v1.91.80.0 fix(eval-plan): price the default eval-arms tier (claude-opus-5-5, gpt-6.1-sol) (#3124)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## [1.91.80.0] - 2026-10-11
+
+**`/eval-plan` prices its default arms out of the box.** `lib/pricing.ts` gains verified rows for `claude-opus-5-5` ($4 / $20 per MTok, cache reads $0.20; Anthropic list prices effective 2026-10-07) and `gpt-6.1-sol` ($2 / $10 per MTok, cached input $0.10; OpenAI model page, standard tier), the two models `gstack-models resolve --role eval-arms` returns under the default `smart` implementation tier. `gstack-eval-plan arms` previously exited `EVAL_PRICE_MISSING` for both; the fail-closed rule is unchanged, only the data was missing.
+
 ## [1.91.79.0] - 2026-10-11
 
 **`/eval-plan` preregisters paid evals for your product, coordination tools keep parallel lanes from colliding, and the autoplan owner sees a one-page brief instead of the full review (multi-agent wave PR E, plan items E1 tier 1, E2, E3).**

VERSION

@@ -1 +1 @@
-1.91.79.0
+1.91.80.0

agents-digest/gstack-AGENTS.md

@@ -1,4 +1,4 @@
-# gstack digest v1.91.79.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.80.0 — regenerate/re-copy after upgrading gstack
 
 Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
 for agent hosts without a full skill install. The full skills add workflows,

lib/pricing.ts

@@ -43,6 +43,8 @@ export const PRICING: Record<string, ModelPricing> = {
   // Claude (Anthropic)
   // https://platform.claude.com/docs/en/models/fable-5-1/overview#pricing
   'claude-fable-5-1':  { input_per_mtok: 10.00, output_per_mtok: 50.00, cached_input_per_mtok: 0.25, as_of: '2026-09' },
+  // https://platform.claude.com/docs/en/models/opus-5-5/overview#pricing (list prices effective 2026-10-07)
+  'claude-opus-5-5':    { input_per_mtok: 4.00,  output_per_mtok: 20.00, cached_input_per_mtok: 0.20, as_of: '2026-10' },
   'claude-opus-4-7':    { input_per_mtok: 15.00, output_per_mtok: 75.00, as_of: '2026-04' },
   'claude-sonnet-4-6':  { input_per_mtok: 3.00,  output_per_mtok: 15.00, as_of: '2026-04' },
   'claude-haiku-4-5':   { input_per_mtok: 1.00,  output_per_mtok: 5.00,  as_of: '2026-04' },
@@ -50,6 +52,8 @@ export const PRICING: Record<string, ModelPricing> = {
   // OpenAI (GPT + o-series)
   // https://developers.openai.com/api/docs/models/gpt-6-astra
   'gpt-6-astra':        { input_per_mtok: 10.00, output_per_mtok: 50.00, cached_input_per_mtok: 1.00, as_of: '2026-09' },
+  // https://developers.openai.com/api/docs/models/gpt-6.1-sol (standard tier, up to 272K input)
+  'gpt-6.1-sol':        { input_per_mtok: 2.00,  output_per_mtok: 10.00, cached_input_per_mtok: 0.10, as_of: '2026-10' },
   'gpt-5.4':            { input_per_mtok: 2.50,  output_per_mtok: 10.00, as_of: '2026-04' },
   'gpt-5.4-mini':       { input_per_mtok: 0.60,  output_per_mtok: 2.40,  as_of: '2026-04' },
   'o3':                 { input_per_mtok: 15.00, output_per_mtok: 60.00, as_of: '2026-04' },

package.json

@@ -1,6 +1,6 @@
 {
   "name": "gstack",
-  "version": "1.91.79",
+  "version": "1.91.80",
   "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
   "license": "MIT",
   "type": "module",

test/pricing-eval-plan.test.ts

@@ -34,6 +34,10 @@ describe('lib/pricing', () => {
     expect(estimateCostUsd({ input: 1_000_000, output: 0, cached: 1_000_000 }, 'claude-fable-5-1')).toBe(10.25);
     expect(estimateCostUsd({ input: 10, output: 10 }, 'nobody/made-this-up')).toBe(0);
   });
+
+  test('the default eval-arms tier (smart) is priced out of the box', () => {
+    for (const model of ['claude-opus-5-5', 'gpt-6.1-sol']) expect(hasPricing(model)).toBe(true);
+  });
 });
 
 describe('preregistration', () => {