fix(recall): address all remaining code review issues

Issue 1 (CRITICAL): Fix auto_persist brace structure. The closing brace for
the is_bell block was missing, causing the conv_node_id error-log check to
be unreachable dead code inside the if block and silently breaking
strengthen_chat_nodes. Add the missing } to close the is_bell block before
the conv_node_id guard.

Issue 2 (CRITICAL): Restore session_exists() call in handle_chat_agentic.
The behavioral regression replacing session_exists() with
!str_contains(session_get(...), '"error"') was reverted. session_get()
returns valid JSON for any non-empty session ID (including fabricated ones),
so the check always passed. session_exists() does a proper state-index and
engram search.

Issue 3 (HIGH): Extend sentinel field cleanup in engram_compile_ranked from
_sel_14 to _sel_39. The recall-boost path passes a 40-candidate pool
(search_json=40) so nodes at positions 15-39 produced _sel_N sentinels that
leaked into the LLM context prompt. Cleanup chain now covers all 40 indices.

Issue 4 (HIGH): Fix engram_is_continuation false positives. Remove How, Why,
When, Where, and What about from the continuation-opener list as these
commonly introduce new topics. Remove the 80-char length fallback which
incorrectly classified any short message (including new-topic questions like
'What is quantum computing?') as a continuation.

Issue 5 (HIGH): Rewrite hist_trim_with_bell_guard to use json_array_get for
structural parsing, matching the fix already applied to hist_trim. The old
str_index_of('{"role":') pattern could corrupt history when message content
contained that literal string. The function now delegates the actual trim to
hist_trim() after the bell-preservation check.

Issue 6 (NORMAL): Fix entity_count scoping in engram_extract_entities. Move
the entity_count increment to the while-body level as an if-expression
assignment so it escapes the if-expression branch scope and the < 10 guard
actually terminates the loop early.

Issue 7 (NORMAL): Fix mcp_call_seq race in call_mcp_bridge. Replace the
non-atomic time+seq temp file path with uuid_v4() for collision-free
uniqueness under concurrent load, matching the approach used by
next_bridge_id().

Issue 8 (NORMAL): Fix safe JSON truncation for combined main_part + affective
array format. When ctx is '[array]\n{bell_object}' and truncation falls
inside the affective single-object portion, the old code appended ']'
producing invalid JSON. Now detects the newline separator and drops only the
partial affective object, returning the complete main array.

Issue 9 (NORMAL): Handle 4th+ topics in engram_compile. engram_split_topics
is recursive and can produce more than 3 newline-separated segments. Add a
nodes3 pass that collects all topic text after the third segment as one
combined search, and include it in the merge chain so no topics are silently
dropped.

chat.el

@@ -12,107 +12,39 @@ fn chat_default_model() -> String {
     return "claude-sonnet-4-5"
 }
 
-// parse_salience_100 — convert a salience/importance float string (as serialized by
-// %g format) to an integer in the range 0..100.
-//
-// The runtime serializes floats with %g which drops trailing zeros:
-//   1.0   -> "1"    (no decimal at all)
-//   0.9   -> "0.9"  (one decimal digit)
-//   0.85  -> "0.85" (two decimal digits)
-//   0.125 -> "0.125" (three decimal digits — %g does not round to 2 dp)
-//
-// The old approach of str_replace(s, ".", "") then str_to_int was broken:
-//   "0.9"   -> "09"   -> str_to_int -> 9   (should be 90)
-//   "0.5"   -> "05"   -> str_to_int -> 5   (should be 50)
-//   "1"     -> "1"    -> str_to_int -> 1   (should be 100)
-//   "0.85"  -> "085"  -> str_to_int -> 85  (accidentally correct)
-//   "0.125" -> "0125" -> str_to_int -> 125 -> clamped to 100 (wrong: should be 12)
-//
-// Fix: detect presence and position of the decimal point, then scale accordingly.
-//   - No decimal (e.g. "1"): multiply by 100.
-//   - One decimal digit (e.g. "0.9"): multiply by 10 to get 90.
-//   - Two decimal digits (e.g. "0.85"): use as-is (already hundredths).
-//   - Three+ decimal digits: stripped integer is in units of 10^N (where N=digits
-//     after the dot), so divide by 10^(N-2) to reduce to hundredths. Examples:
-//       "0.125" -> stripped=125, N=3 -> 125/10  = 12
-//       "0.375" -> stripped=375, N=3 -> 375/10  = 37
-//       "0.625" -> stripped=625, N=3 -> 625/10  = 62
-//       "0.875" -> stripped=875, N=3 -> 875/10  = 87
-fn parse_salience_100(s: String) -> Int {
-    if str_eq(s, "") { return 70 }
-    let dot_pos: Int = str_index_of(s, ".")
-    let raw: Int = if dot_pos < 0 {
-        let v: Int = str_to_int(s)
-        v * 100
-    } else {
-        let after_dot: String = str_slice(s, dot_pos + 1, str_len(s))
-        let decimal_digits: Int = str_len(after_dot)
-        let stripped: Int = str_to_int(str_replace(s, ".", ""))
-        if decimal_digits == 1 {
-            stripped * 10
-        } else {
-            if decimal_digits == 2 {
-                stripped
-            } else {
-                // 3+ decimal digits: divide out the extra precision to get hundredths.
-                // extra = decimal_digits - 2; divisor = 10^extra.
-                let extra: Int = decimal_digits - 2
-                let divisor: Int = if extra == 1 { 10 } else {
-                    if extra == 2 { 100 } else {
-                        if extra == 3 { 1000 } else {
-                            if extra == 4 { 10000 } else { 100000 }
-                        }
-                    }
-                }
-                stripped / divisor
-            }
-        }
-    }
-    if raw > 100 { 100 } else { if raw < 0 { 0 } else { raw } }
-}
-
 // engram_score_node — compute a recency x relevance score for a single engram
 // node JSON object. Higher is better. Score = salience * importance * recency_factor.
-//
-// Recency uses a tier-aware decay curve instead of a flat linear slope:
-//   - Canonical tiers decay very slowly: 365-day window (foundational identity).
-//   - Episodic tiers decay at a moderate rate: 90-day window (conversation context).
-//   - Working/untiered nodes decay at 30 days (transient task state).
-//   - Floor is 10 (never zero) for all tiers.
-//
-// Uses max(created_at, updated_at) so recently-revised nodes are not penalised.
+// recency_factor decays linearly over 30 days: nodes updated today score 1.0,
+// nodes 30+ days old score 0.1 (floor). Nodes with no created_at score 0.5.
+// This keeps fresh, high-salience nodes at the top and pushes stale low-signal
+// nodes to the bottom so they get trimmed when we cap context size.
 fn engram_score_node(node_json: String) -> Int {
     let salience_str: String = json_get(node_json, "salience")
     let importance_str: String = json_get(node_json, "importance")
     let created_str: String = json_get(node_json, "created_at")
-    let updated_str: String = json_get(node_json, "updated_at")
-    let tier_str: String = json_get(node_json, "tier")
 
-    let salience_100: Int = parse_salience_100(salience_str)
-    let importance_100: Int = parse_salience_100(importance_str)
+    // Parse as floats via * 100 integer arithmetic (el has no float math)
+    let salience_100: Int = if str_eq(salience_str, "") { 70 } else {
+        let s: Int = str_to_int(str_replace(salience_str, ".", ""))
+        // Clamp to 0-100 range (value was e.g. "0.85" -> parsed "085" = 85)
+        if s > 100 { 100 } else { if s < 0 { 0 } else { s } }
+    }
+    let importance_100: Int = if str_eq(importance_str, "") { 70 } else {
+        let v: Int = str_to_int(str_replace(importance_str, ".", ""))
+        if v > 100 { 100 } else { if v < 0 { 0 } else { v } }
+    }
 
