fix(tests): repair stale test expectations + emit _EXPLAIN_LEVEL / _QUESTION_TUNING from preamble

Three pre-existing test failures on main were blocking /ship:

- test/skill-validation.test.ts "Step 3.4 test coverage audit" expected the
  literal strings "CODE PATH COVERAGE" and "USER FLOW COVERAGE" which were
  removed when the Step 7 coverage diagram was compressed. Updated assertions
  to check the stable `Code paths:` / `User flows:` labels that still ship.

- test/skill-validation.test.ts "ship step numbering" allowed-substeps list
  didn't include 15.0 (WIP squash) and 15.1 (bisectable commits) which were
  added for continuous checkpoint mode. Extended the allowlist.

- test/writing-style-resolver.test.ts and test/plan-tune.test.ts expected
  `_EXPLAIN_LEVEL` and `_QUESTION_TUNING` bash variables in the preamble but
  generate-preamble-bash.ts had been refactored and those lines were dropped.
  Without them, downstream skills can't read `explain_level` or
  `question_tuning` config at runtime — terse mode and /plan-tune features
  were silently broken.

Added the two bash echo blocks back to generatePreambleBash and refreshed
the golden-file fixtures to match. All three preamble-related golden
baselines (claude/codex/factory) are synchronized with the new output.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

scripts/resolvers/preamble/generate-preamble-bash.ts

@@ -41,6 +41,14 @@ _TEL_START=$(date +%s)
 _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: \${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
+# Writing style verbosity (V1: default = ELI10, terse = tighter V0 prose.
+# Read on every skill run so terse mode takes effect without a restart.)
+_EXPLAIN_LEVEL=$(${ctx.paths.binDir}/gstack-config get explain_level 2>/dev/null || echo "default")
+if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
+echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
+# Question tuning (see /plan-tune). Observational only in V1.
+_QUESTION_TUNING=$(${ctx.paths.binDir}/gstack-config get question_tuning 2>/dev/null || echo "false")
+echo "QUESTION_TUNING: $_QUESTION_TUNING"
 mkdir -p ~/.gstack/analytics
 if [ "$_TEL" != "off" ]; then
 echo '{"skill":"${ctx.skillName}","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

test/fixtures/golden/claude-ship-SKILL.md

@@ -55,6 +55,14 @@ _TEL_START=$(date +%s)
 _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
+# Writing style verbosity (V1: default = ELI10, terse = tighter V0 prose.
+# Read on every skill run so terse mode takes effect without a restart.)
+_EXPLAIN_LEVEL=$(~/.claude/skills/gstack/bin/gstack-config get explain_level 2>/dev/null || echo "default")
+if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
+echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
+# Question tuning (see /plan-tune). Observational only in V1.
+_QUESTION_TUNING=$(~/.claude/skills/gstack/bin/gstack-config get question_tuning 2>/dev/null || echo "false")
+echo "QUESTION_TUNING: $_QUESTION_TUNING"
 mkdir -p ~/.gstack/analytics
 if [ "$_TEL" != "off" ]; then
 echo '{"skill":"ship","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

test/fixtures/golden/codex-ship-SKILL.md

@@ -44,6 +44,14 @@ _TEL_START=$(date +%s)
 _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
+# Writing style verbosity (V1: default = ELI10, terse = tighter V0 prose.
+# Read on every skill run so terse mode takes effect without a restart.)
+_EXPLAIN_LEVEL=$($GSTACK_BIN/gstack-config get explain_level 2>/dev/null || echo "default")
+if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
+echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
+# Question tuning (see /plan-tune). Observational only in V1.
+_QUESTION_TUNING=$($GSTACK_BIN/gstack-config get question_tuning 2>/dev/null || echo "false")
+echo "QUESTION_TUNING: $_QUESTION_TUNING"
 mkdir -p ~/.gstack/analytics
 if [ "$_TEL" != "off" ]; then
 echo '{"skill":"ship","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

test/fixtures/golden/factory-ship-SKILL.md

@@ -46,6 +46,14 @@ _TEL_START=$(date +%s)
 _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
+# Writing style verbosity (V1: default = ELI10, terse = tighter V0 prose.
+# Read on every skill run so terse mode takes effect without a restart.)
+_EXPLAIN_LEVEL=$($GSTACK_BIN/gstack-config get explain_level 2>/dev/null || echo "default")
+if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
+echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
+# Question tuning (see /plan-tune). Observational only in V1.
+_QUESTION_TUNING=$($GSTACK_BIN/gstack-config get question_tuning 2>/dev/null || echo "false")
+echo "QUESTION_TUNING: $_QUESTION_TUNING"
 mkdir -p ~/.gstack/analytics
 if [ "$_TEL" != "off" ]; then
 echo '{"skill":"ship","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

test/skill-validation.test.ts

@@ -1103,7 +1103,9 @@ describe('Step 3.4 test coverage audit', () => {
   test('ship/SKILL.md contains Step 7', () => {
     const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
     expect(content).toContain('Step 7: Test Coverage Audit');
-    expect(content).toContain('CODE PATH COVERAGE');
+    // The coverage diagram collapses code-path and user-flow counts onto one
+    // summary line. Verify that summary is present (labels are stable).
+    expect(content).toContain('Code paths:');
   });
 
   test('Step 3.4 includes quality scoring rubric', () => {
@@ -1153,9 +1155,11 @@ describe('Step 3.4 test coverage audit', () => {
     expect(content).toContain('Empty/zero/boundary states');
   });
 
-  test('Step 3.4 diagram includes USER FLOW COVERAGE section', () => {
+  test('Step 3.4 diagram includes user-flow coverage summary', () => {
     const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
-    expect(content).toContain('USER FLOW COVERAGE');
+    // The diagram was compressed from separate CODE PATH COVERAGE / USER FLOW
+    // COVERAGE section headers into a single summary line. Assert on the
+    // labels that still appear on that summary line.
     expect(content).toContain('Code paths:');
     expect(content).toContain('User flows:');
   });
@@ -1165,8 +1169,9 @@ describe('Step 3.4 test coverage audit', () => {
 
 describe('ship step numbering', () => {
   // Allowed sub-steps that are resolver-generated and intentionally nested:
-  // 8.1 (Plan Verification), 8.2 (Scope Drift), 9.1 (Review Army), 9.2 (Findings Merge), 9.3 (Cross-review dedup)
-  const ALLOWED_SUBSTEPS = new Set(['8.1', '8.2', '9.1', '9.2', '9.3']);
+  // 8.1 (Plan Verification), 8.2 (Scope Drift), 9.1 (Review Army), 9.2 (Findings Merge),
+  // 9.3 (Cross-review dedup), 15.0 (WIP squash — continuous checkpoint), 15.1 (Bisectable commits).
+  const ALLOWED_SUBSTEPS = new Set(['8.1', '8.2', '9.1', '9.2', '9.3', '15.0', '15.1']);
 
   test('ship/SKILL.md.tmpl contains no unexpected fractional step numbers', () => {
     const tmpl = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md.tmpl'), 'utf-8');