From a32931c48f5e4109d43c6340e62c3a82212dae2a Mon Sep 17 00:00:00 2001
From: REKHA SUTHAR <71004640+rekha0suthar@users.noreply.github.com>
Date: Tue, 28 Jul 2026 12:56:58 +0530
Subject: [PATCH] fix: clamp maxAllowedPromptTokens to zero in autocomplete
 pruner

When the LLM contextLength is less than or equal to the sum of
maxTokens and the safety buffer (e.g. when Ollama num_ctx equals
Continue default maxTokens), the calculation

  contextLength - reservedTokens - safetyBuffer

produced a negative value. This caused pruneLength() to return a very
large positive number, making the prompt pruner strip all context and
silently produce an empty completion.

Fixed by clamping maxAllowedPromptTokens to 0 with Math.max(), so the
pruner never attempts to remove more tokens than the prompt contains.

Fixes #13038
---
 core/autocomplete/templating/index.ts | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/core/autocomplete/templating/index.ts b/core/autocomplete/templating/index.ts
index 3ebf29b71be..cb51ef55abb 100644
--- a/core/autocomplete/templating/index.ts
+++ b/core/autocomplete/templating/index.ts
@@ -204,7 +204,10 @@ function pruneLength(llm: ILLM, prompt: string): number {
   const contextLength = llm.contextLength;
   const reservedTokens = llm.completionOptions.maxTokens ?? DEFAULT_MAX_TOKENS;
   const safetyBuffer = getTokenCountingBufferSafety(contextLength);
-  const maxAllowedPromptTokens = contextLength - reservedTokens - safetyBuffer;
+  const maxAllowedPromptTokens = Math.max(
+    0,
+    contextLength - reservedTokens - safetyBuffer,
+  );
   const promptTokenCount = countTokens(prompt, llm.model);
   return promptTokenCount - maxAllowedPromptTokens;
 }