@nijaru/pi-provider-compaction 0.0.11 → 0.0.13

package/README.md

@@ -1,6 +1,6 @@
 # pi-provider-compaction
 
-Experimental cache-aware compaction for [Pi](https://github.com/earendil-works/pi), with portable summaries and optional provider-native checkpoints. Minimum runtime: Pi 0.87.0. Development checks target Pi 1.4.0.
+Experimental cache-aware compaction for [Pi](https://github.com/earendil-works/pi), with portable summaries and optional provider-native checkpoints. Minimum runtime: Pi 0.87.0. Development checks target Pi 1.5.0.
 
 **Experimental; qualified backend probes are not production validation.** Real runner/adapter fixtures and live DeepSeek, MiMo and Codex probes pass, with the preservation and cache-hit qualifications below. Broader backend and deployment validation remains incomplete.
 
@@ -39,15 +39,14 @@ The summary request extends the captured logical prompt, rather than serializing
 ```json
 {
   "providerCompaction": {
-    "cachedSummaries": true,
-    "outcomeNotifications": false
+    "cachedSummaries": true
   }
 }
 ```
 
 These are the defaults on hosts exposing Pi's `getSettings` API; older hosts retain native compaction with cached summaries disabled. Optional `cacheRetention` accepts `"short"`, `"long"`, or `"none"`; omission inherits Pi/provider behavior. Retention is applied per request, not through process-wide environment changes. A longer tier can increase cache-write charges and only works where the adapter/backend supports it.
 
-A cache hit is best effort, not a promised saving. Countdown estimates use the model's declared `promptCache` lifetime for the active tier, measured conservatively from request dispatch. Missing lifetimes remain unknown: DeepSeek, for example, [documents best-effort eviction over hours to days](https://api-docs.deepseek.com/guides/kv_cache/), not a predictable expiry. Pi's successful warmer requests refresh the observed cycle and countdown.
+A cache hit is best effort, not a promised saving. Expiry estimates use the model's declared `promptCache` lifetime for the active tier, measured conservatively from request dispatch. Missing lifetimes remain unknown: DeepSeek, for example, [documents best-effort eviction over hours to days](https://api-docs.deepseek.com/guides/kv_cache/), not a predictable expiry. Pi's successful warmer requests refresh the observed cycle and estimated expiry.
 
 With [pi-compactor's opt-in idle expiry policy](https://github.com/nijaru/pi-compactor#cache-aware-idle-compaction), compaction can run before an estimated expiry. Both extensions share a live ownership/input guard, checked before paid summary and native-checkpoint stages regardless of extension order. A failed or revoked cached-only attempt cancels instead of starting an ordinary summary. It does not start a continuation.
 
@@ -77,7 +76,7 @@ Legacy v1/v2 whole-history checkpoints remain inspectable but are never reinterp
 
 ## Diagnose portable fallback
 
-Committed compaction entries retain the selected path, elapsed time, reported usage, and estimated cost. Optional outcome notifications show those measurements, not hypothetical savings. Portable fallback appends a `pi-provider-compaction:diagnostic` session entry with a fixed reason. Cancelled attempts with reported usage retain that usage in the same diagnostic record; without a saved checkpoint, Pi's extension API cannot include it in compaction totals. Diagnostics stay out of model context and never include request content, credentials, or backend error text.
+Committed compaction entries retain the selected path, elapsed time, reported usage, and estimated cost. Portable fallback appends a `pi-provider-compaction:diagnostic` session entry with a fixed reason. Cancelled attempts with reported usage retain that usage in the same diagnostic record; without a saved checkpoint, Pi's extension API cannot include it in compaction totals. Diagnostics stay out of model context and never include request content, credentials, or backend error text.
 
 These records describe attempts made while the extension was loaded; they cannot explain earlier compactions retroactively. A committed native checkpoint does not by itself prove that a later request replayed it.
 
@@ -102,7 +101,7 @@ pi --extension ./dist/index.js
 
 The manifest loads the built `dist/index.js`, including a bundled stateless Responses serializer validator; source or host dependency changes require a rebuild. `bun run check` rebuilds first and tests the artifact against Pi's actual host serializer, including function-call history replayed as grammar tools. Keep global installation disabled while testing. Publishing and global activation are separate approval steps.
 
-Tests include real Pi 1.4.0 runner/adapter fixtures for all three protocols, repeated prefix compaction, transformed suffix preservation, unchanged fallback, grammar tools, strict defaults, tool IDs, images, prompt updates, cross-model thinking and mid-conversation effort changes. Set `PI_COMPACTOR_FIXTURE_PATH` to a `pi-compactor` entrypoint to check SDK flag precedence and real idle-expiry transactions in both extension orders. Cached-summary fixtures also exercise built-in DeepSeek/Xiaomi dispatch, Anthropic Messages, late tool output, truncated-output fallback and measured usage. The optional installed-fast-mode fixture (`PI_FAST_MODE_FIXTURE_PATH`) checks actual `pi-fast-mode` composition across `/reload`; it creates an isolated fast-mode configuration. `PI_PEAK_HOURS_FIXTURE_PATH` adds request-wide pricing checks in both extension orders, including warming, branch summaries, mixed-API dispatch and composition with `/fast`.
+Tests include real Pi 1.5.0 runner/adapter fixtures for all three protocols, repeated prefix compaction, transformed suffix preservation, unchanged fallback, grammar tools, strict defaults, tool IDs, images, prompt updates, cross-model thinking and mid-conversation effort changes. Set `PI_COMPACTOR_FIXTURE_PATH` to a `pi-compactor` entrypoint to check SDK flag precedence and real idle-expiry transactions in both extension orders. Cached-summary fixtures also exercise built-in DeepSeek/Xiaomi dispatch, Anthropic Messages, late tool output, truncated-output fallback and measured usage. The optional installed-fast-mode fixture (`PI_FAST_MODE_FIXTURE_PATH`) checks actual `pi-fast-mode` composition across `/reload`; it creates an isolated fast-mode configuration. `PI_PEAK_HOURS_FIXTURE_PATH` adds request-wide pricing checks in both extension orders, including warming, branch summaries, mixed-API dispatch and composition with `/fast`.
 
