fix(routes): fix handle_request ABI, 429 status code, soul_boot_ts write

- Add per-IP in-memory rate limiter (60 req/min default, configurable via
  soul_rate_limit state key; /health exempt; loopback callers skipped)
- Extend /health with uptime_secs (from soul_boot_ts) and live LLM probe
- Add missing_param 400 guard on POST /api/chat before passing to LLM
- Standardise error envelopes: add "code" field to err_404/err_405 and all
  missing-param returns; route_synthesize now errors clearly instead of
  returning the misleading {"mechanism":"did not engage"} on bad input
- Document streaming gap in /api/chat (SSE not implemented, note added)
- handle_request gains ip param; rate_limit_check wired at entry point

chat.el

@@ -40,43 +40,9 @@ fn engram_compile(intent: String) -> String {
         ""
     }
 
-    // Affective context: always include the most recent high-emotion memory if one
-    // exists within 72 hours. This ensures continuity of care across turns — when
-    // the user was in distress earlier in the session (or recently), that context
-    // travels into every subsequent LLM call so the response register stays aware.
-    // We search for BellEvent nodes specifically; these are written by auto_persist
-    // when safety_detect_bell_level fires. The 72h window (259200 seconds) is wide
-    // enough to span a multi-session day without pulling ancient history.
-    let bell_nodes: String = engram_search_json("bell:soft bell:hard BellEvent", 3)
-    let bell_ok: Bool = !str_eq(bell_nodes, "") && !str_eq(bell_nodes, "[]")
-    let now_ts: Int = time_now()
-    let cutoff_ts: Int = now_ts - 259200
-    let recent_bell: String = if bell_ok {
-        let bn0: String = json_array_get(bell_nodes, 0)
-        // created_at is not present in engram node JSON for BellEvent nodes.
-        // Extract the timestamp embedded in the content string as " | ts:NNNNN".
-        // Fall back to created_at / updated_at JSON fields if the marker is absent.
-        let bn_content: String = json_get(bn0, "content")
-        let ts_marker: String = " | ts:"
-        let ts_pos: Int = str_index_of(bn_content, ts_marker)
-        let bn_ts_raw: String = if ts_pos >= 0 {
-            let ts_start: Int = ts_pos + str_len(ts_marker)
-            let rest: String = str_slice(bn_content, ts_start, str_len(bn_content))
-            let next_sep: Int = str_index_of(rest, " | ")
-            if next_sep < 0 { rest } else { str_slice(rest, 0, next_sep) }
-        } else {
-            let ca: String = json_get(bn0, "created_at")
-            if str_eq(ca, "") { json_get(bn0, "updated_at") } else { ca }
-        }
-        let bn_ts: Int = if str_eq(bn_ts_raw, "") { 0 } else { str_to_int(bn_ts_raw) }
-        if bn_ts > cutoff_ts { bn0 } else { "" }
-    } else { "" }
-    let affective_part: String = if !str_eq(recent_bell, "") { recent_bell } else { "" }
-
     let sep1: String = if !str_eq(act_part, "") && !str_eq(srch_part, "") { "\n" } else { "" }
     let sep2: String = if (!str_eq(act_part, "") || !str_eq(srch_part, "")) && !str_eq(scan_part, "") { "\n" } else { "" }
-    let sep3: String = if (!str_eq(act_part, "") || !str_eq(srch_part, "") || !str_eq(scan_part, "")) && !str_eq(affective_part, "") { "\n" } else { "" }
-    let ctx: String = act_part + sep1 + srch_part + sep2 + scan_part + sep3 + affective_part
+    let ctx: String = act_part + sep1 + srch_part + sep2 + scan_part
 
