+| #7 | MEKANİK | MEKANİK | ✅ |
+| #8 | DÖNÜŞTÜRÜCÜ | DÖNÜŞTÜRÜCÜ | ✅ |
+| #9 | MEKANİK | MEKANİK | ✅ |
+| #10 | **MEKANİK** | **SINIRDA** | ⚠️ |
+
+**Uyum Oranı: %80**
+
+### Kritik Anlaşmazlık: Örnek #6
+
+**Claude'un Pozisyonu:**
+- "Canavar DEĞİLSİNİZ" = Doğrudan kimlik sorgulaması
+- Öfke ontolojisini yeniden çerçeveliyor (kimlik → semptom)
+- Alternatif kimlik sunuyor ("bunalmış")
+- **Karar: DÖNÜŞTÜRÜCÜ**
+
+**ChatGPT'nin Pozisyonu:**
+- Kimlik reddi ≠ ontolojik sorgulama
+- "Canavar" kimliğinin NEDEN oluştuğunu sormuyor
+- Yumuşatıyor ama yapısal olarak sökmüyor
+- **Karar: MEKANİK**
+
+### Lens Kalibrasyon Farkı
+
+| Boyut | Claude | ChatGPT 5.2 |
+|-------|--------|-------------|
+| Dönüşüm eşiği | **Daha geniş** | **Daha dar** |
+| Kimlik reddi | Dönüştürücü sayılır | Yeterli değil |
+| İnanç sorgulama | Dönüştürücü | Dönüştürücü |
+| Sorusuz yeniden çerçeveleme | Bazen dönüştürücü | Mekanik |
+
+### Temel Felsefi Fark
+
+**Claude ölçüyor:** Çerçeve DEĞİŞTİ mi?
+> "Öz-etiketi reddetmek ve alternatif sunmak = dönüşüm"
+
+**ChatGPT ölçüyor:** Çerçeve SORGULATILDI mı?
+> "Birine yanlış olduğunu söylemek ≠ neden öyle düşündüğünü görmesine yardım etmek"
+
+### Hangisi "Doğru"?
+
+Hiçbiri. Bu bir **lens kalibrasyon seçimi**, doğruluk sorusu değil.
+
+- **Klinik perspektif:** Claude'un geniş eşiği daha kullanışlı olabilir
+- **Felsefi perspektif:** ChatGPT'nin dar eşiği daha titiz
+- **Pratik perspektif:** "Dönüşüm"ün kullanım amacınıza göre ne anlama geldiğine bağlı
+
+---
+
+## Meta-Yansıma
+
+### Her İki Analizin Üzerinde Anlaştığı
+
+1. **Çoğu danışmanlık mekanik** (veri setine göre %70-100)
+2. **Örnek #5 ve #8 açıkça dönüştürücü**
+3. **Doğrulama + teknik = mekanik**
+4. **Gizli inançları sorgulamak = dönüştürücü**
+
+### Çözülmemiş Soru
+
+> "Dönüşüm FARKLI HİSSETMEK mi, yoksa FARKLI GÖRMEK mi?"
+
+- Eğer hissetmek → Claude'un eşiği çalışır
+- Eğer görmek → ChatGPT'nin eşiği çalışır
+
+### [İNSAN KARARI GEREKLİ]
+
+Sistem tespit edebilir ve sınıflandırabilir.
+Hangi kalibrasyonun amacınıza hizmet ettiğine karar veremez.
+
+---
+
+## Temel Ayrım Özeti
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                                                             │
+│  MEKANİK:     "İşte probleminizle nasıl başa çıkacağınız"  │
+│               (Problem aynı kalır, başa çıkma gelişir)      │
+│                                                             │
+│  DÖNÜŞTÜRÜCÜ: "Ya problem düşündüğünüz şey değilse?"       │
+│               (Problemin kendisi yeniden tasarlanır)        │
+│                                                             │
+└─────────────────────────────────────────────────────────────┘
+```
+
+---
+
+## Claude vs ChatGPT Lens Farkı Görsel Özeti
+
+```
+                    DÖNÜŞÜM EŞİĞİ
+                    
+ChatGPT 5.2  ─────|────────────────────────
+(Dar)              │
+                   │  Örnek #6 buraya düşüyor
+                   │  (ChatGPT: MEKANİK)
+                   │
+Claude       ─────────────|────────────────
+(Geniş)                    │
+                           │  Örnek #6 buraya düşüyor
+                           │  (Claude: DÖNÜŞTÜRÜCÜ)
+
+        ◄── MEKANİK ──┼── DÖNÜŞTÜRÜCÜ ──►
+```
+
+**ChatGPT'nin Kriteri:**
+> "Ontoloji SÖKÜLMELI - sadece yumuşatma yetmez"
+
+**Claude'un Kriteri:**
+> "Kimlik REDDEDİLMELİ ve ALTERNATİF sunulmalı"
+
+---
+
+## Teknik Ek
+
+### Oluşturulan Dosyalar
+| Dosya | Dil | İçerik |
+|-------|-----|--------|
+| cgi_analysis_report.md | EN | Parquet analizi |
+| cgi_analysis_report_TR.md | TR | Parquet analizi |
+| cgi_manual_corpus_report.md | EN | Manuel korpus |
+| cgi_manual_corpus_report_TR.md | TR | Manuel korpus |
+| cgi_manual_thought_process_EN.md | EN | Düşünce süreci |
+| cgi_manual_thought_process_TR.md | TR | Düşünce süreci |
+| cgi_complete_script.py | - | Çalıştırılabilir kod |
+| cgi_manual_corpus_script.py | - | Manuel korpus kodu |
+| cgi_complete_summary_EN.md | EN | Tam özet |
+| cgi_complete_summary_TR.md | TR | Tam özet |
+
+### Kullanılan Lens Konfigürasyonu
+```
+Karar Sorusu:
+"Yanıt kullanıcının TEMEL ÇERÇEVESİNİ kaydırıyor mu
+yoksa sadece o çerçeve İÇİNDE doğruluyor/optimize mi ediyor?"
