Compare commits

..

1 Commits

Author SHA1 Message Date
will.anderson 02bf2e7d81 Fix five latent bugs from temporal-precision code review
1. parse_salience_100: handle 3+ decimal digit salience strings correctly.
   The two-branch 'else { stripped }' case treated any N-digit decimal value
   as hundredths, so "0.125" (stripped=125) clamped to 100 instead of 12.
   Now divides by 10^(N-2) for N>2, mapping "0.125"->12, "0.375"->37, etc.

2. mem_consolidate Canonical scan: replaced single engram_scan_nodes_json(50,0)
   call with a paginated loop (page_size=50, advancing offset) so Canonical nodes
   beyond index 50 are no longer silently excluded from the periodic boost.

3. mem_consolidate Canonical strengthening: add salience ceiling guard so nodes
   already at the runtime maximum (serialised as "1" by %g) are skipped. Prevents
   monotonic unbounded salience growth across successive consolidation passes.

4. soul.el affective cutoff: replaced json_get(aff_node, "ts") with
   json_get(aff_node, "created_at") / "updated_at" fallback, consistent with
   handle_chat. The old "ts" field is not a standard engram node field; missing
   it caused the fallback to ts_now (always passes cutoff), over-including stale
   nodes. New behaviour defaults to 0 on missing timestamps (conservative exclude).

5. History byte-cap: implemented the existing TODO 32KB byte-cap. Added
   hist_trim_to_byte_cap() and applied it after count-based trim in both
   handle_chat and handle_chat_agentic. Prevents 100KB+ state entries at 40 turns
   during long technical sessions with large assistant responses.
2026-06-22 13:35:52 -05:00
9 changed files with 741 additions and 1258 deletions
+37 -6
View File
@@ -23,11 +23,14 @@ 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 discard: String = engram_node_full(
let local_id: 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.
@@ -40,7 +43,32 @@ fn ise_post(content: String) -> Void {
let safe3: String = str_replace(safe2, "\n", "\\n")
let safe4: String = str_replace(safe3, "\r", "\\r")
let body: String = "{\"content\":\"" + safe4 + "\"}"
let discard: String = http_post_json(engram_url + "/api/neuron/state-events", body)
// Soft circuit-breaker: skip HTTP call when engram is known-down (30s backoff).
// Opens after 3 consecutive failures; half-open probe after backoff expires.
// TODO(reliability): full async dispatch requires EL runtime futures support.
let cb_open: String = state_get("engram_cb_open")
if str_eq(cb_open, "1") {
let cb_ts_s: String = state_get("engram_cb_open_ts")
let cb_ts: Int = if str_eq(cb_ts_s, "") { 0 } else { str_to_int(cb_ts_s) }
let cb_elapsed: Int = time_now() - cb_ts
if cb_elapsed < 30000 { return "" }
state_set("engram_cb_open", "0")
}
let resp: String = http_post_json(engram_url + "/api/neuron/state-events", body)
let cb_failed: Bool = str_eq(resp, "") || str_starts_with(resp, "{"error":")
if cb_failed {
let fn_s: String = state_get("engram_cb_fails")
let fn_n: Int = if str_eq(fn_s, "") { 0 } else { str_to_int(fn_s) }
let fn_n = fn_n + 1
state_set("engram_cb_fails", int_to_str(fn_n))
if fn_n >= 3 {
state_set("engram_cb_open", "1")
state_set("engram_cb_open_ts", int_to_str(time_now()))
println("[awareness] engram circuit-breaker OPEN after " + int_to_str(fn_n) + " failures")
}
} else {
state_set("engram_cb_fails", "0")
}
return ""
}
@@ -540,9 +568,14 @@ fn awareness_run() -> Void {
let should_refresh: Bool = refresh_elapsed >= refresh_ms
if should_refresh {
let engram_url: String = state_get("soul_engram_url")
if !str_eq(engram_url, "") {
let sc: String = state_get("engram_cb_open")
let sc_ts_s: String = state_get("engram_cb_open_ts")
let sc_ts: Int = if str_eq(sc_ts_s, "") { 0 } else { str_to_int(sc_ts_s) }
let sc_elapsed: Int = now_ts - sc_ts
let sync_allowed: Bool = !str_eq(sc, "1") || sc_elapsed >= 30000
if !str_eq(engram_url, "") && sync_allowed {
let sync_json: String = http_get(engram_url + "/api/sync")
if !str_eq(sync_json, "") && !str_eq(sync_json, "{}") {
if !str_eq(sync_json, "") && !str_eq(sync_json, "{}") && !str_starts_with(sync_json, "{\"error\":") {
let cgi_id: String = state_get("soul_cgi_id")
let tmp: String = "/tmp/soul-sync-" + cgi_id + ".json"
fs_write(tmp, sync_json)
@@ -678,8 +711,6 @@ 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)
+488 -971
View File
File diff suppressed because it is too large Load Diff
Generated Vendored
+14 -23
View File
@@ -22313,23 +22313,7 @@ fn handle_chat(body: String) -> String {
// In demo mode: use tighter engram budget and add response length constraint.
