fix(llm): add stop_sequences parity for tool completions (#1170)

* fix(llm): add stop_sequences parity for tool completions

* refactor(web-openai): dedupe request builders and satisfy no-panics gate

* test(llm): mark multiline assert with safety comment for CI gate

* test(llm): make safety-marked assert formatting-stable

src/llm/bedrock.rs

@@ -176,8 +176,11 @@ impl LlmProvider for BedrockProvider {
             builder = builder.tool_config(tc);
         }
 
-        if let Some(config) = build_inference_config(request.temperature, request.max_tokens, None)
-        {
+        if let Some(config) = build_inference_config(
+            request.temperature,
+            request.max_tokens,
+            request.stop_sequences.as_deref(),
+        ) {
             builder = builder.inference_config(config);
         }