vh
5e47a59b32
The multi-turn Gemma-4 CoT problem is solved. One MeroMero-v2 seat, one weight set,
two aliases: char-rp (prose) + char-rp-reasoning (streaming chain-of-thought).
The winning stack, traced from vLLM source by the four-arm brokkr/dwarf panel:
- vllm/vllm-openai:v0.26.0 — ships transformers 5.14.1 natively, below the
head_dim guard, so Gemma-4-31B loads with no pin and no custom image. It also
carries the #48217 streaming pre-arm fix.
- A patched chat template whose enable_thinking:true branch force-opens a BARE
<|channel> (not <|channel>thought\n -- full-open defeats _preprocess_feed's
injection). --chat-template override, no re-quant.
- Two served-names char-rp / char-rp-thinking; --reasoning-parser gemma4;
default enable_thinking:false. LiteLLM char-rp -> prose, char-rp-reasoning ->
the thinking served-name with enable_thinking:true.
Verified: streaming CoT split 6/6 direct on :8016 and 3/3 through the gateway;
char-rp prose clean on both transports with no trailing-token leak.
Two hard-won facts recorded in persistent-memory:
- STREAMING ONLY. Non-streaming can't split -- extract_reasoning never receives
prompt_token_ids so the pre-arm can't fire (a vLLM one-shot bug unchanged
across v0.24-0.27). Fine here: Lobe/OWUI stream. Upstream PR #49797 fixes
non-streaming too, landing ~v0.28.0 -- then it's a clean image bump.
- KEY-NAME TRAP: vLLM streams reasoning in delta.reasoning; LiteLLM normalizes
to delta.reasoning_content. I lost two false-negative test rounds to this.
Canonical: stacks/meromero-charrp/ (compose + patched_chat_template.jinja) and
stacks/litellm/conf/config.yaml. Rollback is the .env image line + dropping
--chat-template.
356 lines
17 KiB
Django/Jinja
356 lines
17 KiB
Django/Jinja
{%- macro format_parameters(properties, required, filter_keys=false) -%}
|
|
{%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
|
|
{%- set ns = namespace(found_first=false) -%}
|
|
{%- for key, value in properties | dictsort -%}
|
|
{%- set add_comma = false -%}
|
|
{%- if not filter_keys or key not in standard_keys -%}
|
|
{%- if ns.found_first %},{% endif -%}
|
|
{%- set ns.found_first = true -%}
|
|
{{ key }}:{
|
|
{%- if value['description'] -%}
|
|
description:<|"|>{{ value['description'] }}<|"|>
|
|
{%- set add_comma = true -%}
|
|
{%- endif -%}
|
|
{%- if value['type'] | upper == 'STRING' -%}
|
|
{%- if value['enum'] -%}
|
|
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
|
enum:{{ format_argument(value['enum']) }}
|
|
{%- endif -%}
|
|
{%- elif value['type'] | upper == 'ARRAY' -%}
|
|
{%- if value['items'] is mapping and value['items'] -%}
|
|
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
|
items:{
|
|
{%- set ns_items = namespace(found_first=false) -%}
|
|
{%- for item_key, item_value in value['items'] | dictsort -%}
|
|
{%- if item_value is not none -%}
|
|
{%- if ns_items.found_first %},{% endif -%}
|
|
{%- set ns_items.found_first = true -%}
|
|
{%- if item_key == 'properties' -%}
|
|
properties:{
|
|
{%- if item_value is mapping -%}
|
|
{{- format_parameters(item_value, value['items']['required'] | default([])) -}}
|
|
{%- endif -%}
|
|
}
|
|
{%- elif item_key == 'required' -%}
|
|
required:[
|
|
{%- for req_item in item_value -%}
|
|
<|"|>{{- req_item -}}<|"|>
|
|
{%- if not loop.last %},{% endif -%}
|
|
{%- endfor -%}
|
|
]
|
|
{%- elif item_key == 'type' -%}
|
|
{%- if item_value is string -%}
|
|
type:{{ format_argument(item_value | upper) }}
|
|
{%- else -%}
|
|
type:{{ format_argument(item_value | map('upper') | list) }}
|
|
{%- endif -%}
|
|
{%- else -%}
|
|
{{ item_key }}:{{ format_argument(item_value) }}
