Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 will.anderson
|
2865d6ad26 |
@@ -150,43 +150,9 @@ fn engram_compile(intent: String) -> String {
|
||||
""
|
||||
}
|
||||
|
||||
// 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.
|
||||
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)
|
||||
let bn_ts_raw: String = if ts_pos >= 0 {
|
||||
let ts_start: Int = ts_pos + str_len(ts_marker)
|
||||
let rest: String = str_slice(bn_content, ts_start, str_len(bn_content))
|
||||
let next_sep: Int = str_index_of(rest, " | ")
|
||||
if next_sep < 0 { rest } else { str_slice(rest, 0, next_sep) }
|
||||
} else {
|
||||
let ca: String = json_get(bn0, "created_at")
|
||||
if str_eq(ca, "") { json_get(bn0, "updated_at") } else { ca }
|
||||
}
|
||||
let bn_ts: Int = if str_eq(bn_ts_raw, "") { 0 } else { str_to_int(bn_ts_raw) }
|
||||
if bn_ts > cutoff_ts { bn0 } else { "" }
|
||||
} 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 ctx: String = act_part + sep1 + srch_part + sep2 + scan_part
|
||||
|
||||
if str_eq(ctx, "") { return "" }
|
||||
|
||||
@@ -247,6 +213,11 @@ fn hist_append(hist: String, role: String, content: String) -> String {
|
||||
}
|
||||
|
||||
fn hist_trim(hist: String) -> String {
|
||||
// Issue #9 (fragile parser): uses manual str_index_of scan rather than a real
|
||||
// JSON parser. If the history JSON does not contain the expected marker pattern
|
||||
// (e.g. corrupted or truncated), returns the unmodified hist silently — silent
|
||||
// data corruption that causes LLM context-length errors on the next turn.
|
||||
// TODO: replace with json_array_slice() once available in the EL runtime.
|
||||
let inner: String = str_slice(hist, 1, str_len(hist) - 1)
|
||||
let marker: String = "{\"role\":"
|
||||
let i1: Int = str_index_of(inner, marker)
|
||||
@@ -260,69 +231,6 @@ fn hist_trim(hist: String) -> String {
|
||||
return hist
|
||||
}
|
||||
|
||||
// hist_trim_with_bell_guard — trim the history window exactly as hist_trim does, but
|
||||
// before dropping the oldest user/assistant pair check whether the user turn triggered
|
||||
// a bell event. If it did, write a preservation node to engram so the distress exchange
|
||||
// survives the 20-turn window. The LLM window drops it; engram retains it permanently
|
||||
// and engram_compile will surface it again via the affective context path.
|
||||
fn hist_trim_with_bell_guard(hist: String) -> String {
|
||||
// Extract the first turn (should be a user message) to inspect it.
|
||||
let inner: String = str_slice(hist, 1, str_len(hist) - 1)
|
||||
let marker: String = "{\"role\":"
|
||||
let i1: Int = str_index_of(inner, marker)
|
||||
// i1 is the start of the first entry within inner.
|
||||
// Find where the second entry begins to delimit the first entry's JSON.
|
||||
let tail1: String = str_slice(inner, i1 + 1, str_len(inner))
|
||||
let i2: Int = str_index_of(tail1, marker)
|
||||
// The first entry spans from i1 to (i1 + 1 + i2 - 1) within inner.
|
||||
let first_entry_raw: String = if i2 > 0 {
|
||||
str_slice(inner, i1, i1 + 1 + i2 - 1)
|
||||
} else {
|
||||
str_slice(inner, i1, str_len(inner))
|
||||
}
|
||||
let first_role: String = json_get(first_entry_raw, "role")
|
||||
let first_content: String = json_get(first_entry_raw, "content")
|
||||
|
||||
// Only inspect user turns — assistant content doesn't carry bell signals.
|
||||
let bell_level: String = if str_eq(first_role, "user") {
|
||||
safety_detect_bell_level(first_content)
|
||||
} else {
|
||||
"none"
|
||||
}
|
||||
|
||||
// If the turn being evicted triggered a bell, preserve it to engram.
|
||||
// This is distinct from the BellEvent written by auto_persist: that node
|
||||
// carries a short summary. This node carries the full exchange content so
|
||||
// it is recoverable for clinical/continuity review.
