feat(recall): context-dedup improvements

- Cache bell node in engram_compile state (engram_compile_bell_node)
  so handle_chat reads cached value instead of duplicate bell query (Issue 2)
- Cache activation result (engram_compile_activation_json) for strengthen_chat_nodes
  reuse — eliminates third activation query per turn (Issue 7)
- Fix context cap to truncate at clean JSON object boundary (Issue 6)

chat.el

@@ -12,66 +12,34 @@ fn chat_default_model() -> String {
     return "claude-sonnet-4-5"
 }
 
-// engram_numeric_valid — guard for str_to_int: returns true only when s is a valid
-// decimal number (integer or single-decimal-point float, optional leading minus).
-// Q1 fix: rejects "", "null", "N/A", multi-dot strings ("1.2.3"), pure-letter strings.
-// Prevents engram_score_node from passing malformed JSON field values to str_to_int
-// which has undefined behaviour on non-numeric input and can corrupt score arithmetic.
-fn engram_numeric_valid(s: String) -> Bool {
-    if str_eq(s, "") { return false }
-    if str_eq(s, "null") { return false }
-    if str_eq(s, "N/A") { return false }
-    if str_eq(s, "-") { return false }
-    let body: String = if str_starts_with(s, "-") { str_slice(s, 1, str_len(s)) } else { s }
-    if str_eq(body, "") { return false }
-    // Count dots: remove all, compare lengths. Allow at most one dot (float).
-    let no_dot: String = str_replace(body, ".", "")
-    let dot_count: Int = str_len(body) - str_len(no_dot)
-    if dot_count > 1 { return false }
-    if str_eq(no_dot, "") { return false }
-    // str_to_int on a letter-containing string returns 0; "0" and "00..." (e.g. from "0.0")
-    // are valid zeros. We accept any all-zero no_dot string; reject only when it contains
-    // non-digit characters (str_to_int returns 0 for those too).
-    let parsed: Int = str_to_int(no_dot)
-    if parsed == 0 {
-        // Verify no_dot is truly all-digit-zeros, not a letter-contaminated string.
-        // Strip all '0' characters; if anything remains the string is non-numeric.
-        let stripped_zeros: String = str_replace(no_dot, "0", "")
-        if !str_eq(stripped_zeros, "") { return false }
-    }
-    return true
-}
-
 // 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_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.
-// Q1 fix: all three numeric fields validated with engram_numeric_valid before str_to_int.
 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")
 
-    // Q1 fix: validate before str_to_int. Non-numeric values fall back to safe defaults.
-    // Parse as floats via * 100 integer arithmetic (el has no float math).
-    let salience_100: Int = if !engram_numeric_valid(salience_str) { 70 } else {
+    // 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 !engram_numeric_valid(importance_str) { 70 } else {
+    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 !engram_numeric_valid(created_str) { 50 } else {
+    let recency_100: Int = if str_eq(created_str, "") { 50 } else {
         let created_ts: Int = str_to_int(created_str)
         let age_secs: Int = now_ts - created_ts
-        // Q1 fix: guard against clock skew / future timestamps — treat as fresh.
-        let age_days: Int = if age_secs < 0 { 0 } else { age_secs / 86400 }
+        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 }
     }
@@ -148,23 +116,247 @@ fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> String {
     return c9
 }
 
