Merge pull request 'Release v26.05.25.7 — FC-Cleanup tab + UniqueViolation fix + error modal + extension install fix' (#22) from dev into main

pg_dump + zstd in runtime image, lift Quart body cap to 1 GiB. See PR #2.

.forgejo/workflows/build.yml

@@ -2,17 +2,7 @@ name: Build images
 
 on:
   push:
-    # `:dev` builds dropped 2026-05-26 — operator tests from `:latest` after
-    # merge-to-main, not from the dev branch image. Saves one full docker
-    # build per dev push.
-    branches: [main]
-    # Tag-push triggers an immutable per-version image build (e.g.
-    # `:v26.05.26.5`) — gives a real rollback story alongside the floating
-    # `:main` / `:latest`. Layer reuse keeps the registry-storage cost
-    # negligible per tag. Doesn't overlap with the push-to-main build (that
-    # one publishes `:main` + `:latest`; the tag-push build publishes only
-    # `:<tag>`).
-    tags: ['v*']
+    branches: [dev, main]
 
 # Requires repo secret RELEASE_TOKEN — a Forgejo PAT with scopes:
 #   - write:package, read:package  (for docker push to git.fabledsword.com)
@@ -168,56 +158,25 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Download signed XPI from Forgejo release asset (main + tags)
-        # Fires on main-push AND on tag-push. Tag-push builds re-package the
-        # same source code as the preceding main-push build but with an
-        # immutable version tag — they need the XPI too, otherwise the
-        # versioned image ships without the signed extension.
-        #
-        # Tag-push vs main-push race (operator-flagged 2026-05-27 after
-        # v26.05.27.0 hit it): a release cut fires BOTH workflows almost
-        # simultaneously. Main-push runs sign-extension (1-5min AMO round
-        # trip) before publishing the ext-<version> release; tag-push
-        # skips sign-extension (gated to main) and races straight to
-        # this download step. Tag-push lost every time. Fix: poll the
-        # ext-<version> release endpoint with a sleep+retry loop (30s
-        # for up to 10min total) before giving up. Main-push's signing
-        # eventually wins and tag-push picks the release up on a later
-        # iteration.
-        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
+      - name: Download signed XPI from Forgejo release asset (main only)
+        if: github.ref == 'refs/heads/main'
         env:
           TOKEN: ${{ secrets.RELEASE_TOKEN }}
         run: |
           set -eux
           VERSION=$(grep -E '"version"' extension/package.json | head -1 | sed -E 's/.*"version"[[:space:]]*:[[:space:]]*"([^"]+)".*/\1/')
-          # Poll for the ext-<version> release. main-push's sign-extension
-          # step (AMO round-trip, 1-5min) needs to finish + upload before
-          # tag-push can fetch. 30s * 20 = up to 10min wait, then hard-fail.
-          for attempt in $(seq 1 20); do
-            STATUS=$(curl -s -o release.json -w "%{http_code}" \
-              -H "Authorization: token $TOKEN" \
-              "https://git.fabledsword.com/api/v1/repos/bvandeusen/FabledCurator/releases/tags/ext-$VERSION" || echo 000)
-            if [ "$STATUS" = "200" ]; then
-              echo "Found ext-$VERSION release on attempt $attempt"
-              break
-            fi
-            if [ "$attempt" = "20" ]; then
-              echo "ERROR: ext-$VERSION release not available after 10min of polling"
-              echo "Last HTTP status: $STATUS"
-              exit 1
-            fi
-            echo "Attempt $attempt: ext-$VERSION not yet published (HTTP $STATUS); sleeping 30s"
-            sleep 30
-          done
-          # Extract the .xpi asset's browser_download_url (Forgejo's
-          # /releases/assets/<id> endpoint returns ASSET METADATA, not
-          # the binary blob — operator-flagged 2026-05-26: my prior
-          # code curl'd the metadata endpoint without -f and wrote the
-          # resulting 404-page-not-found text into fabledcurator-*.xpi,
-          # which Firefox then rejected as "corrupt").
-          # browser_download_url is the canonical binary endpoint and
-          # is also publicly accessible (no token needed) but we pass
-          # the token anyway for symmetry with private-repo support.
+          # Look up the ext-<version> release; extract the .xpi asset's
+          # browser_download_url (Forgejo's /releases/assets/<id> endpoint
+          # returns ASSET METADATA, not the binary blob — operator-flagged
+          # 2026-05-26: my prior code curl'd the metadata endpoint without
+          # -f and wrote the resulting 404-page-not-found text into
+          # fabledcurator-*.xpi, which Firefox then rejected as "corrupt").
+          # browser_download_url is the canonical binary endpoint and is
+          # also publicly accessible (no token needed) but we pass the
+          # token anyway for symmetry with private-repo support.
+          curl -sf -H "Authorization: token $TOKEN" \
+            "https://git.fabledsword.com/api/v1/repos/bvandeusen/FabledCurator/releases/tags/ext-$VERSION" \
+            -o release.json
           DOWNLOAD_URL=$(python3 -c "import json; r=json.load(open('release.json')); xpis=[a for a in r.get('assets', []) if a.get('name','').endswith('.xpi')]; print(xpis[0]['browser_download_url'])")
           test -n "$DOWNLOAD_URL"
           echo "Downloading XPI from: $DOWNLOAD_URL"
@@ -241,33 +200,8 @@ jobs:
       - name: Determine tag
         id: tag
         run: |
-          # Three trigger shapes:
-          #   refs/tags/v…   → tag-push: opt-in milestone label (vYY.MM.DD,
-          #                    no `.N` per family release-posture rule).
-          #                    Publish ONLY the immutable version tag;
-          #                    don't touch :latest (the main-push build
-          #                    for the merge commit already did that).
-          #   refs/heads/main → push to main: publish :main + :latest
-          #                    (floating) AND :c-<short_sha> (immutable
-          #                    per-commit rollback substrate, per family
-          #                    release-posture rule "Tags are milestones,
-          #                    not gates — commit-SHA images are the
-          #                    rollback unit"). Rollback to any commit
-          #                    becomes `docker pull …:c-<sha>` without a
-          #                    release ceremony.
-          #   anything else  → safety net; shouldn't fire given the `on:`
-          #                    config above. Tag :dev to surface the
-          #                    unexpected run in the registry.
-          # POSIX-safe substring (the runner shell is dash/BusyBox sh, not
-          # bash — `${var:0:7}` errors with "Bad substitution"; cut works
-          # everywhere). Operator-flagged 2026-06-01 after first :c-<sha>
-          # main-push build failed at this step.
-          SHORT_SHA=$(printf '%s' "$GITHUB_SHA" | cut -c1-7)
-          if [ "${GITHUB_REF#refs/tags/}" != "${GITHUB_REF}" ]; then
-            TAG_NAME="${GITHUB_REF#refs/tags/}"
-            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:${TAG_NAME}" >> "$GITHUB_OUTPUT"
-          elif [ "${GITHUB_REF##*/}" = "main" ]; then
-            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:main,git.fabledsword.com/bvandeusen/fabledcurator:latest,git.fabledsword.com/bvandeusen/fabledcurator:c-${SHORT_SHA}" >> "$GITHUB_OUTPUT"
+          if [ "${GITHUB_REF##*/}" = "main" ]; then
+            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:main,git.fabledsword.com/bvandeusen/fabledcurator:latest" >> "$GITHUB_OUTPUT"
           else
             echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:dev" >> "$GITHUB_OUTPUT"
           fi
@@ -297,20 +231,8 @@ jobs:
       - name: Determine tag
         id: tag
         run: |
-          # Mirrors build-web's three-shape logic (tag-push / main-push /
-          # safety-net dev) including the per-commit :c-<short_sha> tag
-          # on main-push per the family release-posture rule. The -ml
-          # image follows the same release cadence as the web image.
-          # POSIX-safe substring (the runner shell is dash/BusyBox sh, not
-          # bash — `${var:0:7}` errors with "Bad substitution"; cut works
-          # everywhere). Operator-flagged 2026-06-01 after first :c-<sha>
-          # main-push build failed at this step.
-          SHORT_SHA=$(printf '%s' "$GITHUB_SHA" | cut -c1-7)
-          if [ "${GITHUB_REF#refs/tags/}" != "${GITHUB_REF}" ]; then
-            TAG_NAME="${GITHUB_REF#refs/tags/}"
-            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:${TAG_NAME}" >> "$GITHUB_OUTPUT"
-          elif [ "${GITHUB_REF##*/}" = "main" ]; then
-            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:main,git.fabledsword.com/bvandeusen/fabledcurator-ml:latest,git.fabledsword.com/bvandeusen/fabledcurator-ml:c-${SHORT_SHA}" >> "$GITHUB_OUTPUT"
+          if [ "${GITHUB_REF##*/}" = "main" ]; then
+            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:main,git.fabledsword.com/bvandeusen/fabledcurator-ml:latest" >> "$GITHUB_OUTPUT"
           else
             echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:dev" >> "$GITHUB_OUTPUT"
           fi
@@ -329,41 +251,3 @@ jobs:
           file: Dockerfile.ml
           push: true
           tags: ${{ steps.tag.outputs.tags }}
-
-  # The desktop GPU agent (#114) — published so the operator pulls + runs it on
-  # the GPU machine instead of building locally. Independent of web/ml (its own
-  # CUDA + onnxruntime-gpu image, context = agent/). Same tag cadence.
-  build-agent:
-    runs-on: python-ci
-    container:
-      image: git.fabledsword.com/bvandeusen/ci-python:3.14
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Determine tag
-        id: tag
-        run: |
-          SHORT_SHA=$(printf '%s' "$GITHUB_SHA" | cut -c1-7)
-          if [ "${GITHUB_REF#refs/tags/}" != "${GITHUB_REF}" ]; then
-            TAG_NAME="${GITHUB_REF#refs/tags/}"
-            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-agent:${TAG_NAME}" >> "$GITHUB_OUTPUT"
-          elif [ "${GITHUB_REF##*/}" = "main" ]; then
-            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-agent:main,git.fabledsword.com/bvandeusen/fabledcurator-agent:latest,git.fabledsword.com/bvandeusen/fabledcurator-agent:c-${SHORT_SHA}" >> "$GITHUB_OUTPUT"
-          else
-            echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-agent:dev" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Login to Forgejo registry
-        uses: docker/login-action@v3
-        with:
-          registry: git.fabledsword.com
-          username: ${{ github.actor }}
-          password: ${{ secrets.RELEASE_TOKEN }}
-
-      - name: Build and push agent image
-        uses: docker/build-push-action@v5
-        with:
-          context: agent
-          file: agent/Dockerfile
-          push: true
-          tags: ${{ steps.tag.outputs.tags }}

.forgejo/workflows/ci.yml

@@ -1,34 +1,17 @@
 name: CI
 
 # CI lanes per FabledRulebook/forgejo.md "CI philosophy":
-#   - lint: ruff only, no dep install — fast-fail for the common lint bounce.
-#   - backend-lint-and-test: `pytest -m "not integration"`, no service containers.
+#   - backend-lint-and-test: ruff + `pytest -m "not integration"`, no service containers.
 #   - frontend-build: vitest unit + vite build.
 #   - integration: pgvector + redis service containers; alembic + `pytest -m integration`.
 
 on:
   push:
     branches: [dev, main]
-  # pull_request trigger intentionally absent — with branches: [dev, main]
-  # above, every PR commit already fires CI via the push event on dev. Adding
-  # pull_request would duplicate runs on dev→main PRs. FC has no fork PRs
-  # (single-operator Forgejo repo) so push coverage is complete.
+  pull_request:
+    branches: [main]
 
 jobs:
-  # Fast-fail lint lane. ruff is pre-installed in the ci-python image, so
-  # this runs with NO dependency install and surfaces the most common bounce
-  # class (lint: I001 / UP037 / ASYNC109 / W293 …) in seconds — instead of
-  # after the backend job's ~30-60s wheel install. ruff is static analysis,
-  # so no DB/secret env is needed.
-  lint:
-    runs-on: python-ci
-    container:
-      image: git.fabledsword.com/bvandeusen/ci-python:3.14
-    steps:
-      - uses: actions/checkout@v4
-      - name: Ruff lint
-        run: ruff check backend/ tests/ alembic/
-
   backend-lint-and-test:
     runs-on: python-ci
     container:
@@ -41,17 +24,13 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      # Cache step removed 2026-05-26: act_runner's cache backend has been
-      # broken on this homelab runner since 2026-05-15 (first as request-
-      # timeout warnings, then as hard "Cannot find module .../dist/restore/
-      # index.js" failures that tank the whole job). The cache step targeted
-      # ~/.cache/pip but the install below uses `uv pip install` primarily,
-      # whose own cache lives at ~/.cache/uv — so the cache step's real
-      # benefit was marginal even when working. Cost of removal: ~30s of
-      # wheel downloads per job. Future re-enable: mount ~/.cache/uv as a
-      # docker volume at the runner level (skips actions/cache entirely),
-      # or fix the runner-side cache backend (clear /var/run/act/actions/*,
-      # pin act_runner version, etc.).
+      - name: Cache pip wheels
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: pip-${{ runner.os }}-py314-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            pip-${{ runner.os }}-py314-
 
       - name: Install Python deps
         # ruff is pre-installed in the ci-python image (see CI-Runner/CI-python/
@@ -66,8 +45,9 @@ jobs:
             pip install -r requirements.txt pytest pytest-asyncio
           fi
 
-      # Ruff moved to the dedicated fast `lint` job above (fails in seconds,
-      # no dep install). This job is now unit tests only.
+      - name: Ruff lint
+        run: ruff check backend/ tests/ alembic/
+
       - name: Pytest (unit only — integration runs in the integration job)
         run: pytest tests/ -v -m "not integration"
 
@@ -92,25 +72,28 @@ jobs:
       - run: npm run test:unit
       - run: npm run build
 
-  # Single integration job — collapsed from a 3-way shard split on 2026-06-04.
-  # The shards existed to parallelize ~8.5min of integration tests; once the
-  # throwaway Postgres runs with fsync OFF (the durability step below) the whole
-  # suite runs in ~45s, so the split only triplicated the ~2min fixed overhead
-  # (container + `uv pip install` + `alembic upgrade head`) and burned 3 of 6
-  # runner slots for no wall-clock gain. One job now: spin up once, install
-  # once, migrate once, run every integration test.
+  # Integration suite split into THREE parallel shards (2026-05-25, runner
+  # capacity bumped 2→6). Each shard gets its own Postgres + Redis service
+  # set and runs alembic + a disjoint subset of integration tests. Shards
+  # share no DB state, so the autouse TRUNCATE fixture in tests/conftest.py
+  # stays single-threaded per shard but multiple shards run in parallel
+  # wall-clock. Approximate split — rebalance once --durations=15 output
+  # reveals which shard is the long pole.
   #
-  # The docker-ps filter scopes to THIS job's own Postgres/Redis service
-  # containers by job name. act_runner strips underscores from job names when
-  # labelling containers (`int_api` matched nothing on 2026-05-25), so the name
-  # stays separator-free (`integration`). The step prints `docker ps -a` first
-  # so a future naming-convention shift surfaces in the log without a
-  # guess-and-push cycle.
+  # Each shard's docker-ps filter uses its own unique job name to scope
+  # service-container resolution. act_runner appears to strip underscores
+  # from job names when building container labels — `int_api` yielded
+  # zero matches on 2026-05-25 — so shards use no-separator names
+  # (`intapi`, `intimp`, `intcore`) instead. Each step prints
+  # `docker ps -a` first so a future naming-convention shift surfaces in
+  # the log without another guess-and-push cycle.
   #
-  # Pre-baking requirements.txt into ci-python:3.14 is intentionally NOT done —
-  # per ci-requirements.md, FC is the only Python consumer of that image and the
-  # CI-Runner "add deps to image when used by >1 project" rule keeps it per-job.
-  integration:
+  # Pre-baking requirements.txt into ci-python:3.14 is intentionally NOT
+  # done — per ci-requirements.md, FC is the only Python consumer of that
+  # image and the CI-Runner project's "add deps to image when used by >1
+  # project" rule keeps the install per-job.
+
+  intapi:
     runs-on: python-ci
     container:
       image: git.fabledsword.com/bvandeusen/ci-python:3.14
@@ -141,14 +124,21 @@ jobs:
           --health-retries 10
     steps:
       - uses: actions/checkout@v4
-      - name: Integration suite (resolve service IPs, migrate, test)
+      - name: Cache pip wheels
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: pip-${{ runner.os }}-py314-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            pip-${{ runner.os }}-py314-
+      - name: API integration shard (resolve service IPs, migrate, test)
         run: |
           set -eux
           echo "=== container landscape (diagnostic for filter scoping) ==="
           docker ps -a --format '{{.ID}} {{.Image}} -> {{.Names}}'
           echo "=== end landscape ==="
-          PG=$(docker ps --filter "name=integration" --filter "ancestor=pgvector/pgvector:pg16" -q | head -n1)
-          RD=$(docker ps --filter "name=integration" --filter "ancestor=redis:7-alpine" -q | head -n1)
+          PG=$(docker ps --filter "name=intapi" --filter "ancestor=pgvector/pgvector:pg16" -q | head -n1)
+          RD=$(docker ps --filter "name=intapi" --filter "ancestor=redis:7-alpine" -q | head -n1)
           test -n "$PG" && test -n "$RD"
           PG_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG")
           RD_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$RD")
@@ -165,14 +155,144 @@ jobs:
           else
             pip install -r requirements.txt pytest pytest-asyncio
           fi
-          # Relax durability on the throwaway CI Postgres so the per-test
-          # TRUNCATE's commit-fsync — the integration teardown's dominant cost
-          # (~1.5-2s/test, which collapsed the suite from ~13min to ~45s) — is
-          # skipped. fsync/full_page_writes are sighup GUCs and synchronous_commit
-          # is user-context, so ALTER SYSTEM + pg_reload_conf() applies them with
-          # NO restart. Ephemeral DB ⇒ fsync-off is safe. Non-fatal so a perms
-          # surprise can't red the job; fabledcurator is the postgres image's
-          # bootstrap superuser.
-          python -c "import os,psycopg; c=psycopg.connect(host=os.environ['DB_HOST'],port=5432,user=os.environ['DB_USER'],password=os.environ['DB_PASSWORD'],dbname=os.environ['DB_NAME'],autocommit=True); [c.execute(q) for q in ('ALTER SYSTEM SET fsync=off','ALTER SYSTEM SET synchronous_commit=off','ALTER SYSTEM SET full_page_writes=off','SELECT pg_reload_conf()')]; c.close()" || echo 'WARN: durability GUC relax failed (continuing)'
           alembic upgrade head
-          pytest tests/ -v -m integration --durations=15
+          pytest tests/test_api_*.py -v -m integration --durations=15
+
+  intimp:
+    runs-on: python-ci
+    container:
+      image: git.fabledsword.com/bvandeusen/ci-python:3.14
+    env:
+      DB_USER: fabledcurator
+      DB_PASSWORD: ci_integration
+      DB_PORT: "5432"
+      DB_NAME: fabledcurator_test
+      SECRET_KEY: ci_integration_placeholder
+    services:
+      postgres:
+        image: pgvector/pgvector:pg16
+        env:
+          POSTGRES_USER: fabledcurator
+          POSTGRES_PASSWORD: ci_integration
+          POSTGRES_DB: fabledcurator_test
+        options: >-
+          --health-cmd "pg_isready -U fabledcurator"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 10
+      redis:
+        image: redis:7-alpine
+        options: >-
+          --health-cmd "redis-cli ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 10
+    steps:
+      - uses: actions/checkout@v4
+      - name: Cache pip wheels
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: pip-${{ runner.os }}-py314-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            pip-${{ runner.os }}-py314-
+      - name: Importer integration shard (resolve service IPs, migrate, test)
+        run: |
+          set -eux
+          echo "=== container landscape (diagnostic for filter scoping) ==="
+          docker ps -a --format '{{.ID}} {{.Image}} -> {{.Names}}'
+          echo "=== end landscape ==="
+          PG=$(docker ps --filter "name=intimp" --filter "ancestor=pgvector/pgvector:pg16" -q | head -n1)
+          RD=$(docker ps --filter "name=intimp" --filter "ancestor=redis:7-alpine" -q | head -n1)
+          test -n "$PG" && test -n "$RD"
+          PG_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG")
+          RD_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$RD")
+          test -n "$PG_IP" && test -n "$RD_IP"
+          export DB_HOST="$PG_IP"
+          export CELERY_BROKER_URL="redis://$RD_IP:6379/0"
+          export CELERY_RESULT_BACKEND="redis://$RD_IP:6379/0"
+          for i in $(seq 1 60); do
+            (echo > "/dev/tcp/$PG_IP/5432") >/dev/null 2>&1 && break
+            sleep 2
+          done
+          if command -v uv >/dev/null 2>&1; then
+            uv pip install --system -r requirements.txt pytest pytest-asyncio
+          else
+            pip install -r requirements.txt pytest pytest-asyncio
+          fi
+          alembic upgrade head
+          pytest tests/test_importer*.py tests/test_import_*.py tests/test_migration_*.py tests/test_phash_*.py tests/test_sidecar_*.py tests/test_scan_*.py tests/test_archive_extractor.py tests/test_backfill_phash.py -v -m integration --durations=15
+
+  intcore:
+    runs-on: python-ci
+    container:
+      image: git.fabledsword.com/bvandeusen/ci-python:3.14
+    env:
+      DB_USER: fabledcurator
+      DB_PASSWORD: ci_integration
+      DB_PORT: "5432"
+      DB_NAME: fabledcurator_test
+      SECRET_KEY: ci_integration_placeholder
+    services:
+      postgres:
+        image: pgvector/pgvector:pg16
+        env:
+          POSTGRES_USER: fabledcurator
+          POSTGRES_PASSWORD: ci_integration
+          POSTGRES_DB: fabledcurator_test
+        options: >-
+          --health-cmd "pg_isready -U fabledcurator"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 10
+      redis:
+        image: redis:7-alpine
+        options: >-
+          --health-cmd "redis-cli ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 10
+    steps:
+      - uses: actions/checkout@v4
+      - name: Cache pip wheels
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: pip-${{ runner.os }}-py314-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            pip-${{ runner.os }}-py314-
+      - name: Core integration shard (everything not api / importer / migration / phash / sidecar / scan / archive / backfill)
+        run: |
+          set -eux
+          echo "=== container landscape (diagnostic for filter scoping) ==="
+          docker ps -a --format '{{.ID}} {{.Image}} -> {{.Names}}'
+          echo "=== end landscape ==="
+          PG=$(docker ps --filter "name=intcore" --filter "ancestor=pgvector/pgvector:pg16" -q | head -n1)
+          RD=$(docker ps --filter "name=intcore" --filter "ancestor=redis:7-alpine" -q | head -n1)
+          test -n "$PG" && test -n "$RD"
+          PG_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG")
+          RD_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$RD")
+          test -n "$PG_IP" && test -n "$RD_IP"
+          export DB_HOST="$PG_IP"
+          export CELERY_BROKER_URL="redis://$RD_IP:6379/0"
+          export CELERY_RESULT_BACKEND="redis://$RD_IP:6379/0"
+          for i in $(seq 1 60); do
+            (echo > "/dev/tcp/$PG_IP/5432") >/dev/null 2>&1 && break
+            sleep 2
+          done
+          if command -v uv >/dev/null 2>&1; then
+            uv pip install --system -r requirements.txt pytest pytest-asyncio
+          else
+            pip install -r requirements.txt pytest pytest-asyncio
+          fi
+          alembic upgrade head
+          pytest tests/ -v -m integration --durations=15 \
+            --ignore-glob='tests/test_api_*.py' \
+            --ignore-glob='tests/test_importer*.py' \
+            --ignore-glob='tests/test_import_*.py' \
+            --ignore-glob='tests/test_migration_*.py' \
+            --ignore-glob='tests/test_phash_*.py' \
+            --ignore-glob='tests/test_sidecar_*.py' \
+            --ignore-glob='tests/test_scan_*.py' \
+            --ignore-glob='tests/test_archive_extractor.py' \
+            --ignore-glob='tests/test_backfill_phash.py'

.gitignore

@@ -61,12 +61,8 @@ Thumbs.db
 
 # Claude Code per-user local overrides (shared .claude/settings.json is OK to commit)
 .claude/settings.local.json
-# Transient scheduler lock/state (committed by accident in 3f30327)
-.claude/scheduled_tasks.lock
-.claude/scheduled_tasks*.json
 
 # Alembic / DB scratch
 alembic/versions/__pycache__/
 *.sqlite
 *.sqlite-journal
-.superpowers/

Dockerfile

@@ -18,16 +18,13 @@ ENV PYTHONUNBUFFERED=1 \
 
 # System deps: ffmpeg (transcode + thumbnails, FC-2), unar (archives, FC-2),
 # libpq for psycopg, postgresql-client + zstd for FC-5 backup/restore
-# (pg_dump + tar --zstd), image libs, megatools (mega.nz public-link downloads
-# for off-platform file-host links, #830 — `megatools dl`; Debian-native, no
-# external MEGA apt repo needed).
+# (pg_dump + tar --zstd), image libs.
 RUN apt-get update && apt-get install -y --no-install-recommends \
         ffmpeg \
         unar \
         libpq5 \
         postgresql-client \
         zstd \
-        megatools \
         libjpeg62-turbo \
         libwebp7 \
         libpng16-16 \

agent/Dockerfile

@@ -1,27 +0,0 @@
-# FabledCurator GPU agent — runs on the desktop with the GPU.
-# CUDA + cuDNN runtime so onnxruntime-gpu can use the card (it needs cuDNN 9 —
-# the plain -runtime image lacks it: "libcudnn.so.9: cannot open shared object
-# file"); ffmpeg for video frames.
-FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04
-
-ENV DEBIAN_FRONTEND=noninteractive PYTHONUNBUFFERED=1
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends python3 python3-pip ffmpeg \
-    && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /app
-# torch from the CUDA-12.4 wheel index (matches the base image); its wheels
-# bundle their own CUDA + cuDNN and coexist with onnxruntime-gpu. Installed
-# first + separately so the GPU build of torch is deterministic and layer-cached.
-RUN pip3 install --no-cache-dir torch==2.6.0 --index-url https://download.pytorch.org/whl/cu124
-COPY requirements.txt .
-RUN pip3 install --no-cache-dir -r requirements.txt
-COPY fc_agent ./fc_agent
-
-# imgutils ONNX models + the transformers SigLIP weights both cache here; mount
-# a volume to persist them across restarts (the SigLIP download is ~3.5 GB once).
-ENV HF_HOME=/models
-EXPOSE 8770
-
-# The control UI; the worker is started from it (or POST /start).
-CMD ["uvicorn", "fc_agent.app:app", "--host", "0.0.0.0", "--port", "8770"]

agent/README.md

@@ -1,71 +0,0 @@
-# FabledCurator GPU agent
-
-A desktop-GPU worker that embeds characters (CCIP) + figure crops for
-FabledCurator. It talks to FC **only over HTTP** — it leases jobs, fetches image
-pixels, runs the models on your GPU, and posts results back. Your FC database and
-Redis stay private; the agent never touches them.
-
-You run it when you want a burst and stop it to reclaim the card.
-
-## 0. Host prerequisite — NVIDIA Container Toolkit
-Docker needs the toolkit to hand the GPU to a container (else: *"could not select
-device driver nvidia with capabilities [[gpu]]"*). On Arch/CachyOS:
-```sh
-sudo pacman -S nvidia-container-toolkit
-sudo nvidia-ctk runtime configure --runtime=docker
-sudo systemctl restart docker
-# verify:
-docker run --rm --gpus all nvidia/cuda:12.4.1-base-ubuntu22.04 nvidia-smi
-```
-
-## 1. Get a token
-In FC: **Settings → Tagging → GPU agent → Generate token** (or Rotate). Copy it.
-
-## 2. Pull (CI publishes it alongside the web/ml images)
-```sh
-docker pull git.fabledsword.com/bvandeusen/fabledcurator-agent:latest
-```
-> Local build for development instead: `docker build -t fc-gpu-agent agent/`
-
-## 3. Run (on the machine with the GPU)
-```sh
-docker run --rm --gpus all -p 8770:8770 \
-  -e FC_URL=http://curator.traefik.internal \
-  -e FC_TOKEN=<paste-the-token> \
-  -v fc-agent-models:/models \
-  git.fabledsword.com/bvandeusen/fabledcurator-agent:latest
-```
-Then open <http://localhost:8770> — the control page. Click **Start** to begin
-draining the queue; **Pause**/**Stop** to yield the GPU. The `-v fc-agent-models`
-volume caches the downloaded ONNX models so restarts are fast.
-
-Kick off a backfill from FC (**GPU agent card → Queue character embedding**), then
-watch the queue counts on the control page (or FC's card) drain.
-
-## Config (env)
-| var | default | meaning |
-|---|---|---|
-| `FC_URL` | `http://localhost:8000` | FC base URL |
-| `FC_TOKEN` | — | the bearer token (required) |
-| `AGENT_ID` | `desktop-agent` | identifies this agent's leases |
-| `BATCH_SIZE` | `4` | jobs leased per round (still processed one at a time) |
-| `CCIP_MODEL` | imgutils default | CCIP model name |
-| `DETECTOR_LEVEL` | `m` | person-detector size: `n` < `s` < `m` < `x` |
-| `POLL_IDLE_SECONDS` | `10` | wait between empty leases |
-
-## ⚠️ Verify on first run
-This part can't be CI-tested (no GPU/models in CI), so confirm against your
-installed `dghs-imgutils` (`pip show dghs-imgutils`) — see `fc_agent/models.py`:
-- `imgutils.detect.detect_person(image, level=...)` returns
-  `[((x0,y0,x1,y1), label, score), ...]`.
-- `imgutils.metrics.ccip_extract_feature(image, model=...)` returns a vector
-  (768-d for caformer). If you want the F1-0.94 variant, set
-  `CCIP_MODEL=ccip-caformer_b36-24` (verify the exact string in imgutils).
-
-If FC's matcher under/over-fires, tune the cosine threshold in
-`backend/app/services/ml/ccip.py` (`DEFAULT_SIM_THRESHOLD`) and use
-`GET /api/ccip/overview` + `/api/ccip/images/<id>` to spot-check.
-
-## CPU fallback
-Swap `onnxruntime-gpu` → `onnxruntime` in `requirements.txt` and drop `--gpus all`
-to grind it slowly on the server instead. Same agent, no card.

agent/docker-compose.yml

@@ -1,53 +0,0 @@
-# FabledCurator GPU agent — desktop run via docker compose.
-#
-# Usage:
-#   1. Generate a token: FC → Settings → Tagging → GPU agent → Generate token.
-#   2. Create a .env next to this file:
-#        FC_URL=http://curator.traefik.internal
-#        FC_TOKEN=<paste-the-token>
-#        # optional: CCIP_MODEL=ccip-caformer_b36-24   (the F1-0.94 variant)
-#   3. docker compose up -d     (pulls the published image)
-#   4. Open http://localhost:8770 → Start. Pause/Stop hands the GPU back.
-#      docker compose down       to stop the container entirely.
-#
-# Surviving a curator redeploy (you're away, can't touch the agent):
-#   - A running agent rides out curator being unreachable on its own — it retries
-#     leasing with capped backoff and resumes when the server is back. In-flight
-#     work is handed back (not failed), so a redeploy never poisons good jobs.
-#   - AUTO_START=1 (below) also resumes the worker if the AGENT container itself
-#     restarts (host reboot / crash via `restart: unless-stopped`) — no click.
-#
-# Needs the NVIDIA Container Toolkit installed on the host for --gpus.
-
-services:
-  fc-gpu-agent:
-    image: git.fabledsword.com/bvandeusen/fabledcurator-agent:latest
-    pull_policy: always
-    ports:
-      - "8770:8770"
-    environment:
-      FC_URL: ${FC_URL:-http://curator.traefik.internal}
-      FC_TOKEN: ${FC_TOKEN:?set FC_TOKEN in .env (FC → GPU agent → Generate token)}
-      CCIP_MODEL: ${CCIP_MODEL:-}
-      DETECTOR_LEVEL: ${DETECTOR_LEVEL:-m}
-      BATCH_SIZE: ${BATCH_SIZE:-4}
-      # Resume the worker automatically on container start (survive a reboot /
-      # crash-restart while you're away). Set to 0 to require a manual Start.
-      AUTO_START: ${AUTO_START:-1}
-      # Crop embedder (SigLIP concept bag): float16 keeps VRAM low on a shared
-      # desktop GPU; the model itself is announced by the server.
-      SIGLIP_DTYPE: ${SIGLIP_DTYPE:-float16}
-    volumes:
-      # Persist the downloaded ONNX models so restarts are fast.
-      - fc-agent-models:/models
-    restart: unless-stopped
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: all
-              capabilities: [gpu]
-
-volumes:
-  fc-agent-models:

agent/fc_agent/app.py

@@ -1,134 +0,0 @@
-"""FastAPI control surface for the agent (served on localhost).
-
-Start / stop the worker pool, tune the worker count live (trades desktop
-responsiveness for throughput), and watch GPU load + progress + the server-side
-queue. Config is env-seeded; the worker count is adjustable here on the fly.
-"""
-from fastapi import FastAPI, Request
-from fastapi.responses import HTMLResponse, JSONResponse
-
-from .config import Config
-from .gpu import read_gpu
-from .worker import Worker
-
-cfg = Config.from_env()
-worker = Worker(cfg)
-app = FastAPI(title="FabledCurator GPU agent")
-
-
-@app.on_event("startup")
-def _maybe_autostart() -> None:
-    # With AUTO_START set, a container restart (host reboot, or `restart:
-    # unless-stopped` after a crash) resumes the worker on its own — the slots
-    # then ride out a still-down curator via lease backoff. Lets the agent
-    # survive a redeploy with nobody at the desktop to click Start.
-    if cfg.auto_start and cfg.token:
-        worker.start()
-
-
-@app.get("/", response_class=HTMLResponse)
-def index() -> str:
-    return _PAGE
-
-
-@app.post("/start")
-def start():
-    worker.start()
-    return JSONResponse(worker.status())
-
-
-@app.post("/stop")
-def stop():
-    worker.stop()
-    return JSONResponse(worker.status())
-
-
-@app.post("/concurrency")
-async def concurrency(request: Request):
-    body = await request.json()
-    worker.set_concurrency(int(body.get("value", 1)))
-    return JSONResponse(worker.status())
-
-
-@app.get("/status")
-def status():
-    s = worker.status()
-    s["fc_url"] = cfg.fc_url
-    s["configured"] = bool(cfg.token)
-    s["gpu"] = read_gpu()
-    try:
-        s["queue"] = worker.client.queue_status()
-    except Exception:
-        s["queue"] = None
-    return JSONResponse(s)
-
-
-_PAGE = """<!doctype html><html><head><meta charset=utf-8>
-<title>FabledCurator GPU agent</title>
-<style>
- body{font:14px system-ui;margin:2rem;max-width:680px;background:#14171a;color:#e8e8e8}
- h1{font-size:18px} button{font:14px system-ui;padding:.5rem 1rem;border:0;border-radius:6px;
- margin-right:.5rem;cursor:pointer;color:#fff} .start{background:#2e7d32}.stop{background:#b3261e}
- .step{background:#33373b;padding:.4rem .7rem;font-weight:700}
- .stat{display:inline-block;margin-right:1.5rem;vertical-align:top}
- .n{font-size:22px;font-weight:700} code{background:#222;padding:2px 6px;border-radius:4px}
- .q,.gpu{margin-top:1rem;color:#9aa} .bar{height:8px;border-radius:4px;background:#222;overflow:hidden;
- max-width:320px;margin-top:4px} .bar>i{display:block;height:100%;background:#3f7d3f}
- .row{margin:.8rem 0}
-</style></head><body>
-<h1>FabledCurator GPU agent</h1>
-<p>FC: <code id=fc>—</code> · token <code id=cfg>—</code></p>
-<div class=row>
- <button class=start onclick=act('start')>Start</button>
- <button class=stop onclick=act('stop')>Stop</button>
-</div>
-<div class=row>
- workers
- <button class=step onclick=setc(-1)>−</button>
- <input id=conc type=number min=1 value=1
-  style="width:3.5rem;font:700 16px system-ui;text-align:center;background:#222;color:#e8e8e8;border:1px solid #444;border-radius:6px;padding:.3rem"
-  onchange="setv(this.value)">
- <button class=step onclick=setc(1)>+</button>
- <span class=cap style=color:#9aa>(more = overlap I/O, fill the GPU) max <b id=capn>8</b></span>
-</div>
-<div class=row>
- <span class=stat><span class=n id=state>stopped</span><br>state</span>
- <span class=stat><span class=n id=active>0</span><br>active now</span>
- <span class=stat><span class=n id=done>0</span><br>processed</span>
- <span class=stat><span class=n id=err>0</span><br>errors</span>
- <span class=stat><span class=n id=wait>0</span><br>waited out</span>
-</div>
-<div id=banner style="display:none;margin:.6rem 0;padding:.5rem .8rem;border-radius:6px;background:#5a4a17;color:#ffe28a">
- curator unreachable — holding work + retrying, will resume on its own (no restart needed)
-</div>
-<div class=gpu id=gpu>GPU — …</div>
-<div class=bar><i id=gpubar style=width:0%></i></div>
-<div class=q id=queue></div>
-<script>
- let CAP=8
- async function act(p){await fetch('/'+p,{method:'POST'});refresh()}
- function setc(d){ setv((parseInt(conc.value||'1'))+d) }
- async function setv(v){
-  v=Math.max(1,Math.min(CAP,parseInt(v)||1)); conc.value=v
-  await fetch('/concurrency',{method:'POST',headers:{'Content-Type':'application/json'},
-   body:JSON.stringify({value:v})});refresh()
- }
- async function refresh(){
-  const s=await (await fetch('/status')).json()
-  CAP=s.max_concurrency||8; capn.textContent=CAP
-  state.textContent=s.state; active.textContent=s.active; done.textContent=s.processed
-  err.textContent=s.errors; fc.textContent=s.fc_url; wait.textContent=s.transient||0
-  // Running but the queue read failed → curator is unreachable; show we're
-  // riding it out rather than erroring.
-  banner.style.display=(s.state==='running' && !s.queue)?'block':'none'
-  if(document.activeElement!==conc) conc.value=s.concurrency
-  conc.max=CAP
-  cfg.textContent=s.configured?'set':'MISSING'
-  if(s.gpu){
-   gpu.textContent=`GPU — ${s.gpu.util_pct}% util · VRAM ${s.gpu.mem_used_mb}/${s.gpu.mem_total_mb} MB · ${s.gpu.temp_c}°C`
-   gpubar.style.width=Math.round(100*s.gpu.mem_used_mb/s.gpu.mem_total_mb)+'%'
-  } else { gpu.textContent='GPU — n/a (CPU fallback?)'; gpubar.style.width='0%' }
-  queue.textContent=s.queue?`queue — pending ${s.queue.pending} · in flight ${s.queue.leased} · done ${s.queue.done} · errored ${s.queue.error}`:'queue — unreachable'
- }
- refresh(); setInterval(refresh,3000)
-</script></body></html>"""

agent/fc_agent/client.py

@@ -1,85 +0,0 @@
-"""HTTP client for the FabledCurator GPU-job API.
-
-The agent's ONLY contact with FC — lease/submit/heartbeat/fail + fetch image
-bytes, all over HTTP with the bearer token. No DB/Redis.
-"""
-import requests
-from requests.adapters import HTTPAdapter
-
-
-class FcClient:
-    def __init__(self, base_url: str, token: str, agent_id: str):
-        self.base = base_url.rstrip("/")
-        self.agent_id = agent_id
-        self.s = requests.Session()
-        self.s.headers["Authorization"] = f"Bearer {token}"
-        # Many worker threads share this Session; the default pool (10) would
-        # throttle them + spam "connection pool is full". Size it for the cap.
-        adapter = HTTPAdapter(pool_connections=64, pool_maxsize=64)
-        self.s.mount("http://", adapter)
-        self.s.mount("https://", adapter)
-
-    def lease(self, batch_size: int) -> list[dict]:
-        r = self.s.post(
-            f"{self.base}/api/gpu/jobs/lease",
-            json={"agent_id": self.agent_id, "batch_size": batch_size},
-            timeout=30,
-        )
-        r.raise_for_status()
-        return r.json().get("jobs", [])
-
-    def submit(self, job_id: int, regions: list[dict], replace_kinds: list[str]) -> dict:
-        r = self.s.post(
-            f"{self.base}/api/gpu/jobs/submit",
-            json={
-                "agent_id": self.agent_id, "job_id": job_id,
-                "regions": regions, "replace_kinds": replace_kinds,
-            },
-            timeout=120,
-        )
-        r.raise_for_status()
-        return r.json()
-
-    def heartbeat(self, job_ids: list[int]) -> None:
-        try:
-            self.s.post(
-                f"{self.base}/api/gpu/jobs/heartbeat",
-                json={"agent_id": self.agent_id, "job_ids": job_ids},
-                timeout=30,
-            )
-        except requests.RequestException:
-            pass
-
-    def fail(self, job_id: int, error: str) -> None:
-        try:
-            self.s.post(
-                f"{self.base}/api/gpu/jobs/fail",
-                json={"agent_id": self.agent_id, "job_id": job_id, "error": error},
-                timeout=30,
-            )
-        except requests.RequestException:
-            pass
-
-    def release(self, job_ids: list[int]) -> None:
-        # Graceful hand-back on stop so orphaned work is re-leased at once.
-        if not job_ids:
-            return
-        try:
-            self.s.post(
-                f"{self.base}/api/gpu/jobs/release",
-                json={"agent_id": self.agent_id, "job_ids": job_ids},
-                timeout=30,
-            )
-        except requests.RequestException:
-            pass
-
-    def fetch_image(self, image_url: str) -> bytes:
-        # image_url is a server-relative path ("/images/...").
-        r = self.s.get(f"{self.base}{image_url}", timeout=180)
-        r.raise_for_status()
-        return r.content
-
-    def queue_status(self) -> dict:
-        r = self.s.get(f"{self.base}/api/gpu/status", timeout=15)
-        r.raise_for_status()
-        return r.json()

