@bman654/clodex 2.11.0 → 2.11.1

package/README.md

@@ -245,8 +245,9 @@ A context window is a cost dial as much as a capacity number. OpenAI prices GPT-
 and later prompts above **272,000 input tokens at 2x input and 1.5x output for the
 full request**, which is why the Codex catalog reports a 272,000 window rather than
 the model's ceiling. Newer families inherit the same boundary, so a model released
-after this was written is covered without a clodex update. Clodex follows that: the default `standard` stop stays under the
-line, and a larger window is something you ask for.
+after this was written is covered without a clodex update. Clodex follows that: the
+default `standard` stop stays under the line, and a larger window is something you
+ask for.
 
 ```sh
 clodex models --context sol=max --save     # this model's default, with a cost warning
@@ -254,19 +255,21 @@ clodex claude --context sol=max            # this launch only, nothing saved
 clodex models --context sol=default --save # back to the provider's tuned window
 ```
 
-Each stop is reported with the numbers behind it: the raw window, the headroom
-percentage the Codex catalog uses, the effective window a client should fill, and the
-account ceiling a larger stop can reach. A stop above the ceiling is clamped and says
-so. When a request's own reported token count crosses the boundary, clodex warns once
-per model for the life of the process, because the client's token count and the
-provider's differ after translation and only the provider's settles it.
+Each stop is reported with the numbers behind it: the raw window, the effective
+window a client should fill, and the account ceiling a larger stop can reach. A stop
+above the ceiling is clamped and says so. When a request's own reported token count
+crosses the boundary, clodex warns once per model for the life of the process,
+because the client's token count and the provider's differ after translation and only
+the provider's settles it.
 
 Two things worth knowing about the numbers:
 
-- **ChatGPT/Codex OAuth models carry a 95% headroom convention**, matching the Codex
-  client. Their reported window is 5% below the raw catalog value: `gpt-5.6-sol`
-  reports 258,400 rather than 272,000. This applies to that provider only; API-key
-  and OpenCode Go models keep their full window.
+- **Clodex reports the window the provider actually gives, and holds nothing back.**
+  Deciding how much of a window to leave free is the client's job — Claude Code
+  already reserves a fixed amount below whatever window it is told, and shrinking the
+  number first only costs usable context. A provider that declares a share of its own
+  is still honoured; clodex just never invents one. Use `--context` if you want a
+  smaller window than the provider offers.
 - **The account ceiling moves.** It is server-side and per-account, and it has
   changed by more than 2x within a single day in the past. `max` reads whatever the
   catalog reports now and clamps to it, so a stale ceiling shrinks the stop rather

package/dist/cli.js

@@ -382,7 +382,7 @@ import { join } from "path";
 // package.json
 var package_default = {
   name: "@bman654/clodex",
-  version: "2.11.0",
+  version: "2.11.1",
   publishConfig: {
     access: "public"
   },
@@ -3121,7 +3121,6 @@ async function deleteProviderCredential(authRef, diag) {
 }
 
 // src/context-modes.ts
-var DEFAULT_EFFECTIVE_CONTEXT_PERCENT = 95;
 function positiveInteger(value) {
   return typeof value === "number" && Number.isSafeInteger(value) && value > 0 ? value : void 0;
 }
@@ -5919,6 +5918,10 @@ function openAiPricingMetadata(id) {
     pricingBoundaryNote: GPT_5_6_PRICING_NOTE
   };
 }
+var LEGACY_IMPOSED_CONTEXT_PERCENT = 95;
+function migratedEffectiveContextPercent(cached) {
+  return cached === LEGACY_IMPOSED_CONTEXT_PERCENT ? void 0 : cached;
+}
 function applyOAuthSeedContextMetadata(models) {
   const seedById = new Map(buildOpenAiOAuthModels().map((model) => [model.id, model]));
   return models.map((model) => {
@@ -5927,7 +5930,7 @@ function applyOAuthSeedContextMetadata(models) {
     return {
       ...model,
       maxContextWindow: model.maxContextWindow ?? seed?.maxContextWindow,
-      effectiveContextPercent: model.effectiveContextPercent ?? seed?.effectiveContextPercent ?? DEFAULT_EFFECTIVE_CONTEXT_PERCENT,
+      effectiveContextPercent: migratedEffectiveContextPercent(model.effectiveContextPercent),
       pricingBoundary: model.pricingBoundary ?? seed?.pricingBoundary ?? pricing.pricingBoundary,
       pricingBoundaryNote: model.pricingBoundaryNote ?? seed?.pricingBoundaryNote ?? pricing.pricingBoundaryNote,
       maxOutputTokens: model.maxOutputTokens ?? seed?.maxOutputTokens,
@@ -5947,7 +5950,7 @@ function buildOpenAiOAuthModels() {
       brand: deriveBrand(prefix),
       contextWindow: resolveContextWindow(seed.id, seed.contextWindow),
       maxContextWindow: seed.maxContextWindow,
-      effectiveContextPercent: seed.effectiveContextPercent ?? DEFAULT_EFFECTIVE_CONTEXT_PERCENT,
+      effectiveContextPercent: seed.effectiveContextPercent,
       pricingBoundary: seed.pricingBoundary ?? pricing.pricingBoundary,
       pricingBoundaryNote: seed.pricingBoundaryNote ?? pricing.pricingBoundaryNote,
       maxOutputTokens: seed.maxOutputTokens,
@@ -15090,7 +15093,10 @@ function buildDynamicOAuthModel(entry, seedById, codexCatalog) {
     brand: deriveBrand(prefix),
     contextWindow: entry.context_window ?? resolveContextWindow(id),
     maxContextWindow: entry.max_context_window,
-    effectiveContextPercent: entry.effective_context_window_percent ?? DEFAULT_EFFECTIVE_CONTEXT_PERCENT,
+    // Absent means no reduction. clodex reports the window the provider actually
+    // gives; deciding how much of it to leave free is the client's job, and Claude
+    // Code already reserves a flat 33,000 tokens below whatever it is told.
+    effectiveContextPercent: entry.effective_context_window_percent,
     maxOutputTokens: entry.max_output_tokens,
     ...openAiPricingMetadata(id),
     modelFormat: "openai",