@windyroad/retrospective 0.27.1 → 0.27.2

package/skills/run-retro/test/run-retro-step-3-tier-3-branch-b-evidence-based.bats

@@ -1,189 +0,0 @@
-#!/usr/bin/env bats
-#
-# P247: run-retro SKILL.md Step 3 Tier 3 Branch B MUST encode the
-# evidence-based rotation contract — "leave-as-is" is eliminated; the
-# fall-through when none of the three concrete triggers (subtopic /
-# date / ≥3 noise entries) fire is **split-by-date as the safe default**,
-# mirroring Branch A's existing precedent.
-#
-# This file mirrors the architecture established for P148's Stage 1
-# fallback-gating clause: behavioural assertions exercise the
-# enforcement layer (check-briefing-budgets.sh) for the OVER /
-# MUST_SPLIT signal shape that drives Branch B input, plus narrow
-# structural backstops linking SKILL.md prose (canonical human source)
-# to the enforcement layer + driver-ticket evidence trail.
-#
-# Architect verdict (2026-05-18, P247): the rotation decision itself
-# is silent agent judgement per ADR-044 framework-mediated surface
-# "Briefing add / remove / rotate" — there is no script to behaviourally
-# exercise the rotation. The script-side behavioural coverage for the
-# Branch B INPUT signal (OVER without MUST_SPLIT) lives in
-# `packages/retrospective/scripts/test/check-briefing-budgets.bats`;
-# this file is the SKILL-prose backstop that confirms the prose names
-# the evidence-based contract terms and the driver ticket.
-#
-# # @adr ADR-037 permitted exception — narrowest justifiable scope.
-# # @adr ADR-044 framework-mediated surface boundary (silent agent rotation).
-# # @adr ADR-061 evidence-based-not-time-based principle (parent class).
-# # @adr ADR-013 Rule 5 (policy-authorised silent proceed).
-# # @adr ADR-052 behavioural-tests-default (structural backstops permitted
-# #              for SKILL-prose-to-enforcement-layer linkage per P081).
-# # @ticket P247 — Branch B fictional-defer (driver).
-# # @ticket P246 — sibling-class at cohort-graduation surface (mirror precedent).
-# # @ticket P145 — predecessor at this surface (MUST_SPLIT subset already
-# #                evidence-based; P247 generalises to OVER subset).
-# # @ticket P081 — behavioural-tests-preferred direction.
-
-setup() {
-  REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../../../../.." && pwd)"
-  SKILL_MD="$REPO_ROOT/packages/retrospective/skills/run-retro/SKILL.md"
-  SCRIPT="$REPO_ROOT/packages/retrospective/scripts/check-briefing-budgets.sh"
-  FIXTURE_DIR="$(mktemp -d)"
-}
-
-teardown() {
-  rm -rf "$FIXTURE_DIR"
-}
-
-# Helper: write a markdown file with N bytes of body content.
-write_briefing_entry() {
-  local path="$1"
-  local target_bytes="$2"
-  : > "$path"
-  printf '# Topic\n\n' >> "$path"
-  local header_size
-  header_size=$(wc -c < "$path" | tr -d ' ')
-  local body_target=$(( target_bytes - header_size ))
-  if [ "$body_target" -gt 0 ]; then
-    local line="- entry text padded out to a known length for byte-budget testing.   "
-    local line_size=${#line}
-    line+=$'\n'
-    local line_count=$(( (body_target + line_size) / (line_size + 1) ))
-    local i=0
-    while [ "$i" -lt "$line_count" ]; do
-      printf '%s' "$line" >> "$path"
-      i=$(( i + 1 ))
-    done
-  fi
-}
-
-# ── Behavioural: Branch B INPUT signal shape ────────────────────────────────
-#
-# Branch B is defined as "file has only OVER line (ratio between 1.0× and
-# 2.0× ceiling)". The check-briefing-budgets.sh script is the enforcement
-# layer that produces this signal. These assertions confirm the signal
-# shape the SKILL contract reads — they exercise the script (not the
-# agent's rotation choice), giving Branch B its input definition.
-
-@test "Branch B input: file at 1.5x ratio emits OVER without MUST_SPLIT (Branch B selector)" {
-  # 1.5x of default 5120 ceiling = 7680 bytes — the canonical Branch B input.
