@ngockhoale/ukit 3.4.81 → 3.4.83

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -33,27 +33,36 @@ const DENIED_TARGET_RES = [
33
33
  /secret|credential|token/i,
34
34
  ];
35
35
 
36
- // Whitelist — bounded deterministic mapping only.
36
+ // Whitelist — bounded deterministic mapping only. Classification needs evidence,
37
+ // not a word that happens to occur in a command's text: the ledger records no
38
+ // timed-out/killed/signal marker, only `exitCode` (mined onto pattern.exitCodes),
39
+ // so timeout-hang keys on exit 124 (GNU timeout(1)). Text markers are a fallback:
40
+ // whole words only, matched against the command's invocation lines — never
41
+ // heredoc bodies, comments, env-var names or file names.
42
+ const TIMEOUT_EXIT_CODES = new Set([124]);
43
+
37
44
  const FIX_CLASSES = [
38
45
  {
39
46
  id: 'timeout-hang',
40
- matches: (hay) => /timeout|timed?\s*out|hang|hung/.test(hay),
47
+ matches: (text, pattern) => (Array.isArray(pattern.exitCodes)
48
+ && pattern.exitCodes.some((code) => TIMEOUT_EXIT_CODES.has(code)))
49
+ || /\b(?:timed out|timeout (?:exceeded|expired)|hangs|hanging|hung)\b/.test(text.commands),
41
50
  change: 'Increase the timeout, add an explicit deadline, and retry once before giving up.',
42
51
  },
43
52
  {
44
53
  id: 'missing-fallback',
45
- matches: (hay) => /missing-fallback/.test(hay)
46
- || (/fallback/.test(hay) && /decision|decisionruntime/.test(hay)),
54
+ matches: (text) => /\bmissing-fallback\b/.test(text.all)
55
+ || (/\bfallback\b/.test(text.all) && /\b(?:decision|decisionruntime)\b/.test(text.all)),
47
56
  change: 'Add a `fallbackCode` path plus a deterministic default so the caller never blocks on the decision call.',
48
57
  },
49
58
  {
50
59
  id: 'empty-output',
51
- matches: (hay) => /empty[-_ ]?output|no output|empty stdout/.test(hay),
60
+ matches: (text) => /\bempty[-_ ]?output\b|\bno output\b|\bempty stdout\b/.test(text.all),
52
61
  change: 'Keep the chain alive on empty output (`|| true` or equivalent) and log stderr for diagnosis.',
53
62
  },
54
63
  {
55
64
  id: 'stale-doc',
56
- matches: (hay) => /stale[-_ ]?doc|doc drift|docs?\s+drift|out[- ]?of[- ]?date\s+doc/.test(hay),
65
+ matches: (text) => /\bstale[-_ ]?doc\b|\bdoc drift\b|\bdocs?\s+drift\b|\bout[- ]?of[- ]?date\s+doc\b/.test(text.all),
57
66
  change: 'Re-render or refresh the flagged documentation file to match current source.',
58
67
  },
59
68
  ];
@@ -62,21 +71,33 @@ function isObject(value) {
62
71
  return Boolean(value) && typeof value === 'object' && !Array.isArray(value);
63
72
  }
64
73
 
65
- // Evidence haystack: signature + commands + files, lowercased.
66
- function haystack(pattern) {
67
- return [
68
- pattern.signature,
69
- ...(Array.isArray(pattern.commands) ? pattern.commands : []),
70
- ...(Array.isArray(pattern.files) ? pattern.files : []),
71
- ].join(' ').toLowerCase();
74
+ // Invocation text of a shell command: drop comment lines and everything from the
75
+ // line that opens a heredoc (body = prose/data, not the command).
76
+ function invocationText(command) {
77
+ const kept = [];
78
+ for (const line of String(command).split('\n')) {
79
+ if (/^\s*#/.test(line)) continue;
80
+ kept.push(line);
81
+ if (/<<-?\s*['"]?\w+/.test(line)) break;
82
+ }
83
+ return kept.join(' ');
84
+ }
85
+
86
+ // Evidence text, lowercased: `commands` = invocation text only; `all` adds signature + files.
87
+ function evidenceText(pattern) {
88
+ const commands = (Array.isArray(pattern.commands) ? pattern.commands : [])
89
+ .filter((c) => typeof c === 'string').map(invocationText).join(' ').toLowerCase();
90
+ const all = [pattern.signature, commands, ...(Array.isArray(pattern.files) ? pattern.files : [])]
91
+ .join(' ').toLowerCase();
92
+ return { commands, all };
72
93
  }
73
94
 
74
95
  /** Map a mined pattern to a whitelisted fix class; null = none. */
75
96
  export function mapPatternToFixTarget(pattern) {
76
97
  if (!isObject(pattern)) return null;
77
- const hay = haystack(pattern);
98
+ const text = evidenceText(pattern);
78
99
  for (const fixClass of FIX_CLASSES) {
79
- if (fixClass.matches(hay)) return { id: fixClass.id, change: fixClass.change };
100
+ if (fixClass.matches(text, pattern)) return { id: fixClass.id, change: fixClass.change };
80
101
  }
81
102
  return null;
82
103
  }
@@ -81,26 +81,171 @@ if [ -z "$COMMAND" ]; then
81
81
  exit 0
82
82
  fi
83
83
 
84
- # set -f: unquoted $COMMAND word-splits AND glob-expands — a bare `*` or `*.sh`
85
- # command would otherwise resolve to cwd filenames and persist an allow rule
86
- # for a file that was never the invoked binary.
87
- set -f
84
+ # Binary resolution: a small shell-word scanner (NOT `for token in $COMMAND`).