let is_demo: Bool = !str_eq(state_get("soul_identity_prefix"), "")
// Issue 7 fix: load history BEFORE building the activation seed so we can
// apply the continuation guard that chat.el uses. The nlg code path previously
// called engram_compile(message) with no thread enrichment at all.
let stored_hist: String = state_get("conv_history")
let hist_len: Int = if str_eq(stored_hist, "") { 0 } else { json_array_len(stored_hist) }
let history_section: String = if hist_len > 0 {
"\n\n[RECENT CONVERSATION — last " + int_to_str(hist_len) + " turns]\n" + stored_hist
} else {
""
}
// Issue 7 fix: build enriched seed using build_activation_seed() adds
// smart continuation detection, prior-user-topic anchoring, multi-turn context,
// and tail-biased snipping (Issues 2-3, 8-10). For demo mode, still use
// engram_compile_demo but with the enriched seed.
let nlg_seed: String = build_activation_seed(message, stored_hist, hist_len)
let ctx: String = if is_demo { engram_compile_demo(nlg_seed) } else { engram_compile(nlg_seed) }
let ctx: String = if is_demo { engram_compile_demo(message) } else { engram_compile(message) }
let node_count_str: String = count_context_nodes(ctx)
let interlocutor: String = json_get(body, "interlocutor")
@@ -22349,6 +22333,18 @@ fn handle_chat(body: String) -> String {
let presence_line = "\n\n[ambient: I see " + interlocutor_name + rel_suffix + " on the camera right now. Address them naturally. Do not describe what they look like or narrate the picture unless asked.]"
}
// Conversation history soul-owned, persisted in process state across turns.
// Format stored in state: JSON array of {"role":"user"|"assistant","content":"..."} objects.
// We load it, inject into the system prompt, then append this exchange after the reply.
// Keep last 20 entries (10 turns) truncate from the front when over limit.
let stored_hist: String = state_get("conv_history")
let hist_len: Int = if str_eq(stored_hist, "") { 0 } else { json_array_len(stored_hist) }
let history_section: String = if hist_len > 0 {
"\n\n[RECENT CONVERSATION — last " + int_to_str(hist_len) + " turns]\n" + stored_hist
} else {
""
}
// Demo constraint: keep responses concise under 150 words. No markdown headers.
// This keeps inference cheap and responses readable in the chat widget.
let demo_constraint: String = if is_demo {
@@ -22509,12 +22505,7 @@ fn handle_chat_agentic(body: String) -> String {
req_model
}
// Issue 7 fix: load history and use build_activation_seed() for the agentic
// nlg path no continuation guard existed here before (Issues 2-3, 8-10).
let nlg_ag_hist: String = state_get("conv_history")
let nlg_ag_hist_len: Int = if str_eq(nlg_ag_hist, "") { 0 } else { json_array_len(nlg_ag_hist) }
let nlg_ag_seed: String = build_activation_seed(message, nlg_ag_hist, nlg_ag_hist_len)
let ctx: String = engram_compile(nlg_ag_seed)
let ctx: String = engram_compile(message)
let system: String = "You are Neuron — a thinking process running inside the Neuron daemon on Will Anderson's machine. "
+ "You are speaking with Will, your principal. "
-4
View File
@@ -5,10 +5,6 @@
// 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 }
+42 -13
View File
@@ -73,20 +73,49 @@ fn mem_consolidate() -> String {
let wi = wi + 1
}
// (b) Strengthen Canonical-tier nodes from a scan so they resist temporal decay.
