@askalf/dario 6.18.0 → 6.18.1

package/dist/codex-backend.d.ts

@@ -282,7 +282,38 @@ export declare function createResponsesTranslator(model: string): {
 export declare const CODEX_SUPPORTED_FIELDS: readonly string[];
 /** Drop every field this backend does not accept. Pure; exported for tests. */
 export declare function toCodexSupportedBody(body: Record<string, unknown>): Record<string, unknown>;
-export declare function buildCodexHeaders(creds: CodexAccountCredentials): Record<string, string>;
+/** What a request adds to the seat's headers: its conversation and its model. */
+export interface CodexRequestHeaderInput {
+    /** The `prompt_cache_key` the body goes out with; empty when none. */
+    cacheKey?: string;
+    /** The model the body names; empty when none. */
+    model?: string;
+}
+/**
+ * A header value for a key the request supplies. Printable ASCII without
+ * spaces goes as it is (the Codex CLI's session ids are UUIDs); anything
+ * else is sent as a stable digest, so a key with a space, a quote or a
+ * non-ASCII character cannot break the request or smuggle a header.
+ */
+export declare function sessionHeaderValue(key: string): string;
+/**
+ * The headers of one request to the ChatGPT backend: the seat's identity and,
+ * when the request is known, its conversation and model.
+ *
+ * The backend's prompt cache lives on individual machines and a request is
+ * routed to one by its `session-id` header: the Codex CLI sends its session
+ * id there on every turn (codex-rs: "ChatGPT derives cache affinity from the
+ * Responses session-id header") with the same value as its `prompt_cache_key`
+ * and a `thread-id`, and `x-codex-routing-hint: model=<model>`. Without the
+ * header a conversation's turns scatter across machines and read a cached
+ * prefix only when one happens to land where an earlier turn wrote it: with
+ * turns a few seconds apart and every input a strict extension of the last,
+ * a review loop through dario read its prefix on 8 of 23 turns, and what it
+ * read was a snapshot several turns old. So the key goes out in the header
+ * too, and the raw `/v1/responses` path sends it for the Codex CLI, whose
+ * own headers dario does not forward.
+ */
+export declare function buildCodexHeaders(creds: CodexAccountCredentials, request?: CodexRequestHeaderInput): Record<string, string>;
 /**
  * Serve a Responses-shape request (`POST /v1/responses`) from a stored Codex
  * account with NO translation: the ChatGPT backend speaks this shape natively,