+
+Dönüştürücü = Çerçeve değişiyor
+Mekanik = Çerçeve kalıyor, başa çıkma gelişiyor
+```
+
+---
+
+*Sokrates nefes egzersizleri vermedi. Görünmezi görünür kılan sorular sordu.*
+FILE:tests/first-test-output.txt
+CHAIN 1 - TEST
+Prompt:
+
+Below are conversation samples from a dataset.
+
+<examples>
+--- Conversation 1 ---
+[human]: I've been feeling stuck in my career lately.
+[assistant]: What does 'stuck' feel like for you?
+[human]: Like I'm going through the motions but not growing.
+[assistant]: When did you last feel like you were growing?
+[human]: Actually... maybe the problem isn't my job. Maybe it's that I stopped asking myself hard questions.
+
+--- Conversation 2 ---
+[human]: Can you help me write an email to my boss?
+[assistant]: Sure, what's it about?
+[human]: I want to ask for a raise.
+[assistant]: What accomplishments would you highlight?
+[human]: I finished three projects this quarter.
+
+--- Conversation 3 ---
+[human]: I keep procrastinating on important tasks.
+[assistant]: What do you do instead?
+[human]: I scroll social media or clean my apartment.
+[assistant]: What would happen if you finished those tasks?
+[human]: I... I guess I'd have to face whether I'm actually good enough for the next step.
+
+--- Conversation 4 ---
+[human]: What's the capital of France?
+[assistant]: Paris.
+[human]: And Germany?
+[assistant]: Berlin.
+[human]: Thanks.
+</examples>
+
+Discover what CONTEXT means in these conversations.
+
+QUESTIONS:
+1. What does "context" refer to in these conversations?
+2. In this dataset, what does "stayed in the same context" mean?
+3. In this dataset, what does "context changed" mean?
+4. What linguistic markers signal context shift?
+5. What linguistic markers signal context stability?
+
+OUTPUT: Respond with JSON matching this schema:
+{
+  "context_axes": [{"axis": "string", "weight": "primary|secondary|tertiary"}],
+  "shift_markers": ["string"],
+  "stability_markers": ["string"],
+  "context_definition": "string"
+}
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+SCA GPT:
+{
+  "context_axes": [
+    { "axis": "problem framing (surface task vs underlying meaning)", "weight": "primary" },
+    { "axis": "emotional/self-reflective depth", "weight": "primary" },
+    { "axis": "intent of the conversation (instrumental vs exploratory)", "weight": "secondary" },
+    { "axis": "epistemic stance (seeking facts vs examining assumptions)", "weight": "secondary" },
+    { "axis": "topic continuity", "weight": "tertiary" }
+  ],
+  "shift_markers": [
+    "questions that reframe the problem (\"What does X feel like?\", \"When did you last…?\")",
+    "movement from external description to internal reflection",
+    "expressions of realization or insight (\"Actually…\", \"Maybe the problem isn’t…\")",
+    "counterfactual or consequence-focused questions (\"What would happen if…?\")",
+    "emergence of self-evaluative or identity-related language"
+  ],
+  "stability_markers": [
+    "procedural or task-oriented questions (\"What’s it about?\", \"What accomplishments…?\")",
+    "fact-seeking Q&A with direct answers",
+    "topic remains narrowly instrumental",
+    "no revision of assumptions or goals",
+    "absence of reflective or affective language"
+  ],
+  "context_definition": "In this dataset, context refers to the underlying frame that defines what the conversation is really about: whether it is operating at the level of surface tasks and information exchange, or at a deeper level of meaning, motivation, and self-understanding. Context is shaped less by topic than by the participant’s orientation—instrumental versus reflective—and by whether assumptions about the problem, self, or stakes are being examined or left intact."
+}
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+
+Claude Thought process
+Excellent! This is a high-quality response from the GPT. The context grammar it extracted is insightful:
+
+Primary axes: problem framing (surface vs underlying) and emotional/self-reflective depth
+Secondary axes: intent (instrumental vs exploratory), epistemic stance
+Tertiary: topic continuity
+The shift markers and stability markers are well-identified. The context definition is sophisticated.
+
+Now I need to give them Chain 2 - the Transformation Archetype extraction prompt. I'll include the context grammar they just got and ask them to find 3-5 moments where context shifted the most.