-  mkdir -p "$FIXTURE_DIR/briefing"
-  write_briefing_entry "$FIXTURE_DIR/briefing/branch-b-canonical.md" 7680
-  run "$SCRIPT" "$FIXTURE_DIR/briefing"
-  [ "$status" -eq 0 ]
-  echo "$output" | grep -E "^OVER branch-b-canonical.md bytes=[0-9]+ threshold=5120"
-  ! echo "$output" | grep -q "^MUST_SPLIT branch-b-canonical.md"
-}
-
-@test "Branch B input: file at 1.0x exactly emits OVER without MUST_SPLIT (Branch B lower edge)" {
-  mkdir -p "$FIXTURE_DIR/briefing"
-  printf '%.0s.' $(seq 1 5120) > "$FIXTURE_DIR/briefing/branch-b-lower-edge.md"
-  run "$SCRIPT" "$FIXTURE_DIR/briefing"
-  [ "$status" -eq 0 ]
-  echo "$output" | grep -E "^OVER branch-b-lower-edge.md bytes=5120 threshold=5120"
-  ! echo "$output" | grep -q "^MUST_SPLIT branch-b-lower-edge.md"
-}
-
-@test "Branch B input: file just under 2.0x (e.g. 1.96x) emits OVER without MUST_SPLIT (P247 evidence — hooks-and-gates-archive.md at 1.96x was deferred)" {
-  # 1.96x of 5120 = 10035 bytes — the upper edge of Branch B, exactly the
-  # case the 2026-05-17 session-4 wrap retro hit and deferred via the
-  # now-eliminated "leave-as-is" branch.
-  mkdir -p "$FIXTURE_DIR/briefing"
-  printf '%.0s.' $(seq 1 10035) > "$FIXTURE_DIR/briefing/upper-edge.md"
-  run "$SCRIPT" "$FIXTURE_DIR/briefing"
-  [ "$status" -eq 0 ]
-  echo "$output" | grep -E "^OVER upper-edge.md bytes=10035 threshold=5120"
-  ! echo "$output" | grep -q "^MUST_SPLIT upper-edge.md"
-}
-
-@test "Branch B input: file UNDER threshold emits NEITHER signal (no Branch B action)" {
-  # The pre-existing skip path: file below threshold = no rotation pass
-  # entry. The SKILL contract's "Empty stdout means no files are over
-  # budget — skip the rest of this pass" precedent is preserved.
-  mkdir -p "$FIXTURE_DIR/briefing"
-  write_briefing_entry "$FIXTURE_DIR/briefing/within-budget.md" 3000
-  run "$SCRIPT" "$FIXTURE_DIR/briefing"
-  [ "$status" -eq 0 ]
-  ! echo "$output" | grep -q "within-budget.md"
-}
-
-@test "Branch B / Branch A boundary: file at exactly 2.0x emits BOTH OVER and MUST_SPLIT (Branch A selector)" {
-  # The contract boundary: 2.0x and above is Branch A (rotation required,
-  # no defer options eligible). 1.0x-2.0x is Branch B. The script-side
-  # MUST_SPLIT signal is the discriminator the SKILL prose reads.
-  mkdir -p "$FIXTURE_DIR/briefing"
-  printf '%.0s.' $(seq 1 10240) > "$FIXTURE_DIR/briefing/exactly-2x.md"
-  run "$SCRIPT" "$FIXTURE_DIR/briefing"
-  [ "$status" -eq 0 ]
-  echo "$output" | grep -E "^OVER exactly-2x.md bytes=10240 threshold=5120"
-  echo "$output" | grep -E "^MUST_SPLIT exactly-2x.md reason=ratio-exceeds-2x"
-}
-
-# ── Structural backstops: SKILL.md prose contract terms (narrow per P081) ───
-#
-# These assertions link SKILL.md prose (canonical human-readable source)
-# to the evidence-based-rotation contract and the driver ticket. Without
-# these links, the prose contract could drift independently from the
-# enforcement layer + driver-ticket evidence trail. Per P081, the scope
-# is narrowed to the smallest set of tokens that prove the contract
-# terms exist in the prose; assertions intentionally avoid coupling to
-# line numbers or sentence-level structure.