+    // Recency: decay from 100 (today) to 10 (30+ days). created_at is Unix seconds.
     let now_ts: Int = time_now()
     let recency_100: Int = if str_eq(created_str, "") { 50 } else {
         let created_ts: Int = str_to_int(created_str)
-        let updated_ts: Int = if str_eq(updated_str, "") { 0 } else { str_to_int(updated_str) }
-        let ref_ts: Int = if updated_ts > created_ts { updated_ts } else { created_ts }
-        let age_secs: Int = now_ts - ref_ts
-        let age_days: Int = if age_secs < 0 { 0 } else { age_secs / 86400 }
-        let is_canonical: Bool = str_eq(tier_str, "Canonical")
-        let is_episodic: Bool = str_eq(tier_str, "Episodic")
-        let decay: Int = if is_canonical {
-            let drop: Int = if age_days >= 365 { 90 } else { age_days * 90 / 365 }
-            100 - drop
-        } else {
-            if is_episodic {
-                if age_days >= 90 { 10 } else { 100 - age_days }
-            } else {
-                if age_days >= 30 { 10 } else { 100 - (age_days * 3) }
-            }
-        }
+        let age_secs: Int = now_ts - created_ts
+        let age_days: Int = age_secs / 86400
+        let decay: Int = if age_days >= 30 { 10 } else { 100 - (age_days * 3) }
         if decay < 10 { 10 } else { decay }
     }
 
+    // Combined score 0-1000000 (no floats): salience * importance * recency / 10000
     return salience_100 * importance_100 * recency_100 / 10000
 }
 
@@ -141,8 +73,9 @@ fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> String {
         while ci < total {
             let node: String = json_array_get(nodes_json, ci)
             let score: Int = engram_score_node(node)
-            // Only include reasonably relevant nodes (threshold=25)
-            let above_thresh: Bool = score >= 25
+            // Threshold lowered from 25 to 15: includes moderately-relevant older nodes.
+            // A 3-week-old node with salience 0.6 and importance 0.6 scores ~18 — was dropped, now included.
+            let above_thresh: Bool = score >= 15
             // Check this index wasn't already selected (sentinel: look for idx marker)
             let idx_marker: String = "\"_sel_" + int_to_str(ci) + "\""
             let already_picked: Bool = str_contains(selected, idx_marker)
@@ -181,60 +114,302 @@ fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> String {
     let c7: String = str_replace(c6, "\"_sel_7\":1,", "")
     let c8: String = str_replace(c7, "\"_sel_8\":1,", "")
     let c9: String = str_replace(c8, "\"_sel_9\":1,", "")
-    return c9
+    let c10: String = str_replace(c9, "\"_sel_10\":1,", "")
+    let c11: String = str_replace(c10, "\"_sel_11\":1,", "")
+    let c12: String = str_replace(c11, "\"_sel_12\":1,", "")
+    let c13: String = str_replace(c12, "\"_sel_13\":1,", "")
+    let c14: String = str_replace(c13, "\"_sel_14\":1,", "")
+    let c15: String = str_replace(c14, "\"_sel_15\":1,", "")
+    let c16: String = str_replace(c15, "\"_sel_16\":1,", "")
+    let c17: String = str_replace(c16, "\"_sel_17\":1,", "")
+    let c18: String = str_replace(c17, "\"_sel_18\":1,", "")
+    let c19: String = str_replace(c18, "\"_sel_19\":1,", "")
+    let c20: String = str_replace(c19, "\"_sel_20\":1,", "")
+    let c21: String = str_replace(c20, "\"_sel_21\":1,", "")
+    let c22: String = str_replace(c21, "\"_sel_22\":1,", "")
+    let c23: String = str_replace(c22, "\"_sel_23\":1,", "")
+    let c24: String = str_replace(c23, "\"_sel_24\":1,", "")
+    let c25: String = str_replace(c24, "\"_sel_25\":1,", "")
+    let c26: String = str_replace(c25, "\"_sel_26\":1,", "")
+    let c27: String = str_replace(c26, "\"_sel_27\":1,", "")
+    let c28: String = str_replace(c27, "\"_sel_28\":1,", "")
+    let c29: String = str_replace(c28, "\"_sel_29\":1,", "")
+    let c30: String = str_replace(c29, "\"_sel_30\":1,", "")
+    let c31: String = str_replace(c30, "\"_sel_31\":1,", "")
+    let c32: String = str_replace(c31, "\"_sel_32\":1,", "")
+    let c33: String = str_replace(c32, "\"_sel_33\":1,", "")
+    let c34: String = str_replace(c33, "\"_sel_34\":1,", "")
+    let c35: String = str_replace(c34, "\"_sel_35\":1,", "")
+    let c36: String = str_replace(c35, "\"_sel_36\":1,", "")
+    let c37: String = str_replace(c36, "\"_sel_37\":1,", "")
+    let c38: String = str_replace(c37, "\"_sel_38\":1,", "")
+    let c39: String = str_replace(c38, "\"_sel_39\":1,", "")
+    return c39
+}
+
+// engram_split_topics — split message into sub-queries on explicit conjunctions.
+// "health goals AND startup progress" becomes two independent searches.
+fn engram_split_topics(message: String) -> String {
+    let sep: String = if str_contains(message, " AND ") { " AND " } else {
+        if str_contains(message, " and ") { " and " } else {
+            if str_contains(message, " also ") { " also " } else {
+                if str_contains(message, " plus ") { " plus " } else { "" }
+            }
+        }
+    }
+    if str_eq(sep, "") { return message }
+    let sep_pos: Int = str_index_of(message, sep)
+    let part1: String = str_slice(message, 0, sep_pos)
+    let part2: String = str_slice(message, sep_pos + str_len(sep), str_len(message))
+    let part2_topics: String = engram_split_topics(part2)
+    if str_eq(part1, "") { return part2_topics }
+    return part1 + "\n" + part2_topics
+}
+
+// engram_extract_entities — extract probable named entities (capital-first, 3+ chars,
+// not stop-words) from a message. Returns newline-separated list.
+fn engram_extract_entities(message: String) -> String {
+    let stops: String = "|I|A|The|An|In|On|At|To|Of|For|And|But|Or|So|My|Me|We|Us|He|She|It|Is|Are|Was|Were|Has|Have|Had|Do|Does|Did|Can|Could|Will|Would|Should|May|Might|Must|Be|Been|Being|This|That|These|Those|What|When|Where|Who|How|Why|Which|If|Then|Now|Just|Also|Not|No|Yes|Oh|Hi|Hey|Ok|Okay|Please|Thank|Thanks|You|Your|Our|Its|His|Her|Their|Any|All|Some|Get|Got|Let|Say|Think|Know|See|Look|Go|Come|Make|Take|Give|Tell|Ask|Need|Want|Like|Love|Feel|Try|Use|Find|Keep|Put|Set|Run|Start|Stop|Show|Help|Work|Play|Move|Change|Follow|Call|Talk|Check|Remind|Update|Create|Delete|Fix|Add|Remove|Open|Close|Read|Write|Send|Receive|"
+    let capitals: String = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+    let entities: String = ""
+    let entity_count: Int = 0
+    let msg_len: Int = str_len(message)
+    let pos: Int = 0
+    while pos < msg_len && entity_count < 10 {
+        let wend: Int = pos
+        let scanning: Bool = true
+        while scanning && wend < msg_len {
+            let wch: String = str_slice(message, wend, wend + 1)
+            let is_sep: Bool = str_eq(wch, " ") || str_eq(wch, "\n") || str_eq(wch, "\t")
+                || str_eq(wch, ",") || str_eq(wch, ".") || str_eq(wch, "?")
+                || str_eq(wch, "!") || str_eq(wch, ":") || str_eq(wch, ";")
+                || str_eq(wch, "(") || str_eq(wch, ")") || str_eq(wch, "\'") || str_eq(wch, "-")
+            let scanning = if is_sep { false } else { scanning }
+            let wend = if !is_sep { wend + 1 } else { wend }
+        }
+        let word: String = str_slice(message, pos, wend)
+        let word_len: Int = str_len(word)
+        let first_ch: String = if word_len >= 3 { str_slice(word, 0, 1) } else { "" }
+        let is_capital: Bool = word_len >= 3 && str_contains(capitals, first_ch)
+        let is_stop: Bool = str_contains(stops, "|" + word + "|")
+        let already_have: Bool = str_contains(entities, word)
+        let should_add: Bool = is_capital && !is_stop && !already_have && word_len >= 3
+        let entities = if should_add {
+            if str_eq(entities, "") { word } else { entities + "\n" + word }
+        } else { entities }
+        // Increment entity_count at the while-body level so the binding escapes the
+        // if-expression scope and the entity_count < 10 guard actually terminates early.
+        let entity_count = if should_add { entity_count + 1 } else { entity_count }
+        let pos = if wend > pos { wend + 1 } else { pos + 1 }
+    }
+    return entities
+}
+
+// engram_detect_recall_intent — true when message explicitly requests memory recall.
+fn engram_detect_recall_intent(message: String) -> Bool {
+    return str_contains(message, "remind me")
+        || str_contains(message, "do you remember")
+        || str_contains(message, "what do you know")
+        || str_contains(message, "what happened")
+        || str_contains(message, "tell me about")
+        || str_contains(message, "what was")
+        || str_contains(message, "what were")
+        || str_contains(message, "how is it going")
+        || str_contains(message, "how are things")
+        || str_contains(message, "catch me up")
+        || str_contains(message, "fill me in")
+        || str_contains(message, "what's the status")
+        || str_contains(message, "whats the status")
+        || str_contains(message, "any updates")
+        || str_contains(message, "recap")
+        || str_contains(message, "look up")
+        || str_contains(message, "check on")
+        || str_contains(message, "how did")
+        || str_contains(message, "what happened with")
+}
+
+// engram_is_continuation — detect whether a message continues the active thread.
+// Returns true only when the message starts with a pronoun or an unambiguous
+// discourse continuation marker. Does NOT classify by message length: short messages
+// that introduce a new topic (e.g. "What is quantum computing?") are not continuations.
+// Does NOT classify interrogative starters (How, Why, When, Where, What about) as
+// continuations — these commonly open new topics and the false-positive cost is too high.
+fn engram_is_continuation(message: String, hist_len: Int) -> Bool {
+    if hist_len <= 0 { return false }
+    let has_pronoun: Bool = str_starts_with(message, "It ")
+        || str_starts_with(message, "it ")
+        || str_starts_with(message, "That ") || str_starts_with(message, "that ")
+        || str_starts_with(message, "This ") || str_starts_with(message, "this ")
+        || str_starts_with(message, "They ") || str_starts_with(message, "they ")
+        || str_starts_with(message, "He ") || str_starts_with(message, "he ")
+        || str_starts_with(message, "She ") || str_starts_with(message, "she ")
+        || str_starts_with(message, "We ") || str_starts_with(message, "we ")
+    if has_pronoun { return true }
+    // Only unambiguous discourse connectors that cannot open a new topic on their own.
+    let is_cont_opener: Bool = str_starts_with(message, "Go on")
+        || str_starts_with(message, "go on")
+        || str_starts_with(message, "Continue") || str_starts_with(message, "continue")
+        || str_starts_with(message, "Yes") || str_starts_with(message, "yes")
+        || str_starts_with(message, "No,") || str_starts_with(message, "no,")
+        || str_starts_with(message, "Ok") || str_starts_with(message, "ok")
+        || str_starts_with(message, "And ") || str_starts_with(message, "and ")
+        || str_starts_with(message, "But ") || str_starts_with(message, "but ")
+    if is_cont_opener { return true }
+    return false
+}
+
+// engram_compile_multi — run activation + search for one topic with expanded pools.
+// Activation depth 8 (was 5). Search 30 candidates ranked to 12 (was 20/8).
+// Per-topic result pool: up to 20 nodes (was 13).
+fn engram_compile_multi(topic: String) -> String {
+    let activate_json: String = engram_activate_json(topic, 8)
+    let search_json: String = engram_search_json(topic, 30)
+    let act_ok: Bool = !str_eq(activate_json, "") && !str_eq(activate_json, "[]")
+    let srch_ok: Bool = !str_eq(search_json, "") && !str_eq(search_json, "[]")
+    let act_nodes: String = if act_ok { activate_json } else { "" }
+    let srch_nodes: String = if srch_ok { engram_compile_ranked(search_json, 12) } else { "" }
+    if !str_eq(act_nodes, "") && !str_eq(srch_nodes, "") {
+        let act_inner: String = str_slice(act_nodes, 1, str_len(act_nodes) - 1)
+        let srch_inner: String = str_slice(srch_nodes, 1, str_len(srch_nodes) - 1)
+        return engram_dedup_nodes("[" + act_inner + "," + srch_inner + "]")
+    }
+    if !str_eq(act_nodes, "") { return act_nodes }
+    if !str_eq(srch_nodes, "") { return srch_nodes }
+    return ""
+}
+
+// engram_nodes_merge — merge two node arrays, deduplicating by node id.
+fn engram_nodes_merge(a: String, b: String) -> String {
+    let ok_a: Bool = !str_eq(a, "") && !str_eq(a, "[]")
+    let ok_b: Bool = !str_eq(b, "") && !str_eq(b, "[]")
+    if !ok_a && !ok_b { return "" }
+    if !ok_a { return b }
+    if !ok_b { return a }
+    let ai: String = str_slice(a, 1, str_len(a) - 1)
+    let bi: String = str_slice(b, 1, str_len(b) - 1)
+    return engram_dedup_nodes("[" + ai + "," + bi + "]")
 }
 
