# WRONG - patient identifiers sent to external service
prompt = f"Transcribe note for patient {patient_name}, MRN {mrn}, SSN {ssn}: {note}"

# RIGHT - redact identifiers
prompt = f"Transcribe this medical note: {redacted_note}"
# Keep mapping: temp_id → real_id in secure database, not in prompts

# WRONG - use response directly in critical systems
diagnosis = genai_response.text
db.execute("UPDATE patients SET diagnosis = ?", diagnosis)

# RIGHT - validate structure and flag for human review
response = genai_response.text
if validate_medical_format(response):
    db.execute("UPDATE patients SET ai_suggested_diagnosis = ?, status = 'PENDING_REVIEW'", response)

# WRONG - no retry logic, fails on rate limit
response = genai_client.chat(request)

# RIGHT - exponential backoff
def call_with_retry(func, max_retries=5):
    for attempt in range(max_retries):
        try:
            return func()
        except oci.exceptions.ServiceError as e:
            if e.status == 429 and attempt < max_retries - 1:
                wait = (2 ** attempt) + random.uniform(0, 1)
                logger.warning(f"Rate limited, retry in {wait:.2f}s")
                time.sleep(wait)
            else:
                raise

Model: command-r-plus
Input:  12M × ($15/1M) = $180/month
Output: 12M × ($75/1M) = $900/month
Total: $1,080/month

70% unique notes = 16.8M tokens
60% simple (command-r): 10M × $1.50 input + $7.50 output = $90
40% complex (command-r-plus): 6.72M × $15 input + $75 output = $605
Total: $695/month (36% savings)

def truncate_for_model(text: str, model: str = "command-r-plus", max_output: int = 2000):
    """Truncate input to fit token budget"""

    # Rough estimate: 1 token ≈ 4 characters
    if model == "command-r-plus":
        max_input_tokens = 128000 - max_output
    elif model == "command-r":
        max_input_tokens = 4000 - max_output
    else:
        max_input_tokens = 2000

    max_chars = max_input_tokens * 4

    if len(text) <= max_chars:
        return text

    # Keep most recent content (chronological data like logs, notes)
    logger.warning(f"Input exceeds {max_input_tokens} tokens, truncating")
    return "...[earlier content truncated]...\n" + text[-max_chars:]

Please carefully analyze the following medical record and provide a comprehensive
summary including all diagnoses, medications, allergies, and treatment plans. Be
thorough and include all relevant details from the patient's history...

[5000 word medical record]

Summarize: diagnoses, meds, allergies, treatment plan.

[5000 word medical record]

import time
import random
from oci.exceptions import ServiceError

def generate_with_backoff(genai_client, request, max_retries=5):
    """Call GenAI with exponential backoff on rate limits"""

    for attempt in range(max_retries):
        try:
            response = genai_client.chat(request)
            return response.data.chat_response.text

        except ServiceError as e:
            if e.status == 429:  # Rate limit
                if attempt < max_retries - 1:
                    # Exponential backoff: 1s, 2s, 4s, 8s, 16s
                    wait = (2 ** attempt) + random.uniform(0, 1)
                    logger.warning(f"Rate limited (429), retry {attempt+1}/{max_retries} in {wait:.1f}s")
                    time.sleep(wait)
                else:
                    logger.error(f"Rate limit exceeded after {max_retries} retries")
                    raise

            elif e.status == 400:  # Bad request (often token limit)
                logger.error(f"Bad request (400): {e.message}")
                if "token" in e.message.lower():
                    logger.error("Token limit exceeded - truncate input")
                raise

            else:
                logger.error(f"GenAI error ({e.status}): {e.message}")
                raise

def validate_medical_response(response: str) -> tuple[bool, list[str]]:
    """Validate GenAI medical response for safety"""

    issues = []

    # Check 1: Response not empty
    if not response or len(response.strip()) < 10:
        issues.append("Response too short or empty")

    # Check 2: No obvious hallucination markers
    hallucination_markers = [
        "I don't have access",
        "I cannot",
        "As an AI",
        "[INSERT",
        "TODO",
    ]
    for marker in hallucination_markers:
        if marker.lower() in response.lower():
            issues.append(f"Potential hallucination marker: {marker}")

    # Check 3: Expected structure present (customize per use case)
    required_sections = ["Chief Complaint", "Assessment", "Plan"]
    missing_sections = [s for s in required_sections if s.lower() not in response.lower()]
    if missing_sections:
        issues.append(f"Missing sections: {missing_sections}")

    # Check 4: No PII leak (if input was redacted)
    pii_patterns = [
        r'\b\d{3}-\d{2}-\d{4}\b',  # SSN
        r'\b[A-Z]{2}\d{6,8}\b',     # MRN patterns
    ]
    for pattern in pii_patterns:
        if re.search(pattern, response):
            issues.append(f"Potential PII in response: {pattern}")

    is_valid = len(issues) == 0
    return is_valid, issues


# Usage
response_text = genai_response.data.chat_response.text
is_valid, issues = validate_medical_response(response_text)

if is_valid:
    store_for_review(response_text)
else:
    logger.warning(f"Invalid response: {issues}")
    flag_for_manual_review(response_text, issues)

def redact_phi(text: str) -> tuple[str, dict]:
    """Remove PHI from text, return redacted text + mapping"""

    mapping = {}
    redacted = text

    # Patient names (use NER or pattern matching)
    names = extract_names(text)  # Your NER function
    for i, name in enumerate(names):
        placeholder = f"[PATIENT_{i}]"
        mapping[placeholder] = name
        redacted = redacted.replace(name, placeholder)

    # Medical Record Numbers
    mrn_pattern = r'\b(MRN|Medical Record):?\s*([A-Z0-9]{6,10})\b'
    redacted = re.sub(mrn_pattern, r'\1: [REDACTED]', redacted)

    # SSN
    ssn_pattern = r'\b\d{3}-\d{2}-\d{4}\b'
    redacted = re.sub(ssn_pattern, '[SSN_REDACTED]', redacted)

    # Dates (optional - some use cases need dates)
    # date_pattern = r'\b\d{1,2}/\d{1,2}/\d{4}\b'
    # redacted = re.sub(date_pattern, '[DATE]', redacted)

    return redacted, mapping


# Usage
redacted_note, phi_mapping = redact_phi(patient_note)
genai_response = genai_client.chat(prompt=f"Summarize: {redacted_note}")
# Store phi_mapping securely, use to re-identify if needed