agent/fc_agent/config.py

@@ -1,36 +0,0 @@
-"""Agent config, all from env (the control container is configured at run)."""
-import os
-from dataclasses import dataclass
-
-
-@dataclass
-class Config:
-    fc_url: str          # base URL of the FabledCurator web service
-    token: str           # the bearer token from Settings → Tagging → GPU agent
-    agent_id: str        # identifies this agent's leases
-    batch_size: int      # jobs a worker leases per round
-    concurrency: int     # INITIAL parallel workers (tunable live from the UI)
-    ccip_model: str      # imgutils CCIP model name ("" → imgutils default)
-    detector_level: str  # imgutils person-detector level: n|s|m|x
-    poll_idle_seconds: float   # wait between empty leases
-    embed_dtype: str     # torch dtype for the crop embedder: float16|float32
-    embed_model_override: str  # force a SigLIP-family model ("" → use the one
-    #                            the server announces in the lease)
-    auto_start: bool     # start the worker pool on boot (so a container restart
-    #                      resumes processing without anyone clicking Start)
-
-    @classmethod
-    def from_env(cls) -> "Config":
-        return cls(
-            fc_url=os.environ.get("FC_URL", "http://localhost:8000").rstrip("/"),
-            token=os.environ.get("FC_TOKEN", ""),
-            agent_id=os.environ.get("AGENT_ID", "desktop-agent"),
-            batch_size=int(os.environ.get("BATCH_SIZE", "4")),
-            concurrency=int(os.environ.get("CONCURRENCY", "1")),
-            ccip_model=os.environ.get("CCIP_MODEL", ""),
-            detector_level=os.environ.get("DETECTOR_LEVEL", "m"),
-            poll_idle_seconds=float(os.environ.get("POLL_IDLE_SECONDS", "10")),
-            embed_dtype=os.environ.get("SIGLIP_DTYPE", "float16"),
-            embed_model_override=os.environ.get("EMBED_MODEL_NAME", ""),
-            auto_start=os.environ.get("AUTO_START", "").lower() in ("1", "true", "yes"),
-        )

agent/fc_agent/crops.py

@@ -1,36 +0,0 @@
-"""Crop primitive — vendored from backend/app/services/ml/crops.py so the agent
-is self-contained. Keep in sync if the floor logic changes."""
-from PIL import Image
-
-MIN_CROP_FRACTION = 0.10
-MIN_CROP_PX = 64
-
-
-def crop_region(
-    img: Image.Image,
-    bbox: tuple[float, float, float, float],
-    *,
-    pad: float = 0.0,
-    min_fraction: float = MIN_CROP_FRACTION,
-    min_px: int = MIN_CROP_PX,
-) -> Image.Image | None:
-    """Crop a NORMALIZED bbox (x, y, w, h in [0,1]); None if below the size
-    floor (max of a fraction-of-short-side and an absolute pixel floor)."""
-    iw, ih = img.size
-    x, y, w, h = bbox
-    px, py, pw, ph = x * iw, y * ih, w * iw, h * ih
-    if pad:
-        px -= pw * pad / 2.0
-        py -= ph * pad / 2.0
-        pw *= (1.0 + pad)
-        ph *= (1.0 + pad)
-    left = max(0, int(round(px)))
-    top = max(0, int(round(py)))
-    right = min(iw, int(round(px + pw)))
-    bottom = min(ih, int(round(py + ph)))
-    if right <= left or bottom <= top:
-        return None
-    floor = max(min_px, int(min_fraction * min(iw, ih)))
-    if min(right - left, bottom - top) < floor:
-        return None
-    return img.crop((left, top, right, bottom)).convert("RGB")

agent/fc_agent/embedder.py

@@ -1,69 +0,0 @@
-"""Crop EMBEDDER for the concept bag — model-agnostic (CLIP/SigLIP-family).
-
-The server trains its per-concept heads in the embedding space of whatever model
-its `embedder_model_version` names; a crop must be embedded with the SAME model
-or its vector lands in a different coordinate system and every head misfires. So
-the model identity (HF name + version) is ANNOUNCED BY THE SERVER in the lease —
-nothing here is hardcoded to SigLIP. Whatever name the server sends is loaded via
-transformers `get_image_features` (the CLIP/SigLIP-family image-tower call); a
-non-CLIP backbone (e.g. a DINO encoder) would need its own pooling adapter.
-
-torch on CUDA, fp16 by default to keep VRAM low on a shared desktop GPU — the
-tiny fp16-vs-fp32 difference is negligible for the linear heads (cosine ~0.999).
-A single inference lock serializes the forward pass: the pipeline is I/O-bound,
-so the GPU isn't the bottleneck, and one model shared across worker threads is
-safest behind a lock.
-"""
-import threading
-
-import numpy as np
-from PIL import Image
-
-
-class CropEmbedder:
-    def __init__(self, model_name: str, dtype: str = "float16"):
-        self._name = model_name
-        self._dtype_name = dtype
-        self._model = None
-        self._processor = None
-        self._torch = None
-        self._device = None
-        self._dt = None
-        self._load_lock = threading.Lock()
-        self._infer_lock = threading.Lock()
-
-    @property
-    def model_name(self) -> str:
-        return self._name
-
-    def load(self) -> None:
-        if self._model is not None:
-            return
-        with self._load_lock:
-            if self._model is not None:
-                return
-            import torch
-            from transformers import AutoImageProcessor, AutoModel
-
-            self._torch = torch
-            self._device = "cuda" if torch.cuda.is_available() else "cpu"
-            dt = getattr(torch, self._dtype_name, torch.float16)
-            if self._device == "cpu":
-                dt = torch.float32   # fp16 matmul is unsupported/slow on CPU
-            self._dt = dt
-            self._processor = AutoImageProcessor.from_pretrained(self._name)
-            model = AutoModel.from_pretrained(self._name, torch_dtype=dt)
-            model.eval().to(self._device)
-            self._model = model
-
-    def embed(self, image: Image.Image) -> list[float]:
-        """A crop → its embedding as a plain float list, ready to POST."""
-        self.load()
-        torch = self._torch
-        enc = self._processor(images=image, return_tensors="pt")
-        pixel_values = enc["pixel_values"].to(self._device, self._dt)
-        with self._infer_lock, torch.no_grad():
-            out = self._model.get_image_features(pixel_values=pixel_values)
-        pooled = out.pooler_output if hasattr(out, "pooler_output") else out
-        vec = pooled[0].float().cpu().numpy().astype(np.float32).reshape(-1)
-        return vec.tolist()

agent/fc_agent/gpu.py

@@ -1,30 +0,0 @@
-"""GPU load readout via nvidia-smi (present in the container thanks to the
-NVIDIA Container Toolkit's `utility` capability). Returns None if unavailable —
-the UI just shows n/a (e.g. CPU-fallback run)."""
-import subprocess
-
-
-def read_gpu() -> dict | None:
-    try:
-        out = subprocess.run(
-            [
-                "nvidia-smi",
-                "--query-gpu=utilization.gpu,memory.used,memory.total,temperature.gpu",
-                "--format=csv,noheader,nounits",
-            ],
-            capture_output=True, text=True, timeout=5, check=True,
-        ).stdout.strip().splitlines()
-    except (OSError, subprocess.SubprocessError):
-        return None
-    if not out:
-        return None
-    parts = [p.strip() for p in out[0].split(",")]
-    try:
-        return {
-            "util_pct": int(float(parts[0])),
-            "mem_used_mb": int(float(parts[1])),
-            "mem_total_mb": int(float(parts[2])),
-            "temp_c": int(float(parts[3])),
-        }
-    except (ValueError, IndexError):
-        return None

agent/fc_agent/media.py

@@ -1,63 +0,0 @@
-"""Image + video handling. Stills load directly; videos are sampled into frames
-(ffmpeg) at the cadence FC sends — so a video becomes a bag of per-frame
-instances, each with a timestamp."""
-import io
-import os
-import subprocess
-import tempfile
-
-from PIL import Image
-
-
-def is_video(mime: str) -> bool:
-    return bool(mime) and (mime.startswith("video/") or mime in {"image/gif"})
-
-
-def to_rgb(img: Image.Image) -> Image.Image:
-    """RGB, flattening any transparency onto white first. A naive convert('RGB')
-    on a palette-with-transparency image (common for character PNGs on a clear
-    background) lets PIL guess the transparent pixels — usually black artifacts
-    that bleed into the crop + the embedding (and the "should be converted to
-    RGBA" warning). Compositing over white gives a clean, consistent background."""
-    if img.mode in ("RGBA", "LA", "PA") or (
-        img.mode == "P" and "transparency" in img.info
-    ):
-        img = img.convert("RGBA")
-        bg = Image.new("RGBA", img.size, (255, 255, 255, 255))
-        return Image.alpha_composite(bg, img).convert("RGB")
-    return img.convert("RGB")
-
-
-def load_image(data: bytes) -> Image.Image:
-    return to_rgb(Image.open(io.BytesIO(data)))
-
-
-def sample_frames(
-    data: bytes, interval_seconds: float, max_frames: int
-) -> list[tuple[float, Image.Image]]:
-    """Extract up to max_frames frames at one-every-interval_seconds via ffmpeg.
-    Returns [(timestamp_seconds, frame)]. Empty on failure (caller falls back)."""
-    interval = max(0.5, float(interval_seconds or 4.0))
-    cap = max(1, int(max_frames or 64))
-    with tempfile.TemporaryDirectory() as tmp:
-        src = os.path.join(tmp, "in")
-        with open(src, "wb") as fh:
-            fh.write(data)
-        pattern = os.path.join(tmp, "f_%05d.jpg")
-        try:
-            subprocess.run(
-                [
-                    "ffmpeg", "-nostdin", "-loglevel", "error", "-i", src,
-                    "-vf", f"fps=1/{interval}", "-frames:v", str(cap),
-                    "-q:v", "3", pattern,
-                ],
-                check=True, timeout=600,
-            )
-        except (subprocess.SubprocessError, FileNotFoundError):
-            return []
-        out: list[tuple[float, Image.Image]] = []
-        names = sorted(n for n in os.listdir(tmp) if n.startswith("f_"))
-        for i, name in enumerate(names[:cap]):
-            with Image.open(os.path.join(tmp, name)) as im:
-                out.append((round(i * interval, 2), to_rgb(im)))
-        return out

agent/fc_agent/models.py

@@ -1,39 +0,0 @@
-"""imgutils model wrappers — the figure DETECTOR + the CCIP EMBEDDER.
-
-⚠️ VERIFY ON FIRST RUN: the exact imgutils function names/signatures + the CCIP
-model string can drift between dghs-imgutils releases. These are the two seams to
-check against your installed version (`pip show dghs-imgutils`):
-  - detect_person(image, level=...) -> [((x0,y0,x1,y1), label, score), ...]
-  - ccip_extract_feature(image, model=...) -> a vector (768-d for caformer)
-imgutils auto-downloads the ONNX models from HuggingFace on first use; GPU is
-used when onnxruntime-gpu is installed.
-"""
-import numpy as np
-from PIL import Image
-
-
-def detect_figures(image: Image.Image, level: str = "m") -> list[tuple[tuple, float | None]]:
-    """Person/figure bounding boxes, NORMALIZED (x, y, w, h in [0,1]) + score.
-    Returns [] if detection finds nothing (caller falls back to whole-image)."""
-    from imgutils.detect import detect_person
-
-    iw, ih = image.size
-    out = []
-    for (x0, y0, x1, y1), _label, score in detect_person(image, level=level):
-        out.append((
-            (x0 / iw, y0 / ih, (x1 - x0) / iw, (y1 - y0) / ih),
-            float(score),
-        ))
-    return out
-
-
-def ccip_vector(image: Image.Image, model: str | None = None) -> list[float]:
-    """The CCIP identity embedding of a (cropped) character image, as a plain
-    float list ready to POST."""
-    from imgutils.metrics import ccip_extract_feature
-
-    feat = (
-        ccip_extract_feature(image, model=model)
-        if model else ccip_extract_feature(image)
-    )
-    return np.asarray(feat, dtype=np.float32).reshape(-1).tolist()

agent/fc_agent/worker.py

@@ -1,274 +0,0 @@
-"""The lease → fetch → detect+embed → submit loop, run by a pool of worker
-slots whose count is tunable live from the UI.
-
-Each slot is an independent loop (its own leases; the server's SKIP-LOCKED lease
-keeps them from colliding). More slots = more GPU load + throughput; the model is
-loaded once and shared, so slots add concurrent inference, not N× model VRAM.
-That's the dial the operator turns to trade desktop responsiveness for speed.
-
-Stop (or shrinking the pool) RELEASES a slot's still-leased jobs immediately so
-orphaned work is re-picked at once rather than waiting out the lease.
-"""
-import threading
-
-import requests
-
-from . import media, models
-from .client import FcClient
-from .config import Config
-from .crops import crop_region
-
-# Cap on the lease-retry backoff: when curator is unreachable (e.g. you redeploy
-# it while away), each slot retries leasing with exponential backoff up to this
-# many seconds, then resumes within this window once the server is back — no
-# restart needed.
-MAX_BACKOFF_SECONDS = 60.0
-
-
-def _is_transient(exc: "requests.RequestException") -> bool:
-    """A server/transport problem (wait it out) vs a job-specific fault (fail it).
-    No response → connection refused/timeout → curator is down → transient. With
-    a response: 5xx, auth (401/403, e.g. a token blip on redeploy), 408/409/429
-    (timeout / our lease reclaimed / rate-limited) are all 'not this job's fault'.
-    A specific 4xx like 404 (image gone) / 400 IS the job's fault → fail it."""
-    resp = getattr(exc, "response", None)
-    if resp is None:
-        return True
-    return resp.status_code >= 500 or resp.status_code in (401, 403, 408, 409, 429)
-
-# Generous cap: the pipeline is usually I/O-bound (downloading + decoding images
-# over HTTP), so the GPU stays underused until many workers overlap that I/O.
-# Push it up while watching the GPU util + VRAM in the UI.
-MAX_CONCURRENCY = 32
-
-# Fallbacks only — the server ANNOUNCES the embedding model (name + version) in
-# the lease so the agent stays model-agnostic and in lock-step with the space
-# the heads were trained in. These cover an older server that doesn't send them.
-DEFAULT_EMBED_MODEL = "google/siglip-so400m-patch14-384"
-DEFAULT_EMBED_VERSION = "siglip-so400m-patch14-384"
-
-
-class _Slot:
-    """One worker loop. `inflight` = jobs leased but not yet processed, so a
-    graceful stop can hand them back."""
-    __slots__ = ("stop", "inflight")
-
-    def __init__(self):
-        self.stop = threading.Event()
-        self.inflight: list[int] = []
-
-
-class Worker:
-    def __init__(self, cfg: Config):
-        self.cfg = cfg
-        self.client = FcClient(cfg.fc_url, cfg.token, cfg.agent_id)
-        self._lock = threading.Lock()
-        self._running = False
-        self._target = max(1, min(MAX_CONCURRENCY, cfg.concurrency))
-        self._slots: list[_Slot] = []
-        self.processed = 0
-        self.errors = 0
-        self.transient = 0        # jobs handed back due to a server outage (NOT
-        #                           failed) — the "waiting out curator" counter
-        self._active = 0          # slots currently mid-image
-        # The crop embedder (SigLIP-family) is built lazily on the first job that
-        # needs it, from the model the server announces — one shared instance.
-        self._embedder = None
-        self._embedder_lock = threading.Lock()
-
-    # --- control -----------------------------------------------------------
-    def start(self):
-        with self._lock:
-            self._running = True
-            self._reconcile_locked()
-
-    def stop(self):
-        with self._lock:
-            self._running = False
-            slots, self._slots = self._slots, []
-        for s in slots:
-            s.stop.set()          # each slot releases its inflight on exit
-
-    def set_concurrency(self, n: int):
-        with self._lock:
-            self._target = max(1, min(MAX_CONCURRENCY, int(n)))
-            if self._running:
-                self._reconcile_locked()
-
-    def _reconcile_locked(self):
-        while len(self._slots) < self._target:
-            slot = _Slot()
-            self._slots.append(slot)
-            threading.Thread(target=self._loop, args=(slot,), daemon=True).start()
-        while len(self._slots) > self._target:
-            self._slots.pop().stop.set()
-
-    def status(self) -> dict:
-        with self._lock:
-            return {
-                "state": "running" if self._running else "stopped",
-                "concurrency": self._target,
-                "max_concurrency": MAX_CONCURRENCY,
-                "workers": len(self._slots),
-                "active": self._active,
-                "processed": self.processed,
-                "errors": self.errors,
-                "transient": self.transient,
-            }
-
-    def _bump(self, *, processed=0, errors=0, active=0, transient=0):
-        with self._lock:
-            self.processed += processed
-            self.errors += errors
-            self.transient += transient
-            self._active += active
-
-    # --- per-slot loop -----------------------------------------------------
-    def _loop(self, slot: _Slot):
-        backoff = self.cfg.poll_idle_seconds
-        while not slot.stop.is_set() and self._running:
-            try:
-                jobs = self.client.lease(self.cfg.batch_size)
-                backoff = self.cfg.poll_idle_seconds      # server answered → reset
-            except Exception:
-                # curator unreachable (redeploy, network drop): wait it out with
-                # exponential backoff, capped — resume on our own when it returns.
-                self._interruptible_sleep(slot, backoff)
-                backoff = min(backoff * 2, MAX_BACKOFF_SECONDS)
-                continue
-            if not jobs:
-                self._interruptible_sleep(slot, self.cfg.poll_idle_seconds)
-                continue
-            slot.inflight = [j["job_id"] for j in jobs]
-            for job in jobs:
-                if slot.stop.is_set() or not self._running:
-                    break
-                ok = self._process(job)
-                slot.inflight = [i for i in slot.inflight if i != job["job_id"]]
-                if not ok:
-                    # Server went away mid-batch: hand the rest back (best effort)
-                    # and back off instead of hammering a recovering server or
-                    # burning the jobs' attempt budgets on fail().
-                    if slot.inflight:
-                        self.client.release(slot.inflight)
-                        slot.inflight = []
-                    self._interruptible_sleep(slot, backoff)
-                    backoff = min(backoff * 2, MAX_BACKOFF_SECONDS)
-                    break
-                if slot.inflight:
-                    self.client.heartbeat(slot.inflight)
-        # Graceful hand-back of anything leased but not processed.
-        if slot.inflight:
-            self.client.release(slot.inflight)
-            slot.inflight = []
-
-    def _interruptible_sleep(self, slot: _Slot, seconds: float):
-        """Sleep, but wake immediately if the slot is told to stop — so a Stop or
-        a pool-shrink doesn't hang for a full backoff window."""
-        slot.stop.wait(timeout=seconds)
-
-    def _ensure_embedder(self, model_name: str):
-        if self._embedder is not None:
-            return self._embedder
-        with self._embedder_lock:
-            if self._embedder is None:
-                from .embedder import CropEmbedder
-                self._embedder = CropEmbedder(model_name, self.cfg.embed_dtype)
-        return self._embedder
-
-    def _process(self, job: dict) -> bool:
-        """Process one job. Returns True when handled (completed, or hard-failed
-        because the job itself is bad) and False on a TRANSPORT error (curator
-        unreachable / 5xx / our lease was reclaimed mid-flight) — which is not
-        the job's fault, so the caller backs off and the job is left to be
-        re-leased rather than fail()ed into its attempt budget."""
-        self._bump(active=1)
-        try:
-            data = self.client.fetch_image(job["image_url"])
-            if media.is_video(job.get("mime", "")):
-                frames = media.sample_frames(
-                    data, job.get("frame_interval_seconds", 4.0),
-                    job.get("max_frames", 64),
-                ) or [(None, media.load_image(data))]
-            else:
-                frames = [(None, media.load_image(data))]
-
-            # task picks what to produce per crop:
-            #   'siglip' (backfill existing images) → concept (SigLIP) regions
-            #     ONLY, so it never churns their figure/CCIP regions or the
-            #     character-reference cache.
-            #   'ccip' / 'both' (a new image's first pass) → figure (CCIP) AND
-            #     concept (SigLIP) in one go, off the same crop.
-            task = job.get("task") or "ccip"
-            want_ccip = task in ("ccip", "both")
-            want_siglip = task in ("ccip", "siglip", "both")
-            replace_kinds = (
-                ["concept"] if task == "siglip" else ["figure", "face", "concept"]
-            )
-
-            embed_version = job.get("embed_version") or DEFAULT_EMBED_VERSION
-            embedder = None
-            if want_siglip:
-                model_name = (
-                    self.cfg.embed_model_override
-                    or job.get("embed_model_name")
-                    or DEFAULT_EMBED_MODEL
-                )
-                embedder = self._ensure_embedder(model_name)
-
-            regions = []
-            ccip_ev = self.cfg.ccip_model or "ccip-default"
-            dv = f"person-{self.cfg.detector_level}"
-            for t, frame in frames:
-                figs = models.detect_figures(frame, self.cfg.detector_level)
-                if not figs:
-                    figs = [((0.0, 0.0, 1.0, 1.0), None)]   # whole-frame fallback
-                for bbox, score in figs:
-                    crop = crop_region(frame, bbox)
-                    if crop is None:
-                        continue
-                    if want_ccip:
-                        regions.append({
-                            "kind": "figure",
-                            "bbox": list(bbox),
-                            "frame_time": t,
-                            "score": score,
-                            "ccip_embedding": models.ccip_vector(
-                                crop, self.cfg.ccip_model or None
-                            ),
-                            "embedding_version": ccip_ev,
-                            "detector_version": dv,
-                        })
-                    if want_siglip:
-                        regions.append({
-                            "kind": "concept",
-                            "bbox": list(bbox),
-                            "frame_time": t,
-                            "score": score,
-                            "siglip_embedding": embedder.embed(crop),
-                            "embedding_version": embed_version,
-                            "detector_version": dv,
-                        })
-            self.client.submit(job["job_id"], regions, replace_kinds)
-            self._bump(processed=1)
-            return True
-        except requests.RequestException as exc:
-            if _is_transient(exc):
-                # curator down/redeploying, a 5xx, or our lease was reclaimed
-                # while we worked. NOT the job's fault — hand it back (best
-                # effort; no-ops if the server is still down, then the server's
-                # orphan-recovery reclaims it) and signal the loop to wait.
-                self._bump(transient=1)
-                self.client.release([job["job_id"]])
-                return False
-            # A job-specific HTTP fault (404 image gone, 400) → fail it so it
-            # doesn't re-lease forever.
-            self._bump(errors=1)
-            self.client.fail(job["job_id"], str(exc)[:500])
-            return True
-        except Exception as exc:   # noqa: BLE001 — a genuine job fault: report it
-            self._bump(errors=1)
-            self.client.fail(job["job_id"], str(exc)[:500])
-            return True
-        finally:
-            self._bump(active=-1)

agent/requirements.txt

@@ -1,15 +0,0 @@
-# CCIP + figure detection (ONNX models, auto-downloaded from HuggingFace).
-dghs-imgutils>=0.4
-# GPU inference for the ONNX models. Swap to onnxruntime (CPU) for a slow
-# server-side fallback run.
-onnxruntime-gpu
-# The crop EMBEDDER (concept bag). torch is installed separately in the
-# Dockerfile from the CUDA-12.4 wheel index so the GPU build is deterministic;
-# transformers loads whatever SigLIP-family model the server announces.
-transformers>=4.45
-# Control surface + HTTP.
-fastapi
-uvicorn[standard]
-requests
-pillow
-numpy

alembic/env.py

@@ -1,28 +1,13 @@
 """Alembic environment — reads DATABASE_URL from app config."""
 
-import os
-import re
 from logging.config import fileConfig
 
-from sqlalchemy import engine_from_config, pool, text
+from sqlalchemy import engine_from_config, pool
 
 from alembic import context
 from backend.app.config import get_config
 from backend.app.models import Base
 
-# Fail a blocked migration FAST instead of hanging forever. Migrations run
-# against the live DB while workers hold locks; 0040's `ALTER series_page` queued
-# behind a tag-merge that held a series_page lock for minutes (the merge runs an
-# unindexed full scan over image_record while repointing series_page) and hung
-# with no timeout — silent, indefinite (operator-flagged 2026-06-07). With a
-# lock_timeout a blocked DDL errors ("canceling statement due to lock timeout")
-# and the entrypoint's `alembic upgrade head` exits non-zero, so the deploy
-# retries / surfaces loudly rather than wedging. Override via env when a known
-# slow-lock window is expected.
-_MIGRATION_LOCK_TIMEOUT = os.environ.get("MIGRATION_LOCK_TIMEOUT", "30s")
-if not re.fullmatch(r"\d+\s*(ms|s|min)?", _MIGRATION_LOCK_TIMEOUT.strip()):
-    _MIGRATION_LOCK_TIMEOUT = "30s"  # ignore a malformed override
-
 config = context.config
 
 if config.config_file_name is not None:
@@ -53,15 +38,6 @@ def run_migrations_online() -> None:
         poolclass=pool.NullPool,
     )
     with connectable.connect() as connection:
-        # Session-level lock_timeout for every DDL statement in this run. Set
-        # (and commit) before alembic opens its own transaction so the GUC
-        # persists on this connection regardless of how alembic structures its
-        # transactions. Value is from our own env, so f-string interpolation is
-        # safe (and it's been pattern-validated above); SET takes no bind params.
-        connection.execute(
-            text(f"SET lock_timeout = '{_MIGRATION_LOCK_TIMEOUT}'")
-        )
-        connection.commit()
         context.configure(
             connection=connection,
             target_metadata=target_metadata,

alembic/versions/0021_image_provenance_unique.py

@@ -1,54 +0,0 @@
-"""provenance-race: dedupe + UNIQUE(image_record_id, post_id) on image_provenance
-
-Revision ID: 0021
-Revises: 0020
-Create Date: 2026-05-26
-
-Closes the race in Importer._apply_sidecar's existence-check + INSERT pattern.
-Two workers writing for the same (image, post) pair both saw no existing row
-and both inserted, leaving duplicates that then broke .scalar_one_or_none()
-on every subsequent deep-scan rederive against those images
-(MultipleResultsFound). Most plausibly seeded when the 5-min recovery sweep
-re-enqueued a still-running long-import task and the second worker collided
-with the first inside _apply_sidecar.
-
-Migration steps:
-  1. DELETE all but min(id) per (image_record_id, post_id) pair. Operator's
-     DB had 2 affected pairs at write-time; harmless no-op if zero.
-  2. Add UNIQUE constraint so the importer's new savepoint+IntegrityError
-     recovery path can trip on collision and re-select, mirroring
-     uq_source_artist_platform_url and uq_post_source_external_id.
-"""
-from typing import Sequence, Union
-
-from alembic import op
-
-revision: str = "0021"
-down_revision: Union[str, None] = "0020"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.execute(
-        """
-        DELETE FROM image_provenance ip1
-        USING image_provenance ip2
-        WHERE ip1.image_record_id = ip2.image_record_id
-          AND ip1.post_id = ip2.post_id
-          AND ip1.id > ip2.id
-        """
-    )
-    op.create_unique_constraint(
-        "uq_image_provenance_image_post",
-        "image_provenance",
-        ["image_record_id", "post_id"],
-    )
-
-
-def downgrade() -> None:
-    op.drop_constraint(
-        "uq_image_provenance_image_post",
-        "image_provenance",
-        type_="unique",
-    )

alembic/versions/0022_source_per_artist_platform.py

@@ -1,223 +0,0 @@
-"""source-collapse: one Source per (artist, platform) — consolidate junk per-post Sources
-
-Revision ID: 0022
-Revises: 0021
-Create Date: 2026-05-26
-
-Closes the operator-flagged 2026-05-26 issue where the filesystem importer
-called _find_or_create_source(url=sd.post_url), creating one Source row per
-imported post URL. Operator's Atole artist had 406 Source rows where there
-should have been 1 (the /cw/Atole subscription Source).
-
-Source represents a subscription feed (one per artist+platform — the
-gallery-dl URL polled by the FC-3 downloader). Posts hang off it. The
-filesystem importer was misusing Source as a per-post key.
-
-Migration steps per (artist_id, platform) group with >1 Source:
-  1. Pick canonical — prefer a URL NOT matching '/posts/<id>$' (real
-     campaign URL like /cw/Atole); else min(id).
-  2. PRE-merge any Posts under non-canonical sources whose
-     external_post_id ALREADY exists under the canonical source. (Same
-     gallery-dl post imported via two different sidecar paths can plant
-     two Post rows with identical external_post_id under different
-     Sources for the same artist.) Repoint ImageProvenance +
-     ImageRecord.primary_post_id to the canonical-side Post, dedupe
-     ImageProvenance against alembic 0021's uq, then delete the
-     non-canonical-side Post. This MUST happen before step 3 — Postgres
-     fires uq_post_source_external_id row-by-row during the bulk UPDATE
-     and the merge-after-reparent ordering 500s on first collision
-     (operator-hit during v26.05.26.1 deploy, 2026-05-26).
-  3. Reparent remaining Posts onto canonical (no collisions possible now).
-  4. Reparent ImageProvenance.source_id off the non-canonical sources.
-  5. Delete the orphan Source rows.
-  6. If the canonical Source's URL still looks like a per-post URL (no
-     campaign URL existed among candidates), rewrite it to
-     'sidecar:<platform>:<artist_slug>' so the artist detail page shows
-     something readable.
-"""
-from typing import Sequence, Union
-
-from alembic import op
-from sqlalchemy import text
-
-revision: str = "0022"
-down_revision: Union[str, None] = "0021"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-_POST_URL_RE = r"/posts/[^/]+$"
-
-
-def upgrade() -> None:
-    conn = op.get_bind()
-
-    # Find (artist_id, platform) groups with > 1 Source row.
-    groups = conn.execute(text("""
-        SELECT artist_id, platform
-        FROM source
-        GROUP BY artist_id, platform
-        HAVING COUNT(*) > 1
-    """)).fetchall()
-
-    for artist_id, platform in groups:
-        rows = conn.execute(
-            text("""
-                SELECT id, url FROM source
-                WHERE artist_id = :a AND platform = :p
-                ORDER BY id ASC
-            """),
-            {"a": artist_id, "p": platform},
-        ).fetchall()
-
-        # Canonical: first row whose URL doesn't look like a per-post URL;
-        # else min(id).
-        canonical_id = None
-        for sid, url in rows:
-            if not _matches_post_url(url):
-                canonical_id = sid
-                break
-        if canonical_id is None:
-            canonical_id = rows[0][0]
-
-        other_ids = [sid for sid, _ in rows if sid != canonical_id]
-        if not other_ids:
-            continue
-
-        # STEP 2: PRE-merge ALL Posts with duplicate external_post_id
-        # across the entire (canonical + others) group, BEFORE the bulk
-        # reparent. Two cases must both be handled:
-        #   (A) canonical has Post X with epid=N; an "other" source has
-        #       Post Y with epid=N → after bulk UPDATE, (canonical, N)
-        #       collides with itself.
-        #   (B) two different "other" sources each have a Post with
-        #       epid=N; canonical has none → after bulk UPDATE, both
-        #       are repointed to (canonical, N) and the second collides.
-        # The earlier version of this migration only handled (A); the
-        # operator's deploy 2026-05-26 tripped (B) at line 139.
-        # Fix: group ALL Posts in the (artist, platform) by epid; for
-        # any group with count>1, pick the keep (prefer one already
-        # under canonical; else lowest id) and merge the rest into it.
-        all_posts = conn.execute(
-            text("""
-                SELECT external_post_id, id, source_id
-                FROM post
-                WHERE source_id = :canonical OR source_id = ANY(:others)
-                ORDER BY external_post_id, id
-            """),
-            {"canonical": canonical_id, "others": other_ids},
-        ).fetchall()
-        by_epid: dict = {}
-        for epid, post_id, src_id in all_posts:
-            by_epid.setdefault(epid, []).append((post_id, src_id))
-        for _epid, posts in by_epid.items():
-            if len(posts) <= 1:
-                continue
-            # Prefer a Post already under canonical as the keep.
-            canonical_posts = [p for p in posts if p[1] == canonical_id]
-            if canonical_posts:
-                keep_id = canonical_posts[0][0]
-            else:
-                keep_id = posts[0][0]  # already sorted by id ASC
-            drop_ids = [p[0] for p in posts if p[0] != keep_id]
-            for drop_id in drop_ids:
-                # Pre-delete image_provenance rows under drop_ whose
-                # image_record_id ALREADY has a provenance under keep —
-                # the UPDATE below would otherwise repoint them and
-                # trip uq_image_provenance_image_post (alembic 0021)
-                # row-by-row before any after-the-fact dedupe could
-                # run. Operator's v26.05.26.3 deploy 2026-05-26 tripped
-                # this at line 123.
-                conn.execute(
-                    text("""
-                        DELETE FROM image_provenance
-                        WHERE post_id = :drop_
-                          AND image_record_id IN (
-                              SELECT image_record_id FROM image_provenance
-                              WHERE post_id = :keep
-                          )
-                    """),
-                    {"keep": keep_id, "drop_": drop_id},
-                )
-                # Now safe to repoint the survivors.
-                conn.execute(
-                    text("""
-                        UPDATE image_provenance SET post_id = :keep
-                        WHERE post_id = :drop_
-                    """),
-                    {"keep": keep_id, "drop_": drop_id},
-                )
-                conn.execute(
-                    text("""
-                        UPDATE image_record SET primary_post_id = :keep
-                        WHERE primary_post_id = :drop_
-                    """),
-                    {"keep": keep_id, "drop_": drop_id},
-                )
-                conn.execute(
-                    text("DELETE FROM post WHERE id = :drop_"),
-                    {"drop_": drop_id},
-                )
-
-        # STEP 3: Bulk reparent the remaining Posts off the other
-        # Sources. After step 2, no collisions on
-        # (canonical, external_post_id) are possible.
-        conn.execute(
-            text("""
-                UPDATE post SET source_id = :canonical
-                WHERE source_id = ANY(:others)
-            """),
-            {"canonical": canonical_id, "others": other_ids},
-        )
-
-        # STEP 4: Reparent ImageProvenance.source_id (denormalized FK).
-        # No UNIQUE on source_id; safe bulk update.
-        conn.execute(
-            text("""
-                UPDATE image_provenance SET source_id = :canonical
-                WHERE source_id = ANY(:others)
-            """),
-            {"canonical": canonical_id, "others": other_ids},
-        )
-
-        # STEP 5: Drop the orphan Sources.
-        conn.execute(
-            text("DELETE FROM source WHERE id = ANY(:others)"),
-            {"others": other_ids},
-        )
-
-        # If the canonical's URL still looks per-post (no campaign URL
-        # existed among the candidates), rewrite to a synthetic anchor so
-        # the artist detail page renders something readable.
-        canonical_url = conn.execute(
-            text("SELECT url FROM source WHERE id = :id"),
-            {"id": canonical_id},
-        ).scalar_one()
-        if _matches_post_url(canonical_url):
-            slug = conn.execute(
-                text("SELECT slug FROM artist WHERE id = :id"),
-                {"id": artist_id},
-            ).scalar_one()
-            conn.execute(
-                text("""
-                    UPDATE source
-                    SET url = :new_url, enabled = false
-                    WHERE id = :id
-                """),
-                {
-                    "id": canonical_id,
-                    "new_url": f"sidecar:{platform}:{slug}",
-                },
-            )
-
-
-def downgrade() -> None:
-    # Lossy migration — orphan Sources deleted, Posts reparented, Posts
-    # merged. No safe downgrade. If you need to roll back the schema
-    # invariant, fork from 0021 and re-run filesystem imports.
-    pass
-
-
-def _matches_post_url(url: str) -> bool:
-    """True if url ends with /posts/<token> (gallery-dl-style per-post URL)."""
-    import re
-    return bool(re.search(_POST_URL_RE, url or ""))

alembic/versions/0023_drop_meta_rating_tag_kinds.py

@@ -1,99 +0,0 @@
-"""drop meta + rating tag kinds — operator-retired 2026-05-26
-
-Revision ID: 0023
-Revises: 0022
-Create Date: 2026-05-26
-
-Operator decided meta + rating aren't valid tag kinds for FC. Per-row
-behavior: DELETE existing rows (operator chose "clean break" over
-"convert to general"). All cascading FKs (image_tag, tag_alias,
-tag_allowlist, tag_reference_embedding, tag_suggestion_rejection,
-series_page) use ondelete="CASCADE" so a single DELETE on tag cleans
-the related rows in one go.
-
-After the data cleanup, recreate the tag_kind ENUM without 'meta' /
-'rating' (Postgres has no `ALTER TYPE ... DROP VALUE`; standard
-rename-create-cast-drop dance). The server default 'general' is
-dropped before the type swap and restored after.
-"""
-from typing import Sequence, Union
-
-from alembic import op
-
-revision: str = "0023"
-down_revision: Union[str, None] = "0022"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # 1. Delete tags of the retired kinds. CASCADE handles related tables.
-    op.execute("DELETE FROM tag WHERE kind IN ('meta', 'rating')")
-
-    # 2. Drop the CHECK constraint that references the enum's literal
-    #    values. Postgres can't resolve `kind = 'character'` across the
-    #    type swap below — the literal would bind to the new tag_kind
-    #    but the column is on tag_kind_old, producing
-    #    "operator does not exist: tag_kind = tag_kind_old".
-    #    (Operator-hit during the v26.05.26.5 deploy attempt; ck was
-    #    originally added by alembic 0002.) Recreated post-swap.
-    op.drop_constraint(
-        "ck_tag_fandom_requires_character", "tag", type_="check"
-    )
-
-    # 3. Drop the server default — ALTER COLUMN TYPE can't carry it
-    #    across the type swap below.
-    op.execute("ALTER TABLE tag ALTER COLUMN kind DROP DEFAULT")
-
-    # 4. Recreate the tag_kind enum without meta/rating.
-    op.execute("ALTER TYPE tag_kind RENAME TO tag_kind_old")
-    op.execute(
-        "CREATE TYPE tag_kind AS ENUM ("
-        "'artist', 'character', 'fandom', 'general', "
-        "'series', 'archive', 'post'"
-        ")"
-    )
-    op.execute(
-        "ALTER TABLE tag "
-        "ALTER COLUMN kind TYPE tag_kind "
-        "USING kind::text::tag_kind"
-    )
-    op.execute("DROP TYPE tag_kind_old")
-
-    # 5. Restore the server default.
-    op.execute("ALTER TABLE tag ALTER COLUMN kind SET DEFAULT 'general'")
-
-    # 6. Restore the CHECK constraint (now bound to the new tag_kind).
-    op.create_check_constraint(
-        "ck_tag_fandom_requires_character",
-        "tag",
-        "(fandom_id IS NULL) OR (kind = 'character')",
-    )
-
-
-def downgrade() -> None:
-    # Add the values back to the enum so old code can boot. The deleted
-    # tag rows are gone permanently — no safe restore.
-    op.drop_constraint(
-        "ck_tag_fandom_requires_character", "tag", type_="check"
-    )
-    op.execute("ALTER TABLE tag ALTER COLUMN kind DROP DEFAULT")
-    op.execute("ALTER TYPE tag_kind RENAME TO tag_kind_old")
-    op.execute(
-        "CREATE TYPE tag_kind AS ENUM ("
-        "'artist', 'character', 'fandom', 'general', "
-        "'series', 'archive', 'post', 'meta', 'rating'"
-        ")"
-    )
-    op.execute(
-        "ALTER TABLE tag "
-        "ALTER COLUMN kind TYPE tag_kind "
-        "USING kind::text::tag_kind"
-    )
-    op.execute("DROP TYPE tag_kind_old")
-    op.execute("ALTER TABLE tag ALTER COLUMN kind SET DEFAULT 'general'")
-    op.create_check_constraint(
-        "ck_tag_fandom_requires_character",
-        "tag",
-        "(fandom_id IS NULL) OR (kind = 'character')",
-    )

alembic/versions/0024_backfill_post_title_from_description.py

@@ -1,80 +0,0 @@
-"""backfill post.post_title from description first-line — 2026-05-27
-
-Revision ID: 0024
-Revises: 0023
-Create Date: 2026-05-27
-
-SubscribeStar gallery-dl always writes `title: ""` and embeds the leading
-sentence inside `content` HTML. FC's sidecar parser was leaving
-post_title NULL for every SubscribeStar post since FC-3 shipped. The
-parser fix (sidecar._first_line_text fallback) now synthesizes a title
-at parse time; this migration applies the same logic retroactively to
-existing rows.
-
-Operator-flagged 2026-05-27 after inspecting
-/mnt/Data/Patreon/Cheunart/subscribestar/ sidecars.
-
-Idempotent: only touches rows where post_title IS NULL or empty AND
-description IS NOT NULL. Re-running the migration is a no-op.
-"""
-from __future__ import annotations
-
-import re
-from typing import Sequence, Union
-
-from alembic import op
-from sqlalchemy import text
-
-revision: str = "0024"
-down_revision: Union[str, None] = "0023"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-_TAG_RE = re.compile(r"<[^>]+>")
-_WS_RE = re.compile(r"\s+")
-
-
-def _first_line_text(body: str, limit: int = 120) -> str | None:
-    """Mirror of sidecar._first_line_text. Kept inline so the migration
-    doesn't carry a runtime import dependency from app code that may
-    have moved by the time the migration is replayed years from now."""
-    if not body:
-        return None
-    text_ = _TAG_RE.sub(" ", body)
-    text_ = text_.replace("\xa0", " ")
-    for line in text_.splitlines():
-        line = _WS_RE.sub(" ", line).strip()
-        if line:
-            if len(line) > limit:
-                return line[: limit - 1].rstrip() + "…"
-            return line
-    return None
-
-
-def upgrade() -> None:
-    bind = op.get_bind()
-    rows = bind.execute(
-        text(
-            "SELECT id, description FROM post "
-            "WHERE (post_title IS NULL OR post_title = '') "
-            "AND description IS NOT NULL AND description <> ''"
-        )
-    ).fetchall()
-    updated = 0
-    for row in rows:
-        derived = _first_line_text(row.description)
-        if not derived:
-            continue
-        bind.execute(
-            text("UPDATE post SET post_title = :t WHERE id = :id"),
-            {"t": derived, "id": row.id},
-        )
-        updated += 1
-    print(f"0024: backfilled post_title on {updated} row(s)")
-
-
-def downgrade() -> None:
-    # No safe restore — we can't tell which post_titles were derived vs
-    # genuinely present. Leave the column alone on rollback.
-    pass