-
-@test "Branch B prose: SKILL.md no longer permits the 'leave-as-is' fall-through (P247 fix verification)" {
-  # The contract negative-assertion: the eliminated branch's literal
-  # token "leave-as-is" must NOT appear as a permitted Branch B
-  # rotation option. The token may legitimately appear inside a
-  # historical-reference context (e.g. "the eliminated 'leave-as-is'
-  # branch") — that's why we don't grep for the bare token but for the
-  # specific surface that previously authorised the defer.
-  ! grep -F "Else: **leave-as-is**" "$SKILL_MD"
-}
-
-@test "Branch B prose: SKILL.md names 'split-by-date (safe default)' as the Branch B fall-through (P247 fix verification)" {
-  # The contract positive-assertion: the new fall-through must be named
-  # explicitly as "split-by-date (safe default)" — the same naming
-  # Branch A already uses, so a reader of the prose sees the alignment
-  # without having to cross-reference Branch A's bullet.
-  grep -F "split-by-date (safe default)" "$SKILL_MD"
-}
-
-@test "Branch B prose: SKILL.md cites P247 as the driver ticket (audit-trail link)" {
-  # Audit-trail link: the prose names P247 so future readers can locate
-  # the evidence trail (user correction quote, sibling-class relationship
-  # to P246, the 14-file evidence from 2026-05-17 session 4 wrap retro).
-  grep -F "P247" "$SKILL_MD"
-}
-
-@test "Branch B prose: SKILL.md cites P246 sibling fix as the evidence-based principle precedent (cross-class linkage)" {
-  # Cross-class linkage: P246 (cohort-graduation surface) is the immediate
-  # sibling fix. The Branch B prose must cite it so the evidence-based-
-  # not-time-based principle is discoverable as a class, not a one-off
-  # SKILL fix.
-  grep -F "P246" "$SKILL_MD"
-}
-
-@test "Branch B prose: SKILL.md cites ADR-044 framework-mediated surface for silent rotation (governance link)" {
-  # Governance link: per architect verdict, Branch B's silent-rotation
-  # discipline is authorised by ADR-044's framework-resolution boundary
-  # ("Briefing add / remove / rotate" line 77). The prose must cite the
-  # ADR so a reader sees the authority for not firing AskUserQuestion
-  # per file in Branch B's fall-through.
-  grep -F "ADR-044" "$SKILL_MD"
-}
-
-@test "Branch B prose: SKILL.md cites ADR-013 Rule 5 for policy-authorised silent proceed (governance link)" {
-  # Companion governance link: ADR-013 Rule 5 is the originating rule
-  # for silent-proceed under policy. Branch B inherits this discipline;
-  # the citation makes the rule chain explicit.
-  grep -F "ADR-013 Rule 5" "$SKILL_MD"
-}

package/skills/run-retro/test/run-retro-step-4a-cross-plugin-dispatch.bats

@@ -1,114 +0,0 @@
-#!/usr/bin/env bats
-#
-# packages/retrospective/skills/run-retro/test/run-retro-step-4a-cross-plugin-dispatch.bats
-#
-# Behavioural tests for run-retro Step 4a's cross-plugin dispatch contract
-# to /wr-itil:transition-problem (P135 Phase 2 / R3 / ADR-044).
-#
-# Step 4a now closes verifying tickets on evidence by delegating to
-# /wr-itil:transition-problem <NNN> close (per ADR-014 commit grain)
-# WITHOUT firing AskUserQuestion. These tests assert the dispatch
-# contract: dispatch occurs on success; failure surfaces in summary;
-# unavailability is gracefully handled (not silently swallowed).
-#
-# Tests are behavioural per ADR-005 / ADR-037 / ADR-044 — they assert
-# what the SKILL contract DOES (mechanism + observable outcome) by
-# inspecting the SKILL.md text + the precedents it cites. No structural
-# greps of the SKILL.md content per ADR-044's deviation-default to
-# behavioural-by-default for skill testing.
-#
-# These contract-assertion tests are documented as the bridge until the
-# behavioural-test harness for LLM-interpreted skills exists (P081 Phase
-# 2/3 deferred; P012 harness work). Per ADR-044 Confirmation Criteria
-# (a), the test FILE exists and is named — the per-assertion shape
-# matures as the harness lands.