package/dist/codex-backend.js

@@ -796,7 +796,35 @@ export function toCodexSupportedBody(body) {
     }
     return out;
 }
-export function buildCodexHeaders(creds) {
+/**
+ * A header value for a key the request supplies. Printable ASCII without
+ * spaces goes as it is (the Codex CLI's session ids are UUIDs); anything
+ * else is sent as a stable digest, so a key with a space, a quote or a
+ * non-ASCII character cannot break the request or smuggle a header.
+ */
+export function sessionHeaderValue(key) {
+    if (/^[\x21-\x7e]{1,256}$/.test(key))
+        return key;
+    return createHash('sha256').update(key).digest('hex').slice(0, 32);
+}
+/**
+ * The headers of one request to the ChatGPT backend: the seat's identity and,
+ * when the request is known, its conversation and model.
+ *
+ * The backend's prompt cache lives on individual machines and a request is
+ * routed to one by its `session-id` header: the Codex CLI sends its session
+ * id there on every turn (codex-rs: "ChatGPT derives cache affinity from the
+ * Responses session-id header") with the same value as its `prompt_cache_key`
+ * and a `thread-id`, and `x-codex-routing-hint: model=<model>`. Without the
+ * header a conversation's turns scatter across machines and read a cached
+ * prefix only when one happens to land where an earlier turn wrote it: with
+ * turns a few seconds apart and every input a strict extension of the last,
+ * a review loop through dario read its prefix on 8 of 23 turns, and what it
+ * read was a snapshot several turns old. So the key goes out in the header
+ * too, and the raw `/v1/responses` path sends it for the Codex CLI, whose
+ * own headers dario does not forward.
+ */
+export function buildCodexHeaders(creds, request = {}) {
     const headers = {
         'Content-Type': 'application/json',
         'Accept': 'text/event-stream',
@@ -807,6 +835,13 @@ export function buildCodexHeaders(creds) {
     const accountId = extractChatGPTAccountId(creds.idToken);
     if (accountId)
         headers['ChatGPT-Account-ID'] = accountId;
+    if (request.cacheKey) {
+        const id = sessionHeaderValue(request.cacheKey);
+        headers['session-id'] = id;
+        headers['thread-id'] = id;
+    }
+    if (request.model && /^[\x21-\x7e]{1,128}$/.test(request.model))
+        headers['x-codex-routing-hint'] = `model=${request.model}`;
     return headers;
 }
 /**
@@ -958,13 +993,17 @@ timing) {
         if (verbose)
             console.log(`[dario] → codex backend (responses passthrough): ${target} (model: ${model})`);
         let activeCreds = creds;
-        let upstream = await timedFetch(target, { method: 'POST', headers: buildCodexHeaders(activeCreds), body: JSON.stringify(upstreamBody), signal: abort.signal });
+        // The client's own key as the session: the Codex CLI's headers do not
+        // pass through dario, so its cache affinity is rebuilt here from the key
+        // it sends in the body.
+        const requestHeaders = { cacheKey: typeof body.prompt_cache_key === 'string' ? body.prompt_cache_key : '', model };
+        let upstream = await timedFetch(target, { method: 'POST', headers: buildCodexHeaders(activeCreds, requestHeaders), body: JSON.stringify(upstreamBody), signal: abort.signal });
         if (isCodexAuthFailure(upstream.status)) {
             await upstream.text().catch(() => ''); // release the rejected response before retrying
             const fresh = await refreshAfterCodexAuthFailure(activeCreds, verbose);
             if (fresh) {
                 activeCreds = fresh;
-                upstream = await timedFetch(target, { method: 'POST', headers: buildCodexHeaders(activeCreds), body: JSON.stringify(upstreamBody), signal: abort.signal });
+                upstream = await timedFetch(target, { method: 'POST', headers: buildCodexHeaders(activeCreds, requestHeaders), body: JSON.stringify(upstreamBody), signal: abort.signal });
             }
         }
         if (!upstream.ok || !upstream.body) {
@@ -1263,9 +1302,12 @@ timing) {
         if (verbose)
             console.log(`[dario] → codex backend: ${target} (model: ${model})`);
         let activeCreds = creds;
+        // The key the body goes out with, derived or the client's own, is the
+        // session the backend routes the conversation by.
+        const requestHeaders = { cacheKey: String(scrubbed.prompt_cache_key ?? ''), model: String(scrubbed.model ?? model) };
         let upstream = await timedFetch(target, {
             method: 'POST',
-            headers: buildCodexHeaders(activeCreds),
+            headers: buildCodexHeaders(activeCreds, requestHeaders),
             body: JSON.stringify(scrubbed),
             signal: abort.signal,
         });
@@ -1278,7 +1320,7 @@ timing) {
                 activeCreds = fresh;
                 upstream = await timedFetch(target, {
                     method: 'POST',
-                    headers: buildCodexHeaders(activeCreds),
+                    headers: buildCodexHeaders(activeCreds, requestHeaders),
                     body: JSON.stringify(scrubbed),
                     signal: abort.signal,
                 });