alembic/versions/0025_fix_subscribestar_post_ids.py

@@ -1,288 +0,0 @@
-"""sidecar-audit followup: correct external_post_id + post_url across all platforms
-
-Revision ID: 0025
-Revises: 0024
-Create Date: 2026-05-27
-
-Closes the operator-flagged 2026-05-27 sidecar audit findings. Three
-data-correctness bugs across non-Patreon platforms had been silently
-corrupting Posts since FC-3 shipped; the parser fix (sidecar.py, same
-commit) addresses new imports. This migration cleans up existing rows.
-
-Per-platform actions:
-
-  subscribestar — gallery-dl wrote the per-attachment id in `id` and
-    the actual post id in `post_id`. FC's parser picked `id`, so every
-    multi-image SubscribeStar post was fragmented into N Post rows.
-    1. For each SubscribeStar Post, read its sidecar (via the related
-       ImageRecord's on-disk path), pull `post_id`, overwrite
-       external_post_id and post_url.
-    2. Merge groups of Posts under one source that now share an
-       external_post_id (fragments of the same actual post). Same
-       ImageProvenance pre-delete + repoint dance as alembic 0022.
-
-  hentaifoundry — sidecars have NO `url` field; `src` is the image
-    URL. FC's parser stored post_url=NULL. Read each HF Post's sidecar
-    for `user` + `index`, derive the canonical /pictures/user/<u>/<i>
-    permalink. external_post_id (= `index`) was already correct.
-
-  discord — gallery-dl wrote the CDN attachment URL in `url`. FC's
-    parser stored that as post_url. Read each Discord Post's sidecar
-    for the server/channel/message triple, derive the proper
-    discord.com/channels/.../<message> permalink. external_post_id (=
-    `message_id`) was already correct.
-
-  pixiv — pure-SQL backfill: replace any `i.pximg.net`-style URL on
-    Post.post_url with the derived `/artworks/<id>` permalink. Pixiv
-    external_post_id (= `id`) was already correct; no sidecar IO
-    needed.
-
-Idempotent: re-running on already-corrected data is a no-op (skips
-rows whose derived value matches what's already stored).
-
-Posts whose related ImageRecord paths don't resolve on disk (orphaned
-filesystem state) are skipped with a count in the migration output —
-those will be picked up by a future deep-scan.
-"""
-from __future__ import annotations
-
-import json
-import re
-from pathlib import Path
-from typing import Sequence, Union
-
-from alembic import op
-from sqlalchemy import text
-
-revision: str = "0025"
-down_revision: Union[str, None] = "0024"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-# Mirror of sidecar._NUMBERING_PREFIX. Kept inline so the migration is
-# self-contained (the operator's banked rule:
-# reference_postgres_enum_swap_drop_checks.md says migrations shouldn't
-# import from runtime app code).
-_NUMBERING_PREFIX = re.compile(r"^\d+_(.+)$")
-
-
-def _find_sidecar(media_path: Path) -> Path | None:
-    """gallery-dl writes the sidecar under the unprefixed stem
-    (`HOLLOW-ICHIGO.json`) while the media file gets a NN_ ordering
-    prefix (`01_HOLLOW-ICHIGO.png`). Try in order:
-      1. <stem>.json next to the media
-      2. <media>.json next to the media (full-name variant)
-      3. strip the NN_ prefix from the stem, then <stripped>.json
-    """
-    if not media_path:
-        return None
-    cand = media_path.with_suffix(".json")
-    if cand.is_file():
-        return cand
-    cand = media_path.parent / f"{media_path.name}.json"
-    if cand.is_file():
-        return cand
-    m = _NUMBERING_PREFIX.match(media_path.stem)
-    if m:
-        cand = media_path.parent / f"{m.group(1)}.json"
-        if cand.is_file():
-            return cand
-    return None
-
-
-def _str_id(v) -> str | None:
-    """str() a JSON scalar id; reject bool (JSON booleans are ints in
-    Python's eyes but they aren't valid sidecar ids)."""
-    if isinstance(v, bool):
-        return None
-    if isinstance(v, (str, int)) and str(v).strip():
-        return str(v).strip()
-    return None
-
-
-def _str_field(v) -> str | None:
-    if isinstance(v, str) and v.strip():
-        return v.strip()
-    return None
-
-
-def upgrade() -> None:
-    conn = op.get_bind()
-
-    # ── PART 1: Per-platform corrections requiring filesystem IO ─────
-    # SubscribeStar, HentaiFoundry, Discord all need fields from the
-    # sidecar to construct the right post_url. We walk each Post's
-    # related ImageRecord.path to find the sidecar, read it, derive,
-    # and update.
-    targets = conn.execute(text("""
-        SELECT p.id, p.external_post_id, p.post_url, s.platform
-        FROM post p
-        JOIN source s ON s.id = p.source_id
-        WHERE s.platform IN ('subscribestar', 'hentaifoundry', 'discord')
-    """)).fetchall()
-
-    stats: dict[str, dict[str, int]] = {
-        plat: {"read": 0, "updated": 0, "no_sidecar": 0}
-        for plat in ("subscribestar", "hentaifoundry", "discord")
-    }
-    for post_row in targets:
-        plat = post_row.platform
-        path = _first_attachment_path(conn, post_row.id)
-        if not path:
-            stats[plat]["no_sidecar"] += 1
-            continue
-        sidecar = _find_sidecar(Path(path))
-        if sidecar is None:
-            stats[plat]["no_sidecar"] += 1
-            continue
-        try:
-            data = json.loads(sidecar.read_text(encoding="utf-8"))
-        except (OSError, json.JSONDecodeError):
-            stats[plat]["no_sidecar"] += 1
-            continue
-        stats[plat]["read"] += 1
-
-        new_epid = post_row.external_post_id
-        new_url = None
-        if plat == "subscribestar":
-            pid = _str_id(data.get("post_id"))
-            if pid:
-                new_epid = pid
-                new_url = f"https://www.subscribestar.com/posts/{pid}"
-        elif plat == "hentaifoundry":
-            user = _str_field(data.get("user")) or _str_field(data.get("artist"))
-            idx = _str_id(data.get("index"))
-            if user and idx:
-                new_url = f"https://www.hentai-foundry.com/pictures/user/{user}/{idx}"
-        elif plat == "discord":
-            sid = _str_id(data.get("server_id"))
-            cid = _str_id(data.get("channel_id"))
-            mid = _str_id(data.get("message_id"))
-            if sid and cid and mid:
-                new_url = f"https://discord.com/channels/{sid}/{cid}/{mid}"
-
-        # Idempotent: skip if nothing changed.
-        if new_epid == post_row.external_post_id and new_url == post_row.post_url:
-            continue
-        conn.execute(
-            text("""
-                UPDATE post
-                SET external_post_id = :epid, post_url = :url
-                WHERE id = :id
-            """),
-            {"epid": new_epid, "url": new_url, "id": post_row.id},
-        )
-        stats[plat]["updated"] += 1
-
-    for plat, s in stats.items():
-        print(
-            f"0025: {plat} — read {s['read']} sidecars, "
-            f"updated {s['updated']} Posts, "
-            f"{s['no_sidecar']} Posts had no resolvable sidecar"
-        )
-
-    # ── PART 2: Merge SubscribeStar fragments now sharing epid ───────
-    # After Part 1, each group of Posts under one source with the SAME
-    # new external_post_id is a fragment-set of the same actual post.
-    # Merge to one canonical row. Pre-handle the same ImageProvenance
-    # collision pattern as alembic 0022 (uq_image_provenance_image_post).
-    fragment_groups = conn.execute(text("""
-        SELECT p.source_id, p.external_post_id,
-               ARRAY_AGG(p.id ORDER BY p.id ASC) AS post_ids
-        FROM post p
-        JOIN source s ON s.id = p.source_id
-        WHERE s.platform = 'subscribestar'
-          AND p.external_post_id IS NOT NULL
-        GROUP BY p.source_id, p.external_post_id
-        HAVING COUNT(*) > 1
-    """)).fetchall()
-
-    merged = 0
-    for grp in fragment_groups:
-        post_ids = list(grp.post_ids)
-        keep_id, *drop_ids = post_ids
-        for drop_id in drop_ids:
-            # Pre-DELETE colliding ImageProvenance under drop_ that
-            # already exist under keep (alembic 0022 banked the pattern).
-            conn.execute(
-                text("""
-                    DELETE FROM image_provenance
-                    WHERE post_id = :drop_
-                      AND image_record_id IN (
-                          SELECT image_record_id FROM image_provenance
-                          WHERE post_id = :keep
-                      )
-                """),
-                {"keep": keep_id, "drop_": drop_id},
-            )
-            conn.execute(
-                text("""
-                    UPDATE image_provenance SET post_id = :keep
-                    WHERE post_id = :drop_
-                """),
-                {"keep": keep_id, "drop_": drop_id},
-            )
-            conn.execute(
-                text("""
-                    UPDATE image_record SET primary_post_id = :keep
-                    WHERE primary_post_id = :drop_
-                """),
-                {"keep": keep_id, "drop_": drop_id},
-            )
-            conn.execute(
-                text("""
-                    UPDATE post_attachment SET post_id = :keep
-                    WHERE post_id = :drop_
-                """),
-                {"keep": keep_id, "drop_": drop_id},
-            )
-            conn.execute(
-                text("DELETE FROM post WHERE id = :drop_"),
-                {"drop_": drop_id},
-            )
-            merged += 1
-    print(f"0025: subscribestar — merged {merged} duplicate Post fragments")
-
-    # ── PART 3: Pixiv post_url backfill (pure SQL) ───────────────────
-    # Pixiv's external_post_id is already correct (gallery-dl's `id` is
-    # the post id). Only post_url needs derivation: replace anything
-    # under i.pximg.net (the file URL) with the /artworks/<id> permalink.
-    pixiv_updated = conn.execute(text("""
-        UPDATE post p
-        SET post_url = 'https://www.pixiv.net/artworks/' || p.external_post_id
-        FROM source s
-        WHERE p.source_id = s.id
-          AND s.platform = 'pixiv'
-          AND p.external_post_id IS NOT NULL
-          AND (p.post_url IS NULL
-               OR p.post_url LIKE 'https://i.pximg.net/%'
-               OR p.post_url LIKE 'http://i.pximg.net/%')
-    """)).rowcount
-    print(f"0025: pixiv — backfilled post_url on {pixiv_updated} Posts")
-
-
-def _first_attachment_path(conn, post_id: int) -> str | None:
-    """Return any ImageRecord.path attached to this post (via
-    ImageProvenance). Lowest-id row keeps the migration deterministic
-    so re-running on the same DB picks the same sidecar."""
-    row = conn.execute(
-        text("""
-            SELECT ir.path
-            FROM image_provenance ip
-            JOIN image_record ir ON ir.id = ip.image_record_id
-            WHERE ip.post_id = :pid
-            ORDER BY ip.id ASC
-            LIMIT 1
-        """),
-        {"pid": post_id},
-    ).first()
-    return row[0] if row else None
-
-
-def downgrade() -> None:
-    # Lossy: external_post_id values were overwritten with the correct
-    # post_id; original per-attachment ids weren't preserved. Post-merge
-    # also deleted drop rows. No safe restore. To roll back the schema
-    # invariant, fork from 0024 and re-run sidecar imports.
-    pass

alembic/versions/0026_import_task_recovery_count_refetched.py

@@ -1,53 +0,0 @@
-"""import_task.recovery_count + refetched — poison-pill circuit breaker
-
-Revision ID: 0026
-Revises: 0025
-Create Date: 2026-05-28
-
-Backs the import-task resilience work (operator-flagged 2026-05-28):
-
-- recovery_count: how many times recover_interrupted_tasks has
-  re-queued this row from a stuck 'processing' state. A row that
-  hard-crashes the worker (OOM / segfault on a corrupt or oversized
-  input) leaves no terminal flip, so the sweep re-queues it — and
-  without a cap it would loop forever, re-crashing the worker each
-  time. After MAX_RECOVERY_ATTEMPTS the sweep marks it 'failed' with a
-  diagnostic instead.
-
-- refetched: whether a one-shot re-download has already been attempted
-  for this task's file. Bounds the Layer-2 re-fetch remediation to a
-  single attempt so source-side corruption doesn't loop.
-
-Both default to 0 / false; additive, no backfill needed.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0026"
-down_revision: Union[str, None] = "0025"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "import_task",
-        sa.Column(
-            "recovery_count", sa.Integer(), nullable=False,
-            server_default="0",
-        ),
-    )
-    op.add_column(
-        "import_task",
-        sa.Column(
-            "refetched", sa.Boolean(), nullable=False,
-            server_default=sa.false(),
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("import_task", "refetched")
-    op.drop_column("import_task", "recovery_count")

alembic/versions/0027_drop_migration_run.py

@@ -1,50 +0,0 @@
-"""drop migration_run — one-and-done GS/IR migration tooling removed
-
-Revision ID: 0027
-Revises: 0026
-Create Date: 2026-05-29
-
-The GS/IR migration tooling (services/migrators, /api/migrate, the
-run_migration task, LegacyMigrationCard, and the MigrationRun model) was
-removed after the migration cutover completed. This drops its now-orphaned
-run-log table. Downgrade recreates the table (mirrors the old model) so the
-migration is reversible.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-from sqlalchemy.dialects.postgresql import JSONB
-
-revision: str = "0027"
-down_revision: Union[str, None] = "0026"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.drop_table("migration_run")
-
-
-def downgrade() -> None:
-    op.create_table(
-        "migration_run",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column("kind", sa.String(length=32), nullable=False),
-        sa.Column("status", sa.String(length=32), nullable=False),
-        sa.Column("dry_run", sa.Boolean(), nullable=False, server_default=sa.false()),
-        sa.Column(
-            "started_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column(
-            "counts", JSONB(), nullable=False, server_default=sa.text("'{}'::jsonb"),
-        ),
-        sa.Column("error", sa.Text(), nullable=True),
-        sa.Column(
-            "metadata", JSONB(), nullable=False, server_default=sa.text("'{}'::jsonb"),
-        ),
-    )
-    op.create_index("ix_migration_run_kind", "migration_run", ["kind"])
-    op.create_index("ix_migration_run_status", "migration_run", ["status"])

alembic/versions/0028_collapse_sidecar_synthetics_into_real_sources.py

@@ -1,190 +0,0 @@
-"""collapse-sidecar-synthetic: repoint Posts/ImageProvenance/DownloadEvents
-from `sidecar:<platform>:<slug>` synthetic Source anchors onto the real
-Source for the same (artist, platform) when one exists, then delete the
-synthetic.
-
-Revision ID: 0028
-Revises: 0027
-Create Date: 2026-05-31
-
-Background: alembic 0022 (2026-05-26) consolidated the old per-post-URL
-Source rows into one canonical Source per (artist, platform). When NO
-real campaign URL was salvageable among the candidates, it rewrote the
-canonical row to url='sidecar:<platform>:<slug>' enabled=false as a
-disabled anchor for any Posts already attached.
-
-That was fine while it was the only Source for that artist+platform.
-But: the unique constraint on Source is (artist_id, platform, url), not
-(artist_id, platform). When the operator later added the real
-subscription via the UI / extension / etc., a SECOND row landed —
-the real one — with id > the synthetic. Both coexisted.
-
-Two follow-on problems surfaced 2026-05-31:
-
-  1. The Subscriptions UI listed both rows. The synthetic was disabled
-     so the scheduler never polled it, but it looked like a phantom
-     subscription. (Fixed in same commit by SourceService.list filter.)
-  2. importer._source_for_sidecar picked Source by `ORDER BY id ASC
-     LIMIT 1`, so EVERY gallery-dl download since the real Source was
-     added attached its Post to the SYNTHETIC anchor, not the real
-     Source. (Fixed in same commit by preferring non-sidecar URLs.)
-
-This migration is the data half of the cleanup: for every (artist,
-platform) with both a synthetic AND a real Source, repoint the
-synthetic's children (Posts, ImageProvenance, DownloadEvents) onto the
-real Source and delete the synthetic. Reuses the same epid/provenance
-collision dance from alembic 0022 because the same uniqueness
-constraints fire row-by-row during bulk UPDATEs.
-
-Lone synthetic anchors — those where no real Source for the same
-(artist, platform) exists (e.g., filesystem-imported artist with no
-subscription added) — are LEFT INTACT. They anchor real imported
-content; deleting them would CASCADE-delete the Posts the operator
-imported. The SourceService.list filter hides them from the UI; the
-operator can delete them by hand if they want the underlying imports
-gone.
-"""
-from typing import Sequence, Union
-
-from alembic import op
-from sqlalchemy import text
-
-revision: str = "0028"
-down_revision: Union[str, None] = "0027"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    conn = op.get_bind()
-
-    # Find (artist_id, platform) groups where BOTH a sidecar synthetic
-    # and at least one real Source exist.
-    groups = conn.execute(text("""
-        SELECT artist_id, platform
-        FROM source
-        GROUP BY artist_id, platform
-        HAVING bool_or(url LIKE 'sidecar:%')
-           AND bool_or(url NOT LIKE 'sidecar:%')
-    """)).fetchall()
-
-    for artist_id, platform in groups:
-        rows = conn.execute(
-            text("""
-                SELECT id, url FROM source
-                WHERE artist_id = :a AND platform = :p
-                ORDER BY id ASC
-            """),
-            {"a": artist_id, "p": platform},
-        ).fetchall()
-
-        synthetic_ids = [sid for sid, url in rows if url.startswith("sidecar:")]
-        real_rows = [(sid, url) for sid, url in rows if not url.startswith("sidecar:")]
-        if not synthetic_ids or not real_rows:
-            continue  # belt+suspenders; the GROUP BY already filtered
-
-        # Canonical real: lowest-id non-sidecar Source.
-        canonical_id = real_rows[0][0]
-
-        # STEP A: PRE-merge Post collisions on (canonical, external_post_id).
-        # Mirror alembic 0022's pre-merge logic — when synth has Post X
-        # epid=N and real has Post Y epid=N, the bulk UPDATE below would
-        # trip uq_post_source_external_id row-by-row. Group all Posts
-        # under (canonical + synthetics) by epid; for any group >1,
-        # pick a keep (prefer one already under canonical, else lowest
-        # id) and merge the rest into it.
-        all_posts = conn.execute(
-            text("""
-                SELECT external_post_id, id, source_id
-                FROM post
-                WHERE source_id = :canonical OR source_id = ANY(:synths)
-                ORDER BY external_post_id, id
-            """),
-            {"canonical": canonical_id, "synths": synthetic_ids},
-        ).fetchall()
-        by_epid: dict = {}
-        for epid, post_id, src_id in all_posts:
-            by_epid.setdefault(epid, []).append((post_id, src_id))
-        for _epid, posts in by_epid.items():
-            if len(posts) <= 1:
-                continue
-            canonical_side = [p for p in posts if p[1] == canonical_id]
-            keep_id = canonical_side[0][0] if canonical_side else posts[0][0]
-            drop_ids = [p[0] for p in posts if p[0] != keep_id]
-            for drop_id in drop_ids:
-                # Pre-delete image_provenance rows under drop_ whose
-                # image_record_id already has provenance under keep —
-                # avoids tripping uq_image_provenance_image_post (0021)
-                # row-by-row during the repoint UPDATE.
-                conn.execute(
-                    text("""
-                        DELETE FROM image_provenance
-                        WHERE post_id = :drop_
-                          AND image_record_id IN (
-                              SELECT image_record_id FROM image_provenance
-                              WHERE post_id = :keep
-                          )
-                    """),
-                    {"keep": keep_id, "drop_": drop_id},
-                )
-                conn.execute(
-                    text("""
-                        UPDATE image_provenance SET post_id = :keep
-                        WHERE post_id = :drop_
-                    """),
-                    {"keep": keep_id, "drop_": drop_id},
-                )
-                conn.execute(
-                    text("""
-                        UPDATE image_record SET primary_post_id = :keep
-                        WHERE primary_post_id = :drop_
-                    """),
-                    {"keep": keep_id, "drop_": drop_id},
-                )
-                conn.execute(
-                    text("DELETE FROM post WHERE id = :drop_"),
-                    {"drop_": drop_id},
-                )
-
-        # STEP B: Bulk reparent the remaining Posts off the synthetics.
-        conn.execute(
-            text("""
-                UPDATE post SET source_id = :canonical
-                WHERE source_id = ANY(:synths)
-            """),
-            {"canonical": canonical_id, "synths": synthetic_ids},
-        )
-
-        # STEP C: Reparent ImageProvenance.source_id (denormalized FK;
-        # no UNIQUE on source_id, safe bulk).
-        conn.execute(
-            text("""
-                UPDATE image_provenance SET source_id = :canonical
-                WHERE source_id = ANY(:synths)
-            """),
-            {"canonical": canonical_id, "synths": synthetic_ids},
-        )
-
-        # STEP D: Reparent any DownloadEvent.source_id. Synthetics are
-        # enabled=false so the scheduler never created events for them;
-        # this is belt+suspenders for any rows planted by manual force
-        # or older code paths.
-        conn.execute(
-            text("""
-                UPDATE download_event SET source_id = :canonical
-                WHERE source_id = ANY(:synths)
-            """),
-            {"canonical": canonical_id, "synths": synthetic_ids},
-        )
-
-        # STEP E: Drop the now-empty synthetics.
-        conn.execute(
-            text("DELETE FROM source WHERE id = ANY(:synths)"),
-            {"synths": synthetic_ids},
-        )
-
-
-def downgrade() -> None:
-    # Lossy migration — synthetic Sources deleted, Posts repointed and
-    # potentially merged. No safe downgrade.
-    pass

alembic/versions/0029_drop_artist_copyright_ml_thresholds.py

@@ -1,71 +0,0 @@
-"""drop artist + copyright ml thresholds; lower general default to 0.50
-
-Revision ID: 0029
-Revises: 0028
-Create Date: 2026-06-01
-
-Operator-flagged 2026-06-01: the view modal's Suggestions panel hides
-most general-category predictions because the default threshold is
-0.95. Lowering the default to 0.50 (matches character) so general
-suggestions surface more aggressively; the value remains tunable in
-Settings → ML.
-
-Same change retires two ML suggestion categories whose Tag.kind
-surfaces are unused:
-
-- `artist`: retired in FC-2d-vii-c — artist identity is acquisition-
-  derived (image_record.artist_id), never ML-inferred. The threshold
-  column was a leftover from before that retirement.
-- `copyright`: retired 2026-06-01 — the app uses `fandom` for the
-  franchise/copyright concept (per TagsView.vue's doc comment); no
-  Tag rows of kind=copyright exist, and the threshold column never
-  fed anything user-visible.
-
-Both columns are dropped from ml_settings; the existing row's
-suggestion_threshold_general value is bumped from 0.95 to 0.50 iff
-it's still at the old default, so deployed installs pick up the new
-UX without overriding any operator tuning.
-"""
-from typing import Sequence, Union
-
-from alembic import op
-from sqlalchemy import text
-
-revision: str = "0029"
-down_revision: Union[str, None] = "0028"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Bump the general threshold for installs still at the old default.
-    op.execute(text(
-        "UPDATE ml_settings "
-        "SET suggestion_threshold_general = 0.50 "
-        "WHERE id = 1 AND suggestion_threshold_general = 0.95"
-    ))
-    op.drop_column("ml_settings", "suggestion_threshold_artist")
-    op.drop_column("ml_settings", "suggestion_threshold_copyright")
-
-
-def downgrade() -> None:
-    # Restore the columns with their prior defaults. The bump from
-    # 0.95 → 0.50 isn't reversible without remembering whether the
-    # operator had explicitly set 0.95 (unlikely — that was just the
-    # default) so we leave the current general value as-is.
-    from sqlalchemy import Column, Float
-
-    op.add_column(
-        "ml_settings",
-        Column(
-            "suggestion_threshold_artist",
-            Float, nullable=False, server_default="0.30",
-        ),
-    )
-    op.add_column(
-        "ml_settings",
-        Column(
-            "suggestion_threshold_copyright",
-            Float, nullable=False, server_default="0.50",
-        ),
-    )

alembic/versions/0030_nullable_post_source_id_denorm_artist_id.py

@@ -1,145 +0,0 @@
-"""nullable post.source_id + denormalized post.artist_id; retire sidecar synthetics
-
-Revision ID: 0030
-Revises: 0029
-Create Date: 2026-06-01
-
-Operator-asked 2026-06-01 after the Dymkens orphan investigation: the
-sidecar synthetic Source pattern (`sidecar:<platform>:<slug>` rows
-with enabled=false) was technically correct but misled the operator
-into thinking they had phantom subscriptions. The synthetics existed
-solely to satisfy `Post.source_id NOT NULL` for filesystem-imported
-content with no real subscription.
-
-This migration makes the data model honest:
-
-1. **Post gets a denormalized `artist_id` column** so artist filters
-   work without traversing `Post → Source.artist_id`. Backfilled from
-   the existing Source linkage, then NOT NULL'd.
-2. **`Post.source_id` becomes nullable**, FK ondelete `CASCADE` → `SET
-   NULL`. Deleting a Source detaches its Posts instead of destroying
-   imported content (semantically: subscription ends, archive stays).
-3. **`ImageProvenance.source_id` becomes nullable** with the same FK
-   semantic change.
-4. **Sidecar synthetic Sources are deleted** — first NULL out the
-   FKs from Post + ImageProvenance pointing at them (so the implicit
-   CASCADE doesn't fire), then delete. DownloadEvent FK is unchanged
-   (still CASCADE'd, NOT NULL'd) — synthetics have `enabled=false`
-   so no events exist for them.
-
-Uniqueness handling: the existing `uq_post_source_external_id`
-(source_id, external_post_id) keeps working for source-bound Posts
-(Postgres treats NULL != NULL so NULL-source rows aren't deduped by
-it). A second partial unique index covers the NULL-source case on
-(artist_id, external_post_id) so filesystem-imported posts still
-dedupe within an artist.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-from sqlalchemy import text
-
-revision: str = "0030"
-down_revision: Union[str, None] = "0029"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    conn = op.get_bind()
-
-    # Step 1: add Post.artist_id, initially nullable for backfill.
-    # FK naming follows the Base.metadata naming_convention
-    # (fk_<table>_<column>_<referred_table>) — alembic 0001 set this up.
-    op.add_column(
-        "post",
-        sa.Column("artist_id", sa.Integer, nullable=True),
-    )
-    op.create_foreign_key(
-        "fk_post_artist_id_artist", "post", "artist",
-        ["artist_id"], ["id"], ondelete="CASCADE",
-    )
-
-    # Step 2: backfill from Source.artist_id (every existing Post has a
-    # Source today, so every row gets populated).
-    conn.execute(text("""
-        UPDATE post p
-        SET artist_id = s.artist_id
-        FROM source s
-        WHERE p.source_id = s.id AND p.artist_id IS NULL
-    """))
-
-    # Sanity: count any remaining NULLs. Should be zero pre-this-migration.
-    remaining = conn.execute(text(
-        "SELECT COUNT(*) FROM post WHERE artist_id IS NULL"
-    )).scalar_one()
-    if remaining:
-        raise RuntimeError(
-            f"alembic 0030: {remaining} post rows have no resolvable "
-            f"artist_id after backfill. Investigate before continuing."
-        )
-
-    # Step 3: enforce NOT NULL + add index for artist-filter queries.
-    op.alter_column("post", "artist_id", nullable=False)
-    op.create_index("ix_post_artist_id", "post", ["artist_id"])
-
-    # Step 4: relax post.source_id + flip FK to SET NULL. The original FK
-    # name from alembic 0001 is `fk_post_source_id_source` per the
-    # NAMING_CONVENTION in models/base.py.
-    op.alter_column("post", "source_id", nullable=True)
-    op.drop_constraint("fk_post_source_id_source", "post", type_="foreignkey")
-    op.create_foreign_key(
-        "fk_post_source_id_source", "post", "source",
-        ["source_id"], ["id"], ondelete="SET NULL",
-    )
-
-    # Step 5: relax image_provenance.source_id + flip FK to SET NULL.
-    op.alter_column("image_provenance", "source_id", nullable=True)
-    op.drop_constraint(
-        "fk_image_provenance_source_id_source", "image_provenance",
-        type_="foreignkey",
-    )
-    op.create_foreign_key(
-        "fk_image_provenance_source_id_source", "image_provenance", "source",
-        ["source_id"], ["id"], ondelete="SET NULL",
-    )
-
-    # Step 6: partial unique index on (artist_id, external_post_id) for
-    # NULL-source Posts. The existing uq_post_source_external_id keeps
-    # guarding source-bound rows; NULL-source rows now dedupe within
-    # an artist.
-    op.execute(
-        "CREATE UNIQUE INDEX uq_post_artist_external_id_null_source "
-        "ON post (artist_id, external_post_id) "
-        "WHERE source_id IS NULL"
-    )
-
-    # Step 7: retire sidecar synthetic Sources. NULL out the references
-    # FIRST (the new FK is SET NULL so CASCADE wouldn't fire anyway, but
-    # being explicit makes the intent clear). Then delete the synthetic
-    # source rows. Any DownloadEvent rows under synthetics CASCADE-die
-    # with the source — synthetics have enabled=false so there shouldn't
-    # be any in practice.
-    conn.execute(text("""
-        UPDATE post
-        SET source_id = NULL
-        WHERE source_id IN (SELECT id FROM source WHERE url LIKE 'sidecar:%')
-    """))
-    conn.execute(text("""
-        UPDATE image_provenance
-        SET source_id = NULL
-        WHERE source_id IN (SELECT id FROM source WHERE url LIKE 'sidecar:%')
-    """))
-    deleted = conn.execute(text(
-        "DELETE FROM source WHERE url LIKE 'sidecar:%' RETURNING id"
-    )).rowcount
-    print(f"alembic 0030: deleted {deleted} sidecar synthetic source rows")
-
-
-def downgrade() -> None:
-    # Lossy migration — the deleted sidecar synthetics can't be
-    # restored from the orphan post.source_id / image_provenance.source_id
-    # values, and the partial unique index encodes a constraint that
-    # NULL-source Posts may now exist. No safe downgrade.
-    pass

alembic/versions/0031_source_backfill_runs_remaining.py

@@ -1,45 +0,0 @@
-"""source.backfill_runs_remaining: sticky deep-scan mode
-
-Revision ID: 0031
-Revises: 0030
-Create Date: 2026-06-01
-
-Tick vs backfill mode for subscription downloads. When
-`backfill_runs_remaining > 0`, the next N download runs use
-`skip: True` + 30-min timeout (walk full history). When 0, runs use
-`skip: "exit:20"` + 14.5-min timeout (catch-up mode, exits early once
-20 contiguous archived items are seen).
-
-Operator-flagged 2026-06-01 (Knuxy run #38887): a creator with ~550
-archived posts saturates the 870s catch-up timeout even when there is
-no new content, because gallery-dl's default `skip: True` keeps walking.
-Tick mode short-circuits that; backfill mode is the explicit opt-in for
-deep history scans.
-
-Default 0 (all existing subscriptions start in tick mode).
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0031"
-down_revision: Union[str, None] = "0030"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "source",
-        sa.Column(
-            "backfill_runs_remaining",
-            sa.Integer,
-            nullable=False,
-            server_default="0",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("source", "backfill_runs_remaining")

alembic/versions/0032_source_error_type.py

@@ -1,41 +0,0 @@
-"""source.error_type: surface ErrorType taxonomy in FailingSourcesCard
-
-Revision ID: 0032
-Revises: 0031
-Create Date: 2026-06-02
-
-Audit 2026-06-02: the backend computes 13 ErrorType categories (auth_error,
-rate_limited, not_found, access_denied, validation_failed, etc.) and
-stamps each one on DownloadEvent.metadata, but the Source row only carried
-the free-text last_error. Operators couldn't bulk-triage failing sources
-("all auth_error → rotate cookies, all rate_limited → just wait") without
-opening Logs per row.
-
-This column receives the last error_type from _update_source_health
-and gets cleared on a successful run. Nullable + indexed so the failing-
-sources rollup can filter/group cheaply.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0032"
-down_revision: Union[str, None] = "0031"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "source",
-        sa.Column("error_type", sa.String(length=32), nullable=True),
-    )
-    op.create_index(
-        "ix_source_error_type", "source", ["error_type"],
-    )
-
-
-def downgrade() -> None:
-    op.drop_index("ix_source_error_type", table_name="source")
-    op.drop_column("source", "error_type")

alembic/versions/0033_suggestion_threshold_default_070.py

@@ -1,48 +0,0 @@
-"""suggestion_threshold default 0.50 → 0.70
-
-Revision ID: 0033
-Revises: 0032
-Create Date: 2026-06-02
-
-Operator-flagged 2026-06-02 — the 0.50 default (set on 2026-06-01) is
-too noisy in practice; raise to 0.70 for both suggestion categories.
-
-Only conditionally updates singletons whose current value is still the
-2026-06-01 default (0.50). Operators who deliberately tuned their row
-to some other value (0.55, 0.65, 0.80, etc. via the Settings UI) keep
-their pick — the migration only catches the unchanged-default case.
-"""
-from typing import Sequence, Union
-
-from alembic import op
-
-revision: str = "0033"
-down_revision: Union[str, None] = "0032"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.execute(
-        "UPDATE ml_settings "
-        "SET suggestion_threshold_character = 0.70 "
-        "WHERE id = 1 AND suggestion_threshold_character = 0.50"
-    )
-    op.execute(
-        "UPDATE ml_settings "
-        "SET suggestion_threshold_general = 0.70 "
-        "WHERE id = 1 AND suggestion_threshold_general = 0.50"
-    )
-
-
-def downgrade() -> None:
-    op.execute(
-        "UPDATE ml_settings "
-        "SET suggestion_threshold_character = 0.50 "
-        "WHERE id = 1 AND suggestion_threshold_character = 0.70"
-    )
-    op.execute(
-        "UPDATE ml_settings "
-        "SET suggestion_threshold_general = 0.50 "
-        "WHERE id = 1 AND suggestion_threshold_general = 0.70"
-    )

alembic/versions/0034_artist_visit.py

@@ -1,53 +0,0 @@
-"""artist_visit: per-artist last-viewed timestamp for the "+N new" badge
-
-Revision ID: 0034
-Revises: 0033
-Create Date: 2026-06-03
-
-Powers the artists-directory "+N new since last visit" badge + ArtistView
-banner. Single row per artist (no user_id yet — rule #47 multi-user ACL
-is aspirational; widens to (user_id, artist_id) PK when User lands).
-
-Seed every existing artist with `last_viewed_at = NOW()` so the badge
-starts at 0 across the board — no noisy "you have 5000 unseen images"
-on first deploy. New artists auto-get a row via
-`ArtistService.find_or_create`.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0034"
-down_revision: Union[str, None] = "0033"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "artist_visit",
-        sa.Column(
-            "artist_id",
-            sa.Integer,
-            sa.ForeignKey("artist.id", ondelete="CASCADE"),
-            primary_key=True,
-        ),
-        sa.Column(
-            "last_viewed_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("NOW()"),
-        ),
-    )
-    # Seed: every existing artist starts "fully caught up". Without this,
-    # every operator with N artists would see N badges (worth of every
-    # image ever imported) on first deploy.
-    op.execute(
-        "INSERT INTO artist_visit (artist_id, last_viewed_at) "
-        "SELECT id, NOW() FROM artist"
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("artist_visit")

alembic/versions/0035_image_record_effective_date.py

@@ -1,70 +0,0 @@
-"""image_record.effective_date: materialized gallery sort key + index
-
-Revision ID: 0035
-Revises: 0034
-Create Date: 2026-06-04
-
-The gallery ordered/cursored on COALESCE(post.post_date,
-image_record.created_at) across the Post outer join. That expression spans
-two tables, so no index can serve it — every /scroll sorted a large slice
-of the library, and the frontend fired ten of them serially per initial
-load. Materialize the value into image_record.effective_date and index
-(effective_date DESC, id DESC) so the cursor scroll is an index range scan.
-
-Backfill = COALESCE(primary post's post_date, created_at) so existing rows
-keep their exact ordering. New rows get the created_at-equivalent server
-default; services/importer.py overrides it with the post's date when a
-primary post with a date is linked.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0035"
-down_revision: Union[str, None] = "0034"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Add nullable first so the backfill can populate before NOT NULL.
-    op.add_column(
-        "image_record",
-        sa.Column("effective_date", sa.DateTime(timezone=True), nullable=True),
-    )
-    # Pure set-based UPDATEs (no per-row params) — immune to the 65535
-    # bind-parameter ceiling regardless of library size.
-    op.execute(
-        """
-        UPDATE image_record AS ir
-        SET effective_date = COALESCE(p.post_date, ir.created_at)
-        FROM post AS p
-        WHERE ir.primary_post_id = p.id
-        """
-    )
-    op.execute(
-        """
-        UPDATE image_record
-        SET effective_date = created_at
-        WHERE effective_date IS NULL
-        """
-    )
-    op.alter_column(
-        "image_record",
-        "effective_date",
-        nullable=False,
-        server_default=sa.text("now()"),
-    )
-    # DESC/DESC matches the gallery's ORDER BY effective_date DESC, id DESC
-    # so the scroll is a forward index scan; raw SQL because alembic's
-    # column list doesn't express per-column DESC cleanly.
-    op.execute(
-        "CREATE INDEX ix_image_record_effective_date "
-        "ON image_record (effective_date DESC, id DESC)"
-    )
-
-
-def downgrade() -> None:
-    op.drop_index("ix_image_record_effective_date", table_name="image_record")
-    op.drop_column("image_record", "effective_date")

alembic/versions/0036_siglip_embedding_hnsw_index.py

@@ -1,41 +0,0 @@
-"""image_record.siglip_embedding: HNSW cosine index for "more like this"
-
-Revision ID: 0036
-Revises: 0035
-Create Date: 2026-06-04
-
-Gallery Phase 3 (visual similarity search) ranks images by
-`siglip_embedding.cosine_distance(source_embedding)`. Without an index that's
-a sequential scan computing a 1152-dim distance for every row — fine at small
-scale, but it grows linearly with the library. Add an HNSW index with
-`vector_cosine_ops` so the top-N nearest search is sub-50ms ANN.
-
-1152 dims is under pgvector's 2000-dim HNSW limit, so HNSW (no training,
-better recall than IVFFlat) is the right choice. ONE-TIME COST: building the
-index over the existing embeddings (~57k vectors on the operator's library)
-locks image_record for ~30-60s during this migration on deploy — acceptable
-for a single-operator homelab. NULL embeddings (videos / not-yet-embedded
-rows) are simply not indexed.
-"""
-from typing import Sequence, Union
-
-from alembic import op
-
-revision: str = "0036"
-down_revision: Union[str, None] = "0035"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Raw SQL: alembic's create_index doesn't express the `USING hnsw (...
-    # vector_cosine_ops)` access-method + opclass cleanly. Must match the
-    # query's cosine_distance operator class to be usable by the planner.
-    op.execute(
-        "CREATE INDEX ix_image_record_siglip_hnsw "
-        "ON image_record USING hnsw (siglip_embedding vector_cosine_ops)"
-    )
-
-
-def downgrade() -> None:
-    op.drop_index("ix_image_record_siglip_hnsw", table_name="image_record")

alembic/versions/0037_patreon_seen_media.py

@@ -1,53 +0,0 @@
-"""patreon_seen_media: per-source ledger of already-ingested Patreon media
-
-Revision ID: 0037
-Revises: 0036
-Create Date: 2026-06-05
-
-Native Patreon ingester (build step 2a). Replaces gallery-dl's
-archive.sqlite3 with our own queryable table. The downloader upserts one
-row per (source, media) so routine walks skip media we've already
-processed; a future "recovery" mode bypasses the ledger to re-walk.
-
-`filehash` is a 32-hex Patreon CDN MD5, OR a video sentinel of the form
-``video:<post_id>:<media_id>`` — hence String(128). The unique
-constraint on (source_id, filehash) is the dedup upsert key.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0037"
-down_revision: Union[str, None] = "0036"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "patreon_seen_media",
-        sa.Column("id", sa.Integer, primary_key=True),
-        sa.Column(
-            "source_id",
-            sa.Integer,
-            sa.ForeignKey("source.id", ondelete="CASCADE"),
-            nullable=False,
-            index=True,
-        ),
-        sa.Column("filehash", sa.String(128), nullable=False),
-        sa.Column("post_id", sa.String(64), nullable=True),
-        sa.Column(
-            "seen_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("NOW()"),
-        ),
-        sa.UniqueConstraint(
-            "source_id", "filehash", name="uq_patreon_seen_media_source_id"
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("patreon_seen_media")

