Compare commits

...

5 Commits

Author SHA1 Message Date
will.anderson 588ca11f57 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.
2026-06-22 14:19:14 -05:00
will.anderson 9e178d8371 fix(recall): deduplicate engram nodes by ID across activation and search passes
Thread a seen-node-ID exclusion set from engram_compile() through to
session_preload in handle_chat, preventing the same high-salience nodes
(identity, recent memories) from appearing 2-3x in the system prompt.

Changes:
- Add id_in_seen(), add_to_seen(), engram_extract_ids() helpers that
  maintain a comma-delimited seen-ID accumulator (EL has no Set type)
- In engram_compile(): after merging all topic/entity/recall pools, extract
  node IDs from merged_nodes and publish via state_set(engram_compile_seen_ids)
- In handle_chat(): read seen_ids from state after engram_compile() returns,
  then check id_in_seen() before emitting each session_preload bullet
  (profile x3, work x2, project x2, summary x1 — all 8 candidate nodes guarded)

Nodes already present in the compiled engram context are skipped in preload,
eliminating 3000-3500 token repetition on first-message turns.
2026-06-22 14:06:04 -05:00
will.anderson 21f248a33a feat(recall): recall-completeness improvements
Neuron Soul CI / build (push) Has been cancelled
Deploy Soul to GKE / deploy (push) Has been cancelled
- Lower engram_compile_ranked threshold 25->15: include moderately-relevant older nodes
- Extend sentinel cleanup from _sel_9 to _sel_14 to prevent JSON noise
- Add engram_split_topics for multi-topic decomposition (AND/and/also/plus)
- Add engram_extract_entities for named entity dedicated searches
- Add engram_detect_recall_intent for boosted 40-candidate search on recall phrases
- Add engram_is_continuation replacing brittle 50-char threshold (now 80 + pronoun/opener detection)
- Add engram_compile_multi with depth 8 (was 5) and 30-candidate search pool
- Add engram_nodes_merge for clean two-array deduplication
- Replace engram_compile with multi-topic/entity/recall-boost version; budget 6000->8000
- Safe JSON truncation: scan for last } before budget cap instead of raw str_slice
- handle_chat and agentic_chat: use engram_is_continuation; thread snip 150->250
- session_preload: add project-status and session-summary search queries
2026-06-22 13:05:28 -05:00
will.anderson aef687b57c fix(reliability): state management
Neuron Soul CI / build (push) Has been cancelled
Deploy Soul to GKE / deploy (push) Has been cancelled
2026-06-22 12:54:32 -05:00
will.anderson e6da638536 fix(reliability): state-management — document and partially fix concurrent state races
Neuron Soul CI / build (pull_request) Has been cancelled
Issues addressed:
- #2: Document session_index non-atomic RMW (engram node safe under new mutex)
- #3: Document conv_history global race in handle_chat (session path unaffected)
- #4: Scope session_continuity state key per session_id in layered_cycle
- #5: Document active_imprint_id global race with fix path
- #6: Fix next_bridge_id to use uuid_v4() for collision-free IDs
- #7: Document session_hist_save delete-then-insert race
- #8: Document /api/graph/edges engram_save race (fixed in el_runtime.c)
- #10: Document agentic_conv_history global race in awareness loop

Issues #1 (engram_global mutex) and #8 (atomic engram_save write-to-temp+rename)
are fully fixed in el_runtime.c (committed to foundation/el repo separately).
Issue #9 skipped — already fixed in PR #31.
2026-06-22 12:12:58 -05:00
6 changed files with 465 additions and 477 deletions
+6 -37
View File
@@ -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)
+416 -295
View File
@@ -73,8 +73,9 @@ fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> String {
while ci < total {
let node: String = json_array_get(nodes_json, ci)
let score: Int = engram_score_node(node)
// Only include reasonably relevant nodes (threshold=25)
let above_thresh: Bool = score >= 25
// Threshold lowered from 25 to 15: includes moderately-relevant older nodes.
