agent input
ThreadItemConverter
Converts thread items to Agent SDK input items. Widgets, Tasks, and Workflows have default conversions but can be customized. Attachments, Tags, and HiddenContextItems require custom handling based on the use case. Other item types are converted automatically.
Source code in chatkit/agent_input.py
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | |
attachment_to_message_content
async
attachment_to_message_content(attachment: Attachment) -> ResponseInputContentParam
Convert an attachment in a user message into a message content part to send to the model. Required when attachments are enabled.
Source code in chatkit/agent_input.py
105 106 107 108 109 110 111 112 113 114 | |
tag_to_message_content
async
tag_to_message_content(tag: UserMessageTagContent) -> ResponseInputContentParam
Convert a tag in a user message into a message content part to send to the model as context. Required when tags are used.
Source code in chatkit/agent_input.py
116 117 118 119 120 121 122 123 124 125 | |
generated_image_to_input
async
generated_image_to_input(item: GeneratedImageItem) -> TResponseInputItem | list[TResponseInputItem] | None
Convert a GeneratedImageItem into input item(s) to send to the model. Override this method to customize the conversion of generated images, such as when your generated image url is not publicly reachable.
Source code in chatkit/agent_input.py
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | |
hidden_context_to_input
async
hidden_context_to_input(item: HiddenContextItem) -> TResponseInputItem | list[TResponseInputItem] | None
Convert a HiddenContextItem into input item(s) to send to the model. Required to override when HiddenContextItems with non-string content are used.
Source code in chatkit/agent_input.py
154 155 156 157 158 159 160 161 162 163 164 165 166 | |
sdk_hidden_context_to_input
async
sdk_hidden_context_to_input(item: SDKHiddenContextItem) -> TResponseInputItem | list[TResponseInputItem] | None
Convert a SDKHiddenContextItem into input item to send to the model. This is used by the ChatKit Python SDK for storing additional context for internal operations. Override if you want to wrap the content in a different format.
Source code in chatkit/agent_input.py
168 169 170 171 172 173 174 175 176 177 | |
task_to_input
async
task_to_input(item: TaskItem) -> TResponseInputItem | list[TResponseInputItem] | None
Convert a TaskItem into input item(s) to send to the model.
Source code in chatkit/agent_input.py
179 180 181 182 183 184 185 | |
structured_input_to_input
async
structured_input_to_input(item: StructuredInputItem) -> TResponseInputItem | list[TResponseInputItem] | None
Convert a StructuredInputItem into input item(s) to send to the model.
Source code in chatkit/agent_input.py
187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | |
workflow_to_input
async
workflow_to_input(item: WorkflowItem) -> TResponseInputItem | list[TResponseInputItem] | None
Describe visible custom workflow tasks as model input.
Source code in chatkit/agent_input.py
211 212 213 214 215 216 217 218 219 220 221 222 | |
widget_to_input
async
widget_to_input(item: WidgetItem) -> TResponseInputItem | list[TResponseInputItem] | None
Convert a WidgetItem into input item(s) to send to the model. By default, WidgetItems converted to a text description with a JSON representation of the widget.
Source code in chatkit/agent_input.py
224 225 226 227 228 229 230 231 232 233 234 | |
client_tool_call_to_input
async
client_tool_call_to_input(item: ClientToolCallItem) -> TResponseInputItem | list[TResponseInputItem] | None
Skip browser tool display records. Use client_tool_continuation_input to resume.
Source code in chatkit/agent_input.py
311 312 313 314 315 | |
client_tool_continuation_input
client_tool_continuation_input(turn: ClientToolTurn) -> list[TResponseInputItem]
Prepare model input from a completed browser tool's native continuation.
A local continuation supplies the whole native input list. A Responses continuation supplies only the missing outputs and requires the matching provider context.
Source code in chatkit/agent_input.py
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 63 64 65 66 67 | |
simple_to_agent_input
async
simple_to_agent_input(thread_items: Sequence[ThreadItem] | ThreadItem) -> list[TResponseInputItem]
Helper that converts thread items using the default ThreadItemConverter.
Source code in chatkit/agent_input.py
382 383 384 385 386 | |