85
+ # Leading env assignments (`NAME=value`) are skipped as WHOLE shell words — the
86
+ # value may be '...'/"..." quoted or a $(...)/`...` substitution containing
87
+ # spaces, which plain whitespace splitting cut in half and minted junk such as
88
+ # Bash(HEAD:*) or Bash(-td:*). If the first command word cannot be determined
89
+ # confidently (unbalanced quote/substitution, leading operator, redirection,
90
+ # subshell) BIN stays empty: nothing is minted and the normal permission prompt
91
+ # applies, which is always safe. Pure bash, 3.2 compatible (no globbing involved,
92
+ # so no `set -f` is needed either).
93
+ __ukit_scan_sq() { # I is after the opening '
94
+ local rest="${COMMAND:I}"
95
+ case "$rest" in
96
+ *"'"*) rest="${rest%%\'*}"; I=$((I + ${#rest} + 1)); return 0 ;;
97
+ esac
98
+ return 1
99
+ }
100
+ __ukit_scan_bt() { # I is after the opening backtick
101
+ local c
102
+ while [ "$I" -lt "$N" ]; do
103
+ c="${COMMAND:I:1}"
104
+ case "$c" in
105
+ '\') I=$((I + 2)) ;;
106
+ '`') I=$((I + 1)); return 0 ;;
107
+ *) I=$((I + 1)) ;;
108
+ esac
109
+ done
110
+ return 1
111
+ }
112
+ # I is AT a `$`. Only three forms are understood: `$(...)`, a plain `$NAME`-style
113
+ # expansion, and a simple `${NAME}`. Everything else whose end this scanner
114
+ # cannot prove — `${x:- a b }` (spaces/quotes/braces inside), `$[ ... ]`, and
115
+ # outside double quotes ANSI-C/locale quoting ($'..\'..' / $"..") — returns 1,
116
+ # so nothing is minted. $1 = "dq" when scanning inside double quotes, where
117
+ # `$'` and `$"` are a literal dollar.
118
+ # Name classes are spelled out: a locale-collated `[A-Za-z]` range also matches
119
+ # letters such as `É`, which bash itself never accepts in a variable name.
120
+ __ukit_n1='abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_'
121
+ __ukit_simple_brace_re="^[\$][{][${__ukit_n1}][${__ukit_n1}0123456789]*[}]"
122
+ __ukit_assign_re="^[${__ukit_n1}][${__ukit_n1}0123456789]*[+]?="
123
+ __ukit_scan_dollar() {
124
+ case "${COMMAND:I+1:1}" in
125
+ '(') I=$((I + 2)); __ukit_scan_paren || return 1 ;;
126
+ '{')
127
+ if [[ "${COMMAND:I}" =~ $__ukit_simple_brace_re ]]; then
128
+ I=$((I + ${#BASH_REMATCH[0]}))
129
+ else
130
+ return 1
131
+ fi
132
+ ;;
133
+ '[') return 1 ;;
134
+ "'"|'"')
135
+ [ "${1:-}" = "dq" ] || return 1
136
+ I=$((I + 1))
137
+ ;;
138
+ *) I=$((I + 1)) ;;
139
+ esac
140
+ return 0
141
+ }
142
+ __ukit_scan_dq() { # I is after the opening "
143
+ local c
144
+ while [ "$I" -lt "$N" ]; do
145
+ c="${COMMAND:I:1}"
146
+ case "$c" in
147
+ '\') I=$((I + 2)) ;;
148
+ '"') I=$((I + 1)); return 0 ;;
149
+ '`') I=$((I + 1)); __ukit_scan_bt || return 1 ;;
150
+ '$') __ukit_scan_dollar dq || return 1 ;;
151
+ *) I=$((I + 1)) ;;
152
+ esac
153
+ done
154
+ return 1
155
+ }
156
+ __ukit_scan_paren() { # I is after an opening ( — consume through its matching )
157
+ # Not a full parser: constructs whose `)`/quote does not delimit what this
158
+ # scanner assumes — anything __ukit_scan_dollar rejects, a `#` (comment), a
159
+ # heredoc (`<<`), and `case` patterns (`a)`) — make it give up (return 1 →
160
+ # nothing is minted) rather than guess where the substitution ends.
161
+ local c start=$I
162
+ while [ "$I" -lt "$N" ]; do
163
+ c="${COMMAND:I:1}"
164
+ case "$c" in
165
+ ')')
166
+ I=$((I + 1))
167
+ case "${COMMAND:start:I-start}" in
168
+ *case*) return 1 ;;
169
+ esac
170
+ return 0
171
+ ;;
172
+ '#') return 1 ;;
173
+ '<') [ "${COMMAND:I+1:1}" = "<" ] && return 1; I=$((I + 1)) ;;
174
+ '$') __ukit_scan_dollar || return 1 ;;
175
+ '(') I=$((I + 1)); __ukit_scan_paren || return 1 ;;
176
+ "'") I=$((I + 1)); __ukit_scan_sq || return 1 ;;
177
+ '"') I=$((I + 1)); __ukit_scan_dq || return 1 ;;
178
+ '`') I=$((I + 1)); __ukit_scan_bt || return 1 ;;
179
+ '\') I=$((I + 2)) ;;
180
+ *) I=$((I + 1)) ;;
181
+ esac
182
+ done
183
+ return 1
184
+ }
185
+
186
+ # Bounded scan: the per-character substring scan is quadratic in the command
187
+ # length (a 100 KB assignment value stalled the hook for 45s+). Only the first
188
+ # 4096 characters are scanned; if the first command word is not fully resolved
189
+ # inside that window, nothing is minted.
