fix(context-dedup): include scan_part and affective_part IDs in seen set

Two design bugs in the state_set placement caused the dedup seen-ID set
to be incomplete even with callsites wired up:

1. state_set("engram_compile_seen_ids") was called immediately after
   merging the main node pools, before scan_part (persona fallback) and
   affective_part (bell node) were computed. Nodes appearing only in
   those segments were never added to the seen set.

2. affective_part is a bare JSON object (bn0 from json_array_get), not
   a JSON array. Passing it to engram_extract_ids would have gotten
   json_array_len == 0 and silently skipped the affective node's ID.

Fix: move state_set to after ctx is assembled from all three segments.
Extract ids_from_merged and ids_from_scan via engram_extract_ids (both
are JSON arrays), and extract ids_from_affective via json_get(affective_part, "id")
directly since it is a bare object. Merge all three via add_to_seen
before publishing to state.

awareness.el

@@ -23,14 +23,11 @@ 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 local_id: String = engram_node_full(
+        let discard: 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.
@@ -43,32 +40,7 @@ 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 + "\"}"
-    // 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")
-    }
+    let discard: String = http_post_json(engram_url + "/api/neuron/state-events", body)
     return ""
 }
 
@@ -568,14 +540,9 @@ fn awareness_run() -> Void {
         let should_refresh: Bool = refresh_elapsed >= refresh_ms
         if should_refresh {
             let engram_url: String = state_get("soul_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 {
+            if !str_eq(engram_url, "") {
                 let sync_json: String = http_get(engram_url + "/api/sync")
-                if !str_eq(sync_json, "") && !str_eq(sync_json, "{}") && !str_starts_with(sync_json, "{\"error\":") {
+                if !str_eq(sync_json, "") && !str_eq(sync_json, "{}") {
                     let cgi_id: String = state_get("soul_cgi_id")
                     let tmp: String = "/tmp/soul-sync-" + cgi_id + ".json"
                     fs_write(tmp, sync_json)
@@ -711,6 +678,8 @@ 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)

imprint.el

@@ -5,6 +5,10 @@
 
 // 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 }

memory.el

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

routes.el

@@ -75,24 +75,14 @@ fn strip_query(path: String) -> String {
 }
 
 fn err_404(path: String) -> String {
-    // __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 + "\"}"
+    return "{\"error\":\"not found\",\"code\":\"not_found\",\"path\":\"" + path + "\"}"
 }
 
 fn err_405(method: String, path: String) -> String {
-    // __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 + "\"}"
+    return "{\"error\":\"method not allowed\",\"code\":\"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 }
@@ -151,8 +141,7 @@ fn route_lineage() -> String {
 
 fn route_imprint_contextual(body: String) -> String {
     if str_eq(body, "") {
-        // Issue #5: empty body is a client error — HTTP 400.
-        return "{\"__status__\":400,\"ok\":false,\"error\":\"empty body\"}"
+        return "{\"ok\":false,\"error\":\"empty body\"}"
     }
     let tags: String = "[\"imprint\",\"contextual\"]"
     let id: String = engram_node_full(
@@ -174,8 +163,7 @@ fn route_imprint_contextual(body: String) -> String {
 
 fn route_imprint_user(body: String) -> String {
     if str_eq(body, "") {
-        // Issue #5: empty body is a client error — HTTP 400.
-        return "{\"__status__\":400,\"ok\":false,\"error\":\"empty body\"}"
+        return "{\"ok\":false,\"error\":\"empty body\"}"
     }
     let tags: String = "[\"imprint\",\"user\"]"
     let id: String = engram_node_full(
@@ -313,13 +301,9 @@ 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 }
-    // 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"
+    // 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"
     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, "") {
@@ -354,33 +338,9 @@ 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.
@@ -392,13 +352,6 @@ 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)
     }
@@ -414,6 +367,9 @@ 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)
@@ -426,8 +382,7 @@ 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, "") {
-                // Issue #5: missing required param — HTTP 400.
-                return "{\"__status__\":400,\"error\":\"message required\"}"
+                return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
             }
             let agentic_flag: Bool = json_get_bool(body, "agentic")
             let reply: String = if agentic_flag {
@@ -571,15 +526,9 @@ 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 "{\"__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\":\"\"}"
+                return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
             }
             let agentic_flag: Bool = json_get_bool(body, "agentic")
             let reply: String = if agentic_flag {

sessions.el

@@ -104,6 +104,8 @@ 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, "") {
@@ -440,6 +442,8 @@ 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