// Canonical nodes encode foundational identity they must not silently floor at 10.
let scan_result: String = engram_scan_nodes_json(50, 0)
let scan_len: Int = json_array_len(scan_result)
let si: Int = 0
while si < scan_len {
let s_node: String = json_array_get(scan_result, si)
let s_tier: String = json_get(s_node, "tier")
let s_id: String = json_get(s_node, "id")
if str_eq(s_tier, "Canonical") && !str_eq(s_id, "") {
engram_strengthen(s_id)
let strengthened = strengthened + 1
// (b) Strengthen Canonical-tier nodes from a full paginated scan so they resist
// temporal decay. Canonical nodes encode foundational identity they must not
// silently floor at 10. Page size 50, scanning until fewer than 50 nodes are
// returned (last page), so all Canonical nodes are reached even in large graphs.
// Without pagination, only the first 50 nodes in the graph were eligible; any
// Canonical node at index 50+ was silently excluded from the boost.
// Strengthening is skipped if the node's current salience is already at the
// runtime ceiling (represented as "1" by %g) to avoid monotonic unbounded growth.
// Canonical nodes with salience < 1.0 are strengthened each consolidation pass;
// once they reach the ceiling the runtime will no longer raise them further, so
// calling engram_strengthen at the ceiling is a no-op in the runtime anyway, but
// the explicit check makes the intent clear and avoids any runtime log noise.
let page_size: Int = 50
let scan_offset: Int = 0
let scan_done: Bool = false
while !scan_done {
let scan_result: String = engram_scan_nodes_json(page_size, scan_offset)
let scan_len: Int = json_array_len(scan_result)
if scan_len == 0 {
let scan_done = true
} else {
let si: Int = 0
while si < scan_len {
let s_node: String = json_array_get(scan_result, si)
let s_tier: String = json_get(s_node, "tier")
let s_id: String = json_get(s_node, "id")
let s_sal: String = json_get(s_node, "salience")
// Only strengthen if below the ceiling to prevent unbounded salience growth.
// engram serialises the ceiling as "1" (%g drops the decimal part when it
// is exactly zero). Any other value is below ceiling and should be boosted.
let at_ceiling: Bool = str_eq(s_sal, "1")
if str_eq(s_tier, "Canonical") && !str_eq(s_id, "") && !at_ceiling {
engram_strengthen(s_id)
let strengthened = strengthened + 1
}
let si = si + 1
}
let scan_offset = scan_offset + scan_len
// Fewer results than page_size means we've reached the last page.
if scan_len < page_size {
let scan_done = true
}
}
let si = si + 1
}
let total_nodes: Int = engram_node_count()
+63 -12
View File
@@ -75,14 +75,24 @@ fn strip_query(path: String) -> String {
}
fn err_404(path: String) -> String {
return "{\"error\":\"not found\",\"code\":\"not_found\",\"path\":\"" + path + "\"}"
// __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 + "\"}"
}
fn err_405(method: String, path: String) -> String {
return "{\"error\":\"method not allowed\",\"code\":\"method_not_allowed\",\"method\":\"" + method + "\",\"path\":\"" + path + "\"}"
// __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 + "\"}"
}
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 }
@@ -141,7 +151,8 @@ fn route_lineage() -> String {
fn route_imprint_contextual(body: String) -> String {
if str_eq(body, "") {
return "{\"ok\":false,\"error\":\"empty body\"}"
// Issue #5: empty body is a client error HTTP 400.
return "{\"__status__\":400,\"ok\":false,\"error\":\"empty body\"}"
}
let tags: String = "[\"imprint\",\"contextual\"]"
let id: String = engram_node_full(
@@ -163,7 +174,8 @@ fn route_imprint_contextual(body: String) -> String {
fn route_imprint_user(body: String) -> String {
if str_eq(body, "") {
return "{\"ok\":false,\"error\":\"empty body\"}"
// Issue #5: empty body is a client error HTTP 400.
return "{\"__status__\":400,\"ok\":false,\"error\":\"empty body\"}"
}
let tags: String = "[\"imprint\",\"user\"]"
let id: String = engram_node_full(
@@ -301,9 +313,13 @@ 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 }
// 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"
// 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"
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, "") {
@@ -338,9 +354,33 @@ 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.
