fix(reliability): state management

soul.el

@@ -162,39 +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.
-    // 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.
@@ -241,13 +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)
         }
@@ -280,14 +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) + ")")
 }
 
@@ -295,9 +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")
 
@@ -305,9 +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")
@@ -322,8 +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
@@ -341,8 +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") {
@@ -365,13 +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)
 
@@ -414,29 +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)