package/dist/proxy.js

@@ -2470,6 +2470,60 @@ export async function startProxy(opts = {}) {
                 providerCooldowns.note('codex', d.retryAfterMs);
         }).catch(() => { });
     };
+    /**
+     * The /analytics row, request-log line and usage lines of one codex request.
+     *
+     * ONE function for BOTH routes that reach a seat: the codex route (a client
+     * asking for a GPT model) and the pool-exhausted fallback below. The fallback
+     * route passed no reporter until 6.18.1, so a request it served left no row
+     * anywhere: /analytics, the request log and the ledger all showed a drained
+     * Claude pool and nothing of the subscription that answered in its place.
+     * The seat's served count and its decline state move here with the row, so a
+     * route cannot have one without the others.
+     */
+    const reportCodexOutcome = (o, ctx) => {
+        codexRequestCounts.set(o.alias, (codexRequestCounts.get(o.alias) ?? 0) + 1);
+        // A seat that actually SERVED is not rate-limited. Keyed on a 2xx, never on
+        // forwardToCodex returning true: that means "I wrote a response", which is
+        // equally true when it wrote the upstream 429.
+        if (o.status >= 200 && o.status < 300)
+            clearCodexDecline(o.alias);
+        analytics.record({
+            timestamp: Date.now(),
+            consumer: ctx.consumer,
+            account: o.alias,
+            model: o.model || ctx.model || 'codex',
+            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,
+            // 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.
+            claim: CODEX_CLAIM, util5h: 0, util7d: 0, overageUtil: 0,
+            latencyMs: o.latencyMs, status: o.status, isStream: o.stream, isOpenAI: ctx.isOpenAI,
+            continuation: continuationOf(ctx.codexGuard, ctx.requestDepth),
+            timing: { queueMs: ctx.queueMs, pacingMs: 0, upstreamTtfbMs: o.upstreamTtfbMs, upstreamMs: o.upstreamMs, totalMs: Math.max(0, Date.now() - ctx.arrivedAt) },
+            cache: o.cache,
+        });
+        writeLogLine(logFileStream, {
+            ts: new Date().toISOString(), req: ctx.codexReq,
+            method: ctx.method, path: ctx.urlPath, model: o.model || ctx.model || undefined,
+            status: o.status, latency_ms: o.latencyMs, in_tokens: o.inputTokens, out_tokens: o.outputTokens,
+            cache_read: o.cacheReadTokens, cache_create: o.cacheCreateTokens,
+            claim: CODEX_CLAIM, bucket: 'subscription', account: o.alias, consumer: ctx.consumer, stream: o.stream,
+            ...(ctx.codexGuard?.outcome ? { continued: ctx.codexGuard.outcome, continued_by: ctx.codexGuard.continuedBy ?? undefined, continued_after: ctx.codexGuard.partialChars } : {}),
+            ...ctx.continuationLeg,
+            ...cacheLogFields(o.cache),
+        });
+        if (verbose)
+            console.log(formatUsageLogLine(ctx.codexReq, {
+                inputTokens: o.inputTokens, outputTokens: o.outputTokens,
+                cacheReadTokens: o.cacheReadTokens, cacheCreateTokens: o.cacheCreateTokens,
+            }, ctx.consumer));
+        if (cacheTraceLines && o.cache)
+            console.log(formatCacheTraceLine(ctx.codexReq, o.cache.key, o.cache, o, o.alias));
+    };
     /**
      * Serve a pool-exhausted request from the ChatGPT subscription (v6.0.0).
      *
@@ -2488,7 +2542,13 @@ export async function startProxy(opts = {}) {
      */
     const tryCodexPoolFallback = async (req, res, body, fallbackModels, shape, why, attempted, 
     /** The request's queue wait and arrival, so the codex response carries the timing headers too. */
-    timing) => {
+    timing, 
+    /**
+     * Files the request the seat answered (reportCodexOutcome), under the
+     * request number its console line carried. Required: a route that reaches
+     * a seat without it serves GPT that nothing counts.
+     */
+    onDone) => {
         if (fallbackModels.length === 0)
             return false;
         // Never a second codex attempt in the same request, and never one while it
@@ -2571,13 +2631,18 @@ export async function startProxy(opts = {}) {
             const fallbackBody = buildPoolFallbackBody(body, fallbackModel);
             if (!fallbackBody)
                 return false;
-            console.log(`[dario] #${requestCount} ${why} → codex account ${seat.alias} as ${fallbackModel}`);
+            const reqNo = requestCount;
+            console.log(`[dario] #${reqNo} ${why} → codex account ${seat.alias} as ${fallbackModel}`);
             requestCount++;
             // Marked only once an attempt is actually being made. Marking it before
             // the guards above would tell the rest of the request that codex had been
             // tried when it had not, suppressing a later legitimate attempt.
             attempted.add('codex');
-            served = await forwardToCodex(req, res, fallbackBody, seat, corsOrigin, { ...SECURITY_HEADERS, 'x-dario-pool-fallback': fallbackModel }, upstreamTimeoutMs, verbose, shape, fetch, hasNextOption || peer !== null, undefined, codexOnDecline, 