|
||||
if !str_eq(bell_level, "none") {
|
||||
let ts: Int = time_now()
|
||||
let ts_str: String = int_to_str(ts)
|
||||
let safe_content: String = str_replace(first_content, "\"", "'")
|
||||
let preserve_content: String = "PRESERVED_BELL:" + bell_level
|
||||
+ " | evicted_at:" + ts_str
|
||||
+ " | message:" + safe_content
|
||||
let preserve_tags: String = "[\"bell-history\",\"bell:" + bell_level + "\",\"evicted\",\"affective\",\"BellEvent\"]"
|
||||
let discard: String = engram_node_full(
|
||||
preserve_content,
|
||||
"BellEvent",
|
||||
"bell:" + bell_level + ":preserved",
|
||||
el_from_float(0.9),
|
||||
el_from_float(0.9),
|
||||
el_from_float(1.0),
|
||||
"Episodic",
|
||||
preserve_tags
|
||||
)
|
||||
}
|
||||
|
||||
// Now perform the standard trim (drop oldest 2 entries = 1 user + 1 assistant pair).
|
||||
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)) + "]"
|
||||
}
|
||||
return hist
|
||||
}
|
||||
|
||||
// clean_llm_response — strips GPT-2 BPE byte-to-unicode artifacts that vLLM
|
||||
// emits when the tokenizer hasn't decoded back to raw bytes.
|
||||
//
|
||||
@@ -368,10 +276,20 @@ fn conv_history_load() -> String {
|
||||
fn handle_chat(body: String) -> String {
|
||||
let message: String = json_get(body, "message")
|
||||
if str_eq(message, "") {
|
||||
return "{\"error\":\"message is required\",\"response\":\"\"}"
|
||||
// Issue #5: missing required param — HTTP 400.
|
||||
return "{\"__status__\":400,\"error\":\"message is required\",\"response\":\"\"}"
|
||||
}
|
||||
|
||||
// Load history BEFORE compiling context so we can anchor activation to the thread.
|
||||
//
|
||||
// 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.
|
||||
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) }
|
||||
@@ -477,7 +395,8 @@ fn handle_chat(body: String) -> String {
|
||||
|| str_starts_with(raw_response, "{\"type\":\"error\"")
|
||||
|| str_contains(raw_response, "authentication_error")
|
||||
if is_error {
|
||||
return "{\"error\":\"llm unavailable\",\"response\":\"\"}"
|
||||
// Issue #6: LLM failure — HTTP 503 (service unavailable).
|
||||
return "{\"__status__\":503,\"error\":\"llm unavailable\",\"response\":\"\"}"
|
||||
}
|
||||
|
||||
let clean_response: String = clean_llm_response(raw_response)
|
||||
@@ -485,10 +404,8 @@ fn handle_chat(body: String) -> String {
|
||||
|
||||
let updated_hist: String = hist_append(stored_hist, "user", message)
|
||||
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.
|
||||
let final_hist: String = if json_array_len(updated_hist2) > 20 {
|
||||
hist_trim_with_bell_guard(updated_hist2)
|
||||
hist_trim(updated_hist2)
|
||||
} else {
|
||||
updated_hist2
|
||||
}
|
||||
@@ -626,7 +543,15 @@ 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 + "}"
|
||||
let tmp: String = "/tmp/neuron-mcp-call.json"
|
||||
// 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"
|
||||
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)
|
||||
}
|
||||
@@ -901,15 +826,25 @@ fn is_builtin_tool(tool_name: String) -> Bool {
|
||||
|| str_starts_with(tool_name, "neuron_")
|
||||
}
|
||||
|
||||
// next_bridge_id — monotonic correlation id for a suspended agentic turn.
|
||||
// Combines boot-relative time with a per-process counter so two unknown-tool
|
||||
// suspensions in the same second still get distinct ids.
|
||||
// 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.
|
||||
//
|
||||
// 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.
|
||||
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))
|
||||
return "br-" + int_to_str(time_now()) + "-" + int_to_str(next)
|
||||
// uuid_v4() provides collision-free uniqueness; counter is decorative.
