Revert "feat(recipes): add reranker touchpoint to OpenRouter (#2164)"

This reverts commit 1a449bf501.

src/core/ai/recipes/openrouter.ts

@@ -23,14 +23,6 @@ import type { Recipe } from '../types.ts';
  * envelope, not every individual model's capability. When in doubt about a
  * specific model, check https://openrouter.ai/models.
  *
- * Reranker: `/api/v1/rerank` proxies cross-encoder rerankers (Cohere v3.5/4-fast/4-pro
- * and NVIDIA Nemotron VL). Wire shape matches `gateway.rerank()`:
- * `{ query, documents, model }` → `{ results: [{ index, relevance_score }] }`.
- * Unlike embedding/chat, the reranker path strictly enforces the `models`
- * allowlist (no openai-compat bypass) — adding new rerank models requires a
- * recipe edit. Cohere bills per-search; the `cost_per_1m_tokens_usd` value
- * is a pseudo-rate for the budget tracker's `chars/4` heuristic.
- *
  * Attribution: OpenRouter recommends `HTTP-Referer` (required for app
  * attribution) + `X-OpenRouter-Title` (preferred; `X-Title` kept as
  * back-compat alias per OR docs). Defaults to `https://gbrain.ai` / `gbrain`;
@@ -107,30 +99,6 @@ export const openrouter: Recipe = {
       // Let upstream errors surface per-model.
       price_last_verified: '2026-05-20',
     },
-    reranker: {
-      models: [
-        'cohere/rerank-v3.5',
-        'cohere/rerank-4-fast',
-        'cohere/rerank-4-pro',
-        'nvidia/llama-nemotron-rerank-vl-1b-v2:free',
-      ],
-      default_model: 'cohere/rerank-v3.5',
-      // Cohere bills per-search, not per-token. This is a pseudo-per-1M rate
-      // for the budget tracker's heuristic (estimates tokens as chars/4).
-      // At ~4K chars/search the tracker estimates ~$0.00025 — in the right
-      // ballpark for the per-search bill. Patch budget-tracker.ts to honour a
-      // `cost_per_search_usd` field for exact accounting.
-      cost_per_1m_tokens_usd: 0.001,
-      price_last_verified: '2026-06-13',
-      // OpenRouter doesn't publish an explicit payload cap; 5MB matches
-      // ZeroEntropy's upstream limit and the gateway's pre-flight ceiling.
-      max_payload_bytes: 5_000_000,
-      // OR serves /rerank under /api/v1. base_url_default already ends in /v1,
-      // so gateway concatenates to …/api/v1/rerank.
-      path: '/rerank',
-      // OpenRouter rerank is fast (<200 ms p50); 5 s covers cold path safely.
-      default_timeout_ms: 5_000,
-    },
   },
   setup_hint:
     'Get an API key at https://openrouter.ai/settings/keys, then `export OPENROUTER_API_KEY=...` and use `openrouter:<provider>/<model>`. Optional overrides: OPENROUTER_BASE_URL (proxy), OPENROUTER_REFERER (attribution URL), OPENROUTER_TITLE (attribution name).',

test/openrouter-reranker-recipe.test.ts

@@ -1,44 +0,0 @@
-import { describe, test, expect } from 'bun:test';
-import { getRecipe } from '../src/core/ai/recipes/index.ts';
-
-describe('OpenRouter recipe — reranker touchpoint', () => {
-  test('declares a reranker touchpoint', () => {
-    const r = getRecipe('openrouter');
-    expect(r).toBeDefined();
-    expect(r!.touchpoints.reranker).toBeDefined();
-  });
-
-  test('models list includes all supported IDs (incl. NVIDIA :free suffix)', () => {
-    const m = getRecipe('openrouter')!.touchpoints.reranker!.models;
-    expect(m).toContain('cohere/rerank-v3.5');
-    expect(m).toContain('cohere/rerank-4-fast');
-    expect(m).toContain('cohere/rerank-4-pro');
-    // The :free suffix must appear in full — gateway.rerank() does exact
-    // string matching against the allowlist (no v0.31.12 extended-model bypass
-    // on the rerank path), so truncating to `nvidia/.../v2` would 403.
-    expect(m).toContain('nvidia/llama-nemotron-rerank-vl-1b-v2:free');
-  });
-
-  test('default_model is cohere/rerank-v3.5', () => {
-    const tp = getRecipe('openrouter')!.touchpoints.reranker!;
-    expect(tp.default_model).toBe('cohere/rerank-v3.5');
-    expect(tp.models).toContain(tp.default_model);
-  });
-
-  test('path is /rerank (NOT ZeroEntropy default /models/rerank)', () => {
-    const tp = getRecipe('openrouter')!.touchpoints.reranker!;
-    expect(tp.path).toBe('/rerank');
-  });
-
-  test('max_payload_bytes and timeout match plan', () => {
-    const tp = getRecipe('openrouter')!.touchpoints.reranker!;
-    expect(tp.max_payload_bytes).toBe(5_000_000);
-    expect(tp.default_timeout_ms).toBe(5_000);
-  });
-
-  test('cost_per_1m_tokens_usd is set (pseudo-rate for per-search billing)', () => {
-    const tp = getRecipe('openrouter')!.touchpoints.reranker!;
-    expect(typeof tp.cost_per_1m_tokens_usd).toBe('number');
-    expect(tp.cost_per_1m_tokens_usd).toBeGreaterThan(0);
-  });
-});