Class: Kward::Client

Inherits:
Object
  • Object
show all
Includes:
ModelPayloads
Defined in:
lib/kward/model/client.rb

Overview

Provider-facing model client used by CLI, RPC, compaction, and memory flows.

Client owns runtime provider selection, credential lookup, retry telemetry, and HTTP requests for the supported model backends. Provider-neutral payload construction and stream parsing live in ModelPayloads and ModelStreamParser; keep new provider mechanics there when they are reusable, and keep product policy such as configured provider/model selection here.

Constant Summary collapse

OPENROUTER_URL = 
URI("https://openrouter.ai/api/v1/chat/completions")
OPENROUTER_MODELS_URL = 
URI("https://openrouter.ai/api/v1/models")
CODEX_URL = 
URI("https://chatgpt.com/backend-api/codex/responses")
ANTHROPIC_URL = 
URI("https://api.anthropic.com/v1/messages")
AUTH_ERROR = 
"No OpenAI OAuth login found. Run `ruby lib/main.rb login`, or set OPENAI_ACCESS_TOKEN/OPENROUTER_API_KEY."
OPENROUTER_AUTH_ERROR = 
"No OpenRouter API key found. Set OPENROUTER_API_KEY or add openrouter_api_key to your Kward config."
COPILOT_AUTH_ERROR = 
"No GitHub Copilot OAuth login found. Run `ruby lib/main.rb login github` or set COPILOT_GITHUB_TOKEN."
ANTHROPIC_AUTH_ERROR = 
"No Anthropic OAuth login found. Run `ruby lib/main.rb login anthropic`."
DEFAULT_OPENAI_MODEL = 
ModelInfo::DEFAULT_OPENAI_MODEL
DEFAULT_OPENROUTER_MODEL = 
ModelInfo::DEFAULT_OPENROUTER_MODEL
DEFAULT_REASONING_EFFORT = 
ModelInfo::DEFAULT_REASONING_EFFORT
RETRY_DELAYS = 
[1, 2].freeze
NON_RETRYABLE_PROVIDER_LIMIT_PATTERNS = 
[
  /GoUsageLimitError/i,
  /FreeUsageLimitError/i,
  /Monthly usage limit reached/i,
  /available balance/i,
  /insufficient[_ ]quota/i,
  /out of (?:budget|credits?)/i,
  /quota exceeded/i,
  /billing/i,
  /payment required/i,
  /(?:usage|spend|credit|quota).*(?:exceeded|reached|exhausted|depleted)/i,
  /(?:exceeded|reached).*(?:usage|quota|credit|budget|balance)/i
].freeze
RequestError = 
Class.new(StandardError) do
  attr_reader :provider, :code, :body

  # Creates an object for model provider requests.
  def initialize(provider:, code:, body:)
    @provider = provider
    @code = code.to_i
    @body = body.to_s
    super("#{provider} request failed: #{code} #{@body}")
  end

  def context_overflow?
    ContextOverflow.error?(self)
  end

  def transient?
    !context_overflow? && !provider_limit? && (code == 429 || code.between?(500, 599))
  end

  def provider_limit?
    text = [message, body].compact.join("\n")
    Kward::Client::NON_RETRYABLE_PROVIDER_LIMIT_PATTERNS.any? { |pattern| text.match?(pattern) }
  end

  def message_after_attempts(attempts)
    "#{provider} request failed after #{attempts} attempts: #{code} #{body}"
  end
end
TRANSIENT_NETWORK_ERRORS = 
[IOError, EOFError, SystemCallError, Net::OpenTimeout, Net::ReadTimeout].freeze

Instance Method Summary collapse

Constructor Details

#initialize(api_key: , model: nil, openai_access_token: , oauth: OpenAIOAuth.new, github_oauth: GithubOAuth.new, anthropic_oauth: AnthropicOAuth.new, config_path: OpenAIOAuth.default_config_path, telemetry_logger: TelemetryLogger.new(config_path: config_path)) ⇒ Client

Creates an object for model provider requests.