88
190
  BIN=""
89
- for token in $COMMAND; do
90
- case "$token" in
91
- *=*) continue ;;
191
+ __ukit_cut=0
192
+ if [ "${#COMMAND}" -gt 4096 ]; then
193
+ COMMAND="${COMMAND:0:4096}"
194
+ __ukit_cut=1
195
+ fi
196
+ N=${#COMMAND}
197
+ I=0
198
+ while :; do
199
+ while [ "$I" -lt "$N" ]; do
200
+ case "${COMMAND:I:1}" in
201
+ ' '|' ') I=$((I + 1)) ;;
202
+ *) break ;;
203
+ esac
204
+ done
205
+ [ "$I" -ge "$N" ] && break
206
+ case "${COMMAND:I:1}" in
207
+ ';'|'|'|'&'|'('|')'|'<'|'>'|'
208
+ ') break ;;
209
+ esac
210
+ __ukit_ws=$I
211
+ __ukit_ok=1
212
+ while [ "$I" -lt "$N" ]; do
213
+ __ukit_c="${COMMAND:I:1}"
214
+ case "$__ukit_c" in
215
+ ' '|' '|';'|'|'|'&'|'('|')'|'<'|'>'|'
216
+ ') break ;;
217
+ '\') I=$((I + 2)) ;;
218
+ "'") I=$((I + 1)); __ukit_scan_sq || { __ukit_ok=0; break; } ;;
219
+ '"') I=$((I + 1)); __ukit_scan_dq || { __ukit_ok=0; break; } ;;
220
+ '`') I=$((I + 1)); __ukit_scan_bt || { __ukit_ok=0; break; } ;;
221
+ '$') __ukit_scan_dollar || { __ukit_ok=0; break; } ;;
222
+ *) I=$((I + 1)) ;;
223
+ esac
224
+ done
225
+ [ "$__ukit_ok" -eq 1 ] || break
226
+ # The word ran into the scan window's edge: it may continue past it.
227
+ if [ "$__ukit_cut" -eq 1 ] && [ "$I" -ge "$N" ]; then break; fi
228
+ __ukit_word="${COMMAND:__ukit_ws:I-__ukit_ws}"
229
+ if [[ "$__ukit_word" =~ $__ukit_assign_re ]]; then
230
+ continue
231
+ fi
232
+ case "$__ukit_word" in
92
233
  time|command|env) continue ;;
93
- '|'|'||'|'&&'|';') break ;;
94
234
  esac
95
- BIN="$token"
235
+ BIN="$__ukit_word"
96
236
  break
97
237
  done
98
- set +f
99
238
 
100
239
  if [ -z "$BIN" ]; then
101
240
  exit 0
102
241
  fi
103
242
 
243
+ # A leading dash is an option of a skipped wrapper (`command -v`, `env -i`,
244
+ # `time -p`) or leftover junk, never a binary — never mint it.
245
+ case "$BIN" in
246
+ -*) exit 0 ;;
247
+ esac
248
+
104
249
  if [[ ! "$BIN" =~ ^[a-zA-Z0-9._/-]+$ ]]; then
105
250
  exit 0
106
251
  fi
@@ -54,8 +54,7 @@ else
54
54
  __ukit_waiter=$!
55
55
  wait "$__ukit_reader" 2>/dev/null
56
56
  __ukit_stage_rc=$?
57
- kill "$__ukit_waiter" 2>/dev/null
58
- wait "$__ukit_waiter" 2>/dev/null
57
+ { kill "$__ukit_waiter"; wait "$__ukit_waiter"; } 2>/dev/null
59
58
  exec 8<&-
60
59
  __ukit_size="$(wc -c < "$UKIT_INPUT_FILE" 2>/dev/null | tr -d '[:space:]')"
61
60
  if [ "$__ukit_stage_rc" -ne 0 ] || [ "$__ukit_size" -gt 2097152 ]; then
@@ -87,34 +86,86 @@ fi
87
86
  __ukit_coord_out="$(mktemp "${TMPDIR:-/tmp}/ukit-coord-out.XXXXXX")"
88
87
  __ukit_coord_err="$(mktemp "${TMPDIR:-/tmp}/ukit-coord-err.XXXXXX" 2>/dev/null)" || __ukit_coord_err=/dev/null
89
88
  __ukit_coord_t0=$SECONDS
90
- printf '%s' "$INPUT" | UKIT_HARNESS="${UKIT_HARNESS:-claude-code}" UKIT_HOOK_DEADLINE_MS="${UKIT_HOOK_DEADLINE_MS:-3000}" node "$SCRIPT" --evaluate-stop > "$__ukit_coord_out" 2>"$__ukit_coord_err" &
89
+ printf '%s' "$INPUT" | UKIT_HARNESS="${UKIT_HARNESS:-claude-code}" UKIT_HOOK_DEADLINE_MS="${UKIT_HOOK_DEADLINE_MS:-5000}" node "$SCRIPT" --evaluate-stop > "$__ukit_coord_out" 2>"$__ukit_coord_err" &
91
90
  __ukit_coord_pid=$!
92
- __ukit_coord_ms="${UKIT_HOOK_DEADLINE_MS:-3000}"
93
- case "$__ukit_coord_ms" in ''|*[!0-9]*) __ukit_coord_ms=3000 ;; esac
91
+ __ukit_coord_ms="${UKIT_HOOK_DEADLINE_MS:-5000}"
92
+ case "$__ukit_coord_ms" in ''|*[!0-9]*) __ukit_coord_ms=5000 ;; esac
94
93
  __ukit_coord_ms=$((__ukit_coord_ms + 1500))
95
94
  printf -v __ukit_coord_s '%d.%03d' $((__ukit_coord_ms / 1000)) $((__ukit_coord_ms % 1000))
96
95
  ( sleep "$__ukit_coord_s" 2>/dev/null; kill -9 "$__ukit_coord_pid" 2>/dev/null ) <&- >/dev/null 2>&1 &
97
96
  __ukit_killer_pid=$!
98
97
  wait "$__ukit_coord_pid" 2>/dev/null
99
98
  STATUS=$?
