Module: Legion::LLM::Fleet::Dispatcher

Extended by:
Legion::Logging::Helper
Defined in:
lib/legion/llm/fleet/dispatcher.rb

Constant Summary collapse

DEFAULT_TIMEOUT = 
30
TIMEOUTS = 
{
  embed:    10,
  chat:     30,
  generate: 30,
  default:  30
}.freeze

Class Method Summary collapse

Class Method Details

.build_routing_key(provider:, request_type:, model:) ⇒ Object 



64
65
66
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 64

def build_routing_key(provider:, request_type:, model:)
  "llm.request.#{provider}.#{request_type}.#{sanitize_model(model)}"
end

.dispatch(model: nil, messages: nil, request: nil, message_context: {}, routing_key: nil, reply_to: nil, **opts) ⇒ Object

Backwards-compatible shim: supports old (model:, messages:) and new (request:, message_context:) callers



23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 23

def dispatch(model: nil, messages: nil, request: nil, message_context: {}, routing_key: nil, reply_to: nil, **opts)
  return error_result('fleet_unavailable', message_context: message_context) unless fleet_available?

  # Old calling convention: build minimal params from model/messages
  if request.nil? && (model || messages)
    provider = opts[:provider] || 'ollama'
    request_type = opts[:request_type] || 'chat'
    routing_key ||= build_routing_key(provider: provider, request_type: request_type, model: model)
    reply_to ||= ReplyDispatcher.agent_queue_name
    correlation_id = publish_request(
      routing_key: routing_key, reply_to: reply_to,
      provider: provider, model: model, request_type: request_type,
      messages: messages, message_context: message_context, **opts
    )
    timeout = resolve_timeout(request_type: request_type, override: opts[:timeout])
    return wait_for_response(correlation_id, timeout: timeout, message_context: message_context)
  end

  # New calling convention
  request_opts =
    if request.respond_to?(:to_h)
      request.to_h.transform_keys(&:to_sym)
    else
      {}
    end
  request_opts = request_opts.merge(opts)

  provider = request_opts[:provider] || 'ollama'
  request_type = request_opts[:request_type] || 'chat'
  model = request_opts[:model]
  routing_key ||= build_routing_key(provider: provider, request_type: request_type, model: model)
  reply_to ||= ReplyDispatcher.agent_queue_name
  correlation_id = publish_request(
    routing_key: routing_key, reply_to: reply_to,
    provider: provider, model: model, request_type: request_type,
    message_context: message_context, **request_opts.except(:provider, :model, :request_type, :timeout)
  )
  timeout = resolve_timeout(request_type: request_type, override: request_opts[:timeout] || opts[:timeout])
  wait_for_response(correlation_id, timeout: timeout, message_context: message_context)
end

.error_result(reason, message_context: {}) ⇒ Object 



159
160
161
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 159

def error_result(reason, message_context: {})
  { success: false, error: reason, message_context: message_context }
end

.fleet_available? ⇒ Boolean

Returns:

  • (Boolean) 


72
73
74
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 72

def fleet_available?
  transport_ready? && fleet_enabled?
end

.fleet_enabled? ⇒ Boolean

Returns:

  • (Boolean) 


81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 81

def fleet_enabled?
  return true unless defined?(Legion::Settings)

  settings = begin
    Legion::Settings[:llm]
  rescue StandardError => e
    handle_exception(e, level: :debug, operation: 'llm.fleet.dispatcher.fleet_enabled')
    nil
  end
  return true unless settings.is_a?(Hash)

  routing = settings[:routing]
  return true unless routing.is_a?(Hash)

  routing.fetch(:use_fleet, true)
end

.fleet_timeout_from_settings(request_type) ⇒ Object 



107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 107

def fleet_timeout_from_settings(request_type)
  return unless defined?(Legion::Settings)

  settings = begin
    Legion::Settings[:llm]
  rescue StandardError => e
    handle_exception(e, level: :debug, operation: 'llm.fleet.dispatcher.resolve_timeout')
    nil
  end

  return unless settings.is_a?(Hash)

  routing = settings[:routing]
  return unless routing.is_a?(Hash)

  fleet_settings = routing.dig(:tiers, :fleet)
  fleet_settings = routing[:fleet] unless fleet_settings.is_a?(Hash)
  return unless fleet_settings.is_a?(Hash)

  fleet_settings.dig(:timeouts, request_type.to_sym) || fleet_settings[:timeout_seconds]
end

.publish_request(**opts) ⇒ Object 



129
130
131
132
133
134
135
136
137
138
139
140
141
142
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 129

def publish_request(**opts)
  correlation_id = "req_#{SecureRandom.uuid}"
  opts[:fleet_correlation_id] = correlation_id

  if defined?(Legion::LLM::Fleet::Request)
    Legion::LLM::Fleet::Request.new(**opts).publish
  elsif defined?(Legion::Extensions::LLM::Gateway::Transport::Messages::InferenceRequest)
    Legion::Extensions::LLM::Gateway::Transport::Messages::InferenceRequest.new(
      reply_to: opts[:reply_to], **opts.except(:reply_to)
    ).publish
  end

  correlation_id
end

.resolve_timeout(request_type: :default, override: nil) ⇒ Object 



98
99
100
101
102
103
104
105
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 98

def resolve_timeout(request_type: :default, override: nil)
  return override if override

  configured = fleet_timeout_from_settings(request_type)
  return configured if configured

  TIMEOUTS[request_type.to_sym] || TIMEOUTS[:default]
end

.sanitize_model(model) ⇒ Object 



68
69
70
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 68

def sanitize_model(model)
  model.to_s.gsub(':', '.')
end

.timeout_result(correlation_id, timeout, message_context: {}) ⇒ Object 



154
155
156
157
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 154

def timeout_result(correlation_id, timeout, message_context: {})
  { success: false, error: 'fleet_timeout', correlation_id: correlation_id,
    timeout: timeout, message_context: message_context }
end

.transport_ready? ⇒ Boolean

Returns:

  • (Boolean) 


76
77
78
79
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 76

def transport_ready?
  !!(defined?(Legion::Settings) &&
     Legion::Settings[:transport][:connected] == true)
end

.wait_for_response(correlation_id, timeout:, message_context: {}) ⇒ Object 



144
145
146
147
148
149
150
151
152
 
# File 'lib/legion/llm/fleet/dispatcher.rb', line 144

def wait_for_response(correlation_id, timeout:, message_context: {})
  future = ReplyDispatcher.register(correlation_id)
  result = future.value!(timeout)
  result || timeout_result(correlation_id, timeout, message_context: message_context)
rescue Concurrent::CancelledOperationError
  timeout_result(correlation_id, timeout, message_context: message_context)
ensure
  ReplyDispatcher.deregister(correlation_id)
end