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
}
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
{%- if value['nullable'] %}
|
|
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
|
nullable:true
|
|
{%- endif -%}
|
|
{%- if value['type'] | upper == 'OBJECT' -%}
|
|
{%- if value['properties'] is defined and value['properties'] is mapping -%}
|
|
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
|
properties:{
|
|
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
|
|
}
|
|
{%- elif value is mapping -%}
|
|
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
|
properties:{
|
|
{{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
|
|
}
|
|
{%- endif -%}
|
|
{%- if value['required'] -%}
|
|
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
|
required:[
|
|
{%- for item in value['required'] | default([]) -%}
|
|
<|"|>{{- item -}}<|"|>
|
|
{%- if not loop.last %},{% endif -%}
|
|
{%- endfor -%}
|
|
]
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
|
type:<|"|>{{ value['type'] | upper }}<|"|>}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{%- endmacro -%}
|
|
{%- macro format_function_declaration(tool_data) -%}
|
|
declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
|
|
{%- set params = tool_data['function']['parameters'] -%}
|
|
{%- if params -%}
|
|
,parameters:{
|
|
{%- if params['properties'] -%}
|
|
properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
|
|
{%- endif -%}
|
|
{%- if params['required'] -%}
|
|
required:[
|
|
{%- for item in params['required'] -%}
|
|
<|"|>{{- item -}}<|"|>
|
|
{{- ',' if not loop.last -}}
|
|
{%- endfor -%}
|
|
],
|
|
{%- endif -%}
|
|
{%- if params['type'] -%}
|
|
type:<|"|>{{- params['type'] | upper -}}<|"|>}
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
{%- if 'response' in tool_data['function'] -%}
|
|
{%- set response_declaration = tool_data['function']['response'] -%}
|
|
,response:{
|
|
{%- if response_declaration['description'] -%}
|
|
description:<|"|>{{- response_declaration['description'] -}}<|"|>,
|
|
{%- endif -%}
|
|
{%- if response_declaration['type'] | upper == 'OBJECT' -%}
|
|
type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
}
|
|
{%- endmacro -%}
|
|
{%- macro format_argument(argument, escape_keys=True) -%}
|
|
{%- if argument is string -%}
|
|
{{- '<|"|>' + argument + '<|"|>' -}}
|
|
{%- elif argument is boolean -%}
|
|
{{- 'true' if argument else 'false' -}}
|
|
{%- elif argument is mapping -%}
|
|
{{- '{' -}}
|
|
{%- set ns = namespace(found_first=false) -%}
|
|
{%- for key, value in argument | dictsort -%}
|
|
{%- if ns.found_first %},{% endif -%}
|
|
{%- set ns.found_first = true -%}
|
|
{%- if escape_keys -%}
|
|
{{- '<|"|>' + key + '<|"|>' -}}
|
|
{%- else -%}
|
|
{{- key -}}
|
|
{%- endif -%}
|
|
:{{- format_argument(value, escape_keys=escape_keys) -}}
|
|
{%- endfor -%}
|
|
{{- '}' -}}
|
|
{%- elif argument is sequence -%}
|
|
{{- '[' -}}
|
|
{%- for item in argument -%}
|
|
{{- format_argument(item, escape_keys=escape_keys) -}}
|
|
{%- if not loop.last %},{% endif -%}
|
|
{%- endfor -%}
|
|
{{- ']' -}}
|
|
{%- else -%}
|
|
{{- argument -}}
|
|
{%- endif -%}
|
|
{%- endmacro -%}
|
|
{%- macro strip_thinking(text) -%}
|
|
{%- set ns = namespace(result='') -%}
|
|
{%- for part in text.split('<channel|>') -%}
|
|
{%- if '<|channel>' in part -%}
|
|
{%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
|
|
{%- else -%}
|
|
{%- set ns.result = ns.result + part -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{{- ns.result | trim -}}
|
|
{%- endmacro -%}
|
|
|
|
