fix(tagging): save WD14 confidences only on the 0.05 grid every page shows (#369) (#373)

* fix(tagging): save WD14 confidences only on the 0.05 grid every page shows (#369)

A saved threshold off the 0.05 step (for example 0.37) blocked Generate and
Start in the workspace Tag image dialogs (native step mismatch) and made the
legacy sliders send 0.35. The server now refuses such a save with a message
that names the setting, a stored one falls back on load, and an accepted one
is stored exactly on the grid. System > Auto-tagging refuses the same values
before Preview tagging review or the batch Review, and hands thresholds on
snapped to the grid. Per-request thresholds keep their own checks.

* test(browser): restore the safety backup policy on system reset

The Recovery policy test in workspace-system-backups saves safety_backup
false at runtime, and /__test__/system/reset restored config.json but not
PromptManagerConfig.SAFETY_BACKUP. A later spec on the same server (Tag
output images review) then saw "No safety backup (the policy is off)". The
new #369 test shifted the CI shards so the two met on one worker.

TESTING.md

@@ -3587,7 +3587,8 @@ npm run --prefix tools/vendor test:workflows -- workspace-system-integrations.sp
 System › Auto-tagging (`web/js/workspace/system-tagging.mjs`, D132–D134) edits one
 server-side tagging configuration, `autotag.defaults` in config.json: `model_type`
 (`wd14-swinv2`, `wd14-vit`, `gguf`, `hf`), `existing` (`skip`, `merge`,
-`replace_after_review`), `general_threshold` and `character_threshold` (0–1),
+`replace_after_review`), `general_threshold` and `character_threshold` (0–1 in
+steps of 0.05, #369),
 `template` (non-blank, at most 4,000 characters and 16 KiB) and `suggestion_limit`
 (1–100). They are host drafts (`autotag_model_type`, `autotag_existing`,
 `autotag_general_threshold`, `autotag_character_threshold`, `autotag_template`,
@@ -3598,7 +3599,13 @@ naming the setting by its row label ("General-tag confidence must be between 0 a
 `settingRefusal` in system.mjs only for a save that carried `autotag_*` keys; every
 other section's plain 400 keeps the generic status) and the control is highlighted.
 The template's limit counts code points, as Python's `len` does. A hand-edited bad value
-falls back to its default on load, one key at a time. `GET /autotag/models` reports the
+falls back to its default on load, one key at a time. Every page shows the thresholds in
+steps of 0.05 (the System rows, the Tag image dialogs, the legacy sliders), so a saved
+threshold off that grid is refused ("General-tag confidence must be a multiple of
+0.05.", `validate_saved_threshold`; `draftProblem` holds back Preview tagging review and
+the batch Review with the same sentence) and falls back on load; an accepted one is
+stored exactly on the grid (#369). A per-request threshold keeps its own check: `/image-annotations/suggest` and
+`/jobs/autotag` take 0–1; the legacy `/autotag/single` and `/autotag/start` only require a number. `GET /autotag/models` reports the
 saved values (`wd14_general_threshold`, `wd14_character_threshold`, `suggestion_limit`,
 `default_prompt`, `model_type`, `existing`), so the Tag image and Auto-tag selected
 dialogs start from them; a preset (the bulk review, Preview tagging review) wins.

py/api/settings_routes.py

@@ -173,8 +173,8 @@ def _validate_autotag_settings(data):
         EXISTING_POLICIES,
         MAX_SUGGESTION_LIMIT,
         MODEL_TYPES,
+        validate_saved_threshold,
         validate_template,
-        validate_threshold,
     )
 
     updates = {}
@@ -198,7 +198,7 @@ def _validate_autotag_settings(data):
     ):
         if key in data:
             try:
-                value = validate_threshold(label, data[key])
+                value = validate_saved_threshold(label, data[key])
             except ValueError as error:
                 raise ValueError(f"{error}.") from None
             updates[key.upper()] = value

