v1.91.130.0 feat(pr-selection): exercised-path consumer map in shadow mode, MAP_GAP and census refresh (#3259)

* fix(pr-selection): scan shebang and .ts imports, fail closed on scan errors, classify repo config safely

A1-1: strip a leading #! before scanImports at every site, treat bun/node
shebang scripts as code, pick the loader by extension (the TSX loader
misread 15 .ts files), and restore the full gate when any other import
scan fails. Broadens selection only: 0 (file, case) pairs lost vs main,
41 files move from no-consumer to consumed.

A1-2: FREE_ONLY_PR_FILES gains six repository-config files, capy/ is
derivable, and a full-gate file is labelled 'full-gate input' instead of
'real unknown dependency'. The replay MISS check honours the same audited
free-only exemptions as the selector.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(test-health): report gate cases and known cost per PR run, lead with cost per merged PR (A1-3)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(testing): correct the PR fallback section, document the lockfile decision (A1-3, A1-4)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* chore(harness): record the A1 test-pr-profile.ts change as non-behavioral (selection only)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(pr-selection): exercised-path consumers and a shadow selection block (A2-1, A2-2, A2-3)

exercisedConsumers() unions touchfiles, the test-file import closure, executable
skill shell and the bins recorded trials ran (test/helpers/exercised-commands.json).
selectPrProfile reports what that map would select in prCoverage.shadow and never
changes the real selection; a map-only diff selects no paid case.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(exercised-map): union-only refresh with a fail-closed contract, census refresh, MAP_GAP and the replay receipt (A2-1, A2-4)

bun run test:exercised-map refreshes from a census run or local artifacts and
writes nothing on unavailable (exit 3) or partial (exit 4) input. The paid report
prints non-blocking MAP_GAP lines; --replay pins 0 misses over the 47 recorded
gate reds.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(test-health): report shadow savings as a lower bound and split red drops into activation misses and flaky drops (A2-3)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(testing): document the exercised-path map, its refresh contract and shadow metrics

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* chore(harness): record the A2 test-pr-profile.ts and paid-report.ts changes as non-behavioral

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(fixtures): register the exercised-map replay fixture as free (read by scripts/exercised-map.ts --replay)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* chore(release): v1.91.127.0

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Revert "chore(release): v1.91.127.0"

This reverts commit 79e3ef6c63.

* chore(release): v1.91.130.0

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

.github/workflows/evals-periodic.yml

@@ -723,6 +723,34 @@ jobs:
           if-no-files-found: ignore
           retention-days: 90
 
+      # Exercised-path map (shadow, non-blocking; docs/TESTING_INTERNALS.md#exercised-path-map):
+      # union this census's own recorded commands into the map, report MAP_GAP lines and
+      # cases that recorded no commands, and print the refresh command. Never fails the run.
+      - name: Refresh the exercised-path map from this census
+        if: always()
+        continue-on-error: true
+        run: |
+          mkdir -p /tmp/exercised-map
+          dirs=()
+          for dir in /tmp/gate-census-report /tmp/paid-report; do [ -d "$dir" ] && dirs+=(--from-dir "$dir"); done
+          status=0
+          bun --no-install run scripts/exercised-map.ts "${dirs[@]}" \
+            --run-id "$GITHUB_RUN_ID" --out /tmp/exercised-map/exercised-commands.json --report /tmp/exercised-map/report.md || status=$?
+          if [ "$status" -ne 0 ]; then
+            echo "exercised-path map refresh failed with exit $status (non-blocking; no map uploaded)" | tee -a "$GITHUB_STEP_SUMMARY"
+          fi
+          if [ -f /tmp/exercised-map/report.md ]; then cat /tmp/exercised-map/report.md >> "$GITHUB_STEP_SUMMARY"; fi
+
+      - name: Upload the refreshed exercised-path map
+        if: always()
+        continue-on-error: true
+        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7
+        with:
+          name: exercised-map-a${{ github.run_attempt }}
+          path: /tmp/exercised-map
+          if-no-files-found: ignore
+          retention-days: 90
+
       # Weekly pass-rate gate over the last 10 weekly runs (drift, rule cases
       # behaving like behavior, quarantine exit/expiry/cap). Fails closed when
       # history cannot be fetched.