Enable interleaved tool reasoning for custom OpenAI-compat endpoints (#5445)

* enable interleaved tool reasoning for custom OpenAI-compat endpoints

Add chat_completion_sources.CUSTOM to interleaved_reasoning_providers so
that local OpenAI-compatible endpoints (e.g. KoboldCPP in Chat Completions
mode) can forward reasoning context in tool-call chains when the user has
configured Interleaved Thinking.

Also expose the Interleaved Thinking UI control for the Custom source so
users can actually opt in — previously the dropdown was hidden behind a
data-source="openrouter" guard.

The custom streaming path already correctly accumulates delta.reasoning_content
from streaming chunks; this change only removes the provider gate that was
silently discarding that data before it reached the API payload.

* don't override invocation reasoning with prior-turn assistant reasoning

When an invocation already has its own reasoning captured at execution
time, preserve it instead of replacing it with previousAssistantReasoning
from the backward scan. The override was correct when invocations never
carried their own reasoning, but now that the custom/openrouter paths
capture per-invocation reasoning, the unconditional replacement caused
all tool calls in a chain to receive the same stale reasoning from an
earlier unrelated assistant turn.

Fall back to previousAssistantReasoning only when clone.reasoning is empty.

public/index.html

@@ -2011,7 +2011,7 @@
                                             <strong data-i18n="enable_functions_desc_4">Not supported when Prompt Post-Processing with "no tools" is used!</strong>
                                         </div>
                                     </div>
-                                    <div class="range-block" data-source="openrouter">
+                                    <div class="range-block" data-source="openrouter,custom">
                                         <div class="flex-container flexFlowColumn wide100p textAlignCenter marginTop10">
                                             <div class="flex-container oneline-dropdown">
                                                 <label for="tool_reasoning_mode" data-i18n="Interleaved Thinking">

public/scripts/openai.js

@@ -257,6 +257,7 @@ export const tool_reasoning_modes = {
 // Providers that support interleaved reasoning forwarding in tool-call chains.
 const interleaved_reasoning_providers = [
     chat_completion_sources.OPENROUTER,
+    chat_completion_sources.CUSTOM,
 ];
 
 export const ZAI_ENDPOINT = {
@@ -1019,8 +1020,8 @@ async function populateChatHistory(messages, prompts, chatCompletion, type = nul
                 const clone = structuredClone(invocation);
                 if (!reasoningIsEligible) {
                     delete clone.reasoning;
-                } else if (previousAssistantReasoning) {
+                } else if (previousAssistantReasoning && !clone.reasoning) {
-                    // Prefer currently editable assistant-text reasoning based on forwarding mode over invocation snapshot.
+                    // Fall back to adjacent assistant-text reasoning only when the invocation has none of its own.
                     clone.reasoning = previousAssistantReasoning;
                 }
                 return clone;