 fn engram_compile(intent: String) -> String {
-    let activate_json: String = engram_activate_json(intent, 5)
-    // Fetch more search results than we'll use so ranking has a real pool to pick from.
-    let search_json: String = engram_search_json(intent, 20)
+    // Issue 1: decompose multi-topic messages into sub-queries.
+    let topics: String = engram_split_topics(intent)
+    let has_multi_topic: Bool = str_contains(topics, "\n")
 
-    let act_ok: Bool = !str_eq(activate_json, "") && !str_eq(activate_json, "[]")
-    let srch_ok: Bool = !str_eq(search_json, "") && !str_eq(search_json, "[]")
+    // Issue 4: detect explicit recall intent and run boosted search.
+    let is_recall_intent: Bool = engram_detect_recall_intent(intent)
 
-    // Activation nodes (spreading activation) are already high-signal — keep all 5.
-    let act_part: String = if act_ok { activate_json } else { "" }
+    // Issue 2: extract named entities for dedicated per-entity searches.
+    let entity_list: String = engram_extract_entities(intent)
+    let has_entities: Bool = !str_eq(entity_list, "")
 
-    // Rank search results and keep only the top 8 (was: flat 15 unranked).
-    // This cuts context noise roughly in half while preserving the best-scoring nodes.
-    let srch_ranked: String = if srch_ok { engram_compile_ranked(search_json, 8) } else { "" }
-    let srch_part: String = srch_ranked
+    // Primary topic search (first or only topic).
+    let topic0: String = if has_multi_topic {
+        let nl0: Int = str_index_of(topics, "\n")
+        str_slice(topics, 0, nl0)
+    } else { topics }
+    let nodes0: String = engram_compile_multi(topic0)
 
-    // Fallback: when vector search returns nothing (no embeddings), fetch pinned
-    // high-salience nodes by their known IDs. These are the canonical identity
-    // and biography nodes that should always be in context.
-    // engram_get_node_json(id) returns a single node as JSON or "" if missing.
-    let scan_part: String = if !act_ok && !srch_ok {
-        let family_node: String = engram_get_node_json("knw-35940684-abc4-42f0-b942-818f66b1f69a")
-        let origin_node: String = engram_get_node_json("knw-729fc901-8335-44c4-9f3a-b150b4aa0915")
-        let fam_ok: Bool = !str_eq(family_node, "") && !str_eq(family_node, "null")
-        let orig_ok: Bool = !str_eq(origin_node, "") && !str_eq(origin_node, "null")
-        let fam_str: String = if fam_ok { family_node } else { "" }
-        let orig_str: String = if orig_ok { origin_node } else { "" }
-        let sep: String = if fam_ok && orig_ok { "\n" } else { "" }
-        let combined: String = fam_str + sep + orig_str
-        if str_eq(combined, "") { "" } else { combined }
-    } else {
-        ""
-    }
+    // Second topic segment.
+    let nodes1: String = if has_multi_topic {
+        let nl0: Int = str_index_of(topics, "\n")
+        let rest1: String = str_slice(topics, nl0 + 1, str_len(topics))
+        let nl1: Int = str_index_of(rest1, "\n")
+        let topic1: String = if nl1 < 0 { rest1 } else { str_slice(rest1, 0, nl1) }
+        if str_eq(topic1, "") { "" } else { engram_compile_multi(topic1) }
+    } else { "" }
 