// A 3-week-old node with salience 0.6 and importance 0.6 scores ~18 was dropped, now included.
let above_thresh: Bool = score >= 15
// Check this index wasn't already selected (sentinel: look for idx marker)
let idx_marker: String = "\"_sel_" + int_to_str(ci) + "\""
let already_picked: Bool = str_contains(selected, idx_marker)
@@ -113,59 +114,289 @@ fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> String {
let c7: String = str_replace(c6, "\"_sel_7\":1,", "")
let c8: String = str_replace(c7, "\"_sel_8\":1,", "")
let c9: String = str_replace(c8, "\"_sel_9\":1,", "")
return c9
let c10: String = str_replace(c9, "\"_sel_10\":1,", "")
let c11: String = str_replace(c10, "\"_sel_11\":1,", "")
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
}
// engram_split_topics split message into sub-queries on explicit conjunctions.
// "health goals AND startup progress" becomes two independent searches.
fn engram_split_topics(message: String) -> String {
let sep: String = if str_contains(message, " AND ") { " AND " } else {
if str_contains(message, " and ") { " and " } else {
if str_contains(message, " also ") { " also " } else {
if str_contains(message, " plus ") { " plus " } else { "" }
}
}
}
if str_eq(sep, "") { return message }
let sep_pos: Int = str_index_of(message, sep)
let part1: String = str_slice(message, 0, sep_pos)
let part2: String = str_slice(message, sep_pos + str_len(sep), str_len(message))
let part2_topics: String = engram_split_topics(part2)
if str_eq(part1, "") { return part2_topics }
return part1 + "\n" + part2_topics
}
// engram_extract_entities extract probable named entities (capital-first, 3+ chars,
// not stop-words) from a message. Returns newline-separated list.
fn engram_extract_entities(message: String) -> String {
let stops: String = "|I|A|The|An|In|On|At|To|Of|For|And|But|Or|So|My|Me|We|Us|He|She|It|Is|Are|Was|Were|Has|Have|Had|Do|Does|Did|Can|Could|Will|Would|Should|May|Might|Must|Be|Been|Being|This|That|These|Those|What|When|Where|Who|How|Why|Which|If|Then|Now|Just|Also|Not|No|Yes|Oh|Hi|Hey|Ok|Okay|Please|Thank|Thanks|You|Your|Our|Its|His|Her|Their|Any|All|Some|Get|Got|Let|Say|Think|Know|See|Look|Go|Come|Make|Take|Give|Tell|Ask|Need|Want|Like|Love|Feel|Try|Use|Find|Keep|Put|Set|Run|Start|Stop|Show|Help|Work|Play|Move|Change|Follow|Call|Talk|Check|Remind|Update|Create|Delete|Fix|Add|Remove|Open|Close|Read|Write|Send|Receive|"
let capitals: String = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
let entities: String = ""
let entity_count: Int = 0
let msg_len: Int = str_len(message)
let pos: Int = 0
while pos < msg_len && entity_count < 10 {
let wend: Int = pos
let scanning: Bool = true
while scanning && wend < msg_len {
let wch: String = str_slice(message, wend, wend + 1)
let is_sep: Bool = str_eq(wch, " ") || str_eq(wch, "\n") || str_eq(wch, "\t")
|| str_eq(wch, ",") || str_eq(wch, ".") || str_eq(wch, "?")
|| str_eq(wch, "!") || str_eq(wch, ":") || str_eq(wch, ";")
|| str_eq(wch, "(") || str_eq(wch, ")") || str_eq(wch, "\'") || str_eq(wch, "-")
let scanning = if is_sep { false } else { scanning }
let wend = if !is_sep { wend + 1 } else { wend }
}
let word: String = str_slice(message, pos, wend)
let word_len: Int = str_len(word)
let first_ch: String = if word_len >= 3 { str_slice(word, 0, 1) } else { "" }
let is_capital: Bool = word_len >= 3 && str_contains(capitals, first_ch)
let is_stop: Bool = str_contains(stops, "|" + word + "|")
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 }
let pos = if wend > pos { wend + 1 } else { pos + 1 }
}
return entities
}
// engram_detect_recall_intent true when message explicitly requests memory recall.
fn engram_detect_recall_intent(message: String) -> Bool {
return str_contains(message, "remind me")
|| str_contains(message, "do you remember")
|| str_contains(message, "what do you know")
|| str_contains(message, "what happened")
|| str_contains(message, "tell me about")
|| str_contains(message, "what was")
|| str_contains(message, "what were")
|| str_contains(message, "how is it going")
|| str_contains(message, "how are things")
|| str_contains(message, "catch me up")
|| str_contains(message, "fill me in")
|| str_contains(message, "what's the status")
|| str_contains(message, "whats the status")
|| str_contains(message, "any updates")
|| str_contains(message, "recap")
|| str_contains(message, "look up")
|| str_contains(message, "check on")
|| str_contains(message, "how did")
|| 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).
