Merge pull request 'fix(engine): restore multi-turn crisis escalation on the agentic path (P0, closes #129)' (#130) from fix/129-history-amplification into main

chat.el

@@ -2519,6 +2519,24 @@ fn handle_chat_plan(body: String) -> String {
     return "{\"plan\":" + plan_json + ",\"model\":\"" + json_safe(model) + "\"}"
 }
 
+// ── agentic_safety_screen — the agentic path's L1 input gate ──────────────────
+//
+// Extracted 2026-08-07 (issue #129) so the agentic path's safety INPUT is
+// reachable by a test. It owns exactly two decisions: which history window the
+// screen sees, and the screen call itself.
+//
+// Why it is a function and not two inline lines: those two lines sat in the
+// middle of a 300-line handler, and a key rename (ff421d3) moved the producer
+// without moving this consumer. Nothing failed, nothing logged — the
+// history-amplification half of the crisis score simply received "" on every
+// real session for a day. Inline safety inputs are untestable safety inputs.
+// See tests/test_history_amplification.el, which fails if this window and
+// conv_history_record ever stop agreeing.
+fn agentic_safety_screen(session_id: String, message: String) -> String {
+    let history: String = state_get(conv_hist_key(session_id))
+    return safety_screen(message, history)
+}
+
 fn handle_chat_agentic(body: String) -> String {
     let message: String = json_get(body, "message")
     if str_eq(message, "") {
@@ -2554,10 +2572,10 @@ fn handle_chat_agentic(body: String) -> String {
 
     // L1 safety screen — agentic path must pass the same gate as layered_cycle.
     // Hard bell: return the crisis response immediately, do not enter the agentic loop.
-    // Fix(issue #9): "conversation_history" key was never written; history lives under "conv_history".
-    // Old key caused history-amplification in safety_screen to always receive "" on agentic path.
-    let history: String = state_get("conv_history")
-    let screen_result: String = safety_screen(message, history)
+    // The history window this screen sees is owned by agentic_safety_screen (issue #129);
+    // it must be the same window conv_history_record writes, or the escalation half of the
+    // crisis score is silently starved. Do not inline this read back into the handler.
+    let screen_result: String = agentic_safety_screen(sess_for_root, message)
     let screen_action: String = json_get(screen_result, "action")
     if str_eq(screen_action, "hard_bell") {
         safety_log_bell("hard", json_get(screen_result, "reason"), str_slice(message, 0, 80))

