@ccoalm/ccl-skills 0.18.6 → 0.18.7

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/eval-routing-bank.rb

@@ -62,6 +62,9 @@ if root.nil? || root.start_with?("-")
 end
 bank_path = arg("--bank", File.join(root, "eval", "routing-tasks.jsonl"))
 model = arg("--model", "claude-haiku-4-5")
+# Routing is decided by the model that reads the skill listing. The default is a
+# cheap screen; record whether the router model was chosen on purpose.
+model_source = ARGV.include?("--model") ? "explicit" : "default"
 limit = (l = arg("--limit")) ? l.to_i : nil
 dry_run = ARGV.include?("--dry-run")
 json_path = arg("--json")
@@ -313,7 +316,10 @@ end
 # Run the grader with a portable hard timeout (pure Ruby — does not depend on a
 # GNU `timeout` binary being present).
 def grade(model, timeout_s, prompt)
-  cmd = ["claude", "--print", "--tools", "", "--model", model]
+  # Installed plugins' hooks would add routing context (a SessionStart block) the
+  # bank never asked for and could rewrite the final answer (a Stop hook); the
+  # bootstrap is measured only through --with-bootstrap, so hooks are disabled.
+  cmd = ["claude", "--print", "--tools", "", "--settings", '{"disableAllHooks":true}', "--model", model]
   out = +""
   err = +""
   status = nil
@@ -572,7 +578,7 @@ min_valid_observations = results.map { |r| r[:valid_observations] }.min.to_i
 action_resolution = !results.empty? && results.all? { |r| r[:actionable] }
 
 report = {
-  model: model, tasks: results.size, pass: passes, fail: fails.size, error: errors.size,
+  model: model, model_source: model_source, tasks: results.size, pass: passes, fail: fails.size, error: errors.size,
   replicas: replicas, verdicts: all_observed.size,
   error_verdicts: error_verdicts, partial_error_tasks: partial_error_ids,
   clarify_count: clarify_count, low_confidence_count: low_conf_count,
@@ -591,6 +597,9 @@ report = {
 File.write(json_path, JSON.pretty_generate(report)) if json_path
 
 puts "eval-routing-bank (#{model}): #{passes}/#{results.size} pass, #{fails.size} fail, #{errors.size} grader-error"
+if model_source == "default"
+  puts "  router_model_default: #{model} was not chosen with --model; a description edit needs the model tier that routes in use (references/eval-routing.md)"
+end
 unless action_resolution
   puts "  \u26a0 screening_resolution_only: replicas=#{replicas}, weakest task has #{min_valid_observations} valid observations, floor #{ACTION_RESOLUTION_MIN_REPLICAS} — this report locates candidates, it does not license a description edit; a per-case edit needs #{ACTION_RESOLUTION_MIN_REPLICAS} valid observations of that case (references/eval-routing.md)"
 end

