Bug report + proposed fix for chat_template.jinja

## Summary

Gemma 4 chat template has two related defects around the
`<|channel>thought` block:

1. **No single convention for who opens the thought channel at generation time.**
On plain thinking turns the prompt ends bare after `<|turn>model\n` (the model must
emit its own opener); after tool responses the prompt pre-opens the channel; with
thinking disabled after tool responses, nothing is emitted at all. No reasoning
parser can satisfy three contracts at once. In production serving (vLLM ≥ 0.26,
`--reasoning-parser gemma4`) any token the model emits before its opener on a plain
turn is classified as **answer content** — users see junk fragments fused onto
replies (observed live: `"althi khalid"` = a leaked `alt` + `hi khalid`).
2. **The post-tool pre-open is emitted outside the model turn on the most common tool
shape.** When the tool-calling assistant message also carried prose content
("Let me check." + tool call → tool result — the standard OpenAI round shape), the
template's closure chain emits `<turn|>` (because `has_content` is true), but the
generation block still assumes the turn is open and appends `<|channel>thought\n`
**after the closed turn, at top level, with no `<|turn>model\n`** — a byte sequence
that never occurs in a valid transcript. With thinking disabled on the same shape,
no generation prompt is emitted at all.

## Root cause

The `add_generation_prompt` block infers "the model turn is still open" from
`ns.prev_message_type == 'tool_response'` — a proxy that disagrees with what the
closure chain actually did whenever the tool-calling message carried prose. And the
thinking on/off prefill is applied in only two of the four reachable states.

## Proposed fix (three edits)

One principle: **record turn-openness where it is decided instead of inferring it
later, and always pre-fill the thought channel — open when thinking is enabled,
closed-empty when it is not.**

**Edit 1 — namespace init** gains a flag:

```jinja
{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None, model_turn_open=false) -%}
```

**Edit 2 — the per-message closure chain records what it did** (the `{%- set -%}`
lines are render-invisible):

```jinja
{%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
{{- '<|tool_response>' -}}
{%- set ns.model_turn_open = true -%}
{%- elif continues_into_next -%}
{%- set ns.model_turn_open = true -%}
{%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
{{- '<turn|>\n' -}}
{%- set ns.model_turn_open = false -%}
{%- else -%}
{%- set ns.model_turn_open = true -%}
{%- endif -%}
```

**Edit 3 — the generation block reads the record and applies one uniform prefill:**

```jinja
{%- if add_generation_prompt -%}
{%- if ns.prev_message_type != 'tool_call' -%}
{%- if not ns.model_turn_open -%}
{{- '<|turn>model\n' -}}
{%- endif -%}
{%- if enable_thinking -%}
{{- '<|channel>thought\n' -}}
{%- else -%}
{{- '<|channel>thought\n<channel|>' -}}
{%- endif -%}
{%- endif -%}
{%- endif -%}
```

Resulting contract, every state: the prompt ends inside an open model turn, with the
thought channel **pre-opened** when thinking is enabled (the parser starts the
generation in reasoning state — pre-thought leakage becomes structurally impossible)
or **pre-closed** when it is not (thinking is actually disabled, including after tool
responses). On the prose-carrying tool round, the turn is correctly re-opened with
`<|turn>model\n` before the prefill — fixing defect 2 for thinking on *and* off.



## Impact

Fixes both defect classes at the source for every client of every serving stack that
splits Gemma 4 reasoning by channel markers. Clients cannot repair this downstream —
once reasoning is mistyped as content, no marker survives to detect it.

chat_template.jinja

@@ -181,7 +181,7 @@
 {%- endmacro -%}
 
 {#- ===== SETUP ===== -#}
-{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None, model_turn_open=false) -%}
 {%- set loop_messages = messages -%}
 {%- set enable_thinking = enable_thinking | default(false) -%}
 {%- set preserve_thinking = preserve_thinking | default(false) -%}
@@ -368,9 +368,14 @@
 
         {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
             {{- '<|tool_response>' -}}
+            {%- set ns.model_turn_open = true -%}
         {%- elif continues_into_next -%}
+            {%- set ns.model_turn_open = true -%}
         {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
             {{- '<turn|>\n' -}}
+            {%- set ns.model_turn_open = false -%}
+        {%- else -%}
+            {%- set ns.model_turn_open = true -%}
         {%- endif -%}
 
     {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
@@ -379,12 +384,14 @@
 {%- 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 -%}
+    {%- if ns.prev_message_type != 'tool_call' -%}
+        {%- if not ns.model_turn_open -%}
+            {{- '<|turn>model\n' -}}
+        {%- endif -%}
+        {%- if enable_thinking -%}
+            {{- '<|channel>thought\n' -}}
+        {%- else -%}
             {{- '<|channel>thought\n<channel|>' -}}
         {%- endif -%}
-    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
-        {{- '<|channel>thought\n' -}}
     {%- endif -%}
-{%- endif -%}
+{%- endif -%}