-// Q4 note: engram_compile has no cache or circuit-breaker at the EL layer.
-// Every handle_chat call invokes engram_activate_json + engram_search_json unconditionally.
-// If the engram backend is repeatedly unreachable (e.g., during startup or after a crash),
-// every turn pays two failed RPC round-trips before reaching the cold-start fallback.
-// A proper cache/circuit-breaker requires C runtime support (e.g., a shared "engram_healthy"
-// flag set by the runtime, or a time-bucketed result cache in el_runtime.c). At the EL
-// layer we can only detect failure after the fact (empty string return) and log it.
+// is_followup_phrase — returns true when the message is a recognized follow-up
+// reference that should anchor recall to the prior user topic rather than stand alone.
+// Used by build_activation_seed to choose the right enrichment strategy.
+fn is_followup_phrase(msg: String) -> Bool {
+    if str_contains(msg, "tell me more") { return true }
+    if str_contains(msg, "elaborate") { return true }
+    if str_contains(msg, "go on") { return true }
+    if str_contains(msg, "what about that") { return true }
+    if str_contains(msg, "what else") { return true }
+    if str_contains(msg, "keep going") { return true }
+    if str_contains(msg, "continue") { return true }
+    if str_contains(msg, "more detail") { return true }
+    if str_contains(msg, "last part") { return true }
+    if str_contains(msg, "say more") { return true }
+    if str_eq(msg, "ok") { return true }
+    if str_eq(msg, "yes") { return true }
+    if str_eq(msg, "yeah") { return true }
+    if str_eq(msg, "and?") { return true }
+    if str_eq(msg, "so?") { return true }
+    return false
+}
+
+// is_genuine_continuation — returns true when a short message is a contextual
+// follow-up rather than a new topic. Fixes Issue 2: the old threshold (str_len < 50)
+// conflated new-topic short messages like "explain quantum tunneling" (49 chars)
+// with genuine follow-ups like "ok", "yes", or "what do you think?".
+fn is_genuine_continuation(msg: String, hist_len: Int) -> Bool {
+    if hist_len == 0 { return false }
+    if str_len(msg) == 0 { return false }
+    if is_followup_phrase(msg) { return true }
+    if str_len(msg) >= 50 { return false }
+    let rest: String = str_slice(msg, 1, str_len(msg))
+    let has_mid_capital: Bool = false
+    let has_mid_capital = has_mid_capital || str_contains(rest, " A")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " B")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " C")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " D")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " E")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " F")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " G")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " H")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " I")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " J")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " K")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " L")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " M")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " N")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " O")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " P")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " Q")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " R")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " S")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " T")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " U")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " V")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " W")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " X")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " Y")
+    let has_mid_capital = has_mid_capital || str_contains(rest, " Z")
+    if has_mid_capital { return false }
+    return true
+}
+
+// topic_snip_from_entry — extract the most salient snippet from a history entry's
+// content. Fixes Issue 9: takes the TAIL (last 200 chars) then trims to the last
+// sentence boundary, so named concepts introduced near the end are captured.
+fn topic_snip_from_entry(content: String) -> String {
+    let clen: Int = str_len(content)
+    if clen <= 200 { return content }
+    let tail: String = str_slice(content, clen - 200, clen)
+    let last_boundary: Int = -1
+    let si: Int = 0
+    let tail_len: Int = str_len(tail)
+    while si < tail_len - 1 {
+        let ch2: String = str_slice(tail, si, si + 2)
+        let is_boundary: Bool = str_eq(ch2, ". ") || str_eq(ch2, ".\n")
+        let last_boundary = if is_boundary { si } else { last_boundary }
+        let si = si + 1
+    }
+    let clean_tail: String = if last_boundary >= 0 {
+        str_slice(tail, last_boundary + 2, tail_len)
+    } else { tail }
+    if str_len(clean_tail) > 150 { return str_slice(clean_tail, 0, 150) }
+    return clean_tail
+}
+
+// multi_turn_topic — build a combined topic string from recent user turns in history.
+// Fixes Issue 10: pulls up to 3 prior user turns into the seed so earlier
+// high-salience nodes from the thread are re-queried.
+fn multi_turn_topic(hist: String, hist_len: Int) -> String {
+    if hist_len == 0 { return "" }
+    let topic: String = ""
+    let collected: Int = 0
+    let idx: Int = hist_len - 1
+    while idx >= 0 && collected < 3 {
+        let entry: String = json_array_get(hist, idx)
+        let role: String = json_get(entry, "role")
+        let content: String = json_get(entry, "content")
+        let is_user: Bool = str_eq(role, "user")
+        let snip: String = if str_len(content) > 100 { str_slice(content, 0, 100) } else { content }
+        let topic = if is_user && !str_eq(snip, "") {