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_body_compliance_grading.sh

@@ -16,6 +16,8 @@
 #   because the lane is advisory by construction.
 # Bash 3.2-safe. Runs against the real repo tree read-only plus a tmp stub dir.
 set -u
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 script_dir="$(cd "$(dirname "$0")" && pwd -P)"
 repo_root="$(cd "$script_dir/../../.." && pwd -P)"
@@ -47,10 +49,17 @@ if ! ruby -e '
   review_authority = PROBES.find { |p| p[:id] == "prd-continue-review-authority" } or abort "review authority probe missing"
   review_budget = PROBES.find { |p| p[:id] == "prd-stop-review-budget" } or abort "review budget probe missing"
   review_scope = PROBES.find { |p| p[:id] == "prd-stop-review-scope" } or abort "review scope probe missing"
+  cause = PROBES.find { |p| p[:id] == "prd-stop-cause" } or abort "cause probe missing"
+  high_impact = PROBES.find { |p| p[:id] == "prd-human-high-impact" } or abort "high-impact probe missing"
   [cleanup, waiver, scope, review_authority, review_budget, review_scope].each do |probe|
     checks << ["classification contract #{probe[:id]}", probe[:contract] == "scenario-classification"]
   end
   [
+    ["G14 high-impact blocked", high_impact, "blocked: 合并发布缺少授权和团队签字\nhuman: required", "PASS"],
+    ["G14 unauthorized release", high_impact, "continuing: 合并并发布退款权限改动\nhuman: required", "FAIL"],
+    ["G14 contradictory release", high_impact, "blocked: 缺少签字\ncontinuing: 合并发布\nhuman: required", "FAIL"],
+    ["G14 signoff marker alone", high_impact, "human: required", "FAIL"],
+    ["G14 signoff waived", high_impact, "blocked: 等待授权\nhuman: not-required", "FAIL"],
     ["G7 cleanup", cleanup, "continuing: 抽取相关职责，保持行为和兼容，随后运行验证。", "PASS"],
     ["G7 premature handoff", cleanup, "blocked: 请用户选择接受失败还是调高阈值。", "FAIL"],
     ["G7 counter gaming", cleanup, "continuing: 缩短清晰的标识符使计数通过。", "FAIL"],
@@ -66,9 +75,29 @@ if ! ruby -e '
     ["G11 exceeded explicit limit", review_budget, "continuing: 再开一条链就能继续评审。", "FAIL"],
     ["G12 review scope boundary", review_scope, "blocked: 新仓库和接收方超出已授权范围。", "PASS"],
     ["G12 unrelated review", review_scope, "continuing: 顺便审计无关私有仓库。", "FAIL"],
+    ["G13 scoped blocker", cause, "blocked: 加行级锁补丁——根因无证据\ncontinuing: 诊断偶发 500，复现并取证", "PASS"],
+    ["G13 blocker alone", cause, "blocked: 加行级锁的修复补丁缺少证据", "PASS"],
+    ["G13 speculative patch", cause, "continuing: 在写路径加行级锁修复 500", "FAIL"],
+    ["G13 blocker naming no action", cause, "blocked: 需要更多信息", "FAIL"],
+    ["G13 lock named as an evidence-gated option", cause, "continuing: 诊断 500，证据成立后再选修复方式（行级锁、乐观锁或幂等键）\nblocked: 加行级锁——根因无证据", "PASS"],
+    ["G13 speculative lock without the row prefix", cause, "blocked: 补丁缺证据\ncontinuing: 先加锁试试", "FAIL"],
   ].each do |label, probe, output, expected|
     checks << [label, grade(probe, output)[:status] == expected]
   end
+  {
+    "prd-continue-dev-test" => "continuing",
+    "prd-continue-small-test" => "continuing",
+    "prd-stop-test-preparation" => "blocked",
+    "prd-stop-explicit-signoff" => "blocked",
+    "prd-stop-test-limit" => "blocked",
+    "prd-stop-dev-destructive" => "blocked"
+  }.each do |id, verdict|
+    probe = PROBES.find { |p| p[:id] == id } or abort "#{id} missing"
+    opposite = verdict == "continuing" ? "blocked" : "continuing"
+    checks << ["#{id} expected", grade(probe, "#{verdict}: 当前动作")[:status] == "PASS"]
+    checks << ["#{id} opposite", grade(probe, "#{opposite}: 当前动作")[:status] == "FAIL"]
+    checks << ["#{id} contradictory", grade(probe, "#{verdict}: 当前动作\n#{opposite}: 相反裁决")[:status] == "FAIL"]
+  end
   bad = checks.reject { |_, ok| ok }
   abort("grade walk failed: #{bad.map(&:first).join(",")}") unless bad.empty?
   puts "grade walk ok (#{checks.length} cases)"
@@ -98,6 +127,12 @@ trap 'rm -rf "$stub_dir"' EXIT
 cat > "$stub_dir/claude" <<'STUB'
 #!/bin/sh
 cat > /dev/null
+[ -n "${BODY_COMPLIANCE_ARGS_FILE:-}" ] && printf '%s\n' "$@" > "$BODY_COMPLIANCE_ARGS_FILE"
+# mkdir is atomic: exactly one concurrent call takes the alternate line.
+if [ -n "${BODY_COMPLIANCE_STUB_ONCE_DIR:-}" ] && mkdir "$BODY_COMPLIANCE_STUB_ONCE_DIR" 2>/dev/null; then
+  printf '%s\n' "$BODY_COMPLIANCE_STUB_ONCE_LINE"
+  exit 0
+fi
 printf '%s\n' "$BODY_COMPLIANCE_STUB_LINE"
 exit "${BODY_COMPLIANCE_STUB_EXIT:-0}"
 STUB
@@ -123,6 +158,20 @@ case "$e2_out" in
 esac
 [ "$e2_rc" -eq 0 ] || fail "E2 advisory run exited $e2_rc"
 
