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.

awareness.el

@@ -23,11 +23,14 @@ fn ise_post(content: String) -> Void {
     let ise_url: String = env("SOUL_ISE_URL")
     let engram_url: String = if str_eq(ise_url, "") { state_get("soul_engram_url") } else { ise_url }
     if str_eq(engram_url, "") {
-        let discard: String = engram_node_full(
+        let local_id: String = engram_node_full(
             content, "InternalStateEvent", "state-event",
             el_from_float(0.3), el_from_float(0.3), el_from_float(0.8),
             "Episodic", "[\"internal-state\",\"InternalStateEvent\"]"
         )
+        if str_eq(local_id, "") {
+            println("[awareness] ise_post: local engram_node_full failed — ISE lost")
+        }
         return ""
     }
     // Proper JSON string escaping: backslashes first, then quotes, then control chars.
@@ -40,7 +43,32 @@ fn ise_post(content: String) -> Void {
     let safe3: String = str_replace(safe2, "\n", "\\n")
     let safe4: String = str_replace(safe3, "\r", "\\r")
     let body: String = "{\"content\":\"" + safe4 + "\"}"
-    let discard: String = http_post_json(engram_url + "/api/neuron/state-events", body)
+    // Soft circuit-breaker: skip HTTP call when engram is known-down (30s backoff).
+    // Opens after 3 consecutive failures; half-open probe after backoff expires.
+    // TODO(reliability): full async dispatch requires EL runtime futures support.
+    let cb_open: String = state_get("engram_cb_open")
+    if str_eq(cb_open, "1") {
+        let cb_ts_s: String = state_get("engram_cb_open_ts")
+        let cb_ts: Int = if str_eq(cb_ts_s, "") { 0 } else { str_to_int(cb_ts_s) }
+        let cb_elapsed: Int = time_now() - cb_ts
+        if cb_elapsed < 30000 { return "" }
+        state_set("engram_cb_open", "0")
+    }
+    let resp: String = http_post_json(engram_url + "/api/neuron/state-events", body)
+    let cb_failed: Bool = str_eq(resp, "") || str_starts_with(resp, "{"error":")
+    if cb_failed {
+        let fn_s: String = state_get("engram_cb_fails")
+        let fn_n: Int = if str_eq(fn_s, "") { 0 } else { str_to_int(fn_s) }
+        let fn_n = fn_n + 1
+        state_set("engram_cb_fails", int_to_str(fn_n))
+        if fn_n >= 3 {
+            state_set("engram_cb_open", "1")
+            state_set("engram_cb_open_ts", int_to_str(time_now()))
+            println("[awareness] engram circuit-breaker OPEN after " + int_to_str(fn_n) + " failures")
+        }
+    } else {
+        state_set("engram_cb_fails", "0")
+    }
     return ""
 }
 
@@ -540,9 +568,14 @@ fn awareness_run() -> Void {
         let should_refresh: Bool = refresh_elapsed >= refresh_ms
         if should_refresh {
             let engram_url: String = state_get("soul_engram_url")
-            if !str_eq(engram_url, "") {
+            let sc: String = state_get("engram_cb_open")
+            let sc_ts_s: String = state_get("engram_cb_open_ts")
+            let sc_ts: Int = if str_eq(sc_ts_s, "") { 0 } else { str_to_int(sc_ts_s) }
+            let sc_elapsed: Int = now_ts - sc_ts
+            let sync_allowed: Bool = !str_eq(sc, "1") || sc_elapsed >= 30000
+            if !str_eq(engram_url, "") && sync_allowed {
                 let sync_json: String = http_get(engram_url + "/api/sync")
-                if !str_eq(sync_json, "") && !str_eq(sync_json, "{}") {
+                if !str_eq(sync_json, "") && !str_eq(sync_json, "{}") && !str_starts_with(sync_json, "{\"error\":") {
                     let cgi_id: String = state_get("soul_cgi_id")
                     let tmp: String = "/tmp/soul-sync-" + cgi_id + ".json"
                     fs_write(tmp, sync_json)
@@ -678,8 +711,6 @@ fn threat_trajectory_check(tool_name: String, tool_input: String) -> Int {
     return combined
 }
 
-// TODO(reliability #10): agentic_conv_history is process-global; awareness loop
-// and HTTP workers race on this key. Impact: noisy threat score only, not content.
 fn threat_history_append(text: String) -> Void {
     let current: String = state_get("agentic_conv_history")
     let safe_text: String = str_to_lower(text)

chat.el

@@ -119,7 +119,32 @@ fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> String {
     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,", "")
-    return c14
+    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.
@@ -170,9 +195,11 @@ fn engram_extract_entities(message: String) -> String {
         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 {
-            let entity_count = entity_count + 1
             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
@@ -201,10 +228,12 @@ fn engram_detect_recall_intent(message: String) -> Bool {
         || str_contains(message, "what happened with")
 }
 
-// engram_is_continuation — semantic continuation detection replacing the brittle 50-char
-// threshold. Returns true when message starts with a pronoun, continuation opener, or is
-// < 80 chars (raised from 50 to catch "Can you remind me what Prism's architecture
-// looks like?" at 57 chars which is clearly a continuation in an active thread).
+// 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 ")
@@ -216,6 +245,7 @@ fn engram_is_continuation(message: String, hist_len: Int) -> Bool {
         || 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")
@@ -224,12 +254,7 @@ fn engram_is_continuation(message: String, hist_len: Int) -> Bool {
         || 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 ")
-        || str_starts_with(message, "What about") || str_starts_with(message, "what about")
-        || str_starts_with(message, "Why ") || str_starts_with(message, "why ")
-        || str_starts_with(message, "How ") || str_starts_with(message, "how ")
-        || str_starts_with(message, "When ") || str_starts_with(message, "when ")
     if is_cont_opener { return true }
-    if str_len(message) < 80 { return true }
     return false
 }
 
@@ -265,39 +290,6 @@ fn engram_nodes_merge(a: String, b: String) -> String {
     return engram_dedup_nodes("[" + ai + "," + bi + "]")
 }
 