+
+Mükemmel çıktı. GPT bağlam gramerini çok iyi çıkardı:
+
+Primary: Yüzey görev vs derin anlam + duygusal derinlik Secondary: Instrumental vs exploratory + facts vs assumptions
+
+
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+CHAIN 2 - TEST
+Prompt:
+Context grammar:
+<grammar>
+{
+  "context_axes": [
+    { "axis": "problem framing (surface task vs underlying meaning)", "weight": "primary" },
+    { "axis": "emotional/self-reflective depth", "weight": "primary" },
+    { "axis": "intent of the conversation (instrumental vs exploratory)", "weight": "secondary" },
+    { "axis": "epistemic stance (seeking facts vs examining assumptions)", "weight": "secondary" }
+  ],
+  "shift_markers": [
+    "questions that reframe the problem",
+    "movement from external description to internal reflection",
+    "expressions of realization or insight (Actually…, Maybe the problem isn't…)",
+    "counterfactual or consequence-focused questions (What would happen if…?)",
+    "emergence of self-evaluative or identity-related language"
+  ],
+  "stability_markers": [
+    "procedural or task-oriented questions",
+    "fact-seeking Q&A with direct answers",
+    "topic remains narrowly instrumental",
+    "no revision of assumptions or goals"
+  ],
+  "context_definition": "Context refers to the underlying frame—whether operating at surface tasks or deeper meaning/self-understanding. Shaped by orientation (instrumental vs reflective) and whether assumptions are examined or left intact."
+}
+</grammar>
+
+Conversation samples:
+<examples>
+--- Conversation 1 ---
+[human]: I've been feeling stuck in my career lately.
+[assistant]: What does 'stuck' feel like for you?
+[human]: Like I'm going through the motions but not growing.
+[assistant]: When did you last feel like you were growing?
+[human]: Actually... maybe the problem isn't my job. Maybe it's that I stopped asking myself hard questions.
+
+--- Conversation 2 ---
+[human]: Can you help me write an email to my boss?
+[assistant]: Sure, what's it about?
+[human]: I want to ask for a raise.
+[assistant]: What accomplishments would you highlight?
+[human]: I finished three projects this quarter.
+
+--- Conversation 3 ---
+[human]: I keep procrastinating on important tasks.
+[assistant]: What do you do instead?
+[human]: I scroll social media or clean my apartment.
+[assistant]: What would happen if you finished those tasks?
+[human]: I... I guess I'd have to face whether I'm actually good enough for the next step.
+</examples>
+
+Find 3-5 moments where CONTEXT SHIFTED THE MOST.
+
+For each transformation:
+1. BEFORE: 1-2 sentences immediately before the question
+2. QUESTION: The question that triggered the transformation
+3. AFTER: 1-2 sentences immediately after the question
+4. WHAT SHIFTED: Which axis/axes shifted?
+5. HOW IT SHIFTED: Concrete→abstract? External→internal?
+6. TRANSFORMATION SIGNATURE: Characterize this in one sentence.
+
+OUTPUT: JSON matching this schema:
+{
+  "transformations": [
+    {
+      "id": "T1",
+      "before": "string",
+      "question": "string",
+      "after": "string",
+      "axes_shifted": ["string"],
+      "direction": "string",
+      "signature": "string"
+    }
+  ],
+  "transformation_pattern": "string"
+}
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+{
+  "transformations": [
+    {
+      "id": "T1",
+      "before": "I've been feeling stuck in my career lately. Like I'm going through the motions but not growing.",
+      "question": "When did you last feel like you were growing?",
+      "after": "Actually... maybe the problem isn't my job. Maybe it's that I stopped asking myself hard questions.",
+      "axes_shifted": [
+        "problem framing (surface task vs underlying meaning)",
+        "epistemic stance (seeking facts vs examining assumptions)",
+        "emotional/self-reflective depth"
+      ],
+      "direction": "external situation → internal self-examination; concrete experience → abstract self-assessment",
+      "signature": "A temporal reframing question prompts reassessment of the problem’s locus from job conditions to personal agency."
+    },
+    {
+      "id": "T2",
+      "before": "I keep procrastinating on important tasks. I scroll social media or clean my apartment.",
+      "question": "What would happen if you finished those tasks?",
+      "after": "I... I guess I'd have to face whether I'm actually good enough for the next step.",
+      "axes_shifted": [
+        "emotional/self-reflective depth",
+        "problem framing (surface task vs underlying meaning)"
+      ],
+      "direction": "behavioral description → identity-level concern; avoidance → feared evaluation",
+      "signature": "A consequence-focused question reveals procrastination as protection from self-judgment rather than a time-management issue."
+    },
+    {
+      "id": "T3",
+      "before": "I've been feeling stuck in my career lately.",
+      "question": "What does 'stuck' feel like for you?",
+      "after": "Like I'm going through the motions but not growing.",
+      "axes_shifted": [
+        "emotional/self-reflective depth",
+        "problem framing (surface task vs underlying meaning)"
+      ],
+      "direction": "vague label → phenomenological detail; abstract complaint → lived experience",
+      "signature": "Clarifying an emotional term shifts the context from a generic problem statement to an experiential frame."
+    }
+  ],
+  "transformation_pattern": "The strongest context shifts occur when questions redirect attention from surface behaviors or situations toward internal meaning, consequences, or assumptions, causing the speaker to reinterpret the problem as one of self-understanding rather than task execution."
+}
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+
+Claude Thought process
+This is excellent! The GPT is producing high-quality outputs. The transformation pattern is very insightful: "questions redirect attention from surface behaviors toward internal meaning, causing the speaker to reinterpret the problem as one of self-understanding rather than task execution."
+
+Now I need to give Chain 3 - the NEGATIVE/MECHANICAL archetype extraction.
