view release on metacpan or  search on metacpan

.claude/skills/perl-ai-langertha/SKILL.md  view on Meta::CPAN

## Simple Chat

```perl
# Synchronous
my $response = $engine->simple_chat('What is Perl?');
print $response;  # Stringifies to content

# Async
use Future::AsyncAwait;
my $response = await $engine->simple_chat_f('Tell me a story.');
say $response->model;              # Model name
say $response->prompt_tokens;      # Token usage
say $response->completion_tokens;
say $response->thinking;           # Chain-of-thought (if available)
```

`Langertha::Response` overloads `""` so it works in string contexts.
</simple-chat>

<tool-calling>
## Tool Calling with MCP

### Step 1: Create MCP Server with tools

.claude/skills/perl-ai-langertha/SKILL.md  view on Meta::CPAN

```perl
my $engine = Langertha::Engine::Anthropic->new(
    api_key     => $ENV{ANTHROPIC_API_KEY},
    model       => 'claude-sonnet-4-6',
    mcp_servers => [$mcp],  # Pass MCP server(s)
);

# One-shot tool calling
my $response = await $engine->chat_with_tools_f('Find all .pm files in lib/');
say $response;
```
</tool-calling>

<raider>
## Raider — Autonomous Agent

```perl
use Langertha::Raider;

my $raider = Langertha::Raider->new(

.claude/skills/perl-ai-langertha/SKILL.md  view on Meta::CPAN

    context_compress_threshold => 0.75,
    compression_engine         => $cheap_model,
    raider_mcp                 => 1,   # Enable self-tools (ask_user, pause, abort)
    plugins                    => ['Langfuse'],
);

# Raid (autonomous tool-calling loop)
my $result = await $raider->raid_f('Review lib/App.pm');

# Result handling
say $result;                # Stringified response
say $result->is_question;   # Agent asked a question
say $result->is_abort;      # Agent aborted

# Continue conversation (has context from previous raids)
my $r2 = await $raider->raid_f('Now suggest improvements.');

# Respond to question
if ($result->is_question) {
    my $next = await $raider->respond_f('Yes, go ahead.');
}

# History management
$raider->add_history('user', $content);  # Replay from DB
$raider->clear_history;                  # Reset

# Metrics
my $m = $raider->metrics;
say "Iterations: $m->{iterations}";
say "Tool calls: $m->{tool_calls}";
```

### Raid Loop (simplified)

1. Auto-compress history if context threshold exceeded
2. Gather tools from MCP servers + inline tools + self-tools
3. Build conversation: mission + history + new messages
4. Call LLM with tools
5. If tool calls: execute via MCP, add results to conversation, loop
6. If no tool calls: extract final text, persist to history, return result