py/config.py

@@ -573,6 +573,7 @@ try:
         MAX_INSTRUCTION_CHARS,
         MODEL_TYPES,
         WD14_MODEL_TYPES,
+        validate_saved_threshold,
         validate_template,
         validate_threshold,
     )
@@ -585,6 +586,7 @@ except ImportError:
         MAX_INSTRUCTION_CHARS,
         MODEL_TYPES,
         WD14_MODEL_TYPES,
+        validate_saved_threshold,
         validate_template,
         validate_threshold,
     )
@@ -631,12 +633,12 @@ class AutotagConfig:
         "existing": ("EXISTING", _valid_existing, "skip"),
         "general_threshold": (
             "GENERAL_THRESHOLD",
-            lambda v: validate_threshold("value", v),
+            lambda v: validate_saved_threshold("value", v),
             0.35,
         ),
         "character_threshold": (
             "CHARACTER_THRESHOLD",
-            lambda v: validate_threshold("value", v),
+            lambda v: validate_saved_threshold("value", v),
             0.85,
         ),
         "template": ("TEMPLATE", validate_template, DEFAULT_TAG_TEMPLATE),

py/tagging_defaults.py

@@ -39,6 +39,25 @@ def validate_threshold(name: str, value: Any) -> float:
     return float(value)
 
 
+# Every page shows the thresholds in steps of 0.05 (the concept's System rows,
+# the Tag image dialogs and the legacy sliders), so a saved one must be on that
+# grid (#369). Per-request thresholds keep their own checks.
+THRESHOLD_STEP = 0.05
+_STEPS_PER_UNIT = round(1 / THRESHOLD_STEP)
+# A computed float can miss the grid by a hair: (0.1 + 0.2) * 20 is 6.000000000000001.
+_STEP_TOLERANCE = 1e-12  # in steps; refuses 0.35000000001
+
+
+def validate_saved_threshold(name: str, value: Any) -> float:
+    """A saved WD14 threshold: in [0, 1] and a multiple of ``THRESHOLD_STEP``,
+    returned exactly on the grid; else ValueError naming ``name``."""
+    value = validate_threshold(name, value)
+    steps = value * _STEPS_PER_UNIT
+    if abs(steps - round(steps)) > _STEP_TOLERANCE:
+        raise ValueError(f"{name} must be a multiple of {THRESHOLD_STEP}")
+    return round(steps) / _STEPS_PER_UNIT
+
+
 def validate_template(value: Any, name: str = "instructions") -> str:
     """Non-empty language-model instructions within the character and byte
     caps, or ValueError naming ``name``."""

tests/browser/workspace-system-tagging.spec.mjs

@@ -188,6 +188,35 @@ test('a refused value shows the server\'s message', async ({ page, request }) =>
     await expect(actionOf(page, 'Preview tagging review')).not.toHaveAttribute('aria-disabled', 'true');
 });
 
+test('a value off the 0.05 step is refused and never reaches the Tag image dialog (#369)', async ({ page, request }) => {
+    const before = (await serverJson(request, SETTINGS_URL)).settings;
+    const STEP = 'General-tag confidence must be a multiple of 0.05.';
+    await selectThenOpen(page, FIRST);
+    await page.locator('#threshold-general').fill('0.37');
+    await page.locator('#threshold-general').press('Tab');
+    // Preview tagging review explains instead of opening a dialog whose Generate the browser would block.
+    await expect(actionOf(page, 'Preview tagging review')).toHaveAttribute('aria-disabled', 'true');
+    await actionOf(page, 'Preview tagging review').focus();
+    await page.keyboard.press('Enter');
+    await expect(toast(page)).toHaveText(STEP);
+    await expect(tagDialog(page)).toHaveCount(0);
+    // The server refuses the save with the same sentence and writes nothing.
+    await save(page).click();
+    await expect(status(page)).toHaveText(STEP);
+    expect((await serverJson(request, SETTINGS_URL)).settings.autotag_general_threshold).toBe(before.autotag_general_threshold);
+    // A value on the step opens the dialog, and its Generate passes the browser's own check and sends.
+    await page.locator('#threshold-general').fill('0.4');
+    await page.locator('#threshold-general').press('Tab');
+    await expect(actionOf(page, 'Preview tagging review')).not.toHaveAttribute('aria-disabled', 'true');
+    await actionOf(page, 'Preview tagging review').click();
+    await expect(tagDialog(page).locator('#image-general-threshold')).toHaveValue('0.4');
+    expect(await tagDialog(page).locator('#image-general-threshold').evaluate(input => input.checkValidity())).toBe(true);
+    const suggested = page.waitForResponse(item => item.url().endsWith('/image-annotations/suggest'));
+    await tagDialog(page).getByRole('button', { name: 'Generate suggestions', exact: true }).click();
+    const answer = await suggested;
+    expect(answer.request().postDataJSON().options.general_threshold).toBe(0.4);
+});
+
 test('Download starts the job and Activity shows it without Cancel', async ({ page, request }) => {
     await unavailable(request, ['wd14-vit']);
     await fakeDownload(request, 'hold');