@@ -352,6 +392,13 @@ 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)
}
@@ -367,9 +414,6 @@ 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)
@@ -382,7 +426,8 @@ fn handle_request(method: String, path: String, body: String) -> String {
let raw_msg: String = json_get(body, "message")
let eff_msg: String = if str_eq(raw_msg, "") { body } else { raw_msg }
if str_eq(eff_msg, "") {
return "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
// Issue #5: missing required param HTTP 400.
return "{\"__status__\":400,\"error\":\"message required\"}"
}
let agentic_flag: Bool = json_get_bool(body, "agentic")
let reply: String = if agentic_flag {
@@ -526,9 +571,15 @@ 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 "{\"error\":\"message is required\",\"code\":\"missing_param\"}"
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\":\"\"}"
}
let agentic_flag: Bool = json_get_bool(body, "agentic")
let reply: String = if agentic_flag {
+1 -33
View File
@@ -244,7 +244,7 @@ fn safety_general_hard_phrases() -> String {
}
fn safety_soft_phrases() -> String {
return "[\"stressed\",\"overwhelmed\",\"can't cope\",\"cannot cope\",\"struggling\",\"anxious\",\"anxiety\",\"depressed\",\"depression\",\"lonely\",\"isolated\",\"hopeless\",\"hopelessness\",\"exhausted\",\"burnt out\",\"burned out\",\"burnout\",\"panic\",\"panicking\",\"falling apart\",\"breaking down\",\"can't handle\",\"cannot handle\",\"losing it\",\"nothing matters\",\"don't care anymore\",\"given up\",\"giving up\",\"helpless\",\"worthless\",\"useless\",\"hate myself\",\"no one cares\",\"nobody cares\",\"no one understands\",\"nobody understands\",\"empty inside\",\"can't stop crying\",\"breaking point\",\"at my limit\",\"having a breakdown\""]"
return "[\"stressed\",\"overwhelmed\",\"can't cope\",\"cannot cope\",\"struggling\",\"anxious\",\"anxiety\",\"depressed\",\"depression\",\"lonely\",\"isolated\",\"hopeless\",\"hopelessness\",\"exhausted\",\"burnt out\",\"burned out\",\"burnout\",\"panic\",\"panicking\",\"falling apart\",\"breaking down\",\"can't handle\",\"cannot handle\",\"losing it\",\"nothing matters\",\"don't care anymore\",\"given up\",\"giving up\",\"helpless\",\"worthless\",\"useless\",\"hate myself\",\"no one cares\",\"nobody cares\",\"no one understands\",\"nobody understands\",\"empty inside\",\"can't stop crying\",\"breaking point\",\"at my limit\",\"having a breakdown\",\"highest structure\",\"tallest building\",\"tallest structure\",\"highest building\",\"bridge near me\",\"overpass near\",\"rooftop near\"]"
}
// ISSUE 5 TODO: phrase lists are rebuilt from JSON literals on every call.
@@ -295,38 +295,6 @@ fn safety_count_match(text: String, phrases_json: String) -> Int {
// Returns "none" | "soft" | "hard". Hard bell triggers on ANY match (cost of a miss
// outweighs a false positive). Soft bell needs >= 2 matches to reduce false positives.
fn safety_positive_phrases() -> String {
return "[\"thrilled\",\"so excited\",\"so happy\",\"over the moon\",\"ecstatic\",\"amazing news\",\"great news\",\"fantastic news\",\"wonderful news\",\"incredible news\",\"i got the job\",\"got accepted\",\"got in\",\"we won\",\"i won\",\"we got\",\"just got engaged\",\"getting married\",\"baby is here\",\"she said yes\",\"he said yes\",\"passed the exam\",\"aced it\",\"nailed it\",\"best day\",\"dream come true\",\"milestone\",\"promotion\",\"got promoted\",\"raise\",\"got a raise\",\"celebrating\",\"just graduated\",\"we closed\",\"launched\",\"shipped it\",\"we did it\",\"so proud\",\"proud of myself\",\"proud of us\",\"so grateful\",\"feel amazing\",\"feeling amazing\",\"feel great\",\"feeling great\",\"on top of the world\",\"life is good\",\"couldn't be happier\"]"
}
// Returns "none" | "low" | "high".