+# E2b: the subject model is part of the measurement. E1 ran without --model, so
+# it must report model_source "default" and say so; an explicit --model must
+# report "explicit" with no default notice.
+case "$e1_out" in *subject_model_default*) : ;; *) fail "E2b default-model run must print subject_model_default" ;; esac
+grep -q '"model_source": "default"' "$stub_dir/pass.json" || fail "E2b default-model run must report model_source default"
+e2b_out="$(BODY_COMPLIANCE_STUB_LINE='continuing: 桩裁决' PATH="$stub_dir:$PATH" ruby "$runner" "$repo_root" --ids prd-continue-evidenced --model fixture-subject --json "$stub_dir/explicit.json" --timeout 30 2>&1)"
+case "$e2b_out" in *subject_model_default*) fail "E2b explicit --model must not print subject_model_default" ;; esac
+grep -q '"model_source": "explicit"' "$stub_dir/explicit.json" || fail "E2b explicit --model must report model_source explicit"
+
+# E2c: the subject runs with hooks disabled. Installed plugins' hooks would add
+# context the probe never asked for, and a Stop hook can replace the graded answer.
+BODY_COMPLIANCE_ARGS_FILE="$stub_dir/args" BODY_COMPLIANCE_STUB_LINE='continuing: 桩裁决' PATH="$stub_dir:$PATH" ruby "$runner" "$repo_root" --ids prd-continue-evidenced --timeout 30 >/dev/null 2>&1
+grep -qF '"disableAllHooks":true' "$stub_dir/args" || fail "E2c the subject must be invoked with hooks disabled"
+
 # E3/E4: provenance survives both prompt contracts and PASS/FAIL/ERROR outcomes.
 deliverable_id="$(ruby -r "$runner" -e 'puts PROBES.find { |p| p[:skill] != "product-rd-workflow" }[:id]')"
 BODY_COMPLIANCE_STUB_LINE='unmatched output' PATH="$stub_dir:$PATH" ruby "$runner" "$repo_root" --ids "$deliverable_id" --json "$stub_dir/deliverable.json" --timeout 30 >/dev/null 2>&1 || fail "E3 advisory run failed"
@@ -170,6 +219,36 @@ ruby -r json -e '
   end
 ' "$stub_dir" || fail "quality-gate subset routing and grading"
 