83
84
85
86
87
88
89
90
91
92
93
94
95
96
 
# File 'lib/kward/model/client.rb', line 83

def initialize(api_key: ENV["OPENROUTER_API_KEY"], model: nil, openai_access_token: ENV["OPENAI_ACCESS_TOKEN"], oauth: OpenAIOAuth.new, github_oauth: GithubOAuth.new, anthropic_oauth: AnthropicOAuth.new, config_path: OpenAIOAuth.default_config_path, telemetry_logger: TelemetryLogger.new(config_path: config_path))
  @openrouter_api_key = presence(api_key)
  @openai_access_token = presence(openai_access_token)
  @oauth = oauth
  @github_oauth = github_oauth
  @anthropic_oauth = anthropic_oauth
  @model = model
  @config_path = File.expand_path(config_path)
  @config = load_config
  @telemetry_logger = telemetry_logger
  @copilot_models = nil
  @openrouter_models = nil
  @openrouter_catalog = nil
end

Instance Method Details

#available_models ⇒ Object

Returns model choices suitable for settings UIs.

Only providers with configured credentials are listed. The active provider may use live catalog data. Inactive logged-in providers use static supported choices plus their configured model so listing models does not perform avoidable network calls for every configured credential.



185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
 
# File 'lib/kward/model/client.rb', line 185

def available_models
  provider = current_provider
  models = []

  if provider_logged_in?("Codex")
    openai_model = model_for("Codex")
    models += ModelInfo::OPENAI_MODEL_CHOICES.map do |id|
      { provider: "Codex", id: id, current: provider == "Codex" && openai_model == id }
    end
    models << { provider: "Codex", id: openai_model, current: provider == "Codex" } unless ModelInfo::OPENAI_MODEL_CHOICES.include?(openai_model)
  end

  if provider_logged_in?("OpenRouter")
    openrouter_model = model_for("OpenRouter")
    openrouter_choices = provider == "OpenRouter" ? openrouter_model_choices : ModelInfo::OPENROUTER_MODEL_CHOICES
    models += openrouter_choices.map do |id|
      { provider: "OpenRouter", id: id, current: provider == "OpenRouter" && openrouter_model == id }
    end
    models << { provider: "OpenRouter", id: openrouter_model, current: provider == "OpenRouter" } unless openrouter_choices.include?(openrouter_model)
  end

  if provider_logged_in?("Copilot")
    copilot_model = model_for("Copilot")
    copilot_choices = provider == "Copilot" ? copilot_model_choices : static_copilot_model_choices
    models += copilot_choices.map do |id|
      { provider: "Copilot", id: id, current: provider == "Copilot" && copilot_model == id }
    end
    models << { provider: "Copilot", id: copilot_model, current: provider == "Copilot" } unless copilot_choices.include?(copilot_model)
  end

  if provider_logged_in?("Anthropic")
    anthropic_model = model_for("Anthropic")
    models += ModelInfo::ANTHROPIC_MODEL_CHOICES.map do |id|
      { provider: "Anthropic", id: id, current: provider == "Anthropic" && anthropic_model == id }
    end
    models << { provider: "Anthropic", id: anthropic_model, current: provider == "Anthropic" } unless ModelInfo::ANTHROPIC_MODEL_CHOICES.include?(anthropic_model)
  end

  # Sort models by provider, then alphabetically by id
  models.sort_by { |model| [model[:provider], model[:id]] }
end

#chat(messages, tools: [], on_reasoning_delta: nil, on_assistant_delta: nil, on_retry: nil, cancellation: nil, steering: nil, max_tokens: nil, provider: nil, model: nil, reasoning: nil) ⇒ Object 



98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
 
# File 'lib/kward/model/client.rb', line 98

def chat(messages, tools: [], on_reasoning_delta: nil, on_assistant_delta: nil, on_retry: nil, cancellation: nil, steering: nil, max_tokens: nil, provider: nil, model: nil, reasoning: nil)
  cancellation&.raise_if_cancelled!
  requested_provider = provider
  url, token, resolved_provider,  = credentials(provider: requested_provider)
  if token.to_s.empty? && !requested_provider.to_s.empty?
    url, token, resolved_provider,  = credentials
    model = nil
    reasoning = nil
  end
  raise auth_error_for(resolved_provider) if token.nil? || token.empty?

