- entrypoint.sh: extend engram health-check timeout 30->60s; set EL_HTTP_TIMEOUT_MS=10000 and EL_HTTP_CONNECT_TIMEOUT_MS=3000 to bound awareness loop blocking window to 10s/call (down from 60s default) - soul.el: 3-attempt retry loop for boot-time /api/nodes+/api/edges fetch; validate non-empty JSON array before loading to prevent silent zero-node identity graph from transient post-healthcheck network hiccup - awareness.el: soft circuit-breaker in ise_post (opens after 3 failures, 30s backoff, half-open probe); /api/sync refresh skips HTTP call when breaker is open; error-JSON detection on sync response TODOs: full async dispatch, connection pooling (require EL futures/persistent curl)
This commit is contained in:
+33
-3
@@ -40,7 +40,32 @@ 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 +565,14 @@ 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)
|
||||
|
||||
Reference in New Issue
Block a user