@@ -162,56 +162,6 @@ 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.
-    // Recency guard: nodes older than 14 days (1,209,600 seconds) are skipped.
-    // Unified at 14 days with chat.el engram_compile and handle_chat affective checks
-    // so all three paths present consistent affective context. The previous 7-day
-    // (604800s) window was inconsistent with the 72h chat.el window, causing
-    // conflicting context: soul.el loaded a 5-day-old crisis node while chat.el
-    // did not include it on subsequent turns. Both now use 14 days.
-    // Results capped at 3 nodes, 200 chars each, to limit context inflation.
-    // TODO(recency): engram_search_json sorts by relevance, not timestamp. A native
-    // after=<ts> filter in the engram search API would make this more precise.
-    let affective_raw: String = engram_search_json("distress crisis upset hopeless bell BellEvent", 3)
-    let affective_ok: Bool = !str_eq(affective_raw, "") && !str_eq(affective_raw, "[]")
-    if affective_ok {
-        let ts_now: Int = time_now()
-        let ts_cutoff: Int = ts_now - 1209600
-        let aff_total: Int = json_array_len(affective_raw)
-        let aff_ctx: String = ""
-        let ai: Int = 0
-        while ai < aff_total {
-            let aff_node: String = json_array_get(affective_raw, ai)
-            let aff_content: String = json_get(aff_node, "content")
-            // Use created_at (the standard engram node timestamp field), consistent
-            // with handle_chat which reads created_at / updated_at. The previous
-            // field name "ts" is not a standard engram field: it was present in some
-            // BellEvent content payloads but absent from standard engram node JSON,
-            // causing json_get to return "" and the fallback to ts_now — meaning ALL
-            // nodes with a missing "ts" field appeared recent, over-including stale
-            // content. With the 14-day window, this amplification was significant.
-            // Fix: read created_at first, fall back to updated_at, then default to 0
-            // (same as handle_chat). A ts of 0 always fails the cutoff check, so nodes
-            // missing both timestamp fields are conservatively excluded rather than
-            // blindly included.
-            let aff_ca: String = json_get(aff_node, "created_at")
-            let aff_ts_str: String = if str_eq(aff_ca, "") { json_get(aff_node, "updated_at") } else { aff_ca }
-            let aff_ts: Int = if str_eq(aff_ts_str, "") { 0 } else { str_to_int(aff_ts_str) }
-            let 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.
@@ -258,13 +208,8 @@ 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)
-        // 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\"") {
+        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)
         }
@@ -297,14 +242,11 @@ fn emit_session_start_event() -> Void {
         + ",\"ts\":" + int_to_str(ts) + "}"
 
     let tags: String = "[\"internal-state\",\"session-start\",\"InternalStateEvent\"]"
-    let session_event_id: String = engram_node_full(
+    let discard: 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) + ")")
 }
 
@@ -312,9 +254,6 @@ 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")
 
@@ -322,9 +261,8 @@ 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 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.
+    // ISSUE 4: safe-mode guard. If safety_screen returned an invalid/empty action
+    // (engram failure or internal error), refuse rather than pass unscreened input.
     let valid_action: Bool = str_eq(screen_action, "hard_bell")
         || str_eq(screen_action, "soft_bell")
         || str_eq(screen_action, "pass")
@@ -339,8 +277,8 @@ 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 for hard bells is already called INSIDE safety_screen
-    // (safety.el line 140). Do NOT call it again here -- double-log avoided.
+    // 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.
     //
     // 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
@@ -358,8 +296,11 @@ 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
-    state_set("session_continuity", cont_status)
+    // 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)
 
     // Identity anomaly: add a gentle verification cue to the input before imprint
     let guided: String = if str_eq(cont_action, "identity_check") {
@@ -382,13 +323,13 @@ fn layered_cycle(raw_input: String) -> String {
         json_get(steward_result, "redirect_to")
     }
 
-    // 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.
+    // 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.
     let augmented_addendum: String = safety_augment_system("", raw_input)
     state_set("layered_cycle_safety_system_addendum", augmented_addendum)
 
@@ -431,29 +372,12 @@ 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 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 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 tmp_path: String = "/tmp/soul-engram-" + soul_cgi_id + ".json"
     fs_write(tmp_path, snapshot_data)
     engram_load(tmp_path)