fix(compressor): skip non-string tool content in summarization pass to prevent AttributeError

Commit 408dd8aa added a non-string guard for Pass 1 (dedup), but the same
pattern exists in Pass 2 (summarization/pruning) where content.startswith()
and len() are called on potentially non-string tool content.

When a provider returns tool results with non-string content (e.g. dict or
int from llama.cpp or similar), the pruning pass crashes with AttributeError.

Add the same isinstance(content, str) guard to Pass 2 for consistency.

agent/context_compressor.py

@@ -600,6 +600,8 @@ class ContextCompressor(ContextEngine):
             # Skip multimodal content (list of content blocks)
             if isinstance(content, list):
                 continue
+            if not isinstance(content, str):
+                continue
             if not content or content == _PRUNED_TOOL_PLACEHOLDER:
                 continue
             # Skip already-deduplicated or previously-summarized results