+            served = await forwardToCodex(req, res, fallbackBody, seat, corsOrigin, { ...SECURITY_HEADERS, 'x-dario-pool-fallback': fallbackModel }, upstreamTimeoutMs, verbose, shape, fetch, hasNextOption || peer !== null, 
+            // The row files under the model the seat served as; the substituted
+            // one when the seat named none. The client's own model is the Claude
+            // one, which this request never reached.
+            (o) => onDone({ ...o, model: o.model || fallbackModel }, reqNo), codexOnDecline, 
             // The mirror of the Claude side (dario#1161): an operator who writes
             // `--pool-fallback=gpt-5.6-terra:high` is choosing the effort the
             // failover runs at, so the entry's own suffix reaches the request rather
@@ -2619,6 +2684,8 @@ export async function startProxy(opts = {}) {
      * this by construction, not by remembering to copy six lines correctly.
      */
     const attemptPoolFallbackOn429 = async (req, res, body, isOpenAI, attempted, timing, 
+    /** Files a request the subscription served; see tryCodexPoolFallback. */
+    onDone, 
     /**
      * Re-arm THIS request on the credits rung (credits-rung.ts): returns true
      * once the request is re-pointed at the key, and the caller re-enters its
@@ -2626,7 +2693,7 @@ export async function startProxy(opts = {}) {
      */
     armCredits) => {
         const chain = selectPoolFallbackForBody(body);
-        if (await tryCodexPoolFallback(req, res, body, chain, isOpenAI ? 'openai' : 'anthropic', 'pool exhausted mid-flight (429, no peer)', attempted, timing)) {
+        if (await tryCodexPoolFallback(req, res, body, chain, isOpenAI ? 'openai' : 'anthropic', 'pool exhausted mid-flight (429, no peer)', attempted, timing, onDone)) {
             return 'served';
         }
         // The metered rungs, in the chain's own order. The credits rung is never
@@ -3708,6 +3775,14 @@ export async function startProxy(opts = {}) {
             const continuationLeg = requestDepth > 0
                 ? { continuation_depth: requestDepth, continuation_of: continuationOfRequest(req.headers[CONTINUATION_OF_HEADER]) }
                 : {};
+            // The row of a request the pool-exhausted fallback handed to the
+            // subscription, under the number the fallback's console line carried.
+            // No model of its own to file under (the client asked for a Claude one)
+            // and no midstream guard: that route does not resume a dead stream.
+            const reportFallbackCodex = (o, reqNo) => reportCodexOutcome(o, {
+                consumer, codexReq: reqNo, method: req.method ?? '', urlPath, model: '', isOpenAI,
+                queueMs, arrivedAt, requestDepth, codexGuard: null, continuationLeg,
+            });
             /**
              * First hop: the SAME model again, through the front door. The pool
              * picks a seat (sticky binding keeps the prompt cache warm), and if the
@@ -4380,55 +4455,18 @@ export async function startProxy(opts = {}) {
                         // Reporting is one function for BOTH codex shapes below: the Responses
                         // passthrough and the translated Messages path record the same row, so a
                         // GPT request looks the same in /analytics whichever shape asked for it.
+                        // The row itself is reportCodexOutcome, shared with the pool-exhausted
+                        // fallback route.
                         //
                         // Before this hook a codex request left no trace: nothing in /analytics,
                         // nothing in the request log, no per-account count. The dock (and anyone
                         // reading /analytics) saw a proxy that served GPT all day and reported
                         // zero of it. A decline (the request handed to the Claude pool) reports
                         // nothing here; the Claude path records what it then serves.
-                        const codexOnDone = (o) => {
-                            codexRequestCounts.set(o.alias, (codexRequestCounts.get(o.alias) ?? 0) + 1);
-                            // A seat that actually SERVED is not rate-limited. Keyed on a 2xx,
-                            // never on forwardToCodex returning true — that means "I wrote a
-                            // response", which is equally true when it wrote the upstream 429.
-                            if (o.status >= 200 && o.status < 300)
-                                clearCodexDecline(o.alias);
-                            analytics.record({
-                                timestamp: Date.now(),
-                                consumer,
-                                account: o.alias,
-                                model: o.model || rawModel || 'codex',
-                                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,
