The claims. The architecture. The limits.

# Every session appends to persistent memory
# with timestamped source tracking

timestamp = datetime.now(timezone.utc)
separator = f"\n\n--- {source} ({timestamp}) ---\n"

if memory:
    existing = memory.content.strip()
    memory.content = existing + separator + new_content
    memory.updated_at = datetime.now(timezone.utc)
else:
    memory = PersonaMemory(
        user_id=user_id,
        persona_key=persona_key,
        content=new_content,
    )

# Call context adapts to WHY the call is happening

def get_trigger_context(trigger_type, call_topic=None):
    if trigger_type == "manual":
        if call_topic:
            return (
                f'The user asked you to call about '
                f'a SPECIFIC topic: "{call_topic}". '
                'Lead with the topic.'
            )
    elif trigger_type == "team_blocked":
        return "The team is working on a milestone..."

# Compression preserves critical preferences
# MUST-ENFORCE count validated before and after

before_count = content.count("MUST-ENFORCE")
compressed = await compress_with_ai(content)
after_count = compressed.count("MUST-ENFORCE")

if after_count < before_count:
    logger.warning("Compression dropped preferences — aborting")
    return None  # Never lose client preferences

# Optimistic lock prevents concurrent corruption
if memory.updated_at != lock_timestamp:
    return None  # Someone wrote while we compressed

# Each milestone runs as an isolated subagent
# with a fresh 1M context window

async def advance_milestone(project, action, status):
    if action == "complete":
        sign_off_milestone(current)
        next_ms = kick_off_milestone(project)
        context = build_milestone_context(next_ms)
        return {"action": "continue", "context": context}
    elif action == "blocked":
        project.build_mode_paused = True
        initiate_call(persona="carl")
        return {"action": "paused"}