|
||||
let uid: String = uuid_v4()
|
||||
return "br-" + uid
|
||||
}
|
||||
|
||||
fn handle_chat_agentic(body: String) -> String {
|
||||
@@ -1442,28 +1377,14 @@ fn auto_persist(req: String, resp: String) -> Void {
|
||||
let safe_msg: String = str_replace(message, "\"", "'")
|
||||
let safe_reply: String = str_replace(reply2, "\"", "'")
|
||||
|
||||
// Detect emotional salience before persisting. safety_detect_bell_level uses the
|
||||
// same phrase lists as the safety layer (safety.el), so the classification is
|
||||
// consistent with what safety_screen already evaluated for this turn.
|
||||
let bell_level: String = safety_detect_bell_level(message)
|
||||
let is_bell: Bool = !str_eq(bell_level, "none")
|
||||
|
||||
// Tag the Conversation node with bell metadata when distress is present so
|
||||
// subsequent affective queries (e.g. engram_compile) can find this exchange.
|
||||
let tags: String = if is_bell {
|
||||
"[\"Conversation\",\"chat\",\"timestamped\",\"bell:" + bell_level + "\",\"affective\"]"
|
||||
} else {
|
||||
"[\"Conversation\",\"chat\",\"timestamped\"]"
|
||||
}
|
||||
|
||||
let content: String = "{\"q\":\"" + safe_msg + "\""
|
||||
+ ",\"a\":\"" + safe_reply + "\""
|
||||
+ ",\"created_at\":" + ts_str
|
||||
+ ",\"source\":\"chat\""
|
||||
+ ",\"bell\":\"" + bell_level + "\""
|
||||
+ ",\"label\":\"chat:" + ts_str + "\"}"
|
||||
|
||||
let conv_node_id: String = engram_node_full(
|
||||
let tags: String = "[\"Conversation\",\"chat\",\"timestamped\"]"
|
||||
engram_node_full(
|
||||
content,
|
||||
"Conversation",
|
||||
"chat:" + ts_str,
|
||||
@@ -1473,72 +1394,6 @@ fn auto_persist(req: String, resp: String) -> Void {
|
||||
"Episodic",
|
||||
tags
|
||||
)
|
||||
|
||||
// When a bell fires, write a dedicated BellEvent node in addition to the
|
||||
// Conversation node. This makes distress moments directly findable by label
|
||||
// ("bell:soft" / "bell:hard") without having to scan all Conversation nodes.
|
||||
// The BellEvent carries higher salience so engram_compile pulls it into context.
|
||||
// The message content is truncated to 120 chars — enough signal, not a full dump.
|
||||
if is_bell {
|
||||
let summary: String = if str_len(message) > 120 { str_slice(message, 0, 120) } else { message }
|
||||
let safe_summary: String = str_replace(summary, "\"", "'")
|
||||
let bell_content: String = "BELL:" + bell_level
|
||||
+ " | ts:" + ts_str
|
||||
+ " | summary:" + safe_summary
|
||||
|
||||
// bell:hard gets peak salience; bell:soft is slightly lower.
|
||||
let sal_a: String = if str_eq(bell_level, "hard") { el_from_float(0.98) } else { el_from_float(0.88) }
|
||||
let sal_b: String = if str_eq(bell_level, "hard") { el_from_float(0.98) } else { el_from_float(0.88) }
|
||||
let sal_c: String = if str_eq(bell_level, "hard") { el_from_float(1.0) } else { el_from_float(0.95) }
|
||||
|
||||
let bell_tags: String = "[\"safety\",\"bell\",\"bell:" + bell_level + "\",\"affective\",\"BellEvent\"]"
|
||||
let bell_ts_str: String = int_to_str(time_now())
|
||||
let bell_label: String = "bell:" + bell_level + ":" + bell_ts_str
|
||||
let bell_node_id: String = engram_node_full(
|
||||
bell_content,
|
||||
"BellEvent",
|
||||
bell_label,
|
||||
sal_a,
|
||||
sal_b,
|
||||
sal_c,
|
||||
"Episodic",
|
||||
bell_tags
|
||||
)
|
||||
|
||||
// Increment session-level bell counter so session_hist_save knows whether
|
||||
// any bell fired during this session when writing a boundary summary.
|
||||
let sess_id: String = json_get(req, "session_id")
|
||||
let bell_key: String = if str_eq(sess_id, "") {
|
||||
"session_bell_count"
|
||||
} else {
|
||||
"session_bell_count:" + sess_id
|
||||
}
|
||||
let prior_count: String = state_get(bell_key)
|
||||
let prior_n: Int = if str_eq(prior_count, "") { 0 } else { str_to_int(prior_count) }
|
||||
state_set(bell_key, int_to_str(prior_n + 1))
|
||||
|
||||
// Also record the highest bell level seen this session so the boundary
|
||||
// summary can classify the session correctly (hard takes precedence).