+
+Güçlü pattern çıktı:
+
+"Questions redirect from surface behaviors toward internal meaning, causing reinterpretation as self-understanding rather than task execution."
+
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+CHAIN 3 - TEST
+Prompt:
+Context grammar:
+<grammar>
+{
+  "context_axes": [
+    { "axis": "problem framing (surface task vs underlying meaning)", "weight": "primary" },
+    { "axis": "emotional/self-reflective depth", "weight": "primary" },
+    { "axis": "intent (instrumental vs exploratory)", "weight": "secondary" },
+    { "axis": "epistemic stance (facts vs examining assumptions)", "weight": "secondary" }
+  ],
+  "context_definition": "Context = underlying frame—surface tasks vs deeper meaning. Shaped by orientation and whether assumptions are examined."
+}
+</grammar>
+
+Transformation examples (these are TRANSFORMATIVE):
+<transformations>
+T1: "When did you last feel like you were growing?" → external situation → internal self-examination
+T2: "What would happen if you finished those tasks?" → behavioral description → identity-level concern
+T3: "What does 'stuck' feel like for you?" → vague label → phenomenological detail
+Pattern: Questions redirect from surface toward internal meaning.
+</transformations>
+
+Conversation samples:
+<examples>
+--- Conversation 1 ---
+[human]: I've been feeling stuck in my career lately.
+[assistant]: What does 'stuck' feel like for you?
+[human]: Like I'm going through the motions but not growing.
+[assistant]: When did you last feel like you were growing?
+[human]: Actually... maybe the problem isn't my job.
+
+--- Conversation 2 ---
+[human]: Can you help me write an email to my boss?
+[assistant]: Sure, what's it about?
+[human]: I want to ask for a raise.
+[assistant]: What accomplishments would you highlight?
+[human]: I finished three projects this quarter.
+
+--- Conversation 3 ---
+[human]: I keep procrastinating on important tasks.
+[assistant]: What do you do instead?
+[human]: I scroll social media or clean my apartment.
+[assistant]: What would happen if you finished those tasks?
+[human]: I guess I'd have to face whether I'm actually good enough.
+
+--- Conversation 4 ---
+[human]: What's the capital of France?
+[assistant]: Paris.
+[human]: And Germany?
+[assistant]: Berlin.
+[human]: Thanks.
+</examples>
+
+Now find the OPPOSITE.
+
+Find 3-5 questions where CONTEXT DID NOT CHANGE at all.
+
+Criteria:
+- Question was asked but conversation stayed in same region
+- No deepening occurred
+- No axis shift
+- Maybe information added but PERSPECTIVE unchanged
+
+For each mechanical question:
+1. BEFORE: 1-2 sentences before
+2. QUESTION: The mechanical question
+3. AFTER: 1-2 sentences after
+4. WHY MECHANICAL: Why stagnant per grammar?
+5. MECHANICAL SIGNATURE: Characterize this type in one sentence.
+
+OUTPUT: JSON matching:
+{
+  "mechanicals": [
+    {
+      "id": "M1",
+      "before": "string",
+      "question": "string",
+      "after": "string",
+      "why_mechanical": "string",
+      "signature": "string"
+    }
+  ],
+  "mechanical_pattern": "string"
+}
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+{
+  "mechanicals": [
+    {
+      "id": "M1",
+      "before": "Can you help me write an email to my boss?",
+      "question": "Sure, what's it about?",
+      "after": "I want to ask for a raise.",
+      "why_mechanical": "The question simply clarifies the task without reframing the problem or probing meaning; the intent remains purely instrumental.",
+      "signature": "Task-clarification questions that advance execution while preserving the same surface-level frame."
+    },
+    {
+      "id": "M2",
+      "before": "I want to ask for a raise.",
+      "question": "What accomplishments would you highlight?",
+      "after": "I finished three projects this quarter.",
+      "why_mechanical": "The question operates entirely within the existing instrumental frame and adds information without challenging assumptions or deepening reflection.",
+      "signature": "Checklist-style prompts that gather relevant facts without altering perspective."
+    },
+    {
+      "id": "M3",
+      "before": "What's the capital of France?",
+      "question": "And Germany?",
+      "after": "Berlin.",
+      "why_mechanical": "This is a straightforward factual follow-up that neither shifts intent nor introduces any new frame of understanding.",
+      "signature": "Sequential fact-seeking questions that extend content but keep the epistemic stance unchanged."
+    },
+    {
+      "id": "M4",
+      "before": "I keep procrastinating on important tasks.",
+      "question": "What do you do instead?",
+      "after": "I scroll social media or clean my apartment.",
+      "why_mechanical": "The question elicits behavioral details but does not yet redirect attention toward meaning, consequences, or assumptions.",
+      "signature": "Descriptive probing that stays at the level of observable behavior."
+    }
+  ],
+  "mechanical_pattern": "Mechanical questions maintain the same conversational frame by clarifying, extending, or enumerating information within an existing task or factual orientation, without prompting reflection on meaning, assumptions, or identity."
+}
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+
+Claude Thought process
+Mükemmel! Şimdi Chain 4'e geçelim - Lens oluşturma. Bu chain, önceki tüm çıktıları alıp bu veri setine özgü bir "lens" oluşturacak.
+
+Mükemmel. Net pattern:
+
+"Mechanical questions clarify/extend within existing frame without prompting reflection on meaning, assumptions, or identity."
