Compare commits

..

8 Commits

Author SHA1 Message Date
will.anderson 774688cfb9 fix/session-continuity-hook
Neuron Soul CI / build (push) Has been cancelled
Deploy Soul to GKE / deploy (push) Failing after 6m0s
2026-06-22 14:29:31 -05:00
will.anderson aa2404b3f7 fix/context-dedup-shared-ids 2026-06-22 14:29:06 -05:00
will.anderson 94b55d667c fix/engram-float-parser 2026-06-22 14:28:17 -05:00
will.anderson f73c913498 fix(session-continuity): address all adversarial review findings
Issue 1 (CRITICAL): Restore parse_float_x100 for correct single-decimal
float handling. "0.9" now correctly yields 90, not 9. Also restores
engram_numeric_valid guard that validates inputs before str_to_int.

Issue 2 (CRITICAL): Fix handle_chat_agentic safety screen history key
regression. state_get("conversation_history") -> state_get("conv_history")
so the safety screen receives actual history instead of always "".

Issue 3 (REAL BUG): Replace _sel_N JSON sentinel injection in
engram_compile_ranked with |N| index string tracking. Sentinels were
leaking into node JSON delivered to the LLM and cleanup only covered
indices 0-14, leaving indices 15+ uncleaned.

Issue 4 (REGRESSION): Restore rendered conversation history formatting.
Conversation history is now rendered as "User: .../Assistant: ..." with
400-char truncation per turn, not raw JSON array injection.

Issue 5 (SCOPE/SAFETY): Restore removed defensive code: engram_numeric_valid
and parse_float_x100 guards; conv_history_load label-based fetch + partial-
write guard + load-failure state flag; conv_history_persist partial-write
guard + failure logging; hist_warning in response envelope.

Issue 6 (UNDOCUMENTED): Restore bell event cutoff from 259200s (3 days)
back to 1209600s (14 days). Also restore PositiveEvent affective context
search that was removed alongside the cutoff change.

Issue 7 (LOGIC REGRESSION): Fix affective_prefix to run every turn
(not just hist_len == 0). The care/joy directives must persist throughout
the session, not vanish after turn 1.

Issue 8 (MINOR): session_summary_write_dated now uses el_from_float(0.85)
for salience and importance (two-decimal) to avoid any ambiguity in float
parsing, and the function is re-added with the session-end hook.
2026-06-22 14:25:29 -05:00
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 aaada3770a fix(recall): deduplicate engram nodes by ID across activation and search passes
engram_compile() already published seen node IDs to state via engram_compile_seen_ids
but handle_chat never read or applied them. Wire up the consumption side:

