.forgejo/workflows/baseline.yml

@@ -17,9 +17,10 @@
 # still has them. That is what makes this the proof for step 1 and the
 # pre-flight for step 2, rather than a one-shot script.
 #
-# `generate: true` additionally autogenerates a candidate baseline from the
+# While the chain is still present it also autogenerates a candidate baseline
-# models and uploads it. That is a starting point, NOT the answer: autogenerate
+# from the models and prints it. That is a starting point, NOT the answer:
-# reads SQLAlchemy metadata, and three things in this schema do not live there —
+# autogenerate reads SQLAlchemy metadata, and three things here do not live
+# there —
 #   * CREATE EXTENSION vector           (0001)
 #   * CREATE EXTENSION tsm_system_rows  (0004)
 #   * the HNSW index on image_record.siglip_embedding, which is raw SQL
@@ -36,10 +37,6 @@ on:
         description: 'Commit/tag that still carries the full 0001..0087 chain'
         type: string
         default: '0a5bbe8'
-      generate:
-        description: 'Also autogenerate a candidate baseline from the models'
-        type: boolean
-        default: false
 
 jobs:
   compare:
@@ -111,13 +108,23 @@ jobs:
             --no-owner --no-privileges -d fc_chain > chain.sql
           wc -l chain.sql
 
-      # Optional: a candidate baseline, autogenerated from the models against an
+      # A candidate baseline, autogenerated from the models against an EMPTY
-      # EMPTY database so every table shows up as a create. Uploaded for a human
+      # database so every table shows up as a create. Printed for a human to
-      # to finish — it will be missing the three raw-SQL items named at the top.
+      # finish — it will be missing the three raw-SQL items named at the top.
+      #
+      # Gated on the TREE, not on a workflow input. A `type: boolean` input
+      # read back as `github.event.inputs.generate == 'true'` silently
+      # evaluated false on this runner (run 4960 skipped this step entirely
+      # with no diagnostic) — the same `github.event.inputs` typing quirk
+      # build.yml already works around. The file count is the real question
+      # anyway: there is nothing to generate once the chain is collapsed.
       - name: Autogenerate a candidate baseline
-        if: ${{ github.event.inputs.generate == 'true' }}
         run: |
           set -eux
+          if [ "$(ls alembic/versions/*.py | wc -l)" -le 1 ]; then
+            echo "already collapsed — nothing to generate"
+            exit 0
+          fi
           docker exec "$PG_CONTAINER" createdb -U fabledcurator fc_gen
           # Hide the existing revisions so alembic sees an empty history and
           # emits the whole schema rather than a delta.
@@ -153,16 +160,25 @@ jobs:
       #
       # pg_dump orders dumpable objects by name within type, not by creation
       # order, so two schemas built by different routes are directly
-      # comparable. The only normalisation applied is dropping blank lines,
+      # comparable. Normalisation is deliberately minimal, because a filter
-      # comment lines and the alembic_version row-count noise — deliberately
+      # that hides a real difference is the one way this check passes when it
-      # minimal, because a filter that hides a real difference is the one way
+      # should fail — blank lines, SQL comments, trailing whitespace, and:
-      # this check passes when it should fail. Whatever is normalised is
+      #
-      # printed, so the filtering itself is reviewable.
+      #   \restrict / \unrestrict — a per-invocation RANDOM NONCE that newer
+      #   pg_dump emits to fence the dump against injection during restore. It
+      #   differs on every run by construction, so it is noise by definition,
+      #   not a schema difference. Measured on run 4960, the control: two dumps
+      #   of the SAME schema came back 1123 lines each and differed on exactly
+      #   these two lines and nothing else. That control is what licenses this
+      #   filter — it was observed to be the only false positive, rather than
+      #   assumed to be one.
       - name: Diff
         run: |
           set -eu
           norm() {
-            grep -vE '^\s*(--|$)' "$1" | sed 's/[[:space:]]*$//'
+            grep -vE '^\s*(--|$)' "$1" \
+              | grep -vE '^\\(un)?restrict ' \
+              | sed 's/[[:space:]]*$//'
           }
           norm chain.sql > a.txt
           norm baseline.sql > b.txt