alembic/versions/0038_patreon_failed_media.py

@@ -1,58 +0,0 @@
-"""patreon_failed_media: per-source dead-letter ledger for failing Patreon media
-
-Revision ID: 0038
-Revises: 0037
-Create Date: 2026-06-06
-
-Plan #705 (#7). Media that keeps failing to download/validate (404'd CDN,
-deleted post, geo-blocked Mux, persistently-corrupt bytes) gets recorded here
-with an attempt counter; once it crosses the dead-letter threshold the ingester
-skips it on routine walks (recovery still re-attempts). A clean download clears
-the row. UNIQUE (source_id, filehash) is the upsert key (same media key the
-seen-ledger uses).
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0038"
-down_revision: Union[str, None] = "0037"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "patreon_failed_media",
-        sa.Column("id", sa.Integer, primary_key=True),
-        sa.Column(
-            "source_id",
-            sa.Integer,
-            sa.ForeignKey("source.id", ondelete="CASCADE"),
-            nullable=False,
-            index=True,
-        ),
-        sa.Column("filehash", sa.String(128), nullable=False),
-        sa.Column("attempts", sa.Integer, nullable=False, server_default="1"),
-        sa.Column("last_error", sa.Text, nullable=True),
-        sa.Column(
-            "first_failed_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("NOW()"),
-        ),
-        sa.Column(
-            "last_failed_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("NOW()"),
-        ),
-        sa.UniqueConstraint(
-            "source_id", "filehash", name="uq_patreon_failed_media_source_id"
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("patreon_failed_media")

alembic/versions/0039_library_audit_resume.py

@@ -1,40 +0,0 @@
-"""library_audit_run: resume cursor + progress timestamp for chunked scans
-
-Revision ID: 0039
-Revises: 0038
-Create Date: 2026-06-07
-
-scan_library_for_rule used to run one 2h pass that timed out on large libraries
-and monopolized the concurrency-1 maintenance queue (operator-flagged). It now
-runs short time-boxed chunks that re-enqueue: `resume_after_id` persists the
-keyset cursor so the next chunk continues where it left off, and
-`last_progress_at` lets the recovery sweep tell a progressing multi-chunk audit
-from a genuinely stuck one.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0039"
-down_revision: Union[str, None] = "0038"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "library_audit_run",
-        sa.Column(
-            "resume_after_id", sa.Integer, nullable=False, server_default="0"
-        ),
-    )
-    op.add_column(
-        "library_audit_run",
-        sa.Column("last_progress_at", sa.DateTime(timezone=True), nullable=True),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("library_audit_run", "last_progress_at")
-    op.drop_column("library_audit_run", "resume_after_id")

alembic/versions/0040_series_chapters.py

@@ -1,108 +0,0 @@
-"""series chapters: chapter layer over series_page (FC-6.1)
-
-Revision ID: 0040
-Revises: 0039
-Create Date: 2026-06-07
-
-A series (Tag kind='series') gains an ordered chapter layer. Reading order
-becomes (series_chapter.chapter_number, series_page.page_number). Every existing
-series is backfilled into a single auto-chapter (chapter_number=1) holding its
-current flat pages, so no data is lost and the old flat ordering is preserved.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0040"
-down_revision: Union[str, None] = "0039"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "series_chapter",
-        sa.Column("id", sa.Integer, primary_key=True),
-        sa.Column(
-            "series_tag_id",
-            sa.Integer,
-            sa.ForeignKey("tag.id", ondelete="CASCADE"),
-            nullable=False,
-        ),
-        sa.Column("chapter_number", sa.Integer, nullable=False),
-        sa.Column("title", sa.Text, nullable=True),
-        sa.Column(
-            "is_placeholder", sa.Boolean, nullable=False, server_default="false"
-        ),
-        sa.Column("stated_page_start", sa.Integer, nullable=True),
-        sa.Column("stated_page_end", sa.Integer, nullable=True),
-        sa.Column(
-            "created_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("now()"),
-        ),
-        sa.Column(
-            "updated_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("now()"),
-        ),
-    )
-    op.create_index(
-        "ix_series_chapter_series_tag_id", "series_chapter", ["series_tag_id"]
-    )
-
-    # New columns on series_page; chapter_id starts nullable so we can backfill.
-    op.add_column(
-        "series_page", sa.Column("chapter_id", sa.Integer, nullable=True)
-    )
-    op.add_column(
-        "series_page", sa.Column("stated_page", sa.Integer, nullable=True)
-    )
-
-    conn = op.get_bind()
-    # One auto-chapter per existing series (any series_tag_id present in pages).
-    conn.execute(
-        sa.text(
-            "INSERT INTO series_chapter "
-            "(series_tag_id, chapter_number, is_placeholder, created_at, updated_at) "
-            "SELECT DISTINCT series_tag_id, 1, false, now(), now() "
-            "FROM series_page"
-        )
-    )
-    # Point every existing page at its series' auto-chapter.
-    conn.execute(
-        sa.text(
-            "UPDATE series_page sp "
-            "SET chapter_id = sc.id "
-            "FROM series_chapter sc "
-            "WHERE sc.series_tag_id = sp.series_tag_id"
-        )
-    )
-
-    # Now lock chapter_id down: NOT NULL + FK (cascade) + index.
-    op.alter_column("series_page", "chapter_id", nullable=False)
-    op.create_foreign_key(
-        "fk_series_page_chapter_id",
-        "series_page",
-        "series_chapter",
-        ["chapter_id"],
-        ["id"],
-        ondelete="CASCADE",
-    )
-    op.create_index(
-        "ix_series_page_chapter_id", "series_page", ["chapter_id"]
-    )
-
-
-def downgrade() -> None:
-    op.drop_index("ix_series_page_chapter_id", table_name="series_page")
-    op.drop_constraint(
-        "fk_series_page_chapter_id", "series_page", type_="foreignkey"
-    )
-    op.drop_column("series_page", "stated_page")
-    op.drop_column("series_page", "chapter_id")
-    op.drop_index("ix_series_chapter_series_tag_id", table_name="series_chapter")
-    op.drop_table("series_chapter")

alembic/versions/0041_series_suggestions.py

@@ -1,98 +0,0 @@
-"""series suggestions: assisted-continuation matcher (FC-6.3)
-
-Revision ID: 0041
-Revises: 0040
-Create Date: 2026-06-07
-
-A confirm-only queue of "this post may continue this series" hints, plus two
-import_settings knobs (enable + score threshold) for the matcher.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0041"
-down_revision: Union[str, None] = "0040"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "series_suggestion",
-        sa.Column("id", sa.Integer, primary_key=True),
-        sa.Column(
-            "post_id",
-            sa.Integer,
-            sa.ForeignKey("post.id", ondelete="CASCADE"),
-            nullable=False,
-        ),
-        sa.Column(
-            "series_tag_id",
-            sa.Integer,
-            sa.ForeignKey("tag.id", ondelete="CASCADE"),
-            nullable=False,
-        ),
-        sa.Column("score", sa.Float, nullable=False),
-        sa.Column("signals", sa.JSON, nullable=True),
-        sa.Column(
-            "status", sa.String(16), nullable=False, server_default="pending"
-        ),
-        sa.Column(
-            "created_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("now()"),
-        ),
-        sa.Column(
-            "updated_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("now()"),
-        ),
-        sa.UniqueConstraint(
-            "post_id", "series_tag_id", name="uq_series_suggestion_post_series"
-        ),
-    )
-    op.create_index(
-        "ix_series_suggestion_post_id", "series_suggestion", ["post_id"]
-    )
-    op.create_index(
-        "ix_series_suggestion_series_tag_id",
-        "series_suggestion",
-        ["series_tag_id"],
-    )
-    op.create_index(
-        "ix_series_suggestion_status", "series_suggestion", ["status"]
-    )
-
-    op.add_column(
-        "import_settings",
-        sa.Column(
-            "series_suggest_enabled",
-            sa.Boolean,
-            nullable=False,
-            server_default=sa.true(),
-        ),
-    )
-    op.add_column(
-        "import_settings",
-        sa.Column(
-            "series_suggest_threshold",
-            sa.Float,
-            nullable=False,
-            server_default="0.5",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("import_settings", "series_suggest_threshold")
-    op.drop_column("import_settings", "series_suggest_enabled")
-    op.drop_index("ix_series_suggestion_status", table_name="series_suggestion")
-    op.drop_index(
-        "ix_series_suggestion_series_tag_id", table_name="series_suggestion"
-    )
-    op.drop_index("ix_series_suggestion_post_id", table_name="series_suggestion")
-    op.drop_table("series_suggestion")

alembic/versions/0042_series_chapter_stated_part.py

@@ -1,32 +0,0 @@
-"""series chapter stated_part: operator-facing Part N label (FC-6.4)
-
-Revision ID: 0042
-Revises: 0041
-Create Date: 2026-06-07
-
-A chapter's positional chapter_number is auto-managed (rewritten 1..N on
-reorder/delete), so it can't double as the installment number the operator wants
-to type (e.g. a series authored from a post that is Part 2). Add a nullable
-stated_part alongside it — the same split as series_page.page_number (order) vs
-series_page.stated_page (printed number). Nullable; the UI falls back to
-chapter_number when unset.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0042"
-down_revision: Union[str, None] = "0041"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "series_chapter", sa.Column("stated_part", sa.Integer, nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("series_chapter", "stated_part")

alembic/versions/0043_post_attachment_per_post_unique.py

@@ -1,62 +0,0 @@
-"""post_attachment: per-post sha uniqueness (empty-post flood fix)
-
-Revision ID: 0043
-Revises: 0042
-Create Date: 2026-06-08
-
-PostAttachment.sha256 was GLOBALLY unique, so a non-art file the creator attaches
-to many posts (a standard pdf/zip/link-card) only ever got ONE row — on the first
-post — leaving every later post a bare shell (no image, no attachment). The native
-Patreon backfill of Anduo surfaced 1589 such shells (operator-flagged 2026-06-08).
-
-Switch to PER-POST uniqueness: the on-disk blob stays sha-deduped, but each post
-gets its own row. Replace the unique sha256 index with a plain lookup index plus
-two partial uniques — (post_id, sha256) for real posts and (sha256) for the
-NULL-post filesystem case (still one row per file there).
-
-Existing data has ≤1 row per sha (the old global unique), so the new partial
-uniques can't be violated on upgrade — no data backfill needed here. The bare-post
-shells themselves are removed by the separate prune-empty-posts cleanup tool.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0043"
-down_revision: Union[str, None] = "0042"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Drop the global unique index; recreate it as a plain (non-unique) lookup
-    # index so sha-based reads keep their index (matches the model's index=True).
-    op.drop_index("ix_post_attachment_sha256", table_name="post_attachment")
-    op.create_index(
-        "ix_post_attachment_sha256", "post_attachment", ["sha256"],
-    )
-    op.create_index(
-        "uq_post_attachment_post_sha", "post_attachment",
-        ["post_id", "sha256"], unique=True,
-        postgresql_where=sa.text("post_id IS NOT NULL"),
-    )
-    op.create_index(
-        "uq_post_attachment_null_post_sha", "post_attachment",
-        ["sha256"], unique=True,
-        postgresql_where=sa.text("post_id IS NULL"),
-    )
-
-
-def downgrade() -> None:
-    op.drop_index(
-        "uq_post_attachment_null_post_sha", table_name="post_attachment"
-    )
-    op.drop_index(
-        "uq_post_attachment_post_sha", table_name="post_attachment"
-    )
-    op.drop_index("ix_post_attachment_sha256", table_name="post_attachment")
-    op.create_index(
-        "ix_post_attachment_sha256", "post_attachment", ["sha256"],
-        unique=True,
-    )

alembic/versions/0044_ml_settings_tagger_store_floor.py

@@ -1,37 +0,0 @@
-"""ml_settings.tagger_store_floor
-
-The ingest confidence floor below which tagger predictions are not stored,
-promoted from the TAGGER_STORE_FLOOR env var to a DB-backed, UI-tunable
-setting. Default 0.70 (was an env default of 0.05): the suggestion path
-already filters at 0.70 and the centroid/learned path covers low-confidence
-preferred tags, so the sub-0.70 tail was redundant weight — it had grown
-image_record's TOAST to ~100 GB. See plan-task #764.
-
-Revision ID: 0044
-Revises: 0043
-Create Date: 2026-06-10
-
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0044"
-down_revision: Union[str, None] = "0043"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "tagger_store_floor", sa.Float(),
-            nullable=False, server_default="0.7",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("ml_settings", "tagger_store_floor")

alembic/versions/0045_image_prediction_table.py

@@ -1,69 +0,0 @@
-"""image_prediction table (DDL only — backfill runs as a background task)
-
-Normalizes the per-image tagger predictions out of the JSON blob into a
-queryable table (#768). This migration creates ONLY the table + indexes — it
-is pure DDL and commits instantly, so web boots immediately.
-
-The data backfill from the existing image_record.tagger_predictions JSON is
-deliberately NOT done here. Doing it inline made the whole migration one
-transaction over the ~100 GB TOAST: nothing committed until the very end, it
-was invisible/unmonitorable mid-run, and an early MATERIALIZED-CTE form spilled
-the full 100 GB to temp. Instead the backfill is the
-backend.app.tasks.admin.backfill_image_predictions_task — batched by id window,
-committed per chunk (visible progress + resumable), idempotent
-(ON CONFLICT DO NOTHING). Trigger it from Settings → Maintenance once web is up.
-
-The old image_record.tagger_predictions column is left in place (vestigial) and
-dropped in a follow-up once the backfill + code cutover are verified — dropping
-it needs an ACCESS EXCLUSIVE lock on the hot image_record table (the 0044 lock
-class), so it's deferred to a quiesced-worker window.
-
-Revision ID: 0045
-Revises: 0044
-Create Date: 2026-06-10
-
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0045"
-down_revision: Union[str, None] = "0044"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "image_prediction",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column(
-            "image_record_id", sa.Integer(),
-            sa.ForeignKey("image_record.id", ondelete="CASCADE"),
-            nullable=False,
-        ),
-        sa.Column("raw_name", sa.String(length=255), nullable=False),
-        sa.Column("category", sa.String(length=64), nullable=False),
-        sa.Column("score", sa.Float(), nullable=False),
-        sa.UniqueConstraint(
-            "image_record_id", "raw_name", name="image_raw_name",
-        ),
-    )
-    op.create_index(
-        "ix_image_prediction_image", "image_prediction", ["image_record_id"],
-    )
-    op.create_index(
-        "ix_image_prediction_name_score", "image_prediction",
-        ["raw_name", "score"],
-    )
-    # No data backfill here — see the module docstring. The one-time copy from
-    # image_record.tagger_predictions runs as backfill_image_predictions_task
-    # (batched, resumable, idempotent), kept out of this transaction so web boots
-    # without waiting on a ~100 GB pass.
-
-
-def downgrade() -> None:
-    op.drop_index("ix_image_prediction_name_score", "image_prediction")
-    op.drop_index("ix_image_prediction_image", "image_prediction")
-    op.drop_table("image_prediction")

alembic/versions/0046_drop_tagger_predictions.py

@@ -1,43 +0,0 @@
-"""drop image_record.tagger_predictions (predictions normalized to image_prediction)
-
-Final step of #768. The per-tag predictions now live in the image_prediction
-table (backfilled from the JSON, read by suggestions + allowlist, written by
-tag_and_embed). The old JSON column is dead weight — and it's the ~100 GB of
-sub-0.70 score tail that bloated image_record's TOAST and broke DB backups
-(#739). Dropping it is a fast catalog change; it does NOT reclaim the disk on
-its own — run `VACUUM FULL image_record` (or pg_repack) afterward, off-hours,
-to return the space to the OS so backups go small.
-
-DROP COLUMN needs a brief ACCESS EXCLUSIVE lock on image_record; env.py's
-lock_timeout guards it, so quiesce the ml-worker if a tagging run is in flight
-(see the migration-lock reference). tagger_model_version is kept — it's the
-"has this been tagged / is it current?" signal the backfill sweep reads.
-
-Revision ID: 0046
-Revises: 0045
-Create Date: 2026-06-11
-
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0046"
-down_revision: Union[str, None] = "0045"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.drop_column("image_record", "tagger_predictions")
-
-
-def downgrade() -> None:
-    # Re-add the column empty. The JSON data is not restored (it lived only in
-    # this column); a downgrade would re-tag or backfill from image_prediction
-    # separately if ever needed.
-    op.add_column(
-        "image_record",
-        sa.Column("tagger_predictions", sa.JSON(), nullable=True),
-    )

alembic/versions/0047_series_chapter_dividers.py

@@ -1,175 +0,0 @@
-"""series chapters become cosmetic dividers; pages become one series-global run
-
-FC-6.x reframe (#789). A series is now ONE flat, series-global ordered run of
-pages; chapters stop owning pages and become labeled dividers anchored to the
-page that begins them.
-
-Migration (order matters — series_page.chapter_id cascades, so it must be
-dropped BEFORE any chapter row is deleted, or pages would cascade away):
-  a. Renumber series_page.page_number to a series-global 1..N (ordered by the
-     OLD (chapter_number, page_number)).
-  b. Add series_chapter.anchor_page_id and populate it with each chapter's first
-     page (lowest new page_number).
-  c. Drop series_page.chapter_id (severs the cascade link).
-  d. Prune chapters that shouldn't become dividers: empty/placeholder ones (no
-     anchor) and the redundant unlabeled chapter that would sit at page 1.
-  e. Reshape series_chapter into the divider: drop chapter_number,
-     is_placeholder, stated_page_start/end; make anchor_page_id NOT NULL +
-     UNIQUE + FK→series_page ON DELETE CASCADE.
-
-Revision ID: 0047
-Revises: 0046
-Create Date: 2026-06-11
-
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0047"
-down_revision: Union[str, None] = "0046"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # a. series-global page numbering, preserving the old reading order.
-    op.execute(
-        """
-        WITH ordered AS (
-            SELECT sp.id,
-                   ROW_NUMBER() OVER (
-                       PARTITION BY sp.series_tag_id
-                       ORDER BY sc.chapter_number, sp.page_number, sp.id
-                   ) AS rn
-            FROM series_page sp
-            JOIN series_chapter sc ON sc.id = sp.chapter_id
-        )
-        UPDATE series_page sp
-        SET page_number = ordered.rn
-        FROM ordered
-        WHERE sp.id = ordered.id
-        """
-    )
-
-    # b. anchor each existing chapter at its first page (lowest new page_number).
-    op.add_column(
-        "series_chapter",
-        sa.Column("anchor_page_id", sa.Integer(), nullable=True),
-    )
-    op.execute(
-        """
-        WITH firsts AS (
-            SELECT DISTINCT ON (sp.chapter_id)
-                   sp.chapter_id, sp.id AS page_id
-            FROM series_page sp
-            ORDER BY sp.chapter_id, sp.page_number, sp.id
-        )
-        UPDATE series_chapter sc
-        SET anchor_page_id = firsts.page_id
-        FROM firsts
-        WHERE firsts.chapter_id = sc.id
-        """
-    )
-
-    # c. sever the ownership link (drops the FK + index with the column) BEFORE
-    #    pruning chapters, so deleting a chapter can't cascade-delete its pages.
-    op.drop_column("series_page", "chapter_id")
-
-    # d. prune chapters that don't become dividers: placeholders / empty ones
-    #    (no anchor), and the unlabeled chapter that would land redundantly at
-    #    page 1 (the series just starts — no divider needed there).
-    op.execute(
-        """
-        DELETE FROM series_chapter sc
-        USING (
-            SELECT sc2.id
-            FROM series_chapter sc2
-            LEFT JOIN series_page sp ON sp.id = sc2.anchor_page_id
-            WHERE sc2.anchor_page_id IS NULL
-               OR (sp.page_number = 1
-                   AND sc2.title IS NULL
-                   AND sc2.stated_part IS NULL)
-        ) gone
-        WHERE sc.id = gone.id
-        """
-    )
-
-    # e. reshape into the divider model.
-    op.drop_column("series_chapter", "chapter_number")
-    op.drop_column("series_chapter", "is_placeholder")
-    op.drop_column("series_chapter", "stated_page_start")
-    op.drop_column("series_chapter", "stated_page_end")
-    op.alter_column("series_chapter", "anchor_page_id", nullable=False)
-    op.create_unique_constraint(
-        "uq_series_chapter_anchor_page", "series_chapter", ["anchor_page_id"]
-    )
-    op.create_foreign_key(
-        "fk_series_chapter_anchor_page",
-        "series_chapter",
-        "series_page",
-        ["anchor_page_id"],
-        ["id"],
-        ondelete="CASCADE",
-    )
-
-
-def downgrade() -> None:
-    # Lossy: dividers can't be reconstructed as owning chapters. Collapse back to
-    # exactly one chapter per series that owns all its pages in order.
-    op.add_column(
-        "series_page", sa.Column("chapter_id", sa.Integer(), nullable=True)
-    )
-    op.drop_constraint(
-        "fk_series_chapter_anchor_page", "series_chapter", type_="foreignkey"
-    )
-    op.drop_constraint(
-        "uq_series_chapter_anchor_page", "series_chapter", type_="unique"
-    )
-    op.drop_column("series_chapter", "anchor_page_id")
-    op.add_column(
-        "series_chapter",
-        sa.Column(
-            "chapter_number", sa.Integer(), nullable=False, server_default="1"
-        ),
-    )
-    op.add_column(
-        "series_chapter",
-        sa.Column(
-            "is_placeholder", sa.Boolean(), nullable=False,
-            server_default="false",
-        ),
-    )
-    op.add_column(
-        "series_chapter",
-        sa.Column("stated_page_start", sa.Integer(), nullable=True),
-    )
-    op.add_column(
-        "series_chapter",
-        sa.Column("stated_page_end", sa.Integer(), nullable=True),
-    )
-    op.execute("DELETE FROM series_chapter")
-    op.execute(
-        """
-        INSERT INTO series_chapter (series_tag_id, chapter_number)
-        SELECT DISTINCT series_tag_id, 1 FROM series_page
-        """
-    )
-    op.execute(
-        """
-        UPDATE series_page sp
-        SET chapter_id = sc.id
-        FROM series_chapter sc
-        WHERE sc.series_tag_id = sp.series_tag_id
-        """
-    )
-    op.alter_column("series_page", "chapter_id", nullable=False)
-    op.create_foreign_key(
-        "fk_series_page_chapter",
-        "series_page",
-        "series_chapter",
-        ["chapter_id"],
-        ["id"],
-        ondelete="CASCADE",
-    )

alembic/versions/0048_series_page_pending_status.py

@@ -1,45 +0,0 @@
-"""series_page pending staging: status + nullable page_number (#789 Phase 2)
-
-Pages added from a post no longer append straight into the run — they land
-'pending' with a NULL page_number, staged grouped by their source post so the
-operator can drop junk (text-free alts, bumpers) and place the keepers into the
-sequence. A page only gets a series-global page_number once it's 'placed'.
-
-Revision ID: 0048
-Revises: 0047
-Create Date: 2026-06-11
-
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0048"
-down_revision: Union[str, None] = "0047"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "series_page",
-        sa.Column(
-            "status", sa.String(length=16), nullable=False,
-            server_default="placed",
-        ),
-    )
-    op.alter_column(
-        "series_page", "page_number",
-        existing_type=sa.Integer(), nullable=True,
-    )
-
-
-def downgrade() -> None:
-    # Lossy: pending pages are unsorted staging rows with no order — drop them.
-    op.execute("DELETE FROM series_page WHERE status = 'pending'")
-    op.alter_column(
-        "series_page", "page_number",
-        existing_type=sa.Integer(), nullable=False,
-    )
-    op.drop_column("series_page", "status")

alembic/versions/0049_external_link_table.py

@@ -1,90 +0,0 @@
-"""external_link table — off-platform file-host links found in post bodies
-
-Creators host the real files on mega.nz / Google Drive / MediaFire / Dropbox /
-Pixeldrain and link them in the post text. This table records each such link
-(so nothing is silently dropped), and doubles as the dedup + dead-letter ledger
-the download worker (a later slice) walks. `url` keeps the FULL link including
-the `#fragment` — mega.nz's decryption key lives there; truncating it makes the
-file undownloadable.
-
-CHECK whitelists for host + status include the full enum up front (incl. the
-download-worker statuses) so the worker slice needs no constraint migration.
-
-Revision ID: 0049
-Revises: 0048
-Create Date: 2026-06-14
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0049"
-down_revision: Union[str, None] = "0048"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "external_link",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column(
-            "post_id", sa.Integer(),
-            sa.ForeignKey("post.id", ondelete="CASCADE"), nullable=False,
-        ),
-        sa.Column(
-            "artist_id", sa.Integer(),
-            sa.ForeignKey("artist.id", ondelete="SET NULL"), nullable=True,
-        ),
-        sa.Column("host", sa.String(length=16), nullable=False),
-        sa.Column("url", sa.Text(), nullable=False),
-        sa.Column("label", sa.Text(), nullable=True),
-        sa.Column(
-            "status", sa.String(length=16), nullable=False,
-            server_default="pending",
-        ),
-        sa.Column("attempts", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("last_error", sa.Text(), nullable=True),
-        sa.Column(
-            "attachment_id", sa.Integer(),
-            sa.ForeignKey("post_attachment.id", ondelete="SET NULL"),
-            nullable=True,
-        ),
-        sa.Column(
-            "created_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column("completed_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("duration_seconds", sa.Float(), nullable=True),
-        sa.CheckConstraint(
-            "host IN ('mega','gdrive','mediafire','dropbox','pixeldrain')",
-            name="ck_external_link_host",
-        ),
-        sa.CheckConstraint(
-            "status IN ('pending','downloading','downloaded','failed',"
-            "'skipped','dead')",
-            name="ck_external_link_status",
-        ),
-    )
-    op.create_index(
-        "ix_external_link_post_id", "external_link", ["post_id"],
-    )
-    op.create_index(
-        "ix_external_link_artist_id", "external_link", ["artist_id"],
-    )
-    op.create_index(
-        "ix_external_link_status", "external_link", ["status"],
-    )
-    op.create_index(
-        "uq_external_link_post_url", "external_link", ["post_id", "url"],
-        unique=True,
-    )
-
-
-def downgrade() -> None:
-    op.drop_index("uq_external_link_post_url", table_name="external_link")
-    op.drop_index("ix_external_link_status", table_name="external_link")
-    op.drop_index("ix_external_link_artist_id", table_name="external_link")
-    op.drop_index("ix_external_link_post_id", table_name="external_link")
-    op.drop_table("external_link")

alembic/versions/0050_external_link_host_toggles.py

@@ -1,38 +0,0 @@
-"""import_settings: per-host enable toggles for external file-host downloads
-
-Operator levers (#830): disable a single host (e.g. mega.nz when it's
-rate-limiting/banning) without touching the others. The worker reads these via
-getattr and defaults to enabled, so the toggles default TRUE (works out of the
-box, rule #26).
-
-Revision ID: 0050
-Revises: 0049
-Create Date: 2026-06-14
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0050"
-down_revision: Union[str, None] = "0049"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-_HOSTS = ("mega", "gdrive", "mediafire", "dropbox", "pixeldrain")
-
-
-def upgrade() -> None:
-    for host in _HOSTS:
-        op.add_column(
-            "import_settings",
-            sa.Column(
-                f"extdl_{host}_enabled", sa.Boolean(), nullable=False,
-                server_default=sa.true(),
-            ),
-        )
-
-
-def downgrade() -> None:
-    for host in _HOSTS:
-        op.drop_column("import_settings", f"extdl_{host}_enabled")

alembic/versions/0051_image_source_provenance.py

@@ -1,38 +0,0 @@
-"""image_record: source_url + source_filehash (inline-image localization)
-
-#830 Phase 2. To render a post body faithfully we serve LOCAL copies of inline
-images instead of hotlinking the public CDN. The join key between a body
-`<img src=CDN>` and the local file is the CDN's 32-hex filehash (the same
-identity extract_media dedups by). Persist it (indexed) plus the full source
-URL for provenance/debugging. Both NULL for filesystem-imported / pre-existing
-rows — those fall back to hotlinking until re-downloaded.
-
-Revision ID: 0051
-Revises: 0050
-Create Date: 2026-06-14
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0051"
-down_revision: Union[str, None] = "0050"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column("image_record", sa.Column("source_url", sa.Text(), nullable=True))
-    op.add_column(
-        "image_record", sa.Column("source_filehash", sa.String(length=32), nullable=True)
-    )
-    op.create_index(
-        "ix_image_record_source_filehash", "image_record", ["source_filehash"]
-    )
-
-
-def downgrade() -> None:
-    op.drop_index("ix_image_record_source_filehash", table_name="image_record")
-    op.drop_column("image_record", "source_filehash")
-    op.drop_column("image_record", "source_url")

alembic/versions/0052_image_duration_seconds.py

@@ -1,32 +0,0 @@
-"""image_record: duration_seconds (Tier-1 video near-dup key)
-
-#871. Videos previously deduped on sha256 only (pHash is images-only), so a
-different encode/remux of the same video imported as a distinct record. Persist
-the container duration so the importer can treat same-artist videos with matching
-duration (+ aspect ratio) as the same content and dedup/supersede like images.
-NULL for images and for video rows imported before this column existed (a
-backfill re-probes those so they participate in dedup).
-
-Revision ID: 0052
-Revises: 0051
-Create Date: 2026-06-16
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0052"
-down_revision: Union[str, None] = "0051"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "image_record", sa.Column("duration_seconds", sa.Float(), nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("image_record", "duration_seconds")

alembic/versions/0053_ml_settings_video_tagging.py

@@ -1,49 +0,0 @@
-"""ml_settings: video tagging knobs (cadence sampling + noise floor)
-
-#747. Video tag quality/perf: sample frames at a fixed cadence (interval) so a
-tag's frame-presence reflects real screen time, cap total frames so long videos
-stay bounded, and keep a tag only if it appears in >= min_tag_frames sampled
-frames. Operator-tunable via Settings → ML (replaces the VIDEO_ML_FRAMES env var).
-
-Revision ID: 0053
-Revises: 0052
-Create Date: 2026-06-16
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0053"
-down_revision: Union[str, None] = "0052"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "video_frame_interval_seconds", sa.Float(), nullable=False,
-            server_default="4.0",
-        ),
-    )
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "video_max_frames", sa.Integer(), nullable=False, server_default="64",
-        ),
-    )
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "video_min_tag_frames", sa.Integer(), nullable=False,
-            server_default="3",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("ml_settings", "video_min_tag_frames")
-    op.drop_column("ml_settings", "video_max_frames")
-    op.drop_column("ml_settings", "video_frame_interval_seconds")

alembic/versions/0054_subscribestar_ledgers.py

@@ -1,82 +0,0 @@
-"""subscribestar_seen_media + subscribestar_failed_media: per-source ledgers
-
-Revision ID: 0054
-Revises: 0053
-Create Date: 2026-06-17
-
-SubscribeStar native ingester (phase 1 of the gallery-dl → native-core
-migration). Mirrors the Patreon ledger tables (0037/0038): a seen-ledger so
-routine walks skip already-ingested media (recovery bypasses it) and a
-dead-letter ledger so persistently-failing media stops re-burning backfill
-chunks. `filehash` is a CDN content hash when present, else a synthesized
-``<post_id>:<filename>`` key — hence String(128). UNIQUE (source_id, filehash)
-is the upsert key on each.
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0054"
-down_revision: Union[str, None] = "0053"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "subscribestar_seen_media",
-        sa.Column("id", sa.Integer, primary_key=True),
-        sa.Column(
-            "source_id",
-            sa.Integer,
-            sa.ForeignKey("source.id", ondelete="CASCADE"),
-            nullable=False,
-            index=True,
-        ),
-        sa.Column("filehash", sa.String(128), nullable=False),
-        sa.Column("post_id", sa.String(64), nullable=True),
-        sa.Column(
-            "seen_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("NOW()"),
-        ),
-        sa.UniqueConstraint(
-            "source_id", "filehash", name="uq_subscribestar_seen_media_source_id"
-        ),
-    )
-    op.create_table(
-        "subscribestar_failed_media",
-        sa.Column("id", sa.Integer, primary_key=True),
-        sa.Column(
-            "source_id",
-            sa.Integer,
-            sa.ForeignKey("source.id", ondelete="CASCADE"),
-            nullable=False,
-            index=True,
-        ),
-        sa.Column("filehash", sa.String(128), nullable=False),
-        sa.Column("attempts", sa.Integer, nullable=False, server_default="1"),
-        sa.Column("last_error", sa.Text, nullable=True),
-        sa.Column(
-            "first_failed_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("NOW()"),
-        ),
-        sa.Column(
-            "last_failed_at",
-            sa.DateTime(timezone=True),
-            nullable=False,
-            server_default=sa.text("NOW()"),
-        ),
-        sa.UniqueConstraint(
-            "source_id", "filehash", name="uq_subscribestar_failed_media_source_id"
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("subscribestar_failed_media")
-    op.drop_table("subscribestar_seen_media")

alembic/versions/0055_image_provenance_from_attachment.py

@@ -1,55 +0,0 @@
-"""image_provenance: from_attachment_id (which archive an image was extracted from)
-
-Milestone #87. When an image is pulled out of a .zip/.rar, record WHICH archive
-PostAttachment it came from, so the provenance UI can show the single archive a
-file lives inside instead of every attachment on the post. Nullable FK with
-ON DELETE SET NULL — a loose (non-archive) download leaves it NULL, and deleting
-the archive attachment forgets the linkage without destroying the (image, post)
-provenance edge. Existing rows are NULL until the reextract backfill stamps them.
-
-Revision ID: 0055
-Revises: 0054
-Create Date: 2026-06-22
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0055"
-down_revision: Union[str, None] = "0054"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "image_provenance",
-        sa.Column("from_attachment_id", sa.Integer(), nullable=True),
-    )
-    op.create_index(
-        "ix_image_provenance_from_attachment_id",
-        "image_provenance",
-        ["from_attachment_id"],
-    )
-    op.create_foreign_key(
-        "fk_image_provenance_from_attachment",
-        "image_provenance",
-        "post_attachment",
-        ["from_attachment_id"],
-        ["id"],
-        ondelete="SET NULL",
-    )
-
-
-def downgrade() -> None:
-    op.drop_constraint(
-        "fk_image_provenance_from_attachment",
-        "image_provenance",
-        type_="foreignkey",
-    )
-    op.drop_index(
-        "ix_image_provenance_from_attachment_id",
-        table_name="image_provenance",
-    )
-    op.drop_column("image_provenance", "from_attachment_id")

alembic/versions/0056_tag_eval_run.py

@@ -1,43 +0,0 @@
-"""tag_eval_run: persisted head-vs-centroid tagging eval runs (#1130)
-
-Milestone #114 slice 1. A long ml-queue eval whose full report must SURVIVE
-navigation, so the run + report live in a row the admin card rehydrates from
-(mirrors library_audit_run). running -> ready / error.
-
-Revision ID: 0056
-Revises: 0055
-Create Date: 2026-06-28
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-from sqlalchemy.dialects.postgresql import JSONB
-
-revision: str = "0056"
-down_revision: Union[str, None] = "0055"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "tag_eval_run",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column("params", JSONB(), nullable=False),
-        sa.Column("status", sa.String(length=16), nullable=False, server_default="running"),
-        sa.Column(
-            "started_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("report", JSONB(), nullable=True),
-        sa.Column("error", sa.Text(), nullable=True),
-        sa.Column("last_progress_at", sa.DateTime(timezone=True), nullable=True),
-    )
-    op.create_index("ix_tag_eval_run_status", "tag_eval_run", ["status"])
-
-
-def downgrade() -> None:
-    op.drop_index("ix_tag_eval_run_status", table_name="tag_eval_run")
-    op.drop_table("tag_eval_run")

alembic/versions/0057_tag_positive_confirmation.py

@@ -1,40 +0,0 @@
-"""tag_positive_confirmation: operator-affirmed correct positives (#1130)
-
-Mirror of tag_suggestion_rejection. "Keep" on a doubted positive records here so
-the eval's doubts list stops resurfacing confirmed-correct images every run.
-
-Revision ID: 0057
-Revises: 0056
-Create Date: 2026-06-28
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0057"
-down_revision: Union[str, None] = "0056"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "tag_positive_confirmation",
-        sa.Column(
-            "image_record_id", sa.Integer(),
-            sa.ForeignKey("image_record.id", ondelete="CASCADE"), primary_key=True,
-        ),
-        sa.Column(
-            "tag_id", sa.Integer(),
-            sa.ForeignKey("tag.id", ondelete="CASCADE"), primary_key=True, index=True,
-        ),
-        sa.Column(
-            "confirmed_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("tag_positive_confirmation")

alembic/versions/0058_tag_head.py

@@ -1,95 +0,0 @@
-"""tag_head + head_training_run: production heads that learn from tags (#114)
-
-The eval (#1130) proved the frozen-embedding + trained-head spine; this lands its
-production form. tag_head stores one logistic-regression head per concept (the
-new suggestion source, replacing Camie + centroid); head_training_run tracks the
-batch that (re)trains them. Adds two head-training tunables to ml_settings.
-
-Revision ID: 0058
-Revises: 0057
-Create Date: 2026-06-28
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-from pgvector.sqlalchemy import Vector
-from sqlalchemy.dialects.postgresql import JSONB
-
-revision: str = "0058"
-down_revision: Union[str, None] = "0057"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-_HEAD_DIM = 1152
-
-
-def upgrade() -> None:
-    op.create_table(
-        "tag_head",
-        sa.Column(
-            "tag_id", sa.Integer(),
-            sa.ForeignKey("tag.id", ondelete="CASCADE"), primary_key=True,
-        ),
-        sa.Column("embedding_version", sa.String(length=128), nullable=False),
-        sa.Column("weights", Vector(_HEAD_DIM), nullable=False),
-        sa.Column("bias", sa.Float(), nullable=False),
-        sa.Column("suggest_threshold", sa.Float(), nullable=False),
-        sa.Column("auto_apply_threshold", sa.Float(), nullable=True),
-        sa.Column("n_pos", sa.Integer(), nullable=False),
-        sa.Column("n_neg", sa.Integer(), nullable=False),
-        sa.Column("ap", sa.Float(), nullable=False),
-        sa.Column("precision_cv", sa.Float(), nullable=False),
-        sa.Column("recall", sa.Float(), nullable=False),
-        sa.Column(
-            "trained_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column("metrics", JSONB(), nullable=True),
-    )
-
-    op.create_table(
-        "head_training_run",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column("params", JSONB(), nullable=False),
-        sa.Column(
-            "status", sa.String(length=16), nullable=False,
-            server_default="running",
-        ),
-        sa.Column(
-            "started_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("n_trained", sa.Integer(), nullable=True),
-        sa.Column("n_skipped", sa.Integer(), nullable=True),
-        sa.Column("error", sa.Text(), nullable=True),
-        sa.Column("last_progress_at", sa.DateTime(timezone=True), nullable=True),
-    )
-    op.create_index(
-        "ix_head_training_run_status", "head_training_run", ["status"],
-    )
-
-    # Head-training tunables on the ml_settings singleton.
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "head_min_positives", sa.Integer(), nullable=False,
-            server_default="8",
-        ),
-    )
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "head_auto_apply_precision", sa.Float(), nullable=False,
-            server_default="0.97",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("ml_settings", "head_auto_apply_precision")
-    op.drop_column("ml_settings", "head_min_positives")
-    op.drop_index("ix_head_training_run_status", table_name="head_training_run")
-    op.drop_table("head_training_run")
-    op.drop_table("tag_head")

alembic/versions/0059_head_auto_apply.py

@@ -1,70 +0,0 @@
-"""head_auto_apply_run + earned-auto-apply settings (#114)
-
-A graduated head can apply its tag without a human, gated by a master switch +
-a support floor. head_auto_apply_run tracks each sweep / dry-run preview.
-
-Revision ID: 0059
-Revises: 0058
-Create Date: 2026-06-29
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-from sqlalchemy.dialects.postgresql import JSONB
-
-revision: str = "0059"
-down_revision: Union[str, None] = "0058"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "head_auto_apply_run",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column(
-            "dry_run", sa.Boolean(), nullable=False, server_default=sa.false()
-        ),
-        sa.Column("params", JSONB(), nullable=False),
-        sa.Column(
-            "status", sa.String(length=16), nullable=False,
-            server_default="running",
-        ),
-        sa.Column(
-            "started_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("n_applied", sa.Integer(), nullable=True),
-        sa.Column("report", JSONB(), nullable=True),
-        sa.Column("error", sa.Text(), nullable=True),
-        sa.Column("last_progress_at", sa.DateTime(timezone=True), nullable=True),
-    )
-    op.create_index(
-        "ix_head_auto_apply_run_status", "head_auto_apply_run", ["status"],
-    )
-
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "head_auto_apply_enabled", sa.Boolean(), nullable=False,
-            server_default=sa.true(),  # opt-out: on by default (operator-asked)
-        ),
-    )
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "head_auto_apply_min_positives", sa.Integer(), nullable=False,
-            server_default="30",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("ml_settings", "head_auto_apply_min_positives")
-    op.drop_column("ml_settings", "head_auto_apply_enabled")
-    op.drop_index(
-        "ix_head_auto_apply_run_status", table_name="head_auto_apply_run"
-    )
-    op.drop_table("head_auto_apply_run")

