alembic/versions/0063_ccip_match_threshold.py

@@ -0,0 +1,33 @@
+"""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")

backend/app/api/ml_admin.py

@@ -21,6 +21,7 @@ _EDITABLE = (
     "head_auto_apply_precision",
     "head_auto_apply_enabled",
     "head_auto_apply_min_positives",
+    "ccip_match_threshold",
 )
 
 
@@ -48,6 +49,7 @@ async def get_settings():
             "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,
         }
     )
 
@@ -115,6 +117,8 @@ def _validate(p: dict) -> str | None:
         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"
     return None
 
 

backend/app/models/ml_settings.py

@@ -86,6 +86,12 @@ class MLSettings(Base):
     head_auto_apply_min_positives: Mapped[int] = mapped_column(
         Integer, nullable=False, default=30
     )
+    # CCIP character-match cosine cut (#114). 0.85 default — the v1 flat 0.75
+    # over-fired (high-reference characters matched a scatter of images); 0.85
+    # keeps the confident single-character matches. Tunable from the agent card.
+    ccip_match_threshold: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.85
+    )
     tagger_model_version: Mapped[str] = mapped_column(
         String(128), nullable=False, default="camie-tagger-v2"
     )

backend/app/services/ml/ccip.py

@@ -16,15 +16,25 @@ the hands-on eval. numpy is imported lazily (API worker has it via pgvector).
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from ...models import ImageRegion, Tag, TagKind
+from ...models import ImageRegion, MLSettings, Tag, TagKind
 from ...models.tag import image_tag
 
-# Cosine-similarity floor to call a figure the same character. Conservative
-# default; tune from real matches (CCIP same-char clusters tightly).
-DEFAULT_SIM_THRESHOLD = 0.75
+# Cosine-similarity floor to call a figure the same character. The live setting
+# (ml_settings.ccip_match_threshold) drives it; this is only the fallback when no
+# threshold is supplied AND no settings row exists.
+DEFAULT_SIM_THRESHOLD = 0.85
 _FIGURE_KINDS = ("face", "figure")
 
 
+async def _settings_threshold(session: AsyncSession) -> float:
+    val = (
+        await session.execute(
+            select(MLSettings.ccip_match_threshold).where(MLSettings.id == 1)
+        )
+    ).scalar_one_or_none()
+    return float(val) if val is not None else DEFAULT_SIM_THRESHOLD
+
+
 def _l2norm(mat, np):
     n = np.linalg.norm(mat, axis=1, keepdims=True)
     n[n == 0] = 1.0
@@ -68,14 +78,18 @@ async def _tag_names(session: AsyncSession, tag_ids: list[int]) -> dict[int, str
 
 
 async def match_image(
-    session: AsyncSession, image_id: int, threshold: float = DEFAULT_SIM_THRESHOLD
+    session: AsyncSession, image_id: int, threshold: float | None = None
 ) -> list[dict]:
     """Character suggestions for one image from its figure-region CCIP vectors:
     [{tag_id, name, category:'character', score, source:'ccip'}], ranked.
     Already-applied character tags are excluded. Empty if the image has no figure
-    CCIP vectors or no character references exist yet."""
+    CCIP vectors or no character references exist yet. threshold defaults to the
+    live ml_settings.ccip_match_threshold."""
     import numpy as np
 
+    if threshold is None:
+        threshold = await _settings_threshold(session)
+
     qvecs = (
         await session.execute(
             select(ImageRegion.ccip_embedding).where(

frontend/src/components/settings/GpuAgentCard.vue

@@ -60,6 +60,22 @@
       Enqueues every image that doesn't have a CCIP embedding yet. Nothing
       processes until the agent is running.
     </p>
+
+    <!-- Match strictness -->
+    <div class="fc-section-h mt-5 mb-1">Character-match strictness</div>
+    <div v-if="ml.settings" class="d-flex align-center" style="gap:12px">
+      <v-slider
+        v-model="threshold" :min="0.70" :max="0.95" :step="0.01"
+        color="accent" hide-details density="compact" class="flex-grow-1"
+        :loading="savingThreshold" @end="onSaveThreshold"
+      />
+      <span class="fc-q__n" style="font-size:16px">{{ threshold.toFixed(2) }}</span>
+    </div>
+    <p class="fc-muted text-caption mt-1 mb-0">
+      How close a figure must be (CCIP cosine) to suggest a character. Higher =
+      stricter — fewer but more confident matches. 0.85 recommended; below ~0.80
+      a heavily-tagged character starts matching everything.
+    </p>
   </MaintenanceTile>
 </template>
 