{%- macro format_tool_response_block(tool_name, response) -%}
|
|
{{- '<|tool_response>' -}}
|
|
{%- if response is mapping -%}
|
|
{{- 'response:' + tool_name + '{' -}}
|
|
{%- for key, value in response | dictsort -%}
|
|
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
|
{%- if not loop.last %},{% endif -%}
|
|
{%- endfor -%}
|
|
{{- '}' -}}
|
|
{%- else -%}
|
|
{{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
|
|
{%- endif -%}
|
|
{{- '<tool_response|>' -}}
|
|
{%- endmacro -%}
|
|
|
|
{%- set ns = namespace(prev_message_type=None) -%}
|
|
{%- set loop_messages = messages -%}
|
|
{{- bos_token -}}
|
|
{#- Handle System/Tool Definitions Block -#}
|
|
{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
|
|
{{- '<|turn>system\n' -}}
|
|
{#- Inject Thinking token at the very top of the FIRST system turn -#}
|
|
{%- if enable_thinking is defined and enable_thinking -%}
|
|
{{- '<|think|>\n' -}}
|
|
{%- set ns.prev_message_type = 'think' -%}
|
|
{%- endif -%}
|
|
{%- if messages[0]['role'] in ['system', 'developer'] -%}
|
|
{%- if messages[0]['content'] is string -%}
|
|
{{- messages[0]['content'] | trim -}}
|
|
{%- elif messages[0]['content'] is sequence -%}
|
|
{%- for item in messages[0]['content'] -%}
|
|
{{- item['text'] | trim + ' '-}}
|
|
{%- endfor -%}
|
|
{%- endif -%}
|
|
{%- set loop_messages = messages[1:] -%}
|
|
{%- endif -%}
|
|
{%- if tools -%}
|
|
{%- for tool in tools %}
|
|
{{- '<|tool>' -}}
|
|
{{- format_function_declaration(tool) | trim -}}
|
|
{{- '<tool|>' -}}
|
|
{%- endfor %}
|
|
{%- set ns.prev_message_type = 'tool' -%}
|
|
{%- endif -%}
|
|
{{- '<turn|>\n' -}}
|
|
{%- endif %}
|
|
|
|
{#- Pre-scan: find last user message index for reasoning guard -#}
|
|
{%- set ns_turn = namespace(last_user_idx=-1) -%}
|
|
{%- for i in range(loop_messages | length) -%}
|
|
{%- if loop_messages[i]['role'] == 'user' -%}
|
|
{%- set ns_turn.last_user_idx = i -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
|
|
{#- Loop through messages -#}
|
|
{%- for message in loop_messages -%}
|
|
{%- if message['role'] != 'tool' -%}
|
|
{%- set ns.prev_message_type = None -%}
|
|
{%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
|
|
{#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
|
|
{%- set prev_nt = namespace(role=None, found=false) -%}
|
|
{%- if loop.index0 > 0 -%}
|
|
{%- for j in range(loop.index0 - 1, -1, -1) -%}
|
|
{%- if not prev_nt.found -%}
|
|
{%- if loop_messages[j]['role'] != 'tool' -%}
|
|
{%- set prev_nt.role = loop_messages[j]['role'] -%}
|
|
{%- set prev_nt.found = true -%}
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{%- endif -%}
|
|
{%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
|
|
{%- if not continue_same_model_turn -%}
|
|
{{- '<|turn>' + role + '\n' }}
|
|
{%- endif -%}
|
|
|
|
{#- Render reasoning/reasoning_content as thinking channel -#}
|
|
{%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
|
|
{%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
|
|
{{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
|
|
{%- endif -%}
|
|
|
|
{%- if message['tool_calls'] -%}
|
|
{%- for tool_call in message['tool_calls'] -%}
|
|
{%- set function = tool_call['function'] -%}
|
|
{{- '<|tool_call>call:' + function['name'] + '{' -}}
|
|
{%- if function['arguments'] is mapping -%}
|
|
{%- set ns_args = namespace(found_first=false) -%}
|
|
{%- for key, value in function['arguments'] | dictsort -%}
|
|
{%- if ns_args.found_first %},{% endif -%}
|
|
{%- set ns_args.found_first = true -%}
|
|
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
|
{%- endfor -%}
|
|