tests/js/workspace-system-tagging.test.js

@@ -307,6 +307,16 @@ test('Preview tagging review opens the Tag image dialog with the section’s val
     assert.deepEqual(draftProblem({ ...HOST, autotag_general_threshold: 1.5 }),
         { key: 'autotag_general_threshold', message: 'General-tag confidence must be between 0 and 1.' });
     assert.equal(draftProblem({ ...HOST, autotag_character_threshold: '' }).key, 'autotag_character_threshold');
+    // #369: every page shows the thresholds in steps of 0.05, so a value off that grid cannot be saved or previewed.
+    assert.deepEqual(draftProblem({ ...HOST, autotag_general_threshold: 0.37 }),
+        { key: 'autotag_general_threshold', message: 'General-tag confidence must be a multiple of 0.05.' });
+    assert.deepEqual(draftProblem({ ...HOST, autotag_character_threshold: 0.33 }),
+        { key: 'autotag_character_threshold', message: 'Character-tag confidence must be a multiple of 0.05.' });
+    assert.equal(draftProblem({ ...HOST, autotag_general_threshold: 0.15, autotag_character_threshold: 0.95 }), null);
+    assert.equal(draftProblem({ ...HOST, autotag_general_threshold: 0, autotag_character_threshold: 1 }), null);
+    // A computed value a hair off the grid passes and is handed on snapped to it, as the server stores it.
+    assert.equal(draftProblem({ ...HOST, autotag_general_threshold: 0.1 + 0.2 }), null);
+    assert.equal(taggingPreset({ ...HOST, autotag_general_threshold: 0.1 + 0.2 }).options.general_threshold, 0.3);
     assert.equal(draftProblem({ ...HOST, autotag_suggestion_limit: 2.5 }).key, 'autotag_suggestion_limit');
     assert.equal(draftProblem({ ...HOST, autotag_suggestion_limit: 0 }, { limit: false }), null);
     assert.deepEqual(draftProblem({ ...HOST, autotag_model_type: 'hf', autotag_template: '  ' }),
@@ -342,6 +352,11 @@ test('Preview tagging review opens the Tag image dialog with the section’s val
         await button('Preview tagging review').dispatch('click');
         assert.deepEqual(calls.toasts, ['General-tag confidence must be between 0 and 1.']);
         assert.equal(calls.opened.length, 1);
+        byId('threshold-general').value = '0.37'; await byId('threshold-general').dispatch('change');
+        assert.equal(button('Preview tagging review').getAttribute('aria-disabled'), 'true');
+        await button('Preview tagging review').dispatch('click');
+        assert.deepEqual(calls.toasts.at(-1), 'General-tag confidence must be a multiple of 0.05.');
+        assert.equal(calls.opened.length, 1);
     } finally { scope.dispose(); dom.restore(); }
 });
 
