Class: Raif::Task
- Inherits:
-
ApplicationRecord
- Object
- ApplicationRecord
- Raif::Task
- Includes:
- Concerns::HasAvailableModelTools, Concerns::HasLlm, Concerns::HasPromptTemplates, Concerns::HasRequestedLanguage, Concerns::HasRuntimeDuration, Concerns::InvokesModelTools, Concerns::JsonSchemaDefinition, Concerns::LlmDataRetention, Concerns::LlmPromptCaching, Concerns::LlmResponseParsing, Concerns::LlmTemperature, Concerns::RunWith
- Defined in:
- app/models/raif/task.rb
Direct Known Subclasses
Constant Summary
Constants included from Concerns::LlmResponseParsing
Concerns::LlmResponseParsing::ASCII_CONTROL_CHARS
Instance Attribute Summary collapse
-
#files ⇒ Object
Returns the value of attribute files.
-
#images ⇒ Object
Returns the value of attribute images.
Class Method Summary collapse
-
.build_for_batch(batch:, batch_custom_id: nil, creator: nil, available_model_tools: [], llm_model_key: nil, images: [], files: [], **args) ⇒ Raif::Task
Builds a Raif::Task and a pending Raif::ModelCompletion attached to the given Raif::ModelCompletionBatch, without performing the LLM request.
-
.find_sti_class(type_name) ⇒ Object
A task's subclass lives in the host application and can be deleted while its rows remain.
- .json_response_schema(&block) ⇒ Object
-
.prompt(creator: nil, **args) ⇒ String
Returns the LLM prompt for the task.
-
.run(creator: nil, available_model_tools: [], llm_model_key: nil, images: [], files: [], **args, &block) ⇒ Raif::Task?
The primary interface for running a task.
-
.system_prompt(creator: nil, **args) ⇒ String
Returns the LLM system prompt for the task.
Instance Method Summary collapse
- #build_prompt ⇒ Object
- #build_system_prompt ⇒ Object
-
#json_response_schema ⇒ Object
Instance method to get the JSON response schema For instance-dependent schemas, builds the schema with this instance as context For class-level schemas, returns the class-level schema.
- #messages ⇒ Object
-
#prepare_for_batch!(batch:, batch_custom_id: nil, skip_prompt_population: false) ⇒ Raif::ModelCompletion
Populates this task's prompts and creates the pending Raif::ModelCompletion that will be sent through the batch.
-
#process_completion!(model_completion) ⇒ self
Wires a (possibly batch-resolved) Raif::ModelCompletion back into this task: links it as the task's raif_model_completion, mirrors raw_response onto the task, processes any tool calls the model made, and transitions the task to completed (or failed, if the underlying completion failed).
-
#prompt_studio_task_attributes ⇒ Hash
Returns additional attributes to assign when creating tasks in Prompt Studio (reruns, batch runs, and judge tasks).
- #re_run(&block) ⇒ Object
- #run(skip_prompt_population: false, &block) ⇒ Object
- #status ⇒ Object
Methods included from Concerns::RunWith
deserialize_run_with_value, gid_string?, locate_gid, serialize_run_with_value
Methods included from Concerns::JsonSchemaDefinition
Methods included from Concerns::LlmResponseParsing
#parse_html_response, #parse_json_response, #parsed_response
Methods included from Concerns::HasRuntimeDuration
#runtime_duration, #runtime_duration_seconds, #runtime_ended_at
Methods included from Concerns::HasAvailableModelTools
Methods included from Concerns::HasRequestedLanguage
#requested_language_name, #system_prompt_language_preference
Methods included from Concerns::HasLlm
Instance Attribute Details
#files ⇒ Object
Returns the value of attribute files.
77 78 79 |
# File 'app/models/raif/task.rb', line 77 def files @files end |
#images ⇒ Object
Returns the value of attribute images.
77 78 79 |
# File 'app/models/raif/task.rb', line 77 def images @images end |
Class Method Details
.build_for_batch(batch:, batch_custom_id: nil, creator: nil, available_model_tools: [], llm_model_key: nil, images: [], files: [], **args) ⇒ Raif::Task
Builds a Raif::Task and a pending Raif::ModelCompletion attached to the given Raif::ModelCompletionBatch, without performing the LLM request. The provider's batch-submission code reads the pending completion's request fields when constructing its per-entry batch payload.