{%- elif function['arguments'] is string -%}
|
|
{{- function['arguments'] -}}
|
|
{%- endif -%}
|
|
{{- '}<tool_call|>' -}}
|
|
{%- endfor -%}
|
|
{%- set ns.prev_message_type = 'tool_call' -%}
|
|
{%- endif -%}
|
|
|
|
{%- set ns_tr_out = namespace(flag=false) -%}
|
|
{%- if message.get('tool_responses') -%}
|
|
{#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
|
|
{%- for tool_response in message['tool_responses'] -%}
|
|
{{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
|
|
{%- set ns_tr_out.flag = true -%}
|
|
{%- set ns.prev_message_type = 'tool_response' -%}
|
|
{%- endfor -%}
|
|
{%- elif message.get('tool_calls') -%}
|
|
{#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
|
|
{%- set ns_tool_scan = namespace(stopped=false) -%}
|
|
{%- for k in range(loop.index0 + 1, loop_messages | length) -%}
|
|
{%- if ns_tool_scan.stopped -%}
|
|
{%- elif loop_messages[k]['role'] != 'tool' -%}
|
|
{%- set ns_tool_scan.stopped = true -%}
|
|
{%- else -%}
|
|
{%- set follow = loop_messages[k] -%}
|
|
{#- Resolve tool_call_id to function name -#}
|
|
{%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
|
|
{%- for tc in message['tool_calls'] -%}
|
|
{%- if tc.get('id') == follow.get('tool_call_id') -%}
|
|
{%- set ns_tname.name = tc['function']['name'] -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{#- Handle content as string or content-parts array -#}
|
|
{%- set tool_body = follow.get('content') -%}
|
|
{%- if tool_body is string -%}
|
|
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
|
{%- elif tool_body is sequence and tool_body is not string -%}
|
|
{%- set ns_txt = namespace(s='') -%}
|
|
{%- for part in tool_body -%}
|
|
{%- if part.get('type') == 'text' -%}
|
|
{%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
|
|
{%- else -%}
|
|
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
|
{%- endif -%}
|
|
{%- set ns_tr_out.flag = true -%}
|
|
{%- set ns.prev_message_type = 'tool_response' -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{%- endif -%}
|
|
|
|
{%- set captured_content -%}
|
|
{%- if message['content'] is string -%}
|
|
{%- if role == 'model' -%}
|
|
{{- strip_thinking(message['content']) -}}
|
|
{%- else -%}
|
|
{{- message['content'] | trim -}}
|
|
{%- endif -%}
|
|
{%- elif message['content'] is sequence -%}
|
|
{%- for item in message['content'] -%}
|
|
{%- if item['type'] == 'text' -%}
|
|
{%- if role == 'model' -%}
|
|
{{- strip_thinking(item['text']) -}}
|
|
{%- else -%}
|
|
{{- item['text'] | trim -}}
|
|
{%- endif -%}
|
|
{%- elif item['type'] == 'image' -%}
|
|
{{- '<|image|>' -}}
|
|
{%- set ns.prev_message_type = 'image' -%}
|
|
{%- elif item['type'] == 'audio' -%}
|
|
{{- '<|audio|>' -}}
|
|
{%- set ns.prev_message_type = 'audio' -%}
|
|
{%- elif item['type'] == 'video' -%}
|
|
{{- '<|video|>' -}}
|
|
{%- set ns.prev_message_type = 'video' -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
{%- endif -%}
|
|
{%- endset -%}
|
|
|
|
{{- captured_content -}}
|
|
{%- set has_content = captured_content | trim | length > 0 -%}
|
|
|
|
{%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
|
|
{{- '<|tool_response>' -}}
|
|
{%- elif not (ns_tr_out.flag and not has_content) -%}
|
|
{{- '<turn|>\n' -}}
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
{%- endfor -%}
|
|
|
|
{%- if add_generation_prompt -%}
|
|
{%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
|
|
{{- '<|turn>model\n' -}}
|
|
{%- if not enable_thinking | default(false) -%}
|
|
{{- '<|channel>thought\n<channel|>' -}}
|
|
{%- else -%}
|
|
{{- '<|channel>' -}}
|
|
{%- endif -%}
|
|
{%- endif -%}
|
|
{%- endif -%} |