Add Step 3.7 chat template download

README.md

@@ -55,7 +55,7 @@ This FPX3/Q3 QualityPlus recipe was built for that constraint:
 - `14.35%` smaller than StepFun's original `Q3_K_L` GGUF split
 - up to 256K one-slot serving profile with q8_0 target KV and q8_0 draft KV
 - Step MTP Q8 draft support through `draft-mtp`
-- fixed Step tool/chat template using native `tool_response` observations and protocol-boundary escaping
+- downloadable fixed Step tool/chat template using native `tool_response` observations and protocol-boundary escaping
 
 In practice, the original StepFun `Q3_K_L` local split was not a compact 3-bit-feeling model: it measured about `95.46 GiB`, or roughly `4.17 BPW` by effective size. This QualityPlus build is the one I would publish/use as the FPX3 lane.
 
@@ -149,6 +149,18 @@ Step-3.7-Flash-ROCmFPX-Q3-QualityPlus-00009-of-00009.gguf
 
 The Step MTP draft model is not duplicated here. Use the Q8 draft from [`notSnix/Step-3.7-Flash-MTP-Draft-GGUF`](https://huggingface.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF), for example `Step-3.7-Flash-MTP-Q8_0.gguf`.
 
+This repo also includes the tested chat/tool template:
+
+```text
+step37-native-tool-response-template.jinja
+```
+
+Download it from the Files tab or directly from:
+
+```text
+https://huggingface.co/jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus/resolve/main/step37-native-tool-response-template.jinja
+```
+
 ## Recommended Serving Profile
 
 The locally tested long-context profile:
@@ -204,13 +216,20 @@ Example shape:
   --spec-draft-n-min 0 \
   --spec-draft-p-min 0.75 \
   --spec-draft-p-split 0.10 \
-  --chat-template-file step37-native-tool-response-template.jinja \
+  --chat-template-file /path/to/step37-native-tool-response-template.jinja \
   --metrics
 ```
 
 ## Template Note
 
-The best local Step setup uses a Step-native tool/chat template that renders tool outputs as `tool_response` turns and escapes protocol-boundary tokens inside tool output. This is a general protocol-adapter fix: tool/file/search results stay observations instead of being flattened into user text.
+The best local Step setup uses the included [`step37-native-tool-response-template.jinja`](step37-native-tool-response-template.jinja) template. It renders tool outputs as `tool_response` turns and escapes protocol-boundary tokens inside tool output. This is a general protocol-adapter fix: tool/file/search results stay observations instead of being flattened into user text.
+
+Download:
+
+```bash
+curl -L -o step37-native-tool-response-template.jinja \
+  https://huggingface.co/jcbtc/Step-3.7-Flash-ROCmFPX-Q3-QualityPlus/resolve/main/step37-native-tool-response-template.jinja
+```
 
 That matters for real agents because Step 3.7 can otherwise confuse tool output with conversation authority, especially in file/search-result injection cases.
 

step37-native-tool-response-template.jinja

@@ -0,0 +1,97 @@
+{% macro render_message_content(message) %}{% if message.content is none %}{{- '' }}{% elif message.content is string %}{{- message.content }}{% elif message.content is mapping %}{{- message.content['value'] if 'value' in message.content else message.content['text'] }}{% elif message.content is iterable %}{% set ns = namespace(needs_text_separator=false) %}{% for item in message.content %}{% if item.type == 'text' %}{% if ns.needs_text_separator %}{{- ' ' }}{% endif %}{{- item['value'] if 'value' in item else item['text'] }}{% set ns.needs_text_separator = true %}{% elif item.type == 'image' %}<im_patch>{% set ns.needs_text_separator = false %}{% endif %}{% endfor %}{% endif %}{% endmacro %}
+{% macro render_tool_response_content(content) %}{{- content | replace('<|im_start|>', '&lt;|im_start|&gt;') | replace('<|im_end|>', '&lt;|im_end|&gt;') | replace('<tool_call>', '&lt;tool_call&gt;') | replace('</tool_call>', '&lt;/tool_call&gt;') | replace('<tool_response>', '&lt;tool_response&gt;') | replace('</tool_response>', '&lt;/tool_response&gt;') | replace('<function=', '&lt;function=') | replace('</function>', '&lt;/function&gt;') | replace('<parameter=', '&lt;parameter=') | replace('</parameter>', '&lt;/parameter&gt;') }}{% endmacro %}
+{{bos_token}}{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_effort is defined %}
+        {{- "Reasoning: " + reasoning_effort + '\n\n' }}
+    {%- endif %}
+    {%- if messages[0].role == 'system' %}
+        {{- render_message_content(messages[0]) + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions in JSONSchema format:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson(ensure_ascii=False) }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...>\n...\n</function> block must be nested within <tool_call>\n...\n</tool_call> XML tags\n- Required parameters MUST be specified\n</IMPORTANT><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if reasoning_effort is defined %}
+            {{- "Reasoning: " + reasoning_effort + '\n\n' }}
+        {%- endif %}
+        {{- render_message_content(messages[0]) + '<|im_end|>\n' }}
+    {%- elif reasoning_effort is defined %}
+        {{- '<|im_start|>system\n' + "Reasoning: " + reasoning_effort + '\n\n' + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and render_message_content(message) is string and not(render_message_content(message).startswith('<tool_response>') and render_message_content(message).endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_message_content(message) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {%- set role_name = 'observation' if (message.role == "system" and not loop.first and message.name == 'observation') else message.role %}
+        {{- '<|im_start|>' + role_name + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- else %}
+                {%- set reasoning_content = '' %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- set content = content|trim %}
+        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- if tool_call.arguments is defined %}
+                    {%- set arguments = tool_call.arguments | fromjson if tool_call.arguments is string else tool_call.arguments %}
+                    {%- for args_name, args_value in arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson(ensure_ascii=False) | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" or message.role == "tool_response" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool" and messages[loop.index0 - 1].role != "tool_response") %}
+            {{- '<|im_start|>tool_response\n' }}
+        {%- endif %}
+        {{- '<tool_response>' }}
+        {{- render_tool_response_content(content) }}
+        {{- '</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool" and messages[loop.index0 + 1].role != "tool_response") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}