@askalf/dario 6.20.0 → 6.20.1

package/README.md

@@ -17,7 +17,7 @@
 
 <p><strong>One local endpoint. Every AI tool you own. Your Claude seats first, your ChatGPT plan and a metered key as the rungs you chain behind them, and a ledger of who paid for what.</strong></p>
 
-<sub><code>npm i -g @askalf/dario</code> or <code>brew install askalf/tap/dario</code> · <strong>0</strong> runtime deps · <a href="https://www.npmjs.com/package/@askalf/dario">SLSA-attested</a> every release · nothing phones home · ~43k lines you can read in a weekend · independent, unofficial, third-party (<a href="DISCLAIMER.md">DISCLAIMER.md</a>)</sub>
+<sub><code>npm i -g @askalf/dario</code> or <code>brew install askalf/tap/dario</code> · <strong>0</strong> runtime deps · <a href="https://www.npmjs.com/package/@askalf/dario">SLSA-attested</a> every release · nothing phones home · ~44k lines you can read in a weekend · independent, unofficial, third-party (<a href="DISCLAIMER.md">DISCLAIMER.md</a>)</sub>
 
 <sub><a href="#start-in-60-seconds">Start</a> · <a href="#why-people-pick-it">Why dario</a> · <a href="#what-it-does-with-a-request">Routing</a> · <a href="#will-my-account-get-suspended">Risk</a> · <a href="#reference">Reference</a> · <a href="#trust--transparency">Trust</a> · <a href="docs/returning.md">Coming back after a while?</a></sub>
 
@@ -114,11 +114,11 @@ dario runs entirely on your machine, authenticates as you with your own Claude l
 
 | Signal | Status |
 |---|---|
-| Source | **~43k** lines of TypeScript across **87** files, auditable in a weekend. One credential path since v5: the pool. |
+| Source | **~44k** lines of TypeScript across **88** files, auditable in a weekend. One credential path since v5: the pool. |
 | Dependencies | **0 runtime.** Verify: `npm ls --production` |
 | Provenance | Every release [SLSA-attested](https://www.npmjs.com/package/@askalf/dario) via GitHub Actions + Sigstore, published with OIDC trusted publishing: no long-lived npm token exists to leak |
 | Scanning | [CodeQL](https://github.com/askalf/dario/actions/workflows/codeql.yml) on every push to master, every PR and weekly · [ClusterFuzzLite](./.github/workflows/cflite.yml) fuzzes the SSE translator, the rejection parsers and the cch stamper weekly · the [OpenSSF Scorecard](https://scorecard.dev/viewer/?uri=github.com/askalf/dario) badge above and the [Best Practices](https://www.bestpractices.dev/projects/13638) entry are live |
-| Tests | **287 test files** run in parallel by `npm test` on Node 18, 20 and 22; the live e2e / compat / stealth suites have their own entry points. Green on every release |
+| Tests | **288 test files** run in parallel by `npm test` on Node 18, 20 and 22; the live e2e / compat / stealth suites have their own entry points. Green on every release |
 | Credentials | Your own subscription tokens, never logged, redacted from errors, `0600` on disk in `0700` dirs |
 | Network | Binds `127.0.0.1` by default; upstream only to configured backends over HTTPS; hardcoded SSRF allow-list; refuses a non-loopback bind without `DARIO_API_KEY`; refuses cross-origin and DNS-rebound browser requests |
 | Telemetry | **None.** No analytics, no tracking, nothing phones home |

package/dist/codex-backend.d.ts

@@ -50,6 +50,9 @@ export interface CodexForwardOutcome {
     outputTokens: number;
     cacheReadTokens: number;
     cacheCreateTokens: number;
+    /** Reasoning tokens counted inside outputTokens (Responses
+     *  `output_tokens_details.reasoning_tokens`); 0 when the backend sent none. */
+    reasoningTokens: number;
     stream: boolean;
     model: string;
     alias: string;
@@ -202,7 +205,17 @@ export interface CodexTokenUsage {
     output: number;
     cacheRead: number;
     cacheCreate: number;
+    /** The part of `output` that was reasoning; see reasoningTokensFromResponses. */
+    reasoning: number;
 }
+/**
+ * The reasoning share of a Responses usage block: `output_tokens_details.
+ * reasoning_tokens`, which OpenAI counts inside `output_tokens` the way
+ * Anthropic counts thinking inside its output. Rounded and capped at the
+ * output it is part of, 0 when absent or malformed, so an analytics row never
+ * carries more reasoning than output.
+ */
+export declare function reasoningTokensFromResponses(u: unknown, output: number): number;
 /**
  * Terminal Responses usage -> analytics accounting. Delegates the netting to
  * anthropicUsageFromResponses so the analytics row and the Anthropic-shape