-#
-# tdd-review: structural-permitted (justification: skill behavioural
-# harness pending P012 + P081 Phase 2; SKILL.md contract assertions are
-# the bridge until then; expected to migrate to behavioural form once
-# the harness exists)
-#
-# @problem P135 Phase 2 R3
-# @adr ADR-044 (Decision-Delegation Contract — verification close on evidence)
-# @adr ADR-014 (commit grain)
-# @adr ADR-022 (verification-pending lifecycle)
-# @adr ADR-005 / ADR-037 (testing strategy — bridge during harness build)
-# @jtbd JTBD-001 / JTBD-006 / JTBD-201
-
-SKILL_FILE="${BATS_TEST_DIRNAME}/../SKILL.md"
-
-setup() {
-  [ -f "$SKILL_FILE" ]
-}
-
-# ── Dispatch contract present in SKILL.md ──────────────────────────────────
-
-@test "Step 4a SKILL.md cites /wr-itil:transition-problem as the close-on-evidence dispatch target" {
-  run grep -F "/wr-itil:transition-problem" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"close"* ]]
-}
-
-@test "Step 4a SKILL.md names ADR-044 framework-resolution boundary as the rationale for no-AskUserQuestion close" {
-  run grep -F "ADR-044" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4a SKILL.md cites ADR-026 grounding for in-session evidence requirement" {
-  run grep -F "ADR-026" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4a SKILL.md cites ADR-014 for commit grain on the close action" {
-  run grep -F "ADR-014" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Failure-mode contracts ──────────────────────────────────────────────────
-
-@test "Step 4a SKILL.md documents dispatch-failure handling (non-zero return surfaced, NOT marked closed)" {
-  run grep -F "dispatch-failed" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4a SKILL.md documents dispatch-unavailable handling (graceful fallback, not silent swallow)" {
-  run grep -F "dispatch-unavailable" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4a SKILL.md surfaces the close-action result in Step 5 retro summary" {
-  run grep -F "Decision column" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Recovery-path documentation ─────────────────────────────────────────────
-
-@test "Step 4a SKILL.md cites P135 Phase 2 R5 recovery-path documentation" {
-  # Matches the cross-reference to the recovery-path bats fixture
-  run grep -F "run-retro-step-4a-recovery-path.bats" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Same-session exclusion preserved (P068 design unchanged) ────────────────
-
-@test "Step 4a SKILL.md preserves same-session-verifyings exclusion from close-on-evidence" {
-  run grep -F "Same-session verifyings excluded" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4a SKILL.md cites the 2026-04-27 P124 verifying-flip-back as the regression-recovery precedent" {
-  run grep -F "P124" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Anti-pattern preserved: NEVER per-candidate AskUserQuestion ─────────────
-
-@test "Step 4a SKILL.md text no longer contains the legacy 'Close P<NNN>' / 'Leave as Verification Pending' / 'Flag for manual review' AskUserQuestion option list" {
-  # Specific prior options were the per-candidate ask (P135 R3 corrective)
-  # Assert the legacy 3-option block is GONE from Step 4a's section.
-  # We bound by line number to scope to Step 4a (lines 317-360 approx) — file-wide grep
-  # would also match the docs preserving history; this is a localised assertion.
-  run awk '/^### 4a\./,/^### 4b\./ {print}' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" != *"Close P<NNN>\` — description: \"Delegate to /wr-itil:manage-problem"* ]]
-}

package/skills/run-retro/test/run-retro-step-4a-prior-session-evidence-drain.bats

@@ -1,168 +0,0 @@
-#!/usr/bin/env bats
-#
-# packages/retrospective/skills/run-retro/test/run-retro-step-4a-prior-session-evidence-drain.bats
-#
-# Contract assertions for run-retro Step 4a's prior-session evidence drain
-# stage (P282). Step 4a's current sub-steps 1-8 scan the CURRENT session's
-# tool-call activity for evidence. This stage consumes durable on-disk
-# evidence — README Verification Queue rows whose `Likely verified?` cell
-# already records `yes — observed: <citations>` from a prior session — that
-# is structurally invisible to current-session scans.