|
||||
let level_key: String = if str_eq(sess_id, "") {
|
||||
"session_bell_level"
|
||||
} else {
|
||||
"session_bell_level:" + sess_id
|
||||
}
|
||||
let prior_level: String = state_get(level_key)
|
||||
let new_level: String = if str_eq(bell_level, "hard") { "hard" } else {
|
||||
if str_eq(prior_level, "hard") { "hard" } else { "soft" }
|
||||
}
|
||||
state_set(level_key, new_level)
|
||||
|
||||
// Stash a short signal summary for the boundary node (last bell wins for
|
||||
// the one-liner; the full history is in per-bell BellEvent nodes).
|
||||
let signal_key: String = if str_eq(sess_id, "") {
|
||||
"session_bell_signal"
|
||||
} else {
|
||||
"session_bell_signal:" + sess_id
|
||||
}
|
||||
state_set(signal_key, safe_summary)
|
||||
}
|
||||
}
|
||||
|
||||
// strengthen_chat_nodes — strengthen the engram nodes that were activated during a chat.
|
||||
|
||||
@@ -7,65 +7,6 @@ import "neuron-api.el"
|
||||
import "sessions.el"
|
||||
import "soul.elh"
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Rate limiting — simple in-memory per-IP sliding window counter.
|
||||
//
|
||||
// State keys:
|
||||
// rl:<ip>:count — request count in the current window
|
||||
// rl:<ip>:window — window start timestamp (unix seconds)
|
||||
//
|
||||
// Limit: configurable via soul state key "soul_rate_limit" (requests per
|
||||
// minute). Falls back to 60 req/min if not set. The /health endpoint is
|
||||
// exempt so monitoring does not consume quota.
|
||||
//
|
||||
// State growth: each unique source IP accumulates exactly 2 state keys
|
||||
// (count + window) for the lifetime of the process. Per-IP storage is
|
||||
// bounded and constant; values reset on window expiry. In aggregate, state
|
||||
// grows linearly with distinct IPs — typical for a trusted-client service.
|
||||
// EL has no state_delete builtin, so keys from inactive IPs persist.
|
||||
// TODO: add state_delete sweep when the EL runtime exposes that primitive.
|
||||
//
|
||||
// Returns "" when the request is allowed, or a 429 JSON body when rejected.
|
||||
// ---------------------------------------------------------------------------
|
||||
fn rate_limit_check(ip: String, path: String) -> String {
|
||||
// Health checks are exempt — they must never be blocked.
|
||||
if str_eq(path, "/health") {
|
||||
return ""
|
||||
}
|
||||
|
||||
let limit_str: String = state_get("soul_rate_limit")
|
||||
let limit: Int = if str_eq(limit_str, "") { 60 } else { str_to_int(limit_str) }
|
||||
|
||||
let now: Int = time_now()
|
||||
let window_key: String = "rl:" + ip + ":window"
|
||||
let count_key: String = "rl:" + ip + ":count"
|
||||
|
||||
let win_str: String = state_get(window_key)
|
||||
let win_start: Int = if str_eq(win_str, "") { now } else { str_to_int(win_str) }
|
||||
|
||||
// New window every 60 seconds.
|
||||
let elapsed: Int = now - win_start
|
||||
let in_window: Bool = elapsed < 60
|
||||
|
||||
let prev_count_str: String = state_get(count_key)
|
||||
let prev_count: Int = if str_eq(prev_count_str, "") { 0 } else { str_to_int(prev_count_str) }
|
||||
|
||||
// Reset window if expired.
|
||||
let eff_count: Int = if in_window { prev_count } else { 0 }
|
||||
let eff_win: Int = if in_window { win_start } else { now }
|
||||
|
||||
let new_count: Int = eff_count + 1
|
||||
state_set(count_key, int_to_str(new_count))
|
||||
state_set(window_key, int_to_str(eff_win))
|
||||
|
||||
if new_count > limit {
|
||||
let retry_after: Int = 60 - (now - eff_win)
|
||||
let eff_retry: Int = if retry_after < 0 { 0 } else { retry_after }
|
||||
return "{\"__status__\":429,\"error\":\"rate limit exceeded\",\"code\":\"rate_limited\",\"retry_after_secs\":" + int_to_str(eff_retry) + "}"
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
fn strip_query(path: String) -> String {
|
||||
let q: Int = str_index_of(path, "?")
