fix(compress): abort instead of dropping messages when summary LLM fails (#28102)

When auxiliary compression's summary generation returns None (aux model
errored, returned non-JSON, timed out, etc.) the compressor previously
still dropped every middle message between compress_start..compress_end
and replaced them with a static 'Summary generation was unavailable'
placeholder. The session kept going but the user silently lost N turns
of context for nothing.

New behavior: on summary failure, compress() aborts entirely — returns
the input messages unchanged and sets _last_compress_aborted=True. The
existing _summary_failure_cooldown_until gate (30-60s) keeps the aux
model from being burned on every turn. Auto-compress callers detect
the no-op (len(after) == len(before)) and stop looping. The chat is
'frozen' at its current size until the next /compress or /new.

Manual /compress (CLI + gateway) now passes force=True which clears
the cooldown so users can retry immediately after an auto-abort. If
the manual retry also fails, the user gets a visible warning telling
them nothing was dropped and how to retry.

- agent/context_compressor.py: compress() gains force= kwarg; failure
  branch sets _last_compress_aborted and returns messages unchanged
  instead of inserting placeholder.
- run_agent.py: _compress_context() detects abort, surfaces warning,
  skips session-rotation entirely, returns messages unchanged.
- cli.py + gateway/run.py: manual /compress paths pass force=True.
- gateway/run.py: hygiene + /compress handlers detect _last_compress_aborted
  and emit the new 'Compression aborted' warning (gateway.compress.aborted)
  instead of the old 'N historical messages were removed' message.
- locales/*.yaml: new gateway.compress.aborted key in all 16 locales.
- tests: updated to assert the abort contract (messages preserved,
  compression_count not incremented, abort flag set, no placeholder
  leaked). New test_force_true_bypasses_failure_cooldown covers the
  manual-retry path.

tests/gateway/test_compress_command.py

@@ -130,19 +130,15 @@ async def test_compress_command_explains_when_token_estimate_rises():
 
 
 @pytest.mark.asyncio
-async def test_compress_command_appends_warning_when_summary_generation_fails():
-    """When the auxiliary summariser fails and the compressor inserts a static
-    fallback placeholder, /compress must append a visible ⚠️ warning to its
-    reply. Otherwise the failure is silently logged and the user has no idea
-    earlier context is unrecoverable."""
+async def test_compress_command_appends_warning_when_compression_aborts():
+    """When the auxiliary summariser fails and the compressor ABORTS (returns
+    messages unchanged), /compress must append a visible ⚠️ warning to its
+    reply telling the user nothing was dropped and how to retry. Otherwise
+    the failure is silently logged and the user has no idea why nothing
+    happened."""
     history = _make_history()
-    # Compressed shape is irrelevant for this test — we only care that the
-    # warning surfaces. Drop one message so the headline is non-noop.
-    compressed = [
-        history[0],
-        {"role": "assistant", "content": "[fallback placeholder]"},
-        history[-1],
-    ]
+    # Abort path: compressor returns the input messages unchanged.
+    compressed = list(history)
     runner = _make_runner(history)
     agent_instance = MagicMock()
     agent_instance.shutdown_memory_provider = MagicMock()
@@ -150,10 +146,11 @@ async def test_compress_command_appends_warning_when_summary_generation_fails():
     agent_instance._cached_system_prompt = ""
     agent_instance.tools = None
     agent_instance.context_compressor.has_content_to_compress.return_value = True
-    # Simulate summary-generation failure: fallback flag set, dropped count
-    # populated, error string captured.
-    agent_instance.context_compressor._last_summary_fallback_used = True
-    agent_instance.context_compressor._last_summary_dropped_count = 7
+    # Simulate compression aborting (force=True bypassed cooldown but the
+    # aux LLM is genuinely broken).
+    agent_instance.context_compressor._last_compress_aborted = True
+    agent_instance.context_compressor._last_summary_fallback_used = False
+    agent_instance.context_compressor._last_summary_dropped_count = 0
     agent_instance.context_compressor._last_summary_error = (
         "404 model not found: gemini-3-flash-preview"
     )
@@ -164,7 +161,7 @@ async def test_compress_command_appends_warning_when_summary_generation_fails():
         if messages == history:
             return 100
         if messages == compressed:
-            return 60
+            return 100
         raise AssertionError(f"unexpected transcript: {messages!r}")
 
     with (
@@ -175,16 +172,14 @@ async def test_compress_command_appends_warning_when_summary_generation_fails():
     ):
         result = await runner._handle_compress_command(_make_event())
 
-    # The compress reply itself still goes through (the transcript was rewritten).
-    assert "Compressed:" in result
-    # ...but a clearly-marked warning must be appended.
+    # A clearly-marked warning must be appended.
     assert "⚠️" in result
-    assert "Summary generation failed" in result
+    assert "Compression aborted" in result
     # Underlying error must surface so users can fix their config.
     assert "404 model not found" in result
-    # Dropped count must be visible — silently losing N messages is the bug.
-    assert "7" in result
-    assert "historical message(s) were removed" in result
+    # User must be told nothing was dropped — the whole point of the
+    # new behavior is no silent data loss.
+    assert "No messages were dropped" in result
     agent_instance.shutdown_memory_provider.assert_called_once()
     agent_instance.close.assert_called_once()
 
@@ -210,6 +205,7 @@ async def test_compress_command_surfaces_aux_model_failure_even_when_recovered()
     agent_instance.tools = None
     agent_instance.context_compressor.has_content_to_compress.return_value = True
     # Fallback placeholder was NOT used — recovery succeeded.
+    agent_instance.context_compressor._last_compress_aborted = False
     agent_instance.context_compressor._last_summary_fallback_used = False
     agent_instance.context_compressor._last_summary_dropped_count = 0
     agent_instance.context_compressor._last_summary_error = None