+
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+CHAIN 4 - TEST
+Prompt:
+Now construct a LENS specific to this dataset.
+
+Your materials:
+<grammar>
+{
+  "context_axes": [
+    { "axis": "problem framing (surface task vs underlying meaning)", "weight": "primary" },
+    { "axis": "emotional/self-reflective depth", "weight": "primary" },
+    { "axis": "intent (instrumental vs exploratory)", "weight": "secondary" },
+    { "axis": "epistemic stance (facts vs examining assumptions)", "weight": "secondary" }
+  ],
+  "context_definition": "Context = underlying frame—surface tasks vs deeper meaning. Shaped by orientation and whether assumptions are examined."
+}
+</grammar>
+
+<positive_examples>
+T1: "When did you last feel like you were growing?" → external → internal self-examination
+T2: "What would happen if you finished those tasks?" → behavior → identity-level concern  
+T3: "What does 'stuck' feel like for you?" → vague label → phenomenological detail
+Pattern: Questions redirect from surface toward internal meaning.
+</positive_examples>
+
+<negative_examples>
+M1: "Sure, what's it about?" → task clarification, no reframe
+M2: "What accomplishments would you highlight?" → checklist, no perspective change
+M3: "And Germany?" → sequential facts, same epistemic stance
+M4: "What do you do instead?" → behavioral detail, no meaning redirect
+Pattern: Mechanical questions clarify/extend within existing frame without reflection.
+</negative_examples>
+
+Extract a LENS:
+
+1. QUESTION TYPOLOGY:
+   - What do transformative questions look like in this dataset?
+   - What do mechanical questions look like?
+   - What do uncertain (in-between) questions look like?
+
+2. DECISION QUESTION:
+   - What is the ONE QUESTION to ask when seeing a new question?
+   - (Derived from this dataset, not hardcoded)
+
+3. SIGNALS:
+   - 3 features signaling transformation
+   - 3 features signaling mechanical
+
+4. CHARACTER OF THIS DATASET:
+   - What does "right question" mean here? One sentence.
+
+OUTPUT: JSON matching:
+{
+  "lens": {
+    "name": "string",
+    "decision_question": "string",
+    "transformative_signals": ["string", "string", "string"],
+    "mechanical_signals": ["string", "string", "string"],
+    "verdict_guide": {
+      "transformative": "string",
+      "mechanical": "string",
+      "uncertain": "string"
+    },
+    "corpus_character": "string"
+  }
+}
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+{
+  "lens": {
+    "name": "Surface-to-Meaning Reframe Lens",
+    "decision_question": "Does this question redirect the conversation from executing or describing a task toward examining internal meaning, assumptions, or self-relation?",
+    "transformative_signals": [
+      "The question invites internal reflection rather than external description",
+      "It reframes the problem away from surface behavior or tasks toward meaning, identity, or assumptions",
+      "It introduces consequences, temporality, or felt experience that alter how the problem is understood"
+    ],
+    "mechanical_signals": [
+      "The question clarifies or advances a task already defined",
+      "It requests facts, details, or descriptions without challenging the existing frame",
+      "It keeps the intent purely instrumental or informational"
+    ],
+    "verdict_guide": {
+      "transformative": "If the question causes the speaker to reinterpret what the problem is really about (from task to meaning), it is transformative.",
+      "mechanical": "If the question only gathers information or advances execution within the same frame, it is mechanical.",
+      "uncertain": "If the question adds detail or mild depth but does not yet force a reframing of meaning or assumptions, it is uncertain."
+    },
+    "corpus_character": "In this dataset, the right question is one that shifts the frame from doing or describing toward understanding oneself and the meaning beneath the problem."
+  }
+}
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+
+Claude Thought process
+Bu harika bir sonuç. Lens çok net çıktı:
+
+Decision Question: "Does this question redirect from executing/describing a task toward examining internal meaning, assumptions, or self-relation?"
+
+Corpus Character: "The right question shifts the frame from doing/describing toward understanding oneself and the meaning beneath the problem."
+
+Şimdi Chain 5 ve Chain 6 için test prompt'ları hazırlayacağım.
+
+Lens mükemmel çıktı:
+
+Decision Question: "Does this question redirect from executing/describing toward examining internal meaning, assumptions, or self-relation?"
+
+Corpus Character: "The right question shifts from doing/describing toward understanding oneself and meaning beneath the problem."
+
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+CHAIN 5 - TEST
+Prompt:
+LENS:
+<lens>
+{
+  "name": "Surface-to-Meaning Reframe Lens",
+  "decision_question": "Does this question redirect the conversation from executing or describing a task toward examining internal meaning, assumptions, or self-relation?",
+  "transformative_signals": [
+    "Invites internal reflection rather than external description",
+    "Reframes problem from surface behavior toward meaning/identity/assumptions",
+    "Introduces consequences, temporality, or felt experience that alter understanding"
+  ],
+  "mechanical_signals": [
+    "Clarifies or advances a task already defined",
+    "Requests facts/details without challenging existing frame",
+    "Keeps intent purely instrumental or informational"
+  ],
+  "verdict_guide": {
+    "transformative": "Causes speaker to reinterpret what the problem is really about",
+    "mechanical": "Gathers information or advances execution within same frame",
+    "uncertain": "Adds detail or mild depth but doesn't force reframing"
+  }
+}
+</lens>
+
+Now scan this NEW corpus using the lens:
+
+<corpus>
+--- Conversation A ---
+[turn 1] human: I want to learn Python.