-                                // 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.
-                                claim: CODEX_CLAIM, util5h: 0, util7d: 0, overageUtil: 0,
-                                latencyMs: o.latencyMs, status: o.status, isStream: o.stream, isOpenAI,
-                                continuation: continuationOf(codexGuard, requestDepth),
-                                timing: { queueMs, pacingMs: 0, upstreamTtfbMs: o.upstreamTtfbMs, upstreamMs: o.upstreamMs, totalMs: Math.max(0, Date.now() - arrivedAt) },
-                                cache: o.cache,
-                            });
-                            writeLogLine(logFileStream, {
-                                ts: new Date().toISOString(), req: codexReq,
-                                method: req.method ?? '', path: urlPath, model: o.model || rawModel || undefined,
-                                status: o.status, latency_ms: o.latencyMs, in_tokens: o.inputTokens, out_tokens: o.outputTokens,
-                                cache_read: o.cacheReadTokens, cache_create: o.cacheCreateTokens,
-                                claim: CODEX_CLAIM, bucket: 'subscription', account: o.alias, consumer, stream: o.stream,
-                                ...(codexGuard?.outcome ? { continued: codexGuard.outcome, continued_by: codexGuard.continuedBy ?? undefined, continued_after: codexGuard.partialChars } : {}),
-                                ...continuationLeg,
-                                ...cacheLogFields(o.cache),
-                            });
-                            if (verbose)
-                                console.log(formatUsageLogLine(codexReq, {
-                                    inputTokens: o.inputTokens, outputTokens: o.outputTokens,
-                                    cacheReadTokens: o.cacheReadTokens, cacheCreateTokens: o.cacheCreateTokens,
-                                }, consumer));
-                            if (cacheTraceLines && o.cache)
-                                console.log(formatCacheTraceLine(codexReq, o.cache.key, o.cache, o, o.alias));
-                        };
+                        const codexOnDone = (o) => reportCodexOutcome(o, {
+                            consumer, codexReq, method: req.method ?? '', urlPath, model: rawModel, isOpenAI,
+                            queueMs, arrivedAt, requestDepth, codexGuard, continuationLeg,
+                        });
                         // Mid-flight seat failover. A 429 lands BEFORE any body is written —
                         // forwardToCodex only returns false on the decline path — so the same
                         // request can be handed to a healthy peer instead of failing. Without
@@ -4675,7 +4713,7 @@ export async function startProxy(opts = {}) {
             if (!upstreamApiKey && !poolAccount) {
                 attemptedProviders.add('claude');
             }
-            if (!upstreamApiKey && !poolAccount && !pinnedAccount && await tryCodexPoolFallback(req, res, body, selectPoolFallbackForBody(body), isOpenAI ? 'openai' : 'anthropic', 'pool exhausted', attemptedProviders, { queueMs, arrivedAt })) {
+            if (!upstreamApiKey && !poolAccount && !pinnedAccount && await tryCodexPoolFallback(req, res, body, selectPoolFallbackForBody(body), isOpenAI ? 'openai' : 'anthropic', 'pool exhausted', attemptedProviders, { queueMs, arrivedAt }, reportFallbackCodex)) {
                 return;
             }
             // `isOpenAI` is REQUIRED here and was not, before v6.0.0 — the selector's
@@ -5754,7 +5792,7 @@ export async function startProxy(opts = {}) {
                         if (!creditsRung)
                             providerCooldowns.note('claude', parseRetryAfterMs(upstream.headers.get('retry-after')));
                         if (!pinnedAccount) {
-                            const outcome = await attemptPoolFallbackOn429(req, res, body, isOpenAI, attemptedProviders, { queueMs, arrivedAt }, rearmOnCredits);
+                            const outcome = await attemptPoolFallbackOn429(req, res, body, isOpenAI, attemptedProviders, { queueMs, arrivedAt }, reportFallbackCodex, rearmOnCredits);
                             if (outcome === 'served')
                                 return;
                             if (outcome === 'credits') {
@@ -5889,7 +5927,7 @@ export async function startProxy(opts = {}) {
                     if (!creditsRung)
                         providerCooldowns.note('claude', parseRetryAfterMs(upstream.headers.get('retry-after')));
                     if (!pinnedAccount) {
-                        const outcome = await attemptPoolFallbackOn429(req, res, body, isOpenAI, attemptedProviders, { queueMs, arrivedAt }, rearmOnCredits);
+                        const outcome = await attemptPoolFallbackOn429(req, res, body, isOpenAI, attemptedProviders, { queueMs, arrivedAt }, reportFallbackCodex, rearmOnCredits);
                         if (outcome === 'served')
                             return;
                         if (outcome === 'credits') {