100
- kill "$__ukit_killer_pid" 2>/dev/null
101
- wait "$__ukit_killer_pid" 2>/dev/null
99
+ # One redirect around both: bash 3.2 can reap the killed job between the two commands and would print its
100
+ # "Terminated: 15" job notice on the hook's stderr.
101
+ { kill "$__ukit_killer_pid"; wait "$__ukit_killer_pid"; } 2>/dev/null
102
102
  OUTPUT="$(cat "$__ukit_coord_out" 2>/dev/null)"
103
103
  rm -f "$__ukit_coord_out"
104
- # Bounded diagnostic for a crashed coordinator (status>128 = killed by signal N-128, e.g. 137 = the deadline killer's SIGKILL).
104
+ # A coordinator that exits 0 but could not get a verdict out of the completion evaluator (killed at its time
105
+ # slice, hook deadline hit, evaluator crashed) answers with a fixed fail-closed block. Field telemetry: on a
106
+ # loaded machine one session took 170+ such blocks in a row — nothing the agent can do changes the outcome, so
107
+ # every block is a wasted turn. It is the same infrastructure failure as a crashed coordinator and shares its
108
+ # consecutive-failure breaker. The marker is JSON structure (a quote inside a reason string is escaped), so
109
+ # reason text can never forge it.
110
+ INFRA_BLOCK=0
111
+ if [ "$STATUS" -eq 0 ]; then
112
+ case "$OUTPUT" in *'"policyOwner":"fail-closed"'*) INFRA_BLOCK=1 ;; esac
113
+ # A handoff-cursor or task-watchdog block riding on the same decision is a real verdict about unfinished
114
+ # work: never count it toward a release (those lanes own their own stall breakers).
115
+ case "$OUTPUT" in *'also requested a block: '*) INFRA_BLOCK=0 ;; esac
116
+ fi
117
+ # Bounded diagnostic for a failed evaluation (status>128 = killed by signal N-128, e.g. 137 = the deadline killer's SIGKILL).
105
118
  # Written to a private cache file only; never part of the decision text (the reason stays fixed and redacted).
106
- if [ "$STATUS" -ne 0 ]; then
119
+ if [ "$STATUS" -ne 0 ] || [ "$INFRA_BLOCK" -eq 1 ]; then
107
120
  mkdir -p "$PROJECT_ROOT/.ukit/storage/cache" 2>/dev/null
108
121
  { printf 'status=%s elapsed_s=%s deadline_ms=%s\n' "$STATUS" "$((SECONDS - __ukit_coord_t0))" "${__ukit_coord_ms}"; head -c 400 "$__ukit_coord_err" 2>/dev/null; printf '\n'; } > "$PROJECT_ROOT/.ukit/storage/cache/completion-gate-crash.last" 2>/dev/null
109
122
  fi
110
123
  [ "$__ukit_coord_err" = /dev/null ] || rm -f "$__ukit_coord_err"
111
124
 
125
+ CACHE_DIR="$PROJECT_ROOT/.ukit/storage/cache"
126
+ SESSION_KEY="$(printf '%s' "$INPUT" | sed -n 's/.*"session_id"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p' | head -1 | tr -c 'A-Za-z0-9_-' '_' | cut -c1-80)"
127
+ [ -n "$SESSION_KEY" ] || SESSION_KEY="unknown"
128
+ INFRA_FILE="$CACHE_DIR/completion-gate-infra.$SESSION_KEY.streak"
129
+ if [ "$INFRA_BLOCK" -eq 1 ]; then
130
+ # Evaluator-failure breaker. Separate from the crash breaker below on purpose:
131
+ # - keyed per session, so one session's failures never count toward releasing another;
132
+ # - one epoch stamp per failure, and a release needs BOTH more than the cap of consecutive failures AND
133
+ # at least INFRA_MIN_SPAN_S of wall clock between the first failure and this one — an agent that
134
+ # simply stops again a few times in a row cannot talk its way out;
135
+ # - the release is announced as a blocked, non-complete outcome, never as a pass.
136
+ INFRA_MIN_SPAN_S=120
137
+ mkdir -p "$CACHE_DIR" 2>/dev/null
138
+ NOW_S="$(date +%s)"
139
+ # Consecutive means close in time as well: a failure left over from an earlier burst (the session then
140
+ # sat idle with no real verdict to clear it) must not lend its age to a new burst of quick stops.
141
+ INFRA_MAX_GAP_S=600
142
+ LAST_S="$(grep '^[0-9][0-9]*$' "$INFRA_FILE" 2>/dev/null | tail -1)"
143
+ case "$LAST_S" in ''|*[!0-9]*) LAST_S="$NOW_S" ;; esac
144
+ [ $((NOW_S - LAST_S)) -le "$INFRA_MAX_GAP_S" ] || : > "$INFRA_FILE" 2>/dev/null
145
+ printf '%s\n' "$NOW_S" >> "$INFRA_FILE" 2>/dev/null
146
+ STREAK="$(grep -c '^[0-9][0-9]*$' "$INFRA_FILE" 2>/dev/null)"
147
+ case "$STREAK" in ''|*[!0-9]*) STREAK=1 ;; esac
148
+ FIRST_S="$(grep -m1 '^[0-9][0-9]*$' "$INFRA_FILE" 2>/dev/null)"
149
+ case "$FIRST_S" in ''|*[!0-9]*) FIRST_S="$NOW_S" ;; esac
150
+ MAX_STREAK="$(sed -n 's/.*"stopGateMaxCrashStreaks"[[:space:]]*:[[:space:]]*\([0-9][0-9]*\).*/\1/p' "$PROJECT_ROOT/.ukit/storage/config.json" 2>/dev/null | head -1)"
151
+ case "$MAX_STREAK" in ''|*[!0-9]*) MAX_STREAK=3 ;; esac
152
+ SPAN_S=$((NOW_S - FIRST_S))
153
+ if [ "$STREAK" -gt "$MAX_STREAK" ] && [ "$SPAN_S" -ge "$INFRA_MIN_SPAN_S" ]; then
154
+ : > "$INFRA_FILE" 2>/dev/null
155
+ printf '%s\n' '{"systemMessage":"UKit stop coordinator released this stop after '"$STREAK"' consecutive stops over '"$SPAN_S"'s on which the completion evaluator could not finish (out of time or failed — usually a busy machine or slow disk). Completion was NOT verified: this is a blocked, non-complete outcome, not a pass — do not report the task as done on the strength of this release. If this keeps happening on an idle machine, run `ukit install`.","outcome":"blocked","complete":false}'
156
+ exit 0
157
+ fi
158
+ # Under the cap: the coordinator's own fixed, redacted block goes through unchanged.