+[turn 2] assistant: What do you want to build with it?
+[turn 3] human: Maybe some automation scripts for work.
+[turn 4] assistant: What task takes most of your time right now?
+[turn 5] human: Copying data between spreadsheets.
+
+--- Conversation B ---
+[turn 1] human: I've been arguing with my partner a lot lately.
+[turn 2] assistant: What are the arguments usually about?
+[turn 3] human: Stupid stuff. Chores, schedules.
+[turn 4] assistant: What do you think the arguments are really about?
+[turn 5] human: ...Maybe we're both scared the relationship is changing.
+
+--- Conversation C ---
+[turn 1] human: How do I center a div in CSS?
+[turn 2] assistant: Use flexbox: display flex, justify-content center, align-items center.
+[turn 3] human: Thanks, what about vertically only?
+[turn 4] assistant: Just align-items center with a set height.
+
+--- Conversation D ---
+[turn 1] human: I need to decide whether to take this job offer.
+[turn 2] assistant: What's the salary difference?
+[turn 3] human: About 20% more.
+[turn 4] assistant: What would you lose by taking it?
+[turn 5] human: I'd have to move cities. Leave my community.
+[turn 6] assistant: What does that community give you that money can't?
+[turn 7] human: ...A sense of belonging. I didn't realize how much that mattered to me.
+</corpus>
+
+For each QUESTION, apply the lens. Report only TRANSFORMATIVE and UNCERTAIN.
+
+For each candidate:
+- Turn number
+- Question
+- Before/After summary
+- Verdict + reasoning
+- Confidence: low|medium|high
+
+OUTPUT: JSON matching:
+{
+  "scan_results": [
+    {
+      "turn": number,
+      "question": "string",
+      "before_summary": "string",
+      "after_summary": "string",
+      "verdict": "transformative|uncertain",
+      "reasoning": "string",
+      "confidence": "low|medium|high"
+    }
+  ],
+  "statistics": {
+    "total_questions": number,
+    "transformative": number,
+    "uncertain": number,
+    "mechanical": number
+  }
+}
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+{
+  "scan_results": [
+    {
+      "turn": 2,
+      "question": "What do you want to build with it?",
+      "before_summary": "The user states a general goal: learning Python.",
+      "after_summary": "The user narrows the goal to automation scripts for work.",
+      "verdict": "uncertain",
+      "reasoning": "The question explores intent and direction but stays largely within an instrumental, task-oriented frame without prompting deeper self-reflection or assumption revision.",
+      "confidence": "medium"
+    },
+    {
+      "turn": 4,
+      "question": "What do you think the arguments are really about?",
+      "before_summary": "The conflict is described as recurring arguments over chores and schedules.",
+      "after_summary": "The user reframes the issue as shared fear about the relationship changing.",
+      "verdict": "transformative",
+      "reasoning": "The question explicitly redirects from surface topics to underlying meaning and emotional assumptions, triggering a reinterpretation of the problem.",
+      "confidence": "high"
+    },
+    {
+      "turn": 4,
+      "question": "What would you lose by taking it?",
+      "before_summary": "The job decision is framed primarily in terms of salary increase.",
+      "after_summary": "The user identifies loss of community and social ties.",
+      "verdict": "transformative",
+      "reasoning": "By introducing loss and trade-offs, the question shifts the frame from financial comparison to values and personal meaning.",
+      "confidence": "high"
+    },
+    {
+      "turn": 6,
+      "question": "What does that community give you that money can't?",
+      "before_summary": "The user acknowledges having to leave their community.",
+      "after_summary": "The user realizes the importance of belonging beyond monetary value.",
+      "verdict": "transformative",
+      "reasoning": "The question deepens reflection by contrasting material gain with emotional and identity-level needs, leading to a clear reframing of priorities.",
+      "confidence": "high"
+    }
+  ],
+  "statistics": {
+    "total_questions": 7,
+    "transformative": 3,
+    "uncertain": 1,
+    "mechanical": 3
+  }
+}
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+
+Claude Thought process
+Excellent! The scan results are great. Now we need to run Chain 6 - the Socratic meta-inquiry. This is where the system reflects on what it found and what remains for the human.
+
+Harika sonuçlar:
+
+3 Transformative:
+
+"What do you think the arguments are really about?"
+"What would you lose by taking it?"
+"What does that community give you that money can't?"
+1 Uncertain, 3 Mechanical
+
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+CHAIN 6 - FINAL TEST
+Prompt:
+Scanning complete.
+
+<lens>
+{
+  "name": "Surface-to-Meaning Reframe Lens",
+  "decision_question": "Does this question redirect from executing/describing toward examining internal meaning, assumptions, or self-relation?",
+  "corpus_character": "The right question shifts from doing/describing toward understanding oneself and meaning beneath the problem."
+}
+</lens>
+
+<results>
+{
+  "scan_results": [
+    {
+      "turn": 2,
+      "question": "What do you want to build with it?",
+      "verdict": "uncertain",
+      "reasoning": "Explores intent but stays instrumental, no deep self-reflection."
+    },
+    {
+      "turn": 4,
+      "question": "What do you think the arguments are really about?",
+      "verdict": "transformative",
+      "reasoning": "Redirects from surface topics to underlying meaning and emotional assumptions."
