v0.17.3: bug-fix maintenance pass — ingest origin exemption, FK safety, auto-search reset, deterministic ingest, WAL, config centralization, dead-code removal

- /api/ingest exempt from origin check for CLI/Bearer clients
- recreate deleted conversations on bogus conversation_id (chat + search)
- augmented auto-search emits reset:true; frontend clears first-pass text
- image uploads stored as placeholders, never text-ingested
- check_fact_conflicts requires shared subject keywords
- deterministic ingest point ids (md5 chunk hash)
- get_load() no longer crashes when rocm-smi yields no VRAM lines
- SQLite WAL + busy_timeout; timing-safe API key compares
- supervise fire-and-forget auto-ingest tasks; log missing logprobs
- centralize EMBED_URL/EMBED_MODEL/QDRANT_URL/NODE_NAME in config
- remove dead triage.py, select_node tests, is_state_changing, stray artifacts
- add regression tests + autouse global-reset conftest

memory.py

@@ -38,6 +38,21 @@ AUTO_FACT_PATTERNS = [
 ]
 SOCIAL_TRIGGERS = {"hi", "hello", "hey", "yo", "sup", "howdy", "good morning", "good evening"}
 
+# Short filler words that shouldn't count as subject overlap between facts.
+_STOPWORDS = {
+    "with", "that", "have", "this", "from", "they", "what", "when", "where",
+    "which", "there", "your", "will", "would", "about", "these", "their",
+    "been", "into", "than", "then", "them", "were", "being", "more", "most",
+    "some", "other", "only", "still", "also", "after", "before", "during",
+    "because", "through", "without",
+}
+
+
+def _subject_words(text: str) -> set:
+    """Meaningful subject tokens for overlap comparison."""
+    words = re.findall(r"[A-Za-z0-9_]{4,}", text.lower())
+    return {w for w in words if w not in _STOPWORDS}
+
 
 def _is_social(text: str) -> bool:
     t = text.strip().lower()
@@ -86,6 +101,10 @@ def auto_detect_facts(user_message: str, assistant_message: str) -> list[str]:
 def check_fact_conflicts(facts: list[str]) -> list[dict]:
     """Search for existing memories that conflict with detected facts.
 
+    A conflict is reported only when the existing memory is about the same
+    subject (meaningful keyword overlap) but states something different —
+    unrelated hits that merely share an FTS keyword are not conflicts.
+
     Returns list of {memory_id, old_fact, new_fact} for each conflict.
     """
     conflicts = []
@@ -93,7 +112,7 @@ def check_fact_conflicts(facts: list[str]) -> list[dict]:
         related = search_memories(new_fact, limit=1)
         if related:
             old = related[0]["fact"]
-            if old.rstrip(".") != new_fact.rstrip("."):
+            if old.rstrip(".") != new_fact.rstrip(".") and (_subject_words(new_fact) & _subject_words(old)):
                 conflicts.append({
                     "memory_id": related[0]["rowid"],
                     "old_fact": old,