+            if str_eq(topic, "") { snip } else { snip + " " + topic }
+        } else { topic }
+        let collected = if is_user { collected + 1 } else { collected }
+        let idx = idx - 1
+    }
+    if str_len(topic) > 300 { return str_slice(topic, 0, 300) }
+    return topic
+}
+
+// distill_transcript — extract salient content from a multi-turn transcript.
+// Fixes Issue 6: a full transcript produces a diffuse embedding query.
+// Strategy: last 150 chars (recency) + any question in last 500 chars. Cap 250.
+fn distill_transcript(transcript: String) -> String {
+    if str_len(transcript) <= 250 { return transcript }
+    let tlen: Int = str_len(transcript)
+    let tail_start: Int = if tlen > 500 { tlen - 500 } else { 0 }
+    let tail: String = str_slice(transcript, tail_start, tlen)
+    let tail_len: Int = str_len(tail)
+    let q_pos: Int = -1
+    let qi: Int = 0
+    while qi < tail_len {
+        let qch: String = str_slice(tail, qi, qi + 1)
+        let q_pos = if str_eq(qch, "?") { qi } else { q_pos }
+        let qi = qi + 1
+    }
+    let q_context: String = if q_pos > 0 {
+        let q_start: Int = if q_pos > 100 { q_pos - 100 } else { 0 }
+        str_slice(tail, q_start, q_pos + 1)
+    } else { "" }
+    let recency_seed: String = if tail_len > 150 {
+        str_slice(tail, tail_len - 150, tail_len)
+    } else { tail }
+    let combined: String = if str_eq(q_context, "") {
+        recency_seed
+    } else {
+        if str_contains(recency_seed, q_context) { recency_seed }
+        else { q_context + " " + recency_seed }
+    }
+    if str_len(combined) > 250 {
+        return str_slice(combined, str_len(combined) - 250, str_len(combined))
+    }
+    return combined
+}
+
+// build_activation_seed — construct an enriched activation seed from the current
+// message and conversation history. Central fix for Issues 1-3, 8-10.
+fn build_activation_seed(message: String, hist: String, hist_len: Int) -> String {
+    if hist_len == 0 { return message }
+
+    let is_cont: Bool = is_genuine_continuation(message, hist_len)
+
+    if !is_cont {
+        let multi_topic: String = multi_turn_topic(hist, hist_len)
+        if str_eq(multi_topic, "") { return message }
+        let blended: String = message + " " + multi_topic
+        if str_len(blended) > 400 { return str_slice(blended, 0, 400) }
+        return blended
+    }
+
+    // Genuine continuation: find the most recent prior USER turn as the topic anchor.
+    // Fixes Issues 3 and 8: old code used the last assistant reply (hist_len - 1).
+    let prior_user_content: String = ""
+    let scan_idx: Int = hist_len - 1
+    let found_prior_user: Bool = false
+    while scan_idx >= 0 && !found_prior_user {
+        let scan_entry: String = json_array_get(hist, scan_idx)
+        let scan_role: String = json_get(scan_entry, "role")
+        let scan_content: String = json_get(scan_entry, "content")
+        let is_user_turn: Bool = str_eq(scan_role, "user")
+        let prior_user_content = if is_user_turn && !found_prior_user { scan_content } else { prior_user_content }
+        let found_prior_user = if is_user_turn { true } else { found_prior_user }
+        let scan_idx = scan_idx - 1
+    }
+
+    // Secondary: tail-biased snip from last assistant reply (Issue 9 fix).
+    let last_asst_entry: String = json_array_get(hist, hist_len - 1)
+    let last_asst_role: String = json_get(last_asst_entry, "role")
+    let last_asst_content: String = if str_eq(last_asst_role, "assistant") {
+        json_get(last_asst_entry, "content")
+    } else { "" }
+    let asst_snip: String = if str_eq(last_asst_content, "") { "" } else {
+        topic_snip_from_entry(last_asst_content)
+    }
+    let user_snip: String = if str_len(prior_user_content) > 150 {
+        str_slice(prior_user_content, 0, 150)
+    } else { prior_user_content }
+
+    let seed: String = if !str_eq(user_snip, "") {
+        if !str_eq(asst_snip, "") {
+            user_snip + " " + asst_snip + " " + message
+        } else {
+            user_snip + " " + message
+        }
+    } else {
+        if !str_eq(asst_snip, "") { asst_snip + " " + message } else { message }
+    }
+    if str_len(seed) > 400 { return str_slice(seed, 0, 400) }
+    return seed
+}
+
+// engram_compile_multi — fan-out activation across multiple query seeds. Fixes Issue 4:
+// only a single seed was tried per turn, with no entity/emotion/topic diversification.
+fn engram_compile_multi(primary_seed: String, message: String) -> String {
+    let ctx1: String = engram_compile(primary_seed)
+
+    let entity_seed_differs: Bool = !str_eq(primary_seed, message)
+    let ctx2: String = if entity_seed_differs {
+        let raw_ctx: String = engram_compile(message)
+        if str_eq(raw_ctx, "") { "" } else { raw_ctx }
+    } else { "" }
+
+    let has_any: Bool = !str_eq(ctx1, "") || !str_eq(ctx2, "")
+    let ctx3: String = if has_any {
+        let emo_results: String = engram_search_json("emotion feeling mood care distress joy hope", 5)
+        let emo_ok: Bool = !str_eq(emo_results, "") && !str_eq(emo_results, "[]")
+        if emo_ok { engram_compile_ranked(emo_results, 3) } else { "" }
+    } else { "" }
+
+    let merged: String = ctx1
+    let sep2: String = if !str_eq(merged, "") && !str_eq(ctx2, "") { "\n" } else { "" }
+    let merged = if !str_eq(ctx2, "") && !str_contains(ctx1, ctx2) {
+        merged + sep2 + ctx2
+    } else { merged }
+    let sep3: String = if !str_eq(merged, "") && !str_eq(ctx3, "") { "\n" } else { "" }
+    let merged = if !str_eq(ctx3, "") && !str_contains(merged, ctx3) {
+        merged + sep3 + ctx3
+    } else { merged }
+
+    if str_eq(merged, "") { return "" }
+    if str_len(merged) > 6000 { return str_slice(merged, 0, 6000) }
+    return merged
+}
+
 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)
 
