danielhanchen commited on
Commit
4e22d7e
·
verified ·
1 Parent(s): 0d5a7f9

Update chat template with tool-calling and turn-balance fixes

Browse files
Files changed (2) hide show
  1. chat_template.jinja +71 -37
  2. tokenizer_config.json +1 -1
chat_template.jinja CHANGED
@@ -116,7 +116,9 @@
116
  }
117
  {%- endmacro -%}
118
  {%- macro format_argument(argument, escape_keys=True) -%}
119
- {%- if argument is string -%}
 
 
120
  {{- '<|"|>' + argument + '<|"|>' -}}
121
  {%- elif argument is boolean -%}
122
  {{- 'true' if argument else 'false' -}}
@@ -172,18 +174,21 @@
172
  {{- '<tool_response|>' -}}
173
  {%- endmacro -%}
174
 
175
- {%- set ns = namespace(prev_message_type=None) -%}
 
176
  {%- set loop_messages = messages -%}
 
 
177
  {{- bos_token -}}
178
  {#- Handle System/Tool Definitions Block -#}
179
- {%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
180
  {{- '<|turn>system\n' -}}
181
  {#- Inject Thinking token at the very top of the FIRST system turn -#}
182
- {%- if enable_thinking is defined and enable_thinking -%}
183
  {{- '<|think|>\n' -}}
184
  {%- set ns.prev_message_type = 'think' -%}
185
  {%- endif -%}
186
- {%- if messages[0]['role'] in ['system', 'developer'] -%}
187
  {%- if messages[0]['content'] is string -%}
188
  {{- messages[0]['content'] | trim -}}
189
  {%- elif messages[0]['content'] is sequence -%}
@@ -217,31 +222,21 @@
217
  {%- if message['role'] != 'tool' -%}
218
  {%- set ns.prev_message_type = None -%}
219
  {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
220
- {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
221
- {%- set prev_nt = namespace(role=None, found=false) -%}
222
- {%- if loop.index0 > 0 -%}
223
- {%- for j in range(loop.index0 - 1, -1, -1) -%}
224
- {%- if not prev_nt.found -%}
225
- {%- if loop_messages[j]['role'] != 'tool' -%}
226
- {%- set prev_nt.role = loop_messages[j]['role'] -%}
227
- {%- set prev_nt.found = true -%}
228
- {%- endif -%}
229
- {%- endif -%}
230
- {%- endfor -%}
231
- {%- endif -%}
232
- {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
233
  {%- if not continue_same_model_turn -%}
234
  {{- '<|turn>' + role + '\n' }}
235
  {%- endif -%}
236
 
237
  {#- Render reasoning/reasoning_content as thinking channel -#}
238
  {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
239
- {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
 
240
  {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
241
  {%- endif -%}
242
 
243
- {%- if message['tool_calls'] -%}
244
- {%- for tool_call in message['tool_calls'] -%}
245
  {%- set function = tool_call['function'] -%}
246
  {{- '<|tool_call>call:' + function['name'] + '{' -}}
247
  {%- if function['arguments'] is mapping -%}
@@ -251,8 +246,18 @@
251
  {%- set ns_args.found_first = true -%}
252
  {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
253
  {%- endfor -%}
 
254
  {%- elif function['arguments'] is string -%}
255
- {{- function['arguments'] -}}
 
 
 
 
 
 
 
 
 
256
  {%- endif -%}
257
  {{- '}<tool_call|>' -}}
258
  {%- endfor -%}
@@ -262,8 +267,8 @@
262
  {%- set ns_tr_out = namespace(flag=false) -%}
263
  {%- if message.get('tool_responses') -%}
264
  {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
265
- {%- for tool_response in message['tool_responses'] -%}
266
- {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
267
  {%- set ns_tr_out.flag = true -%}
268
  {%- set ns.prev_message_type = 'tool_response' -%}
269
  {%- endfor -%}
@@ -277,8 +282,8 @@
277
  {%- else -%}
278
  {%- set follow = loop_messages[k] -%}
279
  {#- Resolve tool_call_id to function name -#}
280
- {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
281
- {%- for tc in message['tool_calls'] -%}
282
  {%- if tc.get('id') == follow.get('tool_call_id') -%}
283
  {%- set ns_tname.name = tc['function']['name'] -%}
284
  {%- endif -%}
@@ -295,6 +300,15 @@
295
  {%- endif -%}
296
  {%- endfor -%}
297
  {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
 
 
 
 
 
 
 
 
 
298
  {%- else -%}
299
  {{- format_tool_response_block(ns_tname.name, tool_body) -}}
300
  {%- endif -%}
@@ -305,29 +319,26 @@
305
  {%- endif -%}
306
 
