Compare commits

...

13 Commits

Author SHA1 Message Date
will.anderson 4a44c24bfb fix(recall): wire id_in_seen guards into session_preload node renders
Neuron Soul CI / build (push) Has been cancelled
Deploy Soul to GKE / deploy (push) Failing after 7m29s
All 8 session_preload node accesses (3 profile, 2 work, 2 project, 1
summary) now check id_in_seen(node_id, seen_ids) before including
content. seen_ids is populated by engram_compile via state and covers
all nodes already in the activation+search context block. Prevents
high-salience nodes from appearing twice in the system prompt.
2026-06-22 15:08:30 -05:00
will.anderson ac1991fe8c Merge branch 'fix/emergency-regressions'
Neuron Soul CI / build (push) Has been cancelled
Deploy Soul to GKE / deploy (push) Failing after 11m10s
2026-06-22 14:53:10 -05:00
will.anderson f2b63f0048 fix(emergency): repair session-continuity regressions from prior merge 2026-06-22 14:51:51 -05:00
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
will.anderson 33cb1138f4 fix(recall): set threshold=25 in all engram_compile_ranked variants 2026-06-22 13:58:17 -05:00
will.anderson ec7efdeeb7 fix(recall): engram score float parsing — pad to 2 decimals before strip 2026-06-22 13:57:33 -05:00
+183 -148
View File
@@ -35,6 +35,41 @@ fn engram_numeric_valid(s: String) -> Bool {
return true
}
// parse_float_x100 parse a float string like "0.85", "0.9", "1.0" into an integer
// scaled by 100 (so "0.85" -> 85, "0.9" -> 90, "1.0" -> 100). Uses only integer
// arithmetic because el has no float math. Normalises to exactly 2 decimal digits
// before stripping the dot so 1-decimal values like "0.9" are not misread as 9.
// Returns 70 (a safe mid-range default) for empty or structurally invalid strings.
fn parse_float_x100(s: String) -> Int {
if str_eq(s, "") { return 70 }
if !str_contains(s, ".") {
// Integer input: treat as a whole number * 100 (e.g. "1" -> 100)
let whole: Int = str_to_int(s)
return whole * 100
}
// Split at the dot. str_slice(s, 0, dot_pos) gives left, rest gives right.
let dot_pos: Int = str_index_of(s, ".")
let left: String = str_slice(s, 0, dot_pos)
let right_raw: String = str_slice(s, dot_pos + 1, str_len(s))
// Normalise right side to exactly 2 decimal digits.
let right: String = if str_eq(right_raw, "") {
"00"
} else {
if str_len(right_raw) == 1 {
right_raw + "0"
} else {
if str_len(right_raw) >= 3 {
str_slice(right_raw, 0, 2)
} else {
right_raw
}
}
}
let left_val: Int = if str_eq(left, "") { 0 } else { str_to_int(left) }
let right_val: Int = str_to_int(right)
return left_val * 100 + right_val
}
// engram_score_node compute a recency x relevance score for a single engram
// node JSON object. Higher is better. Score = salience * importance * recency_factor.
// recency_factor decays linearly over 30 days: nodes updated today score 1.0,
@@ -50,13 +85,13 @@ fn engram_score_node(node_json: String) -> Int {
let tier_str: String = json_get(node_json, "tier")
// Q1 fix: validate before str_to_int. Non-numeric values fall back to safe defaults.
// Parse as floats via * 100 integer arithmetic (el has no float math).
// parse_float_x100 handles 1- and 2-decimal floats correctly ("0.9" -> 90, "0.85" -> 85).
let salience_100: Int = if !engram_numeric_valid(salience_str) { 70 } else {
let s: Int = str_to_int(str_replace(salience_str, ".", ""))
let s: Int = parse_float_x100(salience_str)
if s > 100 { 100 } else { if s < 0 { 0 } else { s } }
}
let importance_100: Int = if !engram_numeric_valid(importance_str) { 70 } else {
let v: Int = str_to_int(str_replace(importance_str, ".", ""))
let v: Int = parse_float_x100(importance_str)
if v > 100 { 100 } else { if v < 0 { 0 } else { v } }
}
@@ -97,7 +132,7 @@ fn engram_render_node(node_json: String) -> String {
}
let salience_str: String = json_get(node_json, "salience")
let sal_100: Int = if str_eq(salience_str, "") { 0 } else {
let s: Int = str_to_int(str_replace(salience_str, ".", ""))
let s: Int = parse_float_x100(salience_str)
if s > 100 { 100 } else { if s < 0 { 0 } else { s } }
}
let salience_hint: String = if str_eq(salience_str, "") { "" } else {
@@ -177,8 +212,8 @@ 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)
// Threshold: includes moderately-relevant older nodes (score >= 15).