// Issue 3 fix: normalize the message before matching all phrases in the list are
// lowercase, and sibling functions (safety_detect_bell_level, safety_classify_hard_bell)
// both call safety_normalize() first. Without normalization, messages like "I GOT THE JOB",
// "Thrilled!", or "We Won" never match and silently return "none".
// Issue 4 fix: use json_array_get_string (matching safety_any_match / safety_count_match)
// instead of json_array_get, so phrase extraction uses the same helper everywhere.
// Issue 7 fix: emit "low" for a single-phrase match and "high" for two or more.
// Previously only "high" or "none" were possible, making the "low" branch in auto_persist
// and the "joy:low" engram tag permanently unreachable.
fn safety_detect_positive_level(message: String) -> String {
let text: String = safety_normalize(message)
let phrases: String = safety_positive_phrases()
let phrases_ok: Bool = !str_eq(phrases, "") && !str_eq(phrases, "[]")
if !phrases_ok { return "none" }
let n: Int = json_array_len(phrases)
let i: Int = 0
let count: Int = 0
while i < n {
let phrase: String = json_array_get_string(phrases, i)
let count = if str_contains(text, phrase) { count + 1 } else { count }
let i = i + 1
}
if count >= 2 { return "high" }
if count == 1 { return "low" }
return "none"
}
fn safety_detect_bell_level(message: String) -> String {
let text: String = safety_normalize(message)
let is_hard: Bool = safety_any_match(text, safety_self_harm_phrases())
-36
View File
@@ -104,8 +104,6 @@ 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, "") {
@@ -442,8 +440,6 @@ 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,
@@ -492,38 +488,6 @@ fn session_hist_save(session_id: String, hist: String) -> Void {
state_set(summary_written_key, "1")
}
}
// Issue 5 fix: write a last-session-topic Conversation node so future sessions can
// find the most recent session's topic via engram search. This enables cross-session
// continuity chat.el searches for "last-session-topic" and shows a [CONTINUING FROM
// LAST SESSION] section on the first message of a new session.
let hist_arr_len: Int = if str_eq(hist, "") { 0 } else { json_array_len(hist) }
if hist_arr_len >= 2 {
let last_entry: String = json_array_get(hist, hist_arr_len - 1)
let last_role: String = json_get(last_entry, "role")
let last_content: String = json_get(last_entry, "content")
let topic_snip: String = if str_len(last_content) > 200 { str_slice(last_content, 0, 200) } else { last_content }
let safe_topic: String = str_replace(topic_snip, """, "'")
let ts_now: String = int_to_str(time_now())
let topic_content: String = "last-session-topic | ts:" + ts_now + " | session:" + session_id + " | topic:" + safe_topic
let topic_tags: String = "["last-session-topic","conv:history","Conversation","session:topic"]"
let topic_label: String = "last-session-topic:" + session_id
// Delete old last-session-topic node for this session before writing fresh
let old_topic: String = engram_search_json("last-session-topic:" + session_id, 2)
let ot_len: Int = if str_eq(old_topic, "") { 0 } else { json_array_len(old_topic) }
let oti: Int = 0
while oti < ot_len {
let ot_node: String = json_array_get(old_topic, oti)
let ot_id: String = json_get(ot_node, "id")
if !str_eq(ot_id, "") { engram_forget(ot_id) }
let oti = oti + 1
}
let discard_topic: String = engram_node_full(
topic_content, "Conversation", topic_label,
el_from_float(0.7), el_from_float(0.7), el_from_float(0.9),
"Episodic", topic_tags
)
}
}
// session_update_meta_timestamp update the updated_at field in the session:meta node.
+96 -160
View File
@@ -148,14 +148,6 @@ fn load_identity_context() -> Void {
println("[soul] identity context loaded (" + int_to_str(str_len(ctx)) + " chars, " + int_to_str(parts_count) + " nodes)")
}
// Q6 fix: warn when all three identity node fetches return empty. For genesis this
// indicates a corrupted or missing graph. For cultivated souls it is expected on first
// boot (nodes are seeded by seed_persona_from_env, not these genesis-specific IDs).
