@leanandmean/coding-agent 0.74.1-scramjet.43 → 0.74.1-scramjet.45

package/docs/rpc.md

@@ -263,7 +263,7 @@ List all configured models.
 {"type": "get_available_models"}
 ```
 
-Response contains an array of full [Model](#model) objects. `RpcClient.getAvailableModels()` projects these to `ModelInfo`, including optional `contextWindowBudget` when present; there is no separate runtime mapping:
+Response contains an array of full [Model](#model) objects. `RpcClient.getAvailableModels()` types these as `ModelInfo`, including optional `maxInputTokens`; there is no runtime projection:
 ```json
 {
   "type": "response",
@@ -527,14 +527,13 @@ Response:
     "contextUsage": {
       "tokens": 60000,
       "contextWindow": 200000,
-      "contextWindowBudget": 200000,
       "percent": 30
     }
   }
 }
 ```
 
-`tokens` contains assistant usage totals for the current session state. `contextUsage.contextWindow` is advertised model capacity, `contextWindowBudget` is the resolved operational budget, and `percent` uses that budget as its denominator. Compaction also uses the operational budget.
+`tokens` contains assistant usage totals for the current session state. `contextUsage.contextWindow` is maximum supported total context and the denominator of `percent`. Compaction uses this same context value with the configured reserve. `contextWindowBudget` has been removed from both model and usage transport contracts; clients must read `contextWindow` instead. See [models.md](models.md#breaking-migration-from-context-budgets).
 
 `contextUsage` is omitted when no model or context window is available. `contextUsage.tokens` and `contextUsage.percent` are `null` immediately after compaction until a fresh post-compaction assistant response provides valid usage data.
 
@@ -1218,7 +1217,6 @@ Source files:
   "reasoning": true,
   "input": ["text", "image"],
   "contextWindow": 200000,
-  "contextWindowBudget": 180000,
   "maxTokens": 16384,
   "cost": {
     "input": 3.0,
@@ -1229,7 +1227,7 @@ Source files:
 }
 ```
 
-`contextWindowBudget` is optional on transported models. When absent, consumers use `contextWindow` as the operational budget.
+`contextWindow` is maximum supported total context. An optional `maxInputTokens` represents only an independently evidenced provider input constraint; it is not another context denominator. The removed budget field is not emitted.
 
 ### UserMessage
 

package/docs/sdk.md

@@ -435,6 +435,14 @@ For each built-in provider request, `createAgentSession()` binds the current ext
 
 > See [examples/sdk/02-custom-model.ts](../examples/sdk/02-custom-model.ts)
 
+### Context and output allocation
+
+Models and usage expose one authoritative total `contextWindow`; `contextWindowBudget` and `getContextWindowBudget()` are removed. See [the migration guide](models.md#breaking-migration-from-context-budgets) before updating external model definitions or consumers.
+
+The `createAgentSession()` stream path checks the current request's estimated input against any genuine `maxInputTokens`, then bounds output by remaining total context and the applicable output maximum. It does not subtract compaction reserve again. The same accounting applies to both built-in summarizer implementations. These are approximate checks, not exact serialized-payload tokenization; custom stream functions and later payload rewrites must honor their own constraints.
+
+OpenRouter's implicit aggregate output maximum is omitted because it can exclude the long-context endpoint; explicit summary output limits are retained. Vercel's Anthropic route still requires an output limit. Codex still omits `max_output_tokens`. Aggregate route compatibility is not guaranteed by scalar metadata. Anthropic/Bedrock simple adapters treat explicit `maxTokens` as a combined output ceiling including thinking, rather than increasing it for reasoning.
+
 ### API Keys and OAuth
 
 API key resolution priority (handled by AuthStorage):

package/examples/extensions/border-status-editor.ts

@@ -52,12 +52,7 @@ function formatContext(ctx: ExtensionContext): string {
 	if (!usage || usage.percent === null) {
 		return "ctx ?";
 	}
-	// SCRAMJET-DIVERGENCE: Show the expanded capacity/budget ContextUsage contract (issue 398).
-	const capacity =
-		usage.contextWindowBudget === usage.contextWindow
-			? ""
-			: ` (${(usage.contextWindow / 1000).toFixed(0)}k capacity)`;
-	return `ctx ${Math.round(usage.percent)}%/${(usage.contextWindowBudget / 1000).toFixed(0)}k${capacity}`;
+	return `ctx ${Math.round(usage.percent)}%/${(usage.contextWindow / 1000).toFixed(0)}k`;
 }
 
 function formatThinking(level: string): string {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@leanandmean/coding-agent",
-  "version": "0.74.1-scramjet.43",
+  "version": "0.74.1-scramjet.45",
   "publishConfig": {
     "access": "public"
   },
@@ -37,9 +37,9 @@
     "test": "vitest --run --passWithNoTests"
   },
   "dependencies": {
-    "@leanandmean/agent": "0.74.1-scramjet.22",
-    "@leanandmean/ai": "0.74.1-scramjet.18",
-    "@leanandmean/tui": "0.74.1-scramjet.15",
+    "@leanandmean/agent": "0.74.1-scramjet.24",
+    "@leanandmean/ai": "0.74.1-scramjet.20",
+    "@leanandmean/tui": "0.74.1-scramjet.17",
     "@silvia-odwyer/photon-node": "^0.3.4",
     "chalk": "^5.5.0",
     "dictionary-en": "^4.0.0",