-#
-# Background: 2026-05-26 evidence in this repo (P282 Related section) —
-# 8/91 `verifying/` rows had `yes — observed: …` from prior sessions; none
-# auto-closed; the Verification Queue grew to 134 KB exceeding the Read-tool
-# 25K-token whole-file cap. Closure required user prompting. The drain
-# closes that gap.
-#
-# Tests are behavioural per ADR-005 / ADR-037 / ADR-044 — they assert what
-# the SKILL contract DOES (mechanism + observable outcome) by inspecting
-# the SKILL.md text + the precedents it cites. Per ADR-044 Confirmation
-# Criteria (a), the test FILE exists and is named; the per-assertion shape
-# matures as the behavioural-test harness for LLM-interpreted skills lands
-# (P081 Phase 2/3 deferred; P012 harness work).
-#
-# tdd-review: structural-permitted (justification: skill behavioural
-# harness pending P012 + P081 Phase 2; SKILL.md contract assertions are
-# the bridge until then; behavioural fixture at the foot of this file
-# exercises a sample README VQ table to confirm the drain's row-detection
-# heuristic against a real evidence-bearing cell)
-#
-# @problem P282
-# @adr ADR-022 (verification-pending lifecycle)
-# @adr ADR-014 (commit grain)
-# @adr ADR-044 (decision-delegation — close-on-evidence)
-# @adr ADR-074 (substance-confirm-before-build — this fix passed the gate)
-# @jtbd JTBD-001 / JTBD-006 / JTBD-201
-
-SKILL_FILE="${BATS_TEST_DIRNAME}/../SKILL.md"
-
-setup() {
-  [ -f "$SKILL_FILE" ] || skip "SKILL.md not found"
-}
-
-@test "run-retro: Step 4a documents a prior-session evidence drain stage (P282)" {
-  # The drain stage is the headline behaviour; SKILL.md must name it.
-  run grep -F 'Prior-session evidence drain (P282)' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "run-retro: prior-session drain reads docs/problems/README.md Verification Queue" {
-  # The cell to consume is in the README's Verification Queue table, not
-  # in any current-session activity stream. SKILL.md must name the source.
-  run awk '/Prior-session evidence drain/,/^   \*\*Composition/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"docs/problems/README.md"* ]]
-  [[ "$output" == *"Verification Queue"* ]]
-}
-
-@test "run-retro: prior-session drain filters on P186 evidence-first cell shape" {
-  # The canonical signal is `yes — observed: <citations>` per P186.
-  # SKILL.md must cite the exact cell shape as the filter predicate so
-  # adopters and future agents can grep for the right value.
-  run awk '/Prior-session evidence drain/,/^   \*\*Composition/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"yes — observed:"* ]]
-  [[ "$output" == *"P186"* ]]
-}
-
-@test "run-retro: prior-session drain preserves same-session exclusion (sub-step 8)" {
-  # The drain MUST inherit Step 4a's same-session exclusion (sub-step 8)
-  # so a session cannot verify its own fix via the README cell either.
-  # The exclusion is the load-bearing constraint distinguishing "prior
-  # session wrote the cell" from "current session wrote the cell".
-  run awk '/Prior-session evidence drain/,/^   \*\*Composition/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"same-session"* ]] || [[ "$output" == *"current session"* ]]
-}
-
-@test "run-retro: prior-session drain delegates close via /wr-itil:transition-problem" {
-  # Per Step 4a's existing dispatch contract (sub-steps 5-7), the close
-  # MUST route through /wr-itil:transition-problem <NNN> close. run-retro
-  # never renames, edits Status, or commits — the ownership boundary holds.
-  run awk '/Prior-session evidence drain/,/^   \*\*Composition/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"/wr-itil:transition-problem"* ]]
-}
-
-@test "run-retro: prior-session drain inherits dispatch outcome contract (P135 R3)" {
-  # The dispatch success / failure / unavailable outcomes are recorded
-  # in the Step 5 Verification Candidates table per sub-step 7. The
-  # drain stage MUST cite the inheritance so behaviour is uniform.
-  run awk '/Prior-session evidence drain/,/^   \*\*Composition/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"sub-step 7"* ]] || [[ "$output" == *"Verification Candidates"* ]]
-}
-
-@test "run-retro: prior-session drain records source distinction in Decision column" {
-  # The Decision column must distinguish drained-from-README from
-  # current-session-dispatched closes so the user can scan the source
-  # of each close at retro-summary review time.