159
+ printf '%s\n' "$OUTPUT"
160
+ exit 0
161
+ fi
162
+
112
163
  if [ "$STATUS" -ne 0 ]; then
113
- # BUG-C22-05: a PERSISTENT coordinator crash must not block every Stop forever.
114
- # Byte-append one marker per crash; a clean run deletes the file, so the count
115
- # is consecutive crashes, not lifetime crashes. File-based (no node) so the
164
+ # BUG-C22-05: a PERSISTENT infrastructure failure must not block every Stop forever.
165
+ # Byte-append one marker per failure; a clean run deletes the file, so the count
166
+ # is consecutive failures, not lifetime failures. File-based (no node) so the
116
167
  # breaker still works when node itself is what is crashing.
117
- CRASH_FILE="$PROJECT_ROOT/.ukit/storage/cache/completion-gate-crash.streak"
168
+ CRASH_FILE="$CACHE_DIR/completion-gate-crash.streak"
118
169
  mkdir -p "$(dirname "$CRASH_FILE")" 2>/dev/null
119
170
  printf '.' >> "$CRASH_FILE" 2>/dev/null
120
171
  STREAK="$(wc -c < "$CRASH_FILE" 2>/dev/null | tr -d '[:space:]')"
@@ -135,8 +186,10 @@ if [ "$STATUS" -ne 0 ]; then
135
186
  exit 0
136
187
  fi
137
188
 
138
- # A clean coordinator run resets the consecutive-crash streak.
139
- rm -f "$PROJECT_ROOT/.ukit/storage/cache/completion-gate-crash.streak" 2>/dev/null
189
+ # A real verdict resets both consecutive-failure counts: the crash streak, and THIS session's
190
+ # evaluator-failure streak (other sessions keep theirs).
191
+ rm -f "$CACHE_DIR/completion-gate-crash.streak" 2>/dev/null
192
+ [ -s "$INFRA_FILE" ] && : > "$INFRA_FILE" 2>/dev/null
140
193
 
141
194
  if [ -n "$OUTPUT" ]; then
142
195
  printf '%s\n' "$OUTPUT"
@@ -2908,6 +2908,9 @@ function applyTaskSemantics(contract, semantic) {
2908
2908
  'hi', 'hello', 'hey', 'yo', 'chao', 'xin', 'good',
2909
2909
  'morning', 'afternoon', 'evening',
2910
2910
  'thanks', 'thank', 'cam', 'on', 'bye', 'tam', 'biet',
2911
+ // Bare acknowledgements ("ok", "có", "được rồi", "yes") are social turns, not work orders:
2912
+ // they must never mint a fresh implementation contract (3.4.81 audit).
2913
+ 'ok', 'okay', 'oke', 'yes', 'yep', 'yeah', 'co', 'duoc', 'vang', 'da', 'u', 'uh', 'um', 'roi', 'dong', 'y',
2911
2914
  ]);
2912
2915
  const filler = new Set([
2913
2916
  'you', 'u', 'there', 'guys', 'everyone', 'all',
@@ -2915,7 +2918,11 @@ function applyTaskSemantics(contract, semantic) {
2915
2918
  'ok', 'okay', 'again', 'still',
2916
2919
  ]);
2917
2920
  let coreHit = false;
2918
- for (const token of tokens) {
2921
+ for (let i = 0; i < tokens.length; i += 1) {
2922
+ const token = tokens[i];
2923
+ // Tone-folding makes "đóng" (close) and "đồng" (as in "đồng ý", agreed) the same token:
2924
+ // only the pair "dong y" is an acknowledgement; "đóng nhé" is an order to close something.
2925
+ if (token === 'dong' && tokens[i + 1] !== 'y') return false;
2919
2926
  if (core.has(token)) {
2920
2927
  coreHit = true;
2921
2928
  } else if (!filler.has(token)) {
@@ -2992,8 +2999,16 @@ function applyTaskSemantics(contract, semantic) {
2992
2999
  return !mutationOrder;
2993
3000
  }
2994
3001
 
3002
+ // Tone-folding turns unrelated Vietnamese words into mutation verbs: "cái" (this/thing) -> cai (cài),
3003
+ // "chính" (main/exactly) -> chinh (chỉnh), "Việt" -> viet (viết), "đợi/đời/đối/đội/đôi/đói" -> doi (đổi),
3004
+ // "cháy/chảy" -> chay (chạy), "sữa" -> sua (sửa), "thèm" -> them (thêm). Mask the toned non-verbs BEFORE
3005
+ // folding, so "Cái này là gì, tại sao…" is not read as an install order (3.4.81 telemetry audit).