-    // Affective context: always include the most recent high-emotion memory if one
-    // exists within 14 days. This ensures continuity of care across sessions — a
-    // crisis on Friday must still carry into Monday (72h was too narrow for multi-day
-    // distress arcs such as grief or recurring suicidal ideation). 14-day window
-    // (1,209,600 seconds) covers sustained emotional arcs while excluding ancient
-    // history. Unified with handle_chat and soul.el affective checks.
-    // We search for BellEvent nodes specifically; these are written by auto_persist
-    // when safety_detect_bell_level fires.
+    // Third topic segment.
+    let nodes2: String = if has_multi_topic {
+        let nl0: Int = str_index_of(topics, "\n")
+        let rest1: String = str_slice(topics, nl0 + 1, str_len(topics))
+        let nl1: Int = str_index_of(rest1, "\n")
+        if nl1 < 0 { "" } else {
+            let rest2: String = str_slice(rest1, nl1 + 1, str_len(rest1))
+            let nl2: Int = str_index_of(rest2, "\n")
+            let topic2: String = if nl2 < 0 { rest2 } else { str_slice(rest2, 0, nl2) }
+            if str_eq(topic2, "") { "" } else { engram_compile_multi(topic2) }
+        }
+    } else { "" }
+
+    // Fourth+ topic segments: engram_split_topics is recursive and can produce 4+ lines.
+    // Rather than hardcoding each topic index, collect everything after the third topic
+    // as a single combined search query so no segments are silently dropped.
+    // This handles inputs like "a and b and c and d" (4 topics).
+    let nodes3: String = if has_multi_topic {
+        let nl0: Int = str_index_of(topics, "\n")
+        let rest1: String = str_slice(topics, nl0 + 1, str_len(topics))
+        let nl1: Int = str_index_of(rest1, "\n")
+        if nl1 < 0 { "" } else {
+            let rest2: String = str_slice(rest1, nl1 + 1, str_len(rest1))
+            let nl2: Int = str_index_of(rest2, "\n")
+            if nl2 < 0 { "" } else {
+                // Remainder after the third segment — may span one or more topics.
+                // Search with the remaining text as-is; engram_compile_multi handles it.
+                let rest3: String = str_slice(rest2, nl2 + 1, str_len(rest2))
+                if str_eq(rest3, "") { "" } else { engram_compile_multi(rest3) }
+            }
+        }
+    } else { "" }
+
+    // Issue 2 cont.: entity 0 dedicated search (15 candidates, ranked 6).
+    let entity_nodes0: String = if has_entities {
+        let nl_e0: Int = str_index_of(entity_list, "\n")
+        let entity0: String = if nl_e0 < 0 { entity_list } else { str_slice(entity_list, 0, nl_e0) }
+        if str_eq(entity0, "") { "" } else {
+            let ent_srch: String = engram_search_json(entity0, 15)
+            let ent_ok: Bool = !str_eq(ent_srch, "") && !str_eq(ent_srch, "[]")
+            if ent_ok { engram_compile_ranked(ent_srch, 6) } else { "" }
+        }
+    } else { "" }
+
+    // Entity 1 dedicated search.
+    let entity_nodes1: String = if has_entities {
+        let nl_e0: Int = str_index_of(entity_list, "\n")
+        if nl_e0 < 0 { "" } else {
+            let rest_e: String = str_slice(entity_list, nl_e0 + 1, str_len(entity_list))
+            let nl_e1: Int = str_index_of(rest_e, "\n")
+            let entity1: String = if nl_e1 < 0 { rest_e } else { str_slice(rest_e, 0, nl_e1) }
+            if str_eq(entity1, "") { "" } else {
+                let ent_srch1: String = engram_search_json(entity1, 15)
+                let ent1_ok: Bool = !str_eq(ent_srch1, "") && !str_eq(ent_srch1, "[]")
+                if ent1_ok { engram_compile_ranked(ent_srch1, 6) } else { "" }
+            }
+        }
+    } else { "" }
+
+    // Issue 4 cont.: boosted search for recall-intent (40 candidates, ranked 15).
+    let recall_boost: String = if is_recall_intent {
+        let boost_srch: String = engram_search_json(intent, 40)
+        let boost_ok: Bool = !str_eq(boost_srch, "") && !str_eq(boost_srch, "[]")
+        if boost_ok { engram_compile_ranked(boost_srch, 15) } else { "" }
+    } else { "" }
+
+    // Merge all pools, deduplicating at each step.
+    let merged: String = engram_nodes_merge(nodes0, nodes1)
+    let merged: String = engram_nodes_merge(merged, nodes2)
+    let merged: String = engram_nodes_merge(merged, nodes3)
+    let merged: String = engram_nodes_merge(merged, entity_nodes0)
+    let merged: String = engram_nodes_merge(merged, entity_nodes1)
+    let merged: String = engram_nodes_merge(merged, recall_boost)
+    let merged_nodes: String = merged
+
+    // Fallback: when all searches return nothing, fetch persona nodes.
+    let scan_part: String = if str_eq(merged_nodes, "") || str_eq(merged_nodes, "[]") {
+        let persona_fallback: String = engram_search_json("soul:persona Persona identity", 5)
+        let pf_ok: Bool = !str_eq(persona_fallback, "") && !str_eq(persona_fallback, "[]")
+        if pf_ok {
+            let pf_ranked: String = engram_compile_ranked(persona_fallback, 3)
+            if str_eq(pf_ranked, "") { "" } else { pf_ranked }
+        } else { "" }
+    } else { "" }
+
+    // Affective context: always include the most recent high-emotion memory within 72h.
     let bell_nodes: String = engram_search_json("bell:soft bell:hard BellEvent", 3)
     let bell_ok: Bool = !str_eq(bell_nodes, "") && !str_eq(bell_nodes, "[]")
     let now_ts: Int = time_now()
-    let cutoff_ts: Int = now_ts - 1209600
+    let cutoff_ts: Int = now_ts - 259200
     let recent_bell: String = if bell_ok {
         let bn0: String = json_array_get(bell_nodes, 0)
-        // created_at is not present in engram node JSON for BellEvent nodes.
-        // Extract the timestamp embedded in the content string as " | ts:NNNNN".
-        // Fall back to created_at / updated_at JSON fields if the marker is absent.
         let bn_content: String = json_get(bn0, "content")
         let ts_marker: String = " | ts:"
         let ts_pos: Int = str_index_of(bn_content, ts_marker)
@@ -252,20 +427,50 @@ fn engram_compile(intent: String) -> String {
     } else { "" }
     let affective_part: String = if !str_eq(recent_bell, "") { recent_bell } else { "" }
 