-  run awk '/Prior-session evidence drain/,/^   \*\*Composition/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"prior-session README cell"* ]]
-}
-
-@test "run-retro: prior-session drain documents the recovery path inline (P135 R5)" {
-  # Closes are reversible via /wr-itil:transition-problem <NNN> known-error
-  # (the verifying-flip-back path); the drain stage inherits this contract.
-  run awk '/Prior-session evidence drain/,/\*\*Closes P282\*\*/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"Recovery"* ]] || [[ "$output" == *"recoverable"* ]] || [[ "$output" == *"reversible"* ]]
-}
-
-@test "run-retro: prior-session drain composes with current-session dispatch ordering" {
-  # The drain fires AFTER sub-steps 5-7 dispatched current-session
-  # evidence. The Composition note must name the ordering so future
-  # readers don't accidentally re-order the stages.
-  run grep -F '**Composition**' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run awk '/Prior-session evidence drain/,/\*\*Closes P282\*\*/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"AFTER"* ]] || [[ "$output" == *"after"* ]]
-}
-
-@test "run-retro: prior-session drain cites the 2026-05-26 evidence motivating the fix" {
-  # The drain's rationale is grounded in observable repo evidence: 8 rows
-  # carried `yes — observed:` across prior sessions and none auto-closed
-  # until user-prompted. SKILL.md cites the evidence so future maintainers
-  # can audit the design driver.
-  run awk '/Prior-session evidence drain/,/\*\*Closes P282\*\*/' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"2026-05-26"* ]] || [[ "$output" == *"134 KB"* ]] || [[ "$output" == *"8/91"* ]]
-}
-
-@test "run-retro: prior-session drain explicitly closes P282" {
-  # The drain stage names P282 as the ticket it closes so the
-  # ticket-to-behavior link is greppable. (Same convention used by
-  # the existing Step 4a header which names P068.)
-  run grep -F '**Closes P282**' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# Behavioural fixture — exercises the row-detection heuristic against a
-# sample README VQ table. Asserts the drain's filter predicate matches
-# `yes — observed:` rows and skips `no — not observed` / `no — observed
-# regression` rows.
-@test "behavioural: drain filter matches yes — observed rows and skips no rows" {
-  # Build a minimal README VQ-shaped fixture in a temp dir.
-  TMP="$(mktemp -d)"
-  cat > "$TMP/README.md" <<'EOF'
-## Verification Queue
-
-| ID | Title | Released | Likely verified? |
-| --- | --- | --- | --- |
-| P100 | sample one | 2026-04-01 | yes — observed: cited evidence |
-| P101 | sample two | 2026-04-02 | no — not observed |
-| P102 | sample three | 2026-04-03 | yes — observed: more evidence |
-| P103 | sample four | 2026-04-04 | no — observed regression |
-EOF
-  # The drain's row-detection predicate: the cell starts with `yes — observed:`.
-  # Assert the fixture matches the expected row count.
-  matched=$(grep -cE '\| yes — observed:' "$TMP/README.md")
-  [ "$matched" -eq 2 ]
-  # And the skip predicates match the other two.
-  skipped=$(grep -cE '\| no — not observed|\| no — observed regression' "$TMP/README.md")
-  [ "$skipped" -eq 2 ]
-  rm -rf "$TMP"
-}

package/skills/run-retro/test/run-retro-step-4a-recovery-path.bats

@@ -1,84 +0,0 @@
-#!/usr/bin/env bats
-#
-# packages/retrospective/skills/run-retro/test/run-retro-step-4a-recovery-path.bats
-#
-# Behavioural tests for run-retro Step 4a's recovery-path documentation
-# (P135 Phase 2 / R5 / ADR-044).
-#
-# Step 4a closes verifying tickets on evidence WITHOUT firing
-# AskUserQuestion (per ADR-044 framework-resolution boundary). The
-# recovery contract is critical: closes are reversible, the recovery
-# path is documented inline in the Step 5 retro summary, and the user
-# can correct via authentic-correction (ADR-044 category 6) if a close
-# was wrong.