@@ -361,6 +376,8 @@ test('the batch review grid, body and Cancel-only reasons (D134, CUJ 4–5)', as
     assert.equal(existingLabel('odd'), 'odd');
     assert.deepEqual(batchBody(HOST), { model_type: 'wd14-swinv2', existing: 'skip',
         options: { general_threshold: 0.35, character_threshold: 0.85 } });
+    // #369: a threshold a hair off the grid is sent snapped to it.
+    assert.equal(batchBody({ ...HOST, autotag_character_threshold: 0.1 + 0.2 }).options.character_threshold, 0.3);
     assert.deepEqual(batchBody(llm), { model_type: 'gguf', existing: 'skip', options: { instructions: HOST.autotag_template } });
     assert.equal(batchCloseNote(PLAN), null);
     assert.equal(batchCloseNote({ ...PLAN, review_required: true }), REPLACE_NOTE);

tests/test_config.py

@@ -516,8 +516,9 @@ class TestAutotagConfig(unittest.TestCase):
         bad_values = {
             "model_type": ["wd14-convnext", 3, None],
             "existing": ["replace", "", True],
-            "general_threshold": [1.5, -0.1, float("nan"), "0.4", True],
-            "character_threshold": [2, float("inf"), None],
+            # #369: a saved threshold off the 0.05 step no page can show.
+            "general_threshold": [1.5, -0.1, float("nan"), "0.4", True, 0.37],
+            "character_threshold": [2, float("inf"), None, 0.33],
             # 4000 characters are at most 16,000 UTF-8 bytes, so the 16 KiB
             # byte cap can only be met past the character cap.
             "template": ["", "   ", "x" * 4001, "\U0001f600" * 4097, "\ud800", 7],
@@ -567,6 +568,27 @@ class TestAutotagConfig(unittest.TestCase):
             config_module.MODEL_TYPES, {"gguf", "hf", "wd14-swinv2", "wd14-vit"}
         )
 
+    def test_saved_threshold_is_a_multiple_of_the_step(self):
+        """#369: every page shows the thresholds in steps of 0.05, so a saved
+        one must be on that grid; it is stored exactly on it."""
+        from py.tagging_defaults import validate_saved_threshold as validate
+
+        for value in (0, 0.05, 0.15, 0.35, 0.85, 1):
+            with self.subTest(value=value):
+                self.assertEqual(validate("x", value), value)
+        self.assertEqual(validate("x", 0.1 + 0.2), 0.3)
+        for value, message in (
+            (0.37, "x must be a multiple of 0.05"),
+            (0.351, "x must be a multiple of 0.05"),
+            (0.35000000001, "x must be a multiple of 0.05"),
+            (1.5, "x must be between 0 and 1"),
+            ("0.4", "x must be a finite number"),
+        ):
+            with self.subTest(value=value):
+                with self.assertRaises(ValueError) as caught:
+                    validate("x", value)
+                self.assertEqual(str(caught.exception), message)
+
     def test_suggestion_limit_setting_validated_on_load(self):
         for value in (0, 101, "10", float("nan"), 2.5, True, None, [10]):
             with self.subTest(value=value):

tests/test_settings_sources.py

@@ -1037,6 +1037,23 @@ class TestAutotagDefaultsSettings(SourcesTestCase):
         settings = (await self._get())["settings"]
         self.assertEqual({key: settings[key] for key in self.SAVED}, self.SAVED)
 
+    async def test_threshold_near_the_grid_is_saved_on_it(self):
+        """#369: a computed value a hair off the 0.05 grid is stored on it, so
+        every page's step check accepts what /settings and the file return."""
+        revision = (await self._get())["revision"]
+        status, data = await self._post(
+            "/prompt_manager/settings",
+            {"expected_revision": revision, "autotag_general_threshold": 0.1 + 0.2},
+        )
+        self.assertEqual(status, 200, data)
+        self.assertEqual(
+            repr(self._read_config()["autotag"]["defaults"]["general_threshold"]),
+            "0.3",
+        )
+        self.assertEqual(
+            repr((await self._get())["settings"]["autotag_general_threshold"]), "0.3"
+        )
+
     async def test_stale_revision_changes_no_default(self):
         revision = (await self._get())["revision"]
         self._write_config({"custom": {"edited": "elsewhere"}})
@@ -1055,6 +1072,16 @@ class TestAutotagDefaultsSettings(SourcesTestCase):
                 1.5,
                 "General-tag confidence must be between 0 and 1.",
             ),
+            (
+                "autotag_general_threshold",
+                0.37,
+                "General-tag confidence must be a multiple of 0.05.",
+            ),
+            (
+                "autotag_character_threshold",
+                0.33,
+                "Character-tag confidence must be a multiple of 0.05.",
+            ),
             (
                 "autotag_character_threshold",
                 "0.8",