let above_thresh: Bool = score >= 15
// Threshold 25: sal=0.5 * imp=0.5 * recency=1.0 -> 50*50*100/10000 = 25.
let above_thresh: Bool = score >= 25
let idx_marker: String = "|" + int_to_str(ci) + "|"
let already_picked: Bool = str_contains(selected_indices, idx_marker)
let is_better: Bool = score > best_score && above_thresh && !already_picked
@@ -198,125 +233,7 @@ fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> String {
}
if str_eq(selected_nodes, "") { return "" }
return "[" + selected_nodes + "]"
}ory.el"
fn chat_default_model() -> String {
let m: String = state_get("soul_model")
if !str_eq(m, "") {
return m
}
let e: String = env("SOUL_LLM_MODEL")
if !str_eq(e, "") {
return e
}
return "claude-sonnet-4-5"
}
// engram_score_node — compute a recency x relevance score for a single engram
// node JSON object. Higher is better. Score = salience * importance * recency_factor.
// recency_factor decays linearly over 30 days: nodes updated today score 1.0,
// 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.
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")
// Parse as floats via * 100 integer arithmetic (el has no float math)
let salience_100: Int = if str_eq(salience_str, "") { 70 } else {
let s: Int = str_to_int(str_replace(salience_str, ".", ""))
// Clamp to 0-100 range (value was e.g. "0.85" -> parsed "085" = 85)
if s > 100 { 100 } else { if s < 0 { 0 } else { s } }
}
let importance_100: Int = if str_eq(importance_str, "") { 70 } else {
let v: Int = str_to_int(str_replace(importance_str, ".", ""))
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 created_ts: Int = str_to_int(created_str)
let age_secs: Int = now_ts - created_ts
let age_days: Int = 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
}
// engram_compile_ranked — build a context string from a JSON array of node objects,
// ordered best-first by score. Only nodes above threshold=15 are included.
// With corrected parsing: sal=0.5 * imp=0.5 at max recency scores 25; threshold 15
// gives headroom for moderately-relevant older nodes while filtering near-zero noise.
// Returns at most max_nodes entries. max_nodes must not exceed 20 (sentinel limit).
fn engram_compile_ranked(nodes_json: String, max_nodes: Int) -> 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 selected_indices: String = ""
let selected_nodes: String = ""
let pass: Int = 0
while pass < max_nodes && pass < total {
let best_idx: Int = -1
let best_score: Int = -1
let ci: Int = 0
while ci < total {
let node: String = json_array_get(nodes_json, ci)
let score: Int = engram_score_node(node)
// 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)
let is_better: Bool = score > best_score && above_thresh && !already_picked
let best_score = if is_better { score } else { best_score }
let best_idx = if is_better { ci } else { best_idx }
let ci = ci + 1
}
if best_idx < 0 {
let pass = total // break
} else {
let chosen: String = json_array_get(nodes_json, best_idx)
let sep: String = if str_eq(selected_nodes, "") { "" } else { "," }
let selected_nodes = selected_nodes + sep + chosen
let selected_indices = selected_indices + "|" + int_to_str(best_idx) + "|"
}
let pass = pass + 1
}
if str_eq(selected_nodes, "") { return "" }
return "[" + selected_nodes + "]"
}
if str_eq(selected, "") { return "" }
// Strip the _sel_N sentinel fields that were used for duplicate-detection bookkeeping.
// The sentinels have the form "\"_sel_N\":1," (trailing comma, space before next key).
// We injected them as the first field in each object, so the pattern is predictable.
// Because el has no regex, remove up to 20 possible sentinel variants by literal replace.
let clean: String = "[" + selected + "]"
let c0: String = str_replace(clean, "\"_sel_0\":1,", "")
let c1: String = str_replace(c0, "\"_sel_1\":1,", "")
let c2: String = str_replace(c1, "\"_sel_2\":1,", "")
let c3: String = str_replace(c2, "\"_sel_3\":1,", "")
let c4: String = str_replace(c3, "\"_sel_4\":1,", "")
let c5: String = str_replace(c4, "\"_sel_5\":1,", "")
let c6: String = str_replace(c5, "\"_sel_6\":1,", "")
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,", "")
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 {
@@ -460,6 +377,38 @@ fn engram_nodes_merge(a: String, b: String) -> String {
return engram_dedup_nodes("[" + ai + "," + bi + "]")
}
// id_in_seen true when node_id appears in the pipe-delimited seen set.