|
||||
if q < 0 {
|
||||
@@ -75,14 +16,24 @@ 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 }
|
||||
@@ -90,35 +41,12 @@ fn route_health() -> String {
|
||||
let edge_ct: Int = engram_edge_count()
|
||||
let pulse: String = state_get("soul.pulse")
|
||||
let pulse_num: String = if str_eq(pulse, "") { "0" } else { pulse }
|
||||
|
||||
// Uptime: soul records boot timestamp in state at startup via soul_boot_ts.
|
||||
// Compute elapsed seconds; fall back to -1 if not yet set.
|
||||
let boot_ts_str: String = state_get("soul_boot_ts")
|
||||
let uptime_secs: Int = if str_eq(boot_ts_str, "") {
|
||||
-1
|
||||
} else {
|
||||
time_now() - str_to_int(boot_ts_str)
|
||||
}
|
||||
|
||||
// LLM connectivity: probe with a minimal call. Any non-error reply = ok.
|
||||
// Use a short, fixed prompt so this never counts against conversation history.
|
||||
let model: String = state_get("soul_model")
|
||||
let eff_model: String = if str_eq(model, "") { "claude-sonnet-4-5" } else { model }
|
||||
let llm_probe: String = llm_call_system(eff_model, "You are a health probe. Reply with the single word: ok", "ping")
|
||||
let llm_ok: Bool = !str_eq(llm_probe, "")
|
||||
&& !str_starts_with(llm_probe, "{\"error\"")
|
||||
&& !str_starts_with(llm_probe, "{\"type\":\"error\"")
|
||||
&& !str_contains(llm_probe, "authentication_error")
|
||||
let llm_status: String = if llm_ok { "ok" } else { "unreachable" }
|
||||
|
||||
return "{\"status\":\"alive\""
|
||||
+ ",\"cgi_id\":\"" + cgi_id + "\""
|
||||
+ ",\"boot\":" + boot_num
|
||||
+ ",\"uptime_secs\":" + int_to_str(uptime_secs)
|
||||
+ ",\"node_count\":" + int_to_str(node_ct)
|
||||
+ ",\"edge_count\":" + int_to_str(edge_ct)
|
||||
+ ",\"pulse\":" + pulse_num
|
||||
+ ",\"llm\":\"" + llm_status + "\""
|
||||
+ ",\"layers\":{\"l0\":\"core\",\"l1\":\"safety\",\"l2\":\"stewardship\",\"l3\":\"" + imprint_current() + "\"}}"
|
||||
}
|
||||
|
||||
@@ -141,7 +69,8 @@ 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 +92,8 @@ 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(
|
||||
@@ -185,15 +115,15 @@ fn route_imprint_user(body: String) -> String {
|
||||
|
||||
fn route_synthesize(body: String) -> String {
|
||||
if str_eq(body, "") {
|
||||
return "{\"error\":\"body is required\",\"code\":\"missing_param\"}"
|
||||
return "{\"mechanism\":\"did not engage\"}"
|
||||
}
|
||||
let parent_a: String = json_get(body, "parent_a")
|
||||
let parent_b: String = json_get(body, "parent_b")
|
||||
if str_eq(parent_a, "") {
|
||||
return "{\"error\":\"parent_a is required\",\"code\":\"missing_param\"}"
|
||||
return "{\"mechanism\":\"did not engage\"}"
|
||||
}
|
||||
if str_eq(parent_b, "") {
|
||||
return "{\"error\":\"parent_b is required\",\"code\":\"missing_param\"}"
|
||||
return "{\"mechanism\":\"did not engage\"}"
|
||||
}
|
||||
let req: String = "synthesize " + parent_a + " " + parent_b
|
||||
let tags: String = "[\"soul-inbox-pending\",\"synthesis-request\"]"
|
||||
@@ -301,9 +231,13 @@ 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, "") {
|
||||
@@ -338,20 +272,45 @@ 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)
|
||||
|
||||
// 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.