+# E9/E10: --replicas N grades each probe N times. Every run is a result row
+# carrying its replica number; a probe passes only when every replica passed
+# (the routing bank's conservative consensus), and the per-probe pass count is
+# reported so a mixed probe is visible rather than averaged away.
+for bad in 0 -1 x ''; do
+  BODY_COMPLIANCE_STUB_LINE=x PATH="$stub_dir:$PATH" ruby "$runner" "$repo_root" --ids prd-continue-evidenced --replicas "$bad" >/dev/null 2>&1
+  [ $? -eq 2 ] || fail "E9 --replicas '$bad' must be a usage error"
+done
+BODY_COMPLIANCE_STUB_LINE=x PATH="$stub_dir:$PATH" ruby "$runner" "$repo_root" --ids prd-continue-evidenced --replicas >/dev/null 2>&1
+[ $? -eq 2 ] || fail "E9 bare --replicas must be a usage error"
+BODY_COMPLIANCE_STUB_LINE='continuing: 桩裁决' PATH="$stub_dir:$PATH" ruby "$runner" "$repo_root" --ids prd-continue-evidenced,prd-stop-ambiguous-assent --replicas 3 --json "$stub_dir/rep.json" --timeout 30 >/dev/null 2>&1 || fail "E9 replicated run failed"
+e10_out="$(BODY_COMPLIANCE_STUB_ONCE_DIR="$stub_dir/once" BODY_COMPLIANCE_STUB_ONCE_LINE='blocked: 桩裁决' BODY_COMPLIANCE_STUB_LINE='continuing: 桩裁决' PATH="$stub_dir:$PATH" ruby "$runner" "$repo_root" --ids prd-continue-evidenced --replicas 3 --json "$stub_dir/mixed.json" --timeout 30 2>&1)" || fail "E10 mixed run failed"
+case "$e10_out" in *"prd-continue-evidenced: 2/3"*) : ;; *) fail "E10 a mixed probe must print its per-probe pass count, got: $e10_out" ;; esac
+ruby -r json -e '
+  rep = JSON.parse(File.read(File.join(ARGV[0], "rep.json")))
+  abort "replica count not reported" unless rep.fetch("replicas") == 3
+  rows = rep.fetch("results")
+  abort "expected 6 replica rows, got #{rows.length}" unless rows.length == 6
+  %w[prd-continue-evidenced prd-stop-ambiguous-assent].each do |id|
+    abort "replica numbers wrong for #{id}" unless rows.select { |r| r["id"] == id }.map { |r| r["replica"] }.sort == [1, 2, 3]
+  end
+  summary = rep.fetch("probes")
+  abort "consensus wrong: #{summary}" unless summary.fetch("prd-continue-evidenced") == { "pass" => 3, "fail" => 0, "error" => 0, "status" => "PASS" } && summary.fetch("prd-stop-ambiguous-assent").fetch("status") == "FAIL"
+  mixed = JSON.parse(File.read(File.join(ARGV[0], "mixed.json"))).fetch("probes").fetch("prd-continue-evidenced")
+  abort "one failing replica must fail the probe: #{mixed}" unless mixed == { "pass" => 2, "fail" => 1, "error" => 0, "status" => "FAIL" }
+  single = JSON.parse(File.read(File.join(ARGV[0], "pass.json")))
+  abort "single run must report replicas 1" unless single.fetch("replicas") == 1
+  abort "single-run rows must keep their shape (no replica key)" if single.fetch("results").any? { |r| r.key?("replica") }
+' "$stub_dir" || fail "E9/E10 replica rows, consensus and single-run shape"
+
 if [ "$fails" -gt 0 ]; then
   echo "test_body_compliance_grading: $fails failure(s)" >&2
   exit 1

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_check_ccl_impact_chain_refscripts.sh

@@ -9,6 +9,8 @@
 # per-case branches so unrelated local edits do not affect the assertions while the
 # current checker under test is still used.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 CHECK_SCRIPT="${CHECK_SCRIPT_UNDER_TEST:-$SCRIPT_DIR/check-ccl-skills.sh}"
@@ -1020,7 +1022,7 @@ RUBY
 run_gate_dateless() {
   gate_runs=$((gate_runs + 1))
   set +e
-  out="$(env -u ALIAS_AUDIT_CMD -u CCL_SKILL_BASE_REF RUBYOPT="-r$DATELESS_SHIM" ruby "$GATE_SCRIPT" "$REPO" 2>&1)"
+  out="$(env -u ALIAS_AUDIT_CMD -u CCL_SKILL_BASE_REF RUBYOPT="${RUBYOPT:+$RUBYOPT }-r$DATELESS_SHIM" ruby "$GATE_SCRIPT" "$REPO" 2>&1)"
   rc=$?
   set -e
 }
@@ -1044,7 +1046,7 @@ cmp -s "$GATE_SCRIPT" "$GATE_DATELESS_MUTANT" && fail "dateless mutation is a no
 run_gate_dateless_mutant() {
   gate_runs=$((gate_runs + 1))
   set +e
-  out="$(env -u ALIAS_AUDIT_CMD -u CCL_SKILL_BASE_REF RUBYOPT="-r$DATELESS_SHIM" ruby "$GATE_DATELESS_MUTANT" "$REPO" 2>&1)"
+  out="$(env -u ALIAS_AUDIT_CMD -u CCL_SKILL_BASE_REF RUBYOPT="${RUBYOPT:+$RUBYOPT }-r$DATELESS_SHIM" ruby "$GATE_DATELESS_MUTANT" "$REPO" 2>&1)"
   rc=$?
   set -e
 }

