@ccoalm/ccl-skills 0.16.0 → 0.18.0

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

@@ -736,7 +736,8 @@ DUAL_TRACK_REF="$REPO_ROOT/skills/skill-extraction-workflow/references/dual-trac
 LEDGER_REF="$REPO_ROOT/skills/skill-extraction-workflow/references/source-register.md"
 WALK_REF="$REPO_ROOT/skills/testing-strategy/references/run-killing-mutation-walk.md"
 DT_SELF_AUDIT_SECTION='### The self-adversary enumeration — method detail (relocated from `SKILL.md`)'
-DT_AUTHORITY_SECTION='### Findings, autonomous budget, and human authority'
+DT_AUTHORITY_SECTION='### Findings and dispositions'
+DT_LANE_SECTION='### The extraction review lane: one review, one challenge'
 TS_CORE_RULES_SECTION='## Core Rules'
 WALK_PROBE_SECTION='## Encoded Probe For Destructive Artifacts'
 LEDGER_RULE_PARAGRAPH='Round-consolidation rule (append-once)'
@@ -749,8 +750,8 @@ assert_in_section "$DUAL_TRACK_REF" "$DT_SELF_AUDIT_SECTION" '**Re-owe after fix
   "process controls (re-owe rule anchored in the self-audit section)"
 assert_in_section "$DUAL_TRACK_REF" "$DT_AUTHORITY_SECTION" 'A convergence or closure declaration must be written falsifiably.' \
   "process controls (falsifiable closure declaration anchored in the authority section)"
-assert_in_section "$DUAL_TRACK_REF" "$DT_AUTHORITY_SECTION" '`continuation_authorization`' \
-  "process controls (continuation authorization anchored in the authority section)"
+assert_in_section "$DUAL_TRACK_REF" "$DT_LANE_SECTION" '**Task authority.**' \
+  "process controls (task authority anchored in the extraction review lane)"
 # Remediation re-owes the pre-cover axes; third same-class round escalates to one full-matrix self-enumeration.
 assert_same_line "$DUAL_TRACK_REF" 'remediation text written mid-round re-owes the draft-time axes BEFORE the candidate goes back to the reviewer' \
   '**Re-owe after fixes.**' \
@@ -768,7 +769,7 @@ assert_same_line "$DUAL_TRACK_REF" 'states × failure points × orderings × res
   '**Re-owe after fixes.**' \
   "process controls (full-matrix axes named)"
 # Convergence/closure declarations are falsifiable: named candidate/evidence/axes/open items, scoped adjectives.
-assert_same_line "$DUAL_TRACK_REF" 'Name the exact candidate identity it covers' \
+assert_same_line "$DUAL_TRACK_REF" 'Name the commit it covers' \
   'must be written falsifiably' \
   "process controls (declaration names the candidate identity)"
 assert_same_line "$DUAL_TRACK_REF" "each lane's terminal evidence, the axes/dimensions the closing self-audit actually crossed, and every standing open item by name" \
@@ -780,29 +781,17 @@ assert_same_line "$DUAL_TRACK_REF" 'cannot be checked false and is inconclusive'
 assert_same_line "$DUAL_TRACK_REF" 'any "full X" adjective is scoped to the named axes, never wider' \
   'must be written falsifiably' \
   "process controls (full-adjective scoped to named axes)"
-# Default continuation retains original authority and accumulated evidence.
-assert_same_line "$DUAL_TRACK_REF" 'necessary in-scope fixes, tests and review are already authorized by default' \
-  '`continuation_authorization`' "process controls (necessary review inherits task authority)"
-assert_same_line "$DUAL_TRACK_REF" 'continuation_basis=existing-task-scope' \
-  '`continuation_authorization`' "process controls (inherited continuation has an explicit basis)"
