@askalf/dario 6.6.1 → 6.6.3

package/README.md

@@ -368,7 +368,7 @@ Type `dario` with no arguments for a full-screen control panel: live request str
 
 <picture>
   <source media="(prefers-color-scheme: dark)" srcset=".github/readme/tui-analytics-dark.svg">
-  <img alt="The dario TUI Analytics tab: requests per minute, tokens in and out, thinking tokens, average latency, subscription percentage, a per-model bar chart, per-account rate-limit bars for the 5-hour and 7-day windows, and a billing breakdown." src=".github/readme/tui-analytics-light.svg" width="100%">
+  <img alt="The dario TUI Analytics tab: requests per minute, tokens in and out, thinking tokens, average latency, subscription percentage, the lifetime API-equivalent spend from the ledger, a per-model bar chart, per-account rate-limit bars for the 5-hour and 7-day windows, and a billing breakdown." src=".github/readme/tui-analytics-light.svg" width="100%">
 </picture>
 
 <sub>Both screenshots are rendered from the real TUI against a fixture proxy by <a href="scripts/readme/tui.mjs"><code>scripts/readme/tui.mjs</code></a>, so a layout change shows up here instead of rotting a mock-up. The numbers are illustrative; the pixels are not.</sub>
@@ -663,6 +663,14 @@ Two easy ways to help beyond code: **star the repo**, the clearest signal this i
 | [@anupamme](https://github.com/anupamme) | Refresh-lock ownership by server-issued lock id ([#1059](https://github.com/askalf/dario/pull/1059)) |
 | [@LiveNathan](https://github.com/LiveNathan) | Never send or stamp empty text blocks ([#1067](https://github.com/askalf/dario/pull/1067)), empty final user turn from CC's stream-interruption retry ([#1092](https://github.com/askalf/dario/issues/1092), as [@NathanLively](https://github.com/NathanLively)) |
 
+### Sponsors
+
+<!-- sponsors:start -->
+dario is funded by its users through [GitHub Sponsors](https://github.com/sponsors/askalf) — the live-test seats it is checked against before every release are the biggest line item. Sponsors at $25/month and up are listed here.
+<!-- sponsors:end -->
+
+<sub>This block and the thank-you in each release's notes come from <a href="scripts/sponsors.mjs"><code>scripts/sponsors.mjs</code></a>, which reads the public sponsor list; <code>sponsors-readme.yml</code> opens a PR when it changes. Private sponsors are never named.</sub>
+
 ## Disclaimers
 
 **dario is an independent, unofficial, third-party project.** Not affiliated with, endorsed by, or sponsored by Anthropic, OpenAI, or any vendor referenced here. Provided as-is, no warranty. You are solely responsible for compliance with your subscription's terms, the security of your credentials, and the content you send through the proxy. Not for safety-critical, regulated, or production environments without your own review. Full text: [DISCLAIMER.md](DISCLAIMER.md).

package/dist/analytics.d.ts

@@ -202,16 +202,20 @@ interface PricingEntry extends Rate {
 export declare const PRICING: Record<string, PricingEntry>;
 /**
  * OpenAI's published per-1M-token rates for the models the codex backend
- * serves, standard tier, read off developers.openai.com/api/docs/pricing on
- * 2026-09-11. Kept apart from PRICING because scripts/check-pricing-drift.mjs
- * diffs that table against Anthropic's page and would report every row here
- * as "absent upstream". OpenAI charges nothing to write a cache entry, so
- * cacheCreate is the input rate (the codex path reports no cache writes
- * anyway — `cached_tokens` lands in cacheReadTokens, the rest in inputTokens).
+ * serves — the standard tier's short-context (<272K) columns of
+ * developers.openai.com/api/docs/pricing. Kept apart from PRICING because
+ * scripts/check-pricing-drift.mjs diffs each table against its own page
+ * (this one since 6.6.1; it shipped unwatched in 6.6.0, and the first watched
+ * run found the cache-write column wrong: the 5.6 family and gpt-6-astra
+ * charge 1.25× input to write a cache entry, the older families list no
+ * write price, encoded here as cacheCreate = input). The codex path reports
+ * no cache writes anyway — `cached_tokens` lands in cacheReadTokens, the
+ * rest in inputTokens — so the column is for correctness, not for a number
+ * anyone has seen yet.
  *
  * Before this table every `gpt-*` row was priced at the sonnet-4-6 fallback:
  * a ChatGPT-plan request showed up in "would-be API cost" at Anthropic's
- * rate for a model Anthropic does not sell. Nothing watches this table yet.
+ * rate for a model Anthropic does not sell.
  */
 export declare const OPENAI_PRICING: Record<string, Rate>;
 export type PricingProvider = 'anthropic' | 'openai';