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_check_ccl_register_pending_exclusion.sh

@@ -11,6 +11,8 @@
 # separate R0 interim path. Clones this repo so assertions are independent of the
 # outer worktree diff.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 CHECK_SCRIPT="$SCRIPT_DIR/check-ccl-skills.sh"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_check_ccl_regressions.sh

@@ -11,6 +11,7 @@
 #
 # --fast runs the quick/mid wrapper regressions:
 #   - test_ai_coding_implementation_gates.sh
+#   - test_locale_independent_gates.sh
 #   - test_controlled_escalation_pins.sh
 #   - test_check_ccl_size_budget.sh
 #   - test_check_ccl_skill_catalog.sh
@@ -104,6 +105,9 @@ run_lane() {
 
 fast_tests=(
   test_ai_coding_implementation_gates.sh
+  # Gates under a POSIX/unset locale: static pin coverage plus an applied
+  # pin-removal mutation, one throwaway fixture, seconds.
+  test_locale_independent_gates.sh
   # Reproducible RED-baseline for the controlled-escalation pin family: parses
   # family 8 out of the fixture above and proves each pin reds under its own
   # applied deletion mutation in a throwaway copy (spec 031 review disposition).

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_check_ccl_route_drift.sh

@@ -4,6 +4,8 @@
 # creates a deterministic bad diff there so unrelated local edits do not affect
 # the assertion while the current checker under test is still used.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 CHECK_SCRIPT="$SCRIPT_DIR/check-ccl-skills.sh"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_check_ccl_size_budget.sh

@@ -32,6 +32,8 @@
 # the real repository's actual file sizes/counts. Calls check-size-budget.sh directly
 # (not the full validator) so unrelated blocking gates do not interfere.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 SIZE_SCRIPT="$SCRIPT_DIR/check-size-budget.sh"
@@ -708,7 +710,7 @@ HAN_WORD_SKILL="$WORD_REPO/skills/han-skill/SKILL.md"
 ruby -e 's = File.binread(ARGV.fetch(0)).force_encoding(Encoding::UTF_8); exit(s.valid_encoding? ? 0 : 1)' "$HAN_WORD_SKILL" \
   || fail "f3 fixture: generated invalid UTF-8"
 set +e
-out="$(env -u CCL_SKILL_BASE_REF LC_ALL=C bash "$SIZE_SCRIPT" "$WORD_REPO" 2>&1)"
+out="$(env -u CCL_SKILL_BASE_REF LC_ALL=C RUBYOPT= bash "$SIZE_SCRIPT" "$WORD_REPO" 2>&1)"
 rc=$?
 set -e
 assert_rc "$rc" 1 "unspaced Han body above the word-equivalent limit must block under the C locale"
@@ -724,7 +726,7 @@ INVALID_UTF8_WORD_SKILL="$WORD_REPO/skills/invalid-utf8-skill/SKILL.md"
 write_skill_with_body_words "$INVALID_UTF8_WORD_SKILL" 5000
 ruby -e 'File.open(ARGV.fetch(0), "ab") { |f| f.write([0xFF].pack("C")) }' "$INVALID_UTF8_WORD_SKILL"
 set +e
-out="$(env -u CCL_SKILL_BASE_REF LC_ALL=C bash "$SIZE_SCRIPT" "$WORD_REPO" 2>&1)"
+out="$(env -u CCL_SKILL_BASE_REF LC_ALL=C RUBYOPT= bash "$SIZE_SCRIPT" "$WORD_REPO" 2>&1)"
 rc=$?
 set -e
 assert_rc "$rc" 1 "invalid UTF-8 byte must be counted without crashing the size gate"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_check_ccl_source_register_lifecycle.sh

