qavr-status

name	qavr-status
description	Display QAVR (Q-Value Augmented Vector Retrieval) system status including mode, interaction counts, top memories by Q-value, and configuration.
version	1.0.0
command	qavr-status

QAVR Status Diagnostic

Purpose: Quick diagnostic view of the QAVR learned memory system.

Usage

/qavr-status [context]

Arguments:

• context (optional): Specific context to check (e.g., "debugging", "research"). Defaults to showing all contexts.

What It Shows

1. System Status

• Mode: Cold (< 100 interactions) or Warm (Q-value ranking active)
• Total Memories: Number of memories with Q-values
• Total Contexts: Number of distinct context types

2. Per-Context Status

For each context (or specified context):

• Interaction count
• Mode (cold/warm)
• Interactions remaining until warm

3. Top Memories

Top 5 memories by Q-value for each warm context:

• Memory ID
• Q-value
• Visit count

4. Configuration

Current QAVR settings from ~/.claude/qavr/config.yaml

Implementation

When this skill is invoked, execute the following:

import sys
sys.path.insert(0, '/home/kim/.claude/qavr')
from q_value_store import QValueStore

store = QValueStore('/home/kim/.claude/qavr/q_values.json')
stats = store.get_stats()

print("=" * 50)
print("QAVR System Status")
print("=" * 50)
print(f"Memories tracked: {stats['memory_count']}")
print(f"Contexts: {stats['context_count']}")
print(f"Warm contexts: {', '.join(stats['warm_contexts']) or 'None'}")
print(f"Cold contexts: {', '.join(stats['cold_contexts']) or 'None'}")
print(f"Total interactions: {stats['total_interactions']}")
print()

# Per-context details
for ctx in store.context_interactions:
    mode = store.get_mode(ctx)
    interactions = store.context_interactions[ctx]
    remaining = store.interactions_to_warm(ctx)
    print(f"Context: {ctx}")
    print(f"  Mode: {mode}")
    print(f"  Interactions: {interactions}")
    if mode == 'cold':
        print(f"  To warm: {remaining} more interactions")
    else:
        print(f"  Top memories:")
        for mem in store.get_top_memories(ctx, 5):
            print(f"    {mem['memory_id']}: Q={mem['q']:.3f} ({mem['visits']} visits)")
    print()

# Config summary
print("Configuration:")
print(f"  Learning rate: {store.config.learning_rate}")
print(f"  Cold threshold: {store.config.cold_start_threshold}")
print(f"  Min Q threshold: {store.config.min_q_threshold}")

Example Output

==================================================
QAVR System Status
==================================================
Memories tracked: 42
Contexts: 3
Warm contexts: debugging, research
Cold contexts: implementation
Total interactions: 287

Context: debugging
  Mode: warm
  Interactions: 156
  Top memories:
    seed_debug_001: Q=0.997 (76 visits)
    mem_debug_042: Q=0.891 (23 visits)
    mem_debug_018: Q=0.834 (41 visits)
    seed_explore_001: Q=0.812 (19 visits)
    mem_debug_033: Q=0.756 (12 visits)

Context: research
  Mode: warm
  Interactions: 112
  Top memories:
    mem_research_007: Q=0.923 (34 visits)
    mem_research_012: Q=0.867 (28 visits)
    seed_research_001: Q=0.801 (19 visits)

Context: implementation
  Mode: cold
  Interactions: 19
  To warm: 81 more interactions

Configuration:
  Learning rate: 0.1
  Cold threshold: 100
  Min Q threshold: 0.3

Related Skills

• confidence-check-skills - Pre-implementation validation (uses QAVR for duplicate detection)
• agent-memory-skills - Agent memory framework with QAVR integration
• chromadb-integration-skills - ChromaDB patterns (QAVR wraps these)