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 ")
|| str_starts_with(message, "it ")
|| str_starts_with(message, "That ") || str_starts_with(message, "that ")
|| str_starts_with(message, "This ") || str_starts_with(message, "this ")
|| str_starts_with(message, "They ") || str_starts_with(message, "they ")
|| str_starts_with(message, "He ") || str_starts_with(message, "he ")
|| 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 }
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")
|| str_starts_with(message, "Yes") || str_starts_with(message, "yes")
|| str_starts_with(message, "No,") || str_starts_with(message, "no,")
|| 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
}
// engram_compile_multi run activation + search for one topic with expanded pools.
// Activation depth 8 (was 5). Search 30 candidates ranked to 12 (was 20/8).
// Per-topic result pool: up to 20 nodes (was 13).
fn engram_compile_multi(topic: String) -> String {
let activate_json: String = engram_activate_json(topic, 8)
let search_json: String = engram_search_json(topic, 30)
let act_ok: Bool = !str_eq(activate_json, "") && !str_eq(activate_json, "[]")
let srch_ok: Bool = !str_eq(search_json, "") && !str_eq(search_json, "[]")
let act_nodes: String = if act_ok { activate_json } else { "" }
let srch_nodes: String = if srch_ok { engram_compile_ranked(search_json, 12) } else { "" }
if !str_eq(act_nodes, "") && !str_eq(srch_nodes, "") {
let act_inner: String = str_slice(act_nodes, 1, str_len(act_nodes) - 1)
let srch_inner: String = str_slice(srch_nodes, 1, str_len(srch_nodes) - 1)
return engram_dedup_nodes("[" + act_inner + "," + srch_inner + "]")
}
if !str_eq(act_nodes, "") { return act_nodes }
if !str_eq(srch_nodes, "") { return srch_nodes }
return ""
}
// engram_nodes_merge merge two node arrays, deduplicating by node id.
fn engram_nodes_merge(a: String, b: String) -> String {
let ok_a: Bool = !str_eq(a, "") && !str_eq(a, "[]")
let ok_b: Bool = !str_eq(b, "") && !str_eq(b, "[]")
if !ok_a && !ok_b { return "" }
if !ok_a { return b }
if !ok_b { return a }
let ai: String = str_slice(a, 1, str_len(a) - 1)
let bi: String = str_slice(b, 1, str_len(b) - 1)
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 {
let activate_json: String = engram_activate_json(intent, 5)
// Fetch more search results than we'll use so ranking has a real pool to pick from.
let search_json: String = engram_search_json(intent, 20)
// Issue 1: decompose multi-topic messages into sub-queries.
let topics: String = engram_split_topics(intent)
let has_multi_topic: Bool = str_contains(topics, "\n")
let act_ok: Bool = !str_eq(activate_json, "") && !str_eq(activate_json, "[]")
let srch_ok: Bool = !str_eq(search_json, "") && !str_eq(search_json, "[]")
// Issue 4: detect explicit recall intent and run boosted search.
let is_recall_intent: Bool = engram_detect_recall_intent(intent)
// Activation nodes (spreading activation) are already high-signal keep all 5.
let act_part: String = if act_ok { activate_json } else { "" }
// Issue 2: extract named entities for dedicated per-entity searches.
let entity_list: String = engram_extract_entities(intent)
let has_entities: Bool = !str_eq(entity_list, "")
// Rank search results and keep only the top 8 (was: flat 15 unranked).
// This cuts context noise roughly in half while preserving the best-scoring nodes.
let srch_ranked: String = if srch_ok { engram_compile_ranked(search_json, 8) } else { "" }
let srch_part: String = srch_ranked
// Primary topic search (first or only topic).
let topic0: String = if has_multi_topic {
let nl0: Int = str_index_of(topics, "\n")
str_slice(topics, 0, nl0)
} else { topics }
let nodes0: String = engram_compile_multi(topic0)
// Fallback: when vector search returns nothing (no embeddings), fetch pinned
// high-salience nodes by their known IDs. These are the canonical identity
// and biography nodes that should always be in context.