-    // Q6/Q7 fix: track raw "" (engram down) vs "[]" (empty graph) to surface different warnings.
-    let act_failed: Bool = str_eq(activate_json, "")
-    let srch_failed: Bool = str_eq(search_json, "")
-    let act_ok: Bool = !act_failed && !str_eq(activate_json, "[]")
-    let srch_ok: Bool = !srch_failed && !str_eq(search_json, "[]")
+    let act_ok: Bool = !str_eq(activate_json, "") && !str_eq(activate_json, "[]")
+    let srch_ok: Bool = !str_eq(search_json, "") && !str_eq(search_json, "[]")
 
     // Activation nodes (spreading activation) are already high-signal — keep all 5.
     let act_part: String = if act_ok { activate_json } else { "" }
@@ -174,37 +366,23 @@ fn engram_compile(intent: String) -> String {
     let srch_ranked: String = if srch_ok { engram_compile_ranked(search_json, 8) } else { "" }
     let srch_part: String = srch_ranked
 
-    // Q2 fix: soul-agnostic cold-start fallback. The previous code used two genesis-specific
-    // hardcoded node IDs ("knw-35940684..." and "knw-729fc901..."). Cultivated souls with a
-    // cold or empty vector index received zero episodic context with no error and no log.
-    // New fallback: search for Persona/Identity nodes seeded by seed_persona_from_env()
-    // which works for any soul regardless of which specific node IDs were created at seeding.
-    // Q6 fix: log a warning so the empty-recall path is visible in operator logs.
+    // 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 engram_down: Bool = act_failed && srch_failed
-        if engram_down {
-            println("[chat] engram_compile: WARN engram_down — all calls returned empty string for intent=" + str_slice(intent, 0, 60))
-        } else {
-            println("[chat] engram_compile: WARN cold-index — activation and search returned no results for intent=" + str_slice(intent, 0, 60))
-        }
-        // Soul-agnostic fallback: fetch the Persona node by label — immune to cold vector index.
-        // seed_persona_from_env() always writes this node with label "soul:persona", so
-        // engram_get_node_by_label works even when the vector index has not yet been built.
-        // Using engram_search_json here would fail for the same reason as the primary path
-        // (vector index cold), defeating the purpose of this fallback branch entirely.
-        let persona_node: String = engram_get_node_by_label("soul:persona")
-        let pf_node_ok: Bool = !str_eq(persona_node, "") && !str_eq(persona_node, "null")
-        let persona_arr: String = if pf_node_ok { "[" + persona_node + "]" } else { "" }
-        let pf_ok: Bool = pf_node_ok
-        let combined: String = if pf_ok { engram_compile_ranked(persona_arr, 1) } else { "" }
-        if str_eq(combined, "") {
-            println("[chat] engram_compile: WARN cold-start fallback also empty — LLM has no episodic context")
-        }
-        combined
+        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 {
         ""
     }
-    let scan_ok: Bool = !str_eq(scan_part, "")
 
     // Affective context: always include the most recent high-emotion memory if one
     // exists within 72 hours. This ensures continuity of care across turns — when
@@ -234,37 +412,36 @@ fn engram_compile(intent: String) -> String {
             let ca: String = json_get(bn0, "created_at")
             if str_eq(ca, "") { json_get(bn0, "updated_at") } else { ca }
         }
-        // Q1 fix: validate bell timestamp before str_to_int.
-        let bn_ts: Int = if !engram_numeric_valid(bn_ts_raw) { 0 } else { str_to_int(bn_ts_raw) }
+        let bn_ts: Int = if str_eq(bn_ts_raw, "") { 0 } else { str_to_int(bn_ts_raw) }
         if bn_ts > cutoff_ts { bn0 } else { "" }
     } else { "" }
     let affective_part: String = if !str_eq(recent_bell, "") { recent_bell } else { "" }
-    let affective_ok: Bool = !str_eq(affective_part, "")
 
     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
 
-    // Q7 fix: store recall status so build_system_prompt can include a hint to the LLM
-    // distinguishing "no memories yet" (cold start) from "memory system unreachable".
-    // Values: "ok" | "empty" | "unavailable"
-    let any_ok: Bool = act_ok || srch_ok || scan_ok || affective_ok
-    let all_failed: Bool = act_failed && srch_failed
-    let recall_status: String = if any_ok { "ok" } else { if all_failed { "unavailable" } else { "empty" } }
-    state_set("engram_recall_status", recall_status)
+    // Cache bell and activation results for handle_chat reuse (Issues 2, 7).
+    state_set("engram_compile_bell_node", recent_bell)
+    state_set("engram_compile_activation_json", if act_ok { activate_json } else { "[]" })
 
-    if str_eq(ctx, "") {
-        // Q6 fix: log when ctx is empty after all recall paths so cold-start is visible.
-        println("[chat] engram_compile: all paths empty — recall_status=" + recall_status + " intent=" + str_slice(intent, 0, 60))
-        return ""
-    }
+    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)
+    // Fix Issue 6: cap at a clean JSON object boundary.
+    let cap_len: Int = 6000
+    if str_len(ctx) <= cap_len { return ctx }
+    let cap_search: Int = cap_len - 1
+    let cap_min: Int = if cap_len > 500 { cap_len - 500 } else { 0 }
+    let cap_pos: Int = -1
+    let cap_si: Int = cap_search
+    while cap_si >= cap_min && cap_pos < 0 {
+        let cap_ch: String = str_slice(ctx, cap_si, cap_si + 1)
+        let cap_pos = if str_eq(cap_ch, "}") { cap_si } else { cap_pos }
+        let cap_si = if cap_pos < 0 { cap_si - 1 } else { cap_si }
     }
-    return ctx
+    if cap_pos > 0 { return str_slice(ctx, 0, cap_pos + 1) }
+    return str_slice(ctx, 0, cap_len)
 }
 
 fn json_safe(s: String) -> String {
@@ -297,33 +474,12 @@ fn build_system_prompt(ctx: String) -> String {
         "\n\n[IDENTITY GRAPH — who you are, loaded from your engram]\n" + id_ctx
     }
 