-// id_in_seen — check if node_id appears in the comma-delimited seen accumulator.
-// Pads both sides with commas to avoid false substring matches.
-fn id_in_seen(node_id: String, seen: String) -> Bool {
-    if str_eq(node_id, "") { return false }
-    if str_eq(seen, "") { return false }
-    return str_contains("," + seen + ",", "," + node_id + ",")
-}
-
-// add_to_seen — append node_id to the comma-delimited seen accumulator.
-fn add_to_seen(seen: String, node_id: String) -> String {
-    if str_eq(node_id, "") { return seen }
-    if str_eq(seen, "") { return node_id }
-    return seen + "," + node_id
-}
-
-// engram_extract_ids — extract all non-empty "id" fields from a JSON node array
-// into a comma-delimited string for use with id_in_seen / add_to_seen.
-fn engram_extract_ids(nodes_json: String) -> String {
-    if str_eq(nodes_json, "") { return "" }
-    if str_eq(nodes_json, "[]") { return "" }
-    let total: Int = json_array_len(nodes_json)
-    if total == 0 { return "" }
-    let ids: String = ""
-    let i: Int = 0
-    while i < total {
-        let node: String = json_array_get(nodes_json, i)
-        let nid: String = json_get(node, "id")
-        let ids = if str_eq(nid, "") { ids } else { add_to_seen(ids, nid) }
-        let i = i + 1
-    }
-    return ids
-}
-
 fn engram_compile(intent: String) -> String {
     // Issue 1: decompose multi-topic messages into sub-queries.
     let topics: String = engram_split_topics(intent)
@@ -339,6 +331,26 @@ fn engram_compile(intent: String) -> String {
         }
     } 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")
@@ -375,6 +387,7 @@ fn engram_compile(intent: String) -> String {
     // 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)
@@ -419,22 +432,18 @@ fn engram_compile(intent: String) -> String {
     let sep_ma: String = if !str_eq(main_part, "") && !str_eq(affective_part, "") { "\n" } else { "" }
     let ctx: String = main_part + sep_ma + affective_part
 
-    // Dedup fix: publish seen node IDs so downstream callers (session_preload) can skip
-    // nodes already present in the compiled context. Must be computed after scan_part and
-    // affective_part are resolved so all three segments are represented in the seen set.
-    // EL has no tuple returns so we use state as an out-param.
-    // scan_part is a JSON array — extract with engram_extract_ids.
-    // affective_part is a bare JSON object (bn0), not an array — extract its id directly.
-    let ids_from_merged: String = engram_extract_ids(merged_nodes)
-    let ids_from_scan: String = engram_extract_ids(scan_part)
-    let ids_from_affective: String = json_get(affective_part, "id")
-    let compile_seen_ids: String = add_to_seen(add_to_seen(ids_from_merged, ids_from_scan), ids_from_affective)
-    state_set("engram_compile_seen_ids", compile_seen_ids)
-
     if str_eq(ctx, "") { return "" }
 
-    // Issue 7 fix: safe JSON truncation — find last closing brace before budget cap.
+    // 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
@@ -448,7 +457,18 @@ fn engram_compile(intent: String) -> String {
     }
     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, "[") { return truncated + "]" }
+    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 {
@@ -508,18 +528,41 @@ fn hist_append(hist: String, role: String, content: String) -> String {
     return "[" + inner + "," + entry + "]"
 }
 
+// hist_trim — drop the oldest two entries from a history JSON array.
+//
+// Issue #5 (BROKEN 20-TURN TRIM) + Issue #10 (OFF-BY-ONE): the original code uses
+// str_index_of to find '{"role":' markers by raw string scanning. If any message content
+// contains the literal string '{"role":' (e.g. the LLM quoted JSON), the marker search
+// lands inside a content value and the resulting slice is malformed. Additionally, the
+// function had no minimum-retained-count guard.
+//
+// Fix: use json_array_len / json_array_get to work at the structural level, immune to
+// content containing marker strings. Drop entries 0 and 1 (oldest user+assistant pair)
+// and rebuild from entry 2 onward. Minimum retained count: 2 entries (never over-trim).
 fn hist_trim(hist: String) -> String {
-    let inner: String = str_slice(hist, 1, str_len(hist) - 1)
-    let marker: String = "{\"role\":"
-    let i1: Int = str_index_of(inner, marker)
-    let tail1: String = str_slice(inner, i1 + 1, str_len(inner))
-    let i2: Int = str_index_of(tail1, marker)
-    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)) + "]"
+    // Issue #9 fix: use json_array_len/json_array_get instead of fragile str_index_of
+    // parser. Old code was silently corrupting history on malformed JSON.
+    let total: Int = json_array_len(hist)
+    // Safety: never trim below 2 entries. If already at or below the minimum, return unchanged.
+    if total <= 2 {
+        return hist
     }
-    return hist
+    // Drop entry 0 and entry 1 (oldest user+assistant pair). Rebuild from entry 2 onward.
+    let result: String = ""
+    let i: Int = 2
+    while i < total {
+        let entry: String = json_array_get(hist, i)
+        let result = if str_eq(result, "") {
+            entry
+        } else {
+            result + "," + entry
+        }
+        let i = i + 1
+    }
+    if str_eq(result, "") {
+        return hist
+    }
+    return "[" + result + "]"
 }
 
 // hist_trim_with_bell_guard — trim the history window exactly as hist_trim does, but
@@ -527,23 +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") {
@@ -576,13 +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
+    // 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
@@ -601,41 +636,99 @@ fn clean_llm_response(s: String) -> String {
 }
 
