fix(compress): make abort-on-summary-failure opt-in via config flag (#28117)

PR #28102 made the summary-failure abort path the unconditional default,
changing established behavior. Gate it behind config.yaml flag
`compression.abort_on_summary_failure` (default False = historical
fallback-placeholder behavior).

- hermes_cli/config.py: new `compression.abort_on_summary_failure` key,
  default False, documented inline.
- agent/agent_init.py: read the flag from compression config and pass to
  ContextCompressor.
- agent/context_compressor.py: `__init__` accepts `abort_on_summary_failure`
  (default False). `compress()` failure branch gates the abort on the
  flag; when False, falls through to the restored legacy fallback path
  (static "summary unavailable" placeholder + drop middle window).
- tests: restore original fallback expectations as default; add new
  TestAbortOnSummaryFailure class for the opt-in mode.

Gateway/CLI plumbing (force=True on /compress, hygiene/handler abort
detection, locale `gateway.compress.aborted` key) from PR #28102 stays
intact — those paths only fire when `_last_compress_aborted` is True,
which now only happens when the flag is enabled.

hermes_cli/config.py

@@ -803,6 +803,17 @@ DEFAULT_CONFIG = {
                                       # 0 for long-running rolling-compaction sessions
                                       # where you want nothing pinned except the
                                       # system prompt + rolling summary + recent tail.
+        "abort_on_summary_failure": False,  # When True, auto-compression that fails
+                                      # to generate a summary (aux LLM errored / returned
+                                      # non-JSON / timed out) aborts entirely instead of
+                                      # dropping the middle window with a static
+                                      # "summary unavailable" placeholder.  Messages are
+                                      # preserved unchanged and the session "freezes" at
+                                      # its current size until the user runs /compress
+                                      # (which bypasses the failure cooldown) or /new.
+                                      # Default False matches historical behavior; set to
+                                      # True if you'd rather pause than silently lose
+                                      # context turns when your aux model is flaky.
     },
 
     # Anthropic prompt caching (Claude via OpenRouter or native Anthropic API).