melchizedek-agents 1.11.0 → 1.11.1

package/CHANGELOG.md

@@ -4,6 +4,23 @@ Consumers of the package read this file; it records changes to the
 **published API surface** (the exports map in `package.json`, the bins,
 the starter pack and the templates), not the repo's full history.
 
+## 1.11.1 — 2026-10-22
+
+**Price rows for `grok-4.3`, `gemini-embedding-001` and `gemini-3.5-flash`**
+(migration `0020_embedding_flash_grok_pricing`). Ledgers held calls of these
+models priced NULL for want of a row. `grok-4.3` is checked against xAI's
+list (its rate under 200k prompt tokens); the two Gemini rows come from
+sources other than Google's current page, which no longer lists them, so
+their `verified_at` is NULL. An existing row is never overwritten.
+
+**`gemini-3.8-flash` and `grok-4.7` at their vendors' lists** (migration
+`0021_correct_gemini_flash_grok_rates`). Both were 0015 placeholders:
+`gemini-3.8-flash` is now $0.75 / $0.075 cached / $3.75 (was $0.30 / $2.50;
+Google lists a rise to $1.50 / $0.15 / $7.50 from 2027-01-01), `grok-4.7`
+$2.00 / $0.50 / $6.00 (was $3.00 / $15.00). A row changes only while it is
+still the seed, at the seed's rates; an operator's rate is kept. Calls
+already priced keep the rate they were written at.
+
 ## 1.11.0 — 2026-10-22
 
 A minor release: DeepSeek joins the providers, and Kimi calls are priced.

package/db/migrations/0020_embedding_flash_grok_pricing.sql

@@ -0,0 +1,38 @@
+-- ============================================================================
+-- 0020_embedding_flash_grok_pricing — price rows for three models a ledger
+--                                     already holds calls of (extends ADR 0136)
+-- ============================================================================
+-- Rows only, in 0017's column layout (USD per million tokens). A deployment's
+-- ledger (penguin's, 2026-10-22) had calls of these three models priced NULL
+-- because no row existed; scripts that re-price NULL rows can now fill them.
+--
+-- grok-4.3: xAI first-party, docs.x.ai/docs/models, checked 2026-10-22. The
+-- row holds the rate under 200k prompt tokens ($1.25 in / $0.20 cached /
+-- $2.50 out); a request of 200k or more is billed at double for all its
+-- tokens ($2.50 / $0.40 / $5.00), which a flat row cannot say: such a call
+-- is underestimated by half.
+--
+-- gemini-embedding-001: Google's GA announcement for the Gemini API
+-- (developers.googleblog.com, "Gemini Embedding now generally available"):
+-- $0.15 per 1M input tokens, no output tokens. Google's current pricing page
+-- lists only its successor (gemini-embedding-2), so verified_at stays NULL.
+--
+-- gemini-3.5-flash: $1.50 in / $0.15 cached / $9.00 out, as two pricing
+-- guides give it, one citing Google's Gemini API pricing documentation
+-- (June 2026). Google's current page no longer lists the model (superseded
+-- by 3.6 and 3.8 Flash), so this could not be checked against the vendor:
+-- verified_at NULL, a steering estimate (0015's convention).
+--
+-- New rows never overwrite a row that exists: an operator's own rates
+-- survive. Nothing secret, nothing personal. Idempotent; safe to re-run.
+-- ============================================================================
+
+INSERT INTO model_pricing (model, input_per_mtok, output_per_mtok, cache_read_per_mtok, cache_write_per_mtok, verified_at, source, note) VALUES
+  ('grok-4.3',             1.25, 2.50, 0.20, NULL, '2026-10-22', 'docs.x.ai/docs/models', 'xAI first-party, checked 2026-10-22; rate under 200k prompt tokens (a request of 200k or more bills $2.50 / $0.40 / $5.00)'),
+  ('gemini-embedding-001', 0.15, 0.00, NULL, NULL, NULL,         'developers.googleblog.com, Gemini Embedding now generally available in the Gemini API', 'Google first-party announcement; input only; no longer on the current pricing page (successor gemini-embedding-2), not re-checked'),
+  ('gemini-3.5-flash',     1.50, 9.00, 0.15, NULL, NULL,         'eesel.ai Gemini 3 pricing guide (citing ai.google.dev pricing, June 2026), agreeing with other guides', 'unverified: off Google''s current pricing page (superseded by 3.6 and 3.8 Flash)')
+ON CONFLICT (model) DO NOTHING;
+
+INSERT INTO melchizedek_schema_version (version, name)
+VALUES (20, '0020_embedding_flash_grok_pricing')
+ON CONFLICT (version) DO NOTHING;