-#
-# These tests assert the SKILL.md documents the recovery path
-# alongside each close action, names the specific recovery invocation,
-# and cites the 2026-04-27 P124 verifying-flip-back precedent as the
-# real-world demonstration of the recovery path working end-to-end.
-#
-# Tests are contract-assertion bridge per ADR-044 Confirmation Criteria
-# (a) — same justification as the cross-plugin-dispatch fixture above.
-#
-# tdd-review: structural-permitted (justification: skill behavioural
-# harness pending P012 + P081 Phase 2; SKILL.md contract assertions
-# bridge until then; expected to migrate to behavioural form once the
-# harness exists)
-#
-# @problem P135 Phase 2 R5
-# @adr ADR-044 (Decision-Delegation Contract — closes are reversible)
-# @adr ADR-022 (verification-pending lifecycle)
-# @adr ADR-014 (commit grain on the recovery commit)
-# @adr ADR-005 / ADR-037 (testing strategy — bridge during harness build)
-# @jtbd JTBD-001 / JTBD-006 / JTBD-201
-
-SKILL_FILE="${BATS_TEST_DIRNAME}/../SKILL.md"
-
-setup() {
-  [ -f "$SKILL_FILE" ]
-}
-
-# ── Recovery-path documented in Step 4a ─────────────────────────────────────
-
-@test "Step 4a SKILL.md documents the recovery path inline alongside close-on-evidence" {
-  run awk '/^### 4a\./,/^### 4b\./ {print}' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"Recovery"* ]]
-}
-
-@test "Step 4a SKILL.md names the recovery skill invocation (transition-problem known-error)" {
-  run awk '/^### 4a\./,/^### 4b\./ {print}' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"transition-problem"* ]]
-  [[ "$output" == *"known-error"* ]]
-}
-
-@test "Step 4a SKILL.md cites 2026-04-27 P124 verifying-flip-back as recovery precedent" {
-  run awk '/^### 4a\./,/^### 4b\./ {print}' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"P124"* ]]
-  [[ "$output" == *"flip-back"* ]]
-}
-
-@test "Step 4a SKILL.md affirms closes are reversible" {
-  run awk '/^### 4a\./,/^### 4b\./ {print}' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"reversible"* ]]
-}
-
-# ── Recovery surfaces in Step 5 summary ─────────────────────────────────────
-
-@test "Step 4a SKILL.md says the close action + recovery path lands in Step 5 retro summary" {
-  run awk '/^### 4a\./,/^### 4b\./ {print}' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [[ "$output" == *"Step 5"* ]] || [[ "$output" == *"summary"* ]]
-}
-
-# ── Authentic-correction surface preserved ──────────────────────────────────
-
-@test "Step 4a SKILL.md routes user disagreement through authentic-correction (ADR-044 category 6)" {
-  run awk '/^### 4a\./,/^### 4b\./ {print}' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  # Either explicit "authentic-correction" or P078 (the canonical correction surface)
-  [[ "$output" == *"authentic-correction"* ]] || [[ "$output" == *"P078"* ]]
-}

package/skills/run-retro/test/run-retro-step-4b-retro-auto-ticket-carveout.bats

@@ -1,115 +0,0 @@
-#!/usr/bin/env bats
-#
-# packages/retrospective/skills/run-retro/test/run-retro-step-4b-retro-auto-ticket-carveout.bats
-#
-# P342: run-retro Step 4b stage classification must mirror the trust-
-# boundary established at Step 4a (verification close-on-evidence) — so
-# the same mechanical-stage carve-out applies whether retro fires in iter
-# context (work-problems Step 5 iter-prompt) OR standalone in main turn.
-#
-# The fix shape amends Step 4b stage classification:
-#   - Mechanical-auto-ticket path: recurring class-of-behaviour /
-#     SKILL-contract drift / hook misbehaviour / framework-gap → Stage 1
-#     auto-creates a ticket via /wr-itil:capture-problem (or
-#     manage-problem if capture sibling not yet available).
-#   - Direction-setting-queue path: genuine user-judgment-bound questions
-#     (design choice, deviation-approval, framework boundary) → queued
-#     as outstanding_questions for orchestrator-level Step 2.5 surface
-#     when retro runs inside an AFK iter; surfaced at retro end when
-#     standalone.