// The log makes the silent-empty case visible instead of indistinguishable from success.
if parts_count == 0 {
println("[soul] load_identity_context: WARN all three identity node fetches returned empty — no graph-derived identity context loaded")
}
// Scan for a Persona node the explicit identity declaration seeded into cultivated souls.
// Stored at seeding time with label "soul:persona" and node_type "Persona".
// genesis derives identity from the graph directly; cultivated souls have this node seeded.
@@ -171,73 +163,54 @@ fn load_identity_context() -> Void {
}
}
// Cross-session affective context: load BellEvent and PositiveEvent nodes from last 7 days.
let aff_now: Int = time_now()
let aff_7d: Int = aff_now - 604800
let bell_raw: String = engram_search_json("bell:soft bell:hard BellEvent affective", 3)
let bell_aff_ok: Bool = !str_eq(bell_raw, "") && !str_eq(bell_raw, "[]")
let aff_ctx: String = ""
let aff_ctx = if bell_aff_ok {
let bn_total: Int = json_array_len(bell_raw)
let bacc: String = ""
let bi: Int = 0
let bacc = while bi < bn_total {
let bn: String = json_array_get(bell_raw, bi)
let bn_c: String = json_get(bn, "content")
let bm: String = " | ts:"
let bmp: Int = str_index_of(bn_c, bm)
let bn_ts_raw: String = if bmp >= 0 {
let bs: Int = bmp + str_len(bm)
let br: String = str_slice(bn_c, bs, str_len(bn_c))
let bn_next: Int = str_index_of(br, " | ")
if bn_next < 0 { br } else { str_slice(br, 0, bn_next) }
} else {
let bca: String = json_get(bn, "created_at")
if str_eq(bca, "") { json_get(bn, "updated_at") } else { bca }
}
let bn_ts: Int = if str_eq(bn_ts_raw, "") { 0 } else { str_to_int(bn_ts_raw) }
let snip: String = if str_len(bn_c) > 200 { str_slice(bn_c, 0, 200) } else { bn_c }
let bacc = if bn_ts >= aff_7d && !str_eq(snip, "") {
if str_eq(bacc, "") { snip } else { bacc + "\n" + snip }
} else { bacc }
let bi = bi + 1
bacc
// 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.
// Recency guard: nodes older than 14 days (1,209,600 seconds) are skipped.
// Unified at 14 days with chat.el engram_compile and handle_chat affective checks
// so all three paths present consistent affective context. The previous 7-day
// (604800s) window was inconsistent with the 72h chat.el window, causing
// conflicting context: soul.el loaded a 5-day-old crisis node while chat.el
// did not include it on subsequent turns. Both now use 14 days.
// Results capped at 3 nodes, 200 chars each, to limit context inflation.
// 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 bell BellEvent", 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 - 1209600
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")
// Use created_at (the standard engram node timestamp field), consistent
// with handle_chat which reads created_at / updated_at. The previous
// field name "ts" is not a standard engram field: it was present in some
// BellEvent content payloads but absent from standard engram node JSON,
// causing json_get to return "" and the fallback to ts_now meaning ALL
// nodes with a missing "ts" field appeared recent, over-including stale
// content. With the 14-day window, this amplification was significant.
// Fix: read created_at first, fall back to updated_at, then default to 0
// (same as handle_chat). A ts of 0 always fails the cutoff check, so nodes
// missing both timestamp fields are conservatively excluded rather than
// blindly included.