alembic/versions/0060_head_metrics.py

@@ -1,74 +0,0 @@
-"""head_metric + head_metrics_snapshot: auto-apply observability (#114)
-
-Running misfire/under-fire counters per concept (captured at correction time,
-since image_tag.source is lost on delete) + a daily per-concept time-series so
-the operator can tune the precision target + support floor from real data.
-
-Revision ID: 0060
-Revises: 0059
-Create Date: 2026-06-29
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0060"
-down_revision: Union[str, None] = "0059"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "head_metric",
-        sa.Column(
-            "tag_id", sa.Integer(),
-            sa.ForeignKey("tag.id", ondelete="CASCADE"), primary_key=True,
-        ),
-        sa.Column("n_misfires", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("n_underfires", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column(
-            "updated_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-    )
-
-    op.create_table(
-        "head_metrics_snapshot",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column(
-            "tag_id", sa.Integer(),
-            sa.ForeignKey("tag.id", ondelete="CASCADE"),
-        ),
-        sa.Column("name", sa.String(length=255), nullable=False),
-        sa.Column(
-            "snapshot_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column("n_auto_applied", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("n_misfires", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("n_underfires", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("ap", sa.Float(), nullable=True),
-        sa.Column("precision_cv", sa.Float(), nullable=True),
-        sa.Column("recall", sa.Float(), nullable=True),
-        sa.Column("n_pos", sa.Integer(), nullable=True),
-    )
-    op.create_index(
-        "ix_head_metrics_snapshot_tag_id", "head_metrics_snapshot", ["tag_id"],
-    )
-    op.create_index(
-        "ix_head_metrics_snapshot_snapshot_at", "head_metrics_snapshot",
-        ["snapshot_at"],
-    )
-
-
-def downgrade() -> None:
-    op.drop_index(
-        "ix_head_metrics_snapshot_snapshot_at", table_name="head_metrics_snapshot"
-    )
-    op.drop_index(
-        "ix_head_metrics_snapshot_tag_id", table_name="head_metrics_snapshot"
-    )
-    op.drop_table("head_metrics_snapshot")
-    op.drop_table("head_metric")

alembic/versions/0061_image_region.py

@@ -1,59 +0,0 @@
-"""image_region: detected/proposed regions + their crop embeddings (#114)
-
-Storage backbone of the crop pipeline. A region = normalized bbox + the crop's
-embedding (CCIP for face/figure → character id; SigLIP for concept regions →
-head bag-of-embeddings). Also serves as grounded-tag bbox provenance.
-
-Revision ID: 0061
-Revises: 0060
-Create Date: 2026-06-29
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-from pgvector.sqlalchemy import Vector
-
-revision: str = "0061"
-down_revision: Union[str, None] = "0060"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-_CCIP_DIM = 768
-_SIGLIP_DIM = 1152
-
-
-def upgrade() -> None:
-    op.create_table(
-        "image_region",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column(
-            "image_record_id", sa.Integer(),
-            sa.ForeignKey("image_record.id", ondelete="CASCADE"), nullable=False,
-        ),
-        sa.Column("kind", sa.String(length=16), nullable=False),
-        # Video/animated: source frame timestamp (seconds); NULL for stills.
-        sa.Column("frame_time", sa.Float(), nullable=True),
-        sa.Column("rx", sa.Float(), nullable=False),
-        sa.Column("ry", sa.Float(), nullable=False),
-        sa.Column("rw", sa.Float(), nullable=False),
-        sa.Column("rh", sa.Float(), nullable=False),
-        sa.Column("score", sa.Float(), nullable=True),
-        sa.Column("detector_version", sa.String(length=64), nullable=True),
-        sa.Column("crop_version", sa.String(length=64), nullable=True),
-        sa.Column("embedding_version", sa.String(length=128), nullable=True),
-        sa.Column("ccip_embedding", Vector(_CCIP_DIM), nullable=True),
-        sa.Column("siglip_embedding", Vector(_SIGLIP_DIM), nullable=True),
-        sa.Column(
-            "created_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-    )
-    op.create_index(
-        "ix_image_region_image_record_id", "image_region", ["image_record_id"],
-    )
-
-
-def downgrade() -> None:
-    op.drop_index("ix_image_region_image_record_id", table_name="image_region")
-    op.drop_table("image_region")

alembic/versions/0062_gpu_job.py

@@ -1,55 +0,0 @@
-"""gpu_job: the HTTP-leased GPU work queue for the desktop agent (#114)
-
-The agent stays HTTP-only — the server enqueues per-(image, task) jobs here and
-the agent leases/submits over the web API; Redis/Postgres stay private.
-
-Revision ID: 0062
-Revises: 0061
-Create Date: 2026-06-29
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0062"
-down_revision: Union[str, None] = "0061"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "gpu_job",
-        sa.Column("id", sa.Integer(), primary_key=True),
-        sa.Column(
-            "image_record_id", sa.Integer(),
-            sa.ForeignKey("image_record.id", ondelete="CASCADE"), nullable=False,
-        ),
-        sa.Column("task", sa.String(length=32), nullable=False),
-        sa.Column(
-            "status", sa.String(length=16), nullable=False,
-            server_default="pending",
-        ),
-        sa.Column("lease_token", sa.String(length=64), nullable=True),
-        sa.Column("leased_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("lease_expires_at", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("attempts", sa.Integer(), nullable=False, server_default="0"),
-        sa.Column("error", sa.Text(), nullable=True),
-        sa.Column(
-            "created_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-        sa.Column(
-            "updated_at", sa.DateTime(timezone=True), nullable=False,
-            server_default=sa.func.now(),
-        ),
-    )
-    op.create_index("ix_gpu_job_image_record_id", "gpu_job", ["image_record_id"])
-    op.create_index("ix_gpu_job_status", "gpu_job", ["status"])
-
-
-def downgrade() -> None:
-    op.drop_index("ix_gpu_job_status", table_name="gpu_job")
-    op.drop_index("ix_gpu_job_image_record_id", table_name="gpu_job")
-    op.drop_table("gpu_job")

alembic/versions/0063_ccip_match_threshold.py

@@ -1,33 +0,0 @@
-"""ml_settings.ccip_match_threshold — tunable CCIP character-match cut (#114)
-
-The v1 matcher used a flat 0.75 cosine; live data showed that over-fires (a
-high-reference character matched a scatter of images). 0.85 keeps the confident
-single-character matches and drops the noise. Tunable from the GPU agent card.
-
-Revision ID: 0063
-Revises: 0062
-Create Date: 2026-06-29
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0063"
-down_revision: Union[str, None] = "0062"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "ccip_match_threshold", sa.Float(), nullable=False,
-            server_default="0.85",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("ml_settings", "ccip_match_threshold")

alembic/versions/0064_ccip_auto_apply.py

@@ -1,42 +0,0 @@
-"""ml_settings: CCIP auto-apply switch + threshold (#114)
-
-Confident CCIP character matches auto-tag (source='ccip_auto') on a daily sweep,
-so identity tags keep flowing without pressing a button. ON by default (opt-out,
-like head auto-apply); the high threshold (0.92, above the 0.85 suggest cut) +
-single-character references keep it safe, and every auto-tag is reversible.
-
-Revision ID: 0064
-Revises: 0063
-Create Date: 2026-06-30
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-revision: str = "0064"
-down_revision: Union[str, None] = "0063"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "ccip_auto_apply_enabled", sa.Boolean(), nullable=False,
-            server_default=sa.true(),
-        ),
-    )
-    op.add_column(
-        "ml_settings",
-        sa.Column(
-            "ccip_auto_apply_threshold", sa.Float(), nullable=False,
-            server_default="0.92",
-        ),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("ml_settings", "ccip_auto_apply_threshold")
-    op.drop_column("ml_settings", "ccip_auto_apply_enabled")

backend/app/__init__.py

@@ -3,23 +3,13 @@
 import logging
 from pathlib import Path
 
-from quart import Quart, request
+from quart import Quart
 
 from .api import all_blueprints
 from .config import get_config
 from .frontend import frontend_bp
 from .services.credential_crypto import CredentialCrypto
 
-# Browser-extension origins. The FabledCurator extension fetches from
-# moz-extension://<uuid>/ on Firefox and chrome-extension://<uuid>/ on
-# Chromium-based browsers. Operator-flagged 2026-05-26: extension's
-# 'Test connection' returned `NetworkError` because the X-Extension-Key
-# header on /api/credentials triggers a CORS preflight that our routes
-# don't handle. Whitelisting only these two schemes (not opening CORS
-# up generally) lets the extension talk to a plain-HTTP self-hosted FC
-# without weakening the no-CORS posture for normal browser usage.
-_EXTENSION_ORIGIN_SCHEMES = ("moz-extension://", "chrome-extension://")
-
 _CREDENTIAL_KEY_PATH = Path("/images/secrets/credential_key.b64")
 
 
@@ -33,39 +23,18 @@ def create_app() -> Quart:
 
     app = Quart(__name__)
     app.secret_key = cfg.secret_key
+    # FC-5: legacy IR ingest JSON can run to tens of MB (hundreds of
+    # thousands of image_tag_associations). Werkzeug's default form
+    # memory cap is 500KB; raise both ceilings so the multipart upload
+    # for /api/migrate/ir_ingest doesn't 413.
+    app.config["MAX_CONTENT_LENGTH"] = 1024 * 1024 * 1024   # 1 GB
+    app.config["MAX_FORM_MEMORY_SIZE"] = 1024 * 1024 * 1024  # 1 GB
 
     for bp in all_blueprints():
         app.register_blueprint(bp)
     # Registered last so /api/* routes win over the SPA catch-all.
     app.register_blueprint(frontend_bp)
 
-    @app.before_request
-    async def _extension_cors_preflight():
-        # Short-circuit OPTIONS preflight from the browser extension with a
-        # 204 + CORS headers (the after_request hook below adds them).
-        # Without this, OPTIONS lands on routes that only declared POST/GET
-        # methods and 405s before the after_request gets a chance.
-        if request.method != "OPTIONS":
-            return None
-        origin = request.headers.get("Origin", "")
-        if any(origin.startswith(s) for s in _EXTENSION_ORIGIN_SCHEMES):
-            return "", 204
-        return None
-
-    @app.after_request
-    async def _extension_cors_headers(response):
-        origin = request.headers.get("Origin", "")
-        if any(origin.startswith(s) for s in _EXTENSION_ORIGIN_SCHEMES):
-            response.headers["Access-Control-Allow-Origin"] = origin
-            response.headers["Access-Control-Allow-Methods"] = (
-                "GET, POST, PATCH, DELETE, OPTIONS"
-            )
-            response.headers["Access-Control-Allow-Headers"] = (
-                "Content-Type, X-Extension-Key"
-            )
-            response.headers["Access-Control-Max-Age"] = "86400"
-        return response
-
     @app.after_serving
     async def _dispose_db_engine() -> None:
         from .extensions import dispose_engine

backend/app/api/__init__.py

@@ -20,15 +20,13 @@ def all_blueprints() -> list[Blueprint]:
     from .artist import artist_bp
     from .artists import artists_bp
     from .attachments import attachments_bp
-    from .ccip import ccip_bp
     from .cleanup import cleanup_bp
     from .credentials import credentials_bp
     from .downloads import downloads_bp
     from .extension import extension_bp
     from .gallery import gallery_bp
-    from .gpu import gpu_bp
-    from .heads import heads_bp
     from .import_admin import import_admin_bp
+    from .migrate import migrate_bp
     from .ml_admin import ml_admin_bp
     from .platforms import platforms_bp
     from .posts import posts_bp
@@ -39,9 +37,7 @@ def all_blueprints() -> list[Blueprint]:
     from .suggestions import suggestions_bp
     from .system_activity import system_activity_bp
     from .system_backup import system_backup_bp
-    from .tag_eval import tag_eval_bp
     from .tags import tags_bp
-    from .thumbnails import thumbnails_bp
     return [
         api_bp,
         attachments_bp,
@@ -57,15 +53,11 @@ def all_blueprints() -> list[Blueprint]:
         admin_bp,
         cleanup_bp,
         import_admin_bp,
+        migrate_bp,
         suggestions_bp,
         allowlist_bp,
         aliases_bp,
-        tag_eval_bp,
-        heads_bp,
-        gpu_bp,
-        ccip_bp,
         ml_admin_bp,
-        thumbnails_bp,
         sources_bp,
         platforms_bp,
         posts_bp,

backend/app/api/_responses.py

@@ -1,16 +0,0 @@
-"""Shared API response helpers."""
-
-from quart import jsonify
-
-
-def error_response(
-    error: str, *, status: int = 400, detail: str | None = None, **extra,
-):
-    """JSON error body + HTTP status. `detail` is included only when given;
-    `extra` keys are merged into the body. Returns the (response, status)
-    tuple Quart expects. Imported as `_bad` by the blueprints."""
-    body = {"error": error}
-    if detail is not None:
-        body["detail"] = detail
-    body.update(extra)
-    return jsonify(body), status

backend/app/api/admin.py

@@ -6,8 +6,6 @@ Five action surfaces:
   DELETE /api/admin/tags/<int:tag_id>              (Tier B)
   POST   /api/admin/tags/<int:dest_id>/merge       (Tier B)
   POST   /api/admin/tags/prune-unused              (Tier A)
-  POST   /api/admin/posts/prune-bare               (Tier A)
-  POST   /api/admin/tags/purge-legacy              (Tier A)
   GET    /api/admin/tags/<int:tag_id>/usage-count  (helper)
 
 Tier-C ops take a dry_run body flag (returns projection inline,
@@ -20,16 +18,21 @@ from __future__ import annotations
 import hashlib
 
 from quart import Blueprint, jsonify, request
-from sqlalchemy import select, text
+from sqlalchemy import select
 
 from ..extensions import get_session
 from ..models import Artist
 from ..services.cleanup_service import project_artist_cascade, project_bulk_image_delete
-from ._responses import error_response as _bad
 
 admin_bp = Blueprint("admin", __name__, url_prefix="/api/admin")
 
 
+def _bad(error: str, *, status: int = 400, **extra):
+    body = {"error": error}
+    body.update(extra)
+    return jsonify(body), status
+
+
 def _bulk_image_confirm_token(image_ids: list[int]) -> str:
     """Stable 8-hex token derived from the sorted id list. Mutates
     when the selection changes; stays the same across modal opens of
@@ -39,31 +42,6 @@ def _bulk_image_confirm_token(image_ids: list[int]) -> str:
     return digest[:8]
 
 
-async def _run_dry_run_op(service_fn, **service_kwargs):
-    """Shared body for the Tier-A dry-run/apply endpoints: read the `dry_run`
-    flag, run the cleanup_service predicate under `run_sync`, and return its
-    result dict. The SAME `service_fn` drives both preview and apply (the flag
-    just toggles), so a handler physically can't let its preview diverge from
-    its delete (rule 93). Default False preserves the existing contract — the UI
-    always passes `dry_run` explicitly (true to preview, false to apply). Extra
-    service kwargs (e.g. `source_id`) pass straight through."""
-    body = await request.get_json(silent=True) or {}
-    dry_run = bool(body.get("dry_run", False))
-    async with get_session() as session:
-        result = await session.run_sync(
-            lambda sync_sess: service_fn(sync_sess, dry_run=dry_run, **service_kwargs)
-        )
-    return jsonify(result)
-
-
-def _queued(async_result):
-    """Standard 202 for an operator-triggered maintenance task: hand the UI the
-    Celery task id so it can tail /maintenance/task-result (or the activity
-    dashboard) for the summary. (trigger_vacuum stays bespoke — the UI doesn't
-    poll it, so it returns no task id.)"""
-    return jsonify({"task_id": async_result.id, "status": "queued"}), 202
-
-
 @admin_bp.route("/artists/<slug>/cascade-delete", methods=["POST"])
 async def artist_cascade_delete(slug: str):
     body = await request.get_json(silent=True) or {}
@@ -119,19 +97,11 @@ async def images_bulk_delete():
             )
         )
 
-    sha8 = _bulk_image_confirm_token(image_ids)
-    expected = f"delete-images-{sha8}"
-
     if dry_run:
-        # Hand the canonical Tier-C confirm token back with the
-        # projection so the frontend doesn't have to recompute SHA-256
-        # client-side via crypto.subtle (Secure-Context-gated,
-        # undefined on plain-HTTP origins per the homelab posture).
-        # Operator-flagged 2026-05-27.
-        projected["confirm_token"] = expected
         return jsonify(projected)
 
-
+    sha8 = _bulk_image_confirm_token(image_ids)
+    expected = f"delete-images-{sha8}"
     if supplied_confirm != expected:
         return _bad(
             "confirm_mismatch",
@@ -171,30 +141,6 @@ async def tag_merge(dest_id: int):
     if not isinstance(source_id, int) or source_id == dest_id:
         return _bad("invalid_source_id", detail="source_id must be int and differ from dest")
 
-    # dry_run: non-mutating preview (counts + sample) so the operator can
-    # confirm the target before the irreversible merge (#8, rule 93 parity).
-    if body.get("dry_run"):
-        async with get_session() as session:
-            try:
-                p = await TagService(session).merge_preview(
-                    source_id=source_id, target_id=dest_id,
-                )
-            except TagValidationError as exc:
-                return _bad("tag_not_found", status=404, detail=str(exc))
-        return jsonify({
-            "preview": {
-                "source_id": p.source_id, "source_name": p.source_name,
-                "target_id": p.target_id, "target_name": p.target_name,
-                "compatible": p.compatible,
-                "images_moving": p.images_moving,
-                "images_already_on_target": p.images_already_on_target,
-                "source_total": p.source_total,
-                "series_pages": p.series_pages,
-                "will_alias": p.will_alias,
-                "sample_thumbnails": p.sample_thumbnails,
-            },
-        })
-
     async with get_session() as session:
         try:
             result = await TagService(session).merge(
@@ -242,206 +188,13 @@ async def tags_prune_unused():
     re-call with dry_run=false."""
     from ..services.cleanup_service import prune_unused_tags
 
-    return await _run_dry_run_op(prune_unused_tags)
-
-
-@admin_bp.route("/posts/prune-bare", methods=["POST"])
-async def posts_prune_bare():
-    """Tier-A: delete bare posts — Post rows with no linked images (primary OR
-    provenance) and no attachments. Dry-run preview list IS the prompt: UI calls
-    with dry_run=true first, shows the count + sample, operator confirms by
-    re-calling with dry_run=false. Same preview/apply-parity predicate as the
-    prune itself, so the preview can't diverge from the delete."""
-    from ..services.cleanup_service import prune_bare_posts
-
-    return await _run_dry_run_op(prune_bare_posts)
-
-
-@admin_bp.route("/posts/reconcile-duplicates", methods=["POST"])
-async def posts_reconcile_duplicates():
-    """Tier-A: unify duplicate post rows for the same real post — the gallery-dl
-    (attachment-id) + native (post-id) duplicates — onto ONE post-id-keyed keeper,
-    moving image/provenance/attachment/link rows over. Images are untouched.
-    dry_run=true returns {groups, posts_to_merge, sample}; dry_run=false applies
-    and returns {groups, merged, sample}. Optional source_id scopes to one source.
-    Same find_duplicate_post_groups predicate drives preview + apply (rule 93)."""
-    from ..services.cleanup_service import reconcile_duplicate_posts
-
     body = await request.get_json(silent=True) or {}
-    raw_source = body.get("source_id")
-    try:
-        source_id = int(raw_source) if raw_source is not None else None
-    except (TypeError, ValueError):
-        return _bad("invalid_source_id", detail="source_id must be an integer")
+    dry_run = bool(body.get("dry_run", False))
 
-    return await _run_dry_run_op(reconcile_duplicate_posts, source_id=source_id)
-
-
-@admin_bp.route("/tags/purge-legacy", methods=["POST"])
-async def tags_purge_legacy():
-    """Tier-A: delete legacy IR-migration tags — archive/post/artist
-    kinds (e.g. `BlenderKnight:Hannah_BJ_Loops`) PLUS general tags with
-    a legacy name prefix (`source:*`, from IR's source kind that fell
-    back to general). dry-run preview returns per-kind + per-prefix
-    counts + a sample so the UI shows exactly what'll go before the
-    operator confirms with dry_run=false."""
-    from ..services.cleanup_service import purge_legacy_tags
-
-    return await _run_dry_run_op(purge_legacy_tags)
-
-
-@admin_bp.route("/tags/reset-content", methods=["POST"])
-async def tags_reset_content():
-    """Tier-A: delete ALL general + character tags (the Camie-suggestable
-    content vocabulary) so the operator can re-tag from scratch via
-    auto-suggest. fandom + series tags + series_page ordering are preserved,
-    and image_prediction rows are untouched so suggestions repopulate.
-    dry-run preview returns per-kind counts + applications + a sample so the
-    UI shows exactly what'll go before the operator confirms (dry_run=false).
-    Irreversible except via DB backup restore."""
-    from ..services.cleanup_service import reset_content_tagging
-
-    return await _run_dry_run_op(reset_content_tagging)
-
-
-@admin_bp.route("/tags/normalize", methods=["POST"])
-async def tags_normalize():
-    """#714: retro-normalize existing tags to the #701 canonical form (Title
-    Case + collapsed whitespace) and merge case/whitespace-variant duplicates.
-
-    dry_run=true (default) returns a projection inline — group/collision/rename
-    counts + a sample of the changes — so the UI shows exactly what'll happen.
-    dry_run=false dispatches the long-running maintenance task (the merge FK
-    repoints can touch many tags); the UI tails the activity dashboard for the
-    summary. Idempotent; back up first (the merges are irreversible)."""
-    from ..services.tag_service import normalize_existing_tags
-
-    body = await request.get_json(silent=True) or {}
-    dry_run = bool(body.get("dry_run", True))
-
-    if dry_run:
-        async with get_session() as session:
-            result = await normalize_existing_tags(session, dry_run=True)
-        return jsonify(result)
-
-    from ..tasks.admin import normalize_tags_task
-
-    async_result = normalize_tags_task.delay()
-    return _queued(async_result)
-
-
-@admin_bp.route("/maintenance/db-stats", methods=["GET"])
-async def db_stats():
-    """Per-table bloat readout (pg_stat_user_tables) for the high-churn tables
-    so the operator can see when a VACUUM is worth running."""
-    from ..tasks.maintenance import VACUUM_TABLES
-
-    wanted = set(VACUUM_TABLES)
     async with get_session() as session:
-        rows = (await session.execute(text(
-            "SELECT relname, n_live_tup, n_dead_tup, last_vacuum, "
-            "last_autovacuum, last_analyze FROM pg_stat_user_tables"
-        ))).all()
-
-    def _iso(v):
-        return v.isoformat() if v is not None else None
-
-    out = []
-    for r in rows:
-        if r.relname not in wanted:
-            continue
-        live = r.n_live_tup or 0
-        dead = r.n_dead_tup or 0
-        total = live + dead
-        out.append({
-            "table": r.relname,
-            "live": live,
-            "dead": dead,
-            "dead_pct": round(100 * dead / total, 1) if total else 0.0,
-            "last_vacuum": _iso(r.last_vacuum),
-            "last_autovacuum": _iso(r.last_autovacuum),
-            "last_analyze": _iso(r.last_analyze),
-        })
-    out.sort(key=lambda t: t["dead"], reverse=True)
-    return jsonify({"tables": out})
-
-
-@admin_bp.route("/maintenance/vacuum", methods=["POST"])
-async def trigger_vacuum():
-    """Operator-triggered VACUUM (ANALYZE) over the high-churn tables — the
-    same maintenance-queue task the weekly Beat schedule runs."""
-    from ..tasks.maintenance import vacuum_analyze
-
-    vacuum_analyze.delay()
-    return jsonify({"status": "queued"}), 202
-
-
-@admin_bp.route("/maintenance/reextract-archives", methods=["POST"])
-async def trigger_reextract_archives():
-    """Operator-triggered re-extract (#713): PostAttachments that are actually
-    archives but were filed opaquely (pre magic-byte gate) get extracted and
-    their members linked to the post. Idempotent; runs on the maintenance queue."""
-    from ..tasks.admin import reextract_archive_attachments_task
-
-    async_result = reextract_archive_attachments_task.delay()
-    return _queued(async_result)
-
-
-@admin_bp.route("/maintenance/prune-missing-files", methods=["POST"])
-async def trigger_prune_missing_files():
-    """Operator-triggered orphan repair (#859): delete ImageRecords whose backing
-    file is gone from disk (e.g. left by the external-attach unlink bug), so they
-    stop 404-ing on playback. The task aborts WITHOUT deleting if a large fraction
-    of files look missing (a filesystem/NFS stall). Maintenance queue;
-    operator-triggered only — never an unattended sweep."""
-    from ..tasks.admin import prune_missing_file_records_task
-
-    async_result = prune_missing_file_records_task.delay()
-    return _queued(async_result)
-
-
-@admin_bp.route("/maintenance/dedup-videos", methods=["POST"])
-async def trigger_dedup_videos():
-    """Tier-1 video dedup (#871). Body {"dry_run": bool}: dry_run=true previews
-    what would be removed (groups / redundant count / reclaimable bytes) WITHOUT
-    deleting; dry_run=false applies it (re-link posts to the keeper, then delete
-    the redundant copies). Either way it first re-probes NULL-duration videos so
-    the existing library participates. Returns the Celery task id — poll
-    /maintenance/task-result/<id> for the summary."""
-    from ..tasks.admin import dedup_videos_task
-
-    body = await request.get_json(silent=True) or {}
-    dry_run = bool(body.get("dry_run", True))  # default to the SAFE preview
-    async_result = dedup_videos_task.delay(dry_run=dry_run)
-    return _queued(async_result)
-
-
-@admin_bp.route("/maintenance/purge-gated-previews", methods=["POST"])
-async def trigger_purge_gated_previews():
-    """Cleanup (#874 follow-up). Body {"dry_run": bool}: dry_run=true previews how
-    many blurred locked-preview images (grabbed from tier-gated Patreon posts
-    before the fix) would be removed WITHOUT deleting; dry_run=false applies it.
-    Re-walks every enabled Patreon source read-only and matches by content hash, so
-    real content downloaded when access existed is provably spared. Returns the
-    Celery task id — poll /maintenance/task-result/<id> for the summary."""
-    from ..tasks.admin import purge_gated_previews_task
-
-    body = await request.get_json(silent=True) or {}
-    dry_run = bool(body.get("dry_run", True))  # default to the SAFE preview
-    async_result = purge_gated_previews_task.delay(dry_run=dry_run)
-    return _queued(async_result)
-
-
-@admin_bp.route("/maintenance/task-result/<task_id>", methods=["GET"])
-async def maintenance_task_result(task_id: str):
-    """Poll a maintenance Celery task's result (the summary dict it returns).
-    Used by the video-dedup card to show the dry-run projection before apply."""
-    from ..celery_app import celery
-
-    res = celery.AsyncResult(task_id)
-    ready = res.ready()
-    return jsonify({
-        "ready": ready,
-        "successful": res.successful() if ready else None,
-        "result": res.result if (ready and res.successful()) else None,
-    })
+        result = await session.run_sync(
+            lambda sync_sess: prune_unused_tags(
+                sync_sess, dry_run=dry_run,
+            )
+        )
+    return jsonify(result)

backend/app/api/allowlist.py

@@ -20,37 +20,12 @@ async def list_allowlist():
                 "tag_name": r.tag_name,
                 "tag_kind": r.tag_kind,
                 "min_confidence": r.min_confidence,
-                "applied_count": r.applied_count,
-                "coverage_count": r.coverage_count,
             }
             for r in rows
         ]
     )
 
 
-@allowlist_bp.route("/tags/<int:tag_id>/allowlist/coverage", methods=["GET"])
-async def coverage(tag_id: int):
-    """Live "at threshold T, a sweep would cover ~N images" projection for the
-    allowlist tuning dashboard. Defaults to the tag's stored threshold."""
-    raw = request.args.get("threshold")
-    async with get_session() as session:
-        svc = AllowlistService(session)
-        if raw is not None:
-            try:
-                threshold = float(raw)
-            except ValueError:
-                return jsonify({"error": "threshold must be a float"}), 400
-            if not (0 < threshold <= 1):
-                return jsonify({"error": "threshold must be in (0, 1]"}), 400
-        else:
-            row = await session.get(TagAllowlist, tag_id)
-            if row is None:
-                return jsonify({"error": "not on allowlist"}), 404
-            threshold = row.min_confidence
-        count = await svc.coverage(tag_id, threshold)
-    return jsonify({"count": count, "threshold": threshold})
-
-
 @allowlist_bp.route("/tags/<int:tag_id>/allowlist", methods=["GET"])
 async def get_one(tag_id: int):
     async with get_session() as session:

backend/app/api/ccip.py

@@ -1,124 +0,0 @@
-"""CCIP / region observability API (#114) — read-only, analysis-shaped.
-
-So the work can be checked through an API as the agent fills in vectors: overall
-coverage (regions by kind, how many images have figure CCIP vectors, which
-characters have enough reference examples to match on) + a per-image drill-down
-(its regions + the CCIP character matches it would get). Mirrors the heads
-metrics endpoint; no GPU, just reads what's stored.
-"""
-
-from quart import Blueprint, jsonify
-from sqlalchemy import distinct, func, select
-
-from ..extensions import get_session
-from ..models import ImageRegion, Tag, TagKind
-from ..models.tag import image_tag
-from ..services.ml.ccip import match_image
-
-ccip_bp = Blueprint("ccip", __name__, url_prefix="/api/ccip")
-
-_FIGURE_KINDS = ("face", "figure")
-
-
-@ccip_bp.route("/overview", methods=["GET"])
-async def overview():
-    async with get_session() as session:
-        by_kind = dict(
-            (
-                await session.execute(
-                    select(ImageRegion.kind, func.count()).group_by(ImageRegion.kind)
-                )
-            ).all()
-        )
-        images_with_figure_ccip = (
-            await session.execute(
-                select(func.count(distinct(ImageRegion.image_record_id)))
-                .where(ImageRegion.kind.in_(_FIGURE_KINDS))
-                .where(ImageRegion.ccip_embedding.is_not(None))
-            )
-        ).scalar_one()
-        # Concept-crop (SigLIP bag) coverage — how far the back-catalogue embed
-        # has progressed, so the max-over-bag scorer's reach is checkable.
-        images_with_concept_siglip = (
-            await session.execute(
-                select(func.count(distinct(ImageRegion.image_record_id)))
-                .where(ImageRegion.kind == "concept")
-                .where(ImageRegion.siglip_embedding.is_not(None))
-            )
-        ).scalar_one()
-        # Per-character reference counts (no vectors loaded) — which characters
-        # have enough examples to match on.
-        ref_rows = (
-            await session.execute(
-                select(image_tag.c.tag_id, Tag.name, func.count())
-                .select_from(ImageRegion)
-                .join(
-                    image_tag,
-                    image_tag.c.image_record_id == ImageRegion.image_record_id,
-                )
-                .join(Tag, Tag.id == image_tag.c.tag_id)
-                .where(Tag.kind == TagKind.character)
-                .where(ImageRegion.kind.in_(_FIGURE_KINDS))
-                .where(ImageRegion.ccip_embedding.is_not(None))
-                .group_by(image_tag.c.tag_id, Tag.name)
-                .order_by(func.count().desc())
-            )
-        ).all()
-        versions = [
-            v for (v,) in (
-                await session.execute(
-                    select(distinct(ImageRegion.embedding_version))
-                )
-            ).all() if v
-        ]
-        auto_applied = (
-            await session.execute(
-                select(func.count()).select_from(image_tag).where(
-                    image_tag.c.source == "ccip_auto"
-                )
-            )
-        ).scalar_one()
-    return jsonify({
-        "regions_by_kind": by_kind,
-        "images_with_figure_ccip": images_with_figure_ccip,
-        "images_with_concept_siglip": images_with_concept_siglip,
-        "characters_with_references": len(ref_rows),
-        "character_references": [
-            {"tag_id": t, "name": n, "n_refs": c} for (t, n, c) in ref_rows
-        ],
-        "embedding_versions": versions,
-        "auto_applied": auto_applied,
-    })
-
-
-@ccip_bp.route("/images/<int:image_id>", methods=["GET"])
-async def image_detail(image_id: int):
-    """An image's stored regions + the CCIP character matches it would get —
-    for spot-checking the agent's output + the matcher."""
-    async with get_session() as session:
-        regions = (
-            await session.execute(
-                select(ImageRegion)
-                .where(ImageRegion.image_record_id == image_id)
-                .order_by(ImageRegion.id)
-            )
-        ).scalars().all()
-        matches = await match_image(session, image_id)
-    return jsonify({
-        "image_id": image_id,
-        "regions": [
-            {
-                "id": r.id,
-                "kind": r.kind,
-                "bbox": [r.rx, r.ry, r.rw, r.rh],
-                "frame_time": r.frame_time,
-                "score": r.score,
-                "detector_version": r.detector_version,
-                "embedding_version": r.embedding_version,
-                "has_ccip": r.ccip_embedding is not None,
-                "has_siglip": r.siglip_embedding is not None,
-            }
-            for r in regions
-        ],
-        "ccip_matches": matches,
-    })

backend/app/api/cleanup.py

@@ -31,13 +31,18 @@ from sqlalchemy import select
 from ..extensions import get_session
 from ..models import LibraryAuditRun
 from ..services import cleanup_service
-from ._responses import error_response as _bad
 
 cleanup_bp = Blueprint("cleanup", __name__, url_prefix="/api/cleanup")
 
 IMAGES_ROOT = Path("/images")
 
 
+def _bad(error: str, *, status: int = 400, **extra):
+    body = {"error": error}
+    body.update(extra)
+    return jsonify(body), status
+
+
 def _min_dim_token(min_w: int, min_h: int) -> str:
     # SHA-256 (not MD5) — Web Crypto's subtle.digest rejects MD5; both
     # sides use SHA-256 truncated to 8 hex chars.
@@ -76,13 +81,6 @@ async def min_dim_preview():
                 s, min_width=min_w, min_height=min_h,
             )
         )
-    # Hand the canonical Tier-C delete token back with the preview so
-    # the frontend doesn't have to recompute SHA-256 client-side.
-    # window.crypto.subtle is Secure-Context-gated and undefined on
-    # plain-HTTP origins (homelab posture); without this the Delete
-    # button silently swallowed the TypeError and never opened the
-    # confirm modal. Operator-flagged 2026-05-27.
-    projection["confirm_token"] = _min_dim_token(min_w, min_h)
     return jsonify(projection)
 
 
@@ -154,15 +152,12 @@ async def audit_history():
         limit = min(int(request.args.get("limit", "20")), 100)
     except ValueError:
         return _bad("invalid_limit")
-    # Optional rule filter so a card can reconnect to ITS latest run on mount
-    # (?rule=transparency&limit=1) — the audit survives navigation; the UI
-    # rehydrates from this rather than losing the in-flight scan.
-    rule = request.args.get("rule") or None
     async with get_session() as session:
-        stmt = select(LibraryAuditRun).order_by(LibraryAuditRun.id.desc())
-        if rule is not None:
-            stmt = stmt.where(LibraryAuditRun.rule == rule)
-        rows = (await session.execute(stmt.limit(limit))).scalars().all()
+        rows = (await session.execute(
+            select(LibraryAuditRun)
+            .order_by(LibraryAuditRun.id.desc())
+            .limit(limit)
+        )).scalars().all()
         return jsonify({"runs": [_serialize_audit_run(r) for r in rows]})
 
 

backend/app/api/credentials.py

@@ -20,7 +20,6 @@ from ..services.credential_service import (
     UnknownPlatformError,
     WrongAuthTypeError,
 )
-from ._responses import error_response as _bad
 
 credentials_bp = Blueprint("credentials", __name__, url_prefix="/api/credentials")
 
@@ -39,6 +38,14 @@ def _get_crypto() -> CredentialCrypto:
     return _crypto
 
 
+def _bad(error: str, *, status: int = 400, detail: str | None = None, **extra):
+    body = {"error": error}
+    if detail is not None:
+        body["detail"] = detail
+    body.update(extra)
+    return jsonify(body), status
+
+
 async def _ext_key_ok(session) -> bool:
     """If X-Extension-Key is supplied, it must match the stored value.
     Missing header → True (browser path; accepted per homelab posture).
@@ -117,58 +124,3 @@ async def delete_credential(platform: str):
         except LookupError:
             return _bad("not_found", status=404)
     return "", 204
-
-
-@credentials_bp.route("/<platform>/verify", methods=["POST"])
-async def verify_credential(platform: str):
-    """Test the stored credential against one of the platform's enabled sources,
-    WITHOUT downloading. Routes through the platform's backend
-    (download_backends.verify_credential) — native ingester for Patreon, an
-    authenticated API page; gallery-dl --simulate for the rest. On success
-    stamps last_verified. Returns {valid: bool|null, reason, last_verified?};
-    valid=null means "couldn't test" (no credential, no enabled source, or an
-    inconclusive network/drift result)."""
-    from ..models import Artist, Source
-    from ..services.download_backends import verify_source_credential
-
-    async with get_session() as session:
-        if not await _ext_key_ok(session):
-            return _bad("unauthorized", status=401)
-        svc = CredentialService(session, _get_crypto())
-        record = await svc.get(platform)
-        if record is None:
-            return jsonify({"valid": None, "reason": "No credential stored for this platform."})
-
-        # Pick an enabled source for this platform to point the probe at.
-        row = (await session.execute(
-            select(Source, Artist)
-            .join(Artist, Artist.id == Source.artist_id)
-            .where(Source.platform == platform, Source.enabled.is_(True))
-            .order_by(Source.id.asc())
-        )).first()
-        if row is None:
-            return jsonify({
-                "valid": None,
-                "reason": "No enabled source for this platform to verify against — add a subscription first.",
-            })
-        source, artist = row
-
-        cookies_path = await svc.get_cookies_path(platform)
-        auth_token = await svc.get_token(platform)
-
-    ok, message = await verify_source_credential(
-        platform=platform,
-        url=source.url,
-        artist_slug=artist.slug,
-        config_overrides=source.config_overrides or {},
-        cookies_path=str(cookies_path) if cookies_path else None,
-        auth_token=auth_token,
-        images_root=Path("/images"),
-    )
-
-    last_verified = None
-    if ok:
-        async with get_session() as session:
-            ts = await CredentialService(session, _get_crypto()).mark_verified(platform)
-            last_verified = ts.isoformat() if ts else None
-    return jsonify({"valid": ok, "reason": message, "last_verified": last_verified})

backend/app/api/downloads.py

@@ -5,10 +5,8 @@ status/source/artist. Returns slim records.
 Detail view: full DownloadEvent including the metadata JSONB.
 """
 
-from datetime import UTC, datetime, timedelta
-
 from quart import Blueprint, jsonify, request
-from sqlalchemy import func, select
+from sqlalchemy import select
 
 from ..extensions import get_session
 from ..models import Artist, DownloadEvent, Source
@@ -44,9 +42,6 @@ def _list_record(event: DownloadEvent, source: Source | None, artist: Artist | N
         "bytes_downloaded": event.bytes_downloaded,
         "error": event.error,
         "summary": _summary_from_metadata(event.metadata_),
-        # plan #709: mid-walk live counts for a RUNNING native-ingester event
-        # (None otherwise; phase 3 overwrites metadata with run_stats on finish).
-        "live": (event.metadata_ or {}).get("live"),
     }
 
 
@@ -100,83 +95,6 @@ async def list_downloads():
     return jsonify([_list_record(e, s, a) for e, s, a in rows])
 
 
-@downloads_bp.route("/stats", methods=["GET"])
-async def downloads_stats():
-    """Status-grouped count over download_event for the dashboard stat chips.
-
-    `?window_hours=` (default 24) bounds by `started_at`. The full set of
-    statuses is always present in the response (zero for missing) so the
-    UI doesn't have to fill in defaults.
-    """
-    try:
-        window_hours = int(request.args.get("window_hours", "24"))
-    except ValueError:
-        return jsonify({"error": "invalid_window_hours"}), 400
-    if window_hours < 1 or window_hours > 24 * 365:
-        return jsonify({"error": "invalid_window_hours"}), 400
-
-    since = datetime.now(UTC) - timedelta(hours=window_hours)
-    out = {"pending": 0, "running": 0, "ok": 0, "error": 0, "skipped": 0}
-    async with get_session() as session:
-        stmt = (
-            select(DownloadEvent.status, func.count())
-            .where(DownloadEvent.started_at >= since)
-            .group_by(DownloadEvent.status)
-        )
-        for status, n in (await session.execute(stmt)).all():
-            if status in out:
-                out[status] = int(n)
-    return jsonify(out)
-
-
-@downloads_bp.route("/activity", methods=["GET"])
-async def downloads_activity():
-    """Hourly download-event counts over the last `?hours=` (default 24).
-
-    Returns a fixed-length, oldest-first bucket array so the UI can render
-    a sparkline directly. Bucketing is done in Python against UTC to dodge
-    session-timezone ambiguity in SQL date_trunc.
-    """
-    try:
-        hours = int(request.args.get("hours", "24"))
-    except ValueError:
-        return jsonify({"error": "invalid_hours"}), 400
-    hours = max(1, min(168, hours))
-
-    now = datetime.now(UTC)
-    end = now.replace(minute=0, second=0, microsecond=0)
-    start = end - timedelta(hours=hours - 1)
-    buckets = [
-        {"hour": (start + timedelta(hours=i)).isoformat(),
-         "ok": 0, "error": 0, "other": 0, "total": 0}
-        for i in range(hours)
-    ]
-
-    async with get_session() as session:
-        rows = (await session.execute(
-            select(DownloadEvent.started_at, DownloadEvent.status)
-            .where(DownloadEvent.started_at >= start)
-        )).all()
-
-    for started_at, status in rows:
-        if started_at is None:
-            continue
-        sa = started_at if started_at.tzinfo else started_at.replace(tzinfo=UTC)
-        idx = int((sa - start).total_seconds() // 3600)
-        if not (0 <= idx < hours):
-            continue
-        b = buckets[idx]
-        if status == "ok":
-            b["ok"] += 1
-        elif status == "error":
-            b["error"] += 1
-        else:
-            b["other"] += 1
-        b["total"] += 1
-
-    return jsonify({"hours": hours, "buckets": buckets})
-
-
 @downloads_bp.route("/<int:event_id>", methods=["GET"])
 async def get_download(event_id: int):
     async with get_session() as session:
@@ -190,20 +108,3 @@ async def get_download(event_id: int):
             return jsonify({"error": "not_found"}), 404
         event, source, artist = row
     return jsonify(_detail_record(event, source, artist))
-
-
-@downloads_bp.route("/recover-stalled", methods=["POST"])
-async def recover_stalled():
-    """Trigger the recover_stalled_download_events sweep on demand.
-
-    The same sweep runs every 5 min via Beat (see celery_app.beat_schedule);
-    this endpoint exists so the operator can force-clear stuck pending/
-    running download_events from the Subscriptions → Downloads maintenance
-    menu without waiting for the next scheduled tick.
-    """
-    # Local import: avoids registering maintenance tasks during blueprint
-    # import (Celery task discovery races with the API import otherwise).
-    from ..tasks.maintenance import recover_stalled_download_events
-
-    recover_stalled_download_events.delay()
-    return jsonify({"queued": True}), 202

backend/app/api/extension.py

@@ -20,7 +20,6 @@ from ..services.extension_service import (
     UnknownPlatformError,
 )
 from ..services.source_service import KNOWN_PLATFORMS
-from ._responses import error_response as _bad
 
 extension_bp = Blueprint("extension", __name__, url_prefix="/api/extension")
 