-#   - Ambiguous → default to mechanical-auto-ticket (per P342 trust-
-#     boundary asymmetry preventing silent queue accumulation).
-#
-# Contract-assertion tests per ADR-037 Permitted Exception (structural
-# checks on prose contract; behavioural harness for SKILL.md pending
-# P081 Phase 2 / P012).
-#
-# @problem P342
-# @adr ADR-044 (Decision-Delegation Contract — mechanical-stage carve-out per Step 4a precedent)
-# @adr ADR-013 Rule 5 (policy-authorised silent proceed for capture-* on retro path)
-# @adr ADR-014 (governance skills commit own work — capture-problem commits per ticket)
-# @adr ADR-032 (foreground-spawns-N-background fanout pattern already documented for Stage 1)
-# @jtbd JTBD-006 (durable WSJF-ranked backlog accumulation)
-# @jtbd JTBD-201 (audit-trail integrity)
-
-SKILL_FILE="${BATS_TEST_DIRNAME}/../SKILL.md"
-
-setup() {
-  [ -f "$SKILL_FILE" ]
-}
-
-# ── Step 4b carve-out subsection presence ───────────────────────────────────
-
-@test "Step 4b P342: SKILL.md names the mechanical-auto-ticket vs direction-setting-queue split" {
-  # The fix establishes a classification split at Stage 1 routing.
-  # Mechanical-class observations route to auto-ticket; direction-class
-  # to outstanding_questions queue.
-  run grep -F "mechanical-auto-ticket" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4b P342: SKILL.md cites Step 4a precedent for the mechanical-stage carve-out" {
-  # The carve-out's authority is the Step 4a verification close-on-
-  # evidence precedent. Cite explicitly so the trust-boundary symmetry
-  # is discoverable.
-  run grep -nE 'Step 4a precedent|same trust[- ]boundary.*Step 4a|Step 4a.*precedent' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4b P342: SKILL.md names recurring class-of-behaviour as auto-ticket route" {
-  # Recurring class-of-behaviour / SKILL-contract drift / hook
-  # misbehaviour / framework-gap → auto-ticket. The taxonomy must be
-  # documented at Step 4b so the same classification fires whether retro
-  # runs in iter context OR standalone.
-  run grep -nE 'recurring class-of-behaviour|class-of-behaviour observation' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4b P342: SKILL.md names direction-setting as outstanding_questions route" {
-  # Direction-setting (design choice, deviation-approval, framework
-  # boundary) → outstanding_questions when retro runs inside an AFK
-  # iter; surfaced at retro end when standalone.
-  run grep -nE 'direction-setting.*outstanding_questions|Direction-setting observation' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 4b P342: SKILL.md names ambiguous default-to-auto-ticket asymmetry" {
-  # Per P342 trust-boundary asymmetry: ambiguous → default to auto-
-  # ticket. This prevents the silent-queue accumulation P342 was filed
-  # to close.
-  run grep -nE 'Ambiguous.*auto-ticket|default to auto-ticket|ambiguous.*default.*ticket' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Cross-reference to work-problems Step 5 iter-prompt carve-out ──────────
-
-@test "Step 4b P342: SKILL.md cross-references work-problems Step 5 iter-prompt symmetry" {
-  # The work-problems iter-prompt amendment is the sibling locus — the
-  # same trust-boundary fires in both surfaces. Cross-reference so the
-  # symmetry is discoverable from either side.
-  run grep -nE 'work-problems Step 5|work-problems.*iter-prompt|Step 5 iter-prompt' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── ADR-044 framework-resolution boundary citation ─────────────────────────
-
-@test "Step 4b P342: SKILL.md cites ADR-044 as the framework-resolution authority for the carve-out" {
-  run grep -F "ADR-044" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── ADR-014 commit ownership preserved ─────────────────────────────────────
-
-@test "Step 4b P342: SKILL.md preserves ADR-014 capture-* commit ownership for auto-ticket path" {
-  # capture-problem (or manage-problem fallback) commits per ADR-014;
-  # run-retro does not commit auto-ticket creates.
-  run grep -F "ADR-014" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── P342 ticket cross-reference ─────────────────────────────────────────────
-
-@test "Step 4b P342: SKILL.md cites P342 as the trust-boundary mirror ticket" {
-  run grep -nE 'P342\b' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}