import sys
sys.path.append('/home/user/claude-skills/orchestrating-agents/scripts')
from claude_client import invoke_claude

response = invoke_claude(
    prompt="Analyze this code for security vulnerabilities: ...",
    model="claude-sonnet-4-6"
)
print(response)

from claude_client import invoke_parallel

prompts = [
    {
        "prompt": "Analyze from security perspective: ...",
        "system": "You are a security expert"
    },
    {
        "prompt": "Analyze from performance perspective: ...",
        "system": "You are a performance optimization expert"
    },
    {
        "prompt": "Analyze from maintainability perspective: ...",
        "system": "You are a software architecture expert"
    }
]

results = invoke_parallel(prompts, model="claude-sonnet-4-6")

for i, result in enumerate(results):
    print(f"\n=== Perspective {i+1} ===")
    print(result)

from claude_client import invoke_parallel

# Large context shared across all sub-agents (e.g., codebase, documentation)
base_context = """
<codebase>
...large codebase or documentation (1000+ tokens)...
</codebase>
"""

prompts = [
    {"prompt": "Find security vulnerabilities in the authentication module"},
    {"prompt": "Identify performance bottlenecks in the API layer"},
    {"prompt": "Suggest refactoring opportunities in the database layer"}
]

# First sub-agent creates cache, subsequent ones reuse it
results = invoke_parallel(
    prompts,
    shared_system=base_context,
    cache_shared_system=True  # 90% cost reduction for cached content
)

from claude_client import ConversationThread

# Create a conversation thread (auto-caches history)
agent = ConversationThread(
    system="You are a code refactoring expert with access to the codebase",
    cache_system=True
)

# Turn 1: Initial analysis
response1 = agent.send("Analyze the UserAuth class for issues")
print(response1)

# Turn 2: Follow-up (reuses cached system + turn 1)
response2 = agent.send("How would you refactor the login method?")
print(response2)

# Turn 3: Implementation (reuses all previous context)
response3 = agent.send("Show me the refactored code")
print(response3)

from claude_client import invoke_claude_streaming

def show_progress(chunk):
    print(chunk, end='', flush=True)

response = invoke_claude_streaming(
    "Write a comprehensive security analysis...",
    callback=show_progress
)

from claude_client import invoke_parallel_streaming

def agent1_callback(chunk):
    print(f"[Security] {chunk}", end='', flush=True)

def agent2_callback(chunk):
    print(f"[Performance] {chunk}", end='', flush=True)

results = invoke_parallel_streaming(
    [
        {"prompt": "Security review: ..."},
        {"prompt": "Performance review: ..."}
    ],
    callbacks=[agent1_callback, agent2_callback]
)

from claude_client import invoke_parallel_interruptible, InterruptToken
import threading
import time

token = InterruptToken()

# Run in background
def run_analysis():
    results = invoke_parallel_interruptible(
        prompts=[...],
        interrupt_token=token
    )
    return results

thread = threading.Thread(target=run_analysis)
thread.start()

# Interrupt after 5 seconds
time.sleep(5)
token.interrupt()

invoke_claude(
    prompt: str | list[dict],
    model: str = "claude-sonnet-4-6",
    system: str | list[dict] | None = None,
    max_tokens: int = 4096,
    temperature: float = 1.0,
    streaming: bool = False,
    cache_system: bool = False,
    cache_prompt: bool = False,
    messages: list[dict] | None = None,
    **kwargs
) -> str

invoke_parallel(
    prompts: list[dict],
    model: str = "claude-sonnet-4-6",
    max_tokens: int = 4096,
    max_workers: int = 5,
    shared_system: str | list[dict] | None = None,
    cache_shared_system: bool = False
) -> list[str]

invoke_claude_streaming(
    prompt: str | list[dict],
    callback: callable = None,
    model: str = "claude-sonnet-4-6",
    system: str | list[dict] | None = None,
    max_tokens: int = 4096,
    temperature: float = 1.0,
    cache_system: bool = False,
    cache_prompt: bool = False,
    **kwargs
) -> str

invoke_parallel_streaming(
    prompts: list[dict],
    callbacks: list[callable] = None,
    model: str = "claude-sonnet-4-6",
    max_tokens: int = 4096,
    max_workers: int = 5,
    shared_system: str | list[dict] | None = None,
    cache_shared_system: bool = False
) -> list[str]

invoke_parallel_interruptible(
    prompts: list[dict],
    interrupt_token: InterruptToken = None,
    # ... same other parameters as invoke_parallel
) -> list[str]

thread = ConversationThread(
    system: str | list[dict] | None = None,
    model: str = "claude-sonnet-4-6",
    max_tokens: int = 4096,
    temperature: float = 1.0,
    cache_system: bool = True
)

response = thread.send(
    user_message: str | list[dict],
    cache_history: bool = True
) -> str

from claude_client import StallDetector

def handle_stall(task_id, idle_seconds):
    print(f"Task {task_id} stalled for {idle_seconds:.1f}s")

detector = StallDetector(timeout=60.0, on_stall=handle_stall)
detector.register("task-1")
detector.start_monitoring(poll_interval=5.0)

# Call heartbeat() during streaming/progress
detector.heartbeat("task-1")

# When done
detector.unregister("task-1")
detector.stop_monitoring()

from task_state import TaskTracker, TaskState

tracker = TaskTracker(max_retries=3)
tracker.add("task-1", category="security")

tracker.claim("task-1")    # UNCLAIMED → CLAIMED
tracker.start("task-1")    # CLAIMED → RUNNING (increments attempt)
tracker.complete("task-1")  # RUNNING → COMPLETED

# On failure with retry:
tracker.fail("task-2", error="timeout")
tracker.retry("task-2")     # FAILED → RETRY_QUEUED (if under max_retries)
tracker.claim("task-2")     # RETRY_QUEUED → CLAIMED

# Query state
tracker.active_count(category="security")
tracker.get_by_state(TaskState.RUNNING)
tracker.summary()  # {"completed": 1, "running": 1, ...}

from orchestration import invoke_with_retry

response = invoke_with_retry(
    "Analyze this code...",
    max_retries=3,
    base_delay_ms=1000,   # 1s, 2s, 4s backoff
    max_delay_ms=10000,   # capped at 10s
)

from orchestration import invoke_parallel_managed, ConcurrencyLimiter

limiter = ConcurrencyLimiter(
    global_limit=10,
    category_limits={"security": 3, "perf": 3}
)

def reconcile(prompts, tracker):
    # Filter out invalid/duplicate work before dispatch
    return [p for p in prompts if should_run(p)]

results = invoke_parallel_managed(
    prompts=[
        {"prompt": "Security review...", "task_id": "sec-1", "category": "security"},
        {"prompt": "Perf review...", "task_id": "perf-1", "category": "perf"},
    ],
    reconcile=reconcile,
    concurrency_limiter=limiter,
    max_retries=3,
    stall_timeout=60.0,
    on_stall=lambda tid, idle: print(f"{tid} stalled"),
)

python3 -c "import anthropic; print(f'✓ anthropic {anthropic.__version__}')"

from claude_client import invoke_claude, ClaudeInvocationError

try:
    response = invoke_claude("Your prompt here")
except ClaudeInvocationError as e:
    print(f"API Error: {e}")
    print(f"Status: {e.status_code}")
    print(f"Details: {e.details}")
except ValueError as e:
    print(f"Configuration Error: {e}")