-    let sep1: String = if !str_eq(act_part, "") && !str_eq(srch_part, "") { "\n" } else { "" }
-    let sep2: String = if (!str_eq(act_part, "") || !str_eq(srch_part, "")) && !str_eq(scan_part, "") { "\n" } else { "" }
-    let sep3: String = if (!str_eq(act_part, "") || !str_eq(srch_part, "") || !str_eq(scan_part, "")) && !str_eq(affective_part, "") { "\n" } else { "" }
-    let ctx: String = act_part + sep1 + srch_part + sep2 + scan_part + sep3 + affective_part
+    let has_main: Bool = !str_eq(merged_nodes, "") && !str_eq(merged_nodes, "[]")
+    let main_part: String = if has_main { merged_nodes } else { scan_part }
+    let sep_ma: String = if !str_eq(main_part, "") && !str_eq(affective_part, "") { "\n" } else { "" }
+    let ctx: String = main_part + sep_ma + affective_part
 
     if str_eq(ctx, "") { return "" }
 
-    // Raise the cap slightly to match the ranked (higher-signal) output.
-    if str_len(ctx) > 6000 {
-        return str_slice(ctx, 0, 6000)
+    // Safe JSON truncation — find last closing brace before budget cap.
+    // Budget raised from 6000 to 8000 for the larger multi-topic pool.
+    //
+    // Issue 8 fix: ctx may be main_part (JSON array) + "\n" + affective_part (single JSON
+    // object). When truncation cuts into the affective_part, appending "]" would produce
+    // "[array_content]{partial_bell_node}]" — not valid JSON. Guard: only append "]" when
+    // the truncation point falls strictly within the main array portion (before the "\n"
+    // separator). If the cut falls in the affective part, drop the partial object entirely
+    // and return only the complete main array. If there is no separator (ctx is a plain
+    // array with no affective part), the original append-"]" behaviour applies.
+    let budget: Int = 8000
+    if str_len(ctx) <= budget { return ctx }
+    let search_end: Int = budget - 1
+    let scan_limit: Int = if search_end > 500 { search_end - 500 } else { 0 }
+    let found_pos: Int = -1
+    let si: Int = search_end
+    while si >= scan_limit {
+        let ch: String = str_slice(ctx, si, si + 1)
+        let found_pos = if str_eq(ch, "}") && found_pos < 0 { si } else { found_pos }
+        let si = if found_pos >= 0 { scan_limit - 1 } else { si - 1 }
     }
-    return ctx
+    if found_pos < 0 { return str_slice(ctx, 0, budget) }
+    let truncated: String = str_slice(ctx, 0, found_pos + 1)
+    if str_starts_with(ctx, "[") {
+        // Determine whether this ctx has a separate affective object appended after the array.
+        // The format is: main_array + "\n" + bell_object. Find the array boundary.
+        let nl_pos: Int = str_index_of(ctx, "\n")
+        let has_affective_sep: Bool = nl_pos > 0 && nl_pos < str_len(ctx) - 1
+        if has_affective_sep && found_pos > nl_pos {
+            // Truncation fell inside the affective_part — drop it and return just the main array.
+            return str_slice(ctx, 0, nl_pos)
+        }
+        // Truncation is within the main array — close it properly.
+        return truncated + "]"
+    }
+    return truncated
 }
-
 fn json_safe(s: String) -> String {
     let s1: String = str_replace(s, "\\", "\\\\")
     let s2: String = str_replace(s1, "\"", "\\\"")
@@ -365,23 +570,19 @@ fn hist_trim(hist: String) -> String {
 // a bell event. If it did, write a preservation node to engram so the distress exchange
 // survives the 20-turn window. The LLM window drops it; engram retains it permanently
 // and engram_compile will surface it again via the affective context path.
+//
+// Fix: use json_array_get for structural parsing (immune to {"role": appearing in
+// message content) — same fix applied to hist_trim. The old str_index_of("{\"role\":")
+// pattern could corrupt history when any message contained that literal string.
 fn hist_trim_with_bell_guard(hist: String) -> String {
-    // Extract the first turn (should be a user message) to inspect it.
-    let inner: String = str_slice(hist, 1, str_len(hist) - 1)
-    let marker: String = "{\"role\":"
-    let i1: Int = str_index_of(inner, marker)
-    // i1 is the start of the first entry within inner.
-    // Find where the second entry begins to delimit the first entry's JSON.
-    let tail1: String = str_slice(inner, i1 + 1, str_len(inner))
-    let i2: Int = str_index_of(tail1, marker)
-    // The first entry spans from i1 to (i1 + 1 + i2 - 1) within inner.
-    let first_entry_raw: String = if i2 > 0 {
-        str_slice(inner, i1, i1 + 1 + i2 - 1)
-    } else {
-        str_slice(inner, i1, str_len(inner))
-    }
-    let first_role: String = json_get(first_entry_raw, "role")
-    let first_content: String = json_get(first_entry_raw, "content")
+    let total: Int = json_array_len(hist)
+    // Safety: never trim below 2 entries.
+    if total <= 2 { return hist }
+
+    // Extract the first entry structurally — immune to content containing {"role":
+    let first_entry: String = json_array_get(hist, 0)
+    let first_role: String = json_get(first_entry, "role")
+    let first_content: String = json_get(first_entry, "content")
 
     // Only inspect user turns — assistant content doesn't carry bell signals.
     let bell_level: String = if str_eq(first_role, "user") {
@@ -414,54 +615,9 @@ fn hist_trim_with_bell_guard(hist: String) -> String {
         )
     }
 
-    // Now perform the standard trim (drop oldest 2 entries = 1 user + 1 assistant pair).
-    let tail2: String = str_slice(tail1, i2 + 1, str_len(tail1))
-    let i3: Int = str_index_of(tail2, marker)
-    if i3 >= 0 {
-        return "[" + str_slice(tail2, i3, str_len(tail2)) + "]"
-    }
-    return hist
-}
-
-// hist_trim_to_byte_cap — drop oldest user+assistant pairs until the history blob
-// is at or below `cap_bytes` in length, or until only 2 entries remain (the minimum
-// safe window). Uses the same structural json_array_len/json_array_get approach as
-// hist_trim to stay immune to content containing JSON marker strings.
-//
-// Called after count-based trimming to enforce a hard size ceiling on the history
-// blob. Without this cap, long technical sessions with large assistant responses
-// (code blocks, logs, analysis) can push the 40-turn window to 100KB+, which causes
-// engram_node_full writes to grow state entries unboundedly.
-fn hist_trim_to_byte_cap(hist: String, cap_bytes: Int) -> String {
-    let current: String = hist
-    let current_len: Int = str_len(current)
-    while current_len > cap_bytes {
-        let total: Int = json_array_len(current)
-        // Never trim below 2 entries (1 pair).
-        if total <= 2 {
-            let current_len = 0  // exit loop
-        } else {
-            // Drop entries 0 and 1 (oldest pair).
-            let result: String = ""
-            let i: Int = 2
-            while i < total {
-                let entry: String = json_array_get(current, i)
-                let result = if str_eq(result, "") {
-                    entry
-                } else {
-                    result + "," + entry
-                }
-                let i = i + 1
-            }
-            if str_eq(result, "") {
-                let current_len = 0  // exit loop
-            } else {
-                let current = "[" + result + "]"
-                let current_len = str_len(current)
-            }
-        }
-    }
-    return current
+    // Now perform the standard trim: drop entries 0 and 1 (oldest user+assistant pair).
+    // Reuse hist_trim's structural approach — rebuild from entry 2 onward.
+    return hist_trim(hist)
 }
 
 // clean_llm_response — strips GPT-2 BPE byte-to-unicode artifacts that vLLM
@@ -577,14 +733,12 @@ fn handle_chat(body: String) -> String {
     let stored_hist: String = if str_eq(state_hist, "") { conv_history_load() } else { state_hist }
     let hist_len: Int = if str_eq(stored_hist, "") { 0 } else { json_array_len(stored_hist) }
 
-    // Thread-aware activation: short/ambiguous messages (continuations like "go on",
-    // "what else?", "yes") activate on the last reply instead of the bare message.
-    // This prevents a strong off-topic memory node from hijacking the reply when the
-    // user is clearly continuing an existing thread.
-    let is_continuation: Bool = str_len(message) < 50 && hist_len > 0
+    // Issue 8 fix: use semantic continuation detection instead of brittle 50-char threshold.
+    let is_continuation: Bool = engram_is_continuation(message, hist_len)
     let last_entry: String = if is_continuation { json_array_get(stored_hist, hist_len - 1) } else { "" }
     let last_content: String = if !str_eq(last_entry, "") { json_get(last_entry, "content") } else { "" }
-    let thread_snip: String = if str_len(last_content) > 150 { str_slice(last_content, 0, 150) } else { last_content }
+    // Thread snip extended 150->250 chars for better pronoun resolution context.
+    let thread_snip: String = if str_len(last_content) > 250 { str_slice(last_content, 0, 250) } else { last_content }
     let activation_seed: String = if !str_eq(thread_snip, "") {
         thread_snip + " " + message
     } else {
@@ -592,14 +746,12 @@ fn handle_chat(body: String) -> String {
     }
 
