from reflexio.models.config_schema import ProfileExtractorConfig

profile_config = ProfileExtractorConfig(
    # Required: Unique name for this extractor
    extractor_name="customer_info",
    # Required: What information to extract
    profile_content_definition_prompt="""
Extract the following user information:
- Name and contact details
- Preferences and interests
- Goals and intent
""",
    # Optional: Context about the interaction type
    context_prompt="""
This is a conversation between a sales agent and a potential customer.
Extract any relevant customer information.
""",
    # Optional: How to categorize extracted profiles
    metadata_definition_prompt="""
Categorize extracted profiles as one of:
- 'basic_info': Name, contact, demographics
- 'preferences': Likes, dislikes, style preferences
- 'intent': Goals, purchase intent, timeline
""",
    # Optional: Only process interactions from these sources
    request_sources_enabled=["chat", "email"],
    # Optional: Require manual triggering instead of auto extraction
    manual_trigger=False
)

# Extractor for demographics - runs on all sources
demographics_config = ProfileExtractorConfig(
    extractor_name="demographics",
    profile_content_definition_prompt="Extract name, age, location, occupation",
)

# Extractor for preferences - only from chat interactions
preferences_config = ProfileExtractorConfig(
    extractor_name="preferences",
    profile_content_definition_prompt="Extract product preferences, style choices, budget range",
    metadata_definition_prompt="choose from 'style_preference' or 'budget_preference'",
    request_sources_enabled=["chat"]
)

# Extractor that requires manual triggering
sentiment_config = ProfileExtractorConfig(
    extractor_name="sentiment_analysis",
    profile_content_definition_prompt="Extract user sentiment and emotional state",
    manual_trigger=True  # Only runs when explicitly triggered
)

config.profile_extractor_configs = [demographics_config, preferences_config, sentiment_config]

# Later, run only specific extractors manually:
client.rerun_profile_generation(
    user_id="user_123",
    extractor_names=["sentiment_analysis"],
    wait_for_response=True
)

from reflexio.models.config_schema import (
    PlaybookConfig,
    PlaybookAggregatorConfig
)

playbook_config = PlaybookConfig(
    # Required: Unique name for this playbook type
    playbook_name="customer_satisfaction",
    # Required: What to extract from interactions
    playbook_definition_prompt="""
Analyze the interaction and extract playbook entries about:
- Was the customer satisfied with the response?
- What could have been done better?
- Any specific complaints or praise?
""",
    # Optional: How to categorize the playbook entries
    metadata_definition_prompt="""
Rate satisfaction: 'positive', 'neutral', 'negative'
""",
    # Optional: When to aggregate user playbooks
    playbook_aggregator_config=PlaybookAggregatorConfig(
        min_cluster_size=5,
        reaggregation_trigger_count=3
    )
)

from reflexio.models.config_schema import (
    AgentSuccessConfig,
    ToolUseConfig
)

success_config = AgentSuccessConfig(
    # Required: Unique name for this evaluation
    evaluation_name="booking_success",
    # Required: Define what success looks like (focus on user outcomes)
    success_definition_prompt="""
Evaluate if the agent successfully:
1. Understood the customer's booking request
2. Provided accurate availability information
3. Completed the booking or explained next steps
4. Left the customer satisfied

A successful interaction ends with either:
- A confirmed booking
- Clear next steps agreed upon
- Customer explicitly stating they're satisfied
""",
    # Optional: How to categorize outcomes
    metadata_definition_prompt="""
Classify outcome as:
- 'booking_completed': Customer completed a booking
- 'booking_pending': Customer will return to complete
- 'booking_cancelled': Customer decided not to book
- 'information_only': Customer was just browsing
""",
    # Optional: Evaluate only a portion of interactions (0.5 = 50%)
    sampling_rate=0.5
)

# Configure tools the agent can use at the Config level
# (shared across success evaluation and playbook extraction)
config.tool_can_use = [
    ToolUseConfig(
        tool_name="check_availability",
        tool_description="Check room/service availability for given dates"
    ),
    ToolUseConfig(
        tool_name="create_booking",
        tool_description="Create a new booking for the customer"
    )
]