@@ -31,6 +30,12 @@ XPI_DIR = Path("/app/frontend/dist/extension")
 _XPI_VERSION_RE = re.compile(r"fabledcurator-(?P<version>[\w.-]+)\.xpi$")
 
 
+def _bad(error: str, *, status: int = 400, **extra):
+    body = {"error": error}
+    body.update(extra)
+    return jsonify(body), status
+
+
 async def _ext_key_required(session) -> bool:
     """Unlike /api/credentials (which accepts the browser path with no
     header), quick-add-source writes server state and must be explicitly
@@ -57,24 +62,6 @@ def _sha256(path: Path) -> str:
     return h.hexdigest()
 
 
-@extension_bp.route("/probe", methods=["GET"])
-async def probe_source():
-    """Read-only resolution of a creator-page URL: tells the extension
-    whether this URL is already a Source, is for an Artist that exists
-    but with a different URL, is brand new, or doesn't match any known
-    platform pattern. Drives the content-script chip's color/copy
-    BEFORE the operator clicks, so the button can show 'already added'
-    without requiring an add-attempt."""
-    url = (request.args.get("url") or "").strip()
-    if not url:
-        return _bad("invalid_body", detail="url query parameter is required")
-    async with get_session() as session:
-        if not await _ext_key_required(session):
-            return _bad("unauthorized", status=401)
-        result = await ExtensionService(session).probe(url)
-    return jsonify(result)
-
-
 @extension_bp.route("/quick-add-source", methods=["POST"])
 async def quick_add_source():
     body = await request.get_json(silent=True)

backend/app/api/gallery.py

@@ -1,6 +1,4 @@
-"""Gallery API: cursor scroll, timeline, jump, image detail, facets."""
-
-from datetime import UTC, datetime, timedelta
+"""Gallery API: cursor scroll, timeline, jump, image detail."""
 
 from quart import Blueprint, jsonify, request
 
@@ -10,104 +8,47 @@ from ..services.gallery_service import GalleryService
 gallery_bp = Blueprint("gallery", __name__, url_prefix="/api/gallery")
 
 
-def _image_json(i):
-    """Serialize a GalleryImage for the scroll/similar list responses."""
-    return {
-        "id": i.id,
-        "sha256": i.sha256,
-        "mime": i.mime,
-        "width": i.width,
-        "height": i.height,
-        "created_at": i.created_at.isoformat(),
-        "posted_at": i.posted_at.isoformat() if i.posted_at else None,
-        "thumbnail_url": i.thumbnail_url,
-        "artist": i.artist,
-    }
-
-
-def _parse_date(raw):
-    """Parse a YYYY-MM-DD query value to a UTC midnight datetime, or None.
-    Raises ValueError (→ 400) on a malformed value."""
-    if not raw:
-        return None
-    return datetime.strptime(raw, "%Y-%m-%d").replace(tzinfo=UTC)
-
-
-def _parse_filters():
-    """Parse the composable gallery filters from query args, returning
-    ``(filters_dict, sort)``. Raises ValueError (→ 400) on malformed ids/dates.
-
-    The structured tag filter (#6) is AND-of-OR plus exclusions:
-    - `tag_id` accepts a single id or a comma-separated list — all ANDed
-      (the include common case; back-compat).
-    - `tag_or` is REPEATABLE; each instance is a comma-separated OR-group, and
-      the image must match at least one tag from EACH group (groups ANDed).
-    - `tag_not` is a comma-separated exclude list (image must carry none).
-
-    `media` is image|video; `sort` is newest|oldest; `platform` selects one
-    platform (or the UNSOURCED_PLATFORM sentinel); `untagged`/`no_artist` are
-    boolean flags; `date_from`/`date_to` are inclusive calendar-day bounds
-    (date_to is widened by a day so the whole day is covered by the service's
-    half-open `< date_to`)."""
-    tag_raw = request.args.get("tag_id")
-    tag_ids = (
-        [int(x) for x in tag_raw.split(",") if x.strip()] if tag_raw else None
-    ) or None
-    tag_or_groups = [
-        grp for raw in request.args.getlist("tag_or")
-        if (grp := [int(x) for x in raw.split(",") if x.strip()])
-    ] or None
-    not_raw = request.args.get("tag_not")
-    tag_exclude = (
-        [int(x) for x in not_raw.split(",") if x.strip()] if not_raw else None
-    ) or None
-    post_id_raw = request.args.get("post_id")
-    post_id = int(post_id_raw) if post_id_raw else None
-    artist_id_raw = request.args.get("artist_id")
-    artist_id = int(artist_id_raw) if artist_id_raw else None
-    media = request.args.get("media")
-    media_type = media if media in ("image", "video") else None
-    sort = request.args.get("sort")
-    sort = sort if sort in ("newest", "oldest") else "newest"
-    platform = request.args.get("platform") or None
-    untagged = request.args.get("untagged") in ("1", "true", "yes")
-    no_artist = request.args.get("no_artist") in ("1", "true", "yes")
-    date_from = _parse_date(request.args.get("date_from"))
-    date_to = _parse_date(request.args.get("date_to"))
-    if date_to is not None:
-        date_to += timedelta(days=1)  # inclusive of the date_to calendar day
-    filters = {
-        "tag_ids": tag_ids, "post_id": post_id, "artist_id": artist_id,
-        "media_type": media_type,
-        "tag_or_groups": tag_or_groups, "tag_exclude": tag_exclude,
-        "platform": platform,
-        "untagged": untagged, "no_artist": no_artist,
-        "date_from": date_from, "date_to": date_to,
-    }
-    return filters, sort
-
-
 @gallery_bp.route("/scroll", methods=["GET"])
 async def scroll():
     cursor = request.args.get("cursor") or None
     try:
         limit = int(request.args.get("limit", "50"))
-        filters, sort = _parse_filters()
     except ValueError:
-        return jsonify({"error": "invalid filter or limit parameter"}), 400
+        return jsonify({"error": "limit must be an integer"}), 400
+    tag_id_raw = request.args.get("tag_id")
+    tag_id = int(tag_id_raw) if tag_id_raw else None
+    post_id_raw = request.args.get("post_id")
+    post_id = int(post_id_raw) if post_id_raw else None
+    artist_id_raw = request.args.get("artist_id")
+    artist_id = int(artist_id_raw) if artist_id_raw else None
 
     async with get_session() as session:
         svc = GalleryService(session)
         try:
             page = await svc.scroll(
-                cursor=cursor, limit=limit, sort=sort, **filters,
+                cursor=cursor, limit=limit, tag_id=tag_id,
+                post_id=post_id, artist_id=artist_id,
             )
         except ValueError as exc:
             return jsonify({"error": str(exc)}), 400
 
     return jsonify(
         {
-            "images": [_image_json(i) for i in page.images],
+            "images": [
+                {
+                    "id": i.id,
+                    "sha256": i.sha256,
+                    "mime": i.mime,
+                    "width": i.width,
+                    "height": i.height,
+                    "created_at": i.created_at.isoformat(),
+                    "posted_at": i.posted_at.isoformat() if i.posted_at else None,
+                    "effective_date": i.effective_date.isoformat(),
+                    "thumbnail_url": i.thumbnail_url,
+                    "artist": i.artist,
+                }
+                for i in page.images
+            ],
             "next_cursor": page.next_cursor,
             "date_groups": [
                 {"year": y, "month": m, "image_ids": ids} for y, m, ids in page.date_groups
@@ -116,46 +57,20 @@ async def scroll():
     )
 
 
-@gallery_bp.route("/similar", methods=["GET"])
-async def similar():
-    """Visual "more like this": images ranked by cosine distance to the
-    `similar_to` image's embedding. Composes with the scope filters (AND) but
-    ignores post_id and sort. Bounded top-N, no cursor."""
-    try:
-        similar_to = int(request.args["similar_to"])
-        limit = int(request.args.get("limit", "100"))
-        filters, _sort = _parse_filters()
-    except (KeyError, ValueError):
-        return jsonify({"error": "similar_to query param required"}), 400
-    # post_id is the exclusive post-detail view — not a similarity scope.
-    scope = {k: v for k, v in filters.items() if k != "post_id"}
-    async with get_session() as session:
-        svc = GalleryService(session)
-        try:
-            images = await svc.similar(image_id=similar_to, limit=limit, **scope)
-        except ValueError as exc:
-            return jsonify({"error": str(exc)}), 400
-    if images is None:
-        return jsonify({"error": "not found"}), 404
-    return jsonify(
-        {
-            "images": [_image_json(i) for i in images],
-            "next_cursor": None,
-            "date_groups": [],
-        }
-    )
-
-
 @gallery_bp.route("/timeline", methods=["GET"])
 async def timeline():
-    try:
-        filters, _sort = _parse_filters()
-    except ValueError:
-        return jsonify({"error": "invalid filter parameter"}), 400
+    tag_id_raw = request.args.get("tag_id")
+    tag_id = int(tag_id_raw) if tag_id_raw else None
+    post_id_raw = request.args.get("post_id")
+    post_id = int(post_id_raw) if post_id_raw else None
+    artist_id_raw = request.args.get("artist_id")
+    artist_id = int(artist_id_raw) if artist_id_raw else None
     async with get_session() as session:
         svc = GalleryService(session)
         try:
-            buckets = await svc.timeline(**filters)
+            buckets = await svc.timeline(
+                tag_id=tag_id, post_id=post_id, artist_id=artist_id
+            )
         except ValueError as exc:
             return jsonify({"error": str(exc)}), 400
     return jsonify(
@@ -163,43 +78,25 @@ async def timeline():
     )
 
 
-@gallery_bp.route("/facets", methods=["GET"])
-async def facets():
-    try:
-        filters, _sort = _parse_filters()
-    except ValueError:
-        return jsonify({"error": "invalid filter parameter"}), 400
-    async with get_session() as session:
-        svc = GalleryService(session)
-        try:
-            f = await svc.facets(**filters)
-        except ValueError as exc:
-            return jsonify({"error": str(exc)}), 400
-    return jsonify(
-        {
-            "total": f.total,
-            "platforms": f.platforms,
-            "untagged": f.untagged,
-            "no_artist": f.no_artist,
-            "date_min": f.date_min.isoformat() if f.date_min else None,
-            "date_max": f.date_max.isoformat() if f.date_max else None,
-        }
-    )
-
-
 @gallery_bp.route("/jump", methods=["GET"])
 async def jump():
     try:
         year = int(request.args["year"])
         month = int(request.args["month"])
-        filters, sort = _parse_filters()
     except (KeyError, ValueError):
         return jsonify({"error": "year and month query params required"}), 400
+    tag_id_raw = request.args.get("tag_id")
+    tag_id = int(tag_id_raw) if tag_id_raw else None
+    post_id_raw = request.args.get("post_id")
+    post_id = int(post_id_raw) if post_id_raw else None
+    artist_id_raw = request.args.get("artist_id")
+    artist_id = int(artist_id_raw) if artist_id_raw else None
     async with get_session() as session:
         svc = GalleryService(session)
         try:
             cursor = await svc.jump_cursor(
-                year=year, month=month, sort=sort, **filters,
+                year=year, month=month, tag_id=tag_id,
+                post_id=post_id, artist_id=artist_id,
             )
         except ValueError as exc:
             return jsonify({"error": str(exc)}), 400

backend/app/api/gpu.py

@@ -1,220 +0,0 @@
-"""GPU-job API (#114): the HTTP surface the desktop agent pulls work from.
-
-The agent stays HTTP-only — it leases jobs, fetches image pixels via the normal
-FC image URLs, and submits embeddings/regions back, all over this API. Redis and
-Postgres are never exposed. The agent endpoints are gated by a bearer token
-(Authorization: Bearer <token>) stored in AppSetting; the admin endpoints
-(token / backfill / status) ride the browser session like the rest of FC's
-homelab admin.
-"""
-
-import secrets
-
-from quart import Blueprint, jsonify, request
-from sqlalchemy import func, select
-from sqlalchemy.dialects.postgresql import insert as pg_insert
-
-from ..extensions import get_session
-from ..models import AppSetting, GpuJob, ImageRecord, MLSettings
-from ..services.gallery_service import image_url
-from ..services.ml.embedder import MODEL_NAME as EMBED_MODEL_NAME
-from ..services.ml.gpu_jobs import GpuJobService
-from ..services.ml.regions import RegionService
-
-gpu_bp = Blueprint("gpu", __name__, url_prefix="/api/gpu")
-
-_TOKEN_KEY = "gpu_agent_token"
-
-
-def _bearer() -> str | None:
-    h = request.headers.get("Authorization", "")
-    return h[7:].strip() if h.startswith("Bearer ") else None
-
-
-async def _agent_authed(session) -> bool:
-    supplied = _bearer()
-    if not supplied:
-        return False
-    stored = (
-        await session.execute(
-            select(AppSetting.value).where(AppSetting.key == _TOKEN_KEY)
-        )
-    ).scalar_one_or_none()
-    return stored is not None and secrets.compare_digest(supplied, stored)
-
-
-# --- Admin (browser): token + backfill + status -------------------------
-
-@gpu_bp.route("/token", methods=["GET"])
-async def get_token():
-    async with get_session() as session:
-        tok = (
-            await session.execute(
-                select(AppSetting.value).where(AppSetting.key == _TOKEN_KEY)
-            )
-        ).scalar_one_or_none()
-    return jsonify({"token": tok, "configured": tok is not None})
-
-
-@gpu_bp.route("/token/rotate", methods=["POST"])
-async def rotate_token():
-    token = secrets.token_urlsafe(32)
-    async with get_session() as session:
-        await session.execute(
-            pg_insert(AppSetting)
-            .values(key=_TOKEN_KEY, value=token)
-            .on_conflict_do_update(index_elements=["key"], set_={"value": token})
-        )
-        await session.commit()
-    return jsonify({"token": token})
-
-
-@gpu_bp.route("/status", methods=["GET"])
-async def status():
-    async with get_session() as session:
-        rows = (
-            await session.execute(
-                select(GpuJob.status, func.count()).group_by(GpuJob.status)
-            )
-        ).all()
-    counts = dict(rows)
-    return jsonify({
-        "pending": counts.get("pending", 0),
-        "leased": counts.get("leased", 0),
-        "done": counts.get("done", 0),
-        "error": counts.get("error", 0),
-    })
-
-
-@gpu_bp.route("/backfill", methods=["POST"])
-async def backfill():
-    """Enqueue a job for every image that doesn't already have one for `task`."""
-    body = await request.get_json(silent=True) or {}
-    task = str(body.get("task") or "ccip")
-    from ..tasks.ml import enqueue_gpu_backfill
-
-    r = enqueue_gpu_backfill.delay(task)
-    return jsonify({"celery_task_id": r.id, "task": task}), 202
-
-
-# --- Agent (bearer token): lease / submit / heartbeat / fail ------------
-
-@gpu_bp.route("/jobs/lease", methods=["POST"])
-async def lease():
-    body = await request.get_json(silent=True) or {}
-    agent_id = str(body.get("agent_id") or "agent")
-    try:
-        batch = min(max(int(body.get("batch_size", 8)), 1), 64)
-    except (TypeError, ValueError):
-        batch = 8
-    async with get_session() as session:
-        if not await _agent_authed(session):
-            return jsonify({"error": "unauthorized"}), 401
-        jobs = await GpuJobService(session).lease(agent_id, batch_size=batch)
-        ml = (
-            await session.execute(select(MLSettings).where(MLSettings.id == 1))
-        ).scalar_one()
-        # image rows for url/mime in one shot
-        ids = [j.image_record_id for j in jobs]
-        imgs = {
-            i.id: i for i in (
-                await session.execute(
-                    select(ImageRecord).where(ImageRecord.id.in_(ids))
-                )
-            ).scalars()
-        } if ids else {}
-        await session.commit()
-        out = []
-        for j in jobs:
-            img = imgs.get(j.image_record_id)
-            if img is None:
-                continue
-            out.append({
-                "job_id": j.id,
-                "image_id": j.image_record_id,
-                "task": j.task,
-                "mime": img.mime,
-                "image_url": image_url(img.path),
-                # For video/animated: the agent samples at this cadence.
-                "frame_interval_seconds": ml.video_frame_interval_seconds,
-                "max_frames": ml.video_max_frames,
-                # The embedding model the agent must use for concept crops, so
-                # its region vectors land in the SAME space the heads trained in.
-                # Server-announced → the agent stays model-agnostic; a swap is a
-                # server setting + a re-embed migration, never an agent change.
-                "embed_model_name": EMBED_MODEL_NAME,
-                "embed_version": ml.embedder_model_version,
-            })
-    return jsonify({"jobs": out})
-
-
-@gpu_bp.route("/jobs/heartbeat", methods=["POST"])
-async def heartbeat():
-    body = await request.get_json(silent=True) or {}
-    agent_id = str(body.get("agent_id") or "agent")
-    job_ids = [int(x) for x in (body.get("job_ids") or [])]
-    async with get_session() as session:
-        if not await _agent_authed(session):
-            return jsonify({"error": "unauthorized"}), 401
-        n = await GpuJobService(session).heartbeat(agent_id, job_ids)
-        await session.commit()
-    return jsonify({"extended": n})
-
-
-@gpu_bp.route("/jobs/submit", methods=["POST"])
-async def submit():
-    """Store a job's regions + close it. regions: [{kind, bbox:[x,y,w,h],
-    frame_time?, score?, *_version?, ccip_embedding?, siglip_embedding?}].
-    replace_kinds defaults to the kinds present in the submitted regions."""
-    body = await request.get_json(silent=True) or {}
-    agent_id = str(body.get("agent_id") or "agent")
-    job_id = body.get("job_id")
-    regions = body.get("regions") or []
-    if job_id is None:
-        return jsonify({"error": "job_id required"}), 400
-    kinds = body.get("replace_kinds") or sorted({r["kind"] for r in regions})
-    async with get_session() as session:
-        if not await _agent_authed(session):
-            return jsonify({"error": "unauthorized"}), 401
-        job = await session.get(GpuJob, int(job_id))
-        if job is None or job.status != "leased" or job.lease_token != agent_id:
-            return jsonify({"error": "lease_invalid"}), 409
-        if kinds:
-            await RegionService(session).replace_regions(
-                job.image_record_id, kinds, regions
-            )
-        await GpuJobService(session).complete(agent_id, int(job_id))
-        await session.commit()
-    return jsonify({"ok": True, "stored": len(regions)})
-
-
-@gpu_bp.route("/jobs/fail", methods=["POST"])
-async def fail():
-    body = await request.get_json(silent=True) or {}
-    agent_id = str(body.get("agent_id") or "agent")
-    job_id = body.get("job_id")
-    if job_id is None:
-        return jsonify({"error": "job_id required"}), 400
-    async with get_session() as session:
-        if not await _agent_authed(session):
-            return jsonify({"error": "unauthorized"}), 401
-        ok = await GpuJobService(session).fail(
-            agent_id, int(job_id), str(body.get("error") or "")
-        )
-        await session.commit()
-    return jsonify({"ok": ok})
-
-
-@gpu_bp.route("/jobs/release", methods=["POST"])
-async def release():
-    """Graceful stop: the agent hands its still-leased jobs back to pending so
-    they're picked up immediately instead of waiting out the lease."""
-    body = await request.get_json(silent=True) or {}
-    agent_id = str(body.get("agent_id") or "agent")
-    job_ids = [int(x) for x in (body.get("job_ids") or [])]
-    async with get_session() as session:
-        if not await _agent_authed(session):
-            return jsonify({"error": "unauthorized"}), 401
-        n = await GpuJobService(session).release(agent_id, job_ids)
-        await session.commit()
-    return jsonify({"released": n})

backend/app/api/heads.py

@@ -1,285 +0,0 @@
-"""Heads API (#114): train + inspect the per-concept heads that power
-suggestions (replacing Camie + centroid).
-
-POST /api/heads/train   — (re)train all eligible heads (one run at a time).
-GET  /api/heads         — status: head count, last-trained, running run, the
-                          per-concept head table (strength + auto-apply ready),
-                          and recent training runs. The card rehydrates from
-                          here so status survives navigation.
-"""
-
-from quart import Blueprint, jsonify, request
-from sqlalchemy import desc, func, select
-
-from ..extensions import get_session
-from ..models import (
-    HeadAutoApplyRun,
-    HeadMetric,
-    HeadMetricsSnapshot,
-    HeadTrainingRun,
-    Tag,
-    TagHead,
-)
-from ..models.tag import image_tag
-from ..services.ml.heads import (
-    HeadAutoApplyAlreadyRunning,
-    HeadAutoApplyDisabled,
-    HeadTrainingAlreadyRunning,
-    start_head_auto_apply_run,
-    start_head_training_run,
-)
-
-heads_bp = Blueprint("heads", __name__, url_prefix="/api/heads")
-
-
-def _serialize_run(run: HeadTrainingRun) -> dict:
-    return {
-        "id": run.id,
-        "params": run.params,
-        "status": run.status,
-        "started_at": run.started_at.isoformat() if run.started_at else None,
-        "finished_at": run.finished_at.isoformat() if run.finished_at else None,
-        "n_trained": run.n_trained,
-        "n_skipped": run.n_skipped,
-        "error": run.error,
-    }
-
-
-@heads_bp.route("/train", methods=["POST"])
-async def train():
-    body = await request.get_json(silent=True) or {}
-    params = body.get("params") or body or {}
-    async with get_session() as session:
-        try:
-            run_id = await session.run_sync(
-                lambda s: start_head_training_run(s, params)
-            )
-        except HeadTrainingAlreadyRunning as running:
-            return jsonify({
-                "error": "training_already_running",
-                "running_id": int(running.args[0]),
-            }), 409
-        await session.commit()
-    return jsonify({"run_id": run_id, "status": "running"}), 202
-
-
-@heads_bp.route("", methods=["GET"])
-async def status():
-    async with get_session() as session:
-        count, last_trained = (
-            await session.execute(
-                select(func.count(), func.max(TagHead.trained_at))
-            )
-        ).one()
-        graduated = (
-            await session.execute(
-                select(func.count()).where(
-                    TagHead.auto_apply_threshold.is_not(None)
-                )
-            )
-        ).scalar_one()
-        running = (
-            await session.execute(
-                select(HeadTrainingRun.id)
-                .where(HeadTrainingRun.status == "running")
-                .order_by(HeadTrainingRun.id.desc())
-                .limit(1)
-            )
-        ).scalar_one_or_none()
-        runs = (
-            await session.execute(
-                select(HeadTrainingRun)
-                .order_by(HeadTrainingRun.id.desc())
-                .limit(10)
-            )
-        ).scalars().all()
-        # The per-concept table: strongest first, capped for the admin card.
-        head_rows = (
-            await session.execute(
-                select(
-                    TagHead.tag_id, Tag.name, Tag.kind,
-                    TagHead.n_pos, TagHead.n_neg, TagHead.ap,
-                    TagHead.precision_cv, TagHead.recall,
-                    TagHead.auto_apply_threshold, TagHead.trained_at,
-                )
-                .join(Tag, Tag.id == TagHead.tag_id)
-                .order_by(desc(TagHead.ap))
-                .limit(500)
-            )
-        ).all()
-        heads = [
-            {
-                "tag_id": r.tag_id,
-                "name": r.name,
-                "category": r.kind.value if hasattr(r.kind, "value") else str(r.kind),
-                "n_pos": r.n_pos,
-                "n_neg": r.n_neg,
-                "ap": r.ap,
-                "precision": r.precision_cv,
-                "recall": r.recall,
-                "auto_apply": r.auto_apply_threshold is not None,
-                "trained_at": r.trained_at.isoformat() if r.trained_at else None,
-            }
-            for r in head_rows
-        ]
-    return jsonify({
-        "head_count": count,
-        "graduated_count": graduated,
-        "last_trained_at": last_trained.isoformat() if last_trained else None,
-        "running_id": running,
-        "runs": [_serialize_run(r) for r in runs],
-        "heads": heads,
-    })
-
-
-def _serialize_apply_run(run: HeadAutoApplyRun) -> dict:
-    return {
-        "id": run.id,
-        "dry_run": run.dry_run,
-        "status": run.status,
-        "started_at": run.started_at.isoformat() if run.started_at else None,
-        "finished_at": run.finished_at.isoformat() if run.finished_at else None,
-        "n_applied": run.n_applied,
-        "report": run.report,
-        "error": run.error,
-    }
-
-
-@heads_bp.route("/auto-apply", methods=["POST"])
-async def auto_apply():
-    """Trigger an earned-auto-apply sweep. {dry_run:true} previews (writes
-    nothing); a real sweep needs head_auto_apply_enabled on."""
-    body = await request.get_json(silent=True) or {}
-    params = {"dry_run": bool(body.get("dry_run", False))}
-    async with get_session() as session:
-        try:
-            run_id = await session.run_sync(
-                lambda s: start_head_auto_apply_run(s, params)
-            )
-        except HeadAutoApplyAlreadyRunning as running:
-            return jsonify({
-                "error": "auto_apply_already_running",
-                "running_id": int(running.args[0]),
-            }), 409
-        except HeadAutoApplyDisabled:
-            return jsonify({"error": "auto_apply_disabled"}), 400
-        await session.commit()
-    return jsonify({"run_id": run_id, "status": "running"}), 202
-
-
-@heads_bp.route("/auto-apply", methods=["GET"])
-async def auto_apply_status():
-    async with get_session() as session:
-        running = (
-            await session.execute(
-                select(HeadAutoApplyRun.id)
-                .where(HeadAutoApplyRun.status == "running")
-                .order_by(HeadAutoApplyRun.id.desc())
-                .limit(1)
-            )
-        ).scalar_one_or_none()
-        runs = (
-            await session.execute(
-                select(HeadAutoApplyRun)
-                .order_by(HeadAutoApplyRun.id.desc())
-                .limit(10)
-            )
-        ).scalars().all()
-    return jsonify({
-        "running_id": running,
-        "runs": [_serialize_apply_run(r) for r in runs],
-    })
-
-
-@heads_bp.route("/metrics", methods=["GET"])
-async def metrics():
-    """Auto-apply observability: per-concept current counts (volume, misfires,
-    under-fires, realized misfire rate, head quality) + the daily time-series so
-    the operator can tune the precision target + support floor from real data."""
-    async with get_session() as session:
-        head_rows = (
-            await session.execute(
-                select(
-                    TagHead.tag_id, Tag.name, TagHead.ap, TagHead.precision_cv,
-                    TagHead.recall, TagHead.auto_apply_threshold, TagHead.n_pos,
-                ).join(Tag, Tag.id == TagHead.tag_id)
-            )
-        ).all()
-        heads = {r.tag_id: r for r in head_rows}
-        metric_rows = (
-            await session.execute(
-                select(
-                    HeadMetric.tag_id, HeadMetric.n_misfires, HeadMetric.n_underfires
-                )
-            )
-        ).all()
-        mets = {r.tag_id: r for r in metric_rows}
-        applied = dict(
-            (
-                await session.execute(
-                    select(image_tag.c.tag_id, func.count())
-                    .where(image_tag.c.source == "head_auto")
-                    .group_by(image_tag.c.tag_id)
-                )
-            ).all()
-        )
-        names = {r.tag_id: r.name for r in head_rows}
-        # Names for metric-only tags (head pruned but corrections recorded).
-        missing = [t for t in mets if t not in names]
-        if missing:
-            for tid, nm in (
-                await session.execute(
-                    select(Tag.id, Tag.name).where(Tag.id.in_(missing))
-                )
-            ).all():
-                names[tid] = nm
-
-        concepts = []
-        for tid in set(heads) | set(mets):
-            h = heads.get(tid)
-            m = mets.get(tid)
-            n_applied = applied.get(tid, 0)
-            n_mis = m.n_misfires if m else 0
-            denom = n_applied + n_mis
-            concepts.append({
-                "tag_id": tid,
-                "name": names.get(tid, str(tid)),
-                "n_auto_applied": n_applied,
-                "n_misfires": n_mis,
-                "n_underfires": m.n_underfires if m else 0,
-                # Of everything this head ever auto-applied, the fraction you
-                # removed — the misfire rate (null until something fired).
-                "misfire_rate": round(n_mis / denom, 4) if denom else None,
-                "ap": h.ap if h else None,
-                "precision_cv": h.precision_cv if h else None,
-                "recall": h.recall if h else None,
-                "auto_apply": bool(h and h.auto_apply_threshold is not None),
-                "n_pos": h.n_pos if h else None,
-            })
-        concepts.sort(key=lambda c: (c["n_misfires"], c["n_auto_applied"]), reverse=True)
-
-        snaps = (
-            await session.execute(
-                select(HeadMetricsSnapshot)
-                .order_by(HeadMetricsSnapshot.snapshot_at.desc())
-                .limit(1000)
-            )
-        ).scalars().all()
-    return jsonify({
-        "concepts": concepts,
-        "snapshots": [
-            {
-                "tag_id": s.tag_id,
-                "name": s.name,
-                "snapshot_at": s.snapshot_at.isoformat() if s.snapshot_at else None,
-                "n_auto_applied": s.n_auto_applied,
-                "n_misfires": s.n_misfires,
-                "n_underfires": s.n_underfires,
-                "ap": s.ap,
-                "precision_cv": s.precision_cv,
-                "recall": s.recall,
-                "n_pos": s.n_pos,
-            }
-            for s in snaps
-        ],
-    })

backend/app/api/import_admin.py

@@ -35,26 +35,10 @@ async def trigger_scan():
 @import_admin_bp.route("/status", methods=["GET"])
 async def status():
     async with get_session() as session:
-        # Active batch = running batch that still has outstanding work.
-        # Plain "most recent running" picks freshly-created scans that
-        # enqueued zero new files and hides the older batch that's
-        # actually being processed. Mirrors the EXISTS predicate
-        # /api/system/stats already uses (api/settings.py:145-160).
-        # Audit 2026-06-02 — /api/import/status and /api/system/stats
-        # used to disagree on the active-batch predicate; the UI banner
-        # said "Scanning…" indefinitely while the stats card said idle.
         active = (
             await session.execute(
                 select(ImportBatch)
-                .where(
-                    ImportBatch.status == "running",
-                    select(ImportTask.id)
-                    .where(
-                        ImportTask.batch_id == ImportBatch.id,
-                        ImportTask.status.in_(["pending", "queued", "processing"]),
-                    )
-                    .exists(),
-                )
+                .where(ImportBatch.status == "running")
                 .order_by(ImportBatch.started_at.desc())
                 .limit(1)
             )
@@ -119,64 +103,24 @@ async def list_tasks():
 
 @import_admin_bp.route("/retry-failed", methods=["POST"])
 async def retry_failed():
-    # Fold SELECT into UPDATE…WHERE…RETURNING — the prior SELECT-then-
-    # UPDATE-WHERE-id-IN pattern blew past psycopg's 65535-parameter
-    # ceiling once failed_ids exceeded ~65k rows.
     async with get_session() as session:
-        result = await session.execute(
-            update(ImportTask)
-            .where(ImportTask.status == "failed")
-            .values(
-                status="queued", error=None,
-                started_at=None, finished_at=None,
-            )
-            .returning(ImportTask.id, ImportTask.task_type)
-        )
-        failed = result.all()
-        if not failed:
+        failed_ids = (
+            await session.execute(select(ImportTask.id).where(ImportTask.status == "failed"))
+        ).scalars().all()
+        if not failed_ids:
             return jsonify({"retried": 0})
+        await session.execute(
+            update(ImportTask)
+            .where(ImportTask.id.in_(failed_ids))
+            .values(status="queued", error=None, started_at=None, finished_at=None)
+        )
         await session.commit()
 
-    from ..tasks.import_file import enqueue_import
-    for tid, task_type in failed:
-        enqueue_import(tid, task_type)
+    from ..tasks.import_file import import_media_file
+    for tid in failed_ids:
+        import_media_file.delay(tid)
 
-    return jsonify({"retried": len(failed)})
-
-
-@import_admin_bp.route("/tasks/<int:task_id>/refetch", methods=["POST"])
-async def refetch_task(task_id: int):
-    """Layer-2 one-shot re-download: delete the (corrupt) file behind a
-    failed import task and re-run its source's downloader to fetch a
-    fresh copy. Only works for files that resolve to an enabled,
-    real-URL subscription Source; filesystem-only imports return
-    no_source.
-
-    Returns one of: refetch_queued (+source_id) / no_source /
-    already_refetched / not_found / not_failed.
-    """
-    async with get_session() as session:
-        result = await session.run_sync(_refetch_task_sync, task_id)
-    if result["status"] == "not_found":
-        return jsonify(result), 404
-    if result["status"] == "not_failed":
-        return jsonify(result), 400
-    return jsonify(result)
-
-
-def _refetch_task_sync(session, task_id: int) -> dict:
-    from pathlib import Path
-
-    from ..models import ImportSettings
-    from ..services.refetch_service import attempt_refetch
-
-    task = session.get(ImportTask, task_id)
-    if task is None:
-        return {"status": "not_found"}
-    if task.status != "failed":
-        return {"status": "not_failed"}
-    settings = ImportSettings.load_sync(session)
-    return attempt_refetch(session, task, Path(settings.import_scan_path))
+    return jsonify({"retried": len(failed_ids)})
 
 
 @import_admin_bp.route("/clear-stuck", methods=["POST"])
@@ -194,26 +138,28 @@ async def clear_stuck():
     autoretry-looped for 2 days after a corrupt-data PIL OSError.
     """
     async with get_session() as session:
-        # Fold SELECT into UPDATE…WHERE — see /retry-failed for the
-        # 65535-parameter ceiling rationale. rowcount is enough here
-        # because we don't need the ids afterward (no .delay()).
-        clear_result = await session.execute(
-            update(ImportTask)
-            .where(
-                ImportTask.status.in_(["pending", "queued", "processing"])
+        stuck_ids = (
+            await session.execute(
+                select(ImportTask.id).where(
+                    ImportTask.status.in_(["pending", "queued", "processing"])
+                )
             )
-            .values(
-                status="failed",
-                finished_at=datetime.now(UTC),
-                error=(
-                    "manually cleared via /api/import/clear-stuck "
-                    "— stuck in non-terminal state; retry once "
-                    "underlying cause (corrupt file, missing model, "
-                    "etc.) is resolved"
-                ),
+        ).scalars().all()
+        if stuck_ids:
+            await session.execute(
+                update(ImportTask)
+                .where(ImportTask.id.in_(stuck_ids))
+                .values(
+                    status="failed",
+                    finished_at=datetime.now(UTC),
+                    error=(
+                        "manually cleared via /api/import/clear-stuck "
+                        "— stuck in non-terminal state; retry once "
+                        "underlying cause (corrupt file, missing model, "
+                        "etc.) is resolved"
+                    ),
+                )
             )
-        )
-        tasks_failed = clear_result.rowcount or 0
 
         # Finalize any 'running' ImportBatch that no longer has any
         # active children. The "Scanning..." banner is driven by
@@ -249,7 +195,7 @@ async def clear_stuck():
         await session.commit()
 
     return jsonify({
-        "tasks_failed": tasks_failed,
+        "tasks_failed": len(stuck_ids),
         "batches_finalized": finalized_batches,
     })
 

backend/app/api/migrate.py

@@ -0,0 +1,112 @@
+"""FC-5: /api/migrate — trigger and poll migration runs.
+
+Ingest kinds (gs_ingest, ir_ingest) accept multipart/form-data with an
+`export_file` field. All other kinds accept JSON. Backup + rollback
+were retired in FC-3h (2026-05-24); use /api/system/backup/* instead.
+"""
+
+import json
+
+from quart import Blueprint, jsonify, request
+from sqlalchemy import select
+
+from ..extensions import get_session
+from ..models import MigrationRun
+from ..tasks.migration import run_migration
+
+migrate_bp = Blueprint("migrate", __name__, url_prefix="/api/migrate")
+
+# 'backup' + 'rollback' retired 2026-05-24 (FC-3h); see /api/system/backup/*.
+_VALID_KINDS = frozenset({
+    "gs_ingest", "ir_ingest", "tag_apply",
+    "ml_queue", "verify", "cleanup",
+})
+_INGEST_KINDS = frozenset({"gs_ingest", "ir_ingest"})
+
+
+def _bad(error: str, *, status: int = 400, **extra):
+    body = {"error": error}
+    body.update(extra)
+    return jsonify(body), status
+
+
+def _run_to_dict(run: MigrationRun) -> dict:
+    return {
+        "id": run.id,
+        "kind": run.kind,
+        "status": run.status,
+        "dry_run": run.dry_run,
+        "started_at": run.started_at.isoformat(),
+        "finished_at": run.finished_at.isoformat() if run.finished_at else None,
+        "counts": run.counts or {},
+        "error": run.error,
+        "metadata": run.metadata_ or {},
+    }
+
+
+@migrate_bp.route("/<kind>", methods=["POST"])
+async def create_run(kind: str):
+    if kind not in _VALID_KINDS:
+        return _bad("unknown_kind", detail=f"kind must be one of {sorted(_VALID_KINDS)}")
+
+    # Ingest kinds accept multipart/form-data; everything else takes JSON.
+    if kind in _INGEST_KINDS:
+        form = await request.form
+        files = await request.files
+        if "export_file" not in files:
+            return _bad("missing_export_file", detail="multipart export_file required")
+        export_file = files["export_file"]
+        try:
+            raw = export_file.read()
+            data = json.loads(raw.decode("utf-8"))
+        except (UnicodeDecodeError, json.JSONDecodeError) as exc:
+            return _bad("invalid_export_file", detail=str(exc))
+        dry_run = str(form.get("dry_run", "false")).lower() in ("true", "1", "yes")
+        params: dict = {"data": data, "dry_run": dry_run}
+    else:
+        body = await request.get_json()
+        if body is None:
+            body = {}
+        if not isinstance(body, dict):
+            return _bad("invalid_body")
+        dry_run = bool(body.get("dry_run", False))
+        params = dict(body)
+
+    async with get_session() as session:
+        run = MigrationRun(kind=kind, status="pending", dry_run=dry_run)
+        session.add(run)
+        await session.commit()
+        await session.refresh(run)
+        run_id = run.id
+
+    run_migration.delay(run_id, kind, params)
+    return jsonify({"run_id": run_id, "status": "pending"}), 202
+
+
+@migrate_bp.route("/runs/<int:run_id>", methods=["GET"])
+async def get_run(run_id: int):
+    async with get_session() as session:
+        run = (await session.execute(
+            select(MigrationRun).where(MigrationRun.id == run_id)
+        )).scalar_one_or_none()
+    if run is None:
+        return _bad("not_found", status=404)
+    return jsonify(_run_to_dict(run))
+
+
+@migrate_bp.route("/runs", methods=["GET"])
+async def list_runs():
+    try:
+        limit = int(request.args.get("limit", "10"))
+    except ValueError:
+        return _bad("invalid_limit")
+    if limit < 1 or limit > 100:
+        return _bad("invalid_limit")
+
+    async with get_session() as session:
+        rows = (await session.execute(
+            select(MigrationRun)
+            .order_by(MigrationRun.id.desc())
+            .limit(limit)
+        )).scalars().all()
+    return jsonify([_run_to_dict(r) for r in rows])

backend/app/api/ml_admin.py

@@ -9,21 +9,12 @@ ml_admin_bp = Blueprint("ml_admin", __name__, url_prefix="/api/ml")
 
 
 _EDITABLE = (
+    "suggestion_threshold_artist",
     "suggestion_threshold_character",
+    "suggestion_threshold_copyright",
     "suggestion_threshold_general",
     "centroid_similarity_threshold",
     "min_reference_images",
-    "tagger_store_floor",
-    "video_frame_interval_seconds",
-    "video_max_frames",
-    "video_min_tag_frames",
-    "head_min_positives",
-    "head_auto_apply_precision",
-    "head_auto_apply_enabled",
-    "head_auto_apply_min_positives",
-    "ccip_match_threshold",
-    "ccip_auto_apply_enabled",
-    "ccip_auto_apply_threshold",
 )
 