|
||||
let ip: String = env("REMOTE_ADDR")
|
||||
if !str_eq(ip, "") {
|
||||
let rl_result: String = rate_limit_check(ip, clean)
|
||||
if !str_eq(rl_result, "") {
|
||||
return rl_result
|
||||
}
|
||||
// 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.
|
||||
|
||||
// Issue #10: Rate limiting is not implemented.
|
||||
// TODO: add a per-IP token-bucket counter returning HTTP 429 when exceeded.
|
||||
// Requires a C-level counter in el_runtime.c or a sidecar reverse proxy.
|
||||
|
||||
// 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)
|
||||
}
|
||||
@@ -379,7 +338,8 @@ 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 {
|
||||
@@ -519,13 +479,15 @@ fn handle_request(method: String, path: String, body: String) -> String {
|
||||
return handle_elp_chat(body)
|
||||
}
|
||||
if str_eq(clean, "/api/chat") {
|
||||
// NOTE: streaming (SSE / chunked transfer) is not implemented. All chat
|
||||
// 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 {
|
||||
|
||||
-42
@@ -368,48 +368,6 @@ fn session_hist_save(session_id: String, hist: String) -> Void {
|
||||
el_from_float(0.6), el_from_float(0.6), el_from_float(0.9),
|
||||
"Episodic", tags
|
||||
)
|
||||
|
||||
// Session boundary emotional summary — written once per session the first time
|
||||
// a bell event has fired. The summary node is findable by future sessions via
|
||||
// broad affective queries ("session:emotional-summary" or "bell distress session").
|
||||
// It is NOT rewritten on every save — the state flag prevents duplicate nodes.
|
||||
let summary_written_key: String = "session_bell_summary_written:" + session_id
|
||||
let already_written: String = state_get(summary_written_key)
|
||||
if str_eq(already_written, "") {
|
||||
let bell_count_key: String = "session_bell_count:" + session_id
|
||||
let bell_count_raw: String = state_get(bell_count_key)
|
||||
let bell_count: Int = if str_eq(bell_count_raw, "") { 0 } else { str_to_int(bell_count_raw) }
|
||||
if bell_count > 0 {
|
||||
let bell_level_key: String = "session_bell_level:" + session_id
|
||||
let bell_signal_key: String = "session_bell_signal:" + session_id
|
||||
let dominant_level: String = state_get(bell_level_key)
|
||||
let last_signal: String = state_get(bell_signal_key)
|
||||
let eff_level: String = if str_eq(dominant_level, "") { "soft" } else { dominant_level }
|
||||
let eff_signal: String = if str_eq(last_signal, "") { "(no signal captured)" } else { last_signal }
|
||||
let ts_now: Int = time_now()
|
||||
let summary_content: String = "session:emotional-summary"
|
||||
+ " | session:" + session_id
|
||||
+ " | bell_count:" + int_to_str(bell_count)
|
||||
+ " | dominant_level:" + eff_level
|
||||
+ " | last_signal:" + eff_signal
|
||||
+ " | ts:" + int_to_str(ts_now)
|
||||
let summary_tags: String = "[\"session-emotional-summary\",\"affective\",\"bell:" + eff_level + "\",\"BellEvent\"]"
|
||||
let summary_sal: String = if str_eq(eff_level, "hard") { el_from_float(0.95) } else { el_from_float(0.85) }
|
||||
let sum_discard: String = engram_node_full(
|
||||
summary_content,
|
||||
"BellEvent",
|
||||
"session:emotional-summary",
|
||||
summary_sal,
|
||||
summary_sal,
|
||||
el_from_float(1.0),
|
||||
"Episodic",
|
||||
summary_tags
|
||||
)
|
||||
// Mark written so we do not create duplicate summary nodes as the
|
||||
// session continues accumulating more turns.
|
||||
state_set(summary_written_key, "1")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// session_update_meta_timestamp — update the updated_at field in the session:meta node.
|
||||
|
||||
@@ -369,7 +369,6 @@ load_identity_context()
|
||||
seed_persona_from_env()
|
||||
let boot_num: Int = mem_boot_count_inc()
|
||||
state_set("soul_boot_count", int_to_str(boot_num))
|
||||
state_set("soul_boot_ts", int_to_str(time_now()))
|
||||
println("[soul] boot #" + int_to_str(boot_num))
|
||||
emit_session_start_event()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user