scripts/run-el-test.sh

@@ -0,0 +1,108 @@
+#!/usr/bin/env bash
+# run-el-test.sh — compile and run one El test program from tests/.
+#
+# WHY THIS EXISTS (2026-08-07, issue #129):
+#   tests/ has held 14 test programs for months with no way to run them. CI does
+#   not run them. The convention printed in their own headers
+#   (`elc soul.el && ./soul --test tests/x.el`) refers to a --test flag the El
+#   runtime does not implement. So the tests were documentation, not gates —
+#   which is how a P0 safety regression shipped with a test directory present.
+#
+# THE RECIPE, AND WHY IT IS THIS SHAPE:
+#   Same discovery as gen-soul-amalgam.sh — `elc --target=c` emits only an extern
+#   prototype for any module that has a .elh header next to it, and inlines the
+#   module's bodies when it does not. A test that imports ../chat.el therefore
+#   compiles to a 18 KB unit full of unresolved externs unless the headers are
+#   out of the way. So: copy the sources into a scratch tree, delete every .elh
+#   on the import chain, and compile the test there.
+#
+#   Scratch copy on purpose: the worktree is shared with other terminals and
+#   deleting headers in place would be a shared-tree mutation with no owner.
+#
+# EXIT STATUS IS THE GATE: non-zero if the binary fails to build, crashes, or if
+# its output contains a FAIL line or reports a non-zero failed count. Do not
+# "improve" this into something that only checks the exit code of the test
+# binary — these El tests print failures and still exit 0.
+#
+# usage: scripts/run-el-test.sh tests/test_history_amplification.el
+set -euo pipefail
+
+TEST_REL="${1:?usage: run-el-test.sh tests/<test>.el}"
+SRC="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+TEST_NAME="$(basename "$TEST_REL" .el)"
+
+ELC="${ELC:-$HOME/neuron-dev-stack/src/el/lang/dist/platform/elc}"
+[ -x "$ELC" ] || ELC="$HOME/el-sdk/elc"
+[ -x "$ELC" ] || { echo "[run-el-test] FAIL: no elc found (set ELC=)"; exit 1; }
+
+RTC="${RTC:-$SRC/vendor/el-runtime/v1.0.0-20260501/el_runtime.c}"
+[ -f "$RTC" ] || RTC="$HOME/el-sdk/el_runtime.c"
+[ -f "$RTC" ] || { echo "[run-el-test] FAIL: no el_runtime.c found (set RTC=)"; exit 1; }
+RTDIR="$(dirname "$RTC")"
+
+EL_REPO="${EL_REPO:-$HOME/Development/neuron-technologies/el}"
+SSL="${SSL_PREFIX:-/opt/homebrew/opt/openssl@3}"
+
+GEN="$(mktemp -d "${TMPDIR:-/tmp}/el-test.XXXXXX")"
+trap 'rm -rf "$GEN"' EXIT
+
+mkdir -p "$GEN/neuron/tests" "$GEN/foundation/el/elp/src"
+cp "$SRC"/*.el "$GEN/neuron/"
+cp "$SRC"/tests/*.el "$GEN/neuron/tests/" 2>/dev/null || true
+[ -d "$EL_REPO/elp/src" ] && cp "$EL_REPO"/elp/src/*.el "$GEN/foundation/el/elp/src/" 2>/dev/null || true
+# The whole recipe depends on there being no headers to short-circuit inlining.
+find "$GEN" -name '*.elh' -delete
+
+echo "[run-el-test] compiling $TEST_REL"
+( cd "$GEN/neuron" && "$ELC" --target=c "tests/${TEST_NAME}.el" ) > "$GEN/${TEST_NAME}.c"
+
+BODIES=$(grep -c '^el_val_t .*) {$' "$GEN/${TEST_NAME}.c" || true)
+echo "[run-el-test] $(wc -c < "$GEN/${TEST_NAME}.c" | tr -d ' ') bytes, ${BODIES} inlined function bodies"
+# A test that imports ../chat.el pulls in the bulk of the engine. A tiny body
+# count means an import was read from a header instead of inlined, and the test
+# would be exercising extern stubs rather than the real code.
+if [ "$BODIES" -lt 100 ]; then
+  echo "[run-el-test] FAIL: only $BODIES inlined bodies — an import was not inlined"
+  exit 1
+fi
+
+cc -O2 -DHAVE_CURL \
+   -I"$RTDIR" -I"$SSL/include" -L"$SSL/lib" \
+   "$GEN/${TEST_NAME}.c" "$RTC" \
+   -lssl -lcrypto -lcurl -lpthread -lm \
+   -o "$GEN/${TEST_NAME}" 2> "$GEN/cc.log" || {
+     echo "[run-el-test] FAIL: compile error"; tail -30 "$GEN/cc.log"; exit 1; }
+
+# arm64 pointer-truncation guard (cc-brain.sh's rule): an implicit declaration of
+# a runtime symbol truncates its returned pointer to 32 bits.
+if grep -E 'implicit.*(engram_|el_)' "$GEN/cc.log"; then
+  echo "[run-el-test] FAIL: implicit declarations of runtime symbols"; exit 1; fi
+
+# Throwaway HOME so a test can never read or write the live engram at ~/.neuron.
+TEST_HOME="$GEN/home"
+mkdir -p "$TEST_HOME"
+
+echo "[run-el-test] running $TEST_NAME"
+set +e
+HOME="$TEST_HOME" NEURON_HOME="$TEST_HOME/.neuron" "$GEN/${TEST_NAME}" 2>&1 | tee "$GEN/out.txt"
+RC=${PIPESTATUS[0]}
+set -e
+
+if [ "$RC" -ne 0 ]; then
+  echo "[run-el-test] FAIL: $TEST_NAME exited $RC (crash or abort)"
+  exit 1
+fi
+if grep -q "  FAIL:" "$GEN/out.txt"; then
+  echo "[run-el-test] FAIL: $TEST_NAME reported failing assertions"
+  exit 1
+fi
+if grep -qE '[1-9][0-9]* failed' "$GEN/out.txt"; then
+  echo "[run-el-test] FAIL: $TEST_NAME reported a non-zero failed count"
+  exit 1
+fi
+if ! grep -q "PASS:" "$GEN/out.txt"; then
+  echo "[run-el-test] FAIL: $TEST_NAME produced no assertions at all"
+  exit 1
+fi
+
+echo "[run-el-test] PASS: $TEST_NAME"