 
@@ -37,23 +28,14 @@ async def get_settings():
         ).scalar_one()
     return jsonify(
         {
+            "suggestion_threshold_artist": s.suggestion_threshold_artist,
             "suggestion_threshold_character": s.suggestion_threshold_character,
+            "suggestion_threshold_copyright": s.suggestion_threshold_copyright,
             "suggestion_threshold_general": s.suggestion_threshold_general,
             "centroid_similarity_threshold": s.centroid_similarity_threshold,
             "min_reference_images": s.min_reference_images,
-            "tagger_store_floor": s.tagger_store_floor,
-            "video_frame_interval_seconds": s.video_frame_interval_seconds,
-            "video_max_frames": s.video_max_frames,
-            "video_min_tag_frames": s.video_min_tag_frames,
             "tagger_model_version": s.tagger_model_version,
             "embedder_model_version": s.embedder_model_version,
-            "head_min_positives": s.head_min_positives,
-            "head_auto_apply_precision": s.head_auto_apply_precision,
-            "head_auto_apply_enabled": s.head_auto_apply_enabled,
-            "head_auto_apply_min_positives": s.head_auto_apply_min_positives,
-            "ccip_match_threshold": s.ccip_match_threshold,
-            "ccip_auto_apply_enabled": s.ccip_auto_apply_enabled,
-            "ccip_auto_apply_threshold": s.ccip_auto_apply_threshold,
         }
     )
 
@@ -69,65 +51,13 @@ async def patch_settings():
         s = (
             await session.execute(select(MLSettings).where(MLSettings.id == 1))
         ).scalar_one()
-
-        # Merge the patch over current values, then validate the result as a
-        # whole — the store-floor invariant couples three fields, so they
-        # can't be checked one at a time.
-        proposed = {f: getattr(s, f) for f in _EDITABLE}
         for field in _EDITABLE:
             if field in body:
-                proposed[field] = body[field]
-
-        err = _validate(proposed)
-        if err is not None:
-            return jsonify({"error": err}), 400
-
-        for field in _EDITABLE:
-            setattr(s, field, proposed[field])
+                setattr(s, field, body[field])
         await session.commit()
     return await get_settings()
 
 
-def _validate(p: dict) -> str | None:
-    """Returns an error string if the proposed settings are invalid, else None.
-
-    Invariant (plan-task #764): the per-category suggestion thresholds can't
-    drop below tagger_store_floor — nothing below the floor is stored, so a
-    lower threshold would silently surface nothing in that gap. The UI clamps
-    the sliders to the floor; this is the server-side backstop.
-    """
-    floor = p["tagger_store_floor"]
-    if not (0.0 <= floor <= 1.0):
-        return "tagger_store_floor must be between 0 and 1"
-    for cat in ("character", "general"):
-        if p[f"suggestion_threshold_{cat}"] < floor:
-            return (
-                f"suggestion_threshold_{cat} cannot be below tagger_store_floor "
-                f"({floor}) — predictions below the floor are not stored"
-            )
-    # Video tagging (#747).
-    if p["video_frame_interval_seconds"] <= 0:
-        return "video_frame_interval_seconds must be > 0"
-    if p["video_max_frames"] < 1:
-        return "video_max_frames must be >= 1"
-    if p["video_min_tag_frames"] < 1:
-        return "video_min_tag_frames must be >= 1"
-    if p["video_min_tag_frames"] > p["video_max_frames"]:
-        return "video_min_tag_frames cannot exceed video_max_frames"
-    # Head training (#114).
-    if int(p["head_min_positives"]) < 1:
-        return "head_min_positives must be >= 1"
-    if not (0.5 <= float(p["head_auto_apply_precision"]) <= 0.999):
-        return "head_auto_apply_precision must be between 0.5 and 0.999"
-    if int(p["head_auto_apply_min_positives"]) < 1:
-        return "head_auto_apply_min_positives must be >= 1"
-    if not (0.5 <= float(p["ccip_match_threshold"]) <= 0.999):
-        return "ccip_match_threshold must be between 0.5 and 0.999"
-    if not (0.5 <= float(p["ccip_auto_apply_threshold"]) <= 0.999):
-        return "ccip_auto_apply_threshold must be between 0.5 and 0.999"
-    return None
-
-
 @ml_admin_bp.route("/backfill", methods=["POST"])
 async def trigger_backfill():
     from ..tasks.ml import backfill

backend/app/api/posts.py

@@ -5,11 +5,18 @@ from quart import Blueprint, jsonify, request
 from ..extensions import get_session
 from ..services.post_feed_service import PostFeedService
 from ..services.source_service import KNOWN_PLATFORMS
-from ._responses import error_response as _bad
 
 posts_bp = Blueprint("posts", __name__, url_prefix="/api/posts")
 
 
+def _bad(error: str, *, status: int = 400, detail: str | None = None, **extra):
+    body = {"error": error}
+    if detail is not None:
+        body["detail"] = detail
+    body.update(extra)
+    return jsonify(body), status
+
+
 @posts_bp.route("", methods=["GET"])
 async def list_posts():
     args = request.args
@@ -17,10 +24,7 @@ async def list_posts():
     cursor = args.get("cursor") or None
     artist_id_raw = args.get("artist_id")
     platform = args.get("platform") or None
-    q = (args.get("q") or "").strip() or None
     limit_raw = args.get("limit", "24")
-    direction = args.get("direction", "older")
-    around_raw = args.get("around")
 
     try:
         limit = int(limit_raw)
@@ -29,16 +33,6 @@ async def list_posts():
     if limit < 1 or limit > 100:
         return _bad("invalid_limit", detail="limit must be between 1 and 100")
 
-    if direction not in ("older", "newer"):
-        return _bad("invalid_direction", detail="direction must be 'older' or 'newer'")
-
-    around_id = None
-    if around_raw is not None:
-        try:
-            around_id = int(around_raw)
-        except ValueError:
-            return _bad("invalid_around", detail="around must be an integer post id")
-
     artist_id = None
     if artist_id_raw is not None:
         try:
@@ -53,19 +47,10 @@ async def list_posts():
         )
 
     async with get_session() as session:
-        svc = PostFeedService(session)
-        if around_id is not None:
-            result = await svc.around(
-                post_id=around_id, artist_id=artist_id,
-                platform=platform, q=q, limit=limit,
-            )
-            if result is None:
-                return _bad("not_found", status=404, detail=f"post id={around_id}")
-            return jsonify(result)
         try:
-            page = await svc.scroll(
+            page = await PostFeedService(session).scroll(
                 cursor=cursor, artist_id=artist_id,
-                platform=platform, q=q, limit=limit, direction=direction,
+                platform=platform, limit=limit,
             )
         except ValueError as exc:
             # Service raises ValueError for malformed cursors only;

backend/app/api/settings.py

@@ -25,29 +25,15 @@ _EDITABLE_FIELDS = (
     "download_schedule_default_seconds",
     "download_event_retention_days",
     "download_failure_warning_threshold",
-    "series_suggest_enabled",
-    "series_suggest_threshold",
-    "extdl_mega_enabled",
-    "extdl_gdrive_enabled",
-    "extdl_mediafire_enabled",
-    "extdl_dropbox_enabled",
-    "extdl_pixeldrain_enabled",
-)
-
-# Per-host external-download toggles — all plain booleans, validated uniformly.
-_EXTDL_TOGGLE_FIELDS = (
-    "extdl_mega_enabled",
-    "extdl_gdrive_enabled",
-    "extdl_mediafire_enabled",
-    "extdl_dropbox_enabled",
-    "extdl_pixeldrain_enabled",
 )
 
 
 @settings_bp.route("/settings/import", methods=["GET"])
 async def get_import_settings():
     async with get_session() as session:
-        row = await ImportSettings.load(session)
+        row = (
+            await session.execute(select(ImportSettings).where(ImportSettings.id == 1))
+        ).scalar_one()
     return jsonify({
         "min_width": row.min_width,
         "min_height": row.min_height,
@@ -62,13 +48,6 @@ async def get_import_settings():
         "download_schedule_default_seconds": row.download_schedule_default_seconds,
         "download_event_retention_days": row.download_event_retention_days,
         "download_failure_warning_threshold": row.download_failure_warning_threshold,
-        "series_suggest_enabled": row.series_suggest_enabled,
-        "series_suggest_threshold": row.series_suggest_threshold,
-        "extdl_mega_enabled": row.extdl_mega_enabled,
-        "extdl_gdrive_enabled": row.extdl_gdrive_enabled,
-        "extdl_mediafire_enabled": row.extdl_mediafire_enabled,
-        "extdl_dropbox_enabled": row.extdl_dropbox_enabled,
-        "extdl_pixeldrain_enabled": row.extdl_pixeldrain_enabled,
     })
 
 
@@ -119,24 +98,10 @@ async def update_import_settings():
         if not isinstance(v, int) or isinstance(v, bool) or v < 1 or v > 100:
             return _bad_int("download_failure_warning_threshold", 1, 100)
 
-    if "series_suggest_enabled" in body and not isinstance(
-        body["series_suggest_enabled"], bool
-    ):
-        return jsonify(
-            {"error": "series_suggest_enabled must be a boolean"}
-        ), 400
-    for tog in _EXTDL_TOGGLE_FIELDS:
-        if tog in body and not isinstance(body[tog], bool):
-            return jsonify({"error": f"{tog} must be a boolean"}), 400
-    if "series_suggest_threshold" in body:
-        v = body["series_suggest_threshold"]
-        if not isinstance(v, (int, float)) or isinstance(v, bool) or v < 0 or v > 1:
-            return jsonify(
-                {"error": "series_suggest_threshold must be a number in [0, 1]"}
-            ), 400
-
     async with get_session() as session:
-        row = await ImportSettings.load(session)
+        row = (
+            await session.execute(select(ImportSettings).where(ImportSettings.id == 1))
+        ).scalar_one()
         for field in _EDITABLE_FIELDS:
             if field in body:
                 setattr(row, field, body[field])

backend/app/api/sources.py

@@ -5,7 +5,6 @@ from sqlalchemy import select
 
 from ..extensions import get_session
 from ..models import DownloadEvent, Source
-from ..services.scheduler_service import active_platform_cooldowns, scheduler_status
 from ..services.source_service import (
     KNOWN_PLATFORMS,
     ArtistNotFoundError,
@@ -15,11 +14,18 @@ from ..services.source_service import (
     SourceService,
     UnknownPlatformError,
 )
-from ._responses import error_response as _bad
 
 sources_bp = Blueprint("sources", __name__, url_prefix="/api/sources")
 
 
+def _bad(error: str, *, status: int = 400, detail: str | None = None, **extra):
+    body = {"error": error}
+    if detail is not None:
+        body["detail"] = detail
+    body.update(extra)
+    return jsonify(body), status
+
+
 @sources_bp.route("", methods=["GET"])
 async def list_sources():
     artist_id_raw = request.args.get("artist_id")
@@ -29,19 +35,11 @@ async def list_sources():
             artist_id = int(artist_id_raw)
         except ValueError:
             return _bad("invalid_artist_id", detail="artist_id must be an integer")
-    failing = request.args.get("failing", "").lower() in ("1", "true", "yes")
     async with get_session() as session:
-        records = await SourceService(session).list(artist_id=artist_id, failing=failing)
+        records = await SourceService(session).list(artist_id=artist_id)
     return jsonify([r.to_dict() for r in records])
 
 
-@sources_bp.route("/schedule-status", methods=["GET"])
-async def schedule_status():
-    """FC-dashboards: scheduler health for the Subscriptions hub."""
-    async with get_session() as session:
-        return jsonify(await scheduler_status(session))
-
-
 @sources_bp.route("/<int:source_id>", methods=["GET"])
 async def get_source(source_id: int):
     async with get_session() as session:
@@ -85,22 +83,6 @@ async def create_source():
             return _bad("empty_url", detail=str(exc))
         except DuplicateSourceError as exc:
             return _bad("duplicate", status=409, existing_id=exc.existing_id)
-
-        # Immediate kickoff: a new enabled source is armed for backfill (#693)
-        # but would otherwise sit idle until the next scheduler tick (~60s).
-        # Enqueue the first walk now, skipping only if the platform is in a
-        # rate-limit cooldown (the scheduler picks it up when that clears).
-        dispatch_id = None
-        if record.enabled:
-            cooldowns = await active_platform_cooldowns(session)
-            if record.platform not in cooldowns:
-                session.add(DownloadEvent(source_id=record.id, status="pending"))
-                await session.commit()
-                dispatch_id = record.id
-
-    if dispatch_id is not None:
-        from ..tasks.download import download_source
-        download_source.delay(dispatch_id)
     return jsonify(record.to_dict()), 201
 
 
@@ -136,140 +118,12 @@ async def delete_source(source_id: int):
     return "", 204
 
 
-@sources_bp.route("/<int:source_id>/backfill", methods=["POST"])
-async def set_backfill(source_id: int):
-    """Plan #693/#697 + #830: start/stop a backfill, or start a recovery /
-    recapture. Body: `{"action": "start" | "stop" | "recover" | "recapture"}`
-    (default "start"). 'start' walks the full post history in time-boxed chunks
-    until it reaches the bottom (then the source shows 'complete'); 'recover' is
-    the same walk but bypasses the Patreon seen-ledger to re-fetch
-    dropped-and-deleted near-dups under the current pHash threshold; 'recapture'
-    re-grabs EVERY post's body + external links and localizes on-disk inline
-    images WITHOUT re-downloading media; 'stop' cancels any back to tick mode.
-    Returns the updated source dict (incl. backfill_state / backfill_chunks /
-    backfill_bypass_seen / backfill_recapture)."""
-    from pathlib import Path
-
-    from ..services.credential_service import CredentialService
-    from ..services.download_backends import (
-        uses_native_ingester,
-        verify_source_credential,
-    )
-    from .credentials import _get_crypto
-
-    payload = await request.get_json(silent=True) or {}
-    action = payload.get("action", "start")
-    if action not in ("start", "stop", "recover", "recapture"):
-        return _bad(
-            "invalid_action",
-            detail="action must be 'start', 'stop', 'recover', or 'recapture'",
-        )
-
-    # Pre-flight (plan #703 #2): before arming a deep walk on a native-ingester
-    # platform (where verify is one cheap API page), refuse if the credential is
-    # DEFINITIVELY rejected — don't burn chunks against expired cookies. Proceed
-    # on valid OR inconclusive (a network blip shouldn't block). Gated to native
-    # platforms: gallery-dl verify is a slow --simulate subprocess, too heavy for
-    # an arm action. The credential read happens in a session that's CLOSED
-    # before the verify network call (don't hold a DB conn across the request).
-    if action in ("start", "recover", "recapture"):
-        async with get_session() as session:
-            rec = await SourceService(session).get(source_id)
-            if rec is None:
-                return _bad("not_found", status=404)
-            native = uses_native_ingester(rec.platform)
-            if native:
-                cred = CredentialService(session, _get_crypto())
-                cookies_path = await cred.get_cookies_path(rec.platform)
-                auth_token = await cred.get_token(rec.platform)
-        if native:
-            ok, message = await verify_source_credential(
-                platform=rec.platform,
-                url=rec.url,
-                artist_slug=rec.artist_slug,
-                config_overrides=rec.config_overrides or {},
-                cookies_path=str(cookies_path) if cookies_path else None,
-                auth_token=auth_token,
-                images_root=Path("/images"),
-            )
-            if ok is False:
-                return _bad("credential_rejected", detail=message, status=409)
-
-    async with get_session() as session:
-        try:
-            svc = SourceService(session)
-            if action == "start":
-                record = await svc.start_backfill(source_id)
-            elif action == "recover":
-                record = await svc.start_recovery(source_id)
-            elif action == "recapture":
-                record = await svc.start_recapture(source_id)
-            else:
-                record = await svc.stop_backfill(source_id)
-        except LookupError:
-            return _bad("not_found", status=404)
-    return jsonify(record.to_dict())
-
-
-@sources_bp.route("/<int:source_id>/preview", methods=["POST"])
-async def preview_source_endpoint(source_id: int):
-    """Plan #708 B4: dry-run — count what a backfill WOULD download for a native
-    platform (Patreon today), without downloading. Walks the first few feed pages
-    and counts media not already in the seen/dead ledgers. Returns
-    {total_new, posts_scanned, pages_scanned, has_more, sample[]} or 409 + reason
-    (unresolvable campaign id / auth / drift). 400 for gallery-dl platforms (no
-    cheap dry-run — their verify is a slow --simulate)."""
-    from pathlib import Path
-
-    from ..services.credential_service import CredentialService
-    from ..services.download_backends import preview_source, uses_native_ingester
-    from ..tasks._sync_engine import sync_session_factory
-    from .credentials import _get_crypto
-
-    async with get_session() as session:
-        rec = await SourceService(session).get(source_id)
-        if rec is None:
-            return _bad("not_found", status=404)
-        if not uses_native_ingester(rec.platform):
-            return _bad(
-                "unsupported",
-                detail="Preview is only available for native-ingester platforms.",
-                status=400,
-            )
-        cred = CredentialService(session, _get_crypto())
-        cookies_path = await cred.get_cookies_path(rec.platform)
-
-    # The walk + ledger reads are sync (run off the request loop); the process
-    # sync engine is the same one the download task uses.
-    result = await preview_source(
-        platform=rec.platform,
-        url=rec.url,
-        source_id=source_id,
-        config_overrides=rec.config_overrides or {},
-        cookies_path=str(cookies_path) if cookies_path else None,
-        images_root=Path("/images"),
-        sync_session_factory=sync_session_factory(),
-    )
-    if "error" in result:
-        return _bad("preview_failed", detail=result["error"], status=409)
-    return jsonify(result)
-
-
 @sources_bp.route("/<int:source_id>/check", methods=["POST"])
 async def check_source(source_id: int):
     """FC-3c: enqueue a download for this source.
 
     Returns 202 with the new DownloadEvent id. If a pending/running
-    event already exists for this source, returns 409 with that id. If
-    the source's platform is currently in a rate-limit cooldown, returns
-    **202 with `{status: "deferred", cooldown_until, platform}`** and
-    does NOT create an event or dispatch — the bulk retry path uses this
-    to avoid bowling N sources right back into the rate limit the
-    cooldown is preventing. Single-click "retry this one source" passes
-    `?force=true` to override the cooldown (operator-explicit, useful
-    for rapid auth-fix testing). The in-flight guard always applies.
-    """
-    force = (request.args.get("force") or "").lower() in ("1", "true", "yes")
+    event already exists for this source, returns 409 with that id."""
     async with get_session() as session:
         source = (await session.execute(
             select(Source).where(Source.id == source_id)
@@ -279,19 +133,6 @@ async def check_source(source_id: int):
         if not source.enabled:
             return _bad("source_disabled", detail="enable the source first")
 
-        # Cooldown gate (unless explicitly overridden). Checked before the
-        # in-flight guard because a deferred retry doesn't need to create
-        # or check for an event at all.
-        if not force:
-            cooldowns = await active_platform_cooldowns(session)
-            expires_at = cooldowns.get(source.platform)
-            if expires_at is not None:
-                return jsonify({
-                    "status": "deferred",
-                    "platform": source.platform,
-                    "cooldown_until": expires_at.isoformat(),
-                }), 202
-
         in_flight = (await session.execute(
             select(DownloadEvent.id).where(
                 DownloadEvent.source_id == source_id,

backend/app/api/suggestions.py

@@ -3,48 +3,16 @@
 from quart import Blueprint, jsonify, request
 
 from ..extensions import get_session
-from ..models import Tag, TagAllowlist
 from ..services.ml.allowlist import AllowlistService
 from ..services.ml.suggestions import SuggestionService
 
 suggestions_bp = Blueprint("suggestions", __name__, url_prefix="/api")
 
 
-async def _accept_payload(session, svc, newly_added: bool, tag_id: int) -> dict:
-    """Shape the accept/alias response. When accepting newly allowlists a tag,
-    include the coverage PROJECTION (at the tag's threshold) so the UI can show
-    a non-blocking "auto-applying to ~N images" toast — the actual apply runs
-    async via apply_allowlist_tags, so this is an estimate, not a post-hoc
-    count (#7)."""
-    payload = {"allowlisted": newly_added}
-    if newly_added:
-        tag = await session.get(Tag, tag_id)
-        row = await session.get(TagAllowlist, tag_id)
-        payload["tag_id"] = tag_id
-        payload["tag_name"] = tag.name if tag is not None else None
-        payload["projected_count"] = await svc.coverage(
-            tag_id, row.min_confidence if row is not None else 0.90,
-        )
-    return payload
-
-
 @suggestions_bp.route("/images/<int:image_id>/suggestions", methods=["GET"])
 async def get_suggestions(image_id: int):
-    # ?min=<float> overrides the configured per-category thresholds so the typed
-    # tag-input dropdown can surface EVERY stored prediction (min=0), including
-    # low-confidence actions/features, in canonical formatting. Omitted → the
-    # curated above-threshold list the Suggestions panel uses.
-    override = None
-    raw_min = request.args.get("min")
-    if raw_min is not None:
-        try:
-            override = min(1.0, max(0.0, float(raw_min)))
-        except ValueError:
-            return jsonify({"error": "min must be a float in [0,1]"}), 400
     async with get_session() as session:
-        sl = await SuggestionService(session).for_image(
-            image_id, threshold_override=override
-        )
+        sl = await SuggestionService(session).for_image(image_id)
     return jsonify(
         {
             "by_category": {
@@ -56,15 +24,6 @@ async def get_suggestions(image_id: int):
                         "score": round(s.score, 4),
                         "source": s.source,
                         "creates_new_tag": s.creates_new_tag,
-                        # raw model key (alias is stored under this) + whether an
-                        # operator alias produced this suggestion — drive the
-                        # modal's "Treat as alias"/"Remove alias" affordances.
-                        "raw_name": s.raw_name,
-                        "via_alias": s.via_alias,
-                        # operator dismissed this tag for this image — surfaced
-                        # (not dropped) so the rail can show it rejected + offer
-                        # one-click un-reject.
-                        "rejected": s.rejected,
                     }
                     for s in items
                 ]
@@ -83,15 +42,13 @@ async def accept_suggestion(image_id: int):
         return jsonify({"error": "tag_id required"}), 400
     tag_id = body["tag_id"]
     async with get_session() as session:
-        svc = AllowlistService(session)
-        newly_added = await svc.accept(image_id, tag_id)
-        payload = await _accept_payload(session, svc, newly_added, tag_id)
+        newly_added = await AllowlistService(session).accept(image_id, tag_id)
         await session.commit()
     if newly_added:
         from ..tasks.ml import apply_allowlist_tags
 
         apply_allowlist_tags.delay(tag_id=tag_id)
-    return jsonify(payload)
+    return "", 204
 
 
 @suggestions_bp.route(
@@ -102,24 +59,19 @@ async def alias_suggestion(image_id: int):
     required = {"alias_string", "alias_category", "canonical_tag_id"}
     if not body or not required.issubset(body):
         return jsonify({"error": f"required: {sorted(required)}"}), 400
-    canonical_tag_id = body["canonical_tag_id"]
     async with get_session() as session:
-        svc = AllowlistService(session)
-        newly_added = await svc.add_alias_and_accept(
+        newly_added = await AllowlistService(session).add_alias_and_accept(
             image_id,
             body["alias_string"],
             body["alias_category"],
-            canonical_tag_id,
-        )
-        payload = await _accept_payload(
-            session, svc, newly_added, canonical_tag_id,
+            body["canonical_tag_id"],
         )
         await session.commit()
     if newly_added:
         from ..tasks.ml import apply_allowlist_tags
 
-        apply_allowlist_tags.delay(tag_id=canonical_tag_id)
-    return jsonify(payload)
+        apply_allowlist_tags.delay(tag_id=body["canonical_tag_id"])
+    return "", 204
 
 
 @suggestions_bp.route(
@@ -135,21 +87,6 @@ async def dismiss_suggestion(image_id: int):
     return "", 204
 
 
-@suggestions_bp.route(
-    "/images/<int:image_id>/suggestions/undismiss", methods=["POST"]
-)
-async def undismiss_suggestion(image_id: int):
-    """Reverse a per-image dismissal (reject-recovery). Idempotent — undoing a
-    tag that isn't rejected is a no-op delete."""
-    body = await request.get_json()
-    if not body or "tag_id" not in body:
-        return jsonify({"error": "tag_id required"}), 400
-    async with get_session() as session:
-        await AllowlistService(session).undismiss(image_id, body["tag_id"])
-        await session.commit()
-    return "", 204
-
-
 @suggestions_bp.route("/suggestions/bulk", methods=["POST"])
 async def bulk_suggestions():
     body = await request.get_json()

backend/app/api/system_activity.py

@@ -20,7 +20,6 @@ from sqlalchemy import desc, func, select
 from ..config import get_config
 from ..extensions import get_session
 from ..models import TaskRun
-from ..services.scheduler_service import scheduler_status
 
 system_activity_bp = Blueprint(
     "system_activity", __name__, url_prefix="/api/system/activity",
@@ -31,7 +30,7 @@ system_activity_bp = Blueprint(
 # absent.
 _QUEUE_NAMES = (
     "default", "import", "thumbnail", "ml",
-    "download", "scan", "maintenance", "maintenance_long",
+    "download", "scan", "maintenance",
 )
 
 # Cache module-level so all requests share the cache between polls.
@@ -82,22 +81,17 @@ def _read_workers_sync() -> dict:
     }
 
 
-async def _queues_cached() -> dict:
-    """Per-queue Redis LLEN, cached 2s. Shared by /queues and /summary."""
-    now = time.time()
-    if _QUEUE_CACHE["data"] is None or (now - _QUEUE_CACHE["ts"]) > _QUEUE_CACHE_TTL:
-        _QUEUE_CACHE["data"] = await asyncio.to_thread(_read_queues_sync)
-        _QUEUE_CACHE["ts"] = now
-    return _QUEUE_CACHE["data"]
-
-
 @system_activity_bp.route("/queues", methods=["GET"])
 async def get_queues():
     """Per-queue Redis LLEN. Cached 2s.
 
     Response: {queues: {name: depth_or_null}, fetched_at: iso8601}
     """
-    return jsonify(await _queues_cached())
+    now = time.time()
+    if _QUEUE_CACHE["data"] is None or (now - _QUEUE_CACHE["ts"]) > _QUEUE_CACHE_TTL:
+        _QUEUE_CACHE["data"] = await asyncio.to_thread(_read_queues_sync)
+        _QUEUE_CACHE["ts"] = now
+    return jsonify(_QUEUE_CACHE["data"])
 
 
 @system_activity_bp.route("/workers", methods=["GET"])
@@ -113,41 +107,11 @@ async def get_workers():
     return jsonify(_WORKER_CACHE["data"])
 
 
-@system_activity_bp.route("/summary", methods=["GET"])
-async def get_summary():
-    """One-call rollup for the always-on TopNav pipeline indicator:
-    scheduler health, per-queue pending depths, currently-running count, and
-    recent (24h) failure count. Cheap — cached queue LLENs + two TaskRun
-    counts — so it's safe to poll app-wide."""
-    queues_data = await _queues_cached()
-    depths = queues_data.get("queues", {})
-    queued_total = sum(v for v in depths.values() if isinstance(v, int))
-    since = datetime.now(UTC) - timedelta(hours=24)
-    async with get_session() as session:
-        scheduler = await scheduler_status(session)
-        running = (await session.execute(
-            select(func.count(TaskRun.id)).where(TaskRun.status == "running")
-        )).scalar_one()
-        failing = (await session.execute(
-            select(func.count(TaskRun.id))
-            .where(TaskRun.status.in_(["error", "timeout"]))
-            .where(TaskRun.finished_at >= since)
-        )).scalar_one()
-    return jsonify({
-        "scheduler": scheduler,
-        "queues": depths,
-        "queued_total": queued_total,
-        "running": int(running),
-        "failing": int(failing),
-    })
-
-
 @system_activity_bp.route("/runs", methods=["GET"])
 async def list_runs():
     """Paginated task_run history. Query params:
       queue=<name>     filter to one queue
       status=<status>  filter to one status (running/ok/error/timeout/retry)
-      task=<substr>    case-insensitive substring match on task_name
       limit=<int>      default 50, max 200
       before_id=<int>  cursor for keyset pagination
 
@@ -162,7 +126,6 @@ async def list_runs():
 
     queue = request.args.get("queue")
     status = request.args.get("status")
-    task = request.args.get("task")
     before_id_raw = request.args.get("before_id")
     before_id = int(before_id_raw) if before_id_raw else None
 
@@ -172,11 +135,6 @@ async def list_runs():
             stmt = stmt.where(TaskRun.queue == queue)
         if status:
             stmt = stmt.where(TaskRun.status == status)
-        if task:
-            # Task names contain literal underscores (download_source,
-            # vacuum_analyze) — escape LIKE wildcards so a search for
-            # "vacuum_analyze" doesn't treat "_" as a single-char match.
-            stmt = stmt.where(TaskRun.task_name.ilike(f"%{_escape_like(task)}%", escape="\\"))
         if before_id is not None:
             stmt = stmt.where(TaskRun.id < before_id)
         stmt = stmt.limit(limit + 1)
@@ -232,12 +190,6 @@ async def list_failures():
     })
 
 
-def _escape_like(value: str) -> str:
-    """Escape SQL LIKE/ILIKE metacharacters so user search text is matched
-    literally. Pairs with `escape="\\"` on the .ilike() call."""
-    return value.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
-
-
 def _row_to_dict(r: TaskRun) -> dict:
     return {
         "id": r.id,

backend/app/api/system_backup.py

@@ -14,7 +14,6 @@ from sqlalchemy import desc, select
 
 from ..extensions import get_session
 from ..models import BackupRun, ImportSettings
-from ._responses import error_response as _bad
 
 system_backup_bp = Blueprint(
     "system_backup", __name__, url_prefix="/api/system/backup",
@@ -30,6 +29,12 @@ _BACKUP_SETTINGS_FIELDS = (
 )
 
 
+def _bad(error: str, *, status: int = 400, **extra):
+    body = {"error": error}
+    body.update(extra)
+    return jsonify(body), status
+
+
 def _row_to_dict(r: BackupRun) -> dict:
     return {
         "id": r.id,
@@ -227,7 +232,9 @@ async def delete_run(run_id: int):
 @system_backup_bp.route("/settings", methods=["GET"])
 async def get_settings():
     async with get_session() as session:
-        row = await ImportSettings.load(session)
+        row = (await session.execute(
+            select(ImportSettings).where(ImportSettings.id == 1)
+        )).scalar_one()
     return jsonify({
         "backup_db_nightly_enabled": row.backup_db_nightly_enabled,
         "backup_db_nightly_hour_utc": row.backup_db_nightly_hour_utc,
@@ -247,7 +254,9 @@ async def patch_settings():
         return err
 
     async with get_session() as session:
-        row = await ImportSettings.load(session)
+        row = (await session.execute(
+            select(ImportSettings).where(ImportSettings.id == 1)
+        )).scalar_one()
         for field in _BACKUP_SETTINGS_FIELDS:
             if field in body:
                 setattr(row, field, body[field])

backend/app/api/tag_eval.py

@@ -1,70 +0,0 @@
-"""Tag-eval API (#1130): trigger + revisit the head-vs-centroid eval.
-
-The run + full report live in the tag_eval_run row, so the admin card rehydrates
-from GET (history / detail) on mount — the report survives navigation rather than
-living in transient frontend state.
-"""
-
-from quart import Blueprint, jsonify, request
-from sqlalchemy import select
-
-from ..extensions import get_session
-from ..models import TagEvalRun
-from ..services.ml.tag_eval import EvalAlreadyRunning, start_tag_eval_run
-
-tag_eval_bp = Blueprint("tag_eval", __name__, url_prefix="/api/tag-eval")
-
-
-def _serialize(run: TagEvalRun, *, include_report: bool) -> dict:
-    out = {
-        "id": run.id,
-        "params": run.params,
-        "status": run.status,
-        "started_at": run.started_at.isoformat() if run.started_at else None,
-        "finished_at": run.finished_at.isoformat() if run.finished_at else None,
-        "error": run.error,
-    }
-    if include_report:
-        out["report"] = run.report
-    return out
-
-
-@tag_eval_bp.route("", methods=["POST"])
-async def create():
-    body = await request.get_json(silent=True) or {}
-    params = body.get("params") or body or {}
-    async with get_session() as session:
-        try:
-            run_id = await session.run_sync(
-                lambda s: start_tag_eval_run(s, params)
-            )
-        except EvalAlreadyRunning as running:
-            return jsonify({
-                "error": "eval_already_running",
-                "running_id": int(running.args[0]),
-            }), 409
-        await session.commit()
-    return jsonify({"run_id": run_id, "status": "running"}), 202
-
-
-@tag_eval_bp.route("", methods=["GET"])
-async def history():
-    try:
-        limit = min(int(request.args.get("limit", "20")), 100)
-    except ValueError:
-        return jsonify({"error": "invalid_limit"}), 400
-    async with get_session() as session:
-        rows = (await session.execute(
-            select(TagEvalRun).order_by(TagEvalRun.id.desc()).limit(limit)
-        )).scalars().all()
-        # List is light — no full report (the detail endpoint carries it).
-        return jsonify({"runs": [_serialize(r, include_report=False) for r in rows]})
-
-
-@tag_eval_bp.route("/<int:run_id>", methods=["GET"])
-async def detail(run_id: int):
-    async with get_session() as session:
-        run = await session.get(TagEvalRun, run_id)
-        if run is None:
-            return jsonify({"error": "not_found"}), 404
-        return jsonify(_serialize(run, include_report=True))

backend/app/api/tags.py

@@ -2,25 +2,19 @@
 
 from quart import Blueprint, jsonify, request
 from sqlalchemy import exists, select
-from sqlalchemy.dialects.postgresql import insert as pg_insert
 from sqlalchemy.exc import IntegrityError
 
 from ..extensions import get_session
-from ..models import Tag, TagKind, TagPositiveConfirmation
+from ..models import Tag, TagKind
 from ..models.tag_allowlist import TagAllowlist
 from ..services.bulk_tag_service import BulkTagService
-from ..services.ml.aliases import AliasService
-from ..services.series_match_service import SeriesMatchService
 from ..services.series_service import SeriesError, SeriesService
 from ..services.tag_directory_service import TagDirectoryService
-from ..services.tag_query import serialize_tag
 from ..services.tag_service import (
     TagMergeConflict,
     TagService,
     TagValidationError,
-    normalize_tag_name,
 )
-from ..utils.tag_prefix import parse_kind_prefix
 
 tags_bp = Blueprint("tags", __name__, url_prefix="/api")
 
@@ -75,7 +69,17 @@ async def autocomplete():
         hits = await svc.autocomplete(q, kind=kind, limit=limit)
 
     return jsonify(
-        [{**serialize_tag(h), "image_count": h.image_count} for h in hits]
+        [
+            {
+                "id": h.id,
+                "name": h.name,
+                "kind": h.kind,
+                "fandom_id": h.fandom_id,
+                "fandom_name": h.fandom_name,
+                "image_count": h.image_count,
+            }
+            for h in hits
+        ]
     )
 
 
@@ -101,46 +105,15 @@ async def directory():
 
 @tags_bp.route("/tags", methods=["POST"])
 async def create_tag():
-    """Create a tag. Two input shapes accepted:
-      1. Explicit: {name, kind, fandom_id?} — caller already split, kind wins.
-      2. IR-suffix: {name} where name = "kind:Name" (e.g. "artist:Eric").
-         The server runs parse_kind_prefix(name) to derive kind; the colon
-         and prefix are stripped from the stored tag name. If no recognized
-         prefix is present, the kind defaults to `general`.
-    Explicit kind ALWAYS wins (backward-compat for existing callers).
-    """
     body = await request.get_json()
-    if not body or "name" not in body:
-        return jsonify({"error": "name required"}), 400
+    if not body or "name" not in body or "kind" not in body:
+        return jsonify({"error": "name and kind required"}), 400
     name = body["name"]
-    explicit_kind_raw = body.get("kind")
-
-    if explicit_kind_raw is not None:
-        # Caller provided kind — honor it; don't re-parse.
-        kind = _coerce_kind(explicit_kind_raw)
-        if kind is None:
-            return jsonify({"error": f"invalid kind {explicit_kind_raw!r}"}), 400
-    else:
-        # IR-style: parse "kind:Name" from the raw name.
-        parsed_kind, parsed_name = parse_kind_prefix(name)
-        if parsed_kind is not None:
-            name = parsed_name
-            kind = _coerce_kind(parsed_kind)
-            # parse_kind_prefix only returns kinds from KNOWN_KINDS which
-            # are all valid TagKind members, so _coerce_kind can't return
-            # None here — but defensive.
-            if kind is None:
-                return jsonify({"error": f"invalid kind {parsed_kind!r}"}), 400
-        else:
-            kind = TagKind.general
-
+    kind = _coerce_kind(body["kind"])
+    if kind is None:
+        return jsonify({"error": f"invalid kind {body['kind']!r}"}), 400
     fandom_id = body.get("fandom_id")
 
-    # #701: Title-Case operator-entered tags. Only here (the explicit create
-    # endpoint), NOT in the shared find_or_create — the ML tagger uses that path
-    # and must keep the booru vocabulary's casing for allowlist matching.
-    name = normalize_tag_name(name)
-
     async with get_session() as session:
         svc = TagService(session)
         try:
@@ -158,7 +131,17 @@ async def list_tags_for_image(image_id: int):
     async with get_session() as session:
         svc = TagService(session)
         tags = await svc.list_for_image(image_id)
-    return jsonify([serialize_tag(t) for t in tags])
+    return jsonify(
+        [
+            {
+                "id": t.id,
+                "name": t.name,
+                "kind": t.kind.value,
+                "fandom_id": t.fandom_id,
+            }
+            for t in tags
+        ]
+    )
 
 
 @tags_bp.route("/images/<int:image_id>/tags", methods=["POST"])
@@ -184,79 +167,15 @@ async def remove_tag_from_image(image_id: int, tag_id: int):
     return "", 204
 
 
-@tags_bp.route("/images/<int:image_id>/tags/<int:tag_id>/confirm", methods=["POST"])
-async def confirm_tag_on_image(image_id: int, tag_id: int):
-    """Operator affirmed an applied tag is correct ("keep" on a doubted positive).
-    Idempotent; recorded so the eval's doubts list stops resurfacing it (#1130)."""
-    async with get_session() as session:
-        await session.execute(
-            pg_insert(TagPositiveConfirmation)
-            .values(image_record_id=image_id, tag_id=tag_id)
-            .on_conflict_do_nothing(index_elements=["image_record_id", "tag_id"])
-        )
-        await session.commit()
-    return "", 204
-
-
-@tags_bp.route("/tags/<int:tag_id>", methods=["GET"])
-async def get_tag(tag_id: int):
-    """Resolve a single tag (used by the gallery to label its active
-    tag-filter chip)."""
-    async with get_session() as session:
-        tag = await session.get(Tag, tag_id)
-        if tag is None:
-            return jsonify({"error": "tag not found"}), 404
-        return jsonify(
-            {
-                "id": tag.id,
-                "name": tag.name,
-                "kind": tag.kind.value,
-                "fandom_id": tag.fandom_id,
-            }
-        )
-
-
-@tags_bp.route("/tags/<int:tag_id>/aliases", methods=["GET"])
-async def list_tag_aliases(tag_id: int):
-    """Model keys that fold into this tag (tag-side alias view). Remove via the
-    shared DELETE /api/aliases/<string>/<category>."""
-    async with get_session() as session:
-        if await session.get(Tag, tag_id) is None:
-            return jsonify({"error": "tag not found"}), 404
-        rows = await AliasService(session).list_for_tag(tag_id)
-    return jsonify(
-        [
-            {
-                "alias_string": r.alias_string,
-                "alias_category": r.alias_category,
-            }
-            for r in rows
-        ]
-    )
-
-
 @tags_bp.route("/tags/<int:tag_id>", methods=["PATCH"])
-async def update_tag(tag_id: int):
-    """Rename and/or re-fandom a tag. Body may carry `name` and/or
-    `fandom_id` (a fandom tag id, or null to clear — character tags only).
-    `merge: true` resolves a collision by merging into the existing tag.
-    """
-    body = await request.get_json() or {}
-    has_name = "name" in body
-    has_fandom = "fandom_id" in body
-    if not has_name and not has_fandom:
-        return jsonify({"error": "name or fandom_id required"}), 400
-    do_merge = bool(body.get("merge"))
+async def rename_tag(tag_id: int):
+    body = await request.get_json()
+    if not body or "name" not in body:
+        return jsonify({"error": "name required"}), 400
     async with get_session() as session:
         svc = TagService(session)
         try:
-            tag = None
-            if has_name:
-                tag = await svc.rename(tag_id, body["name"])
-            if has_fandom:
-                tag = await svc.set_fandom(
-                    tag_id, body["fandom_id"], merge=do_merge
-                )
+            tag = await svc.rename(tag_id, body["name"])
         except TagMergeConflict as exc:
             return jsonify(
                 {
@@ -273,12 +192,7 @@ async def update_tag(tag_id: int):
             return jsonify({"error": str(exc)}), 400
         await session.commit()
         return jsonify(
-            {
-                "id": tag.id,
-                "name": tag.name,
-                "kind": tag.kind.value,
-                "fandom_id": tag.fandom_id,
-            }
+            {"id": tag.id, "name": tag.name, "kind": tag.kind.value}
         )
 
 
@@ -304,12 +218,6 @@ async def merge_tag(source_id: int):
         from ..tasks.ml import apply_allowlist_tags
 
         apply_allowlist_tags.delay(tag_id=result.target_id)
-    # Tag merge invalidates the target's centroid (the merged-in source
-    # tag's images now contribute to it). Daily list_drifted catches it
-    # within 24h, but eager recompute closes the suggestion-quality dip
-    # in the meantime. Audit 2026-06-02.
-    from ..tasks.ml import recompute_centroid
-    recompute_centroid.delay(result.target_id)
     return jsonify(
         {
             "target": {
@@ -385,31 +293,6 @@ def _series_err(exc: SeriesError):
     return jsonify({"error": msg}), status
 