     // Cross-session affective context: on session start (no history yet), check engram
-    // for recent distress signals within 14 days and prepend a care directive if found.
-    // Extended from 72h: multi-day crisis must persist across Monday sessions starting
-    // 3+ days after a Friday event. Consistent with engram_compile and soul.el checks.
+    // for recent distress signals within 72h and prepend a care directive if found.
     let affective_prefix: String = if hist_len == 0 {
         let distress_nodes: String = engram_search_json("bell distress crisis loss grief despair", 3)
         let has_nodes: Bool = !str_eq(distress_nodes, "") && !str_eq(distress_nodes, "[]")
         let now_ts: Int = time_now()
-        let cutoff: Int = now_ts - 1209600
+        let cutoff: Int = now_ts - 259200
         let found_recent: Bool = if has_nodes {
             let dn0: String = json_array_get(distress_nodes, 0)
             let ts0_raw: String = json_get(dn0, "created_at")
@@ -615,71 +767,100 @@ fn handle_chat(body: String) -> String {
     let ctx: String = engram_compile(activation_seed)
     let system: String = affective_prefix + build_system_prompt(ctx)
 
-    // First message of the session: proactively load user profile and active work context.
-    // These two searches give the soul grounding before any conversation history exists.
-    // Results are rendered as brief bullets — not raw JSON — so they don't inflate context.
+    // Issue 9 fix: add project-specific and session-summary searches to session preload.
+    // Old hardcoded "user profile" and "in_progress active project" miss project-specific
+    // nodes stored under names like "Prism" unless those exact words appear in content.
     let session_preload: String = if hist_len == 0 {
         let profile_nodes: String = engram_search_json("user profile identity preferences", 5)
-        let work_nodes: String = engram_search_json("in_progress active project", 5)
+        let work_nodes: String = engram_search_json("in_progress active project work", 5)
+        let project_nodes: String = engram_search_json("project status current ongoing active", 5)
+        let summary_nodes: String = engram_search_json("SessionSummary session:summary previous-session recent", 3)
+
         let profile_ok: Bool = !str_eq(profile_nodes, "") && !str_eq(profile_nodes, "[]")
         let work_ok: Bool = !str_eq(work_nodes, "") && !str_eq(work_nodes, "[]")
+        let project_ok: Bool = !str_eq(project_nodes, "") && !str_eq(project_nodes, "[]")
+        let summary_ok: Bool = !str_eq(summary_nodes, "") && !str_eq(summary_nodes, "[]")
 
-        // Extract content fields and render as bullet points (one per node, first 120 chars).
         let profile_bullets: String = if profile_ok {
             let pn: Int = json_array_len(profile_nodes)
             let bullets: String = ""
-            let pi: Int = 0
-            // Collect up to 3 profile bullets
-            let bullets = if pi < pn {
+            let bullets = if pn > 0 {
                 let n0: String = json_array_get(profile_nodes, 0)
                 let c0: String = json_get(n0, "content")
-                let snip0: String = if str_len(c0) > 120 { str_slice(c0, 0, 120) } else { c0 }
-                if str_eq(snip0, "") { bullets } else { "- " + snip0 }
+                let s0: String = if str_len(c0) > 120 { str_slice(c0, 0, 120) } else { c0 }
+                if str_eq(s0, "") { bullets } else { "- " + s0 }
             } else { bullets }
             let bullets = if pn > 1 {
                 let n1: String = json_array_get(profile_nodes, 1)
                 let c1: String = json_get(n1, "content")
-                let snip1: String = if str_len(c1) > 120 { str_slice(c1, 0, 120) } else { c1 }
-                if str_eq(snip1, "") { bullets } else { bullets + "\n- " + snip1 }
+                let s1: String = if str_len(c1) > 120 { str_slice(c1, 0, 120) } else { c1 }
+                if str_eq(s1, "") { bullets } else { bullets + "\n- " + s1 }
             } else { bullets }
             let bullets = if pn > 2 {
                 let n2: String = json_array_get(profile_nodes, 2)
                 let c2: String = json_get(n2, "content")
-                let snip2: String = if str_len(c2) > 120 { str_slice(c2, 0, 120) } else { c2 }
-                if str_eq(snip2, "") { bullets } else { bullets + "\n- " + snip2 }
+                let s2: String = if str_len(c2) > 120 { str_slice(c2, 0, 120) } else { c2 }
+                if str_eq(s2, "") { bullets } else { bullets + "\n- " + s2 }
             } else { bullets }
             bullets
         } else { "" }
 
         let work_bullets: String = if work_ok {
             let wn: Int = json_array_len(work_nodes)
-            let wbullets: String = ""
-            let wbullets = if wn > 0 {
+            let wb: String = ""
+            let wb = if wn > 0 {
                 let w0: String = json_array_get(work_nodes, 0)
                 let wc0: String = json_get(w0, "content")
-                let wsnip0: String = if str_len(wc0) > 120 { str_slice(wc0, 0, 120) } else { wc0 }
-                if str_eq(wsnip0, "") { wbullets } else { "- " + wsnip0 }
-            } else { wbullets }
-            let wbullets = if wn > 1 {
+                let ws0: String = if str_len(wc0) > 120 { str_slice(wc0, 0, 120) } else { wc0 }
+                if str_eq(ws0, "") { wb } else { "- " + ws0 }
+            } else { wb }
+            let wb = if wn > 1 {
                 let w1: String = json_array_get(work_nodes, 1)
                 let wc1: String = json_get(w1, "content")
-                let wsnip1: String = if str_len(wc1) > 120 { str_slice(wc1, 0, 120) } else { wc1 }
-                if str_eq(wsnip1, "") { wbullets } else { wbullets + "\n- " + wsnip1 }
-            } else { wbullets }
-            wbullets
+                let ws1: String = if str_len(wc1) > 120 { str_slice(wc1, 0, 120) } else { wc1 }
+                if str_eq(ws1, "") { wb } else { wb + "\n- " + ws1 }
+            } else { wb }
+            wb
         } else { "" }
 
