From 9b29206ba34bd268a1184049faa75ebb206d680c Mon Sep 17 00:00:00 2001 From: garrytan Date: Sat, 31 Oct 2026 18:32:47 +0000 Subject: [PATCH 1/4] pricing: rows for claude-haiku-5-5, gpt-6-luna and gemini-4-argon (#3640) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- lib/pricing.ts | 8 ++++++++ test/pricing-eval-plan.test.ts | 17 +++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/lib/pricing.ts b/lib/pricing.ts index 9d867e442..95c94598a 100644 --- a/lib/pricing.ts +++ b/lib/pricing.ts @@ -51,6 +51,9 @@ export const PRICING: Record = { // https://platform.claude.com/docs/en/about-claude/pricing (fetched 2026-10-12) 'claude-sonnet-5-5': { input_per_mtok: 2.00, output_per_mtok: 10.00, cached_input_per_mtok: 0.10, as_of: '2026-10' }, 'claude-sonnet-4-6': { input_per_mtok: 3.00, output_per_mtok: 15.00, as_of: '2026-04' }, + // https://platform.claude.com/docs/en/about-claude/pricing (fetched 2026-10-31; standard tier, prompts up to + // 100,000 tokens; the $0.50 / $2.50 / $0.05 rate above that is excluded like the other long-context surcharges) + 'claude-haiku-5-5': { input_per_mtok: 0.10, output_per_mtok: 0.50, cached_input_per_mtok: 0.01, as_of: '2026-10' }, 'claude-haiku-4-5': { input_per_mtok: 1.00, output_per_mtok: 5.00, as_of: '2026-04' }, // OpenAI (GPT + o-series) @@ -58,6 +61,8 @@ export const PRICING: Record = { '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' }, + // https://developers.openai.com/api/docs/models/gpt-6-luna (fetched 2026-10-31; standard tier, up to 272K input) + 'gpt-6-luna': { input_per_mtok: 0.10, output_per_mtok: 0.50, cached_input_per_mtok: 0.01, as_of: '2026-10' }, 'gpt-5.4': { input_per_mtok: 2.50, output_per_mtok: 10.00, as_of: '2026-04' }, // https://developers.openai.com/api/docs/models/gpt-4o (fetched 2026-10-13; gbrain's LongMemEval judge, the official scorer's model; // the alias only: the gpt-4o-2024-05-13 snapshot has its own price) @@ -67,6 +72,9 @@ export const PRICING: Record = { 'o4-mini': { input_per_mtok: 1.10, output_per_mtok: 4.40, as_of: '2026-04' }, // Google + // https://ai.google.dev/gemini-api/docs/pricing (fetched 2026-10-31; the rates starting 2026-12-01, so estimates + // never under-price; through 2026-11-30 the page lists $2.00 / $10.00 / $0.10 cached; thinking tokens bill as output) + 'gemini-4-argon': { input_per_mtok: 4.00, output_per_mtok: 20.00, cached_input_per_mtok: 0.20, as_of: '2026-10' }, // https://ai.google.dev/gemini-api/docs/pricing (fetched 2026-10-12; standard tier through 2026-12-31, // the page lists $1.50 / $7.50 / $0.15 cached starting 2027-01-01) 'gemini-3.8-flash': { input_per_mtok: 0.75, output_per_mtok: 3.75, cached_input_per_mtok: 0.075, as_of: '2026-10' }, diff --git a/test/pricing-eval-plan.test.ts b/test/pricing-eval-plan.test.ts index 8784d88a0..ae4f03a7f 100644 --- a/test/pricing-eval-plan.test.ts +++ b/test/pricing-eval-plan.test.ts @@ -41,6 +41,12 @@ describe('lib/pricing', () => { 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); }); + + test('claude-haiku-5-5, gpt-6-luna and gemini-4-argon are priced (#3640)', () => { + for (const model of ['claude-haiku-5-5', 'anthropic/claude-haiku-5-5', 'gpt-6-luna', 'openai/gpt-6-luna', 'gemini-4-argon']) expect(hasPricing(model)).toBe(true); + expect(estimateCostUsd({ input: 1_000_000, output: 1_000_000 }, 'claude-haiku-5-5')).toBe(0.6); + expect(estimateCostUsd({ input: 1_000_000, output: 1_000_000 }, 'gemini-4-argon')).toBe(24); + }); }); describe('preregistration', () => { @@ -67,6 +73,17 @@ describe('arms', () => { const unpriced = resolveArms({ cwd: d, explicit: ['gpt-6-astra', 'made-up-model'] }); expect(unpriced.errors.map(e => e.code)).toEqual(['EVAL_PRICE_MISSING']); expect(renderArms(unpriced, { input: 1000, output: 1000 })).toContain('price=MISSING'); + const added = resolveArms({ cwd: d, explicit: ['claude-haiku-5-5', 'gpt-6-luna', 'gemini-4-argon'] }); + expect(added.errors).toEqual([]); + }); + + test('a policy document naming