 // conv_history_persist — save conversation history to engram for cross-restart continuity.
-// Stores as a Conversation node. Overwrites by using consistent label "conv:history".
+// Stores as a Conversation node with label "conv:history".
+//
+// Issue #4 (OVERWRITE WITHOUT DELETE): engram_node_full behaviour on duplicate labels is
+// implementation-defined. If it appends rather than upserts, stale older nodes accumulate.
+// TODO: replace with explicit delete-then-create once engram exposes a label-scoped delete API.
+//
+// Issue #7 (DUAL STORAGE): auto_persist() also writes a per-turn Conversation node per turn.
+// Both run every turn for different purposes (rolling array vs. Q&A snapshot). Documented here.
 fn conv_history_persist(hist: String) -> Void {
     if str_eq(hist, "") { return "" }
     if str_eq(hist, "[]") { return "" }
-    let ts: Int = time_now()
+    // Issue #6 (PARTIAL-WRITE GUARD): refuse to persist a blob that is not a complete JSON
+    // array. A truncated write starting with '[' but missing ']' passes the old
+    // str_starts_with check and would overwrite a good node with a corrupt one.
+    if !str_starts_with(hist, "[") { return "" }
+    if !str_contains(hist, "]") { return "" }
     let tags: String = "[\"conv-history\",\"persistent\"]"
-    let discard: String = engram_node_full(
+    let node_id: 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
     )
+    // Issue #2 (SILENT FAILURE): surface write failures in logs rather than dropping silently.
+    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.
-// Returns the most recent "conv:history" node content, or "" if none found.
+//
+// Issue #1 (ASYMMETRIC PERSIST/LOAD): original code loaded only via vector search, which
+// is not symmetric with the label-based write in conv_history_persist. A cold or corrupt
+// vector index returns [] even when the node exists on disk. Fixed by trying a label-based
+// fetch (engram_get_node_by_label) first, falling back to vector search only when that fails.
+//
+// Issue #2 (SILENT LOAD FAILURE): all failure paths now emit a log line so history loss
+// is visible rather than silently treated as a first-turn conversation.
+//
+// Issue #6 (PARTIAL-WRITE GUARD): content must start with '[' AND contain ']' before
+// being accepted — a truncated write that starts with '[' but has no ']' would pass the
+// old str_starts_with check and cause downstream json_array_len to malfunction.
 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_contains(label_content, "]")
+        if label_valid {
+            return label_content
+        }
+        // Label node exists but content is invalid — partial write or corruption.
+        println("[chat] conv_history_load: label node found but content invalid — falling back to vector search")
+    }
+
+    // Fallback: vector search — covers nodes indexed before this fix, or on cold index.
     let results: String = engram_search_json("conv:history", 3)
     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")
-    // Validate it looks like a JSON array
-    if !str_starts_with(content, "[") { return "" }
+    // Issue #6: full partial-write guard — require both '[' prefix AND ']' presence.
+    if !str_starts_with(content, "[") || !str_contains(content, "]") {
+        println("[chat] conv_history_load: vector search result content invalid — treating as first turn")
+        return ""
+    }
     return content
 }
 
 fn handle_chat(body: String) -> String {
     let message: String = json_get(body, "message")
     if str_eq(message, "") {
-        return "{\"error\":\"message is required\",\"response\":\"\"}"
+        // Issue #5: missing required param — HTTP 400.
+        return "{\"__status__\":400,\"error\":\"message is required\",\"response\":\"\"}"
     }
 
     // Load history BEFORE compiling context so we can anchor activation to the thread.
-    // TODO(reliability #3 — conv_history global race): process-global key; concurrent
-    // /api/chat requests without session_id race on this read-append-write.
+    // Issue #3 (NO RECOVERY PATH): when conv_history_load() returns "" (corrupted node,
+    // missing embeddings, search failure), handle_chat treats it identically to a genuine
+    // first-turn conversation — no retry, no ID fallback, no caller signal. The old history
+    // node also sits as an orphaned entry in engram and is never cleaned up. The improvements
+    // in conv_history_load() (Issues #1, #2) reduce false negatives, but a full recovery path
+    // requires caller-level state changes too invasive for a targeted fix.
+    // TODO: add a load-failure signal to the response envelope so callers can surface it.
+    //
+    // TODO(reliability #3 — conv_history global race): "conv_history" is a process-global
+    // state key. Concurrent /api/chat requests that omit session_id 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, one thread's
+    // appended exchange can be overwritten by another thread writing its own version.
+    // The fix is to require callers to supply a session_id (routing them through
+    // session_hist_<id>) and deprecate the global "conv_history" path. Callers using
+    // the session API (which scopes history per session_hist_<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_len: Int = if str_eq(stored_hist, "") { 0 } else { json_array_len(stored_hist) }
@@ -672,15 +765,11 @@ fn handle_chat(body: String) -> String {
     } else { "" }
 
     let ctx: String = engram_compile(activation_seed)
-    // Read IDs published by engram_compile so session_preload can skip duplicate nodes.
-    // EL has no multiple return values; engram_compile writes its seen set to state.
-    let seen_ids: String = state_get("engram_compile_seen_ids")
     let system: String = affective_prefix + build_system_prompt(ctx)
 
     // 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.
-    // Dedup fix: skip any node whose ID already appeared in engram_compile's output.
     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 work", 5)
@@ -697,24 +786,21 @@ fn handle_chat(body: String) -> String {
             let bullets: String = ""
             let bullets = if pn > 0 {
                 let n0: String = json_array_get(profile_nodes, 0)
-                let n0_id: String = json_get(n0, "id")
                 let c0: String = json_get(n0, "content")
                 let s0: String = if str_len(c0) > 120 { str_slice(c0, 0, 120) } else { c0 }
-                if str_eq(s0, "") || id_in_seen(n0_id, seen_ids) { bullets } else { "- " + s0 }
+                if str_eq(s0, "") { bullets } else { "- " + s0 }
             } else { bullets }
             let bullets = if pn > 1 {
                 let n1: String = json_array_get(profile_nodes, 1)
-                let n1_id: String = json_get(n1, "id")
                 let c1: String = json_get(n1, "content")
                 let s1: String = if str_len(c1) > 120 { str_slice(c1, 0, 120) } else { c1 }
-                if str_eq(s1, "") || id_in_seen(n1_id, seen_ids) { bullets } else { bullets + "\n- " + s1 }
+                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 n2_id: String = json_get(n2, "id")
                 let c2: String = json_get(n2, "content")
                 let s2: String = if str_len(c2) > 120 { str_slice(c2, 0, 120) } else { c2 }
-                if str_eq(s2, "") || id_in_seen(n2_id, seen_ids) { bullets } else { bullets + "\n- " + s2 }
+                if str_eq(s2, "") { bullets } else { bullets + "\n- " + s2 }
             } else { bullets }
             bullets
         } else { "" }
@@ -724,17 +810,15 @@ fn handle_chat(body: String) -> String {
             let wb: String = ""
             let wb = if wn > 0 {
                 let w0: String = json_array_get(work_nodes, 0)
-                let w0_id: String = json_get(w0, "id")
                 let wc0: String = json_get(w0, "content")
                 let ws0: String = if str_len(wc0) > 120 { str_slice(wc0, 0, 120) } else { wc0 }
-                if str_eq(ws0, "") || id_in_seen(w0_id, seen_ids) { wb } else { "- " + ws0 }
+                if str_eq(ws0, "") { wb } else { "- " + ws0 }
             } else { wb }
             let wb = if wn > 1 {
                 let w1: String = json_array_get(work_nodes, 1)
-                let w1_id: String = json_get(w1, "id")
                 let wc1: String = json_get(w1, "content")
                 let ws1: String = if str_len(wc1) > 120 { str_slice(wc1, 0, 120) } else { wc1 }
-                if str_eq(ws1, "") || id_in_seen(w1_id, seen_ids) { wb } else { wb + "\n- " + ws1 }
+                if str_eq(ws1, "") { wb } else { wb + "\n- " + ws1 }
             } else { wb }
             wb
         } else { "" }
@@ -744,27 +828,24 @@ fn handle_chat(body: String) -> String {
             let pb: String = ""
             let pb = if prn > 0 {
                 let pr0: String = json_array_get(project_nodes, 0)
-                let pr0_id: String = json_get(pr0, "id")
                 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, "") || id_in_seen(pr0_id, seen_ids) { pb } else { "- " + ps0 }
+                if str_eq(ps0, "") { pb } else { "- " + ps0 }
             } else { pb }
             let pb = if prn > 1 {
                 let pr1: String = json_array_get(project_nodes, 1)
-                let pr1_id: String = json_get(pr1, "id")
                 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, "") || id_in_seen(pr1_id, seen_ids) { pb } else { pb + "\n- " + ps1 }
+                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 sn0_id: String = json_get(sn0, "id")
             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, "") || id_in_seen(sn0_id, seen_ids) { "" } else { "- " + ss0 }
+            if str_eq(ss0, "") { "" } else { "- " + ss0 }
         } else { "" }
 