web/js/workspace/system-tagging.mjs

@@ -85,6 +85,9 @@ export const STATUS_COPY = Object.freeze({
 export const SETTING_PROBLEMS = Object.freeze({
     autotag_general_threshold: 'General-tag confidence must be between 0 and 1.',
     autotag_character_threshold: 'Character-tag confidence must be between 0 and 1.',
+    // #369: every page shows the thresholds in steps of 0.05, so the server saves only values on that grid.
+    autotag_general_threshold_step: 'General-tag confidence must be a multiple of 0.05.',
+    autotag_character_threshold_step: 'Character-tag confidence must be a multiple of 0.05.',
     autotag_suggestion_limit: 'Suggestions per image must be a whole number from 1 to 100.',
     // The server's two template sentences (`validate_template`), blank first.
     autotag_template: 'LLM tag template must be non-empty text.',
@@ -171,10 +174,15 @@ export function draftValue(key, text) {
 }
 
 const unit = value => typeof value === 'number' && Number.isFinite(value) && value >= 0 && value <= 1;
+// A multiple of 0.05 within the server's tolerance (`validate_saved_threshold`): (0.1 + 0.2) * 20 is 6.000000000000001.
+const onStep = value => Math.abs(value * 20 - Math.round(value * 20)) <= 1e-12;
+// A threshold on the grid, handed on exactly as the server stores it (anything else is left for draftProblem to refuse).
+const snapped = value => (unit(value) && onStep(value) ? Math.round(value * 20) / 20 : value);
 
 /**
  * The first setting the chosen model would use that the section cannot send, as `{key, message}`, else null: WD14
- * reads both thresholds, the language models the template; Generate also reads the suggestion count (`limit`).
+ * reads both thresholds (0 to 1 in steps of 0.05, #369), the language models the template; Generate also reads the
+ * suggestion count (`limit`).
  */
 export function draftProblem(values, { limit = true } = {}) {
     const model = values.autotag_model_type;
@@ -189,6 +197,7 @@ export function draftProblem(values, { limit = true } = {}) {
         }
         const valid = key === 'autotag_suggestion_limit' ? Number.isInteger(value) && value >= 1 && value <= 100 : unit(value);
         if (!valid) return { key, message: SETTING_PROBLEMS[key] };
+        if (key !== 'autotag_suggestion_limit' && !onStep(value)) return { key, message: SETTING_PROBLEMS[`${key}_step`] };
     }
     return null;
 }
@@ -197,7 +206,8 @@ export function draftProblem(values, { limit = true } = {}) {
 export function taggingPreset(values) {
     const model = values.autotag_model_type;
     const options = CLASSIFIERS.has(model)
-        ? { general_threshold: values.autotag_general_threshold, character_threshold: values.autotag_character_threshold }
+        ? { general_threshold: snapped(values.autotag_general_threshold),
+            character_threshold: snapped(values.autotag_character_threshold) }
         : { instructions: values.autotag_template };
     return { model, options: { ...options, suggestion_limit: values.autotag_suggestion_limit } };
 }
@@ -206,7 +216,8 @@ export function taggingPreset(values) {
 export function batchBody(values) {
     const model = values.autotag_model_type;
     const options = CLASSIFIERS.has(model)
-        ? { general_threshold: values.autotag_general_threshold, character_threshold: values.autotag_character_threshold }
+        ? { general_threshold: snapped(values.autotag_general_threshold),
+            character_threshold: snapped(values.autotag_character_threshold) }
         : { instructions: values.autotag_template };
     return { model_type: model, existing: values.autotag_existing, options };
 }