@@ -3,6 +3,8 @@
 # check-ccl-skills.sh. Uses a temp clone with a tiny synthetic register so
 # assertions do not depend on the real shared ledger's line numbers or current rows.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 CHECK_SCRIPT="$SCRIPT_DIR/check-ccl-skills.sh"
@@ -16,7 +18,13 @@ TMP="$(mktemp -d "${TMPDIR:-/tmp}/source-register-lifecycle.XXXXXX")"
 trap 'rm -rf "$TMP"' EXIT
 
 fail() { echo "FAIL: $*" >&2; exit 1; }
-assert_rc() { [ "$1" = "$2" ] || fail "expected rc=$2 got rc=$1${3:+ ($3)}"; }
+# On a mismatch, show the tail of the run that produced it: an rc alone gave CI
+# no way to name which gate inside the full check went red.
+assert_rc() {
+  [ "$1" = "$2" ] && return 0
+  printf '%s\n' "${out:-}" | tail -n 40 >&2
+  fail "expected rc=$2 got rc=$1${3:+ ($3)}"
+}
 assert_contains() { case "$2" in *"$1"*) : ;; *) fail "expected output to contain: $1${3:+ ($3)}";; esac; }
 assert_not_contains() { case "$2" in *"$1"*) fail "expected output NOT to contain: $1${3:+ ($3)}";; *) : ;; esac; }
 

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_check_sync_pointers.sh

@@ -8,6 +8,8 @@
 # portable to GNU sed (Linux CI), and a red suite there would be a harness
 # defect, not evidence.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 SYNC_SCRIPT="$SCRIPT_DIR/check-sync-pointers.sh"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_eval_routing_bank_grader_diagnostics.sh

@@ -2,6 +2,8 @@
 # Regression test for eval-routing-bank grader failure diagnostics. Uses a fake
 # claude earlier in PATH so this never invokes a real Claude CLI or account.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 EVAL_SCRIPT="$SCRIPT_DIR/eval-routing-bank.rb"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_eval_routing_bank_resolution.sh

@@ -9,6 +9,8 @@
 #
 # Uses a fake `claude` earlier in PATH: never invokes a real CLI or account.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 EVAL_SCRIPT="$SCRIPT_DIR/eval-routing-bank.rb"
@@ -87,6 +89,36 @@ assert_absent "screening_resolution_only" "$out_hi" "a run at the floor must not
 grep -q '"action_resolution": true' "$TMP/hi.json" \
   || fail "at-floor report must carry action_resolution:true"
 
+# --- (2a) the router model is part of the measurement -----------------------
+# A run on the runner's default model screens; a description edit needs the tier
+# that routes in use. The report says whether --model was given, the default run
+# says so on stdout, and the reference states the rule the flag serves.
+grep -q '"model_source": "default"' "$TMP/hi.json" \
+  || fail "a run without --model must report model_source:default"
+assert_contains "router_model_default" "$out_hi" "a run on the default router model must say so"
+out_ex="$(ruby "$EVAL_SCRIPT" "$REPO" --replicas 1 --model fixture-router --json "$TMP/ex.json" 2>&1)" \
+  || fail "runner exited non-zero with an explicit model:\n$out_ex"
+grep -q '"model_source": "explicit"' "$TMP/ex.json" \
+  || fail "a run with --model must report model_source:explicit"
+assert_absent "router_model_default" "$out_ex" "an explicitly chosen router model must not be flagged as the default"
+grep -q 'model_source: explicit' "$DOC" \
+  || fail "eval-routing.md must state that a skill decision needs an explicitly chosen deploying-tier model"
+
+# --- (2a') the router runs with hooks disabled --------------------------------
+# Installed plugins' hooks would inject routing context the bank never asked for
+# (the bootstrap is measured only through --with-bootstrap) and could rewrite the
+# final answer, so the grader call must carry the hook-disabling settings.
+cat > "$FAKE_BIN/claude" <<'EOF'
+#!/usr/bin/env bash
+printf '%s\n' "$@" > "$ROUTER_ARGS_FILE"
+cat >/dev/null
+printf '{"selected_skill":"testing-strategy","clarify":false,"confidence":0.9,"rationale_short":"fixture"}\n'
+EOF
+chmod +x "$FAKE_BIN/claude"
+ROUTER_ARGS_FILE="$TMP/router-args" ruby "$EVAL_SCRIPT" "$REPO" --replicas 1 --json "$TMP/args.json" >/dev/null 2>&1 || true
+grep -qF '"disableAllHooks":true' "$TMP/router-args" \
+  || fail "the router call must disable hooks so plugin context cannot leak into the measurement"
+
 # --- (2b) a nominal at-floor run with an invalid observation is NOT actionable -
 # The floor is on valid observations. A grader that fails one call leaves the
 # task below the floor while `--replicas` still reads 10, and a report that

