diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3b7d019..44eaa6a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,7 +4,7 @@
 
 ### Changed
 
-- **`maxTokens` now matches the CLI registry instead of a uniform 16384 (#195).** Every Opus entry and `claude-sonnet-5` go to **64000**, `claude-sonnet-4-6` and `claude-haiku-4-5` to **32000** — the `max_output_tokens.default` each model actually declares in the compiled CLI 2.1.220 registry. OCP never enforced this value; it is propagated to OpenClaw, where it **caps the outbound request**: `maxTokens = Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens)`. OpenClaw's reasoning budgets are medium 8192 / high 16384, and when `maxTokens <= thinkingBudget` it clamps thinking to `maxTokens - 1024` — so a model declared at 16384 running at **high** reasoning spent ~15360 on thinking and left **~1024 tokens for the actual answer**. `ocp-connect`'s independent family table moves to the family floor (opus 64000, sonnet 32000, haiku 32000) since prefixes cannot distinguish versions. Expect longer answers and correspondingly higher per-request quota burn on long generations.
+- **`maxTokens` now matches the CLI registry instead of a uniform 16384 (#195).** Every Opus entry and `claude-sonnet-5` go to **64000**, `claude-sonnet-4-6` and `claude-haiku-4-5` to **32000** — the `max_output_tokens.default` each model declares in the compiled CLI 2.1.220 registry. This corrects **advertised metadata only**: `models.json` is the SPOT (ADR 0003) and every value in it should be the truth about the model. **It changes nothing about how OCP behaves.** OCP never enforces `maxTokens` — `buildCliArgs` passes no output-token flag to the CLI at all — and OpenClaw addresses a local OCP over `openai-completions`, whose request field (`max_completion_tokens`) appears nowhere in this repo. The value is consumed only by clients that choose to honour it, via `setup.mjs` / `scripts/sync-openclaw.mjs` / `ocp-connect`. **Expect no change in answer length or quota burn.** `ocp-connect`'s independent family table moves to the family floor (opus 64000, sonnet 32000, haiku 32000) since prefixes cannot distinguish versions.
 
 ## v3.25.0 — 2026-07-27
 
diff --git a/ocp-connect b/ocp-connect
index 2495491..15cc7b3 100755
--- a/ocp-connect
+++ b/ocp-connect
@@ -147,7 +147,11 @@ def get_model_meta(mid):
     for prefix, meta in sorted(model_meta.items(), key=lambda x: -len(x[0])):
         if mid.startswith(prefix):
             return meta
-    return {"name": mid + " (OCP)", "reasoning": False, "maxTokens": 8192}
+    # Unknown id = most likely a model newer than this script. 32000 is the LOWEST
+    # max_output_tokens.default in the CLI 2.1.220 registry (haiku/sonnet-4-6), so it is the
+    # safe floor: never over-advertises a real model, and no longer contradicts the rest of
+    # this table by sitting below every family in it.
+    return {"name": mid + " (OCP)", "reasoning": False, "maxTokens": 32000}
 
 for mid in model_ids:
     meta = get_model_meta(mid)
diff --git a/test-features.mjs b/test-features.mjs
index a932eef..6eb9b69 100644
--- a/test-features.mjs
+++ b/test-features.mjs
@@ -4299,21 +4299,27 @@ test("models.json: every aliases value resolves to a real models[].id (referenti
   }
 });
 
-// maxTokens must leave room for a visible answer once a client's thinking budget is taken out
-// (#195). OCP never enforces maxTokens itself — it is propagated to OpenClaw (setup.mjs,
-// scripts/sync-openclaw.mjs) where it CAPS the outbound request:
-//     maxTokens = Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens)
-// OpenClaw's reasoning budgets are medium 8192 / high 16384, and when maxTokens <= thinkingBudget
-// it clamps thinking to maxTokens - 1024. So a model declared at 16384 running at `high` spent
-// ~15360 on thinking and left ~1024 for the actual answer — which is what this repo shipped until
-// v3.25.0. Asserting the PRINCIPLE rather than pinning per-model numbers: a value test would need
-// editing every time a model is added, and would not say why.
-const _spotHighThinkingBudget = 16384; // OpenClaw's `high` reasoning budget
-test("models.json: every maxTokens exceeds the high thinking budget, leaving room for output (#195)", () => {
+// maxTokens is ADVERTISED metadata, not an OCP-enforced limit (#195). OCP never reads it —
+// buildCliArgs passes no output-token flag to the CLI — and OpenClaw reaches a local OCP over
+// `openai-completions`, whose request field (max_completion_tokens) appears nowhere in this repo.
+// It is consumed only by clients that choose to honour it, via setup.mjs / sync-openclaw.mjs /
+// ocp-connect. So the invariant worth testing is simply that models.json tells the truth: each
+// value must equal the model's max_output_tokens.default in the CLI registry.
+//
+// Pinned per model deliberately. A threshold assertion would let every entry sit at some arbitrary
+// value above the bar and still call itself "registry-aligned" — which is the actual claim. Adding
+// a model means adding a row here, and that is the point: the row is where you record what the
+// registry said when you checked.
+const _spotRegistryMaxTokens = {           // CLI 2.1.220, id-anchored max_output_tokens.default
+  "claude-opus-5": 64000, "claude-opus-4-8": 64000, "claude-opus-4-7": 64000, "claude-opus-4-6": 64000,
+  "claude-sonnet-5": 64000, "claude-sonnet-4-6": 32000, "claude-haiku-4-5-20251001": 32000,
+};
+test("models.json: every maxTokens equals the CLI registry's max_output_tokens.default (#195)", () => {
   for (const m of _spotModels.models) {
-    assert.ok(m.maxTokens > _spotHighThinkingBudget,
-      `${m.id} declares maxTokens=${m.maxTokens} <= ${_spotHighThinkingBudget}: at OpenClaw's 'high' reasoning ` +
-      `level the thinking budget would consume all but ~1024 tokens of the response`);
+    const want = _spotRegistryMaxTokens[m.id];
+    assert.ok(want !== undefined,
+      `${m.id} has no recorded registry value — extract it id-anchored from the CLI binary and add a row`);
+    assert.equal(m.maxTokens, want, `${m.id}: models.json says ${m.maxTokens}, CLI registry says ${want}`);
   }
 });