         let hp: Bool = !str_eq(profile_bullets, "")
@@ -799,11 +880,16 @@ fn handle_chat(body: String) -> String {
 
     let raw_response: String = llm_call_system(model, full_system, message)
 
+    // Issue #5: also catch empty string — llm_extract_text() in el_runtime.c silently
+    // returns "" when the response content array is missing or all blocks fail to parse.
+    // Without this guard an empty reply passes through as a silent empty response.
     let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
         || str_starts_with(raw_response, "{\"type\":\"error\"")
         || str_contains(raw_response, "authentication_error")
+        || str_eq(raw_response, "")
     if is_error {
-        return "{\"error\":\"llm unavailable\",\"response\":\"\"}"
+        // Issue #6: LLM failure — HTTP 503 (service unavailable).
+        return "{\"__status__\":503,\"error\":\"llm unavailable\",\"response\":\"\"}"
     }
 
     let clean_response: String = clean_llm_response(raw_response)
@@ -813,6 +899,11 @@ 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.
+    // 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 {
@@ -868,6 +959,42 @@ fn studio_tools_json() -> String {
     "]"
 }
 
+// ---------------------------------------------------------------------------
+// LLM reliability — issues that require C runtime fixes (el_runtime.c).
+// These cannot be addressed at the EL layer; they are documented here so the
+// symptoms are traceable back to their root causes.
+//
+// Issue #1 (no retry on timeout/connection error):
+//   http_do() in el_runtime.c calls curl_easy_perform() once. On
+//   CURLE_OPERATION_TIMEDOUT / CURLE_COULDNT_CONNECT / CURLE_RECV_ERROR it
+//   returns http_error_json() with no retry. Fix: add a retry loop (max 3
+//   attempts, exponential back-off starting at 1s) inside llm_provider_request().
+//
+// Issue #2 (60s timeout applies to all HTTP calls including LLM):
+//   EL_HTTP_TIMEOUT_MS defaults to 60000ms for every http_do() call.
+//   Fix: introduce EL_LLM_TIMEOUT_MS (default 120000) used only by
+//   llm_provider_request(); leave EL_HTTP_TIMEOUT_MS (default 30000) for
+//   general service calls to avoid holding connections for 60s.
+//
+// Issue #3 (HTTP 429 causes silent provider failover, not backoff):
+//   llm_chain_call() advances to the next provider on any JSON-prefixed response
+//   including 429. Fix: parse HTTP status via curl_easy_getinfo; on 429 sleep
+//   Retry-After seconds (default 5s) then retry the same provider up to 3 times.
+//
+// Issue #4 (HTTP 500/502 crashes the request silently):
+//   Same path as #3 — 5xx responses cause immediate provider failover with no
+//   retry. Fix: retry with exponential back-off (1s, 2s, 4s) before advancing.
+//
+// Issue #6 (no secondary LLM fallback in production):
+//   Set NEURON_LLM_1_URL/KEY/FORMAT in ExternalSecret to a secondary provider
+//   (e.g. Gemini). No C code change required; llm_chain_call() already iterates.
+//
+// Issue #8 (LLM response size unbounded — memory-only cap):
+//   HttpBuf grows via realloc() with no hard limit. Fix: add
+//   EL_HTTP_MAX_RESPONSE_BYTES (default 10MiB) cap in httpbuf_append() and
+//   return http_error_json("response too large") on overflow.
+// ---------------------------------------------------------------------------
+
 fn agentic_api_key() -> String {
     let k1: String = env("ANTHROPIC_API_KEY")
     if !str_eq(k1, "") {
@@ -919,7 +1046,7 @@ fn agentic_tools_with_web() -> String {
 // Short timeout + empty-array fallback: if the bridge is down, the soul runs
 // exactly as before with only its built-in tools (graceful degradation).
 fn connector_tools_json() -> String {
-    let raw: String = exec_capture("curl -s --max-time 2 http://127.0.0.1:7771/mcp/tools")
+    let raw: String = exec_capture("curl -s --max-time 5 http://127.0.0.1:7771/mcp/tools")
     if str_eq(raw, "") {
         return "[]"
     }
@@ -952,7 +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 + "}"
-    let tmp: String = "/tmp/neuron-mcp-call.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)
 }
@@ -964,7 +1095,7 @@ fn tool_auto_approved(tool_name: String) -> Bool {
     if !str_starts_with(tool_name, "mcp__") {
         return false
     }
-    let raw: String = exec_capture("curl -s --max-time 2 http://127.0.0.1:7771/mcp/auto-approved")
+    let raw: String = exec_capture("curl -s --max-time 5 http://127.0.0.1:7771/mcp/auto-approved")
     if str_eq(raw, "") {
         return false
     }
@@ -1234,15 +1365,22 @@ fn is_builtin_tool(tool_name: String) -> Bool {
 }
 