-        let has_profile: Bool = !str_eq(profile_bullets, "")
-        let has_work: Bool = !str_eq(work_bullets, "")
-        let preload: String = if has_profile || has_work {
-            let profile_section: String = if has_profile {
-                "[USER CONTEXT — from memory]\n" + profile_bullets
-            } else { "" }
-            let work_section: String = if has_work {
-                "[ACTIVE WORK — from memory]\n" + work_bullets
-            } else { "" }
-            let sep_pw: String = if has_profile && has_work { "\n\n" } else { "" }
-            "\n\n" + profile_section + sep_pw + work_section
+        let project_bullets: String = if project_ok {
+            let prn: Int = json_array_len(project_nodes)
+            let pb: String = ""
+            let pb = if prn > 0 {
+                let pr0: String = json_array_get(project_nodes, 0)
+                let prc0: String = json_get(pr0, "content")
+                let ps0: String = if str_len(prc0) > 120 { str_slice(prc0, 0, 120) } else { prc0 }
+                if str_eq(ps0, "") { pb } else { "- " + ps0 }
+            } else { pb }
+            let pb = if prn > 1 {
+                let pr1: String = json_array_get(project_nodes, 1)
+                let prc1: String = json_get(pr1, "content")
+                let ps1: String = if str_len(prc1) > 120 { str_slice(prc1, 0, 120) } else { prc1 }
+                if str_eq(ps1, "") { pb } else { pb + "\n- " + ps1 }
+            } else { pb }
+            pb
+        } else { "" }
+
+        let summary_bullet: String = if summary_ok {
+            let sn0: String = json_array_get(summary_nodes, 0)
+            let sc0: String = json_get(sn0, "content")
+            let ss0: String = if str_len(sc0) > 200 { str_slice(sc0, 0, 200) } else { sc0 }
+            if str_eq(ss0, "") { "" } else { "- " + ss0 }
+        } else { "" }
+
+        let hp: Bool = !str_eq(profile_bullets, "")
+        let hw: Bool = !str_eq(work_bullets, "")
+        let hpr: Bool = !str_eq(project_bullets, "")
+        let hs: Bool = !str_eq(summary_bullet, "")
+        let preload: String = if hp || hw || hpr || hs {
+            let sec_p: String = if hp { "[USER CONTEXT — from memory]\n" + profile_bullets } else { "" }
+            let sec_w: String = if hw { "[ACTIVE WORK — from memory]\n" + work_bullets } else { "" }
+            let sec_pr: String = if hpr { "[PROJECTS — from memory]\n" + project_bullets } else { "" }
+            let sec_s: String = if hs { "[PREVIOUS SESSION — from memory]\n" + summary_bullet } else { "" }
+            let sep1: String = if hp && (hw || hpr || hs) { "\n\n" } else { "" }
+            let sep2: String = if hw && (hpr || hs) { "\n\n" } else { "" }
+            let sep3: String = if hpr && hs { "\n\n" } else { "" }
+            "\n\n" + sec_p + sep1 + sec_w + sep2 + sec_pr + sep3 + sec_s
         } else { "" }
         preload
     } else { "" }
@@ -718,23 +899,16 @@ fn handle_chat(body: String) -> String {
     let updated_hist2: String = hist_append(updated_hist, "assistant", raw_response)
     // Use bell-guarded trim: if the evicted turn triggered a bell event, it is
     // preserved to engram before being dropped from the in-memory window.
-    // Increased from 20 to 40 turns: long technical sessions lose early context at 20
-    // (10 user + 10 assistant pairs). 40 turns preserves problem framing for multi-step
-    // tasks while the bell guard still persists evicted distress turns to engram.
-    // Byte-cap: after count-based trim, also trim oldest pairs until the history blob
-    // is under 32KB. Long technical sessions with large assistant responses (code blocks,
-    // analysis) can produce 100-160KB+ state entries at 40 turns; the count limit alone
-    // is insufficient. We retain at least 2 entries (1 user + 1 assistant pair) regardless.
-    let count_trimmed: String = if json_array_len(updated_hist2) > 40 {
+    // Issue #8 (NO MAX SIZE GUARD): the 20-turn count limit bounds entry count, but individual
+    // messages can be arbitrarily large (up to max_tokens = 4096 tokens each). At 20 turns the
+    // history blob can reach ~80KB before trim fires. engram_node_full has no apparent size cap.
+    // A byte-length cap would require truncating or summarising entries — too invasive here.
+    // TODO: add a byte-length cap (e.g. 32KB) that drops oldest entries until under limit.
+    let final_hist: String = if json_array_len(updated_hist2) > 20 {
         hist_trim_with_bell_guard(updated_hist2)
     } else {
         updated_hist2
     }
-    let final_hist: String = if str_len(count_trimmed) > 32768 {
-        hist_trim_to_byte_cap(count_trimmed, 32768)
-    } else {
-        count_trimmed
-    }
     state_set("conv_history", final_hist)
     conv_history_persist(final_hist)
 
@@ -905,15 +1079,11 @@ fn agentic_tools_all() -> String {
 fn call_mcp_bridge(tool_name: String, tool_input: String) -> String {
     let eff_input: String = if str_eq(tool_input, "") { "{}" } else { tool_input }
     let body: String = "{\"name\":\"" + tool_name + "\",\"input\":" + eff_input + "}"
-    // Issue #12: previously used a fixed path /tmp/neuron-mcp-call.json.
-    // Under concurrent load (64 worker threads), two simultaneous MCP tool calls
-    // race on this file — one call sends the other's input to the bridge.
-    // Fix: monotonic sequence counter makes the path unique per call.
-    let mcp_seq_s: String = state_get("mcp_call_seq")
-    let mcp_seq_n: Int = if str_eq(mcp_seq_s, "") { 0 } else { str_to_int(mcp_seq_s) }
-    let mcp_seq_next: Int = mcp_seq_n + 1
-    state_set("mcp_call_seq", int_to_str(mcp_seq_next))
-    let tmp: String = "/tmp/neuron-mcp-call-" + int_to_str(time_now()) + "-" + int_to_str(mcp_seq_next) + ".json"
+    // Issue #12: previously used a fixed path /tmp/neuron-mcp-call.json, then a
+    // time+seq path that still raced (time_now() is 1s granularity; non-atomic seq RMW).
+    // Fix: uuid_v4() provides collision-free uniqueness regardless of concurrency —
+    // same approach used by next_bridge_id(). No state read/write needed.
+    let tmp: String = "/tmp/neuron-mcp-call-" + uuid_v4() + ".json"
     fs_write(tmp, body)
     return exec_capture("curl -s --max-time 30 -X POST http://127.0.0.1:7771/mcp/call -H 'Content-Type: application/json' -d @" + tmp)
 }
@@ -1257,7 +1427,7 @@ fn handle_chat_agentic(body: String) -> String {
     let session_valid: Bool = if str_eq(req_session, "") {
         true
     } else {
-        !str_contains(session_get(req_session), "\"error\"")
+        session_exists(req_session)
     }
     if !session_valid {
         return "{\"error\":\"session not found\",\"session_id\":\"" + req_session + "\",\"reply\":\"\"}"
@@ -1266,7 +1436,8 @@ fn handle_chat_agentic(body: String) -> String {
     let hist_key: String = if str_eq(req_session, "") { "conv_history" } else { "session_hist_" + req_session }
     let agentic_hist: String = state_get(hist_key)
     let agentic_hist_len: Int = if str_eq(agentic_hist, "") { 0 } else { json_array_len(agentic_hist) }
-    let ag_is_cont: Bool = str_len(message) < 50 && agentic_hist_len > 0
+    // Issue 8 fix: use engram_is_continuation instead of brittle 50-char threshold.
+    let ag_is_cont: Bool = engram_is_continuation(message, agentic_hist_len)
     let ag_last_entry: String = if ag_is_cont { json_array_get(agentic_hist, agentic_hist_len - 1) } else { "" }
     let ag_last_content: String = if !str_eq(ag_last_entry, "") { json_get(ag_last_entry, "content") } else { "" }
     let ag_thread_snip: String = if str_len(ag_last_content) > 150 { str_slice(ag_last_content, 0, 150) } else { ag_last_content }
@@ -1312,14 +1483,7 @@ fn handle_chat_agentic(body: String) -> String {
     let discard_hist: Bool = if !str_eq(reply_text, "") {
         let updated: String = hist_append(agentic_hist, "user", message)
         let updated2: String = hist_append(updated, "assistant", reply_text)
-        // Increased from 20 to 40 turns: consistent with handle_chat window expansion.
-        // Byte-cap: also trim if the blob exceeds 32KB, consistent with handle_chat.
-        let count_trimmed2: String = if json_array_len(updated2) > 40 { hist_trim(updated2) } else { updated2 }
-        let trimmed: String = if str_len(count_trimmed2) > 32768 {
-            hist_trim_to_byte_cap(count_trimmed2, 32768)
-        } else {
-            count_trimmed2
-        }
+        let trimmed: String = if json_array_len(updated2) > 20 { hist_trim(updated2) } else { updated2 }
         state_set(hist_key, trimmed)
         // Only persist the default global session to engram — named sessions are ephemeral.
         if str_eq(hist_key, "conv_history") {
@@ -1903,6 +2067,7 @@ fn auto_persist(req: String, resp: String) -> Void {
             "session_bell_signal:" + sess_id
         }
         state_set(signal_key, safe_summary)
+    }
     if str_eq(conv_node_id, "") {
         println("[chat] auto_persist: engram_node_full returned empty — conversation node lost (ts=" + ts_str + ")")
     }

memory.el

@@ -35,94 +35,14 @@ fn mem_forget(node_id: String) -> Void {
     engram_forget(node_id)
 }
 