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 pipe-delimited seen set.
fn add_to_seen(seen: String, node_id: String) -> String {
if str_eq(node_id, "") { return seen }
if id_in_seen(node_id, seen) { return seen }
return seen + "|" + node_id + "|"
}
// engram_extract_ids extract the "id" field from each node in a JSON array,
// returning a pipe-delimited string suitable for 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 seen: String = ""
let i: Int = 0
while i < total {
let node: String = json_array_get(nodes_json, i)
let node_id: String = json_get(node, "id")
let seen = add_to_seen(seen, node_id)
let i = i + 1
}
return seen
}
// Q4 note: engram_compile has no cache or circuit-breaker at the EL layer.
// Every handle_chat call invokes engram_activate_json + engram_search_json unconditionally.
// If the engram backend is repeatedly unreachable (e.g., during startup or after a crash),
@@ -549,6 +498,10 @@ fn engram_compile(intent: String) -> String {
let merged: String = engram_nodes_merge(merged, recall_boost)
let merged_nodes: String = merged
// Publish compiled IDs to state so session_preload can skip duplicate nodes.
let ids_from_merged: String = engram_extract_ids(merged_nodes)
state_set("engram_compile_seen_ids", ids_from_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)
@@ -613,12 +566,8 @@ fn engram_compile(intent: String) -> String {
let sep_ma: String = if !str_eq(main_part, "") && !str_eq(affective_part, "") { "\n" } else { "" }
let ctx: String = main_part + sep_ma + affective_part
// Q7 fix: store recall status so build_system_prompt can include a hint to the LLM
// distinguishing "no memories yet" (cold start) from "memory system unreachable".
// Values: "ok" | "empty" | "unavailable"
let any_ok: Bool = act_ok || srch_ok || scan_ok || affective_ok
let all_failed: Bool = act_failed && srch_failed
let recall_status: String = if any_ok { "ok" } else { if all_failed { "unavailable" } else { "empty" } }
// Publish recall_status for build_system_prompt: "ok" when ctx has content, "empty" otherwise.
let recall_status: String = if str_eq(ctx, "") { "empty" } else { "ok" }
state_set("engram_recall_status", recall_status)
if str_eq(ctx, "") {
@@ -680,6 +629,17 @@ fn build_system_prompt(ctx: String, chat_mode: Bool) -> String {
"\n\n[IDENTITY GRAPH — who you are, loaded from your engram]\n" + id_ctx
}
// soul_affective_context is loaded at boot by load_identity_context() with BellEvent/
// PositiveEvent nodes from the last 7 days. Surfaced here so the LLM sees historical
// emotional patterns from prior sessions at every turn.
// Issue 1 fix: declare affective_boot_block before it is referenced in the return.
let boot_aff_ctx: String = state_get("soul_affective_context")
let affective_boot_block: String = if str_eq(boot_aff_ctx, "") {
""
} else {
"\n\n[CROSS-SESSION EMOTIONAL CONTEXT — from prior sessions]\n" + boot_aff_ctx
}
// Q7 fix: if recall produced no results, include a hint so the LLM can respond
// authentically ("I seem to be starting fresh" vs "memory system may be down")
// rather than silently acting as if it has context it doesn't have.
@@ -874,6 +834,29 @@ fn conv_history_load() -> String {
return content
}
// session_preload_bullets render up to max_bullets nodes from a JSON array as
// bullet lines, truncating content at snip_len chars each.
fn session_preload_bullets(nodes: String, max_bullets: Int, snip_len: Int) -> String {
if str_eq(nodes, "") { return "" }
if str_eq(nodes, "[]") { return "" }
let total: Int = json_array_len(nodes)
let limit: Int = if max_bullets < total { max_bullets } else { total }
let bullets: String = ""
let i: Int = 0
while i < limit {
let node: String = json_array_get(nodes, i)
let content: String = json_get(node, "content")
let snip: String = if str_len(content) > snip_len { str_slice(content, 0, snip_len) } else { content }
let bullets = if str_eq(snip, "") {
bullets
} else {
if str_eq(bullets, "") { "- " + snip } else { bullets + "\n- " + snip }
}
let i = i + 1
}
return bullets
}
fn handle_chat(body: String) -> String {
let message: String = json_get(body, "message")
if str_eq(message, "") {
@@ -959,9 +942,10 @@ fn handle_chat(body: String) -> String {
}
}
// Issue 4 fix: engram_compile_multi adds entity + emotion fan-out seeds
let ctx: String = engram_compile_multi(activation_seed, message)
let system: String = affective_prefix + build_system_prompt(ctx)
let ctx: String = engram_compile(activation_seed)
let system: String = affective_prefix + build_system_prompt(ctx, true)
let seen_ids: String = state_get("engram_compile_seen_ids")
// 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
@@ -991,21 +975,24 @@ fn handle_chat(body: String) -> String {
let bullets: String = ""
let bullets = if pn > 0 {
let n0: String = json_array_get(profile_nodes, 0)
