Changelog, dev startup, README, AgentHub 0.4.0, model catalog, and landing site (#7)

Branch-length batch covering tooling, the model layer, the Web App and the public
surfaces. Highlights:

- Changelog: a per-release `changelog/<version>/` tree, grouped by the surface each
  change touches, with a root CHANGELOG.md holding one line per release.
- Dev startup: `scripts/dev-prebuild.mjs` serializes the skills+core prebuild behind a
  lock and keeps `pnpm install` current; `pnpm dev` runs server+web together.
- AgentHub 0.3.3 -> 0.4.0: OmniMessage complete payloads carry one opaque `fidelity`
  object in place of item-level `signature`/`phase`, threaded verbatim through Trace,
  replay and resume; malformed classification adapted to the new error types.
- Model layer: a model is always referenced by an explicit `(provider, model_id)` pair.
  The provider is never inferred, guessed or defaulted -- both the catalog inference and
  the unique-match config resolution are gone, and CLI, SDK, server routes and
  run_subagent all require the complete pair. Catalog gains the Qwen Token Plan, Qwen
  Pay-As-You-Go and Fireworks AI gateways, plus an expanded OpenRouter group.
- Web App: catalog preset sync and per-group speed test on the Models page, positional
  slash commands, a markdown renderer, skill-library update reminders, and a vertically
  centred draft page whose upward menus size themselves to the room available.
- Public surfaces: restructured READMEs, the penguin.ooo landing site and blog, refreshed
  benchmark results for both suites, and the demo videos playing on the landing page.

Includes the fixes from a full review of the branch: 23 confirmed findings, among them a
provider-inference bug that could send one vendor's API key to another vendor's endpoint,
and an Escape handler that destroyed the composer's contents unrecoverably.

Verified on the branch head: pnpm test (1127 passing, 7 packages), pnpm typecheck and
pnpm format:check clean, Playwright e2e 14/14.

packages/web/test/model-grouping.test.ts

@@ -10,7 +10,11 @@
  */
 import { describe, expect, it } from "vitest";
 import { MODEL_PROVIDERS } from "@prismshadow/penguin-core/model-catalog";
-import { groupModelRows, matchesQuery } from "../src/features/models/model-grouping";
+import {
+  groupModelRows,
+  orderModelsLikeLibrary,
+  matchesQuery,
+} from "../src/features/models/model-grouping";
 import type { ModelRowLike } from "../src/features/models/model-grouping";
 
 const rows: ModelRowLike[] = [
@@ -64,7 +68,10 @@ describe("groupModelRows", () => {
     expect(MODEL_PROVIDERS.map((p) => p.id)).toEqual([
       "deepseek",
       "openrouter",
+      "fireworks",
       "siliconflow",
+      "qwen-token-plan",
+      "qwen-pay-as-you-go",
       "google",
       "anthropic",
       "openai",
@@ -123,3 +130,26 @@ describe("groupModelRows", () => {
     expect(groupModelRows(mixed, "zeta").map((g) => g.provider.id)).toEqual(["zeta-lab"]);
   });
 });
+
+describe("orderModelsLikeLibrary", () => {
+  it("flattens to the library page's order: built-in provider order, user groups after, custom last", () => {
+    const rows: ModelRowLike[] = [
+      { provider: "custom", modelId: "my-proxy" },
+      { provider: "my-gateway", modelId: "own-1" },
+      { provider: "moonshot", modelId: "kimi-k3" },
+      { provider: "deepseek", modelId: "deepseek-v4-flash" },
+      { provider: "openrouter", modelId: "anthropic/claude-fable-5" },
+      { provider: "deepseek", modelId: "deepseek-v4-pro" },
+    ];
+    expect(orderModelsLikeLibrary(rows).map((r) => `${r.provider} ${r.modelId}`)).toEqual([
+      // deepseek first (in-group order preserved), then the openrouter gateway, then moonshot,
+      // then custom, then the user-defined group appended after the built-ins.
+      "deepseek deepseek-v4-flash",
+      "deepseek deepseek-v4-pro",
+      "openrouter anthropic/claude-fable-5",
+      "moonshot kimi-k3",
+      "custom my-proxy",
+      "my-gateway own-1",
+    ]);
+  });
+});