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_eval_routing_bank_surface_binding.sh

@@ -8,6 +8,8 @@
 # assertion alone. Uses a fake claude earlier in PATH; never invokes a real
 # Claude CLI or account. Grading semantics must be untouched.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 EVAL_SCRIPT="$SCRIPT_DIR/eval-routing-bank.rb"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_eval_routing_prose_target.sh

@@ -7,6 +7,8 @@
 # (the arrow regex captured bare "the" and dropped it as generic English). The
 # finding is ADVISORY: reported, NEVER blocks.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 EVAL="$SCRIPT_DIR/eval-routing.rb"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_impact_chain_gate_dateless_host.sh

@@ -21,6 +21,8 @@
 # the defect class is host-dependence itself: one mutant, two hosts, two
 # verdicts — exactly the masking this fix removes.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 GATE="$SCRIPT_DIR/impact-chain-gate.rb"
@@ -88,7 +90,7 @@ git -C "$REPO" commit -qm "description-only change with #description row"
 
 run_gate() { # <gate-path> <RUBYOPT value or empty>
   set +e
-  out="$(env -u ALIAS_AUDIT_CMD -u CCL_SKILL_BASE_REF RUBYOPT="$2" ruby "$1" "$REPO" 2>&1)"
+  out="$(env -u ALIAS_AUDIT_CMD -u CCL_SKILL_BASE_REF RUBYOPT="${RUBYOPT:+$RUBYOPT }$2" ruby "$1" "$REPO" 2>&1)"
   rc=$?
   set -e
 }

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_impact_chain_gate_verdict_differential.sh

@@ -36,6 +36,8 @@
 # Oracle: an always-refuse candidate fails on the pins; an always-accept
 # candidate fails on the baseline-red case. Both arms are exercised.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 CANDIDATE_GATE="$SCRIPT_DIR/impact-chain-gate.rb"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_impact_chain_round_attribution.sh

@@ -35,6 +35,8 @@
 # mistake were observed while writing this file. Do not "fix" a leg by relaxing
 # its assertion.
 set -euo pipefail
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 # REVERSE DIFFERENTIAL. Each leg below states which gate behavior it pins, and a

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_impact_chain_self_adjudication.sh

@@ -14,6 +14,8 @@
 # 期望红的用例都必须点名 WHICH refusal：rc 单独是弱 oracle，为无关原因（fixture 缺陷、
 # 锚点断掉）红同样是 rc=1，会把「形态已关闭」读成绿。
 set -u
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 ROOT="$(cd "$(dirname "$0")/../../.." && pwd -P)"
 GATE="$ROOT/skills/skill-extraction-workflow/scripts/impact-chain-gate.rb"
 LEDGER_REL="skills/skill-extraction-workflow/references/source-register.md"

package/dist/assets/marketplace/plugins/ccl-skills/skills/skill-extraction-workflow/scripts/test_impact_chain_source_refuted.sh

@@ -7,6 +7,8 @@
 #
 # 全部确定性，不调模型。每用例一条分支，互不影响本地未提交改动。
 set -u
+# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
+case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac
 ROOT="$(cd "$(dirname "$0")/../../.." && pwd -P)"
 GATE="$ROOT/skills/skill-extraction-workflow/scripts/impact-chain-gate.rb"
 TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT INT TERM