a newly priced model yields that arm', () => { + const d = tmp(); + const doc = path.join(d, 'MODELS.md'); + fs.writeFileSync(doc, '- cheap arm: claude-haiku-5-5\n- strong arm: claude-opus-5-5\n'); + const r = resolveArms({ cwd: d, policyDoc: doc, modelsCli: () => ({ code: 1, stdout: '' }) }); + expect(r.errors).toEqual([]); + expect(r.arms.map(a => a.model).sort()).toEqual(['claude-haiku-5-5', 'claude-opus-5-5']); }); test('the eval-arms role is read through the models CLI seam, never the network', () => { From 15e00f6f4a11945bdb30ddc5450a4bb4c20d2b23 Mon Sep 17 00:00:00 2001 From: garrytan Date: Sat, 31 Oct 2026 18:32:47 +0000 Subject: [PATCH 2/4] docs: name gpt-6.1-sol and gpt-6-luna as the current Codex tiers (#2943) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- changelog.d/gsta214-a.md | 9 +++++++++ codex/SKILL.md | 2 +- codex/SKILL.md.tmpl | 2 +- docs/hosts.md | 13 ++++++++----- 4 files changed, 19 insertions(+), 7 deletions(-) create mode 100644 changelog.d/gsta214-a.md diff --git a/changelog.d/gsta214-a.md b/changelog.d/gsta214-a.md new file mode 100644 index 000000000..216ddb5bd --- /dev/null +++ b/changelog.d/gsta214-a.md @@ -0,0 +1,9 @@ +**Eval planning prices Claude Haiku 5.5, GPT-6 Luna and Gemini 4 Argon, and the Codex docs name the current OpenAI tiers (#3640, #2943).** Before, `gstack-eval-plan arms --arms claude-haiku-5-5` stopped with EVAL_PRICE_MISSING because `lib/pricing.ts` had no row for it. docs/hosts.md and the /codex example still named gpt-5.6-sol as the current Sol model. + +### Added +- **Price rows** for `claude-haiku-5-5` ($0.10 / $0.50, cached $0.01, standard tier up to 100,000 tokens), `gpt-6-luna` ($0.10 / $0.50, cached $0.01) and `gemini-4-argon` ($4.00 / $20.00, cached $0.20). Each row cites its provider page. Argon uses the rates that start on 2026-12-01, so estimates never come in low after that date. A repository's model-policy document that names one of these models now gets it as an eval arm. + +### Changed +- **docs/hosts.md and /codex** name `gpt-6-astra`, `gpt-6.1-sol` and `gpt-6-luna` as the current tiers. They also say the bounded-scope overlay still applies only to `gpt-5.6-sol` until it has its own eval. + +Thanks to @exGeni (#3640) and @DanCanadian (#2943) for the reports. The TypeSafe Jev rows from #3640 are not included, because a $0 output price breaks the price table's rule that every row has an output price. diff --git a/codex/SKILL.md b/codex/SKILL.md index ab76ed9e4..0c0ecd0f4 100644 --- a/codex/SKILL.md +++ b/codex/SKILL.md @@ -550,7 +550,7 @@ codex >=0.144), the `-c` form explicitly overrides any top-level web search regardless of configuration, so on the default Review path the flag is a harmless no-op — only exec-based modes actually search. -If the user specifies a model (e.g., `/codex review -m gpt-5.6-sol` or +If the user specifies a model (e.g., `/codex review -m gpt-6.1-sol` or `/codex challenge --model gpt-daybreak-blue-latest`), translate it to the same config form and replace the default model flag with `-c "model=\"\""`. Native review also requires `-c "review_model=\"\""`; replace both model values together. diff --git a/codex/SKILL.md.tmpl b/codex/SKILL.md.tmpl index 9f55d3052..981013dab 100644 --- a/codex/SKILL.md.tmpl +++ b/codex/SKILL.md.tmpl @@ -271,7 +271,7 @@ codex >=0.144), the `-c` form explicitly overrides any top-level web search regardless of configuration, so on the default Review path the flag is a harmless no-op — only exec-based modes actually search. -If the user specifies a model (e.g., `/codex review -m gpt-5.6-sol` or +If the user specifies a model (e.g., `/codex review -m gpt-6.1-sol` or `/codex challenge --model gpt-daybreak-blue-latest`), translate it to the same config form and replace the default model flag with `-c "model=\"\""`. Native review also requires `-c "review_model=\"\""`; replace both model values together. diff --git a/docs/hosts.md b/docs/hosts.md index 1a18e0650..53ff7f765 