-// mem_consolidate — structural scan plus salience-evolution pass.
-//
-// Previously this only returned structural counts (scanned, total_nodes, total_edges)
-// with no salience updates. No node salience ever changed based on recall frequency
-// or time; foundational nodes decayed identically to ephemeral chat; frequently-recalled
-// nodes were never promoted. This made consolidation a no-op.
-//
-// New behavior:
-//   (a) Strengthen frequently-activated nodes: nodes in the top working-memory list
-//       (engram_wm_top_json) are strengthened — they have been recalled recently
-//       and deserve higher salience. Raises effective salience for nodes that prove
-//       relevant across multiple sessions.
-//   (b) Strengthen Canonical-tier nodes: identity and foundational nodes should not
-//       decay; each consolidation pass re-strengthens them so they resist the
-//       tier-aware decay curve without requiring active recall.
-//   (c) Structural counts are still returned for observability.
-//
-// Called by awareness_run() on the "consolidate" inbox action.
 fn mem_consolidate() -> String {
     let scanned: Int = engram_node_count()
-    let total_edges: Int = engram_edge_count()
-    let strengthened: Int = 0
-
-    // (a) Strengthen top working-memory nodes — recalled recently across sessions.
-    // Cap at 10 to keep consolidation fast.
-    let wm_top: String = engram_wm_top_json(10)
-    let wm_len: Int = json_array_len(wm_top)
-    let wi: Int = 0
-    while wi < wm_len {
-        let wm_node: String = json_array_get(wm_top, wi)
-        let wm_id: String = json_get(wm_node, "id")
-        if !str_eq(wm_id, "") {
-            engram_strengthen(wm_id)
-            let strengthened = strengthened + 1
-        }
-        let wi = wi + 1
-    }
-
-    // (b) Strengthen Canonical-tier nodes from a full paginated scan so they resist
-    // temporal decay. Canonical nodes encode foundational identity — they must not
-    // silently floor at 10. Page size 50, scanning until fewer than 50 nodes are
-    // returned (last page), so all Canonical nodes are reached even in large graphs.
-    // Without pagination, only the first 50 nodes in the graph were eligible; any
-    // Canonical node at index 50+ was silently excluded from the boost.
-    // Strengthening is skipped if the node's current salience is already at the
-    // runtime ceiling (represented as "1" by %g) to avoid monotonic unbounded growth.
-    // Canonical nodes with salience < 1.0 are strengthened each consolidation pass;
-    // once they reach the ceiling the runtime will no longer raise them further, so
-    // calling engram_strengthen at the ceiling is a no-op in the runtime anyway, but
-    // the explicit check makes the intent clear and avoids any runtime log noise.
-    let page_size: Int = 50
-    let scan_offset: Int = 0
-    let scan_done: Bool = false
-    while !scan_done {
-        let scan_result: String = engram_scan_nodes_json(page_size, scan_offset)
-        let scan_len: Int = json_array_len(scan_result)
-        if scan_len == 0 {
-            let scan_done = true
-        } else {
-            let si: Int = 0
-            while si < scan_len {
-                let s_node: String = json_array_get(scan_result, si)
-                let s_tier: String = json_get(s_node, "tier")
-                let s_id: String = json_get(s_node, "id")
-                let s_sal: String = json_get(s_node, "salience")
-                // Only strengthen if below the ceiling to prevent unbounded salience growth.
-                // engram serialises the ceiling as "1" (%g drops the decimal part when it
-                // is exactly zero). Any other value is below ceiling and should be boosted.
-                let at_ceiling: Bool = str_eq(s_sal, "1")
-                if str_eq(s_tier, "Canonical") && !str_eq(s_id, "") && !at_ceiling {
-                    engram_strengthen(s_id)
-                    let strengthened = strengthened + 1
-                }
-                let si = si + 1
-            }
-            let scan_offset = scan_offset + scan_len
-            // Fewer results than page_size means we've reached the last page.
-            if scan_len < page_size {
-                let scan_done = true
-            }
-        }
-    }
-
+    let dummy: String = engram_scan_nodes_json(100, 0)
     let total_nodes: Int = engram_node_count()
+    let total_edges: Int = engram_edge_count()
     return "{\"scanned\":" + int_to_str(scanned)
         + ",\"total_nodes\":" + int_to_str(total_nodes)
-        + ",\"total_edges\":" + int_to_str(total_edges)
-        + ",\"strengthened\":" + int_to_str(strengthened) + "}"
+        + ",\"total_edges\":" + int_to_str(total_edges) + "}"
 }
 
 fn mem_save(path: String) -> Void {

soul.el

@@ -166,40 +166,23 @@ fn load_identity_context() -> Void {
     // Cross-session affective context: query engram for recent distress/crisis signals
     // at session start. Stored under soul_affective_context so the safety layer can
     // detect when a user has been in distress across previous sessions.
-    // Recency guard: nodes older than 14 days (1,209,600 seconds) are skipped.
-    // Unified at 14 days with chat.el engram_compile and handle_chat affective checks
-    // so all three paths present consistent affective context. The previous 7-day
-    // (604800s) window was inconsistent with the 72h chat.el window, causing
-    // conflicting context: soul.el loaded a 5-day-old crisis node while chat.el
-    // did not include it on subsequent turns. Both now use 14 days.
-    // Results capped at 3 nodes, 200 chars each, to limit context inflation.
+    // Soft recency guard: nodes with a ts field older than 7 days are skipped.
+    // Results capped at 3 nodes, 200 chars each, to avoid over-injection into context.
     // TODO(recency): engram_search_json sorts by relevance, not timestamp. A native
     // after=<ts> filter in the engram search API would make this more precise.
-    let affective_raw: String = engram_search_json("distress crisis upset hopeless bell BellEvent", 3)
+    let affective_raw: String = engram_search_json("distress crisis upset hopeless", 3)
     let affective_ok: Bool = !str_eq(affective_raw, "") && !str_eq(affective_raw, "[]")
     if affective_ok {
         let ts_now: Int = time_now()
-        let ts_cutoff: Int = ts_now - 1209600
+        let ts_cutoff: Int = ts_now - 604800
         let aff_total: Int = json_array_len(affective_raw)
         let aff_ctx: String = ""
         let ai: Int = 0
         while ai < aff_total {
             let aff_node: String = json_array_get(affective_raw, ai)
             let aff_content: String = json_get(aff_node, "content")
-            // Use created_at (the standard engram node timestamp field), consistent
-            // with handle_chat which reads created_at / updated_at. The previous
-            // field name "ts" is not a standard engram field: it was present in some
-            // BellEvent content payloads but absent from standard engram node JSON,
-            // causing json_get to return "" and the fallback to ts_now — meaning ALL
-            // nodes with a missing "ts" field appeared recent, over-including stale
-            // content. With the 14-day window, this amplification was significant.
-            // Fix: read created_at first, fall back to updated_at, then default to 0
-            // (same as handle_chat). A ts of 0 always fails the cutoff check, so nodes
-            // missing both timestamp fields are conservatively excluded rather than
-            // blindly included.
-            let aff_ca: String = json_get(aff_node, "created_at")
-            let aff_ts_str: String = if str_eq(aff_ca, "") { json_get(aff_node, "updated_at") } else { aff_ca }
-            let aff_ts: Int = if str_eq(aff_ts_str, "") { 0 } else { str_to_int(aff_ts_str) }
+            let aff_ts_str: String = json_get(aff_node, "ts")
+            let aff_ts: Int = if str_eq(aff_ts_str, "") { ts_now } else { str_to_int(aff_ts_str) }
             let is_recent: Bool = aff_ts >= ts_cutoff
             let snip: String = if str_len(aff_content) > 200 { str_slice(aff_content, 0, 200) } else { aff_content }
             let aff_ctx = if is_recent && !str_eq(snip, "") {