package/dist/codex-backend.js

@@ -535,6 +535,24 @@ export function chatCompletionsUsage(u) {
     }
     return out;
 }
+/**
+ * The reasoning share of a Responses usage block: `output_tokens_details.
+ * reasoning_tokens`, which OpenAI counts inside `output_tokens` the way
+ * Anthropic counts thinking inside its output. Rounded and capped at the
+ * output it is part of, 0 when absent or malformed, so an analytics row never
+ * carries more reasoning than output.
+ */
+export function reasoningTokensFromResponses(u, output) {
+    if (!u || typeof u !== 'object')
+        return 0;
+    const d = u.output_tokens_details;
+    if (!d || typeof d !== 'object')
+        return 0;
+    const n = d.reasoning_tokens;
+    if (typeof n !== 'number' || !Number.isFinite(n) || n <= 0)
+        return 0;
+    return Math.min(Math.round(n), Math.max(0, Math.floor(output)));
+}
 /**
  * Terminal Responses usage -> analytics accounting. Delegates the netting to
  * anthropicUsageFromResponses so the analytics row and the Anthropic-shape
@@ -550,6 +568,7 @@ export function splitResponsesUsage(u) {
         output: a.output_tokens,
         cacheRead: a.cache_read_input_tokens ?? 0,
         cacheCreate: a.cache_creation_input_tokens ?? 0,
+        reasoning: reasoningTokensFromResponses(u, a.output_tokens),
     };
 }
 /**
@@ -947,7 +966,8 @@ timing) {
         reported = true;
         try {
             onDone({ status, latencyMs: Date.now() - startedAt, upstreamTtfbMs: ttfbMs(), upstreamMs: upstreamMsNow(), inputTokens: usage?.input ?? 0, outputTokens: usage?.output ?? 0,
-                cacheReadTokens: usage?.cacheRead ?? 0, cacheCreateTokens: usage?.cacheCreate ?? 0, stream: true, model, alias: creds.alias, cache });
+                cacheReadTokens: usage?.cacheRead ?? 0, cacheCreateTokens: usage?.cacheCreate ?? 0, reasoningTokens: usage?.reasoning ?? 0,
+                stream: true, model, alias: creds.alias, cache });
         }
         catch { /* never break a served request */ }
     };
@@ -1205,6 +1225,7 @@ timing) {
                 status, latencyMs: Date.now() - startedAt, upstreamTtfbMs: ttfbMs(), upstreamMs: upstreamMsNow(),
                 inputTokens: usage?.input ?? 0, outputTokens: usage?.output ?? 0,
                 cacheReadTokens: usage?.cacheRead ?? 0, cacheCreateTokens: usage?.cacheCreate ?? 0,
+                reasoningTokens: usage?.reasoning ?? 0,
                 stream, model, alias: creds.alias, cache,
             });
         }

package/dist/proxy.js

@@ -2610,7 +2610,10 @@ export async function startProxy(opts = {}) {
             inputTokens: o.inputTokens, outputTokens: o.outputTokens,
             // Anthropic convention, like every other row: inputTokens is
             // net of the cached prefix, which sits in cacheReadTokens.
-            cacheReadTokens: o.cacheReadTokens, cacheCreateTokens: o.cacheCreateTokens, thinkingTokens: 0,
+            cacheReadTokens: o.cacheReadTokens, cacheCreateTokens: o.cacheCreateTokens,
+            // The backend's reasoning tokens, counted inside outputTokens exactly as
+            // Claude's thinking is, so the ledger's thinking share covers both.
+            thinkingTokens: o.reasoningTokens,
             // No Anthropic rate-limit headers on this path; the claim
             // names the engine and is subscription billing, so the
             // overage guard (#288) leaves it alone.

package/docs/pool-keys-and-analytics.md

@@ -72,7 +72,7 @@ The rolling window forgets on every restart; the **ledger** does not. Since 6.6
     Thinking: 2.1M of 3.4M output tokens (62%) · $156 of the number above
 ```
 
-The `Thinking:` line is the share of output tokens that were the model's reasoning, read from the usage block upstream returns on Claude traffic, and what that reasoning would have cost at each model's output rate. It is the first number to look at when a bill surprises you: a reasoning model at its default effort can spend most of its output thinking on work that did not need it, and `output_config.effort` (or a `:low` model-name suffix, see [configuration](configuration.md#per-request-effort-by-model-name)) is a cheaper fix than a smaller model. `dario usage --by-key` shows the share per key, so the lane that is thinking the most is one line away.
+The `Thinking:` line is the share of output tokens that were the model's reasoning, read from the usage block upstream returns (Claude's `output_tokens_details.thinking_tokens`, and on the ChatGPT-subscription engine `output_tokens_details.reasoning_tokens`, both counted inside output), and what that reasoning would have cost at each model's output rate. It is the first number to look at when a bill surprises you: a reasoning model at its default effort can spend most of its output thinking on work that did not need it, and `output_config.effort` (or a `:low` model-name suffix, see [configuration](configuration.md#per-request-effort-by-model-name)) is a cheaper fix than a smaller model. `dario usage --by-key` shows the share per key, so the lane that is thinking the most is one line away.
 
 Only served requests count. Traffic that was metered anyway — an API key upstream, or Anthropic's paid `extra_usage` overage — is kept in its own column and reported as spent, not saved. `dario usage --card` writes the headline as a 640×320 SVG you can drop in a README or a post, and `--donut` writes the same number as three rings — by model, by key, subscription vs metered; `--no-ledger` / `DARIO_LEDGER=0` turns the file off, `DARIO_LEDGER_PATH` moves it, and `GET /analytics/ledger` is the per-day table behind the number. Details: [api-equivalent-spend.md](api-equivalent-spend.md).
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@askalf/dario",
-  "version": "6.20.0",
+  "version": "6.20.1",
   "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, opt-in failover when one hits its limit, and a ledger of what each plan absorbed.",
   "type": "module",
   "bin": {
@@ -91,7 +91,7 @@
     "node": ">=18.0.0"
   },
   "devDependencies": {
-    "@types/node": "^26.6.5",
+    "@types/node": "^26.6.6",
     "tsx": "^4.23.15",
     "typescript": "^5.7.0"
   }