100644 --- a/docs/hosts.md +++ b/docs/hosts.md @@ -154,11 +154,14 @@ digest's first line shows its gstack version; re-copy it after upgrading. For Codex, setup reads the top-level `model` from `${CODEX_HOME:-~/.codex}/config.toml` and generates the matching behavioral profile, falling back to `gpt-6-astra` when no usable model is configured. -`gpt-5.6-sol` automatically receives bounded-scope instructions that -finish the requested lake without expanding into adjacent cleanup or speculative -hardening. The Sol profile is exact-match only: dated snapshots and other 5.6 -variants get the generic GPT profile, and setup warns on near-misses like -`gpt-5.6-sol-2026-08-01`. Override detection with `./setup --host codex --model ` — the +The current OpenAI tiers are `gpt-6-astra` (frontier), `gpt-6.1-sol` (smart, the +default eval and outside-voice tier) and `gpt-6-luna` (lowest cost); `gpt-6.1-sol` +and `gpt-6-luna` get the generic GPT profile. Only `gpt-5.6-sol` receives the +bounded-scope instructions that finish the requested lake without expanding into +adjacent cleanup or speculative hardening, because that patch was measured on 5.6 +Sol; extending it to `gpt-6.1-sol` waits for its own scope eval. The Sol profile is +exact-match only: dated snapshots and other 5.6 variants get the generic GPT +profile, and setup warns on near-misses like `gpt-5.6-sol-2026-08-01`. Override detection with `./setup --host codex --model ` — the override applies to that run only; set `model` in your Codex `config.toml` to make it stick across upgrades. After changing your Codex model, rerun `./setup --host codex` to regenerate the skills. From 5608b75e2335e7494f093aba0a0eff982f943dd2 Mon Sep 17 00:00:00 2001 From: garrytan Date: Mon, 2 Nov 2026 23:18:43 +0000 Subject: [PATCH 3/4] docs(hosts): gpt-6.1-sol is the default eval tier, not the outside-voice default Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- docs/hosts.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/hosts.md b/docs/hosts.md index 53ff7f765..dfa83c274 100644 --- a/docs/hosts.md +++ b/docs/hosts.md @@ -155,7 +155,7 @@ For Codex, setup reads the top-level `model` from `${CODEX_HOME:-~/.codex}/config.toml` and generates the matching behavioral profile, falling back to `gpt-6-astra` when no usable model is configured. The current OpenAI tiers are `gpt-6-astra` (frontier), `gpt-6.1-sol` (smart, the -default eval and outside-voice tier) and `gpt-6-luna` (lowest cost); `gpt-6.1-sol` +default eval tier) and `gpt-6-luna` (lowest cost); `gpt-6.1-sol` and `gpt-6-luna` get the generic GPT profile. Only `gpt-5.6-sol` receives the bounded-scope instructions that finish the requested lake without expanding into adjacent cleanup or speculative hardening, because that patch was measured on 5.6 From 386a71baf06b62ff4e7cdf032ecd79ac51c11e88 Mon Sep 17 00:00:00 2001 From: garrytan Date: Mon, 2 Nov 2026 23:26:41 +0000 Subject: [PATCH 4/4] test(autoplan): use a model id with no price row for the unpriced-spend-cap case (claude-haiku-5-5 is priced now) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- test/autoplan-run-api.test.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/autoplan-run-api.test.ts b/test/autoplan-run-api.test.ts index 155ea7831..d243e374c 100644 --- a/test/autoplan-run-api.test.ts +++ b/test/autoplan-run-api.test.ts @@ -205,7 +205,7 @@ describe('gstack-autoplan run --native-runner api --runner api', () => { mode = 'ok'; calls = 0; const kind = ['GSTACK', 'SESSION', 'KIND'].join('_'); - const r = await run('unpriced', ['--spend-cap', '1'], { ANTHROPIC_API_KEY: 'ak-test', OPENAI_API_KEY: 'sk-test', [kind]: 'spawned' }, 'anthropic/claude-haiku-5-5'); + const r = await run('unpriced', ['--spend-cap', '1'], { ANTHROPIC_API_KEY: 'ak-test', OPENAI_API_KEY: 'sk-test', [kind]: 'spawned' }, 'anthropic/claude-unpriced-test-0'); expect(r.status).toBe(3); expect(r.stdout + r.stderr).toContain('SPEND_CAP_EXCEEDED'); expect(calls).toBe(0);