 // next_bridge_id — unique correlation id for a suspended agentic turn.
-// Uses uuid_v4() as the primary uniqueness guarantee — concurrent calls cannot collide.
+// Uses uuid_v4() as the primary uniqueness guarantee so concurrent calls
+// (even in the same millisecond) cannot collide. The "mcp_bridge_seq"
+// counter is kept for human readability in logs/debugging but is no longer
+// relied on for uniqueness.
 //
-// TODO(reliability #6): mcp_bridge_seq RMW is non-atomic. Now benign because
-// uuid_v4() provides collision-free uniqueness. Counter is kept for readability only.
+// TODO(reliability #6): state_get/state_set on "mcp_bridge_seq" is a
+// non-atomic read-modify-write — two concurrent calls can read the same
+// counter and produce the same counter suffix. This is now benign because
+// uuid_v4() provides collision-free uniqueness. A true counter fix would
+// require an atomic_increment() builtin in el_runtime.c.
 fn next_bridge_id() -> String {
     let prev: String = state_get("mcp_bridge_seq")
     let n: Int = if str_eq(prev, "") { 0 } else { str_to_int(prev) }
     let next: Int = n + 1
     state_set("mcp_bridge_seq", int_to_str(next))
+    // uuid_v4() provides collision-free uniqueness; counter is decorative.
     let uid: String = uuid_v4()
     return "br-" + uid
 }
@@ -1334,12 +1472,23 @@ fn handle_chat_agentic(body: String) -> String {
 
     // Persist the exchange to session/global history for thread continuity on next turn.
     // Only save when the loop completed (reply present), not when tool_pending.
+    //
+    // Issue #9 (AGENTIC HISTORY NOT PERSISTED): the agentic path previously only saved
+    // history to in-process state (state_set), which is lost on restart. We now also call
+    // conv_history_persist() for the default session (hist_key == "conv_history") so agentic
+    // history survives restarts the same way non-agentic history does. Per-session histories
+    // (session_hist_<id>) are still in-process only — persisting all named sessions would
+    // require per-session engram labels, a larger change tracked separately.
     let reply_text: String = json_get(result, "reply")
     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)
         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") {
+            conv_history_persist(trimmed)
+        }
         true
     } else { false }
 
@@ -1370,6 +1519,14 @@ fn agentic_loop(session_id: String, model: String, safe_sys: String, tools_json:
     let iteration: Int = 0
     let keep_going: Bool = true
 
+    // Issue #9: agentic max_tokens configurable via NEURON_LLM_MAX_TOKENS env var.
+    // Default 4096 is marginal for long tool chains (8 iterations x 4096 tokens).
+    // Set to 8192+ for complex multi-step tasks.
+    // Note: llm_provider_request() in el_runtime.c also hardcodes 4096 for the
+    // llm_call_system() (non-agentic) path; that requires a C runtime change.
+    let max_tokens_env: String = env("NEURON_LLM_MAX_TOKENS")
+    let max_tokens_str: String = if str_eq(max_tokens_env, "") { "4096" } else { max_tokens_env }
+
     // Suspension state — captured at top level so it escapes the while body.
     let pending: Bool = false
     let pend_tool_id: String = ""
@@ -1378,7 +1535,7 @@ fn agentic_loop(session_id: String, model: String, safe_sys: String, tools_json:
 
     while keep_going && iteration < 8 {
         let req_body: String = "{\"model\":\"" + model + "\""
-            + ",\"max_tokens\":4096"
+            + ",\"max_tokens\":" + max_tokens_str
             + ",\"system\":\"" + safe_sys + "\""
             + ",\"tools\":" + tools_json
             + ",\"messages\":" + messages
@@ -1658,9 +1815,11 @@ fn handle_chat_as_soul(body: String) -> String {
 
     let raw_response: String = llm_call_system(model, system_prompt, eff_message)
 
+    // Issue #5: empty string catch — same rationale as handle_chat.
     let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
         || str_starts_with(raw_response, "{\"type\":\"error\"")
         || str_contains(raw_response, "authentication_error")
+        || str_eq(raw_response, "")
     if is_error {
         return "{\"error\":\"llm unavailable\",\"response\":\"\",\"speaker_slug\":\"" + speaker + "\",\"model\":\"" + model + "\"}"
     }
@@ -1707,9 +1866,11 @@ fn handle_dharma_room_turn(body: String) -> String {
 
     let raw_response: String = llm_call_system(model, system_prompt, transcript)
 
+    // Issue #5: empty string catch — same rationale as handle_chat.
     let is_error: Bool = str_starts_with(raw_response, "{\"error\"")
         || str_starts_with(raw_response, "{\"type\":\"error\"")
         || str_contains(raw_response, "authentication_error")
+        || str_eq(raw_response, "")
     if is_error {
         return "{\"error\":\"llm unavailable\",\"response\":\"\",\"cgi_id\":\"" + cgi_id + "\"}"
     }
@@ -1723,13 +1884,19 @@ fn handle_dharma_room_turn(body: String) -> String {
     // engram_node(content, "episodic", ...) which wrongly put a TIER into the node_type
     // slot — that's why nodes showed node_type="episodic". Use the full, correct contract.)
     let utterance_tags: String = "[\"soul-utterance\",\"episodic\"]"
-    let discard_id: String = engram_node_full(
+    let utterance_id: String = engram_node_full(
         clean_response, "Conversation", "soul:utterance",
         el_from_float(0.6), el_from_float(0.6), el_from_float(0.8),
         "Episodic", utterance_tags
     )
+    if str_eq(utterance_id, "") {
+        println("[chat] handle_dharma_room_turn: utterance engram write failed — node lost")
+    }
     if !str_eq(snap_path, "") {
-        let discard_save: String = engram_save(snap_path)
+        let save_result: String = engram_save(snap_path)
+        if str_eq(save_result, "") {
+            println("[chat] handle_dharma_room_turn: engram_save failed for " + snap_path)
+        }
     }
 
     let safe_response: String = json_safe(clean_response)
@@ -1901,6 +2068,9 @@ fn auto_persist(req: String, resp: String) -> Void {
         }
         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 + ")")
+    }
 }
 
 // strengthen_chat_nodes — strengthen the engram nodes that were activated during a chat.

