@@ -13,7 +13,7 @@ import { CODEX_REASONING_LEVELS, codexEffortRank, configuredReasoningEfforts, mo
1313import { getModelMetadata , getModelMetadataCaseInsensitive , listModelMetadata , resolveMetadataProvider } from "../../generated/model-metadata" ;
1414import { enrichProviderFromRegistry , shouldCaseFoldMetadataModelId } from "../../providers/derive" ;
1515import { getProviderRegistryEntry } from "../../providers/registry" ;
16- import { applyProviderContextCap , providerContextCap } from "../../providers/context-cap" ;
16+ import { applyProviderContextCap , clampAutoCompactTokenLimit , providerContextCap } from "../../providers/context-cap" ;
1717import { routedSlug , slugEquals , slugsEquivalent } from "../../providers/slug-codec" ;
1818import { identifyRoutedModel } from "../../adapters/identity" ;
1919import { filterCursorConfiguredModelsByLiveDiscovery } from "../../adapters/cursor/discovery" ;
@@ -144,10 +144,22 @@ const NATIVE_GPT56_FAMILY = new Set<string>([
144144 NATIVE_DAYBREAK_BLUE_MODEL ,
145145] ) ;
146146
147- export const NATIVE_OPENAI_CONTEXT_OVERRIDES : Record < string , { contextWindow ?: number ; maxContextWindow ?: number ; maxInputTokens ?: number } > = {
147+ export interface NativeOpenAiContextOverride {
148+ contextWindow ?: number ;
149+ maxContextWindow ?: number ;
150+ /** Measured hard input ceiling. This is admission authority, not compaction policy. */
151+ maxInputTokens ?: number ;
152+ /** Model-specific soft budget exposed to Codex as auto_compact_token_limit. */
153+ autoCompactTokenLimit ?: number ;
154+ }
155+
156+ export const NATIVE_OPENAI_CONTEXT_OVERRIDES : Record < string , NativeOpenAiContextOverride > = {
148157 "gpt-5.5" : { contextWindow : 272_000 , maxContextWindow : 272_000 } ,
149158 "gpt-5.4" : { contextWindow : 1_000_000 , maxContextWindow : 1_000_000 } ,
150159 "gpt-5.3-codex-spark" : { contextWindow : 100_000 , maxContextWindow : 100_000 } ,
160+ // The shared clamp derives 90% of the effective 272k default (or 922k opt-in) for every
161+ // GPT-5.6 member. Per-model soft budgets may lower that value; no ineffective Sol-only
162+ // upper bound is stored here.
151163 "gpt-5.6-sol" : { contextWindow : NATIVE_GPT56_CONTEXT_WINDOW , maxContextWindow : NATIVE_GPT56_MAX_INPUT_TOKENS , maxInputTokens : NATIVE_GPT56_MAX_INPUT_TOKENS } ,
152164 "gpt-5.6-terra" : { contextWindow : NATIVE_GPT56_CONTEXT_WINDOW , maxContextWindow : NATIVE_GPT56_MAX_INPUT_TOKENS , maxInputTokens : NATIVE_GPT56_MAX_INPUT_TOKENS } ,
153165 "gpt-5.6-luna" : { contextWindow : NATIVE_GPT56_CONTEXT_WINDOW , maxContextWindow : NATIVE_GPT56_MAX_INPUT_TOKENS , maxInputTokens : NATIVE_GPT56_MAX_INPUT_TOKENS } ,
@@ -274,6 +286,30 @@ export function nativeOpenAiMaxInputTokens(slug: string, limits?: NativeContextL
274286 return window === undefined ? narrowed : Math . min ( narrowed , window ) ;
275287}
276288
289+ /** Effective native soft budget. User configuration may lower, but never raise, the model default. */
290+ export function nativeOpenAiAutoCompactTokenLimit (
291+ slug : string ,
292+ limits ?: NativeContextLimitsInput ,
293+ configuredLimit ?: number ,
294+ ) : number | undefined {
295+ const contextWindow = nativeOpenAiContextWindow ( slug , limits ) ;
296+ if ( contextWindow === undefined ) return undefined ;
297+ const nativeDefault = NATIVE_OPENAI_CONTEXT_OVERRIDES [ slug ] ?. autoCompactTokenLimit ;
298+ const positiveConfigured = typeof configuredLimit === "number" && configuredLimit > 0
299+ ? configuredLimit
300+ : undefined ;
301+ const softLimit = nativeDefault === undefined
302+ ? positiveConfigured
303+ : positiveConfigured === undefined
304+ ? nativeDefault
305+ : Math . min ( nativeDefault , positiveConfigured ) ;
306+ return clampAutoCompactTokenLimit (
307+ contextWindow ,
308+ nativeOpenAiMaxInputTokens ( slug , limits ) ,
309+ softLimit ,
310+ ) ;
311+ }
312+
277313export function nativeInputModalities ( slug : string ) : string [ ] {
278314 const upstream = PINNED_NATIVE_CAPABILITY_ENTRIES . get ( slug ) ;
279315 if ( Array . isArray ( upstream ?. input_modalities ) && upstream ! . input_modalities ! . length > 0 ) {
@@ -384,7 +420,9 @@ export function desktopVisibleNativeSlugs(
384420 ] ) ;
385421}
386422
387- export function nativeModelRows ( config : Pick < OcxConfig , "disabledModels" | "combos" | "providerContextCaps" | "providers" > ) : Array < { slug : string ; disabled : boolean ; contextWindow ?: number ; maxInputTokens ?: number } > {
423+ export function nativeModelRows (
424+ config : Pick < OcxConfig , "disabledModels" | "combos" | "providerContextCaps" | "providers" > ,
425+ ) : Array < { slug : string ; disabled : boolean ; contextWindow ?: number ; maxInputTokens ?: number ; autoCompactTokenLimit ?: number } > {
388426 const disabled = disabledNativeSlugs ( config ) ;
389427 const shadowed = configuredNativeAliasSlugs ( config ) ;
390428 // Both user levers, not just the cap: a per-model window set from the dashboard has to show
@@ -393,11 +431,17 @@ export function nativeModelRows(config: Pick<OcxConfig, "disabledModels" | "comb
393431 return NATIVE_OPENAI_MODELS . filter ( slug => ! shadowed . has ( slug ) ) . map ( slug => {
394432 const contextWindow = nativeOpenAiContextWindow ( slug , limits ) ;
395433 const maxInputTokens = nativeOpenAiMaxInputTokens ( slug , limits ) ;
434+ const autoCompactTokenLimit = nativeOpenAiAutoCompactTokenLimit (
435+ slug ,
436+ limits ,
437+ config . providers ?. [ OPENAI_CODEX_PROVIDER_ID ] ?. modelAutoCompactTokenLimits ?. [ slug ] ,
438+ ) ;
396439 return {
397440 slug,
398441 disabled : disabled . has ( slug ) ,
399442 ...( contextWindow !== undefined ? { contextWindow } : { } ) ,
400443 ...( maxInputTokens !== undefined ? { maxInputTokens } : { } ) ,
444+ ...( autoCompactTokenLimit !== undefined ? { autoCompactTokenLimit } : { } ) ,
401445 } ;
402446 } ) ;
403447}
0 commit comments