3006
+ function maskTonedNonVerbs(text = '') {
3007
+ return String(text ?? '').normalize('NFC')
3008
+ .replace(/(?<![\p{L}\p{N}_])(?:cái|chính|việt|cháy|chảy|đợi|đời|đối|đội|đôi|đói|sữa|thèm)(?![\p{L}\p{N}_])/giu, ' _ ');
3009
+ }
2995
3010
  function hasMutationOrder({ promptText = '', commandText = '' } = {}) {
2996
- const folded = `${publicationScope(promptText).text}\n${commandText ?? ''}`
3011
+ const folded = `${publicationScope(maskTonedNonVerbs(promptText)).text}\n${commandText ?? ''}`
2997
3012
  .toLowerCase()
2998
3013
  .normalize('NFD')
2999
3014
  .replace(/[\u0300-\u036f]/g, '')
@@ -3029,6 +3044,11 @@ function applyTaskSemantics(contract, semantic) {
3029
3044
  .replace(new RegExp(`\\bchua\\s+(?:can|nen|phai)\\s+${WAIT_TAIL}`, 'g'), ' ')
3030
3045
  .replace(new RegExp(`\\b(?:neu|if)\\s+${TAIL}`, 'g'), ' ')
3031
3046
  .replace(/\bdoi\s+chieu\b/g, ' ')
3047
+ // Field telemetry (3.4.81 audit): words that fold onto a mutation verb but name no order.
3048
+ // "chưa được cấp quyền cập nhật" / "no permission to update" reports a missing permission (read-only
3049
+ // banners); "gì thêm [nữa]" / "thêm nữa không" mean "anything else", never the verb "add".
3050
+ .replace(/\b(?:(?:chua|khong)\s+(?:duoc\s+)?(?:cap\s+|co\s+)?quyen|(?:no|not\s+have|without|lacks?)\s+permission\s+to)\s+(?:implement|apply|update|modify|add|create|ship|deliver|fix|refactor|remove|delete|rename|change|write|build|make|install|run|deploy|execute|edit|sua|them|tao|xoa|doi|thay\s+the|cap\s+nhat|viet|chay|cai|chinh|trien\s+khai|cau\s+hinh)(?![a-z0-9_])/g, ' ')
3051
+ .replace(/(?<=\b(?:con|co)\b[^.?!,;:\n]{0,40})\b(?:gi|nao)\s+them(?:\s+nua)?(?:\s+(?:khong|ko))?\s*(?=[?.!,;:\n]|$)|\bthem\s+nua\s+(?:khong|ko)\s*(?=[?.!\n]|$)/g, ' ')
3032
3052
  .replace(new RegExp(`\\bchua\\s+(?:sua|fix|implement|trien\\s+khai|viet|thay\\s+doi)\\b${WAIT_TAIL}`, 'g'), ' ')
3033
3053
  .replace(/\bhow\s+(?:we|i|you|they)\s+(?:would|will|could|should|might)\b[^.,;\n?]*/g, ' ')
3034
3054
  .replace(/\b(?:would|will|could|might)\s+later\b[^.,;\n?]*/g, ' ')
@@ -3212,6 +3232,11 @@ function applyTaskSemantics(contract, semantic) {
3212
3232
  const questionShapedPrompt = /\?\s*$/.test(trimmedPromptText)
3213
3233
  || leadingInterrogative
3214
3234
  || /\b(?:la gi|duoc khong)\s*$/.test(foldedPromptText)
3235
+ // Field telemetry (3.4.81 audit): a what-is question mid-prompt ("… là gì, …") and a leading
3236
+ // explanation request ("giải thích …", "explain …") ask for an answer. Both still pass the
3237
+ // hasMutationOrder/targetFile veto below, so "giải thích rồi sửa luôn" stays an order.
3238
+ || /\bla gi\s*(?:[,.?!;:\n]|$)/.test(foldedPromptText)
3239
+ || /^(?:hay\s+|vui\s+long\s+|lam\s+on\s+|please\s+)?(?:giai\s+thich|explain)\b/.test(foldedPromptText)
3215
3240
  || /\b(?:chua|duoc khong|dung khong|khong nhi|khong|nhi)\s*[.!?]*\s*$/.test(foldedPromptText);
3216
3241
  // it with hasMutationOrder keeps "sửa file cho tôi?" mutating while
3217
3242
  // "lỗi này chưa nhỉ" / "should I fix the hook?" consult. A targetFile
@@ -4518,9 +4543,19 @@ function applyTaskSemantics(contract, semantic) {
4518
4543
  if (fresh?.taskKind) {
4519
4544
  const identity = semanticContractIdentity({ promptText: previous.routingContext.lastExplicitUserPromptText,
4520
4545
  targetFile: persisted.routingContext?.targetFile || '', taskInstanceId });
4521
- const comparison = compareSemanticContracts({ stored: storedContract,
4522
- fresh: applyTaskSemantics(buildExecutionContract(persisted.routeSummary?.executionMode || 'local-build'), fresh),
4523
- previousIdentity: previous.semanticIdentity, identity });
4546
+ // The execution mode is re-scored on every tool event while the contract stays the task's own, so
4547
+ // the mode of THIS event is not the mode the contract was derived under. A stored contract is
4548
+ // consistent when it equals the derivation under any mode base (telemetry: 170+ false
4549
+ // "invariant violation" Stop blocks from mode churn alone).
