chore: retire the tag-eval harness — it proved the heads system, job done (operator-approved)

The head-vs-centroid eval (#1130) existed to prove the 'frozen embedding + trained head' spine; the operator accepted the tagging system and dropped the harness. Removed per rule 22: TagEvalCard + store, /api/tag_eval blueprint, tag_eval_run ml task, recover-stalled-tag-eval-runs sweep + beat entry, TagEvalRun model + table (migration 0073), and its tests. The eval's data loaders + metric helpers were NOT eval-specific — the nightly heads trainer runs on them — so they moved verbatim to services/ml/training_data.py (heads.py import updated; behavior unchanged). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
2026-07-02 12:41:24 -04:00
parent a7abcc41ca
commit eaea4308fc
17 changed files with 178 additions and 1091 deletions
@@ -1,57 +0,0 @@
-import { defineStore } from 'pinia'
-
-import { useApi } from '../composables/useApi.js'
-
-// Tag-eval (#1130): trigger + revisit the head-vs-centroid learning-curve eval.
-// The run + full report live server-side (tag_eval_run), so the card rehydrates
-// from getRun() on mount — the report survives navigation.
-export const useTagEvalStore = defineStore('tagEval', () => {
-  const api = useApi()
-
-  async function start(params) {
-    return await api.post('/api/tag-eval', { body: { params } })
-  }
-
-  async function getRun(id) {
-    return await api.get(`/api/tag-eval/${id}`)   // includes the full report
-  }
-
-  // The most recent run (light row, no report) — the card calls getRun() with
-  // its id to pull the persisted report on mount.
-  async function latest() {
-    const body = await api.get('/api/tag-eval', { params: { limit: 1 } })
-    return (body.runs && body.runs[0]) || null
-  }
-
-  // --- Acting on the head's example lists (closes the learn-from-tags loop).
-  // These write the SAME tables the head trains on: image_tag (positives) and
-  // tag_suggestion_rejection (negatives, via the dismiss endpoint).
-
-  // "Yes, it is this" — apply the tag (new positive).
-  async function applyTag(imageId, tagId) {
-    return await api.post(`/api/images/${imageId}/tags`,
-      { body: { tag_id: tagId, source: 'manual' } })
-  }
-
-  // "No, it's not" on an UNtagged suggestion — record a rejection (hard negative).
-  async function rejectTag(imageId, tagId) {
-    return await api.post(`/api/images/${imageId}/suggestions/dismiss`,
-      { body: { tag_id: tagId } })
-  }
-
-  // "Not it" on one of YOUR positives the head doubts — remove the tag AND
-  // record the rejection (kills the bad positive, leaves a hard negative).
-  async function removeTag(imageId, tagId) {
-    await api.delete(`/api/images/${imageId}/tags/${tagId}`)
-    return await api.post(`/api/images/${imageId}/suggestions/dismiss`,
-      { body: { tag_id: tagId } })
-  }
-
-  // "Keep" — affirm a doubted positive is correct. Records a confirmation so it
-  // stops resurfacing in the doubts list (it stays a positive either way).
-  async function confirmTag(imageId, tagId) {
-    return await api.post(`/api/images/${imageId}/tags/${tagId}/confirm`)
-  }
-
-  return { start, getRun, latest, applyTag, rejectTag, removeTag, confirmTag }
-})