The task is persisted with started_at: nil (state :pending). The pending ModelCompletion has raif_model_completion_batch_id pointing at the batch and batch_custom_id set to the value used as the provider's custom_id in the batch payload.
223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 |
# File 'app/models/raif/task.rb', line 223 def self.build_for_batch(batch:, batch_custom_id: nil, creator: nil, available_model_tools: [], llm_model_key: nil, images: [], files: [], **args) task = build_task_instance( creator: creator, available_model_tools: available_model_tools, llm_model_key: llm_model_key, images: images, files: files, **args ) task.save! task.prepare_for_batch!(batch: batch, batch_custom_id: batch_custom_id) task end |
.find_sti_class(type_name) ⇒ Object
A task's subclass lives in the host application and can be deleted while its rows remain. Reading such a row must not raise: it is the oldest rows that are most likely to name a class that is gone, and those are exactly the ones Raif::ArchiveTasksJob has to serialize and the admin has to list. The row's own columns are all that either path needs.
87 88 89 90 91 |
# File 'app/models/raif/task.rb', line 87 def self.find_sti_class(type_name) super rescue ActiveRecord::SubclassNotFound Raif::Task end |
.json_response_schema(&block) ⇒ Object
323 324 325 326 327 328 329 |
# File 'app/models/raif/task.rb', line 323 def self.json_response_schema(&block) if block_given? json_schema_definition(:json_response, &block) elsif schema_defined?(:json_response) schema_for(:json_response) end end |
.prompt(creator: nil, **args) ⇒ String
Returns the LLM prompt for the task.
310 311 312 |
# File 'app/models/raif/task.rb', line 310 def self.prompt(creator: nil, **args) new(creator:, **args).build_prompt end |
.run(creator: nil, available_model_tools: [], llm_model_key: nil, images: [], files: [], **args, &block) ⇒ Raif::Task?
The primary interface for running a task. It will hit the LLM with the task's prompt and system prompt and return a Raif::Task object. It will also create a new Raif::ModelCompletion record.
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 |
# File 'app/models/raif/task.rb', line 115 def self.run(creator: nil, available_model_tools: [], llm_model_key: nil, images: [], files: [], **args, &block) task = build_task_instance( creator: creator, available_model_tools: available_model_tools, llm_model_key: llm_model_key, images: images, files: files, started_at: Time.current, **args ) task.save! task.run(&block) task rescue StandardError => e task&.failed! # An authorization veto is intentional, not a model failure - re-raise it # to the caller instead of logging/reporting it as an error. raise if e.is_a?(Raif::Errors::ModelCompletionAuthorizationError) logger.error e. logger.error e.backtrace.join("\n") if defined?(Airbrake) notice = Airbrake.build_notice(e) notice[:context][:component] = "raif_task" notice[:context][:action] = name Airbrake.notify(notice) end task end |
.system_prompt(creator: nil, **args) ⇒ String
Returns the LLM system prompt for the task.
319 320 321 |
# File 'app/models/raif/task.rb', line 319 def self.system_prompt(creator: nil, **args) new(creator:, **args).build_system_prompt end |
Instance Method Details
#build_prompt ⇒ Object
347 348 349 |
# File 'app/models/raif/task.rb', line 347 def build_prompt raise NotImplementedError, "Raif::Task subclasses must implement #build_prompt" end |
#build_system_prompt ⇒ Object
351 352 353 354 355 356 |
# File 'app/models/raif/task.rb', line 351 def build_system_prompt sp = Raif.config.task_system_prompt_intro sp = sp.call(self) if sp.respond_to?(:call) sp += system_prompt_language_preference if requested_language_key.present? sp end |
#json_response_schema ⇒ Object
Instance method to get the JSON response schema For instance-dependent schemas, builds the schema with this instance as context For class-level schemas, returns the class-level schema
334 335 336 |
# File 'app/models/raif/task.rb', line 334 def json_response_schema schema_for_instance(:json_response) end |
#messages ⇒ Object
301 302 303 |
# File 'app/models/raif/task.rb', line 301 def [{ "role" => "user", "content" => }] end |
#prepare_for_batch!(batch:, batch_custom_id: nil, skip_prompt_population: false) ⇒ Raif::ModelCompletion
Populates this task's prompts and creates the pending Raif::ModelCompletion that will be sent through the batch. Mirrors Raif::Task#run's default behavior: prompts are rebuilt every call unless skip_prompt_population: true is passed (e.g. for re-prepare flows where the caller has hand-set prompts and wants them preserved).