- Read engram_compile_seen_ids from state after engram_compile() returns
- Check each session_preload candidate node (profile x3, work x2, project x2,
  summary x3) against id_in_seen() before emitting its content bullet
- Nodes already present in the compiled engram context are skipped entirely,
  preventing the same high-salience identity/memory nodes from appearing 2-3x
  in the system prompt and burning 3000-3500 tokens on repetition
2026-06-22 14:03:48 -05:00
will.anderson a0299c0a89 fix(recall): session-end summary hook + session summary recall at start 2026-06-22 14:01:56 -05:00
+77 -13
View File
@@ -253,10 +253,13 @@ fn chat_default_model() -> String {
// nodes 30+ days old score 0.1 (floor). Nodes with no created_at score 0.5.
// This keeps fresh, high-salience nodes at the top and pushes stale low-signal
// nodes to the bottom so they get trimmed when we cap context size.
// Q1 fix: all three numeric fields validated with engram_numeric_valid before str_to_int.
fn engram_score_node(node_json: String) -> Int {
let salience_str: String = json_get(node_json, "salience")
let importance_str: String = json_get(node_json, "importance")
let created_str: String = json_get(node_json, "created_at")
let updated_str: String = json_get(node_json, "updated_at")
let tier_str: String = json_get(node_json, "tier")
// parse_float_x100 handles 1- and 2-decimal floats correctly ("0.9" -> 90, "0.85" -> 85).
// Default 70 when field is absent; clamp to 0-100 range.
@@ -269,17 +272,16 @@ fn engram_score_node(node_json: String) -> Int {
if v > 100 { 100 } else { if v < 0 { 0 } else { v } }
}
// Recency: decay from 100 (today) to 10 (30+ days). created_at is Unix seconds.
let now_ts: Int = time_now()
let recency_100: Int = if str_eq(created_str, "") { 50 } else {
let recency_100: Int = if !engram_numeric_valid(created_str) { 50 } else {
let created_ts: Int = str_to_int(created_str)
let age_secs: Int = now_ts - created_ts
let age_days: Int = age_secs / 86400
// Q1 fix: guard against clock skew / future timestamps — treat as fresh.
let age_days: Int = if age_secs < 0 { 0 } else { age_secs / 86400 }
let decay: Int = if age_days >= 30 { 10 } else { 100 - (age_days * 3) }
if decay < 10 { 10 } else { decay }
}
// Combined score 0-1000000 (no floats): salience * importance * recency / 10000
return salience_100 * importance_100 * recency_100 / 10000
}
@@ -594,7 +596,7 @@ fn engram_compile(intent: String) -> String {
} else { "" }
} else { "" }
// Affective context: always include the most recent high-emotion memory within 72h.
// Affective context: always include the most recent high-emotion memory within 14 days.
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()
@@ -1001,6 +1003,7 @@ fn handle_chat(body: String) -> String {
// 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 work", 5)
@@ -1026,21 +1029,24 @@ fn handle_chat(body: String) -> String {
let bullets: String = ""
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 s0: String = if str_len(c0) > 120 { str_slice(c0, 0, 120) } else { c0 }
if str_eq(s0, "") { bullets } else { "- " + s0 }
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 s1: String = if str_len(c1) > 120 { str_slice(c1, 0, 120) } else { c1 }
if str_eq(s1, "") { bullets } else { bullets + "\n- " + s1 }
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 s2: String = if str_len(c2) > 120 { str_slice(c2, 0, 120) } else { c2 }
if str_eq(s2, "") { bullets } else { bullets + "\n- " + s2 }
if str_eq(s2, "") || id_in_seen(n2_id, seen_ids) { bullets } else { bullets + "\n- " + s2 }
} else { bullets }
bullets
} else { "" }
@@ -1050,15 +1056,17 @@ fn handle_chat(body: String) -> String {
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 ws0: String = if str_len(wc0) > 120 { str_slice(wc0, 0, 120) } else { wc0 }
if str_eq(ws0, "") { wb } else { "- " + ws0 }
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 ws1: String = if str_len(wc1) > 120 { str_slice(wc1, 0, 120) } else { wc1 }
if str_eq(ws1, "") { wb } else { wb + "\n- " + ws1 }
if str_eq(ws1, "") || id_in_seen(w1_id, seen_ids) { wb } else { wb + "\n- " + ws1 }
} else { wb }
wb
} else { "" }
@@ -1068,24 +1076,27 @@ fn handle_chat(body: String) -> String {
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, "") { pb } else { "- " + ps0 }
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, "") { pb } else { pb + "\n- " + ps1 }
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, "") { "" } else { "- " + ss0 }
if str_eq(ss0, "") || id_in_seen(sn0_id, seen_ids) { "" } else { "- " + ss0 }
} else { "" }
let hp: Bool = !str_eq(profile_bullets, "")
@@ -2477,3 +2488,56 @@ fn strengthen_chat_nodes(activation_nodes: String) -> Void {
let i = i + 1
}
}
// session_summary_autogenerate build a minimal summary from conversation history without LLM.
// Extracts user message snippets (first 80 chars each, up to 5 turns).
// Called by the session-end hook when >= 5 complete turns have occurred.
fn session_summary_autogenerate(hist: String) -> String {
if str_eq(hist, "") { return "" }
if str_eq(hist, "[]") { return "" }
let total: Int = json_array_len(hist)
if total == 0 { return "" }
let snippets: String = ""
let count: Int = 0
let i: Int = 0
while i < total && count < 5 {
let entry: String = json_array_get(hist, i)
let role: String = json_get(entry, "role")
if str_eq(role, "user") {
let msg: String = json_get(entry, "content")
let snip: String = if str_len(msg) > 80 { str_slice(msg, 0, 80) } else { msg }
let snippets = if str_eq(snippets, "") { snip } else { snippets + "; " + snip }
let count = count + 1
}
let i = i + 1
}
if str_eq(snippets, "") { return "" }
return "Session covered: " + snippets
}
// session_summary_write_dated write a SessionSummary node with a caller-supplied dated label.
// Unlike a global-label write, this does NOT delete old nodes each session accumulates its
// own node so engram_search_json("session:summary") can return multiple past sessions.
// The label must be unique per session (e.g. "session:summary:<boot_ts>").
// Uses salience 0.85/importance 0.85 (two-decimal) to avoid the single-decimal parse bug.
fn session_summary_write_dated(summary_text: String, label: String) -> String {
if str_eq(summary_text, "") { return "" }
if str_eq(label, "") { return "" }
let safe_text: String = str_replace(summary_text, "\"", "'")
let trimmed: String = if str_len(safe_text) > 800 { str_slice(safe_text, 0, 800) } else { safe_text }
let ts: Int = time_now()
let ts_str: String = int_to_str(ts)
let content: String = "[session-summary] " + trimmed + " | ts:" + ts_str
let tags: String = "[\"SessionSummary\",\"session-summary\",\"previous-session\",\"consolidate\"]"
let node_id: String = engram_node_full(
content, "SessionSummary", label,
el_from_float(0.85), el_from_float(0.85), el_from_float(1.0),
"Episodic", tags
)
if str_eq(node_id, "") {
println("[chat] session_summary_write_dated: engram write failed — summary node lost (label=" + label + ")")
return ""
}
println("[chat] session_summary_write_dated: wrote SessionSummary (" + int_to_str(str_len(content)) + " chars) label=" + label + " -> " + node_id)
return node_id
}