let id0: 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 id_in_seen(id0, seen_ids) || str_eq(s0, "") { bullets } else { "- " + s0 }
} else { bullets }
let bullets = if pn > 1 {
let n1: String = json_array_get(profile_nodes, 1)
let id1: 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 id_in_seen(id1, seen_ids) || str_eq(s1, "") { bullets } else { bullets + "\n- " + s1 }
} else { bullets }
let bullets = if pn > 2 {
let n2: String = json_array_get(profile_nodes, 2)
let id2: 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 id_in_seen(id2, seen_ids) || str_eq(s2, "") { bullets } else { bullets + "\n- " + s2 }
} else { bullets }
bullets
} else { "" }
@@ -1015,15 +1002,17 @@ fn handle_chat(body: String) -> String {
let wb: String = ""
let wb = if wn > 0 {
let w0: String = json_array_get(work_nodes, 0)
let wid0: 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 id_in_seen(wid0, seen_ids) || str_eq(ws0, "") { wb } else { "- " + ws0 }
} else { wb }
let wb = if wn > 1 {
let w1: String = json_array_get(work_nodes, 1)
let wid1: 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 id_in_seen(wid1, seen_ids) || str_eq(ws1, "") { wb } else { wb + "\n- " + ws1 }
} else { wb }
wb
} else { "" }
@@ -1033,24 +1022,27 @@ fn handle_chat(body: String) -> String {
let pb: String = ""
let pb = if prn > 0 {
let pr0: String = json_array_get(project_nodes, 0)
let prid0: 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 id_in_seen(prid0, seen_ids) || str_eq(ps0, "") { pb } else { "- " + ps0 }
} else { pb }
let pb = if prn > 1 {
let pr1: String = json_array_get(project_nodes, 1)
let prid1: 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 id_in_seen(prid1, seen_ids) || str_eq(ps1, "") { 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 snid0: 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 id_in_seen(snid0, seen_ids) || str_eq(ss0, "") { "" } else { "- " + ss0 }
} else { "" }
let hp: Bool = !str_eq(profile_bullets, "")
@@ -1124,12 +1116,29 @@ fn handle_chat(body: String) -> String {
state_set("conv_history", final_hist)
conv_history_persist(final_hist)
// Automatic session-end summary: write/overwrite the SessionSummary node on each turn
// so process restarts always have a continuity snapshot (no shutdown hook needed).
// Uses autogenerate (no LLM) so it is cheap the node is overwritten not appended.
let auto_sum: String = session_summary_autogenerate(final_hist)
if !str_eq(auto_sum, "") {
let discard_sum: String = session_summary_write(auto_sum)
// Session-end summary hook: write a dated SessionSummary node once per boot when
// the conversation reaches >= 5 user turns (10 hist entries = 5 user+assistant pairs).
// Uses a per-boot label ("session:summary:<boot_ts>") so summaries accumulate across
// sessions instead of overwriting a single global node. A state flag prevents rewriting
// on every subsequent turn once the threshold is crossed.
let final_hist_len: Int = json_array_len(final_hist)
if final_hist_len >= 10 {
let already_wrote: String = state_get("session_summary_written")
if str_eq(already_wrote, "") {
// Derive (or create) a stable boot-scoped session id.
let boot_id: String = state_get("session_boot_id")
let boot_id = if str_eq(boot_id, "") {
let new_id: String = int_to_str(time_now())
state_set("session_boot_id", new_id)
new_id
} else { boot_id }
let sess_label: String = "session:summary:" + boot_id
let auto_sum: String = session_summary_autogenerate(final_hist)
if !str_eq(auto_sum, "") {
let discard_sum: String = session_summary_write_dated(auto_sum, sess_label)
state_set("session_summary_written", "1")
}
}
}
let activation_nodes: String = engram_activate_json(message, 2)
@@ -1591,7 +1600,7 @@ fn handle_chat_agentic(body: String) -> String {
if str_eq(screen_action, "hard_bell") {
safety_log_bell("hard", json_get(screen_result, "reason"), str_slice(message, 0, 80))
return "{\"reply\":\"" + json_safe(safety_validate("", "hard_bell")) + "\",\"model\":\"\",\"agentic\":true,\"tools_used\":[]}"
}
let req_model: String = json_get(body, "model")
let model: String = if str_eq(req_model, "") { chat_default_model() } else { req_model }
@@ -2212,6 +2221,32 @@ fn session_summary_write(summary_text: String) -> String {
return node_id
}
// session_summary_write_dated write a SessionSummary node with a caller-supplied dated label.
// Unlike session_summary_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>").
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(0.9), el_from_float(0.8), 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
}
// session_summary_autogenerate build a minimal summary from conversation history without LLM.
// Extracts user message snippets (first 80 chars each, up to 5 turns).
// Used as the automatic session-end hook so every turn produces a continuity snapshot.