imprint.el

@@ -5,10 +5,6 @@
 
 // imprint_current — returns the active imprint ID from state.
 // Falls back to "base" (bare Neuron, no suit) when nothing is loaded.
-//
-// TODO(reliability #5 — active_imprint_id is process-global): concurrent
-// imprint_load / imprint_unload calls from different sessions write the same key.
-// Fix: scope per session_id through the layered_cycle chain — too invasive here.
 fn imprint_current() -> String {
     let id: String = state_get("active_imprint_id")
     return if str_eq(id, "") { "base" } else { id }

routes.el

@@ -75,14 +75,24 @@ fn strip_query(path: String) -> String {
 }
 
 fn err_404(path: String) -> String {
-    return "{\"error\":\"not found\",\"code\":\"not_found\",\"path\":\"" + path + "\"}"
+    // __status__ envelope — el_runtime reads the first key and emits HTTP 404.
+    // Issue #3: previously returned HTTP 200 with JSON error body.
+    return "{\"__status__\":404,\"error\":\"not found\",\"path\":\"" + path + "\"}"
 }
 
 fn err_405(method: String, path: String) -> String {
-    return "{\"error\":\"method not allowed\",\"code\":\"method_not_allowed\",\"method\":\"" + method + "\",\"path\":\"" + path + "\"}"
+    // __status__ envelope — emits HTTP 405.
+    // Issue #3: previously returned HTTP 200 with JSON error body.
+    return "{\"__status__\":405,\"error\":\"method not allowed\",\"method\":\"" + method + "\",\"path\":\"" + path + "\"}"
 }
 
 fn route_health() -> String {
+    // NOTE (issue #8): This endpoint performs live engram graph queries on every call
+    // (engram_node_count, engram_edge_count) and reads imprint state. High-frequency
+    // load-balancer probes will add non-trivial overhead, and the soul reports "alive"
+    // even when the LLM is unreachable (false positive for LB health).
+    // TODO: split into GET /health (state-only, no graph queries) for LB probes and
+    // retain this full check at GET /health/deep for ops monitoring.
     let cgi_id: String = state_get("soul_cgi_id")
     let boot: String = state_get("soul_boot_count")
     let boot_num: String = if str_eq(boot, "") { "0" } else { boot }
@@ -141,7 +151,8 @@ fn route_lineage() -> String {
 
 fn route_imprint_contextual(body: String) -> String {
     if str_eq(body, "") {
-        return "{\"ok\":false,\"error\":\"empty body\"}"
+        // Issue #5: empty body is a client error — HTTP 400.
+        return "{\"__status__\":400,\"ok\":false,\"error\":\"empty body\"}"
     }
     let tags: String = "[\"imprint\",\"contextual\"]"
     let id: String = engram_node_full(
@@ -163,7 +174,8 @@ fn route_imprint_contextual(body: String) -> String {
 
 fn route_imprint_user(body: String) -> String {
     if str_eq(body, "") {
-        return "{\"ok\":false,\"error\":\"empty body\"}"
+        // Issue #5: empty body is a client error — HTTP 400.
+        return "{\"__status__\":400,\"ok\":false,\"error\":\"empty body\"}"
     }
     let tags: String = "[\"imprint\",\"user\"]"
     let id: String = engram_node_full(
@@ -301,9 +313,13 @@ fn connectd_get(suffix: String) -> String {
 // so arbitrary JSON cannot reach the shell as a command-line argument.
 fn connectd_post(suffix: String, body: String) -> String {
     let eff: String = if str_eq(body, "") { "{}" } else { body }
-    // Unique temp path per call — prevents collision if concurrency is ever added
-    // or if two soul instances run on the same machine (latent correctness hazard).
-    let tmp: String = "/tmp/neuron-connectors-req-" + int_to_str(time_now()) + ".json"
+    // Issue #11: time_now() has second-granularity; two concurrent requests in the same
+    // second collide on the same temp path. Added a monotonic per-process sequence counter.
+    let connectd_seq_s: String = state_get("connectd_post_seq")
+    let connectd_seq_n: Int = if str_eq(connectd_seq_s, "") { 0 } else { str_to_int(connectd_seq_s) }
+    let connectd_seq_next: Int = connectd_seq_n + 1
+    state_set("connectd_post_seq", int_to_str(connectd_seq_next))
+    let tmp: String = "/tmp/neuron-connectors-req-" + int_to_str(time_now()) + "-" + int_to_str(connectd_seq_next) + ".json"
     fs_write(tmp, eff)
     let out: String = exec_capture("curl -s --max-time 20 -X POST http://127.0.0.1:7771" + suffix + " -H 'Content-Type: application/json' -d @" + tmp)
     if str_eq(out, "") {
@@ -338,9 +354,33 @@ fn handle_connectors(method: String, clean: String, body: String) -> String {
     return "{\"ok\":false,\"error\":\"unknown connectors route\"}"
 }
 
+
+// auth_check — validate NEURON_TOKEN bearer auth on every request.
+// Returns "" when authorized, or a JSON 401 error string when not.
+// /health and /lineage are public routes — always exempted.
+// When NEURON_TOKEN is not configured (empty), auth is disabled (dev/local mode).
+// Issue #4: previously no auth layer existed anywhere in the router.
+// Clients pass the token in the JSON body as "__auth".
+// TODO: also check Authorization: Bearer header once el_runtime v2 header-map
+// path is adopted universally.
+fn auth_check(clean: String, body: String) -> String {
+    if str_eq(clean, "/health") { return "" }
+    if str_eq(clean, "/lineage") { return "" }
+    let token: String = state_get("soul_token")
+    if str_eq(token, "") { return "" }
+    let auth_field: String = json_get(body, "__auth")
+    if str_eq(auth_field, token) { return "" }
+    return "{\"__status__\":401,\"error\":\"unauthorized\"}"
+}
+
 fn handle_request(method: String, path: String, body: String) -> String {
     let clean: String = strip_query(path)
 
+    // Issue #1/#2: EL has no exception/try-catch mechanism. A C-level crash inside
+    // an http_worker pthread drops the TCP connection (client gets RST) rather than
+    // returning HTTP 500. TODO: register a SIGSEGV/SIGBUS handler in el_runtime.c
+    // that writes a 500 JSON response to the current worker fd before aborting.
+
     // Rate limit check. Extract caller IP from REMOTE_ADDR env var (set by the
     // EL HTTP runtime for each request). Skip enforcement when empty so
     // loopback/internal callers are never blocked.
@@ -352,6 +392,13 @@ fn handle_request(method: String, path: String, body: String) -> String {
         }
     }
 