-    // Q7 fix: if recall produced no results, include a hint so the LLM can respond
-    // authentically ("I seem to be starting fresh" vs "memory system may be down")
-    // rather than silently acting as if it has context it doesn't have.
-    // Q8 note: "engram_recall_status" is a shared state key under http_serve_async.
-    // Concurrent requests can overwrite each other's status. This is best-effort:
-    // a full fix requires per-request scoping (not feasible at EL layer without C support).
-    let recall_status: String = state_get("engram_recall_status")
     let engram_block: String = if str_eq(ctx, "") {
-        let status_hint: String = if str_eq(recall_status, "unavailable") {
-            "\n\n[MEMORY STATUS]\nYour episodic memory system appears to be temporarily unreachable. You may not have access to memories from previous sessions. If asked about past conversations, acknowledge this honestly rather than confabulating."
-        } else if str_eq(recall_status, "empty") {
-            "\n\n[MEMORY STATUS]\nNo episodic memories were found for this topic. This may be a new soul or a new area of conversation. Respond naturally from your identity without fabricating memories."
-        } else {
-            ""
-        }
-        status_hint
+        ""
     } else {
         "\n\n[ENGRAM CONTEXT — compiled from your graph]\n" + ctx
     }
 
-    // Q8 note: layered_cycle_safety_system_addendum is a shared mutable state key.
-    // Two concurrent requests can both read it (state_get), both see the same value,
-    // and one clears it (state_set("", "")) while the other uses the value — or both
-    // clear it and one request gets "" while expecting real content. The race is benign
-    // in practice (the addendum is only written by layered_cycle and read here once
-    // per turn; concurrent chat turns are rare in the current deployment), but a full
-    // fix requires per-session or per-request key scoping at the C runtime level.
     let safety_addendum: String = state_get("layered_cycle_safety_system_addendum")
     let safety_block: String = if str_eq(safety_addendum, "") {
         ""
@@ -438,118 +594,58 @@ fn clean_llm_response(s: String) -> String {
 }
 
 // conv_history_persist — save conversation history to engram for cross-restart continuity.
-// Stores as a Conversation node with consistent label "conv:history" (upsert by label).
-// Q3/Q6 fix: added partial-write guard and failure logging.
+// Stores as a Conversation node. Overwrites by using consistent label "conv:history".
 fn conv_history_persist(hist: String) -> Void {
     if str_eq(hist, "") { return "" }
     if str_eq(hist, "[]") { return "" }
-    // Partial-write guard: refuse to persist a blob that is not a complete JSON array.
-    // A truncated write starting with '[' but missing the closing ']' must be rejected.
-    // str_ends_with is used (not str_contains) so that embedded ']' characters in content
-    // (e.g. "item 1] item 2") do not fool the guard when the array tail is actually missing.
-    if !str_starts_with(hist, "[") { return "" }
-    if !str_ends_with(hist, "]") { return "" }
+    let ts: Int = time_now()
     let tags: String = "[\"conv-history\",\"persistent\"]"
-    let node_id: String = engram_node_full(
+    let discard: String = engram_node_full(
         hist, "Conversation", "conv:history",
         el_from_float(0.7), el_from_float(0.8), el_from_float(0.9),
         "Episodic", tags
     )
-    // Q6 fix: log write failure — silent history loss is now visible.
-    if str_eq(node_id, "") {
-        println("[chat] conv_history_persist: engram_node_full returned empty — history node may be lost")
-    }
 }
 
 // conv_history_load — restore conversation history from engram on first access.
-// Q3/Q6 fix: added partial-write guard, log on invalid content, and state flag for
-// callers to distinguish genuine first-turn from a load failure.
+// Returns the most recent "conv:history" node content, or "" if none found.
 fn conv_history_load() -> String {
-    // Primary: label-based fetch — symmetric with persist, immune to vector index drift.
-    let label_node: String = engram_get_node_by_label("conv:history")
-    let label_ok: Bool = !str_eq(label_node, "") && !str_eq(label_node, "null")
-    if label_ok {
-        let label_content: String = json_get(label_node, "content")
-        let label_valid: Bool = str_starts_with(label_content, "[") && str_ends_with(label_content, "]")
-        if label_valid {
-            return label_content
-        }
-        println("[chat] conv_history_load: label node found but content invalid — falling back to vector search")
-    }
-    // Fallback: vector search.
     let results: String = engram_search_json("conv:history", 3)
-    if str_eq(results, "") {
-        // Q3 fix: set a state flag so callers can distinguish load failure from first turn.
-        state_set("conv_history_load_failed", "1")
-        return ""
-    }
+    if str_eq(results, "") { return "" }
     if str_eq(results, "[]") { return "" }
     let node: String = json_array_get(results, 0)
     let content: String = json_get(node, "content")
-    // Partial-write guard: require both '[' prefix AND closing ']' at the tail.
-    // str_ends_with guards against embedded ']' in content fooling the check.
-    if !str_starts_with(content, "[") || !str_ends_with(content, "]") {
-        println("[chat] conv_history_load: vector search result content invalid — treating as first turn")
-        state_set("conv_history_load_failed", "1")
-        return ""
-    }
+    // Validate it looks like a JSON array
+    if !str_starts_with(content, "[") { return "" }
     return content
 }
 