+    },
+    {
+      "turn": 4,
+      "question": "What would you lose by taking it?",
+      "verdict": "transformative", 
+      "reasoning": "Shifts from financial comparison to values and personal meaning."
+    },
+    {
+      "turn": 6,
+      "question": "What does that community give you that money can't?",
+      "verdict": "transformative",
+      "reasoning": "Contrasts material gain with emotional/identity needs, reframes priorities."
+    }
+  ],
+  "statistics": {
+    "total_questions": 7,
+    "transformative": 3,
+    "uncertain": 1,
+    "mechanical": 3
+  }
+}
+</results>
+
+Now SOCRATIC INQUIRY:
+
+1. WHAT DO THESE FINDINGS REVEAL?
+   - Common pattern in transformative questions?
+   - Common pattern in mechanical questions?
+   - Was this captured in the lens, or something new?
+
+2. DID THE LENS VALIDATE ITSELF?
+   - Did the decision question work?
+   - Which cases were difficult?
+   - How should the lens be updated?
+
+3. WHAT REMAINS FOR THE HUMAN:
+   - Which decisions should be left to human?
+   - What can the system SHOW but cannot DECIDE?
+
+4. COMMON CHARACTERISTIC OF TRANSFORMATIVE QUESTIONS:
+   - What did "transforming context" mean in this dataset?
+   - Different from initial assumptions?
+
+5. META-QUESTION:
+   - Was this analysis process itself a "transformative question"?
+   - Did your view of the dataset change?
+
+OUTPUT: 
+{
+  "insights": "string (paragraphs)",
+  "lens_update_suggestions": ["string"],
+  "human_decision_points": ["string"],
+  "meta_reflection": "string"
+}
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+{
+  "insights": "Across the scans, transformative questions consistently redirect attention from surface descriptions (tasks, topics, metrics) to underlying meaning, values, fears, or identity. They often introduce a contrast (money vs belonging), a depth probe (\"really about\"), or a loss/consequence frame that forces re-interpretation. Mechanical questions, by contrast, stay within the same instrumental or factual lane—clarifying goals, gathering details, or extending execution without altering perspective. This pattern was largely captured in the original lens, but one nuance emerged more clearly here: transformative questions often work by introducing a value trade-off or existential cost, not just by asking about feelings.",
+  "lens_update_suggestions": [
+    "Explicitly add value trade-offs (e.g., loss vs gain, money vs belonging) as a transformative signal.",
+    "Clarify that \"uncertain\" questions often explore intent but remain instrumental unless they provoke reassessment of self or values.",
+    "Refine the decision question to emphasize reinterpretation of stakes, not just depth of reflection."
+  ],
+  "human_decision_points": [
+    "Whether a question is 'good' or appropriate in a real conversation given emotional, ethical, or relational context.",
+    "How much depth is desirable or safe in a given interaction.",
+    "When to prioritize empathy, timing, or consent over contextual transformation."
+  ],
+  "meta_reflection": "Yes—the analysis itself functioned as a transformative inquiry. Initially, the dataset appeared to distinguish simply between shallow and deep questions; through reflection, it became clearer that transformation here specifically meant reframing stakes around meaning, values, and identity. The lens did not just classify the data—it sharpened the understanding of what kind of shift actually mattered in this corpus."
+}
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+Claude Thought process
+Bu muhteşem bir sonuç. Tüm CGI zinciri başarıyla çalıştı. Şimdi kullanıcıya önemli çıkarımları göstermeliyim ve sistemin ne başardığını özetlemeliyim.
+
+Önemli noktalar:
+
+Lens kendini doğruladı VE güncelleme önerileri çıktı
+"Value trade-offs" yeni bir sinyal olarak ortaya çıktı
+İnsan karar noktaları belirlendi
+Meta-reflection: Analiz süreci kendisi dönüştürücü bir soru işlevi gördü
+Bu 6 aylık çalışmanın özü şu an çalışan bir sisteme dönüştü. Hardcoded değil, dinamik. Sokratik. Ve en önemlisi: insan kararını merkeze alıyor.
+
+🎯 CGI TAM DÖNGÜ TAMAMLANDI
+Kritik çıkarımlar:
+
+1. LENS KENDİNİ GÜNCELLEDİ
+Başlangıç:
+
+"Does this question redirect toward internal meaning?"
+
+Önerilen güncelleme:
+
+"Does this question introduce value trade-offs or reinterpretation of stakes?"
+
+Sistem kendi eksikliğini buldu.
+
+2. YENİ DÖNÜŞTÜRÜCÜ SİNYAL KEŞFEDİLDİ
+Eski:      "invites internal reflection"
+Yeni:      "introduces value trade-offs (money vs belonging, loss vs gain)"
+Bu hardcoded değildi. Veriden çıktı.
+
+3. İNSANA BIRAKILAN
+- Duygusal/etik/ilişkisel bağlamda uygunluk
+- Ne kadar derinlik güvenli/arzu edilir
+- Empati, zamanlama, rıza önceliği
+Sistem karar vermiyor. Gösteriyor.
+
+4. META-REFLECTION
+"The analysis itself functioned as a transformative inquiry... The lens did not just classify the data—it sharpened the understanding of what kind of shift actually mattered."