307
  {%- set captured_content -%}
308
- {%- if message['content'] is string -%}
309
  {%- if role == 'model' -%}
310
  {{- strip_thinking(message['content']) -}}
311
  {%- else -%}
312
  {{- message['content'] | trim -}}
313
  {%- endif -%}
314
- {%- elif message['content'] is sequence -%}
315
  {%- for item in message['content'] -%}
316
- {%- if item['type'] == 'text' -%}
317
  {%- if role == 'model' -%}
318
  {{- strip_thinking(item['text']) -}}
319
  {%- else -%}
320
  {{- item['text'] | trim -}}
321
  {%- endif -%}
322
- {%- elif item['type'] == 'image' -%}
323
  {{- '<|image|>' -}}
324
- {%- set ns.prev_message_type = 'image' -%}
325
- {%- elif item['type'] == 'audio' -%}
326
  {{- '<|audio|>' -}}
327
- {%- set ns.prev_message_type = 'audio' -%}
328
- {%- elif item['type'] == 'video' -%}
329
  {{- '<|video|>' -}}
330
- {%- set ns.prev_message_type = 'video' -%}
331
  {%- endif -%}
332
  {%- endfor -%}
333
  {%- endif -%}
@@ -336,16 +347,39 @@
336
  {{- captured_content -}}
337
  {%- set has_content = captured_content | trim | length > 0 -%}
338
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
339
  {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
340
  {{- '<|tool_response>' -}}
341
- {%- elif not (ns_tr_out.flag and not has_content) -%}
 
342
  {{- '<turn|>\n' -}}
343
  {%- endif -%}
 
 
 
344
  {%- endif -%}
345
  {%- endfor -%}
346
 
347
  {%- if add_generation_prompt -%}
348
  {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
349
  {{- '<|turn>model\n' -}}
 
 
350
  {%- endif -%}
351
- {%- endif -%}
 
116
  }
117
  {%- endmacro -%}
118
  {%- macro format_argument(argument, escape_keys=True) -%}
119
+ {%- if argument is none -%}
120
+ {{- 'null' -}}
121
+ {%- elif argument is string -%}
122
  {{- '<|"|>' + argument + '<|"|>' -}}
123
  {%- elif argument is boolean -%}
124
  {{- 'true' if argument else 'false' -}}
 
174
  {{- '<tool_response|>' -}}
175
  {%- endmacro -%}
176
 
177
+ {#- ===== SETUP ===== -#}
178
+ {%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
179
  {%- set loop_messages = messages -%}
180
+ {%- set enable_thinking = enable_thinking | default(false) -%}
181
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
182
  {{- bos_token -}}
183
  {#- Handle System/Tool Definitions Block -#}
184
+ {%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
185
  {{- '<|turn>system\n' -}}
186
  {#- Inject Thinking token at the very top of the FIRST system turn -#}
187
+ {%- if enable_thinking -%}
188
  {{- '<|think|>\n' -}}
189
  {%- set ns.prev_message_type = 'think' -%}
190
  {%- endif -%}
191
+ {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
192
  {%- if messages[0]['content'] is string -%}
193
  {{- messages[0]['content'] | trim -}}
194
  {%- elif messages[0]['content'] is sequence -%}
 
222
  {%- if message['role'] != 'tool' -%}
223
  {%- set ns.prev_message_type = None -%}
224
  {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
225
+ {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
226
+ {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
 
 
 
 
 
 
 
 
 
 
 
227
  {%- if not continue_same_model_turn -%}
228
  {{- '<|turn>' + role + '\n' }}
229
  {%- endif -%}
230
 
231
  {#- Render reasoning/reasoning_content as thinking channel -#}
232
  {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
233
+ {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
234
+ {%- if thinking_text and thinking_gate -%}
235
  {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
236
  {%- endif -%}
237
 
238
+ {%- if message.get('tool_calls') -%}
239
+ {%- for tool_call in message.get('tool_calls') -%}
240
  {%- set function = tool_call['function'] -%}
241
  {{- '<|tool_call>call:' + function['name'] + '{' -}}
242
  {%- if function['arguments'] is mapping -%}
 
246
  {%- set ns_args.found_first = true -%}
247
  {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
248
  {%- endfor -%}
249
+ {%- elif function['arguments'] is none -%}
250
  {%- elif function['arguments'] is string -%}
251
+ {#- Pre-serialized args (e.g. an OpenAI JSON string). We cannot JSON-parse
252
+ portably in-template, so render non-fatally instead of erroring. Strip an
253
+ outer {...} so it composes with the DSL braces rather than double-wrapping.
254
+ Prefer passing arguments as a mapping for exact Gemma DSL. -#}
255
+ {%- set argstr = function['arguments'] | trim -%}
256
+ {%- if argstr[:1] == '{' and argstr[-1:] == '}' -%}
257
+ {{- argstr[1:-1] -}}
258
+ {%- else -%}
259
+ {{- function['arguments'] -}}
260
+ {%- endif -%}
261
  {%- endif -%}
262
  {{- '}<tool_call|>' -}}
263
  {%- endfor -%}
 