The default batch_custom_id is "raif_task_<task.id>" — a task-specific identifier. Other producers (non-task) should pass an explicit batch_custom_id when building their own pending completions via Raif::Llm#build_pending_model_completion; the only requirement is uniqueness within the batch.
275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 |
# File 'app/models/raif/task.rb', line 275 def prepare_for_batch!(batch:, batch_custom_id: nil, skip_prompt_population: false) populate_prompts unless skip_prompt_population save! if changed? effective_batch_custom_id = batch_custom_id.presence || "raif_task_#{id}" mc = llm.build_pending_model_completion( messages: , source: self, system_prompt: system_prompt, response_format: response_format.to_sym, available_model_tools: available_model_tools, temperature: self.class.temperature, anthropic_prompt_caching_enabled: self.class.anthropic_prompt_caching_enabled, bedrock_prompt_caching_enabled: self.class.bedrock_prompt_caching_enabled, open_ai_store_responses: self.class.open_ai_store_responses, open_router_data_collection: self.class.open_router_data_collection, open_router_zdr: self.class.open_router_zdr, raif_model_completion_batch: batch, batch_custom_id: effective_batch_custom_id ) self.raif_model_completion = mc mc end |
#process_completion!(model_completion) ⇒ self
Wires a (possibly batch-resolved) Raif::ModelCompletion back into this task: links it as the task's raif_model_completion, mirrors raw_response onto the task, processes any tool calls the model made, and transitions the task to completed (or failed, if the underlying completion failed). Called by both the synchronous #run path and the batch completion handler after the provider's per-entry result has been applied.
194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
# File 'app/models/raif/task.rb', line 194 def process_completion!(model_completion) self.raif_model_completion = model_completion.becomes(Raif::ModelCompletion) update(raw_response: raif_model_completion.raw_response) if raif_model_completion.failed? # Failure detail (failure_error / failure_reason) lives on the model # completion; the task's `failed_at` is just a state marker. failed! else process_model_tool_invocations completed! end self end |
#prompt_studio_task_attributes ⇒ Hash
Returns additional attributes to assign when creating tasks in Prompt Studio (reruns, batch runs, and judge tasks). Override in your ApplicationTask or task subclass to include app-specific attributes.
343 344 345 |
# File 'app/models/raif/task.rb', line 343 def prompt_studio_task_attributes {} end |
#re_run(&block) ⇒ Object
180 181 182 183 |
# File 'app/models/raif/task.rb', line 180 def re_run(&block) update_columns(started_at: Time.current) run(skip_prompt_population: true, &block) end |
#run(skip_prompt_population: false, &block) ⇒ Object
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 |
# File 'app/models/raif/task.rb', line 150 def run(skip_prompt_population: false, &block) update_columns(started_at: Time.current) if started_at.nil? populate_prompts unless skip_prompt_population streaming_block = if block_given? proc do |model_completion, delta, sse_event| update_columns(raw_response: model_completion.raw_response, updated_at: Time.current) block.call(model_completion, delta, sse_event) end end mc = llm.chat( messages: , source: self, system_prompt: system_prompt, response_format: response_format.to_sym, available_model_tools: available_model_tools, temperature: self.class.temperature, anthropic_prompt_caching_enabled: self.class.anthropic_prompt_caching_enabled, bedrock_prompt_caching_enabled: self.class.bedrock_prompt_caching_enabled, open_ai_store_responses: self.class.open_ai_store_responses, open_router_data_collection: self.class.open_router_data_collection, open_router_zdr: self.class.open_router_zdr, &streaming_block ) process_completion!(mc) end |
#status ⇒ Object
93 94 95 96 97 98 99 100 101 102 103 |
# File 'app/models/raif/task.rb', line 93 def status if completed_at? :completed elsif failed_at? :failed elsif started_at? :in_progress else :pending end end |