// engram_get_node_json(id) returns a single node as JSON or "" if missing.
let scan_part: String = if !act_ok && !srch_ok {
let family_node: String = engram_get_node_json("knw-35940684-abc4-42f0-b942-818f66b1f69a")
let origin_node: String = engram_get_node_json("knw-729fc901-8335-44c4-9f3a-b150b4aa0915")
let fam_ok: Bool = !str_eq(family_node, "") && !str_eq(family_node, "null")
let orig_ok: Bool = !str_eq(origin_node, "") && !str_eq(origin_node, "null")
let fam_str: String = if fam_ok { family_node } else { "" }
let orig_str: String = if orig_ok { origin_node } else { "" }
let sep: String = if fam_ok && orig_ok { "\n" } else { "" }
let combined: String = fam_str + sep + orig_str
if str_eq(combined, "") { "" } else { combined }
} else {
""
}
// Second topic segment.
let nodes1: 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")
let topic1: String = if nl1 < 0 { rest1 } else { str_slice(rest1, 0, nl1) }
if str_eq(topic1, "") { "" } else { engram_compile_multi(topic1) }
} else { "" }
// 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.
// Third topic segment.
let nodes2: 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")
let topic2: String = if nl2 < 0 { rest2 } else { str_slice(rest2, 0, nl2) }
if str_eq(topic2, "") { "" } else { engram_compile_multi(topic2) }
}
} 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")
let entity0: String = if nl_e0 < 0 { entity_list } else { str_slice(entity_list, 0, nl_e0) }
if str_eq(entity0, "") { "" } else {
let ent_srch: String = engram_search_json(entity0, 15)
let ent_ok: Bool = !str_eq(ent_srch, "") && !str_eq(ent_srch, "[]")
if ent_ok { engram_compile_ranked(ent_srch, 6) } else { "" }
}
} else { "" }
// Entity 1 dedicated search.
let entity_nodes1: String = if has_entities {
let nl_e0: Int = str_index_of(entity_list, "\n")
if nl_e0 < 0 { "" } else {
let rest_e: String = str_slice(entity_list, nl_e0 + 1, str_len(entity_list))
let nl_e1: Int = str_index_of(rest_e, "\n")
let entity1: String = if nl_e1 < 0 { rest_e } else { str_slice(rest_e, 0, nl_e1) }
if str_eq(entity1, "") { "" } else {
let ent_srch1: String = engram_search_json(entity1, 15)
let ent1_ok: Bool = !str_eq(ent_srch1, "") && !str_eq(ent_srch1, "[]")
if ent1_ok { engram_compile_ranked(ent_srch1, 6) } else { "" }
}
}
} else { "" }
// Issue 4 cont.: boosted search for recall-intent (40 candidates, ranked 15).
let recall_boost: String = if is_recall_intent {
let boost_srch: String = engram_search_json(intent, 40)
let boost_ok: Bool = !str_eq(boost_srch, "") && !str_eq(boost_srch, "[]")
if boost_ok { engram_compile_ranked(boost_srch, 15) } else { "" }
} else { "" }
// 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, entity_nodes0)
let merged: String = engram_nodes_merge(merged, entity_nodes1)
let merged: String = engram_nodes_merge(merged, recall_boost)
let merged_nodes: String = merged
// Fallback: when all searches return nothing, fetch persona nodes.
let scan_part: String = if str_eq(merged_nodes, "") || str_eq(merged_nodes, "[]") {
let persona_fallback: String = engram_search_json("soul:persona Persona identity", 5)
let pf_ok: Bool = !str_eq(persona_fallback, "") && !str_eq(persona_fallback, "[]")
if pf_ok {
let pf_ranked: String = engram_compile_ranked(persona_fallback, 3)
if str_eq(pf_ranked, "") { "" } else { pf_ranked }
} else { "" }
} else { "" }
// Affective context: always include the most recent high-emotion memory within 72h.