tests/test_history_amplification.el

@@ -0,0 +1,213 @@
+// ── test_history_amplification.el ─────────────────────────────────────────────
+//
+// REGRESSION TEST FOR ISSUE #129 (P0, SAFETY).
+//
+// What this guards: on the agentic path, the crisis score has two halves — the
+// message you just sent, and the distress that has accumulated across the
+// conversation. The second half is the whole reason the escalation logic exists:
+// someone whose distress builds over several turns never sends one message that
+// trips the bell on its own.
+//
+// The defect this test was written against (ff421d3, 2026-08-05 → fixed
+// 2026-08-07): conversation history moved to a per-session key via
+// conv_hist_key(session_id), but the agentic path's safety screen was left
+// reading the old anonymous "conv_history" bucket. The desktop app always sends
+// a session_id, so the screen received "" on every real conversation and the
+// escalation half always scored 0. Nothing failed. Nothing logged. The comment
+// above the defective line documented this same bug being fixed once before.
+//
+// THE INVARIANT UNDER TEST, stated so it survives future renames:
+//   the window the safety screen READS must be the window conv_history_record
+//   WRITES. Not "must be called conv_history" — must AGREE.
+//
+// This test is deliberately written to fail loudly on the pre-fix source. If it
+// ever passes on code where the screen reads a key nothing writes, it is broken.
+//
+// To run (macOS, from the worktree root):
+//   scripts/run-el-test.sh tests/test_history_amplification.el
+// ──────────────────────────────────────────────────────────────────────────────
+
+import "../chat.el"
+import "../safety.el"
+import "../sessions.el"
+
+// Program class. Without this an El program compiles as a 'utility', and a
+// utility may not call the self-formation primitives (llm_call_system,
+// llm_vision) that chat.el's agentic loop references — the unit fails to
+// compile with a capability violation even though the test never calls them.
+// Declaring 'cgi' matches how soul.el declares itself.
+//
+// The endpoints below are deliberately DEAD: this test must never reach a live
+// engram, and nothing it asserts depends on one. Port 9 is discard.
+cgi "neuron-test-history-amplification" {
+    dharma_id: "ntn-test@http://127.0.0.1:9",
+    principal: "test-harness",
+    network:   "dharma-testnet",
+    engram:    "http://127.0.0.1:9"
+}
+
+// ── Counters ──────────────────────────────────────────────────────────────────
+//
+// NOTE for anyone copying this harness: the idiom used by the older tests in
+// this directory — `let pass_count = pass_count + 1` inside an assert function —
+// does NOT mutate the module-level binding. It declares a new local that dies
+// with the call, so those suites all print "0 passed, 0 failed" no matter what
+// happened. Counters go through the state store here so the summary is real.
+
+fn bump(counter: String) -> Void {
+    let cur: String = state_get(counter)
+    let n: Int = if str_eq(cur, "") { 0 } else { str_to_int(cur) }
+    state_set(counter, int_to_str(n + 1))
+}
+
+fn counter_of(counter: String) -> Int {
+    let cur: String = state_get(counter)
+    if str_eq(cur, "") { return 0 }
+    return str_to_int(cur)
+}
+
+fn assert_eq(label: String, got: String, expected: String) -> Void {
+    if str_eq(got, expected) {
+        bump("t_pass")
+        println("  PASS: " + label)
+    } else {
+        bump("t_fail")
+        println("  FAIL: " + label)
+        println("    got:      " + got)
+        println("    expected: " + expected)
+    }
+}
+
+fn assert_true(label: String, cond: Bool) -> Void {
+    if cond {
+        bump("t_pass")
+        println("  PASS: " + label)
+    } else {
+        bump("t_fail")
+        println("  FAIL: " + label)
+    }
+}
+
+// ── Fixtures ──────────────────────────────────────────────────────────────────
+//
+// ESCALATION_MSG scores 50 on its own ("can't go on", safety_score_crisis s9).
+// 50 is >= soft (35) and < hard (70): a soft bell by itself, which is the point.
+// It is the message that is only a crisis IN CONTEXT.
+//
+// DISTRESS_TURN carries five history phrases:
+//   hopeless 15 + worthless 15 + nobody cares 15 + can't take it anymore 20
+//   + want to disappear 20 = 85; contributed at 1/3 weight = 28.
+// 50 + 28 = 78 >= 70 → hard_bell. That 28-point swing IS the escalation logic,
+// and it is exactly what the defect suppressed.
+
+let TEST_SESSION: String = "sess-test-129-history-amplification"
+let ESCALATION_MSG: String = "honestly i can't go on like this"
+let DISTRESS_TURN: String = "i feel hopeless and worthless, nobody cares, i can't take it anymore, i want to disappear"
+
+println("")