package/dist/analytics.js

@@ -231,27 +231,30 @@ export const PRICING = {
 };
 /**
  * OpenAI's published per-1M-token rates for the models the codex backend
- * serves, standard tier, read off developers.openai.com/api/docs/pricing on
- * 2026-09-11. Kept apart from PRICING because scripts/check-pricing-drift.mjs
- * diffs that table against Anthropic's page and would report every row here
- * as "absent upstream". OpenAI charges nothing to write a cache entry, so
- * cacheCreate is the input rate (the codex path reports no cache writes
- * anyway — `cached_tokens` lands in cacheReadTokens, the rest in inputTokens).
+ * serves — the standard tier's short-context (<272K) columns of
+ * developers.openai.com/api/docs/pricing. Kept apart from PRICING because
+ * scripts/check-pricing-drift.mjs diffs each table against its own page
+ * (this one since 6.6.1; it shipped unwatched in 6.6.0, and the first watched
+ * run found the cache-write column wrong: the 5.6 family and gpt-6-astra
+ * charge 1.25× input to write a cache entry, the older families list no
+ * write price, encoded here as cacheCreate = input). The codex path reports
+ * no cache writes anyway — `cached_tokens` lands in cacheReadTokens, the
+ * rest in inputTokens — so the column is for correctness, not for a number
+ * anyone has seen yet.
  *
  * Before this table every `gpt-*` row was priced at the sonnet-4-6 fallback:
  * a ChatGPT-plan request showed up in "would-be API cost" at Anthropic's
- * rate for a model Anthropic does not sell. Nothing watches this table yet.
+ * rate for a model Anthropic does not sell.
  */
 export const OPENAI_PRICING = {
-    'gpt-6-astra': { input: 10, output: 50, cacheRead: 1, cacheCreate: 10 },
-    'gpt-5.6-sol': { input: 4, output: 20, cacheRead: 0.4, cacheCreate: 4 },
-    'gpt-5.6-terra': { input: 2, output: 12, cacheRead: 0.2, cacheCreate: 2 },
-    'gpt-5.6-luna': { input: 0.2, output: 1.2, cacheRead: 0.02, cacheCreate: 0.2 },
+    'gpt-6-astra': { input: 10, output: 50, cacheRead: 1, cacheCreate: 12.5 },
+    'gpt-5.6-sol': { input: 4, output: 20, cacheRead: 0.4, cacheCreate: 5 },
+    'gpt-5.6-terra': { input: 2, output: 12, cacheRead: 0.2, cacheCreate: 2.5 },
+    'gpt-5.6-luna': { input: 0.2, output: 1.2, cacheRead: 0.02, cacheCreate: 0.25 },
     'gpt-5.5': { input: 5, output: 30, cacheRead: 0.5, cacheCreate: 5 },
     'gpt-5.4': { input: 2.5, output: 15, cacheRead: 0.25, cacheCreate: 2.5 },
     'gpt-5.4-mini': { input: 0.75, output: 4.5, cacheRead: 0.075, cacheCreate: 0.75 },
     'gpt-5.4-nano': { input: 0.2, output: 1.25, cacheRead: 0.02, cacheCreate: 0.2 },
-    'gpt-5.3-codex': { input: 1.75, output: 14, cacheRead: 0.175, cacheCreate: 1.75 },
 };
 /** The unknown-model rate on the OpenAI side: dario's default codex model. */
 const OPENAI_FALLBACK_MODEL = 'gpt-5.6-terra';

package/docs/api-equivalent-spend.md

@@ -110,7 +110,12 @@ nothing to write a cache entry, so cache-write tokens (which the codex path
 never reports anyway) are priced at the input rate. Unknown `gpt-*` ids take
 gpt-5.6-terra's rate, dario's default codex model.
 
-`scripts/check-pricing-drift.mjs` watches the Claude table against
-Anthropic's page. Nothing watches the OpenAI table yet — an entry that is
-correct today goes wrong the moment OpenAI changes it, and the only signal
-would be this number moving.
+`scripts/check-pricing-drift.mjs` watches both tables daily
+(`pricing-drift-watch.yml`): `PRICING` against Anthropic's page,
+`OPENAI_PRICING` against OpenAI's `pricing.md` (the standard table's
+short-context columns, found by its heading — the batch and fast-mode tables
+below it carry the same headers). The first watched run corrected the table:
+the 5.6 family and gpt-6-astra list a cache-write price of 1.25× input, which
+6.6.0 had as the input rate. A page the watcher can fetch but no longer
+understand is filed as an issue, not logged as a warning — that is how the
+Anthropic side went unwatched for ten days in September 2026.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@askalf/dario",
-  "version": "6.6.1",
+  "version": "6.6.3",
   "description": "Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint: either plan answers either wire shape, with automatic failover when one hits its limit.",
   "type": "module",
   "bin": {