@@ -69,14 +85,18 @@ import { computed, onMounted, onUnmounted, ref } from 'vue'
 
 import MaintenanceTile from '../common/MaintenanceTile.vue'
 import { useGpuStore } from '../../stores/gpu.js'
+import { useMLStore } from '../../stores/ml.js'
 import { copyText } from '../../utils/clipboard.js'
 
 const store = useGpuStore()
+const ml = useMLStore()
 const loading = ref(true)
 const tokenValue = ref(null)
 const masked = ref(true)
 const rotating = ref(false)
 const backfilling = ref(false)
+const threshold = ref(0.85)
+const savingThreshold = ref(false)
 const queue = ref({ pending: 0, leased: 0, done: 0, error: 0 })
 let pollTimer = null
 
@@ -94,9 +114,27 @@ onMounted(async () => {
   }
   await refreshQueue()
   pollTimer = setInterval(() => { if (!document.hidden) refreshQueue() }, 5000)
+  try {
+    await ml.loadSettings()
+    if (ml.settings?.ccip_match_threshold != null) {
+      threshold.value = ml.settings.ccip_match_threshold
+    }
+  } catch { /* non-fatal */ }
 })
 onUnmounted(() => { if (pollTimer) clearInterval(pollTimer) })
 
+async function onSaveThreshold() {
+  savingThreshold.value = true
+  try {
+    await ml.patchSettings({ ccip_match_threshold: threshold.value })
+    toast({ text: `Match strictness set to ${threshold.value.toFixed(2)}`, type: 'success' })
+  } catch (e) {
+    toast({ text: `Could not save: ${e.message}`, type: 'error' })
+  } finally {
+    savingThreshold.value = false
+  }
+}
+
 async function refreshQueue() {
   try { queue.value = await store.status() } catch { /* non-fatal */ }
 }

frontend/src/stores/explore.js

@@ -11,7 +11,7 @@ import { toast } from '../utils/toast.js'
 // trail. The store ALSO acts as a TagPanel "host" (current/currentImageId +
 // tag CRUD over the anchor) so the Explore workspace reuses the modal's tag
 // rail verbatim for modal-parity tagging while rabbit-holing.
-const NEIGHBOR_LIMIT = 24
+const NEIGHBOR_LIMIT = 40   // a wider pool → more variety to browse + jump into
 
 export const useExploreStore = defineStore('explore', () => {
   const api = useApi()
@@ -81,16 +81,26 @@ export const useExploreStore = defineStore('explore', () => {
     return cursor.value > 0 ? breadcrumb.value[cursor.value - 1].id : null
   }
 
-  // → target: the next already-visited crumb if we'd stepped back, else a
-  // RANDOM neighbour to keep the rabbit-hole going. Null if neither exists.
+  // → target: after a ←, walk forward through the already-visited trail
+  // (browser-style). Otherwise jump to a varied neighbour to keep the
+  // rabbit-hole going — null if neither exists.
   function forwardTarget () {
     if (cursor.value >= 0 && cursor.value < breadcrumb.value.length - 1) {
       return breadcrumb.value[cursor.value + 1].id
     }
-    if (neighbors.value.length) {
-      return neighbors.value[Math.floor(Math.random() * neighbors.value.length)].id
-    }
-    return null
+    if (!neighbors.value.length) return null
+    // Prefer UNVISITED neighbours so → opens something new instead of landing on
+    // a crumb (which snaps the cursor back into the trail — the "loops back"
+    // report). Fall back to the full set only if every neighbour's been seen.
+    const seen = new Set(breadcrumb.value.map((c) => c.id))
+    let pool = neighbors.value.filter((n) => !seen.has(n.id))
+    if (!pool.length) pool = neighbors.value
+    // neighbors come similarity-sorted (nearest first). Skip the closest slice —
+    // those near-duplicates are exactly what you get stuck cycling through — and
+    // pick from the more-varied remainder, for real variance in the walk.
+    const skip = pool.length >= 6 ? Math.floor(pool.length / 3) : 0
+    const cands = pool.slice(skip)
+    return cands[Math.floor(Math.random() * cands.length)].id
   }
 
   function reset () {

tests/test_ccip.py

@@ -86,3 +86,20 @@ async def test_no_figure_vectors_means_no_match(db):
     query = await _img(db, "g" * 64)
     await db.commit()
     assert await match_image(db, query.id) == []
+
+
+@pytest.mark.asyncio
+async def test_threshold_gates_borderline_match(db):
+    # A figure ~0.9 cosine from the reference: matched at 0.85, dropped at 0.95.
+    raven = await TagService(db).find_or_create("Raven", TagKind.character)
+    ref = await _img(db, "h" * 64)
+    await _figure(db, ref.id, _ccip(0))                 # e0
+    await _tag_image(db, ref.id, raven.id)
+    near = [0.0] * 768
+    near[0], near[1] = 0.9, 0.4359                       # |·|=1, cos(e0)=0.9
+    query = await _img(db, "i" * 64)
+    await _figure(db, query.id, near)
+    await db.commit()
+
+    assert any(m["tag_id"] == raven.id for m in await match_image(db, query.id, 0.85))
+    assert await match_image(db, query.id, 0.95) == []