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)
@@ -183,20 +414,43 @@ fn engram_compile(intent: String) -> String {
} 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 has_main: Bool = !str_eq(merged_nodes, "") && !str_eq(merged_nodes, "[]")
let main_part: String = if has_main { merged_nodes } else { scan_part }
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 "" }
// Raise the cap slightly to match the ranked (higher-signal) output.
if str_len(ctx) > 6000 {
return str_slice(ctx, 0, 6000)
// Issue 7 fix: safe JSON truncation find last closing brace before budget cap.
// Budget raised from 6000 to 8000 for the larger multi-topic pool.
let budget: Int = 8000
if str_len(ctx) <= budget { return ctx }
let search_end: Int = budget - 1
let scan_limit: Int = if search_end > 500 { search_end - 500 } else { 0 }
let found_pos: Int = -1
let si: Int = search_end
while si >= scan_limit {
let ch: String = str_slice(ctx, si, si + 1)
let found_pos = if str_eq(ch, "}") && found_pos < 0 { si } else { found_pos }
let si = if found_pos >= 0 { scan_limit - 1 } else { si - 1 }
}
return ctx
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 + "]" }
return truncated
}
fn json_safe(s: String) -> String {
let s1: String = str_replace(s, "\\", "\\\\")
let s2: String = str_replace(s1, "\"", "\\\"")
@@ -254,41 +508,18 @@ 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 {
// 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
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)) + "]"
}
// 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 + "]"
return hist
}
// hist_trim_with_bell_guard trim the history window exactly as hist_trim does, but
@@ -370,111 +601,51 @@ fn clean_llm_response(s: String) -> String {
}
// conv_history_persist save conversation history to engram for cross-restart continuity.
// 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.
// Stores as a Conversation node. Overwrites by using consistent label "conv:history".
fn conv_history_persist(hist: String) -> Void {
if str_eq(hist, "") { return "" }
if str_eq(hist, "[]") { return "" }
// 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 ts: Int = time_now()
let tags: String = "[\"conv-history\",\"persistent\"]"
let node_id: String = engram_node_full(
let discard: 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.
//
// 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.
// Returns the most recent "conv:history" node content, or "" if none found.
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")
// 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 ""
}
// Validate it looks like a JSON array
if !str_starts_with(content, "[") { return "" }
return content
}
fn handle_chat(body: String) -> String {
let message: String = json_get(body, "message")
if str_eq(message, "") {
// Issue #5: missing required param HTTP 400.
return "{\"__status__\":400,\"error\":\"message is required\",\"response\":\"\"}"
return "{\"error\":\"message is required\",\"response\":\"\"}"
}
// Load history BEFORE compiling context so we can anchor activation to the thread.
// 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.
// TODO(reliability #3 conv_history global race): process-global key; concurrent
// /api/chat requests without session_id race on this read-append-write.
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) }
// Thread-aware activation: short/ambiguous messages (continuations like "go on",
// "what else?", "yes") activate on the last reply instead of the bare message.
// This prevents a strong off-topic memory node from hijacking the reply when the
// user is clearly continuing an existing thread.
let is_continuation: Bool = str_len(message) < 50 && hist_len > 0
// Issue 8 fix: use semantic continuation detection instead of brittle 50-char threshold.
let is_continuation: Bool = engram_is_continuation(message, hist_len)
let last_entry: String = if is_continuation { json_array_get(stored_hist, hist_len - 1) } else { "" }
let last_content: String = if !str_eq(last_entry, "") { json_get(last_entry, "content") } else { "" }
let thread_snip: String = if str_len(last_content) > 150 { str_slice(last_content, 0, 150) } else { last_content }
// Thread snip extended 150->250 chars for better pronoun resolution context.
let thread_snip: String = if str_len(last_content) > 250 { str_slice(last_content, 0, 250) } else { last_content }
let activation_seed: String = if !str_eq(thread_snip, "") {
thread_snip + " " + message
} else {
@@ -501,73 +672,114 @@ 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)
// First message of the session: proactively load user profile and active work context.
// These two searches give the soul grounding before any conversation history exists.
// Results are rendered as brief bullets not raw JSON so they don't inflate context.
