diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index c812299..ba6ceff 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -98,11 +98,6 @@ jobs:
 
       - run: pnpm install --frozen-lockfile
       - run: pnpm --filter api exec prisma migrate deploy
-      # TEMPORAIRE — recalibration de CONFIDENCE_THRESHOLD (tech-step-matcher.ts)
-      # contre le vrai service Python démarré ci-dessus. À retirer une fois
-      # la valeur choisie et reportée dans le code (voir le plan de migration).
-      - run: pnpm --filter api exec prisma db seed
-      - run: pnpm --filter api exec tsx src/scripts/calibrate-tech-step-threshold.ts
       - run: pnpm --filter api test
 
   intent-service-test:
diff --git a/apps/api/src/lib/recipe-matching/tech-step-matcher.ts b/apps/api/src/lib/recipe-matching/tech-step-matcher.ts
index 93c18a0..0bc3267 100644
--- a/apps/api/src/lib/recipe-matching/tech-step-matcher.ts
+++ b/apps/api/src/lib/recipe-matching/tech-step-matcher.ts
@@ -242,18 +242,31 @@ export function splitIntoClauses(
  * `TECH_STEP_TRAINING_DATA` — see `test/tech-step-matcher.test.ts` for the
  * cases this threshold was picked to pass.
  *
- * Raised from `0.65` after finding real (non-adversarial) misclassified
- * clauses that scored just above the old threshold — e.g. English recipe
- * text run through the French classifier (which must find *nothing*,
- * confirmed by `recipe-translation.test.ts`'s own locale-isolation test)
- * scored `0.69` for `boil`, essentially classifier noise on
- * out-of-vocabulary input rather than a real, confident verdict. The
- * clauses this threshold exists to actually trust score far higher in
- * practice (`0.91`–`1.0` for the real corrected cases found this session)
- * — `0.75` sits comfortably above the noise floor and below every genuine
- * match seen so far.
+ * Recalibrated to `0.45` for the migration off `node-nlp` to
+ * `services/tech-step-intent-service` (spaCy `textcat`, exclusive classes
+ * over ~26 techniques) — its score distribution is meaningfully different
+ * from node-nlp's own classifier, and the old `0.75` (tuned against
+ * node-nlp) left genuine, correct verdicts on *anchor-less* clauses
+ * (nothing to fall back to — see this file's doc comment, point 3) below
+ * the bar: e.g. `melt` scored `0.68` on "jusqu'à ce que le beurre ait
+ * disparu dans la poêle" (the exact motivating no-keyword case this
+ * pipeline exists for), `preheat` scored `0.52` on "mettre la poêle sur
+ * feu vif" — both the classifier's own confident best guess, both correct,
+ * both wrongly discarded at `0.75`. `0.45` clears both with margin while
+ * staying far above the noise floor: English recipe text run through the
+ * French classifier (must find *nothing*, confirmed by
+ * `recipe-translation.test.ts`'s own locale-isolation test) scored `0.04`
+ * for every technique — indistinguishable from the ~1/26 uniform baseline
+ * over this many exclusive classes, nowhere near `0.45`. Cross-checked
+ * against `apps/api/src/scripts/calibrate-tech-step-threshold.ts`'s sweep
+ * over `TECH_STEP_EVAL_DATASET`: aggregate F1 climbs to its plateau
+ * (`0.987`) starting exactly at `0.45` and stays flat through `0.95`, so
+ * this is the lowest threshold that already captures every gain available
+ * from trusting the classifier more — a higher value would only ever
+ * discard more anchor-less true positives like the two above, never buy
+ * back any precision.
  */
-export const CONFIDENCE_THRESHOLD = 0.75;
+export const CONFIDENCE_THRESHOLD = 0.45;
 
 /**
  * One clause's full classification detail — the finer-grained sibling of