package/db/migrations/0021_correct_gemini_flash_grok_rates.sql

@@ -0,0 +1,46 @@
+-- ============================================================================
+-- 0021_correct_gemini_flash_grok_rates — two seed rows to their vendors'
+--                                        current lists (extends ADR 0136)
+-- ============================================================================
+-- 0015 seeded gemini-3.8-flash and grok-4.7 from melch-obs's pricing.toml as
+-- unverified estimates. Checked 2026-10-22 against the vendors' lists, both
+-- were wrong:
+--
+--   gemini-3.8-flash  ai.google.dev/gemini-api/docs/pricing (paid, standard):
+--                     $0.75 in / $0.075 cached / $3.75 out, thinking billed
+--                     as output, through 2026-12-31. Google has announced
+--                     $1.50 / $0.15 / $7.50 from 2027-01-01; a flat row cannot
+--                     say the date, so that needs its own row change then.
+--                     Seed: $0.30 / $2.50 (a placeholder at 3.7's rate).
+--   grok-4.7          docs.x.ai/docs/models: $2.00 in / $0.50 cached / $6.00
+--                     out under 200k prompt tokens (a request of 200k or more
+--                     bills $4.00 / $1.00 / $12.00 for all its tokens, which a
+--                     flat row underestimates by half). Seed: $3.00 / $15.00.
+--
+-- A row changes only while it is still the seed: source melch-obs/pricing.toml,
+-- verified_at NULL, and the seed's own rates. A rate an operator set is kept.
+--
+-- Rows already priced keep what they were priced at: the ledger records the
+-- rate in force at write time (db/telemetry.sql). Re-pricing history is a
+-- deliberate UPDATE, never a migration. Idempotent; safe to re-run.
+-- ============================================================================
+
+UPDATE model_pricing
+   SET input_per_mtok = 0.75, output_per_mtok = 3.75, cache_read_per_mtok = 0.075,
+       verified_at = '2026-10-22', source = 'ai.google.dev/gemini-api/docs/pricing',
+       note = 'Gemini API paid standard tier, checked 2026-10-22; rate through 2026-12-31 (Google lists $1.50 / $0.15 / $7.50 from 2027-01-01)',
+       updated_at = now()
+ WHERE model = 'gemini-3.8-flash' AND source = 'melch-obs/pricing.toml' AND verified_at IS NULL
+   AND input_per_mtok = 0.30 AND output_per_mtok = 2.50;
+
+UPDATE model_pricing
+   SET input_per_mtok = 2.00, output_per_mtok = 6.00, cache_read_per_mtok = 0.50,
+       verified_at = '2026-10-22', source = 'docs.x.ai/docs/models',
+       note = 'xAI first-party, checked 2026-10-22; rate under 200k prompt tokens (a request of 200k or more bills $4.00 / $1.00 / $12.00)',
+       updated_at = now()
+ WHERE model = 'grok-4.7' AND source = 'melch-obs/pricing.toml' AND verified_at IS NULL
+   AND input_per_mtok = 3.00 AND output_per_mtok = 15.00;
+
+INSERT INTO melchizedek_schema_version (version, name)
+VALUES (21, '0021_correct_gemini_flash_grok_rates')
+ON CONFLICT (version) DO NOTHING;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "melchizedek-agents",
-  "version": "1.11.0",
+  "version": "1.11.1",
   "description": "A multi-model, multi-agent orchestration framework — YAML-defined syndicates on the engine's own agent loop, Supabase or Postgres session persistence, pgvector long-term memory. Companion repo to the lyceumagents.com curriculum.",
   "type": "module",
   "license": "MIT",