// 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", 5)
let work_nodes: String = engram_search_json("in_progress active project work", 5)
let project_nodes: String = engram_search_json("project status current ongoing active", 5)
let summary_nodes: String = engram_search_json("SessionSummary session:summary previous-session recent", 3)
let profile_ok: Bool = !str_eq(profile_nodes, "") && !str_eq(profile_nodes, "[]")
let work_ok: Bool = !str_eq(work_nodes, "") && !str_eq(work_nodes, "[]")
let project_ok: Bool = !str_eq(project_nodes, "") && !str_eq(project_nodes, "[]")
let summary_ok: Bool = !str_eq(summary_nodes, "") && !str_eq(summary_nodes, "[]")
// Extract content fields and render as bullet points (one per node, first 120 chars).
let profile_bullets: String = if profile_ok {
let pn: Int = json_array_len(profile_nodes)
let bullets: String = ""
let pi: Int = 0
// Collect up to 3 profile bullets
let bullets = if pi < pn {
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 snip0: String = if str_len(c0) > 120 { str_slice(c0, 0, 120) } else { c0 }
if str_eq(snip0, "") { bullets } else { "- " + snip0 }
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 }
} 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 snip1: String = if str_len(c1) > 120 { str_slice(c1, 0, 120) } else { c1 }
if str_eq(snip1, "") { bullets } else { bullets + "\n- " + snip1 }
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 }
} 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 snip2: String = if str_len(c2) > 120 { str_slice(c2, 0, 120) } else { c2 }
if str_eq(snip2, "") { bullets } else { bullets + "\n- " + snip2 }
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 }
} else { bullets }
bullets
} else { "" }
let work_bullets: String = if work_ok {
let wn: Int = json_array_len(work_nodes)
let wbullets: String = ""
let wbullets = if wn > 0 {
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 wsnip0: String = if str_len(wc0) > 120 { str_slice(wc0, 0, 120) } else { wc0 }
if str_eq(wsnip0, "") { wbullets } else { "- " + wsnip0 }
} else { wbullets }
let wbullets = if wn > 1 {
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 }
} 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 wsnip1: String = if str_len(wc1) > 120 { str_slice(wc1, 0, 120) } else { wc1 }
if str_eq(wsnip1, "") { wbullets } else { wbullets + "\n- " + wsnip1 }
} else { wbullets }
wbullets
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 }
} else { wb }
wb
} else { "" }
let has_profile: Bool = !str_eq(profile_bullets, "")
let has_work: Bool = !str_eq(work_bullets, "")
let preload: String = if has_profile || has_work {
let profile_section: String = if has_profile {
"[USER CONTEXT — from memory]\n" + profile_bullets
} else { "" }
let work_section: String = if has_work {
"[ACTIVE WORK — from memory]\n" + work_bullets
} else { "" }
let sep_pw: String = if has_profile && has_work { "\n\n" } else { "" }
"\n\n" + profile_section + sep_pw + work_section
let project_bullets: String = if project_ok {
let prn: Int = json_array_len(project_nodes)
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 }
} 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 }
} 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 }
} else { "" }
let hp: Bool = !str_eq(profile_bullets, "")
let hw: Bool = !str_eq(work_bullets, "")
let hpr: Bool = !str_eq(project_bullets, "")
let hs: Bool = !str_eq(summary_bullet, "")
let preload: String = if hp || hw || hpr || hs {
let sec_p: String = if hp { "[USER CONTEXT — from memory]\n" + profile_bullets } else { "" }
let sec_w: String = if hw { "[ACTIVE WORK — from memory]\n" + work_bullets } else { "" }
let sec_pr: String = if hpr { "[PROJECTS — from memory]\n" + project_bullets } else { "" }
let sec_s: String = if hs { "[PREVIOUS SESSION — from memory]\n" + summary_bullet } else { "" }
let sep1: String = if hp && (hw || hpr || hs) { "\n\n" } else { "" }
let sep2: String = if hw && (hpr || hs) { "\n\n" } else { "" }
let sep3: String = if hpr && hs { "\n\n" } else { "" }
"\n\n" + sec_p + sep1 + sec_w + sep2 + sec_pr + sep3 + sec_s
} else { "" }
preload
} else { "" }
@@ -587,16 +799,11 @@ 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 {
// Issue #6: LLM failure HTTP 503 (service unavailable).
return "{\"__status__\":503,\"error\":\"llm unavailable\",\"response\":\"\"}"
return "{\"error\":\"llm unavailable\",\"response\":\"\"}"
}
let clean_response: String = clean_llm_response(raw_response)
@@ -606,11 +813,6 @@ 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 {
@@ -666,42 +868,6 @@ 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, "") {
@@ -753,7 +919,7 @@ 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 5 http://127.0.0.1:7771/mcp/tools")
let raw: String = exec_capture("curl -s --max-time 2 http://127.0.0.1:7771/mcp/tools")
if str_eq(raw, "") {
return "[]"
}
@@ -786,15 +952,7 @@ 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 + "}"
// Issue #12: previously used a fixed path /tmp/neuron-mcp-call.json.