267
  {%- set ns_tr_out = namespace(flag=false) -%}
268
  {%- if message.get('tool_responses') -%}
269
  {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
270
+ {%- for tool_response in message.get('tool_responses') -%}
271
+ {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
272
  {%- set ns_tr_out.flag = true -%}
273
  {%- set ns.prev_message_type = 'tool_response' -%}
274
  {%- endfor -%}
 
282
  {%- else -%}
283
  {%- set follow = loop_messages[k] -%}
284
  {#- Resolve tool_call_id to function name -#}
285
+ {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
286
+ {%- for tc in message.get('tool_calls') -%}
287
  {%- if tc.get('id') == follow.get('tool_call_id') -%}
288
  {%- set ns_tname.name = tc['function']['name'] -%}
289
  {%- endif -%}
 
300
  {%- endif -%}
301
  {%- endfor -%}
302
  {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
303
+ {%- for part in tool_body -%}
304
+ {%- if part.get('type') in ['image', 'image_url'] -%}
305
+ {{- '<|image|>' -}}
306
+ {%- elif part.get('type') in ['audio', 'input_audio'] -%}
307
+ {{- '<|audio|>' -}}
308
+ {%- elif part.get('type') == 'video' -%}
309
+ {{- '<|video|>' -}}
310
+ {%- endif -%}
311
+ {%- endfor -%}
312
  {%- else -%}
313
  {{- format_tool_response_block(ns_tname.name, tool_body) -}}
314
  {%- endif -%}
 
319
  {%- endif -%}
320
 
321
  {%- set captured_content -%}
322
+ {%- if message.get('content') is string -%}
323
  {%- if role == 'model' -%}
324
  {{- strip_thinking(message['content']) -}}
325
  {%- else -%}
326
  {{- message['content'] | trim -}}
327
  {%- endif -%}
328
+ {%- elif message.get('content') is sequence -%}
329
  {%- for item in message['content'] -%}
330
+ {%- if item.get('type') == 'text' -%}
331
  {%- if role == 'model' -%}
332
  {{- strip_thinking(item['text']) -}}
333
  {%- else -%}
334
  {{- item['text'] | trim -}}
335
  {%- endif -%}
336
+ {%- elif item.get('type') in ['image', 'image_url'] -%}
337
  {{- '<|image|>' -}}
338
+ {%- elif item.get('type') in ['audio', 'input_audio'] -%}
 
339
  {{- '<|audio|>' -}}
340
+ {%- elif item.get('type') == 'video' -%}
 
341
  {{- '<|video|>' -}}
 
342
  {%- endif -%}
343
  {%- endfor -%}
344
  {%- endif -%}
 
347
  {{- captured_content -}}
348
  {%- set has_content = captured_content | trim | length > 0 -%}
349
 
350
+ {#- Forward-scan: find next non-tool message role for continuation detection -#}
351
+ {%- set next_nt = namespace(role=None, found=false) -%}
352
+ {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
353
+ {%- if not next_nt.found -%}
354
+ {%- if loop_messages[j]['role'] != 'tool' -%}
355
+ {%- set next_nt.role = loop_messages[j]['role'] -%}
356
+ {%- set next_nt.found = true -%}
357
+ {%- endif -%}
358
+ {%- endif -%}
359
+ {%- endfor -%}
360
+
361
+ {%- set continues_into_next = (
362
+ role == 'model'
363
+ and next_nt.role == 'assistant'
364
+ and (not message.get('tool_calls') or ns_tr_out.flag)
365
+ ) -%}
366
+
367
  {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
368
  {{- '<|tool_response>' -}}
369
+ {%- elif continues_into_next -%}
370
+ {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
371
  {{- '<turn|>\n' -}}
372
  {%- endif -%}
373
+
374
+ {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
375
+ {%- set ns.prev_non_tool_role = message['role'] -%}
376
  {%- endif -%}
377
  {%- endfor -%}
378
 