-assert_same_line "$DUAL_TRACK_REF" 'the original authorization reference and scope' \
-  '`continuation_authorization`' "process controls (original authority remains traceable)"
-assert_same_line "$DUAL_TRACK_REF" 'changed method or added evidence, cumulative rounds' \
-  '`continuation_authorization`' "process controls (checkpoint requires method and spending evidence)"
-assert_same_line "$DUAL_TRACK_REF" "links between the old sequence's terminal evidence and the new sequence" \
-  '`continuation_authorization`' "process controls (successive sequences retain their links)"
-assert_same_line "$DUAL_TRACK_REF" 'fresh current-candidate bindings and preserves every prior receipt, focus, finding and disposition' \
-  '`continuation_authorization`' "process controls (fresh binding does not discard history)"
-assert_same_line "$DUAL_TRACK_REF" 'The existing per-sequence format, timeout and validation bounds remain unchanged' \
-  '`continuation_authorization`' "process controls (bounded invocation format remains enforced)"
-assert_same_line "$DUAL_TRACK_REF" 'never relabel these calls as newly human-requested or erase earlier spending' \
-  '`continuation_authorization`' "process controls (no fabricated human request or count reset)"
-assert_same_line "$DUAL_TRACK_REF" 'Ask only for scope or authority the original task lacks, an explicit user limit' \
-  '`continuation_authorization`' "process controls (real missing authority and user limits remain blocking)"
-assert_same_line "$DUAL_TRACK_REF" 'Continuation waives no review, test or evidence obligation and grants no merge, publication or risk-acceptance authority' \
-  '`continuation_authorization`' "process controls (continuation is not a waiver or landing authority)"
-assert_same_line "$DUAL_TRACK_REF" 'Never infer a lane waiver from silence or from authorization to continue' \
-  '`continuation_authorization`' "process controls (no inferred lane waiver)"
+# Task authority: necessary passes are inherited, never relabelled, never a waiver or merge grant.
+assert_same_line "$DUAL_TRACK_REF" 'necessary in-scope fixes, tests and review passes by default' \
+  '**Task authority.**' "process controls (necessary review inherits task authority)"
+assert_same_line "$DUAL_TRACK_REF" 'never relabels an Agent-run pass as newly human-requested' \
+  '**Task authority.**' "process controls (no fabricated human request)"
+assert_same_line "$DUAL_TRACK_REF" 'never infers a lane waiver from silence or from authorization to continue' \
+  '**Task authority.**' "process controls (no inferred lane waiver)"
+assert_same_line "$DUAL_TRACK_REF" 'Ask only for scope or authority the original task lacks, or when an explicit user limit' \
+  '**Task authority.**' "process controls (real missing authority and user limits remain blocking)"
+assert_same_line "$DUAL_TRACK_REF" 'waives no review, test or evidence obligation and grants no merge, publication or risk-acceptance authority' \
+  '**Task authority.**' "process controls (passes are not a waiver or landing authority)"
 assert_contains "$PRODUCT_SKILL" 'Necessary fixes, tests and review inherit task authorization' \
   "process controls (implementation entry reaches inherited authority)"
 assert_contains "$PRE_FINAL_REF" 'continuation_basis=existing-task-scope' \