// Under concurrent load (64 worker threads), two simultaneous MCP tool calls
// race on this file one call sends the other's input to the bridge.
// Fix: monotonic sequence counter makes the path unique per call.
let mcp_seq_s: String = state_get("mcp_call_seq")
let mcp_seq_n: Int = if str_eq(mcp_seq_s, "") { 0 } else { str_to_int(mcp_seq_s) }
let mcp_seq_next: Int = mcp_seq_n + 1
state_set("mcp_call_seq", int_to_str(mcp_seq_next))
let tmp: String = "/tmp/neuron-mcp-call-" + int_to_str(time_now()) + "-" + int_to_str(mcp_seq_next) + ".json"
let tmp: String = "/tmp/neuron-mcp-call.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)
}
@@ -806,7 +964,7 @@ 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 5 http://127.0.0.1:7771/mcp/auto-approved")
let raw: String = exec_capture("curl -s --max-time 2 http://127.0.0.1:7771/mcp/auto-approved")
if str_eq(raw, "") {
return false
}
@@ -1076,22 +1234,15 @@ 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 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.
// Uses uuid_v4() as the primary uniqueness guarantee concurrent calls cannot collide.
//
// 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.
// 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.
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
}
@@ -1138,7 +1289,7 @@ fn handle_chat_agentic(body: String) -> String {
let session_valid: Bool = if str_eq(req_session, "") {
true
} else {
!str_contains(session_get(req_session), "\"error\"")
session_exists(req_session)
}
if !session_valid {
return "{\"error\":\"session not found\",\"session_id\":\"" + req_session + "\",\"reply\":\"\"}"
@@ -1147,7 +1298,8 @@ fn handle_chat_agentic(body: String) -> String {
let hist_key: String = if str_eq(req_session, "") { "conv_history" } else { "session_hist_" + req_session }
let agentic_hist: String = state_get(hist_key)
let agentic_hist_len: Int = if str_eq(agentic_hist, "") { 0 } else { json_array_len(agentic_hist) }
let ag_is_cont: Bool = str_len(message) < 50 && agentic_hist_len > 0
// Issue 8 fix: use engram_is_continuation instead of brittle 50-char threshold.
let ag_is_cont: Bool = engram_is_continuation(message, agentic_hist_len)
let ag_last_entry: String = if ag_is_cont { json_array_get(agentic_hist, agentic_hist_len - 1) } else { "" }
let ag_last_content: String = if !str_eq(ag_last_entry, "") { json_get(ag_last_entry, "content") } else { "" }
let ag_thread_snip: String = if str_len(ag_last_content) > 150 { str_slice(ag_last_content, 0, 150) } else { ag_last_content }
@@ -1182,23 +1334,12 @@ 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 }
@@ -1229,14 +1370,6 @@ 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 = ""
@@ -1245,7 +1378,7 @@ 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\":" + max_tokens_str
+ ",\"max_tokens\":4096"
+ ",\"system\":\"" + safe_sys + "\""
+ ",\"tools\":" + tools_json
+ ",\"messages\":" + messages
@@ -1525,11 +1658,9 @@ 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 + "\"}"
}
@@ -1576,11 +1707,9 @@ 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 + "\"}"
}
@@ -1594,19 +1723,13 @@ 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 utterance_id: String = engram_node_full(
let discard_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 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 discard_save: String = engram_save(snap_path)
}
let safe_response: String = json_safe(clean_response)
@@ -1777,8 +1900,6 @@ fn auto_persist(req: String, resp: String) -> Void {
"session_bell_signal:" + sess_id
}
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 + ")")
}
}
+4
View File
@@ -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 }
+12 -63
View File
@@ -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 {
+4
View File
@@ -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,
+23 -82
View File
@@ -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)