  current_model = model_for(resolved_provider, override_model: model)
  current_model = resolved_copilot_chat_model(current_model) if resolved_provider == "Copilot" && model.nil?

  validate_image_support!(resolved_provider, current_model, messages)
  request_body = JSON.dump(request_body_payload(resolved_provider, messages, tools, max_tokens: max_tokens, model: current_model, reasoning: reasoning))
  with_retries(resolved_provider, current_model, request_bytes: request_body.bytesize, on_retry: on_retry, cancellation: cancellation) do
    request_started_at = @telemetry_logger.monotonic_now
    message = nil
    status = "completed"
    error = nil
    begin
      message = chat_provider_request(
        provider: resolved_provider,
        url: url,
        token: token,
        account_id: ,
        messages: messages,
        tools: tools,
        request_body: request_body,
        current_model: current_model,
        on_reasoning_delta: on_reasoning_delta,
        on_assistant_delta: on_assistant_delta,
        cancellation: cancellation,
        max_tokens: max_tokens
      )
    rescue StandardError => e
      status = "failed"
      error = e
      raise e
    ensure
      log_model_request(provider: resolved_provider, model: current_model, request_bytes: request_body.bytesize, duration_ms: @telemetry_logger.duration_ms(request_started_at), status: status, error: error, usage: message && (message["usage"] || message[:usage]))
    end
  end
rescue *TRANSIENT_NETWORK_ERRORS => e
  raise Kward::Cancellation::CancelledError, "cancelled" if cancellation&.cancelled?

  log_error("model_request_error", e)
  raise e
rescue StandardError => e
  log_error("model_request_error", e)
  raise e
end

#current_context_parts(messages, tools) ⇒ Object

Projects messages/tools into the provider-specific context shape without sending it.



235
236
237
 
# File 'lib/kward/model/client.rb', line 235

def current_context_parts(messages, tools)
  build_context_parts(current_provider, messages, tools)
end

#current_context_window ⇒ Object

Returns the known context window for the active provider/model pair.



174
175
176
177
 
# File 'lib/kward/model/client.rb', line 174

def current_context_window
  state = current_model_state
  ModelInfo.context_window(state[:provider], state[:model])
end

#current_model ⇒ Object

Returns the model id that will be used for the next request.



164
165
166
 
# File 'lib/kward/model/client.rb', line 164

def current_model
  current_model_state[:model]
end

#current_provider ⇒ Object

Returns the active provider label after applying env/config/credential fallback rules.



153
154
155
156
157
158
159
160
161
 
# File 'lib/kward/model/client.rb', line 153

def current_provider
  _url, _token, provider = credentials
  provider
rescue StandardError
  label = ModelInfo.provider_label(configured_provider)
  return label unless label.empty?

  openai_configured? ? "Codex" : "OpenRouter"
end

#current_reasoning_effort ⇒ Object

Returns the configured reasoning effort for providers that support it.



169
170
171
 
# File 'lib/kward/model/client.rb', line 169

def current_reasoning_effort
  current_model_state[:reasoning_effort]
end

#openrouter_catalog ⇒ Object

Fetches the full OpenRouter public model catalog for settings UIs.



228
229
230
231
232
 
# File 'lib/kward/model/client.rb', line 228

def openrouter_catalog
  fetch_openrouter_models(full_catalog: true).map do |id|
    { provider: "OpenRouter", id: id, current: current_provider == "OpenRouter" && model_for("OpenRouter") == id }
  end.sort_by { |model| model[:id] }
end

#reload_config ⇒ Object

Reloads config-backed provider settings and clears live model catalog caches.



247
248
249
250
251
252
 
# File 'lib/kward/model/client.rb', line 247

def reload_config
  @config = load_config
  @copilot_models = nil
  @openrouter_models = nil
  @openrouter_catalog = nil
end

#supports_in_flight_steer? ⇒ Boolean

Returns whether the active provider can accept steering while a turn is streaming.

Returns:

  • (Boolean) 


240
241
242
243
244
 
# File 'lib/kward/model/client.rb', line 240

def supports_in_flight_steer?
  current_provider == "Codex"
rescue StandardError
  false
end