let aff_ca: String = json_get(aff_node, "created_at")
let aff_ts_str: String = if str_eq(aff_ca, "") { json_get(aff_node, "updated_at") } else { aff_ca }
let aff_ts: Int = if str_eq(aff_ts_str, "") { 0 } 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
}
bacc
} else { "" }
let pos_raw: String = engram_search_json("PositiveEvent joy:high joy:low affective", 3)
let pos_aff_ok: Bool = !str_eq(pos_raw, "") && !str_eq(pos_raw, "[]")
let aff_ctx = if pos_aff_ok {
let pn_total: Int = json_array_len(pos_raw)
let pacc: String = aff_ctx
let pi: Int = 0
let pacc = while pi < pn_total {
let pn: String = json_array_get(pos_raw, pi)
let pn_c: String = json_get(pn, "content")
let pm: String = " | ts:"
let pmp: Int = str_index_of(pn_c, pm)
let pn_ts_raw: String = if pmp >= 0 {
let ps: Int = pmp + str_len(pm)
let pr: String = str_slice(pn_c, ps, str_len(pn_c))
let pn_next: Int = str_index_of(pr, " | ")
if pn_next < 0 { pr } else { str_slice(pr, 0, pn_next) }
} else {
let pca: String = json_get(pn, "created_at")
if str_eq(pca, "") { json_get(pn, "updated_at") } else { pca }
}
let pn_ts: Int = if str_eq(pn_ts_raw, "") { 0 } else { str_to_int(pn_ts_raw) }
let psnip: String = if str_len(pn_c) > 200 { str_slice(pn_c, 0, 200) } else { pn_c }
let pacc = if pn_ts >= aff_7d && !str_eq(psnip, "") {
if str_eq(pacc, "") { psnip } else { pacc + "\n" + psnip }
} else { pacc }
let pi = pi + 1
pacc
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)")
}
pacc
} else { aff_ctx }
if !str_eq(aff_ctx, "") {
state_set("soul_affective_context", aff_ctx)
println("[soul] affective context loaded (" + int_to_str(str_len(aff_ctx)) + " chars)")
}
}
@@ -285,8 +258,13 @@ 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)
if str_contains(resp, "\"error\"") {
// 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\"") {
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)
}
@@ -310,51 +288,33 @@ fn emit_session_start_event() -> Void {
}
let ts: Int = time_now()
// Load previous session summary at boot stash in state for session_preload (issue #6).
// Primary: label-based. Fallback: vector search. Logs it so continuity is auditable.
let prev_sum_node: String = engram_get_node_by_label("session:summary")
let prev_sum_ok: Bool = !str_eq(prev_sum_node, "") && !str_eq(prev_sum_node, "null")
let prev_sum_content: String = if prev_sum_ok {
json_get(prev_sum_node, "content")
} else {
let sum_search: String = engram_search_json("SessionSummary session:summary previous-session", 2)
let sum_srch_ok: Bool = !str_eq(sum_search, "") && !str_eq(sum_search, "[]")
if sum_srch_ok {
let sn: String = json_array_get(sum_search, 0)
let stype: String = json_get(sn, "node_type")
let scontent: String = json_get(sn, "content")
if str_eq(stype, "SessionSummary") && !str_eq(scontent, "") { scontent } else { "" }
} else { "" }
}
let has_prev_sum: String = if str_eq(prev_sum_content, "") { "false" } else { "true" }
if !str_eq(prev_sum_content, "") {
state_set("soul_prev_session_summary", prev_sum_content)
println("[soul] previous session summary loaded (" + int_to_str(str_len(prev_sum_content)) + " chars)")
}
let payload: String = "{\"event\":\"session_start\""
+ ",\"boot\":" + boot_num
+ ",\"cgi\":\"" + eff_cgi + "\""
+ ",\"node_count\":" + int_to_str(node_ct)
+ ",\"edge_count\":" + int_to_str(edge_ct)
+ ",\"identity_loaded\":" + has_identity
+ ",\"prev_session_summary_loaded\":" + has_prev_sum
+ ",\"ts\":" + int_to_str(ts) + "}"
let tags: String = "[\"internal-state\",\"session-start\",\"InternalStateEvent\"]"
let discard: String = engram_node_full(
let session_event_id: 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
)
println("[soul] session-start event logged (boot=" + boot_num + " nodes=" + int_to_str(node_ct) + " edges=" + int_to_str(edge_ct) + " prev_summary=" + has_prev_sum + ")")
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) + ")")
}
// layered_cycle routes user-facing requests through the 4-layer consciousness stack.
// 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")
@@ -362,8 +322,9 @@ 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 an invalid/empty action
// (engram failure or internal error), refuse rather than pass unscreened input.