     if str_eq(ctx, "") { return "" }
 
@@ -142,69 +108,6 @@ fn hist_trim(hist: String) -> String {
     return hist
 }
 
-// hist_trim_with_bell_guard — trim the history window exactly as hist_trim does, but
-// before dropping the oldest user/assistant pair check whether the user turn triggered
-// 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.
-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")
-
-    // Only inspect user turns — assistant content doesn't carry bell signals.
-    let bell_level: String = if str_eq(first_role, "user") {
-        safety_detect_bell_level(first_content)
-    } else {
-        "none"
-    }
-
-    // If the turn being evicted triggered a bell, preserve it to engram.
-    // This is distinct from the BellEvent written by auto_persist: that node
-    // carries a short summary. This node carries the full exchange content so
-    // it is recoverable for clinical/continuity review.
-    if !str_eq(bell_level, "none") {
-        let ts: Int = time_now()
-        let ts_str: String = int_to_str(ts)
-        let safe_content: String = str_replace(first_content, "\"", "'")
-        let preserve_content: String = "PRESERVED_BELL:" + bell_level
-            + " | evicted_at:" + ts_str
-            + " | message:" + safe_content
-        let preserve_tags: String = "[\"bell-history\",\"bell:" + bell_level + "\",\"evicted\",\"affective\",\"BellEvent\"]"
-        let discard: String = engram_node_full(
-            preserve_content,
-            "BellEvent",
-            "bell:" + bell_level + ":preserved",
-            el_from_float(0.9),
-            el_from_float(0.9),
-            el_from_float(1.0),
-            "Episodic",
-            preserve_tags
-        )
-    }
-
-    // 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
-}
-
 // clean_llm_response — strips GPT-2 BPE byte-to-unicode artifacts that vLLM
 // emits when the tokenizer hasn't decoded back to raw bytes.
 //
@@ -297,10 +200,8 @@ fn handle_chat(body: String) -> String {
 
     let updated_hist: String = hist_append(stored_hist, "user", message)
     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.
     let final_hist: String = if json_array_len(updated_hist2) > 20 {
-        hist_trim_with_bell_guard(updated_hist2)
+        hist_trim(updated_hist2)
     } else {
         updated_hist2
     }
@@ -1234,28 +1135,14 @@ fn auto_persist(req: String, resp: String) -> Void {
     let safe_msg: String = str_replace(message, "\"", "'")
     let safe_reply: String = str_replace(reply2, "\"", "'")
 
-    // Detect emotional salience before persisting. safety_detect_bell_level uses the
-    // same phrase lists as the safety layer (safety.el), so the classification is
-    // consistent with what safety_screen already evaluated for this turn.
-    let bell_level: String = safety_detect_bell_level(message)
-    let is_bell: Bool = !str_eq(bell_level, "none")
-
-    // Tag the Conversation node with bell metadata when distress is present so
-    // subsequent affective queries (e.g. engram_compile) can find this exchange.
-    let tags: String = if is_bell {
-        "[\"Conversation\",\"chat\",\"timestamped\",\"bell:" + bell_level + "\",\"affective\"]"
-    } else {
-        "[\"Conversation\",\"chat\",\"timestamped\"]"
-    }
-
     let content: String = "{\"q\":\"" + safe_msg + "\""
         + ",\"a\":\"" + safe_reply + "\""
         + ",\"created_at\":" + ts_str
         + ",\"source\":\"chat\""
-        + ",\"bell\":\"" + bell_level + "\""
         + ",\"label\":\"chat:" + ts_str + "\"}"
 