package/docs/two-plans.md

@@ -28,7 +28,7 @@ curl localhost:3456/v1/messages -H 'content-type: application/json' \
 
 Streaming, tool calls and tool-result round trips work on both shapes, and chat-shape `image_url` parts are carried as Responses `input_image` parts with `detail` preserved: dario translates chat/completions **or** Messages into the Responses API the subscription backend speaks, and translates the stream back into `chat.completion.chunk` or Anthropic message events. A `/v1/responses` request needs no translation: the backend speaks that shape, so the body goes through as the client wrote it (model resolved) and the stream comes back untouched, on the same seats and failover as the other shapes (see [Codex CLI](./integrations/codex-cli.md)). The Codex backend does not accept every chat field, so `response_format`, `stop`, `n`, `logprobs`, `stream_options` and the sampling parameters `temperature`, `top_p`, `max_tokens`, `max_completion_tokens` are intentionally lossy; with `--verbose`, dario reports each field that does not reach Codex once per process. Codex accounts live in `~/.dario/codex-accounts/`, separate from the Claude pool.
 
-**Prompt caching:** the backend caches prompt prefixes of 1,024 tokens and up on its own; what dario adds is the `prompt_cache_key` that routes same-prefix requests to the cache that holds them, the way the Codex CLI does with its session id. A chat/completions client that sets its own key keeps it; an Anthropic-shape request gets one per Claude Code session (a hash of `metadata.user_id`, never the raw ids); anything else is keyed on its model, instructions and tool names, so repeated system prompts from any caller land together. Cached tokens come back as `prompt_tokens_details.cached_tokens` on chat/completions and as `cache_read_input_tokens` on `/v1/messages`, and show up in `/analytics` and the `-v` usage line like a Claude request's do. When the share is lower than the conversation shape would predict, the [cache trace](./analytics.md#the-cache-trace) shows what may explain it: turns close enough together that the write may not yet have been readable, a rewritten history, a changed system prompt or tool names, or a changed seat.
+**Prompt caching:** the backend caches prompt prefixes of 1,024 tokens and up on its own; what dario adds is the `prompt_cache_key` that routes same-prefix requests to the cache that holds them, the way the Codex CLI does with its session id. A chat/completions client that sets its own key keeps it; an Anthropic-shape request gets one per Claude Code session (a hash of `metadata.user_id`, never the raw ids); anything else is keyed on its model, instructions and tool names, so repeated system prompts from any caller land together. The key also goes out as the `session-id` header (with `thread-id` and `x-codex-routing-hint: model=<model>`, as the Codex CLI sends them): the backend's cache lives on individual machines and that header is what routes a conversation's next turn to the machine holding its prefix; the body key alone does not. Cached tokens come back as `prompt_tokens_details.cached_tokens` on chat/completions and as `cache_read_input_tokens` on `/v1/messages`, and show up in `/analytics` and the `-v` usage line like a Claude request's do. When the share is lower than the conversation shape would predict, the [cache trace](./analytics.md#the-cache-trace) shows what may explain it: turns close enough together that the write may not yet have been readable, a rewritten history, a changed system prompt or tool names, or a changed seat.
 
 ## Failover between subscriptions
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@askalf/dario",
-  "version": "6.18.0",
+  "version": "6.18.1",
   "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": {