feat: per-user auto-memory with ResponseContext

Three memory channels: hidden tool (sol.memory.set/get in scripts),
pre-response injection (relevant memories loaded into system prompt),
and post-response extraction (ministral-3b extracts facts after each
response). User isolation enforced at Rust level — user_id derived
from Matrix sender, never from script arguments.

New modules: context (ResponseContext), memory (schema, store, extractor).
ResponseContext threaded through responder → tools → script runtime.
OpenSearch index sol_user_memory created on startup alongside archive.

config/sol.toml

@@ -6,6 +6,7 @@ state_store_path = "/data/matrix-state"
 [opensearch]
 url = "http://opensearch.data.svc.cluster.local:9200"
 index = "sol_archive"
+memory_index = "sol_user_memory"
 batch_size = 50
 flush_interval_ms = 2000
 embedding_pipeline = "tuwunel_embedding_pipeline"
@@ -17,12 +18,24 @@ research_model = "mistral-large-latest"
 max_tool_iterations = 5
 
 [behavior]
-response_delay_min_ms = 2000
-response_delay_max_ms = 8000
+response_delay_min_ms = 100
+response_delay_max_ms = 2300
 spontaneous_delay_min_ms = 15000
 spontaneous_delay_max_ms = 60000
-spontaneous_threshold = 0.7
+spontaneous_threshold = 0.85
 room_context_window = 30
 dm_context_window = 100
 backfill_on_join = true
 backfill_limit = 10000
+instant_responses = false
+cooldown_after_response_ms = 15000
+evaluation_context_window = 200
+reaction_threshold = 0.6
+reaction_enabled = true
+detect_sol_in_conversation = true
+script_timeout_secs = 5
+script_max_heap_mb = 64
+script_fetch_allowlist = []
+memory_extraction_enabled = true
+# evaluation_prompt_active = "custom prompt when Sol is already in conversation..."
+# evaluation_prompt_passive = "custom prompt when Sol hasn't spoken yet..."