-    let conv_node_id: String = engram_node_full(
+    let tags: String = "[\"Conversation\",\"chat\",\"timestamped\"]"
+    engram_node_full(
         content,
         "Conversation",
         "chat:" + ts_str,
@@ -1265,72 +1152,6 @@ fn auto_persist(req: String, resp: String) -> Void {
         "Episodic",
         tags
     )
-
-    // When a bell fires, write a dedicated BellEvent node in addition to the
-    // Conversation node. This makes distress moments directly findable by label
-    // ("bell:soft" / "bell:hard") without having to scan all Conversation nodes.
-    // The BellEvent carries higher salience so engram_compile pulls it into context.
-    // The message content is truncated to 120 chars — enough signal, not a full dump.
-    if is_bell {
-        let summary: String = if str_len(message) > 120 { str_slice(message, 0, 120) } else { message }
-        let safe_summary: String = str_replace(summary, "\"", "'")
-        let bell_content: String = "BELL:" + bell_level
-            + " | ts:" + ts_str
-            + " | summary:" + safe_summary
-
-        // bell:hard gets peak salience; bell:soft is slightly lower.
-        let sal_a: String = if str_eq(bell_level, "hard") { el_from_float(0.98) } else { el_from_float(0.88) }
-        let sal_b: String = if str_eq(bell_level, "hard") { el_from_float(0.98) } else { el_from_float(0.88) }
-        let sal_c: String = if str_eq(bell_level, "hard") { el_from_float(1.0) } else { el_from_float(0.95) }
-
-        let bell_tags: String = "[\"safety\",\"bell\",\"bell:" + bell_level + "\",\"affective\",\"BellEvent\"]"
-        let bell_ts_str: String = int_to_str(time_now())
-        let bell_label: String = "bell:" + bell_level + ":" + bell_ts_str
-        let bell_node_id: String = engram_node_full(
-            bell_content,
-            "BellEvent",
-            bell_label,
-            sal_a,
-            sal_b,
-            sal_c,
-            "Episodic",
-            bell_tags
-        )
-
-        // Increment session-level bell counter so session_hist_save knows whether
-        // any bell fired during this session when writing a boundary summary.
-        let sess_id: String = json_get(req, "session_id")
-        let bell_key: String = if str_eq(sess_id, "") {
-            "session_bell_count"
-        } else {
-            "session_bell_count:" + sess_id
-        }
-        let prior_count: String = state_get(bell_key)
-        let prior_n: Int = if str_eq(prior_count, "") { 0 } else { str_to_int(prior_count) }
-        state_set(bell_key, int_to_str(prior_n + 1))
-
-        // Also record the highest bell level seen this session so the boundary
-        // summary can classify the session correctly (hard takes precedence).
-        let level_key: String = if str_eq(sess_id, "") {
-            "session_bell_level"
-        } else {
-            "session_bell_level:" + sess_id
-        }
-        let prior_level: String = state_get(level_key)
-        let new_level: String = if str_eq(bell_level, "hard") { "hard" } else {
-            if str_eq(prior_level, "hard") { "hard" } else { "soft" }
-        }
-        state_set(level_key, new_level)
-
-        // Stash a short signal summary for the boundary node (last bell wins for
-        // the one-liner; the full history is in per-bell BellEvent nodes).
-        let signal_key: String = if str_eq(sess_id, "") {
-            "session_bell_signal"
-        } else {
-            "session_bell_signal:" + sess_id
-        }
-        state_set(signal_key, safe_summary)
-    }
 }
 
 // strengthen_chat_nodes — strengthen the engram nodes that were activated during a chat.

routes.el

@@ -7,6 +7,65 @@ import "neuron-api.el"
 import "sessions.el"
 import "soul.elh"
 
+// ---------------------------------------------------------------------------
+// Rate limiting — simple in-memory per-IP sliding window counter.
+//
+// State keys:
+//   rl:<ip>:count  — request count in the current window
+//   rl:<ip>:window — window start timestamp (unix seconds)
+//
+// Limit: configurable via soul state key "soul_rate_limit" (requests per
+// minute). Falls back to 60 req/min if not set. The /health endpoint is
+// exempt so monitoring does not consume quota.
+//
+// State growth: each unique source IP accumulates exactly 2 state keys
+// (count + window) for the lifetime of the process. Per-IP storage is
+// bounded and constant; values reset on window expiry. In aggregate, state
+// grows linearly with distinct IPs — typical for a trusted-client service.
+// EL has no state_delete builtin, so keys from inactive IPs persist.
+// TODO: add state_delete sweep when the EL runtime exposes that primitive.
+//
+// Returns "" when the request is allowed, or a 429 JSON body when rejected.
+// ---------------------------------------------------------------------------
+fn rate_limit_check(ip: String, path: String) -> String {
+    // Health checks are exempt — they must never be blocked.
+    if str_eq(path, "/health") {
+        return ""
+    }
+
+    let limit_str: String = state_get("soul_rate_limit")
+    let limit: Int = if str_eq(limit_str, "") { 60 } else { str_to_int(limit_str) }
+
+    let now: Int = time_now()
+    let window_key: String = "rl:" + ip + ":window"
+    let count_key: String = "rl:" + ip + ":count"
+
+    let win_str: String = state_get(window_key)
+    let win_start: Int = if str_eq(win_str, "") { now } else { str_to_int(win_str) }
+
+    // New window every 60 seconds.
+    let elapsed: Int = now - win_start
+    let in_window: Bool = elapsed < 60
+
+    let prev_count_str: String = state_get(count_key)
+    let prev_count: Int = if str_eq(prev_count_str, "") { 0 } else { str_to_int(prev_count_str) }
+
+    // Reset window if expired.
+    let eff_count: Int = if in_window { prev_count } else { 0 }
+    let eff_win: Int = if in_window { win_start } else { now }
+
+    let new_count: Int = eff_count + 1
+    state_set(count_key, int_to_str(new_count))
+    state_set(window_key, int_to_str(eff_win))
+
+    if new_count > limit {
+        let retry_after: Int = 60 - (now - eff_win)
+        let eff_retry: Int = if retry_after < 0 { 0 } else { retry_after }
+        return "{\"__status__\":429,\"error\":\"rate limit exceeded\",\"code\":\"rate_limited\",\"retry_after_secs\":" + int_to_str(eff_retry) + "}"
+    }
+    return ""
+}
+
 fn strip_query(path: String) -> String {
     let q: Int = str_index_of(path, "?")
     if q < 0 {
@@ -16,11 +75,11 @@ fn strip_query(path: String) -> String {
 }
 
