Model matrix — 5 tiers, local hard workers + cloud overseers

config/models.json is the authoritative catalog. Hot path (T1/T2) stays
local; cloud is consulted only for overview (T3), strategic (T4), and
gatekeeper (T5) calls. J named qwen3.5 + newer models (minimax-m2.7,
glm-5, qwen3-next) specifically — all mapped with real reachable IDs
verified against ollama.com/api/tags.

Tier shape:
- t1_hot     mistral + qwen2.5 local       — 50-200 calls/scenario
- t2_review  qwen2.5 + qwen3 local         — 5-14 calls/event
- t3_overview gpt-oss:120b cloud           — 1-3 calls/scenario
- t4_strategic qwen3.5:397b + glm-4.7      — 1-10 calls/day
- t5_gatekeeper kimi-k2-thinking           — 1-5 calls/day, audit-logged

Rate budgets are declared in-config — Ollama Cloud paid tier is generous
but we cap overview/strategic/gatekeeper so no single rogue scenario can
blow the day's quota.

Experimental rotation list wired but disabled by default. When enabled,
T4 randomly routes 10% of calls to a rotating minimax/GLM/qwen-next/
deepseek/nemotron/cogito/mistral-large candidate, logs comparisons, and
auto-promotes after 3 rotations of wins.

Playbook versioning SPEC embedded under `playbook_versioning` key: every
seed gets version + parent_id + retired_at + architecture_snapshot, so
when a schema migration breaks a playbook we can pinpoint which change
retired it. Implementation flagged for next sprint (touches gateway +
catalogd + mcp-server) — not wired here.

- scenario.ts now loads config/models.json at init, env vars still override
- mcp-server exposes /models/matrix read-only so UI can render it

mcp-server/index.ts

@@ -833,6 +833,22 @@ async function main() {
           });
         }
 
+        // Model matrix — read config/models.json and expose read-only.
+        // Strips internal notes that could drift; the source of truth is
+        // the file itself. UI can render tiers, rate budgets, and the
+        // experimental rotation list from this endpoint.
+        if (url.pathname === "/models/matrix") {
+          try {
+            const raw = await Bun.file("../config/models.json").text();
+            return ok(JSON.parse(raw));
+          } catch (e) {
+            return new Response(JSON.stringify({ error: `models.json not found: ${(e as Error).message}` }), {
+              status: 404,
+              headers: { "content-type": "application/json" },
+            });
+          }
+        }
+
         // Proof JSON API (same data, no HTML)
         if (url.pathname === "/proof.json") {
           const ds = await api("GET", "/catalog/datasets") as any[];