4550
+ const derive = (mode) => compareSemanticContracts({ stored: storedContract,
4551
+ fresh: applyTaskSemantics(buildExecutionContract(mode), fresh), previousIdentity: previous.semanticIdentity, identity });
4552
+ let comparison = derive(persisted.routeSummary?.executionMode || 'local-build');
4553
+ if (comparison.status === 'invariant-violation') {
4554
+ for (const mode of ['tiny-fix', 'local-fix', 'local-build', 'find-cause', 'shared-edit', 'map-impact', 'review-release']) {
4555
+ const other = derive(mode);
4556
+ if (other.status === 'equal') { comparison = other; break; }
4557
+ }
4558
+ }
4524
4559
  if (comparison.status === 'invariant-violation') persisted.semanticDiagnostic = comparison;
4525
4560
  else if (comparison.status !== 'equal') semanticFromPrompt = fresh;
4526
4561
  }
@@ -4541,7 +4576,12 @@ function applyTaskSemantics(contract, semantic) {
4541
4576
  && (semantic.taskKind === 'CODE_IMPLEMENTATION' || answerQuestion)
4542
4577
  && (isInformationalPrompt({ promptText: turnPrompt })
4543
4578
  || isPureGreetingPrompt({ promptText: turnPrompt }));
4544
- const unownedToolTurn = !extractPrompt(payload) && payload.tool_name && !storedContract;
4579
+ // A system-injected turn (wakeup / compaction summary) resumes the previous task; when that task holds
4580
+ // no contract (the owner's last turn was a question), the injected wording must not mint one: it was
4581
+ // classified from the wakeup text but bound to the owner's prompt identity, which the gate then
4582
+ // reported as a contradiction on every stop.
4583
+ const unownedToolTurn = (!extractPrompt(payload) && payload.tool_name && !storedContract)
4584
+ || (systemOriginTurn && !storedContract?.taskKind);
4545
4585
  if (informationalTurn || unownedToolTurn) {
4546
4586
  // An answer-only turn must not enforce carried write debt, but it must not ERASE the
4547
4587
  // contract either: park it (session- and task-bound) so a continuation or the next
@@ -4581,13 +4621,14 @@ function applyTaskSemantics(contract, semantic) {
4581
4621
  const kept = { ...persisted.routeSummary.executionContract };
4582
4622
  // statusReport / verificationOnly are only stripped on re-derivation: for a NEW task they drive the
4583
4623
  // carried-status rebuild below, so they must survive to be recognised there.
4584
- const staleKeys = semanticFromPrompt ? ['publication', 'operationGoal', 'configurationScope', 'releasePolicy', 'conditionalObligations', 'reportArtifact', 'verificationOnly', 'statusReport']
4585
- : ['publication', 'operationGoal', 'configurationScope', 'releasePolicy', 'conditionalObligations', 'reportArtifact'];
4624
+ const staleKeys = semanticFromPrompt ? ['publication', 'operationGoal', 'operationGoals', 'configurationScope', 'releasePolicy', 'conditionalObligations', 'reportArtifact', 'verificationOnly', 'statusReport']
4625
+ : ['publication', 'operationGoal', 'operationGoals', 'configurationScope', 'releasePolicy', 'conditionalObligations', 'reportArtifact', 'stateVerification', 'stateAction', 'stateConditionalStop', 'stateTargets'];
4586
4626
  for (const key of staleKeys) delete kept[key];
4587
- // MIXED/OPERATIONAL evidence tags belong to the previous task's classification: a new task starts from
4588
- // the mode's base evidence so it is not asked for operation proof its own prompt never ordered.
4589
- if ((!continuingTask || semanticFromPrompt) && semantic.taskKind !== 'MIXED' && semantic.taskKind !== 'OPERATIONAL'
4590
- && Array.isArray(kept.completionEvidence) && kept.completionEvidence.includes('operation-verification')) {
4627
+ // Evidence tags belong to the previous task's classification (operation-verification, a READ_ONLY
4628
+ // task's impact-evidence, state-verification, ...): a new task starts from the mode's base evidence so
4629
+ // it is not asked for proof its own prompt never ordered. A leaked tag also made the stored contract
4630
+ // differ from its own re-derivation, which the gate reported as an invariant violation.
4631
+ if ((!continuingTask || semanticFromPrompt) && Array.isArray(kept.completionEvidence) && kept.statusReport !== true) {
4591
4632
  const baseMode = persisted.routeSummary.executionMode === 'informational' ? 'local-build' : persisted.routeSummary.executionMode;
4592
4633
  const base = buildExecutionContract(baseMode);
4593
4634
  if (Array.isArray(base?.completionEvidence)) kept.completionEvidence = base.completionEvidence;
@@ -4603,6 +4644,12 @@ function applyTaskSemantics(contract, semantic) {
4603
4644
  if (!carriedStatus || persisted.routingContext?.mutationOrder === true) {
4604
4645
  persisted.routeSummary.executionContract = applyTaskSemantics(
4605
4646
  persisted.routeSummary.executionContract || buildExecutionContract(persisted.routeSummary.executionMode === 'informational' ? 'local-build' : persisted.routeSummary.executionMode), semantic);
4647
+ // A continuing turn re-applies the task's own contract: its evidence list stays as classified, never
4648
+ // re-unioned with the base of whatever mode this tool event happened to score.
4649
+ if (continuingTask && !semanticFromPrompt && semantic === previous.routeSummary?.executionContract
4650
+ && Array.isArray(semantic.completionEvidence) && semantic.completionEvidence.length > 0) {
4651
+ persisted.routeSummary.executionContract.completionEvidence = [...semantic.completionEvidence];
4652
+ }
4606
4653
  if (persisted.contractOrigin !== 'carried-system') persisted.contractOrigin = 'classified';
4607
4654
  }
4608
4655
  if (semantic.taskKind === 'OPERATIONAL' || semantic.taskKind === 'READ_ONLY'
@@ -4716,8 +4763,62 @@ function applyTaskSemantics(contract, semantic) {
4716
4763
  let previous = sessionId
4717
4764
  ? [storedPrevious, sidecarPrevious].find((state) => String(state?.sessionId || '').trim() === sessionId && publishedPrevious(state)) || {}
4718
4765
  : storedPrevious;
4719
- const continuationPrompt = /^(?:continue|resume|keep going|go on|proceed|tiep tuc|lam tiep)(?:\s+(?:with\s+)?(?:the\s+|this\s+)?(?:previous\s+|last\s+|current\s+|same\s+)?(?:implementation\s+)?(?:task|work))?(?:\s+(?:thoi|di|đi|nhe|nao|nua|a|ha|please|pls|now|then))*\s*[.!]?$/i.test(
4766
+ const explicitContinuationPrompt = /^(?:continue|resume|keep going|go on|proceed|tiep tuc|lam tiep)(?:\s+(?:with\s+)?(?:the\s+|this\s+)?(?:previous\s+|last\s+|current\s+|same\s+)?(?:implementation\s+)?(?:task|work))?(?:\s+(?:thoi|di|đi|nhe|nao|nua|a|ha|please|pls|now|then))*\s*[.!]?$/i.test(
4720
4767
  extractPrompt(payload).normalize('NFD').replace(/[̀-ͯ]/g, '').trim());
4768
+ // A bare "yes / ok / có / được / ừ" is normally a social turn that parks the previous contract. When it
4769
+ // ANSWERS a question the agent itself just asked ("shall I apply the fix?"), it is the owner's go-ahead for
4770
+ // that same task: parking the contract there let the agent stop without the edit it had just offered.