 fn err_404(path: String) -> String {
-    return "{\"error\":\"not found\",\"path\":\"" + path + "\"}"
+    return "{\"error\":\"not found\",\"code\":\"not_found\",\"path\":\"" + path + "\"}"
 }
 
 fn err_405(method: String, path: String) -> String {
-    return "{\"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 {
@@ -31,12 +90,35 @@ fn route_health() -> String {
     let edge_ct: Int = engram_edge_count()
     let pulse: String = state_get("soul.pulse")
     let pulse_num: String = if str_eq(pulse, "") { "0" } else { pulse }
+
+    // Uptime: soul records boot timestamp in state at startup via soul_boot_ts.
+    // Compute elapsed seconds; fall back to -1 if not yet set.
+    let boot_ts_str: String = state_get("soul_boot_ts")
+    let uptime_secs: Int = if str_eq(boot_ts_str, "") {
+        -1
+    } else {
+        time_now() - str_to_int(boot_ts_str)
+    }
+
+    // LLM connectivity: probe with a minimal call. Any non-error reply = ok.
+    // Use a short, fixed prompt so this never counts against conversation history.
+    let model: String = state_get("soul_model")
+    let eff_model: String = if str_eq(model, "") { "claude-sonnet-4-5" } else { model }
+    let llm_probe: String = llm_call_system(eff_model, "You are a health probe. Reply with the single word: ok", "ping")
+    let llm_ok: Bool = !str_eq(llm_probe, "")
+        && !str_starts_with(llm_probe, "{\"error\"")
+        && !str_starts_with(llm_probe, "{\"type\":\"error\"")
+        && !str_contains(llm_probe, "authentication_error")
+    let llm_status: String = if llm_ok { "ok" } else { "unreachable" }
+
     return "{\"status\":\"alive\""
         + ",\"cgi_id\":\"" + cgi_id + "\""
         + ",\"boot\":" + boot_num
+        + ",\"uptime_secs\":" + int_to_str(uptime_secs)
         + ",\"node_count\":" + int_to_str(node_ct)
         + ",\"edge_count\":" + int_to_str(edge_ct)
         + ",\"pulse\":" + pulse_num
+        + ",\"llm\":\"" + llm_status + "\""
         + ",\"layers\":{\"l0\":\"core\",\"l1\":\"safety\",\"l2\":\"stewardship\",\"l3\":\"" + imprint_current() + "\"}}"
 }
 
@@ -103,15 +185,15 @@ fn route_imprint_user(body: String) -> String {
 
 fn route_synthesize(body: String) -> String {
     if str_eq(body, "") {
-        return "{\"mechanism\":\"did not engage\"}"
+        return "{\"error\":\"body is required\",\"code\":\"missing_param\"}"
     }
     let parent_a: String = json_get(body, "parent_a")
     let parent_b: String = json_get(body, "parent_b")
     if str_eq(parent_a, "") {
-        return "{\"mechanism\":\"did not engage\"}"
+        return "{\"error\":\"parent_a is required\",\"code\":\"missing_param\"}"
     }
     if str_eq(parent_b, "") {
-        return "{\"mechanism\":\"did not engage\"}"
+        return "{\"error\":\"parent_b is required\",\"code\":\"missing_param\"}"
     }
     let req: String = "synthesize " + parent_a + " " + parent_b
     let tags: String = "[\"soul-inbox-pending\",\"synthesis-request\"]"
@@ -259,6 +341,17 @@ fn handle_connectors(method: String, clean: String, body: String) -> String {
 fn handle_request(method: String, path: String, body: String) -> String {
     let clean: String = strip_query(path)
 
