@mono-agent/agent-runtime 0.12.0 → 0.13.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mono-agent/agent-runtime",
-  "version": "0.12.0",
+  "version": "0.13.0",
   "description": "Agent runtime supporting Claude SDK/CLI, Codex, OpenCode, and Pi SDK bridges out of the box",
   "type": "module",
   "license": "GPL-3.0-only",

package/src/agent/tools/pi-bridge.js

@@ -334,7 +334,7 @@ function readSkillTool(skillNames = [], { skillsRoot, dataDir, skills = [] } = {
   return {
     name: "ReadSkill",
     label: "Read Skill",
-    description: "Load the full instructions for a named skill.",
+    description: "Load the complete instructions for a named skill. Use ReadSkill instead of Read for SKILL.md files.",
     parameters: objectSchema({ name: { type: "string", enum: enumNames } }, ["name"]),
     async execute(_toolCallId, { name }) {
       if (sharedRoot) {

package/src/ai/providers/pi-native/result-builder.js

@@ -7,6 +7,7 @@
 // takes its inputs explicitly and returns the verbatim runtime-result contract
 // (diagnostics key spellings, error fields, and shape unchanged — I9).
 
+import { calculateContextTokens } from "@earendil-works/pi-agent-core";
 import { isContextLimitError } from "../pi-errors.js";
 import { isLikelyContextTermination } from "../../../agent/compaction.js";
 import { isProviderAuthFailureText } from "../../failure.js";
@@ -31,6 +32,28 @@ export function usageFromMessages(messages = []) {
   return usage;
 }
 
+/**
+ * Normalize the final provider request's usage into an exact context snapshot.
+ * Unlike usageFromMessages(), this deliberately does not aggregate earlier
+ * requests in the run: the last assistant usage is the same provider-counted
+ * value Pi's compaction logic trusts, so it can decrease after compaction.
+ * @param {any} assistantMessage
+ * @returns {{input: number, output: number, cacheRead: number, cacheCreation: number, total: number}|null}
+ */
+export function contextUsageFromAssistantMessage(assistantMessage) {
+  if (assistantMessage?.role !== "assistant" || !assistantMessage.usage) return null;
+  if (assistantMessage.stopReason === "error" || assistantMessage.stopReason === "aborted") return null;
+  const total = Number(calculateContextTokens(assistantMessage.usage)) || 0;
+  if (total <= 0) return null;
+  return {
+    input: Number(assistantMessage.usage.input) || 0,
+    output: Number(assistantMessage.usage.output) || 0,
+    cacheRead: Number(assistantMessage.usage.cacheRead) || 0,
+    cacheCreation: Number(assistantMessage.usage.cacheWrite) || 0,
+    total,
+  };
+}
+
 /**
  * Classify a pi error message into a runtime failure kind. Context-window
  * overflows map to context_limit so the router can try the configured fallback;
@@ -51,9 +74,19 @@ export function failureKindForPiError(message, diagnostics, { maxTurnsHit = fals
 
 /**
  * Emit the per-run cache / cost / provider-completed events.
- * @param {{onEvent: (event: any) => void, resolved: any, reference: string, usage: {input: number, output: number, cacheRead: number, cacheWrite: number, cost: number}, estimatedCost: number, start: number, externalAbort: boolean}} params
+ * @param {{onEvent: (event: any) => void, resolved: any, reference: string, usage: {input: number, output: number, cacheRead: number, cacheWrite: number, cost: number}, contextUsage?: {input: number, output: number, cacheRead: number, cacheCreation: number, total: number}|null, contextWindow?: number, estimatedCost: number, start: number, externalAbort: boolean}} params
  */
-export function emitUsageCostEvents({ onEvent, resolved, reference, usage, estimatedCost, start, externalAbort }) {
+export function emitUsageCostEvents({
+  onEvent,
+  resolved,
+  reference,
+  usage,
+  contextUsage,
+  contextWindow,
+  estimatedCost,
+  start,
+  externalAbort,
+}) {
   if (usage.cacheRead > 0) {
     onEvent({ type: "cache_hit", sdk: resolved.sdk, model: reference, tokens: usage.cacheRead, source: "prompt_cache" });
   }
@@ -72,6 +105,16 @@ export function emitUsageCostEvents({ onEvent, resolved, reference, usage, estim
       cacheCreationTokens: Number(usage.cacheWrite) || 0,
     },
   });
+  if (contextUsage) {
+    const effectiveContextWindow = Number(contextWindow) || 0;
+    onEvent({
+      type: "context_usage",
+      sdk: resolved.sdk,
+      model: reference,
+      ...(effectiveContextWindow > 0 ? { contextWindow: effectiveContextWindow } : {}),
+      tokens: contextUsage,
+    });
+  }
   onEvent({
     type: "provider_request_completed",
     sdk: resolved.sdk,

