fix: stop false Compressing-context card for preflight compression

PR #6184 narrowed the agent-status-to-SSE bridge to real compression
start notices, but the 'preflight compression:' pattern matches the
Hermes agent's preflight check message ("Preflight compression: ~X
tokens >= Y threshold"). This fires on every new session where the
system prompt alone exceeds the threshold, showing a "Compressing
context" card before any model output — a false positive.

Remove 'preflight compression:' from the pattern. The preflight check
is a one-time pre-model-call estimate, not a mid-conversation
compression event that the user needs to see.

api/streaming.py

@@ -587,8 +587,7 @@ def _is_agent_compression_start_status(kind: str, message: str) -> bool:
     if 'compressed' in m and 'compressing' not in m and 'compression attempt' not in m:
         return False
     return (
-        'preflight compression:' in m
-        or 'pre-api compression:' in m
+        'pre-api compression:' in m
         or 'compacting context' in m
         or 'context too large' in m
         or '— compressing (' in m

tests/test_auto_compression_card.py

@@ -473,7 +473,10 @@ def test_agent_status_callback_emits_compressing_and_warning_events():
 
 def test_agent_compression_start_status_matches_real_emitters_only():
     # Real start notices from hermes-agent emitters
-    assert _is_agent_compression_start_status(
+    # Preflight compression is excluded — it fires on every new session
+    # where the system prompt alone exceeds the threshold, producing a
+    # false "Compressing context" card before any model output.
+    assert not _is_agent_compression_start_status(
         "lifecycle",
         "📦 Preflight compression: ~101,000 tokens >= 96,000 threshold. This may take a moment.",
     )