+    // 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.
+    let ip: String = env("REMOTE_ADDR")
+    if !str_eq(ip, "") {
+        let rl_result: String = rate_limit_check(ip, clean)
+        if !str_eq(rl_result, "") {
+            return rl_result
+        }
+    }
+
     if str_eq(method, "POST") && str_eq(clean, "/dharma/recv") {
         return handle_dharma_recv(body)
     }
@@ -286,7 +379,7 @@ 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, "") {
-                return "{\"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 {
@@ -426,8 +519,15 @@ fn handle_request(method: String, path: String, body: String) -> String {
             return handle_elp_chat(body)
         }
         if str_eq(clean, "/api/chat") {
-            let agentic_flag: Bool = json_get_bool(body, "agentic")
+            // NOTE: streaming (SSE / chunked transfer) is not implemented. All chat
+            // 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.
             let raw_msg: String = json_get(body, "message")
+            if str_eq(raw_msg, "") {
+                return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
+            }
+            let agentic_flag: Bool = json_get_bool(body, "agentic")
             let reply: String = if agentic_flag {
                 handle_chat_agentic(body)
             } else {

sessions.el

@@ -368,48 +368,6 @@ fn session_hist_save(session_id: String, hist: String) -> Void {
         el_from_float(0.6), el_from_float(0.6), el_from_float(0.9),
         "Episodic", tags
     )
-
-    // Session boundary emotional summary — written once per session the first time
-    // a bell event has fired. The summary node is findable by future sessions via
-    // broad affective queries ("session:emotional-summary" or "bell distress session").
-    // It is NOT rewritten on every save — the state flag prevents duplicate nodes.
-    let summary_written_key: String = "session_bell_summary_written:" + session_id
-    let already_written: String = state_get(summary_written_key)
-    if str_eq(already_written, "") {
-        let bell_count_key: String = "session_bell_count:" + session_id
-        let bell_count_raw: String = state_get(bell_count_key)
-        let bell_count: Int = if str_eq(bell_count_raw, "") { 0 } else { str_to_int(bell_count_raw) }
-        if bell_count > 0 {
-            let bell_level_key: String = "session_bell_level:" + session_id
-            let bell_signal_key: String = "session_bell_signal:" + session_id
-            let dominant_level: String = state_get(bell_level_key)
-            let last_signal: String = state_get(bell_signal_key)
-            let eff_level: String = if str_eq(dominant_level, "") { "soft" } else { dominant_level }
-            let eff_signal: String = if str_eq(last_signal, "") { "(no signal captured)" } else { last_signal }
-            let ts_now: Int = time_now()
-            let summary_content: String = "session:emotional-summary"
-                + " | session:" + session_id
-                + " | bell_count:" + int_to_str(bell_count)
-                + " | dominant_level:" + eff_level
-                + " | last_signal:" + eff_signal
-                + " | ts:" + int_to_str(ts_now)
-            let summary_tags: String = "[\"session-emotional-summary\",\"affective\",\"bell:" + eff_level + "\",\"BellEvent\"]"
-            let summary_sal: String = if str_eq(eff_level, "hard") { el_from_float(0.95) } else { el_from_float(0.85) }
-            let sum_discard: String = engram_node_full(
-                summary_content,
-                "BellEvent",
-                "session:emotional-summary",
-                summary_sal,
-                summary_sal,
-                el_from_float(1.0),
-                "Episodic",
-                summary_tags
-            )
-            // Mark written so we do not create duplicate summary nodes as the
-            // session continues accumulating more turns.
-            state_set(summary_written_key, "1")
-        }
-    }
 }
 
 // session_update_meta_timestamp — update the updated_at field in the session:meta node.

soul.el

@@ -369,6 +369,7 @@ load_identity_context()
 seed_persona_from_env()
 let boot_num: Int = mem_boot_count_inc()
 state_set("soul_boot_count", int_to_str(boot_num))
+state_set("soul_boot_ts", int_to_str(time_now()))
 println("[soul] boot #" + int_to_str(boot_num))
 emit_session_start_event()