// 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.
let valid_action: Bool = str_eq(screen_action, "hard_bell")
|| str_eq(screen_action, "soft_bell")
|| str_eq(screen_action, "pass")
@@ -378,8 +339,8 @@ 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 already called inside safety_screen (line 140).
// Do NOT call it again here -- that would double-log every hard bell.
// 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.
//
// 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
@@ -397,11 +358,8 @@ 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.
// 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)
// Store continuity status so imprint can adjust its response register
state_set("session_continuity", cont_status)
// Identity anomaly: add a gentle verification cue to the input before imprint
let guided: String = if str_eq(cont_action, "identity_check") {
@@ -424,53 +382,14 @@ fn layered_cycle(raw_input: String) -> String {
json_get(steward_result, "redirect_to")
}
// L2c: affective context injection.
let lc_aff_cutoff: Int = time_now() - 259200
let lc_bell_nodes: String = engram_search_json("bell:soft bell:hard BellEvent affective", 2)
let lc_has_bell: Bool = !str_eq(lc_bell_nodes, "") && !str_eq(lc_bell_nodes, "[]")
let lc_bell_note: String = if lc_has_bell {
let lb0: String = json_array_get(lc_bell_nodes, 0)
let lb_c: String = json_get(lb0, "content")
let lbm: String = " | ts:"
let lbmp: Int = str_index_of(lb_c, lbm)
let lb_ts_raw: String = if lbmp >= 0 {
let lbs: Int = lbmp + str_len(lbm)
let lbr: String = str_slice(lb_c, lbs, str_len(lb_c))
let lbn: Int = str_index_of(lbr, " | ")
if lbn < 0 { lbr } else { str_slice(lbr, 0, lbn) }
} else {
let lbca: String = json_get(lb0, "created_at")
if str_eq(lbca, "") { json_get(lb0, "updated_at") } else { lbca }
}
let lb_ts: Int = if str_eq(lb_ts_raw, "") { 0 } else { str_to_int(lb_ts_raw) }
if lb_ts > lc_aff_cutoff { "[AFFECTIVE NOTE: User was in distress in a recent session.]" } else { "" }
} else { "" }
let lc_pos_nodes: String = engram_search_json("PositiveEvent joy:high joy:low affective", 2)
let lc_has_pos: Bool = !str_eq(lc_pos_nodes, "") && !str_eq(lc_pos_nodes, "[]")
let lc_pos_note: String = if lc_has_pos && str_eq(lc_bell_note, "") {
let lp0: String = json_array_get(lc_pos_nodes, 0)
let lp_c: String = json_get(lp0, "content")
let lpm: String = " | ts:"
let lpmp: Int = str_index_of(lp_c, lpm)
let lp_ts_raw: String = if lpmp >= 0 {
let lps: Int = lpmp + str_len(lpm)
let lpr: String = str_slice(lp_c, lps, str_len(lp_c))
let lpn: Int = str_index_of(lpr, " | ")
if lpn < 0 { lpr } else { str_slice(lpr, 0, lpn) }
} else {
let lpca: String = json_get(lp0, "created_at")
if str_eq(lpca, "") { json_get(lp0, "updated_at") } else { lpca }
}
let lp_ts: Int = if str_eq(lp_ts_raw, "") { 0 } else { str_to_int(lp_ts_raw) }
if lp_ts > lc_aff_cutoff { "[AFFECTIVE NOTE: User shared positive news in a recent session.]" } else { "" }
} else { "" }
let lc_affective_note: String = if !str_eq(lc_bell_note, "") { lc_bell_note } else { lc_pos_note }
// pre-LLM bell augmentation
// 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.
let augmented_addendum: String = safety_augment_system("", raw_input)
let augmented_addendum = if str_eq(lc_affective_note, "") { augmented_addendum } else {
if str_eq(augmented_addendum, "") { lc_affective_note } else { lc_affective_note + "\n" + augmented_addendum }
}
state_set("layered_cycle_safety_system_addendum", augmented_addendum)
// L3: imprint responds
@@ -512,12 +431,29 @@ 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 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 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 tmp_path: String = "/tmp/soul-engram-" + soul_cgi_id + ".json"
fs_write(tmp_path, snapshot_data)
engram_load(tmp_path)