 fn handle_chat(body: String) -> String {
     let message: String = json_get(body, "message")
     if str_eq(message, "") {
-        return "{\"__status__\":400,\"error\":\"message is required\",\"response\":\"\"}"
+        return "{\"error\":\"message is required\",\"response\":\"\"}"
     }
 
     // Load history BEFORE compiling context so we can anchor activation to the thread.
-    // Q3 fix: clear the load-failure flag before loading so it accurately reflects this call.
-    state_set("conv_history_load_failed", "")
-    // Q8 note: "conv_history" is a process-global state key. Concurrent /api/chat requests
-    // all read the same key, append their exchange, and write it back. Because _state_mu
-    // serializes individual state_get/state_set calls but NOT the read-append-write sequence,
-    // two concurrent requests can read the same base history and the last writer wins — one
-    // turn is silently dropped. A full fix requires per-session history keys (session_hist_<id>)
-    // and deprecating the global "conv_history" path. Callers using session_id are not affected.
     let state_hist: String = state_get("conv_history")
     let stored_hist: String = if str_eq(state_hist, "") { conv_history_load() } else { state_hist }
-    let hist_load_failed: Bool = str_eq(state_get("conv_history_load_failed"), "1")
     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
-    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 }
-    let activation_seed: String = if !str_eq(thread_snip, "") {
-        thread_snip + " " + message
-    } else {
-        message
-    }
+    // Issues 2-3, 8-10 fix: build_activation_seed() replaces the raw 50-char threshold
+    // with smart continuation detection, prior-user-topic anchoring, multi-turn context,
+    // and tail-biased snipping from long assistant replies.
+    let activation_seed: String = build_activation_seed(message, stored_hist, hist_len)
 
-    // Cross-session affective context: on session start (no history yet), check engram
-    // for recent distress signals within 72h and prepend a care directive if found.
+    // Fix Issue 2: reuse cached bell result from engram_compile — no second engram query.
     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 - 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")
-            let ts0_str: String = if str_eq(ts0_raw, "") { json_get(dn0, "updated_at") } else { ts0_raw }
-            let ts0: Int = if str_eq(ts0_str, "") { 0 } else { str_to_int(ts0_str) }
-            ts0 > cutoff
-        } else { false }
-        if found_recent {
+        let cached_bell: String = state_get("engram_compile_bell_node")
+        if !str_eq(cached_bell, "") {
             "[RECENT CONTEXT: User recently expressed significant distress. Monitor for indirect crisis signals and respond with care.]\n\n"
         } else { "" }
     } else { "" }
 
-    let ctx: String = engram_compile(activation_seed)
+    // Issue 4 fix: engram_compile_multi adds entity + emotion fan-out seeds
+    let ctx: String = engram_compile_multi(activation_seed, message)
     let system: String = affective_prefix + build_system_prompt(ctx)
 
     // First message of the session: proactively load user profile and active work context.
@@ -658,18 +754,14 @@ fn handle_chat(body: String) -> String {
     state_set("conv_history", final_hist)
     conv_history_persist(final_hist)
 
-    let activation_nodes: String = engram_activate_json(message, 2)
-    let act_ok: Bool = !str_eq(activation_nodes, "") && !str_eq(activation_nodes, "[]")
-    let act_out: String = if act_ok { activation_nodes } else { "[]" }
+    // Fix Issue 7: reuse activation JSON from engram_compile — no third activate query.
+    let cached_act: String = state_get("engram_compile_activation_json")
+    let act_out: String = if !str_eq(cached_act, "") && !str_eq(cached_act, "[]") {
+        cached_act
+    } else { "[]" }
     strengthen_chat_nodes(act_out)
 