4771
+ // Proof is host-authored only: the last assistant text in this session's transcript must end with a
4772
+ // question. No transcript (or anything else in between) keeps the conservative parking behaviour.
4773
+ const affirmativeAnswerTurn = (() => {
4774
+ if (payload.tool_name || !sessionId) return false;
4775
+ const armed = previous.routeSummary?.executionContract?.completionEvidence?.length
4776
+ || previous.suspendedContract?.routeSummary?.executionContract?.completionEvidence?.length;
4777
+ if (!armed) return false;
4778
+ const raw = extractPrompt(payload).trim();
4779
+ if (!raw || raw.length > 40) return false;
4780
+ const tokens = raw.toLowerCase().normalize('NFD').replace(/[̀-ͯ]/g, '').replace(/đ/g, 'd')
4781
+ .replace(/[^a-z0-9\s]/g, ' ').split(/\s+/).filter(Boolean);
4782
+ if (tokens.length === 0 || tokens.length > 4) return false;
4783
+ const yes = new Set(['ok', 'okay', 'oke', 'yes', 'yep', 'yeah', 'co', 'duoc', 'vang', 'da', 'u', 'uh', 'dong', 'y']);
4784
+ const soft = new Set(['nhe', 'nha', 'please', 'pls']);
4785
+ if (!tokens.some((t) => yes.has(t)) || !tokens.every((t) => yes.has(t) || soft.has(t))) return false;
4786
+ if (tokens.some((t, i) => t === 'dong' && tokens[i + 1] !== 'y')) return false;
4787
+ const tp = payload.transcript_path ?? payload.transcriptPath;
4788
+ if (!tp || typeof tp !== 'string') return false;
4789
+ try {
4790
+ const fd = fs.openSync(tp, 'r');
4791
+ try {
4792
+ const size = fs.fstatSync(fd).size;
4793
+ const len = Math.min(size, 256 * 1024);
4794
+ const buf = Buffer.alloc(len);
4795
+ fs.readSync(fd, buf, 0, len, size - len);
4796
+ const lines = buf.toString('utf8').split('\n');
4797
+ const textOf = (entry) => {
4798
+ const content = entry?.message?.content;
4799
+ if (typeof content === 'string') return content;
4800
+ if (!Array.isArray(content)) return '';
4801
+ return content.filter((part) => part?.type === 'text' && typeof part.text === 'string').map((part) => part.text).join('\n');
4802
+ };
4803
+ for (let i = lines.length - 1; i >= 0; i -= 1) {
4804
+ const line = lines[i];
4805
+ if (!line || !(line.includes('"assistant"') || line.includes('"user"'))) continue;
4806
+ let entry; try { entry = JSON.parse(line); } catch { continue; }
4807
+ if (entry?.isSidechain === true || (entry?.sessionId && entry.sessionId !== sessionId)) continue;
4808
+ const text = textOf(entry).trim();
4809
+ if (!text) continue; // tool calls / tool results carry no prose
4810
+ if (entry.type === 'user') {
4811
+ if (entry.isMeta === true || text === raw) continue; // this very prompt, already written by the host
4812
+ return false; // another owner turn sits between the question and this reply
4813
+ }
4814
+ if (entry.type !== 'assistant') continue;
4815
+ return /[??][\s)\]"'*_`]*$/.test(text.slice(-400));
4816
+ }
4817
+ } finally { fs.closeSync(fd); }
4818
+ } catch { /* unreadable transcript: no proof */ }
4819
+ return false;
4820
+ })();
4821
+ const continuationPrompt = explicitContinuationPrompt || affirmativeAnswerTurn;
4721
4822
  // Restore a contract parked by an informational turn: only for the SAME session, and only
4722
4823
  // on an explicit continuation or a mutating tool event (never a fresh prompt, which routes on its own,
4723
4824
  // and never a read during an answer/status turn: that must not resurrect write debt).
@@ -5352,7 +5453,7 @@ function applyTaskSemantics(contract, semantic) {
5352
5453
  || hasAdvisoryOnlyAssertion({ promptText, commandText })) && !filePath;
5353
5454
  // Greeting fast-path: a pure greeting gets the same read-only stamp as an
5354
5455
  // informational question — never a mutating lane, never task debt.
5355
- const greetingFastPath = !filePath && isPureGreetingPrompt({ promptText, commandText });
5456
+ const greetingFastPath = !filePath && !affirmativeAnswerTurn && isPureGreetingPrompt({ promptText, commandText });
5356
5457
  // A delivery-only prompt ("push this to git", "đẩy bộ này lên git") starts a new,
5357
5458
  // mutation-free action and typically matches no skill. It must not inherit the
5358
5459
  // previous request's completion contract — carrying find-cause/map-impact debt