 
-def _opt_int(body, key: str):
-    """(value, error) — value is None when absent, error is (json, status)."""
-    if not body or body.get(key) is None:
-        return None, None
-    try:
-        return int(body[key]), None
-    except (TypeError, ValueError):
-        return None, (jsonify({"error": f"{key} must be an integer"}), 400)
-
-
-def _parse_int_list(body, key: str, *, max_ids: int = 500):
-    """(list, error) for a required list of ints under `key`."""
-    if not body or key not in body:
-        return None, (jsonify({"error": f"{key} required"}), 400)
-    raw = body[key]
-    if not isinstance(raw, list) or not raw:
-        return None, (jsonify({"error": f"{key} must be a non-empty list"}), 400)
-    if len(raw) > max_ids:
-        return None, (jsonify({"error": f"too many ids (max {max_ids})"}), 400)
-    try:
-        return [int(x) for x in raw], None
-    except (TypeError, ValueError):
-        return None, (jsonify({"error": f"{key} must be integers"}), 400)
-
-
 @tags_bp.route("/series/<int:tag_id>/pages", methods=["GET"])
 async def series_pages(tag_id: int):
     async with get_session() as session:
@@ -450,26 +333,15 @@ async def series_remove(tag_id: int):
     return jsonify({"removed_count": n})
 
 
-@tags_bp.route("/series/<int:tag_id>/pages/number", methods=["POST"])
-async def series_set_page_number(tag_id: int):
-    """Set one placed page's number — the operator's value (sparse, gaps
-    allowed); pass page_number: null to leave it unnumbered."""
-    body = await request.get_json() or {}
-    image_id, ierr = _opt_int(body, "image_id")
-    if ierr:
-        return ierr
-    if image_id is None:
-        return jsonify({"error": "image_id required"}), 400
-    if "page_number" not in body:
-        return jsonify({"error": "page_number required (may be null)"}), 400
-    page_number, perr = _opt_int(body, "page_number")
-    if perr:
-        return perr
+@tags_bp.route("/series/<int:tag_id>/reorder", methods=["POST"])
+async def series_reorder(tag_id: int):
+    body = await request.get_json()
+    ids, err = _parse_bulk_ids(body, max_ids=500)
+    if err:
+        return err
     async with get_session() as session:
         try:
-            await SeriesService(session).set_page_number(
-                tag_id, image_id, page_number
-            )
+            await SeriesService(session).reorder(tag_id, ids)
         except SeriesError as exc:
             return _series_err(exc)
         await session.commit()
@@ -492,201 +364,3 @@ async def series_cover(tag_id: int):
             return _series_err(exc)
         await session.commit()
     return jsonify({"ok": True})
-
-
-# ---- chapter dividers (FC-6.x) -------------------------------------------
-# A chapter is a cosmetic divider anchored to the page that begins it; it owns
-# no pages. Page ordering follows each page's operator-set number (the
-# /pages/number endpoint), so there is no per-chapter reorder/merge — those are
-# gone.
-
-
-@tags_bp.route("/series/<int:tag_id>/chapters", methods=["POST"])
-async def series_chapter_create(tag_id: int):
-    body = await request.get_json() or {}
-    anchor, aerr = _opt_int(body, "anchor_image_id")
-    if aerr:
-        return aerr
-    if anchor is None:
-        return jsonify({"error": "anchor_image_id required"}), 400
-    title = body.get("title")
-    if title is not None and not isinstance(title, str):
-        return jsonify({"error": "title must be a string"}), 400
-    part, perr = _opt_int(body, "stated_part")
-    if perr:
-        return perr
-    async with get_session() as session:
-        try:
-            ch = await SeriesService(session).create_divider(
-                tag_id, anchor, title=title, stated_part=part,
-            )
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify(ch)
-
-
-@tags_bp.route(
-    "/series/<int:tag_id>/chapters/<int:chapter_id>", methods=["PATCH"]
-)
-async def series_chapter_update(tag_id: int, chapter_id: int):
-    body = await request.get_json() or {}
-    kwargs: dict = {}
-    if "title" in body:
-        if body["title"] is not None and not isinstance(body["title"], str):
-            return jsonify({"error": "title must be a string"}), 400
-        kwargs.update(set_title=True, title=body["title"])
-    if "stated_part" in body:
-        part, perr = _opt_int(body, "stated_part")
-        if perr:
-            return perr
-        kwargs.update(set_part=True, stated_part=part)
-    if "anchor_image_id" in body:
-        anchor, aerr = _opt_int(body, "anchor_image_id")
-        if aerr:
-            return aerr
-        if anchor is None:
-            return jsonify(
-                {"error": "anchor_image_id must be an integer"}
-            ), 400
-        kwargs.update(set_anchor=True, anchor_image_id=anchor)
-    async with get_session() as session:
-        try:
-            await SeriesService(session).update_divider(
-                tag_id, chapter_id, **kwargs
-            )
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify({"ok": True})
-
-
-@tags_bp.route(
-    "/series/<int:tag_id>/chapters/<int:chapter_id>", methods=["DELETE"]
-)
-async def series_chapter_delete(tag_id: int, chapter_id: int):
-    async with get_session() as session:
-        try:
-            await SeriesService(session).delete_divider(tag_id, chapter_id)
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify({"ok": True})
-
-
-# ---- browse list + post→series flows (FC-6.2) -----------------------------
-
-
-@tags_bp.route("/series", methods=["GET"])
-async def series_list():
-    args = request.args
-    sort = args.get("sort", "recent")
-    if sort not in ("recent", "name", "size"):
-        return jsonify({"error": "sort must be recent|name|size"}), 400
-    artist_id = None
-    if args.get("artist_id") is not None:
-        try:
-            artist_id = int(args["artist_id"])
-        except ValueError:
-            return jsonify({"error": "artist_id must be an integer"}), 400
-    async with get_session() as session:
-        rows = await SeriesService(session).list_series(
-            sort=sort, artist_id=artist_id
-        )
-    return jsonify({"series": rows})
-
-
-@tags_bp.route("/series/from-post", methods=["POST"])
-async def series_from_post():
-    body = await request.get_json()
-    post_id, err = _opt_int(body, "post_id")
-    if err:
-        return err
-    if post_id is None:
-        return jsonify({"error": "post_id required"}), 400
-    async with get_session() as session:
-        try:
-            out = await SeriesService(session).promote_post_to_series(post_id)
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify(out)
-
-
-@tags_bp.route("/series/<int:tag_id>/add-post", methods=["POST"])
-async def series_add_post(tag_id: int):
-    body = await request.get_json()
-    post_id, err = _opt_int(body, "post_id")
-    if err:
-        return err
-    if post_id is None:
-        return jsonify({"error": "post_id required"}), 400
-    async with get_session() as session:
-        try:
-            out = await SeriesService(session).add_post(tag_id, post_id)
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify(out)
-
-
-@tags_bp.route("/series/<int:tag_id>/pending/place", methods=["POST"])
-async def series_place_pending(tag_id: int):
-    """Place staged (pending) pages into the run, numbered sequentially from
-    `start_page` in the given order (#789). start_page null → unnumbered."""
-    body = await request.get_json()
-    ids, err = _parse_bulk_ids(body, max_ids=500)
-    if err:
-        return err
-    start, serr = _opt_int(body, "start_page")
-    if serr:
-        return serr
-    async with get_session() as session:
-        try:
-            n = await SeriesService(session).place_pending(
-                tag_id, ids, start_page=start
-            )
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify({"placed_count": n})
-
-
-# ---- suggestion queue (FC-6.3) --------------------------------------------
-
-
-@tags_bp.route("/series/suggestions", methods=["GET"])
-async def series_suggestions_list():
-    async with get_session() as session:
-        rows = await SeriesMatchService(session).list_pending()
-    return jsonify({"suggestions": rows})
-
-
-@tags_bp.route("/series/suggestions/<int:sid>/accept", methods=["POST"])
-async def series_suggestion_accept(sid: int):
-    async with get_session() as session:
-        try:
-            out = await SeriesMatchService(session).accept(sid)
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify(out)
-
-
-@tags_bp.route("/series/suggestions/<int:sid>/dismiss", methods=["POST"])
-async def series_suggestion_dismiss(sid: int):
-    async with get_session() as session:
-        try:
-            await SeriesMatchService(session).dismiss(sid)
-        except SeriesError as exc:
-            return _series_err(exc)
-        await session.commit()
-    return jsonify({"ok": True})
-
-
-@tags_bp.route("/series/suggestions/rescan", methods=["POST"])
-async def series_suggestions_rescan():
-    from ..tasks.admin import rescan_series_suggestions_task
-
-    res = rescan_series_suggestions_task.delay()
-    return jsonify({"task_id": res.id})

backend/app/api/thumbnails.py

@@ -1,28 +0,0 @@
-"""Thumbnail admin API: backfill trigger."""
-
-import asyncio
-
-from quart import Blueprint, jsonify
-
-thumbnails_bp = Blueprint("thumbnails", __name__, url_prefix="/api/thumbnails")
-
-
-@thumbnails_bp.route("/backfill", methods=["POST"])
-async def trigger_backfill():
-    """Run the backfill scan synchronously, return the counts. The actual
-    thumbnail generation work is still off-loaded to the thumbnail Celery
-    queue via `generate_thumbnail.delay()` per missing row — so this
-    handler is fast even on a 100k-image library (a scan is just SELECT
-    id, thumbnail_path + a file.stat() per row, no heavy work).
-
-    Operator-flagged 2026-06-01: the previous fire-and-forget shape
-    returned `{celery_task_id}` only, so the admin UI had no idea whether
-    backfill found 0 or 5000 candidates — \"found nothing\" was
-    indistinguishable from \"the worker isn't picking up the task.\""""
-    from ..tasks.thumbnail import _run_backfill_scan
-
-    # Sync scan inside an executor so we don't block the event loop.
-    counts = await asyncio.get_running_loop().run_in_executor(
-        None, _run_backfill_scan,
-    )
-    return jsonify(counts), 200

backend/app/celery_app.py

@@ -28,9 +28,9 @@ def make_celery() -> Celery:
             "backend.app.tasks.import_file",
             "backend.app.tasks.thumbnail",
             "backend.app.tasks.maintenance",
+            "backend.app.tasks.migration",
             "backend.app.tasks.ml",
             "backend.app.tasks.download",
-            "backend.app.tasks.external",
             "backend.app.tasks.backup",
             "backend.app.tasks.admin",
             "backend.app.tasks.library_audit",
@@ -43,51 +43,17 @@ def make_celery() -> Celery:
             "backend.app.tasks.ml.*": {"queue": "ml"},
             "backend.app.tasks.thumbnail.*": {"queue": "thumbnail"},
             "backend.app.tasks.download.*": {"queue": "download"},
-            # External file-host fetches are downloads — same lane (they can run
-            # long, but the download worker already tolerates long backfills).
-            "backend.app.tasks.external.*": {"queue": "download"},
             "backend.app.tasks.scan.*": {"queue": "scan"},
-            # `maintenance` is the QUICK lane — recovery sweeps, vacuum, cleanup
-            # (concurrency-1 on the scheduler). The long one-shots (DB backups,
-            # library audits, admin maintenance: normalize/re-extract/cascade-
-            # delete) run on a SEPARATE `maintenance_long` lane + worker so they
-            # can never starve the quick self-healing sweeps (operator-flagged
-            # 2026-06-07: a 2h audit blocked vacuum/backup/normalize for hours).
             "backend.app.tasks.maintenance.*": {"queue": "maintenance"},
-            "backend.app.tasks.backup.*": {"queue": "maintenance_long"},
-            "backend.app.tasks.admin.*": {"queue": "maintenance_long"},
-            "backend.app.tasks.library_audit.*": {"queue": "maintenance_long"},
+            "backend.app.tasks.migration.*": {"queue": "maintenance"},
+            "backend.app.tasks.backup.*": {"queue": "maintenance"},
+            "backend.app.tasks.admin.*": {"queue": "maintenance"},
+            "backend.app.tasks.library_audit.*": {"queue": "maintenance"},
         },
         # Heavy ML tasks need fair dispatch — see ImageRepo's precedent.
         task_acks_late=True,
         worker_prefetch_multiplier=1,
-        # Broker resilience (2026-06-24): a swarm overlay-network blip after a
-        # redeploy left Redis healthy but transiently unreachable, and a worker
-        # starting in that window crash-looped on the initial broker connect
-        # (kombu OperationalError) instead of waiting it out — needing a manual
-        # Redis reset to recover. Retry the broker FOREVER (None) on startup and
-        # at runtime so a transient outage self-heals when routing returns,
-        # rather than the worker exiting.
         broker_connection_retry_on_startup=True,
-        broker_connection_retry=True,
-        broker_connection_max_retries=None,
-        # Redis-transport socket options (apply to the BROKER connection): a
-        # short connect timeout + TCP keepalive so a dead/blocked socket is
-        # noticed and retried, and a periodic health check that proactively
-        # reconnects a live worker through a network hiccup.
-        broker_transport_options={
-            "socket_connect_timeout": 5,
-            "socket_timeout": 30,
-            "socket_keepalive": True,
-            "retry_on_timeout": True,
-            "health_check_interval": 30,
-        },
-        # Same hardening for the Redis RESULT backend (separate connection pool).
-        redis_socket_connect_timeout=5,
-        redis_socket_timeout=30,
-        redis_socket_keepalive=True,
-        redis_retry_on_timeout=True,
-        redis_backend_health_check_interval=30,
         beat_schedule={
             "recover-interrupted-tasks": {
                 "task": "backend.app.tasks.maintenance.recover_interrupted_tasks",
@@ -109,36 +75,6 @@ def make_celery() -> Celery:
                 "task": "backend.app.tasks.ml.apply_allowlist_tags",
                 "schedule": 86400.0,
             },
-            "train-heads-nightly": {
-                "task": "backend.app.tasks.ml.scheduled_train_heads",
-                "schedule": 86400.0,  # passive cadence; manual retrain stays available
-            },
-            "apply-head-tags-daily": {
-                "task": "backend.app.tasks.ml.scheduled_apply_head_tags",
-                "schedule": 86400.0,  # no-op unless head_auto_apply_enabled
-            },
-            "recover-orphaned-gpu-jobs": {
-                "task": "backend.app.tasks.ml.recover_orphaned_gpu_jobs",
-                "schedule": 60.0,  # quick pickup of work a dead agent orphaned
-            },
-            "enqueue-ccip-backfill-hourly": {
-                "task": "backend.app.tasks.ml.enqueue_gpu_backfill",
-                "schedule": 3600.0,  # auto-feed new images (+ retry errored) so
-                "args": ("ccip",),   # the queue keeps moving without the button
-            },
-            "enqueue-siglip-backfill-daily": {
-                "task": "backend.app.tasks.ml.enqueue_gpu_backfill",
-                "schedule": 86400.0,  # drain the concept-crop back-catalogue +
-                "args": ("siglip",),  # retry failed embeds, no button needed
-            },
-            "ccip-auto-apply-daily": {
-                "task": "backend.app.tasks.ml.scheduled_ccip_auto_apply",
-                "schedule": 86400.0,  # no-op unless ccip_auto_apply_enabled
-            },
-            "snapshot-head-metrics-daily": {
-                "task": "backend.app.tasks.maintenance.snapshot_head_metrics",
-                "schedule": 86400.0,
-            },
             "integrity-verify-weekly": {
                 "task": "backend.app.tasks.maintenance.verify_integrity",
                 "schedule": 604800.0,  # weekly
@@ -151,10 +87,6 @@ def make_celery() -> Celery:
                 "task": "backend.app.tasks.maintenance.cleanup_old_download_events",
                 "schedule": 86400.0,  # daily
             },
-            "recover-stalled-download-events": {
-                "task": "backend.app.tasks.maintenance.recover_stalled_download_events",
-                "schedule": 300.0,  # every 5 min, matches recover-interrupted-tasks
-            },
             "recover-stalled-task-runs": {
                 "task": "backend.app.tasks.maintenance.recover_stalled_task_runs",
                 "schedule": 300.0,  # every 5 min, matches recover-interrupted-tasks
@@ -163,10 +95,6 @@ def make_celery() -> Celery:
                 "task": "backend.app.tasks.maintenance.prune_task_runs",
                 "schedule": 86400.0,  # daily
             },
-            "vacuum-analyze": {
-                "task": "backend.app.tasks.maintenance.vacuum_analyze",
-                "schedule": 604800.0,  # weekly — reclaim dead-tuple bloat + refresh stats
-            },
             "fc3h-backup-db-nightly": {
                 "task": "backend.app.tasks.backup.backup_db_nightly",
                 "schedule": 3600.0,  # hourly tick; task self-gates on configured UTC hour
@@ -175,68 +103,6 @@ def make_celery() -> Celery:
                 "task": "backend.app.tasks.backup.prune_backups",
                 "schedule": 86400.0,  # daily
             },
-            # Audit 2026-06-02 — three new per-entity recovery sweeps.
-            # Each runs every 5 min like the other recover_stalled_*
-            # sweeps; each is a no-op when nothing is stuck.
-            "recover-stalled-backup-runs": {
-                "task": "backend.app.tasks.maintenance.recover_stalled_backup_runs",
-                "schedule": 300.0,
-            },
-            "recover-stalled-library-audit-runs": {
-                "task": "backend.app.tasks.maintenance.recover_stalled_library_audit_runs",
-                "schedule": 300.0,
-            },
-            "recover-stalled-tag-eval-runs": {
-                "task": "backend.app.tasks.maintenance.recover_stalled_tag_eval_runs",
-                "schedule": 300.0,
-            },
-            "recover-stalled-head-training-runs": {
-                "task": "backend.app.tasks.maintenance.recover_stalled_head_training_runs",
-                "schedule": 300.0,
-            },
-            "recover-stalled-head-auto-apply-runs": {
-                "task": "backend.app.tasks.maintenance.recover_stalled_head_auto_apply_runs",
-                "schedule": 300.0,
-            },
-            "recover-stalled-import-batches": {
-                "task": "backend.app.tasks.maintenance.recover_stalled_import_batches",
-                "schedule": 300.0,
-            },
-            # Audit 2026-06-02 — daily retention for two entities
-            # whose terminal rows otherwise accumulate forever.
-            "prune-library-audit-runs": {
-                "task": "backend.app.tasks.maintenance.prune_library_audit_runs",
-                "schedule": 86400.0,
-            },
-            "prune-import-batches": {
-                "task": "backend.app.tasks.maintenance.prune_import_batches",
-                "schedule": 86400.0,
-            },
-            # Audit 2026-06-02 — backfill_thumbnails's docstring claimed
-            # "periodic Beat" but the entry was never registered, so the
-            # library got no self-healing thumbnail repair; only the
-            # manual admin-UI button fired it. Daily cadence is gentle
-            # (the task is idempotent and only enqueues regen for rows
-            # whose stored thumbnails are missing or corrupt).
-            "backfill-thumbnails-daily": {
-                "task": "backend.app.tasks.thumbnail.backfill_thumbnails",
-                "schedule": 86400.0,
-            },
-            # External file-host downloads (#830): a steady sweep catches links
-            # the post-download hook missed (worker down, etc.); recovery re-tries
-            # dead links daily; retention prunes long-dead rows.
-            "extdl-sweep": {
-                "task": "backend.app.tasks.external.sweep_external_links",
-                "schedule": 600.0,  # every 10 min
-            },
-            "extdl-recover-daily": {
-                "task": "backend.app.tasks.external.recover_external_links",
-                "schedule": 86400.0,
-            },
-            "extdl-prune-daily": {
-                "task": "backend.app.tasks.external.prune_external_links",
-                "schedule": 86400.0,
-            },
         },
         timezone="UTC",
     )

backend/app/celery_signals.py

@@ -54,14 +54,7 @@ _INT32_MIN = -2_147_483_648
 
 def _queue_for(task) -> str:
     """Reverse the task→queue routing from celery_app.task_routes.
-    Keep in sync if task_routes is reordered.
-
-    Audit 2026-06-02: backup/admin/library_audit prefixes were
-    missing here even though task_routes sent all three to
-    'maintenance'. The TaskRun.queue column then lied for those
-    rows (claimed 'default') so per-queue dashboard filters and
-    per-queue threshold overrides silently missed them.
-    """
+    Keep in sync if task_routes is reordered."""
     name = getattr(task, "name", "") or ""
     if name.startswith("backend.app.tasks.import_file."):
         return "import"
@@ -69,23 +62,13 @@ def _queue_for(task) -> str:
         return "ml"
     if name.startswith("backend.app.tasks.thumbnail."):
         return "thumbnail"
-    if name.startswith((
-        "backend.app.tasks.download.",
-        # External file-host fetches share the download lane (celery_app
-        # routes external.* → download). Mirror it here or TaskRun.queue
-        # lies 'default' for them, so per-queue dashboard filters and the
-        # per-queue threshold override miss them — the same gap the
-        # 2026-06-02 audit fixed for backup/admin/library_audit.
-        "backend.app.tasks.external.",
-    )):
+    if name.startswith("backend.app.tasks.download."):
         return "download"
     if name.startswith("backend.app.tasks.scan."):
         return "scan"
     if name.startswith((
         "backend.app.tasks.maintenance.",
-        "backend.app.tasks.backup.",
-        "backend.app.tasks.admin.",
-        "backend.app.tasks.library_audit.",
+        "backend.app.tasks.migration.",
     )):
         return "maintenance"
     return "default"

backend/app/models/__init__.py

@@ -2,42 +2,25 @@
 
 from .app_setting import AppSetting
 from .artist import Artist
-from .artist_visit import ArtistVisit
 from .backup_run import BackupRun
 from .base import Base
 from .credential import Credential
 from .download_event import DownloadEvent
-from .external_link import ExternalLink
-from .gpu_job import GpuJob
-from .head_auto_apply_run import HeadAutoApplyRun
-from .head_metric import HeadMetric
-from .head_metrics_snapshot import HeadMetricsSnapshot
-from .head_training_run import HeadTrainingRun
-from .image_prediction import ImagePrediction
 from .image_provenance import ImageProvenance
 from .image_record import ImageRecord
-from .image_region import ImageRegion
 from .import_batch import ImportBatch
 from .import_settings import ImportSettings
 from .import_task import ImportTask
 from .library_audit_run import LibraryAuditRun
+from .migration_run import MigrationRun
 from .ml_settings import MLSettings
-from .patreon_failed_media import PatreonFailedMedia
-from .patreon_seen_media import PatreonSeenMedia
 from .post import Post
 from .post_attachment import PostAttachment
-from .series_chapter import SeriesChapter
 from .series_page import SeriesPage
-from .series_suggestion import SeriesSuggestion
 from .source import Source
-from .subscribestar_failed_media import SubscribeStarFailedMedia
-from .subscribestar_seen_media import SubscribeStarSeenMedia
 from .tag import Tag, TagKind, image_tag
 from .tag_alias import TagAlias
 from .tag_allowlist import TagAllowlist
-from .tag_eval_run import TagEvalRun
-from .tag_head import TagHead
-from .tag_positive_confirmation import TagPositiveConfirmation
 from .tag_reference_embedding import TagReferenceEmbedding
 from .tag_suggestion_rejection import TagSuggestionRejection
 from .task_run import TaskRun
@@ -46,43 +29,26 @@ __all__ = [
     "Base",
     "AppSetting",
     "Artist",
-    "ArtistVisit",
     "BackupRun",
     "Source",
     "Credential",
-    "PatreonFailedMedia",
-    "PatreonSeenMedia",
-    "SubscribeStarFailedMedia",
-    "SubscribeStarSeenMedia",
     "Post",
     "PostAttachment",
-    "SeriesChapter",
     "SeriesPage",
-    "SeriesSuggestion",
     "ImageRecord",
-    "ImagePrediction",
     "ImageProvenance",
-    "ImageRegion",
     "Tag",
     "TagKind",
     "image_tag",
     "DownloadEvent",
-    "ExternalLink",
-    "GpuJob",
     "ImportBatch",
     "ImportTask",
     "ImportSettings",
     "LibraryAuditRun",
     "MLSettings",
-    "HeadAutoApplyRun",
-    "HeadMetric",
-    "HeadMetricsSnapshot",
-    "HeadTrainingRun",
+    "MigrationRun",
     "TagAlias",
     "TagAllowlist",
-    "TagEvalRun",
-    "TagHead",
-    "TagPositiveConfirmation",
     "TagReferenceEmbedding",
     "TagSuggestionRejection",
     "TaskRun",

backend/app/models/artist_visit.py

@@ -1,36 +0,0 @@
-"""ArtistVisit — per-artist 'last viewed' timestamp.
-
-Powers the "+N new since last visit" badge on the artists directory and
-the matching banner on `ArtistView`. One row per artist, single global
-operator. When the multi-user model lands, the PK widens to
-`(user_id, artist_id)` — currently aspirational only (no User model,
-no services/access.py); operator approved skipping `user_id` for now
-under rule #22 (breaking changes welcome).
-
-Seed at migration time: every existing artist gets `last_viewed_at = NOW()`
-so the badge starts at 0 across the board (no noisy "5000 unseen" on
-first deploy). New artists also auto-get a row via
-`ArtistService.find_or_create`.
-"""
-
-from datetime import datetime
-
-from sqlalchemy import DateTime, ForeignKey, Integer, func
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-
-class ArtistVisit(Base):
-    __tablename__ = "artist_visit"
-
-    artist_id: Mapped[int] = mapped_column(
-        Integer,
-        ForeignKey("artist.id", ondelete="CASCADE"),
-        primary_key=True,
-    )
-    last_viewed_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True),
-        nullable=False,
-        server_default=func.now(),
-    )

backend/app/models/external_link.py

@@ -1,73 +0,0 @@
-"""ExternalLink — an off-platform file-host link found in a post body.
-
-Creators host the actual files (films, packs) on mega.nz / Google Drive /
-MediaFire / Dropbox / Pixeldrain and drop the link in the post text. This row
-is the record that the link existed (so nothing is silently dropped), the
-dedup + dead-letter ledger for fetching it, and the driver the download worker
-walks. `url` keeps the FULL link including the `#fragment` (mega's decryption
-key) — truncating it makes the file undownloadable.
-
-status lifecycle: pending → downloading → downloaded | failed | dead
-(too many attempts) | skipped (host disabled). `attachment_id` links the
-captured file once a download lands (SET NULL so deleting the attachment
-doesn't delete the link record).
-"""
-
-from datetime import datetime
-
-from sqlalchemy import (
-    DateTime,
-    Float,
-    ForeignKey,
-    Index,
-    Integer,
-    String,
-    Text,
-    func,
-    text,
-)
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-# Kept in sync with link_extract.SUPPORTED_HOSTS and the CHECK in migration 0049.
-HOSTS = ("mega", "gdrive", "mediafire", "dropbox", "pixeldrain")
-STATUSES = ("pending", "downloading", "downloaded", "failed", "skipped", "dead")
-
-
-class ExternalLink(Base):
-    __tablename__ = "external_link"
-    __table_args__ = (
-        # One row per (post, url). The full url (incl. #fragment) is the identity
-        # — the same file linked twice in a post collapses to one row.
-        Index("uq_external_link_post_url", "post_id", "url", unique=True),
-        Index("ix_external_link_status", "status"),
-    )
-
-    id: Mapped[int] = mapped_column(Integer, primary_key=True)
-    post_id: Mapped[int] = mapped_column(
-        ForeignKey("post.id", ondelete="CASCADE"), nullable=False, index=True
-    )
-    artist_id: Mapped[int | None] = mapped_column(
-        ForeignKey("artist.id", ondelete="SET NULL"), nullable=True, index=True
-    )
-    host: Mapped[str] = mapped_column(String(16), nullable=False)
-    url: Mapped[str] = mapped_column(Text, nullable=False)
-    label: Mapped[str | None] = mapped_column(Text, nullable=True)
-    status: Mapped[str] = mapped_column(
-        String(16), nullable=False, server_default="pending"
-    )
-    attempts: Mapped[int] = mapped_column(
-        Integer, nullable=False, server_default=text("0")
-    )
-    last_error: Mapped[str | None] = mapped_column(Text, nullable=True)
-    attachment_id: Mapped[int | None] = mapped_column(
-        ForeignKey("post_attachment.id", ondelete="SET NULL"), nullable=True
-    )
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-    completed_at: Mapped[datetime | None] = mapped_column(
-        DateTime(timezone=True), nullable=True
-    )
-    duration_seconds: Mapped[float | None] = mapped_column(Float, nullable=True)

backend/app/models/gpu_job.py

@@ -1,50 +0,0 @@
-"""GpuJob — a unit of GPU work the desktop agent pulls over HTTP (#114).
-
-The durable work list that lets the agent stay HTTP-only: the server enqueues a
-job per (image, task) — e.g. detect figures + CCIP-embed — and the agent LEASES a
-batch, computes on its GPU, then SUBMITS results, all over the already-exposed web
-API. Redis/Postgres stay private. A lease has an expiry; the lease query itself
-re-claims expired leases (agent died / stopped mid-batch), so the queue is
-self-healing without a separate sweep. One job is per ITEM; the agent fans a
-VIDEO out into per-frame instances internally (see image_region.frame_time).
-
-State: pending → leased → done | error (a failure under the attempt cap returns to
-pending for another agent).
-"""
-
-from datetime import datetime
-
-from sqlalchemy import DateTime, ForeignKey, Integer, String, Text, func
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-
-class GpuJob(Base):
-    __tablename__ = "gpu_job"
-
-    id: Mapped[int] = mapped_column(Integer, primary_key=True)
-    image_record_id: Mapped[int] = mapped_column(
-        ForeignKey("image_record.id", ondelete="CASCADE"), index=True
-    )
-    # What to compute, e.g. 'ccip' (detect figures + CCIP-embed) or 'siglip_region'.
-    task: Mapped[str] = mapped_column(String(32), nullable=False)
-    status: Mapped[str] = mapped_column(
-        String(16), nullable=False, default="pending", index=True
-    )
-    # pending | leased | done | error
-    lease_token: Mapped[str | None] = mapped_column(String(64), nullable=True)
-    leased_at: Mapped[datetime | None] = mapped_column(
-        DateTime(timezone=True), nullable=True
-    )
-    lease_expires_at: Mapped[datetime | None] = mapped_column(
-        DateTime(timezone=True), nullable=True
-    )
-    attempts: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    error: Mapped[str | None] = mapped_column(Text, nullable=True)
-    created_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-    updated_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )

backend/app/models/head_auto_apply_run.py

@@ -1,46 +0,0 @@
-"""HeadAutoApplyRun — persisted lifecycle of an earned-auto-apply sweep (#114).
-
-A graduated head can apply its tag to images it scores above the head's
-auto-apply threshold, without a human. This row tracks one such sweep (or a
-dry-run PREVIEW of it) so the result survives navigation and the admin card can
-show what fired / what would fire. Mirrors HeadTrainingRun. State machine:
-running → ready / error. The `report` JSONB holds per-concept counts
-(applied / projected / scanned).
-"""
-
-from datetime import datetime
-from typing import Any
-
-from sqlalchemy import Boolean, DateTime, Integer, String, Text, func
-from sqlalchemy.dialects.postgresql import JSONB
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-
-class HeadAutoApplyRun(Base):
-    __tablename__ = "head_auto_apply_run"
-
-    id: Mapped[int] = mapped_column(Integer, primary_key=True)
-    # dry_run=True is a PREVIEW: scores + counts what WOULD apply, writes nothing
-    # (preview/apply parity, rule 93).
-    dry_run: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
-    params: Mapped[dict[str, Any]] = mapped_column(JSONB, nullable=False)
-    status: Mapped[str] = mapped_column(
-        String(16), nullable=False, default="running", index=True
-    )
-    # running | ready | error
-    started_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-    finished_at: Mapped[datetime | None] = mapped_column(
-        DateTime(timezone=True), nullable=True
-    )
-    # Total tags applied across all heads this sweep (0 for a clean dry-run).
-    n_applied: Mapped[int | None] = mapped_column(Integer, nullable=True)
-    # Per-concept breakdown: [{tag_id, name, applied, scanned, threshold}, ...].
-    report: Mapped[dict[str, Any] | None] = mapped_column(JSONB, nullable=True)
-    error: Mapped[str | None] = mapped_column(Text, nullable=True)
-    last_progress_at: Mapped[datetime | None] = mapped_column(
-        DateTime(timezone=True), nullable=True
-    )

backend/app/models/head_metric.py

@@ -1,32 +0,0 @@
-"""HeadMetric — running correction counters per concept (#114 observability).
-
-Earned auto-apply fires graduated heads; to TUNE it we need to know how often a
-head's auto-applied tag was wrong (the operator removed it = a MISFIRE) and how
-often the operator had to add a tag a head exists for by hand (an UNDER-FIRE,
-the head missed it). image_tag.source is lost when a row is deleted, so these
-are captured as durable cumulative counters at correction time — they survive
-head retrain/prune (keyed by tag, not by the head row). The daily snapshot reads
-them into the time-series.
-"""
-
-from datetime import datetime
-
-from sqlalchemy import DateTime, ForeignKey, Integer, func
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-
-class HeadMetric(Base):
-    __tablename__ = "head_metric"
-
-    tag_id: Mapped[int] = mapped_column(
-        ForeignKey("tag.id", ondelete="CASCADE"), primary_key=True
-    )
-    # An auto-applied (source='head_auto') tag the operator later REMOVED.
-    n_misfires: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    # A tag with a head that the operator added by HAND (the head missed it).
-    n_underfires: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    updated_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )

backend/app/models/head_metrics_snapshot.py

@@ -1,38 +0,0 @@
-"""HeadMetricsSnapshot — a daily per-concept time-series point (#114).
-
-The "amount of change over time" reporting the operator asked for: once a day,
-record each concept's auto-applied VOLUME (current head_auto tags), cumulative
-misfires/under-fires, and the head's measured quality. Plotting these rows over
-time shows whether auto-apply is landing better/worse and whether tagging more is
-sharpening a concept — the signal for tuning the precision target + support floor.
-"""
-
-from datetime import datetime
-
-from sqlalchemy import DateTime, Float, ForeignKey, Integer, String, func
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-
-class HeadMetricsSnapshot(Base):
-    __tablename__ = "head_metrics_snapshot"
-
-    id: Mapped[int] = mapped_column(Integer, primary_key=True)
-    tag_id: Mapped[int] = mapped_column(
-        ForeignKey("tag.id", ondelete="CASCADE"), index=True
-    )
-    # Denormalized so a snapshot stays readable even if the tag is later renamed.
-    name: Mapped[str] = mapped_column(String(255), nullable=False)
-    snapshot_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now(), index=True
-    )
-    # Current count of source='head_auto' applications still standing.
-    n_auto_applied: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    n_misfires: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    n_underfires: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
-    # The head's measured quality at snapshot time (null if no head exists).
-    ap: Mapped[float | None] = mapped_column(Float, nullable=True)
-    precision_cv: Mapped[float | None] = mapped_column(Float, nullable=True)
-    recall: Mapped[float | None] = mapped_column(Float, nullable=True)
-    n_pos: Mapped[int | None] = mapped_column(Integer, nullable=True)

backend/app/models/head_training_run.py

@@ -1,44 +0,0 @@
-"""HeadTrainingRun — persisted lifecycle of a head-training batch (#114).
-
-Mirrors TagEvalRun so the run SURVIVES navigation and the admin card can show
-live + historical status instead of holding it in transient frontend state.
-Training is idempotent (it upserts tag_head rows), so a SIGKILL'd run is harmless
-— a maintenance recovery sweep flips a stalled `running` row to `error`, and the
-next run re-trains. State machine: running → ready / error.
-"""
-
-from datetime import datetime
-from typing import Any
-
-from sqlalchemy import DateTime, Integer, String, Text, func
-from sqlalchemy.dialects.postgresql import JSONB
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-
-class HeadTrainingRun(Base):
-    __tablename__ = "head_training_run"
-
-    id: Mapped[int] = mapped_column(Integer, primary_key=True)
-    # Training parameters: {min_positives, neg_ratio, precision_target, ...}.
-    params: Mapped[dict[str, Any]] = mapped_column(JSONB, nullable=False)
-    status: Mapped[str] = mapped_column(
-        String(16), nullable=False, default="running", index=True
-    )
-    # running | ready | error
-    started_at: Mapped[datetime] = mapped_column(
-        DateTime(timezone=True), nullable=False, server_default=func.now()
-    )
-    finished_at: Mapped[datetime | None] = mapped_column(
-        DateTime(timezone=True), nullable=True
-    )
-    # How many concepts got a (re)trained head vs were skipped (too few labels).
-    n_trained: Mapped[int | None] = mapped_column(Integer, nullable=True)
-    n_skipped: Mapped[int | None] = mapped_column(Integer, nullable=True)
-    error: Mapped[str | None] = mapped_column(Text, nullable=True)
-    # Last time the task made progress — the recovery sweep tells a live run from
-    # a SIGKILL'd one by this (mirrors TagEvalRun).
-    last_progress_at: Mapped[datetime | None] = mapped_column(
-        DateTime(timezone=True), nullable=True
-    )

backend/app/models/image_prediction.py

@@ -1,37 +0,0 @@
-"""ImagePrediction — one row per (image, tagger vocab prediction).
-
-Replaces the image_record.tagger_predictions JSON blob (#768). Storing the
-raw Camie/booru vocab name (not a tag_id) preserves the suggestion read
-path's semantics: raw_name → canonical Tag resolution happens at read time
-via the alias map, and accepting a prediction can CREATE the Tag. The store
-floor (ml_settings.tagger_store_floor) is applied at WRITE time, so only
-predictions >= the floor land here.
-"""
-
-from sqlalchemy import Float, ForeignKey, Index, String, UniqueConstraint
-from sqlalchemy.orm import Mapped, mapped_column
-
-from .base import Base
-
-
-class ImagePrediction(Base):
-    __tablename__ = "image_prediction"
-    __table_args__ = (
-        UniqueConstraint(
-            "image_record_id", "raw_name", name="image_raw_name",
-        ),
-        # Per-image read (suggestion build) and the "images with tag X above
-        # Y" query the JSON blob never allowed.
-        Index("ix_image_prediction_image", "image_record_id"),
-        Index("ix_image_prediction_name_score", "raw_name", "score"),
-    )
-
-    id: Mapped[int] = mapped_column(primary_key=True)
-    image_record_id: Mapped[int] = mapped_column(
-        ForeignKey("image_record.id", ondelete="CASCADE"), nullable=False,
-    )
-    # The raw tagger vocab key (booru form) — NOT a tag_id. Resolved to a
-    # canonical Tag at read time, exactly as the old JSON keys were.
-    raw_name: Mapped[str] = mapped_column(String(255), nullable=False)
-    category: Mapped[str] = mapped_column(String(64), nullable=False)
-    score: Mapped[float] = mapped_column(Float, nullable=False)

backend/app/models/image_provenance.py

@@ -1,18 +1,14 @@
 """ImageProvenance — links an ImageRecord to a Post.
 
-One image can have many provenance rows — different posts each contribute
-metadata (enrich-on-duplicate rule, spec §3: a downloaded image that is a
-pHash dupe of an existing record gets a NEW provenance row for the new post
-appended, rather than the metadata being dropped). But the (image, post)
-pair is unique — alembic 0021 enforces uq_image_provenance_image_post
-after operator-flagged 2026-05-26 saw _apply_sidecar's existence-check +
-INSERT race plant duplicates that then broke .scalar_one_or_none() on
-every later deep-scan rederive (MultipleResultsFound).
+Many-to-one (one image, many provenance rows) enables the enrich-on-duplicate
+rule (spec §3): when a downloaded image is a pHash dupe of an existing
+record, we append a new provenance row to the existing record rather than
+dropping the metadata.
 """
 
 from datetime import datetime
 
-from sqlalchemy import JSON, DateTime, ForeignKey, Integer, UniqueConstraint, func
+from sqlalchemy import JSON, DateTime, ForeignKey, Integer, func
 from sqlalchemy.orm import Mapped, mapped_column
 
 from .base import Base
@@ -20,12 +16,6 @@ from .base import Base
 
 class ImageProvenance(Base):
     __tablename__ = "image_provenance"
-    __table_args__ = (
-        UniqueConstraint(
-            "image_record_id", "post_id",
-            name="uq_image_provenance_image_post",
-        ),
-    )
 
     id: Mapped[int] = mapped_column(Integer, primary_key=True)
     image_record_id: Mapped[int] = mapped_column(
@@ -34,22 +24,8 @@ class ImageProvenance(Base):
     post_id: Mapped[int] = mapped_column(
         ForeignKey("post.id", ondelete="CASCADE"), nullable=False, index=True
     )
-    # Nullable since alembic 0030 — provenance rows for filesystem-imported
-    # content with no subscription have NULL source_id. FK ondelete SET
-    # NULL so deleting a Source detaches its provenance rows instead of
-    # destroying the linkage between image and post.
-    source_id: Mapped[int | None] = mapped_column(
-        ForeignKey("source.id", ondelete="SET NULL"), nullable=True, index=True
-    )
-    # The archive PostAttachment this image was extracted FROM, when it came
-    # out of a .zip/.rar rather than as a loose file (milestone #87). Lets the
-    # provenance UI show the exact archive a file lives inside instead of every
-    # attachment on the post. NULL for loose downloads and pre-backfill rows.
-    # SET NULL so deleting the archive attachment never destroys the (image,
-    # post) edge — it just forgets which archive it came from.
-    from_attachment_id: Mapped[int | None] = mapped_column(
-        ForeignKey("post_attachment.id", ondelete="SET NULL"),
-        nullable=True, index=True,
+    source_id: Mapped[int] = mapped_column(
+        ForeignKey("source.id", ondelete="CASCADE"), nullable=False, index=True
     )
     captured_metadata: Mapped[dict | None] = mapped_column(JSON, nullable=True)
     captured_at: Mapped[datetime] = mapped_column(