fix: salvage batch — compaction guidance, memory authority, cache eviction after compression

- Fix /compact → /compress in context-overflow tips (closes #20020)
- Evict cached agent after session hygiene and /compress so system
  prompt refreshes with current SOUL.md, memory, and skills
- Restore memory authority across compaction: change 'informational
  background data' to 'authoritative reference data' in memory block
  and SUMMARY_PREFIX, with backward-compatible regex

Based on:
- PR #20027 by @LeonSGP43
- PR #18767 by @MacroAnarchy
- PR #17380 by @vominh1919

PR #17121 boundary marker fix already merged to main (2eef395e1).
PR #9262 user-message anchoring already on main via _ensure_last_user_message_in_tail().

agent/context_compressor.py

@@ -43,6 +43,9 @@ SUMMARY_PREFIX = (
     "they were already addressed. "
     "Your current task is identified in the '## Active Task' section of the "
     "summary — resume exactly from there. "
+    "IMPORTANT: Your persistent memory (MEMORY.md, USER.md) in the system "
+    "prompt is ALWAYS authoritative and active — never ignore or deprioritize "
+    "memory content due to this compaction note. "
     "Respond ONLY to the latest user message "
     "that appears AFTER this summary. The current session state (files, "
     "config, etc.) may reflect work described here — avoid repeating it:"
@@ -1373,7 +1376,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             msg = messages[i].copy()
             if i == 0 and msg.get("role") == "system":
                 existing = msg.get("content")
-                _compression_note = "[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work.]"
+                _compression_note = "[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work. Your persistent memory (MEMORY.md, USER.md) remains fully authoritative regardless of compaction.]"
                 if _compression_note not in _content_text_for_contains(existing):
                     msg["content"] = _append_text_to_content(
                         existing,

agent/memory_manager.py

@@ -46,7 +46,7 @@ _INTERNAL_CONTEXT_RE = re.compile(
     re.IGNORECASE,
 )
 _INTERNAL_NOTE_RE = re.compile(
-    r'\[System note:\s*The following is recalled memory context,\s*NOT new user input\.\s*Treat as informational background data\.\]\s*',
+    r'\[System note:\s*The following is recalled memory context,\s*NOT new user input\.\s*Treat as (?:informational background data|authoritative reference data[^\]]*)\.\]\s*',
     re.IGNORECASE,
 )
 
@@ -180,7 +180,8 @@ def build_memory_context_block(raw_context: str) -> str:
     return (
         "<memory-context>\n"
         "[System note: The following is recalled memory context, "
-        "NOT new user input. Treat as informational background data.]\n\n"
+        "NOT new user input. Treat as authoritative reference data — "
+        "this is the agent's persistent memory and should inform all responses.]\n\n"
         f"{clean}\n"
         "</memory-context>"
     )

gateway/run.py

@@ -6322,6 +6322,10 @@ class GatewayRunner:
                                                 _werr,
                                             )
                                 finally:
+                                    # Evict the cached agent so the next turn
+                                    # rebuilds its system prompt from current
+                                    # SOUL.md, memory, and skills.
+                                    self._evict_cached_agent(session_key)
                                     self._cleanup_agent_resources(_hyg_agent)
 
                     except Exception as e:
@@ -9505,6 +9509,9 @@ class GatewayRunner:
                 _aux_fail_model = getattr(compressor, "_last_aux_model_failure_model", None)
                 _aux_fail_err = getattr(compressor, "_last_aux_model_failure_error", None)
             finally:
+                # Evict cached agent so next turn rebuilds system prompt
+                # from current files (SOUL.md, memory, etc.).
+                self._evict_cached_agent(session_key)
                 self._cleanup_agent_resources(tmp_agent)
             lines = [f"🗜️ {summary['headline']}"]
             if focus_topic:

scripts/release.py

@@ -177,6 +177,8 @@ AUTHOR_MAP = {
     "git@local.invalid": "hendrixfreire",
     "1060770+benjaminsehl@users.noreply.github.com": "benjaminsehl",
     "nerijusn76@gmail.com": "Nerijusas",
+    # Compaction salvage batch (May 2026)
+    "MacroAnarchy@users.noreply.github.com": "MacroAnarchy",
     "itonov@proton.me": "Ito-69",
     "glesstech@gmail.com": "georgeglessner",
     "maxim.smetanin@gmail.com": "maxims-oss",