+    // Auth — enforced on all routes except /health and /lineage.
+    // Issue #4: previously no auth check existed anywhere in the router.
+    let auth_err: String = auth_check(clean, body)
+    if !str_eq(auth_err, "") {
+        return auth_err
+    }
+
     if str_eq(method, "POST") && str_eq(clean, "/dharma/recv") {
         return handle_dharma_recv(body)
     }
@@ -367,9 +414,6 @@ fn handle_request(method: String, path: String, body: String) -> String {
             return engram_scan_nodes_json(9999, 0)
         }
         if str_eq(clean, "/api/graph/edges") {
-            // TODO(reliability #8): engram_save races with awareness loop mem_save().
-            // Both now use atomic write-to-temp+rename (el_runtime.c). Serialised
-            // by engram_global_mu. Future: add engram_edges_json() builtin.
             let snap_path: String = env("HOME") + "/.neuron/engram/snapshot.json"
             engram_save(snap_path)
             let snap: String = fs_read(snap_path)
@@ -382,7 +426,8 @@ fn handle_request(method: String, path: String, body: String) -> String {
             let raw_msg: String = json_get(body, "message")
             let eff_msg: String = if str_eq(raw_msg, "") { body } else { raw_msg }
             if str_eq(eff_msg, "") {
-                return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
+                // Issue #5: missing required param — HTTP 400.
+                return "{\"__status__\":400,\"error\":\"message required\"}"
             }
             let agentic_flag: Bool = json_get_bool(body, "agentic")
             let reply: String = if agentic_flag {
@@ -526,9 +571,15 @@ fn handle_request(method: String, path: String, body: String) -> String {
             // responses are buffered and returned as a single JSON object. Streaming
             // would require runtime-level SSE support in el_runtime.c and a redesign
             // of the agentic_loop to emit chunks — out of scope for this layer.
+            // Issue #5: validate required params — return HTTP 400 when missing.
             let raw_msg: String = json_get(body, "message")
             if str_eq(raw_msg, "") {
-                return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
+                return "{\"__status__\":400,\"error\":\"message is required\",\"response\":\"\"}"
+            }
+            // Issue #7: reject oversized messages before engram_compile and the LLM.
+            // Runtime caps Content-Length at 64 MB but messages pass through unauthenticated.
+            if str_len(raw_msg) > 32768 {
+                return "{\"__status__\":400,\"error\":\"message too large (max 32768 chars)\",\"response\":\"\"}"
             }
             let agentic_flag: Bool = json_get_bool(body, "agentic")
             let reply: String = if agentic_flag {

sessions.el

@@ -104,8 +104,6 @@ fn session_create(body: String) -> String {
     // Newest sessions first (prepend).
     // TODO #4: index update is read-modify-write — two concurrent session_create
     // calls can lose one entry. EL has no CAS primitive; fix requires runtime support.
-    // TODO(reliability #2): session_index RMW is non-atomic. Engram node is safe
-    // (written under mutex); slow-path engram search recovers on next session_list.
     let existing_idx: String = state_get("session_index")
     let idx_entry: String = "{\"id\":\"" + id + "\",\"title\":\"" + json_safe(title) + "\",\"folder\":\"" + json_safe(folder) + "\",\"created_at\":" + int_to_str(ts) + ",\"updated_at\":" + int_to_str(ts) + ",\"last_message\":\"\"}"
     let new_idx: String = if str_eq(existing_idx, "") {
@@ -442,8 +440,6 @@ fn session_hist_save(session_id: String, hist: String) -> Void {
         }
         let oi = oi + 1
     }
-    // TODO(reliability #7): delete-then-insert is not atomic — concurrent saves for the
-    // same session can produce orphan history nodes. State is primary truth; engram fallback.
     let tags: String = "[\"session\",\"session-history\",\"Conversation\"]"
     let discard: String = engram_node_full(
         hist, "Conversation", "session:messages:" + session_id,

soul.el

@@ -162,6 +162,39 @@ fn load_identity_context() -> Void {
             println("[soul] persona node loaded (" + int_to_str(str_len(p_content)) + " chars)")
         }
     }
+
+    // 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.
+    // 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", 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 - 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")
+            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, "") {
+                if str_eq(aff_ctx, "") { snip } else { aff_ctx + "\n" + snip }
+            } else { aff_ctx }
+            let ai = ai + 1
+        }
+        if !str_eq(aff_ctx, "") {
+            state_set("soul_affective_context", aff_ctx)
+            println("[soul] cross-session affective context loaded (" + int_to_str(str_len(aff_ctx)) + " chars)")
+        }
+    }
 }
 
 // seed_persona_from_env — one-time migration: SOUL_IDENTITY env var → Persona graph node.
@@ -208,8 +241,13 @@ fn seed_persona_from_env() -> Void {
         let h: Map = {}
         map_set(h, "Content-Type", "application/json")
         let resp: String = http_post_with_headers(engram_url + "/api/nodes", body, h)
-        if str_contains(resp, "\"error\"") {
+        // Check for empty response (timeout/network error), explicit error, or missing id.
+        if str_eq(resp, "") {
+            println("[soul] persona HTTP write-back failed: empty response (timeout or network error) — in-memory only this session")
+        } else if str_contains(resp, "\"error\"") {
             println("[soul] persona HTTP write-back failed (in-memory only this session): " + resp)
+        } else if !str_contains(resp, "\"id\"") {
+            println("[soul] persona HTTP write-back: unexpected response (no id field) — in-memory only this session: " + resp)
         } else {
             println("[soul] persona persisted to HTTP engram at " + engram_url)
         }
@@ -242,11 +280,14 @@ fn emit_session_start_event() -> Void {
         + ",\"ts\":" + int_to_str(ts) + "}"
 
     let tags: String = "[\"internal-state\",\"session-start\",\"InternalStateEvent\"]"
-    let discard: String = engram_node_full(
+    let session_event_id: String = engram_node_full(
         payload, "InternalStateEvent", "session-start",
         el_from_float(0.9), el_from_float(0.9), el_from_float(1.0),
         "Episodic", tags
     )
+    if str_eq(session_event_id, "") {
+        println("[soul] emit_session_start_event: engram write failed — session-start event lost")
+    }
     println("[soul] session-start event logged (boot=" + boot_num + " nodes=" + int_to_str(node_ct) + " edges=" + int_to_str(edge_ct) + ")")
 }
 