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

@@ -18,7 +18,7 @@
 #   - test_generic_r0_leak_scan.sh
 #   - test_shared_git_surface_gate.sh
 #   - test_extraction_review_gate.sh
-#   - test_validate_extraction_review_state.sh
+#   - test_check_review_evidence_present.sh
 #   - test_check_ccl_route_drift.sh
 #   - test_check_sync_pointers.sh
 #   - test_check_ccl_register_pending_exclusion.sh
@@ -122,10 +122,8 @@ fast_tests=(
   test_generic_r0_leak_scan.sh
   test_shared_git_surface_gate.sh
   test_extraction_review_gate.sh
-  test_validate_extraction_review_state.sh
-  # Merge-side binding between the landing candidate and the review evidence that
-  # inspected it: own throwaway git repo, no clone, seconds.
-  test_review_ledger_binding.sh
+  # Review-evidence presence gate: own throwaway git repo, seconds.
+  test_check_review_evidence_present.sh
   # Candidate-SHA-bound gate receipts (mint/verify): own throwaway git repo,
   # no clone, seconds — belongs in the lane every run exercises.
   test_gate_receipt.sh

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

@@ -0,0 +1,81 @@
+#!/usr/bin/env bash
+# Regression for check_review_evidence_present.py: a pull request that changes
+# skills/ or hooks/ must carry at least one conclusive review result; everything
+# else passes untouched. Own throwaway git repo.
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
+GATE="$SCRIPT_DIR/check_review_evidence_present.py"
+TMP="$(mktemp -d "${TMPDIR:-/tmp}/review-evidence.XXXXXX")"
+trap 'rm -rf "$TMP"' EXIT
+
+pass=0
+fail() { echo "FAIL: $*" >&2; exit 1; }
+ok() { pass=$((pass + 1)); echo "ok   - $1"; }
+
+REPO="$TMP/repo"
+git init -q "$REPO"
+git -C "$REPO" config user.email test@example.invalid
+git -C "$REPO" config user.name "Test User"
+mkdir -p "$REPO/skills/demo" "$REPO/docs"
+printf -- '---\nname: demo\ndescription: demo skill\n---\n\n# demo\n\nKeep the rule, always.\n' > "$REPO/skills/demo/SKILL.md"
+echo "# doc" > "$REPO/docs/a.md"
+git -C "$REPO" add -A && git -C "$REPO" commit -qm base
+BASE="$(git -C "$REPO" rev-parse HEAD)"
+
+result() { # result <path> <mode> <status>
+  mkdir -p "$(dirname "$REPO/$1")"
+  printf '{"schema_version":3,"mode":"%s","status":"%s","selected_client":"codex"}\n' \
+    "$2" "$3" > "$REPO/$1"
+}
+
+# case <label> <expected rc> <expected token> <setup...>: reset to base, apply setup, commit, run.
+run_case() {
+  local label="$1" want_rc="$2" want="$3"; shift 3
+  git -C "$REPO" checkout -q --detach "$BASE"
+  git -C "$REPO" clean -qfdx
+  "$@"
+  git -C "$REPO" add -A
+  git -C "$REPO" commit -qm case --allow-empty
+  set +e
+  out="$(python3 "$GATE" --repo-root "$REPO" --base "$BASE" 2>&1)"
+  rc=$?
+  set -e
+  [ "$rc" = "$want_rc" ] || fail "$label: expected rc=$want_rc got rc=$rc: $out"
+  case "$out" in *"$want"*) : ;; *) fail "$label: expected '$want': $out" ;; esac
+  ok "$label"
+}
+
+docs_only() { echo "more" >> "$REPO/docs/a.md"; }
+skill_change() { echo "rule" >> "$REPO/skills/demo/SKILL.md"; }
+hook_change() { mkdir -p "$REPO/hooks"; echo "#!/bin/sh" > "$REPO/hooks/h.sh"; }
+both_passes() { result specs/r1/evidence/round1-review.json review findings; result specs/r1/evidence/round2-challenge.json challenge passed; }
+
+run_case "no skills or hooks change needs nothing" 0 review_evidence_not_required docs_only
+run_case "skill change with no evidence is refused" 1 "no conclusive review result" skill_change
+run_case "hook change with no evidence is refused" 1 review_evidence_missing hook_change
+run_case "review plus challenge passes" 0 "review_evidence_present_ok: 1 review, 1 challenge" \
+  bash -c "$(declare -f result skill_change both_passes); REPO='$REPO'; skill_change; both_passes"
+run_case "a file replaced by a symlink still needs evidence" 1 review_evidence_missing \
+  bash -c "rm '$REPO/skills/demo/SKILL.md'; ln -s ../../docs/a.md '$REPO/skills/demo/SKILL.md'"
+run_case "a review alone is enough for the gate" 0 "review_evidence_present_ok: 1 review, 0 challenge" \
+  bash -c "$(declare -f result skill_change); REPO='$REPO'; skill_change; result specs/r1/evidence/round1-review.json review passed"
+run_case "a challenge alone does not satisfy the gate" 1 review_evidence_missing \
+  bash -c "$(declare -f result skill_change); REPO='$REPO'; skill_change; result specs/r1/evidence/round2-challenge.json challenge passed"
+run_case "an inconclusive result does not count" 1 review_evidence_missing \
+  bash -c "$(declare -f result skill_change); REPO='$REPO'; skill_change; result specs/r1/evidence/round1-review.json review inconclusive"
+run_case "a result outside an evidence directory does not count" 1 review_evidence_missing \
+  bash -c "$(declare -f result skill_change); REPO='$REPO'; skill_change; result specs/r1/round1-review.json review passed; result specs/r1/round2-challenge.json challenge passed"
+run_case "malformed JSON does not count" 1 review_evidence_missing \
+  bash -c "mkdir -p '$REPO/specs/r1/evidence'; echo 'not json' > '$REPO/specs/r1/evidence/round1-review.json'; echo rule >> '$REPO/skills/demo/SKILL.md'"
+
+set +e
+out="$(python3 "$GATE" --repo-root "$REPO" --base does-not-exist 2>&1)"
+rc=$?
+set -e
+[ "$rc" = 2 ] || fail "an unresolvable base must be unevaluated (rc=2), got rc=$rc"
+case "$out" in *review_evidence_unevaluated*) : ;; *) fail "unresolvable base reason: $out" ;; esac
+ok "an unresolvable base is unevaluated, never a pass"
+
+[ "$pass" = 11 ] || fail "expected 11 assertions, saw $pass"
+echo "test_check_review_evidence_present_ok ($pass assertions)"