from scripts import boot
print(boot())

from scripts import TYPES  # {'decision', 'world', 'anomaly', 'experience', 'procedure'}

from scripts import remember

# Store a workflow
id = remember(
    "Deploy workflow: 1) Run tests 2) Build artifacts 3) Push to staging 4) Smoke test 5) Promote to prod",
    "procedure",
    tags=["deployment", "workflow"],
)

# Retrieve workflows
procedures = recall(type="procedure", tags=["deployment"])

from scripts import remember, remember_bg, flush

# Blocking write (default)
id = remember("User prefers dark mode", "decision", tags=["ui"], conf=0.9)

# Background write (non-blocking)
remember("Quick note", "world", sync=False)

# Ensure all background writes complete before conversation ends
flush()

from scripts import recall

# FTS5 search with BM25 ranking + Porter stemmer
memories = recall("dark mode")

# Filtered queries
decisions = recall(type="decision", conf=0.85, n=20)
tasks = recall("API", tags=["task"], n=15)
urgent = recall(tags=["task", "urgent"], tag_mode="all", n=10)

# Comprehensive retrieval (v4.1.0)
all_memories = recall(fetch_all=True, n=1000)  # Get all memories without search filtering

# Time-windowed queries (v4.3.0) - since/until with inclusive bounds
recent = recall("API", since="2025-02-01")
jan_memories = recall(since="2025-01-01", until="2025-01-31T23:59:59Z")

# Multi-tag convenience (v4.3.0)
both = recall(tags_all=["correction", "bsky"])    # AND: must have all tags
either = recall(tags_any=["therapy", "self-improvement"])  # OR: any tag matches

# Wildcard patterns are NOT supported - use fetch_all instead
# recall("*", n=1000)  # ❌ Raises ValueError
# recall(fetch_all=True, n=1000)  # ✅ Correct approach

from scripts import remember, get_alternatives

# Store decision with alternatives considered
id = remember(
    "Chose PostgreSQL for the database",
    "decision",
    tags=["architecture", "database"],
    alternatives=[
        {"option": "MongoDB", "rejected": "Schema-less adds complexity for our relational data"},
        {"option": "SQLite", "rejected": "Doesn't support concurrent writes at our scale"},
    ]
)

# Later: retrieve what was considered
alts = get_alternatives(id)
for alt in alts:
    print(f"Rejected {alt['option']}: {alt.get('rejected', 'no reason')}")

from scripts import get_chain

# Follow refs up to 3 levels deep (default)
chain = get_chain("memory-uuid", depth=3)
for m in chain:
    print(f"[depth={m['_chain_depth']}] {m['summary'][:80]}")

# Useful for understanding supersede chains, consolidated memory origins, etc.

from scripts import recall_batch, remember_batch

# Multiple searches in one call (uses server-side FTS5 with BM25 ranking)
results = recall_batch(["architecture", "turso", "FTS5"], n=5)
for i, result_set in enumerate(results):
    print(f"Query {i}: {len(result_set)} results")

# Multiple stores in one call
ids = remember_batch([
    {"what": "User prefers dark mode", "type": "decision", "tags": ["ui"]},
    {"what": "Project uses React", "type": "world", "tags": ["tech"]},
    {"what": "Found auth bug", "type": "anomaly", "conf": 0.7},
])

from scripts import forget, supersede

# Soft delete (sets deleted_at, excluded from queries)
forget("memory-uuid")

# Version without losing history
supersede(original_id, "User now prefers Python 3.12", "decision", conf=0.9)

from scripts import config_get, config_set, config_delete, config_list, profile, ops

# Read
config_get("identity")                    # Single key
profile()                                  # All profile entries
ops()                                      # All ops entries
config_list()                              # Everything

# Write
config_set("new-key", "value", "profile")  # Category: 'profile', 'ops', or 'journal'
config_set("bio", "Short bio here", "profile", char_limit=500)  # Enforce max length
config_set("core-rule", "Never modify this", "ops", read_only=True)  # Mark immutable

# Delete
config_delete("old-key")

from scripts import journal, journal_recent, journal_prune

# Record what happened this interaction
journal(
    topics=["project-x", "debugging"],
    user_stated="Will review PR tomorrow",
    my_intent="Investigating memory leak"
)

# Boot: load recent entries for context
for entry in journal_recent(10):
    print(f"[{entry['t'][:10]}] {entry.get('topics', [])}: {entry.get('my_intent', '')}")

# Maintenance: keep last 40 entries
pruned = journal_prune(keep=40)

from scripts import remember, flush

remember("Derived insight", "experience", sync=False)
remember("Another note", "world", sync=False)

# Before conversation ends:
flush()  # Blocks until all background writes finish

from scripts import session_save, session_resume, sessions

# Save a checkpoint before ending session
session_save("Implementing FTS5 search", context={"files": ["cache.py"], "status": "in-progress"})

# In a new session: resume from last checkpoint
checkpoint = session_resume("previous-session-id")
print(checkpoint['summary'])      # What was happening
print(checkpoint['context'])      # Custom context data
print(len(checkpoint['recent_memories']))  # Recent memories from that session

# List available session checkpoints
for s in sessions():
    print(f"{s['session_id']}: {s['summary'][:60]}")

from scripts import consolidate

# Preview what would be consolidated
result = consolidate(dry_run=True)
for c in result['clusters']:
    print(f"Tag '{c['tag']}': {c['count']} memories")

# Actually consolidate (creates summaries, demotes originals to background)
result = consolidate(dry_run=False, min_cluster=3)
print(f"Consolidated {result['consolidated']} clusters, demoted {result['demoted']} memories")

# Scope to specific tags
result = consolidate(tags=["debugging"], dry_run=False)

from scripts import therapy_reflect

# Preview discovered patterns without creating memories
result = therapy_reflect(dry_run=True)
for c in result['clusters']:
    print(f"Pattern ({len(c['source_ids'])} episodes): {c['pattern'][:80]}")
    print(f"  Common tags: {c['tags']}")

# Create semantic memories from patterns
result = therapy_reflect(dry_run=False)
print(f"Created {result['created']} pattern memories from {len(result['clusters'])} clusters")