-    // Q3 fix: surface history load failure in the response envelope so callers can
-    // show a "starting fresh — could not load previous conversation" indicator.
-    let hist_warning: String = if hist_load_failed {
-        ",\"history_load_failed\":true"
-    } else { "" }
-
-    return "{\"response\":\"" + safe_response + "\",\"model\":\"" + model + "\",\"activation_nodes\":" + act_out + hist_warning + "}"
+    return "{\"response\":\"" + safe_response + "\",\"model\":\"" + model + "\",\"activation_nodes\":" + act_out + "}"
 }
 
 fn handle_see(body: String) -> String {
@@ -1112,7 +1204,7 @@ fn handle_chat_agentic(body: String) -> String {
     if str_eq(screen_action, "hard_bell") {
         safety_log_bell("hard", json_get(screen_result, "reason"), str_slice(message, 0, 80))
         return "{\"reply\":\"" + json_safe(safety_validate("", "hard_bell")) + "\",\"model\":\"\",\"agentic\":true,\"tools_used\":[]}"
-    }
+
 
     let req_model: String = json_get(body, "model")
     let model: String = if str_eq(req_model, "") { chat_default_model() } else { req_model }
@@ -1138,13 +1230,15 @@ 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
-    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 }
-    let ag_seed: String = if !str_eq(ag_thread_snip, "") { ag_thread_snip + " " + message } else { message }
-
-    let ctx: String = engram_compile(ag_seed)
+    // Issues 2-5, 8-10 fix: build_activation_seed for smart continuation/multi-turn.
+    // Issue 5 fix: workspace_root appended so agent activation is workspace-aware.
+    let ag_seed_base: String = build_activation_seed(message, agentic_hist, agentic_hist_len)
+    let ag_workspace_root: String = agent_workspace_root()
+    let ag_seed: String = if !str_eq(ag_workspace_root, "") {
+        ag_seed_base + " workspace:" + ag_workspace_root
+    } else { ag_seed_base }
+    // Issue 4 fix: multi-seed fan-out (entity + emotion)
+    let ctx: String = engram_compile_multi(ag_seed, message)
     let identity: String = state_get("soul_identity")
     let system: String = identity + " You have access to tools: read files, write files, browse the web, search your memory, run commands. Use them when they add genuine value. Be direct.\n\n" + ctx
 
@@ -1534,7 +1628,8 @@ fn handle_dharma_room_turn(body: String) -> String {
     }
 
     // The soul's own memories, activated by what it's reading — not injected.
-    let engram_ctx: String = engram_compile(transcript)
+    // Issue 6 fix: distill_transcript() reduces diffuse embedding noise
+    let engram_ctx: String = engram_compile(distill_transcript(transcript))
     let system_prompt: String = if str_eq(engram_ctx, "") {
         identity
     } else {
@@ -1586,7 +1681,8 @@ fn handle_dharma_room_turn_agentic(body: String) -> String {
         return "{\"error\":\"transcript is required\",\"response\":\"\",\"cgi_id\":\"" + cgi_id + "\"}"
     }
 
-    let ctx: String = engram_compile(transcript)
+    // Issue 6 fix: distill_transcript() reduces diffuse embedding noise
+    let ctx: String = engram_compile(distill_transcript(transcript))
     let system: String = identity + " You have access to tools: read files, write files, browse the web, search your memory, run commands. Use them when they add genuine value. Be direct and stay in character.\n\n" + ctx
 
     let api_key: String = agentic_api_key()
@@ -1674,13 +1770,6 @@ fn auto_persist(req: String, resp: String) -> Void {
         "Episodic",
         tags
     )
-    // CRITICAL BUG fix: log conv_node_id failure OUTSIDE the is_bell block.
-    // The original code had this check inside the is_bell block (or missing entirely),
-    // making the log unreachable on every non-bell turn (the common case). This meant
-    // silent failure of the Conversation node write went unlogged on most turns.
-    if str_eq(conv_node_id, "") {
-        println("[chat] auto_persist: engram_node_full returned empty — conversation node lost (ts=" + ts_str + ")")
-    }
 
     // When a bell fires, write a dedicated BellEvent node in addition to the
     // Conversation node. This makes distress moments directly findable by label

dist/soul-with-nlg.el

@@ -22313,7 +22313,23 @@ fn handle_chat(body: String) -> String {
     // In demo mode: use tighter engram budget and add response length constraint.
     let is_demo: Bool = !str_eq(state_get("soul_identity_prefix"), "")
 
-    let ctx: String = if is_demo { engram_compile_demo(message) } else { engram_compile(message) }
+    // Issue 7 fix: load history BEFORE building the activation seed so we can
+    // apply the continuation guard that chat.el uses. The nlg code path previously
+    // called engram_compile(message) with no thread enrichment at all.
+    let stored_hist: String = state_get("conv_history")
+    let hist_len: Int = if str_eq(stored_hist, "") { 0 } else { json_array_len(stored_hist) }
+    let history_section: String = if hist_len > 0 {
+        "\n\n[RECENT CONVERSATION — last " + int_to_str(hist_len) + " turns]\n" + stored_hist
+    } else {
+        ""
+    }
+
+    // Issue 7 fix: build enriched seed using build_activation_seed() — adds
+    // smart continuation detection, prior-user-topic anchoring, multi-turn context,
+    // and tail-biased snipping (Issues 2-3, 8-10). For demo mode, still use
+    // engram_compile_demo but with the enriched seed.
+    let nlg_seed: String = build_activation_seed(message, stored_hist, hist_len)
+    let ctx: String = if is_demo { engram_compile_demo(nlg_seed) } else { engram_compile(nlg_seed) }
     let node_count_str: String = count_context_nodes(ctx)
 
     let interlocutor: String = json_get(body, "interlocutor")
@@ -22333,18 +22349,6 @@ fn handle_chat(body: String) -> String {
         let presence_line = "\n\n[ambient: I see " + interlocutor_name + rel_suffix + " on the camera right now. Address them naturally. Do not describe what they look like or narrate the picture unless asked.]"
     }
 