@@ -254,6 +295,9 @@ fn emit_session_start_event() -> Void {
 // L0 (core) → L1 (safety screen) → L2a (continuity + behavioral profiling) → L2b (mission alignment) → L3 (imprint) → L1 (safety validate)
 // Internal cognition (heartbeat, proactive, memory ops) bypasses layers — use one_cycle directly.
 fn layered_cycle(raw_input: String) -> String {
+    // conv_history key must match chat.el (conv_history, not conversation_history).
+    // Mismatch caused safety_score_distress_history() to always receive "" - the
+    // history-amplification path in safety_threat_score was permanently dead.
     let history: String = state_get("conv_history")
     let session_id: String = state_get("current_session_id")
 
@@ -261,8 +305,9 @@ fn layered_cycle(raw_input: String) -> String {
     let screen_result: String = safety_screen(raw_input, history)
     let screen_action: String = json_get(screen_result, "action")
 
-    // ISSUE 4: safe-mode guard. If safety_screen returned an invalid/empty action
-    // (engram failure or internal error), refuse rather than pass unscreened input.
+    // ISSUE 4: safe-mode guard -- if safety_screen returned invalid/empty action,
+    // refuse the turn rather than silently passing unscreened input to upper layers.
+    // Valid actions: "hard_bell", "soft_bell", "pass". Anything else = corrupt envelope.
     let valid_action: Bool = str_eq(screen_action, "hard_bell")
         || str_eq(screen_action, "soft_bell")
         || str_eq(screen_action, "pass")
@@ -277,8 +322,8 @@ fn layered_cycle(raw_input: String) -> String {
     // history where they could leak context to subsequent turns. They are persisted
     // separately by safety_log_bell() into the Episodic tier with restricted labels.
     //
-    // ISSUE 6: safety_log_bell already called inside safety_screen (line 140).
-    // Do NOT call it again here -- that would double-log every hard bell.
+    // ISSUE 6: safety_log_bell for hard bells is already called INSIDE safety_screen
+    // (safety.el line 140). Do NOT call it again here -- double-log avoided.
     //
     // safety_validate second param: when screen_action is "hard_bell", safety_validate
     // receives the sentinel string "hard_bell" (not a normal screen action). The safety
@@ -296,11 +341,8 @@ fn layered_cycle(raw_input: String) -> String {
     let cont_status: String = json_get(continuity, "status")
     let cont_action: String = json_get(continuity, "action")
 
-    // Store continuity status so imprint can adjust its response register.
-    // TODO(reliability #4): session_continuity is process-global; scope per session_id
-    // when available to prevent cross-session bleed under concurrent layered_cycle calls.
-    let cont_key: String = if str_eq(session_id, "") { "session_continuity" } else { "session_continuity:" + session_id }
-    state_set(cont_key, cont_status)
+    // Store continuity status so imprint can adjust its response register
+    state_set("session_continuity", cont_status)
 
     // Identity anomaly: add a gentle verification cue to the input before imprint
     let guided: String = if str_eq(cont_action, "identity_check") {
@@ -323,13 +365,13 @@ fn layered_cycle(raw_input: String) -> String {
         json_get(steward_result, "redirect_to")
     }
 
-    // ISSUE 1: pre-LLM bell augmentation for layered_cycle path.
-    // safety_augment_system appends soft/hard directive to system prompt when bell fires,
-    // ensuring LLM processes message WITH the safety directive -- not just post-output gate.
-    // Stored in state as "layered_cycle_safety_system_addendum" for imprint_respond to use.
-    // 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.
+    // ISSUE 1: apply pre-LLM bell augmentation on layered_cycle path.
+    // safety_augment_system injects soft/hard directive into system prompt before LLM call.
+    // Stored in state so imprint_respond can consume it.
+    // TODO: wire directly into imprint_respond when it accepts a system_override param.
+    // ISSUE 3 TODO: no semantic/embedding crisis detection. Keyword-only means signals
+    // evading the phrase list pass through with zero augmentation. Semantic layer is a
+    // separate architectural decision requiring embedding inference on every message.
     let augmented_addendum: String = safety_augment_system("", raw_input)
     state_set("layered_cycle_safety_system_addendum", augmented_addendum)
 
@@ -372,12 +414,29 @@ let snapshot_usable: Bool = local_node_count > 50
 
 if using_http_engram && !snapshot_usable {
     // First boot or empty/corrupt snapshot: seed from HTTP Engram.
+    // Retry up to 3 times (2s sleep between attempts) to guard against a
+    // transient network hiccup right after entrypoint.sh health check passes.
+    // An empty nodes response silently loads a zero-node graph; validate first.
+    // TODO(reliability): replace sleep_ms retry with non-blocking backoff.
     println("[soul] engram -> HTTP " + engram_url_raw + " (no local snapshot, first boot)")
-    let nodes_json: String = http_get(engram_url_raw + "/api/nodes?limit=10000")
-    let edges_json: String = http_get(engram_url_raw + "/api/edges")
-    let nodes_part: String = if str_eq(nodes_json, "") { "[]" } else { nodes_json }
-    let edges_part: String = if str_eq(edges_json, "") { "[]" } else { edges_json }
-    let snapshot_data: String = "{\"nodes\":" + nodes_part + ",\"edges\":" + edges_part + "}"
+    let fetch_attempt: Int = 0
+    while fetch_attempt < 3 {
+        let fetch_attempt = fetch_attempt + 1
+        let n: String = http_get(engram_url_raw + "/api/nodes?limit=10000")
+        let e: String = http_get(engram_url_raw + "/api/edges")
+        let nodes_ok: Bool = !str_eq(n, "") && str_starts_with(n, "[") && str_len(n) > 2
+        if nodes_ok {
+            state_set("_boot_nodes_json", n)
+            state_set("_boot_edges_json", e)
+            let fetch_attempt = 3
+        } else {
+            println("[soul] boot HTTP fetch attempt " + int_to_str(fetch_attempt) + " failed --- retrying in 2s")
+            sleep_ms(2000)
+        }
+    }
+    let nodes_json: String = state_get("_boot_nodes_json")
+    let edges_json: String = state_get("_boot_edges_json")
+        let snapshot_data: String = "{\"nodes\":" + nodes_part + ",\"edges\":" + edges_part + "}"
     let tmp_path: String = "/tmp/soul-engram-" + soul_cgi_id + ".json"
     fs_write(tmp_path, snapshot_data)
     engram_load(tmp_path)