package/src/ai/providers/pi-native.js

@@ -52,6 +52,7 @@ import {
   buildErrorDetails,
   buildErrorResult,
   buildSuccessResult,
+  contextUsageFromAssistantMessage,
   emitCapabilitiesResolved,
   emitUsageCostEvents,
   usageFromMessages,
@@ -608,7 +609,19 @@ export async function generatePiNativeResponse(systemPrompt, options = {}) {
       cachedTokens: usage.cacheRead,
       cacheWriteTokens: usage.cacheWrite,
     });
-    emitUsageCostEvents({ onEvent, resolved, reference, usage, estimatedCost, start, externalAbort: runState.externalAbort });
+    emitUsageCostEvents({
+      onEvent,
+      resolved,
+      reference,
+      usage,
+      contextUsage: runState.externalAbort || runState.maxTurnsHit || runError
+        ? null
+        : contextUsageFromAssistantMessage(lastAssistant),
+      contextWindow: runState.compaction.policy?.contextWindow,
+      estimatedCost,
+      start,
+      externalAbort: runState.externalAbort,
+    });
 
     const rawErrorMessage = runState.externalAbort
       ? null

package/types/ai/providers/pi-native/result-builder.d.ts

@@ -10,6 +10,21 @@ export function usageFromMessages(messages?: Array<any>): {
     cacheWrite: number;
     cost: number;
 };
+/**
+ * Normalize the final provider request's usage into an exact context snapshot.
+ * Unlike usageFromMessages(), this deliberately does not aggregate earlier
+ * requests in the run: the last assistant usage is the same provider-counted
+ * value Pi's compaction logic trusts, so it can decrease after compaction.
+ * @param {any} assistantMessage
+ * @returns {{input: number, output: number, cacheRead: number, cacheCreation: number, total: number}|null}
+ */
+export function contextUsageFromAssistantMessage(assistantMessage: any): {
+    input: number;
+    output: number;
+    cacheRead: number;
+    cacheCreation: number;
+    total: number;
+} | null;
 /**
  * Classify a pi error message into a runtime failure kind. Context-window
  * overflows map to context_limit so the router can try the configured fallback;
@@ -25,9 +40,9 @@ export function failureKindForPiError(message: string | null, diagnostics: Recor
 }): string | null;
 /**
  * Emit the per-run cache / cost / provider-completed events.
- * @param {{onEvent: (event: any) => void, resolved: any, reference: string, usage: {input: number, output: number, cacheRead: number, cacheWrite: number, cost: number}, estimatedCost: number, start: number, externalAbort: boolean}} params
+ * @param {{onEvent: (event: any) => void, resolved: any, reference: string, usage: {input: number, output: number, cacheRead: number, cacheWrite: number, cost: number}, contextUsage?: {input: number, output: number, cacheRead: number, cacheCreation: number, total: number}|null, contextWindow?: number, estimatedCost: number, start: number, externalAbort: boolean}} params
  */
-export function emitUsageCostEvents({ onEvent, resolved, reference, usage, estimatedCost, start, externalAbort }: {
+export function emitUsageCostEvents({ onEvent, resolved, reference, usage, contextUsage, contextWindow, estimatedCost, start, externalAbort, }: {
     onEvent: (event: any) => void;
     resolved: any;
     reference: string;
@@ -38,6 +53,14 @@ export function emitUsageCostEvents({ onEvent, resolved, reference, usage, estim
         cacheWrite: number;
         cost: number;
     };
+    contextUsage?: {
+        input: number;
+        output: number;
+        cacheRead: number;
+        cacheCreation: number;
+        total: number;
+    } | null;
+    contextWindow?: number;
     estimatedCost: number;
     start: number;
     externalAbort: boolean;