fix(compression): reset _last_summary_error at start of compress()

The per-call reset block at the top of compress() cleared
_last_summary_dropped_count and _last_summary_fallback_used but
not _last_summary_error. Functionally this didn't break the
gateway warning path (callers gate on _last_summary_fallback_used
first, and _last_summary_error is overwritten on the next failure),
but it left the three tracking fields inconsistent — anyone
reading _last_summary_error standalone after a successful compress
would see a stale value from a previous failed compress.

Reset all three together so the per-call contract is uniform.

agent/context_compressor.py

@@ -1207,6 +1207,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         # after compress() returns to decide whether to surface a warning.
         self._last_summary_dropped_count = 0
         self._last_summary_fallback_used = False
+        self._last_summary_error = None
         n_messages = len(messages)
         # Only need head + 3 tail messages minimum (token budget decides the real tail size)
         _min_for_compress = self.protect_first_n + 3 + 1