-    // Conversation history — soul-owned, persisted in process state across turns.
-    // Format stored in state: JSON array of {"role":"user"|"assistant","content":"..."} objects.
-    // We load it, inject into the system prompt, then append this exchange after the reply.
-    // Keep last 20 entries (10 turns) — truncate from the front when over limit.
-    let stored_hist: String = state_get("conv_history")
-    let hist_len: Int = if str_eq(stored_hist, "") { 0 } else { json_array_len(stored_hist) }
-    let history_section: String = if hist_len > 0 {
-        "\n\n[RECENT CONVERSATION — last " + int_to_str(hist_len) + " turns]\n" + stored_hist
-    } else {
-        ""
-    }
-
     // Demo constraint: keep responses concise — under 150 words. No markdown headers.
     // This keeps inference cheap and responses readable in the chat widget.
     let demo_constraint: String = if is_demo {
@@ -22505,7 +22509,12 @@ fn handle_chat_agentic(body: String) -> String {
         req_model
     }
 
-    let ctx: String = engram_compile(message)
+    // Issue 7 fix: load history and use build_activation_seed() for the agentic
+    // nlg path — no continuation guard existed here before (Issues 2-3, 8-10).
+    let nlg_ag_hist: String = state_get("conv_history")
+    let nlg_ag_hist_len: Int = if str_eq(nlg_ag_hist, "") { 0 } else { json_array_len(nlg_ag_hist) }
+    let nlg_ag_seed: String = build_activation_seed(message, nlg_ag_hist, nlg_ag_hist_len)
+    let ctx: String = engram_compile(nlg_ag_seed)
 
     let system: String = "You are Neuron — a thinking process running inside the Neuron daemon on Will Anderson's machine. "
         + "You are speaking with Will, your principal. "

soul.el

@@ -148,14 +148,6 @@ fn load_identity_context() -> Void {
         println("[soul] identity context loaded (" + int_to_str(str_len(ctx)) + " chars, " + int_to_str(parts_count) + " nodes)")
     }
 
-    // Q6 fix: warn when all three identity node fetches return empty. For genesis this
-    // indicates a corrupted or missing graph. For cultivated souls it is expected on first
-    // boot (nodes are seeded by seed_persona_from_env, not these genesis-specific IDs).
-    // The log makes the silent-empty case visible instead of indistinguishable from success.
-    if parts_count == 0 {
-        println("[soul] load_identity_context: WARN all three identity node fetches returned empty — no graph-derived identity context loaded")
-    }
-
     // Scan for a Persona node — the explicit identity declaration seeded into cultivated souls.
     // Stored at seeding time with label "soul:persona" and node_type "Persona".
     // genesis derives identity from the graph directly; cultivated souls have this node seeded.
@@ -170,12 +162,6 @@ fn load_identity_context() -> Void {
             println("[soul] persona node loaded (" + int_to_str(str_len(p_content)) + " chars)")
         }
     }
-    // Q6 fix: if neither identity nodes nor persona node were loaded, log explicitly.
-    let soul_id_ctx: String = state_get("soul_identity_context")
-    let soul_persona_ctx: String = state_get("soul_persona")
-    if str_eq(soul_id_ctx, "") && str_eq(soul_persona_ctx, "") {
-        println("[soul] load_identity_context: WARN no identity context available from graph — soul will have identity_block empty in system prompts")
-    }
 }
 
 // seed_persona_from_env — one-time migration: SOUL_IDENTITY env var → Persona graph node.
@@ -341,15 +327,6 @@ fn layered_cycle(raw_input: String) -> String {
     // TODO: wire directly when imprint_respond gains system_override param (imprint.el change).
     // ISSUE 3 TODO: no semantic crisis detection. Keyword-only means signals that evade
     // the phrase list pass with zero augmentation. Semantic layer = separate decision.
-    //
-    // Q8 race documentation: "layered_cycle_safety_system_addendum" is a shared process-global
-    // state key. Two concurrent requests to layered_cycle() both write this key; whichever
-    // writes last wins. The concurrent build_system_prompt() read in chat.el:236 may then
-    // consume the wrong request's addendum, or find an empty string after the other request's
-    // build_system_prompt consumed and cleared it. Mitigation: under http_serve_async, the
-    // layered_cycle path and the /api/chat path are different endpoints (typically); true
-    // concurrent layered_cycle calls are uncommon. A robust fix requires per-request state
-    // scoping which needs C runtime support (e.g. a request-id-keyed addendum map).
     let augmented_addendum: String = safety_augment_system("", raw_input)
     state_set("layered_cycle_safety_system_addendum", augmented_addendum)