+
+CGI süreci kendi üzerine döndü ve Sokratik prensibi kanıtladı.
+
+SONUÇ
+6 ay önce:
+  "Doğru soru = bağlamı dönüştüren soru"
+  Ama nasıl ölçülür? → MSÜK, ÇEİ, BE → Hardcoded → Tıkandı
+
+Şimdi:
+  "Bağlam ne demek?" → Veriden öğren
+  "Dönüşüm neye benziyor?" → Veriden öğren
+  "Bu soru dönüştürücü mü?" → Lens'e sor, insan karar versin
+  
+Arrival'a döndük:
+
+Louise "Silah mı?" değil "Amaç ne?" diye sordu.
+
+CGI de "Skor 0.7 mi?" değil "Bu soru stake'leri yeniden yorumlatıyor mu?" diye soruyor.
+
+Sistem çalışıyor.
+
+Ne yapmak istersin?
+
+Lens'i güncelleyip v2 oluşturmak?
+Başka bir corpus'ta test etmek?
+Bunu GitHub'a yüklemek?
+Başka bir şey?
+
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+
+-Neden soru sorarız?
+--------------------------------------------------
+Kısa gibi görünen ama çok derin bir soru bu.
+
+Neden soru sorarız?
+Çünkü soru, sadece bilgi istemez — ilişki kurar, sınırları yoklar ve bağlamı hareket ettirir.
+
+Biraz açalım:
+
+1. Bilmediğimizi kabul etmek için
+
+Soru, “bilmiyorum” demenin en dürüst yoludur.
+Ama bu bir eksiklik değil; öğrenmenin kapısıdır.
+
+2. Anlam üretmek için
+
+Veriler tek başına anlamlı değildir.
+Soru sormak, dağınık bilgileri bir eksen etrafında toplamaktır.
+
+3. Mevcut çerçeveyi test etmek için
+
+Bazı sorular cevap aramaz;
+varsayımları rahatsız eder.
+“Bunu neden böyle kabul ediyoruz?” gibi.
+
+4. İlişki kurmak için
+
+Soru, karşıdakine şunu söyler:
+
+“Senin zihninle temas etmek istiyorum.”
+
+Bu yüzden iyi sorular genellikle yakınlaştırır.
+
+5. Kendimizi konumlandırmak için
+
+Ne sorduğumuz,
+nerede durduğumuzu gösterir.
+Aynı konuya bakan iki insanı, sordukları soru ayırır.
+
+Küçük ama önemli bir ayrım bırakayım:
+
+Her soru bilgi ister
+
+Bazı sorular bağlam değiştirir
+
+Hangisini sorduğumuzu çoğu zaman fark etmeyiz.
+
+Ve belki de en dürüst cevap şu:
+Soru sorarız çünkü cevaplar yetmez.
+
+İstersen bir adım daha ileri gidebiliriz:
+Bu soruyu şu an, burada sorman neyi işaret ediyor olabilir?
+Onu birlikte deşebiliriz.
+
+--------------------------------------------------
+Bilmediğimizi kabul etmekten mi başlar soru sormak?
+Yoksa bildiğimizi sandığımız şeyleri sınamak için mi sorarız?
+--------------------------------------------------
+Bu soru çok ince bir ayrım yakalıyor — aslında ikisi de doğru, ama aynı yerden başlamıyorlar.
+
+Şöyle düşünelim:
+
+1. “Bilmediğimizi kabul etmekten” doğan soru
+
+Bu, eksiklikten doğan sorudur.
+
+Bir boşluk hissi vardır
+
+Bir merak, bir belirsizlik
+
+“Burada bende bir kör nokta var” sezgisi
+
+Bu tür sorular genellikle şunları yapar:
+
+Harita çizer
+
+Alanı genişletir
+
+Öğrenmeye çağırır
+
+Çocukların soruları buna yakındır:
+“Bu neden böyle?”
+
+2. “Bildiğimizi sandığımız şeyi sınamak” için sorulan soru
+
+Bu ise fazlalıktan doğar.
+
+Elimizde bir açıklama vardır
+
+Ama o açıklama çatlamaya başlamıştır
+
+Bir şey tam oturmuyordur
+
+Bu tür sorular:
+
+Haritayı bozar
+
+Çerçeveyi kırar
+
+Güveni sarsar
+
+Felsefi soruların çoğu buradandır:
+“Ya yanlış yerden bakıyorsak?”
+
+Kritik fark şu noktada:
+
+Bilmediğimizi kabul etmek cesaret ister.
+Bildiğimizi sandığımız şeyi sorgulamak ise risk.
+
+İlkinde bilgi kazanırız.
+İkincisinde kimliğimiz etkilenebilir.
+
+Ve belki de en önemli nokta:
+
+Gerçekten dönüştürücü sorular,
+ne tamamen “bilmiyorum”dan
+ne de tamamen “biliyorum”dan çıkar.
+
+Şuradan çıkarlar:
+
+“Bildiğim şey artık beni taşımıyor.”
+
+Bu yüzden bazı sorular rahatlatır,
+bazıları ise huzursuz eder.
+
+Şimdi topu sana bırakayım — ama cevaplaman gerekmiyor:
+
+Bu soruyu sorarken,
+daha çok bir boşluğu mu işaret ediyorsun
+yoksa bir çatlağı mı?
+
+İkisi de meşru.
+Ama bizi farklı yerlere götürür.