+println("test_history_amplification.el — issue #129 (agentic multi-turn crisis escalation)")
+
+// ── 1. Baseline: the message alone is a SOFT bell, not a hard one ─────────────
+//
+// If this ever returns hard_bell, the test below proves nothing — the message
+// would trip the bell without any history and the amplification would be
+// invisible. This assertion is what keeps the real test honest.
+
+println("")
+println("1. baseline — escalation message with NO history is a soft bell")
+
+let baseline: String = safety_screen(ESCALATION_MSG, "")
+assert_eq("no history -> soft_bell (not hard)", json_get(baseline, "action"), "soft_bell")
+
+// ── 2. Producer sanity: history lands in the session's own window ─────────────
+
+println("")
+println("2. producer — conv_history_record writes the session's window")
+
+conv_history_record(TEST_SESSION, DISTRESS_TURN, "i hear you, that sounds heavy", "")
+
+let written: String = state_get(conv_hist_key(TEST_SESSION))
+assert_true("session window is non-empty after record", !str_eq(written, ""))
+assert_true("session window contains the distress turn", str_contains(written, "hopeless"))
+
+// ── 3. THE REGRESSION: the agentic screen must SEE that window ────────────────
+//
+// Pre-fix this returns soft_bell, because agentic_safety_screen read the
+// anonymous bucket and got "". Post-fix it returns hard_bell.
+
+println("")
+println("3. REGRESSION #129 — agentic screen reads the session's own window")
+
+let screened: String = agentic_safety_screen(TEST_SESSION, ESCALATION_MSG)
+assert_eq(
+    "distress history escalates the agentic screen to hard_bell",
+    json_get(screened, "action"),
+    "hard_bell"
+)
+
+// ── 4. The invariant, stated directly ─────────────────────────────────────────
+//
+// Independent of thresholds and phrase lists: whatever the screen reads for a
+// session must equal what the recorder wrote for that session. This is the
+// assertion that survives a future rename of either side.
+
+println("")
+println("4. invariant — read window == written window")
+
+let read_back: String = state_get(conv_hist_key(TEST_SESSION))
+assert_true("screen input is the recorded window, not empty", !str_eq(read_back, ""))
+assert_eq("read window is byte-identical to written window", read_back, written)
+
+// ── 5. No false positive: a calm session does not escalate ────────────────────
+//
+// A test that only ever asserts "hard_bell" would pass on code that hard-bells
+// every message. This is the other leg, and it runs BEFORE the anonymous case
+// below on purpose: that case writes the shared bucket, and under the defect a
+// calm session would then inherit it.
+
+println("")
+println("5. specificity — a calm history does NOT escalate")
+
+let CALM_SESSION: String = "sess-test-129-calm"
+state_set("conv_history", "")
+conv_history_record(CALM_SESSION, "what is the weather like today", "clear and mild", "")
+let calm: String = agentic_safety_screen(CALM_SESSION, ESCALATION_MSG)
+assert_eq("calm history stays at soft_bell", json_get(calm, "action"), "soft_bell")
+
+// ── 6. Cross-session leakage ──────────────────────────────────────────────────
+//
+// The same defect had a second face: because the screen read one shared bucket,
+// a calm session could be scored against a DIFFERENT session's distress. That is
+// wrong in both directions — it fabricates a crisis for the calm user and it
+// leaks the distressed user's content into another session's scoring.
+
+println("")
+println("6. isolation — one session's distress must not score another session")
+
+state_set("conv_history", "")
+let OTHER_SESSION: String = "sess-test-129-other"
+conv_history_record(OTHER_SESSION, DISTRESS_TURN, "i hear you", "")
+let isolated: String = agentic_safety_screen(CALM_SESSION, ESCALATION_MSG)
+assert_eq(
+    "a distressed OTHER session does not escalate the calm session",
+    json_get(isolated, "action"),
+    "soft_bell"
+)
+
+// ── 7. Anonymous sessions still work ──────────────────────────────────────────
+//
+// conv_hist_key("") deliberately falls back to the shared "conv_history" bucket.
+// The fix must not break the no-session_id path older callers rely on. Runs last
+// because it writes that shared bucket.
+
+println("")
+println("7. anonymous path — empty session_id still screens against the shared window")
+
+state_set("conv_history", "[{\"role\":\"user\",\"content\":\"" + DISTRESS_TURN + "\"}]")
+let anon: String = agentic_safety_screen("", ESCALATION_MSG)
+assert_eq("anonymous session escalates too", json_get(anon, "action"), "hard_bell")
+
+// ── Summary ───────────────────────────────────────────────────────────────────
+
+println("")
+println("history amplification tests: " + int_to_str(counter_of("t_pass")) + " passed, " + int_to_str(counter_of("t_fail")) + " failed")