379
  {%- if add_generation_prompt -%}
380
  {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
381
  {{- '<|turn>model\n' -}}
382
+ {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
383
+ {{- '<|channel>thought\n' -}}
384
  {%- endif -%}
385
+ {%- endif -%}
tokenizer_config.json CHANGED
@@ -92,5 +92,5 @@
92
  "think_token": "<|think|>",
93
  "tokenizer_class": "GemmaTokenizer",
94
  "unk_token": "<unk>",
95
- "chat_template": "{%- macro format_parameters(properties, required, filter_keys=false) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if not filter_keys or key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking is defined and enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages[0]['role'] in ['system', 'developer'] -%}\n {%- if messages[0]['content'] is string -%}\n {{- messages[0]['content'] | trim -}}\n {%- elif messages[0]['content'] is sequence -%}\n {%- for item in messages[0]['content'] -%}\n {{- item['text'] | trim + ' '-}}\n {%- endfor -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n {%- set prev_nt = namespace(role=None, found=false) -%}\n {%- if loop.index0 > 0 -%}\n {%- for j in range(loop.index0 - 1, -1, -1) -%}\n {%- if not prev_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set prev_nt.role = loop_messages[j]['role'] -%}\n {%- set prev_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n\n {%- if message['tool_calls'] -%}\n {%- for tool_call in message['tool_calls'] -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is string -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message['tool_responses'] -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}\n {%- for tc in message['tool_calls'] -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n\n {%- set captured_content -%}\n {%- if message['content'] is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message['content'] is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item['type'] == 'image' -%}\n {{- '<|image|>' -}}\n {%- set ns.prev_message_type = 'image' -%}\n {%- elif item['type'] == 'audio' -%}\n {{- '<|audio|>' -}}\n {%- set ns.prev_message_type = 'audio' -%}\n {%- elif item['type'] == 'video' -%}\n {{- '<|video|>' -}}\n {%- set ns.prev_message_type = 'video' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endset -%}\n\n {{- captured_content -}}\n {%- set has_content = captured_content | trim | length > 0 -%}\n\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif not (ns_tr_out.flag and not has_content) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- endif -%}\n{%- endif -%}"
96
  }
 
92
  "think_token": "<|think|>",
93
  "tokenizer_class": "GemmaTokenizer",
94
  "unk_token": "<unk>",
95
+ "chat_template": "{%- macro format_parameters(properties, required, filter_keys=false) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if not filter_keys or key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is none -%}\n {{- 'null' -}}\n {%- elif argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{#- ===== SETUP ===== -#}\n{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}\n{%- set loop_messages = messages -%}\n{%- set enable_thinking = enable_thinking | default(false) -%}\n{%- set preserve_thinking = preserve_thinking | default(false) -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}\n {%- if messages[0]['content'] is string -%}\n {{- messages[0]['content'] | trim -}}\n {%- elif messages[0]['content'] is sequence -%}\n {%- for item in messages[0]['content'] -%}\n {{- item['text'] | trim + ' '-}}\n {%- endfor -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}\n {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}\n {%- if thinking_text and thinking_gate -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n\n {%- if message.get('tool_calls') -%}\n {%- for tool_call in message.get('tool_calls') -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is none -%}\n {%- elif function['arguments'] is string -%}\n {#- Pre-serialized args (e.g. an OpenAI JSON string). We cannot JSON-parse\n portably in-template, so render non-fatally instead of erroring. Strip an\n outer {...} so it composes with the DSL braces rather than double-wrapping.\n Prefer passing arguments as a mapping for exact Gemma DSL. -#}\n {%- set argstr = function['arguments'] | trim -%}\n {%- if argstr[:1] == '{' and argstr[-1:] == '}' -%}\n {{- argstr[1:-1] -}}\n {%- else -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message.get('tool_responses') -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}\n {%- for tc in message.get('tool_calls') -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- for part in tool_body -%}\n {%- if part.get('type') in ['image', 'image_url'] -%}\n {{- '<|image|>' -}}\n {%- elif part.get('type') in ['audio', 'input_audio'] -%}\n {{- '<|audio|>' -}}\n {%- elif part.get('type') == 'video' -%}\n {{- '<|video|>' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n\n {%- set captured_content -%}\n {%- if message.get('content') is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message.get('content') is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item.get('type') == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item.get('type') in ['image', 'image_url'] -%}\n {{- '<|image|>' -}}\n {%- elif item.get('type') in ['audio', 'input_audio'] -%}\n {{- '<|audio|>' -}}\n {%- elif item.get('type') == 'video' -%}\n {{- '<|video|>' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endset -%}\n\n {{- captured_content -}}\n {%- set has_content = captured_content | trim | length > 0 -%}\n\n {#- Forward-scan: find next non-tool message role for continuation detection -#}\n {%- set next_nt = namespace(role=None, found=false) -%}\n {%- for j in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if not next_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set next_nt.role = loop_messages[j]['role'] -%}\n {%- set next_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n\n {%- set continues_into_next = (\n role == 'model'\n and next_nt.role == 'assistant'\n and (not message.get('tool_calls') or ns_tr_out.flag)\n ) -%}\n\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif continues_into_next -%}\n {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n\n {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}\n {%- set ns.prev_non_tool_role = message['role'] -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}\n {{- '<|channel>thought\\n' -}}\n {%- endif -%}\n{%- endif -%}\n"
96
  }