 Authenticated cached-summary smoke tests use synthetic history, including a value beyond the ordinary tool-result excerpt, and check continuation:
 

package/cached-summary.ts

@@ -17,13 +17,12 @@ export interface CacheState {
 	cachedTokens: number;
 	inputTokens: number;
 }
-export interface CacheConfig { cachedSummaries: boolean; cacheRetention?: CacheRetention; outcomeNotifications: boolean }
+export interface CacheConfig { cachedSummaries: boolean; cacheRetention?: CacheRetention }
 export function cacheConfig(settings: unknown): CacheConfig {
 	const raw = isObject(settings) && isObject(settings.providerCompaction) ? settings.providerCompaction : {};
 	return {
 		cachedSummaries: raw.cachedSummaries !== false,
 		cacheRetention: raw.cacheRetention === "long" || raw.cacheRetention === "short" || raw.cacheRetention === "none" ? raw.cacheRetention : undefined,
-		outcomeNotifications: raw.outcomeNotifications === true,
 	};
 }
 export function supportsCachedSummary(model: Model<any> | undefined): boolean {

package/dist/index.js

@@ -1591,8 +1591,7 @@ function cacheConfig(settings) {
   const raw = isObject(settings) && isObject(settings.providerCompaction) ? settings.providerCompaction : {};
   return {
     cachedSummaries: raw.cachedSummaries !== false,
-    cacheRetention: raw.cacheRetention === "long" || raw.cacheRetention === "short" || raw.cacheRetention === "none" ? raw.cacheRetention : undefined,
-    outcomeNotifications: raw.outcomeNotifications === true
+    cacheRetention: raw.cacheRetention === "long" || raw.cacheRetention === "short" || raw.cacheRetention === "none" ? raw.cacheRetention : undefined
   };
 }
 function supportsCachedSummary(model) {
@@ -2246,6 +2245,7 @@ function combineUsage(first, second) {
       result[key] = (first[key] ?? 0) + (second[key] ?? 0);
   for (const key of ["input", "output", "cacheRead", "cacheWrite", "total"])
     result.cost[key] += second.cost[key];
+  result.cost.totalFromProvider = first.cost.totalFromProvider === true && second.cost.totalFromProvider === true;
   return result;
 }
 function supportedRouteOptions(model, options) {
@@ -2257,7 +2257,7 @@ function supportedRouteOptions(model, options) {
   return !["AZURE_OPENAI_BASE_URL", "AZURE_OPENAI_RESOURCE_NAME", "AZURE_OPENAI_API_VERSION", "AZURE_OPENAI_DEPLOYMENT_NAME_MAP"].some((key) => process.env[key] !== undefined && options.env?.[key] === undefined);
 }
 function pi_provider_compaction_default(pi) {
-  const configuration = () => typeof pi.getSettings === "function" ? cacheConfig(pi.getSettings()) : { cachedSummaries: false, outcomeNotifications: false, cacheRetention: undefined };
+  const configuration = () => typeof pi.getSettings === "function" ? cacheConfig(pi.getSettings()) : { cachedSummaries: false, cacheRetention: undefined };
   const secret = randomBytes(32);
   const routeDigest = (value) => createHmac("sha256", secret).update(JSON.stringify(value)).digest("hex");
   let runtimeId = randomUUID2();
@@ -2705,10 +2705,6 @@ function pi_provider_compaction_default(pi) {
     const owned = isObject(recorded) && equal(recorded, lastOutcome);
     if (!owned && !fallbackReason && readNativeCompactionDetails(event.compactionEntry.details)?.version !== 3)
       fallback("another handler supplied the committed result");
-    if (owned) {
-      if (configuration().outcomeNotifications && lastOutcome)
-        context.ui.notify(`Compacted via ${lastOutcome.path} in ${(lastOutcome.elapsedMs / 1000).toFixed(1)}s${lastOutcome.usage ? `; cache read ${lastOutcome.usage.cacheRead}, write ${lastOutcome.usage.cacheWrite}; estimated cost $${lastOutcome.usage.cost.total.toFixed(6)}` : ""}`, "info");
-    }
     if (fallbackReason)
       pi.appendEntry("pi-provider-compaction:diagnostic", { status: `portable: ${fallbackReason}` });
     active = undefined;

package/index.ts

@@ -112,6 +112,7 @@ function combineUsage(first: Usage | undefined, second: Usage | undefined): Usag
 	for (const key of ["input", "output", "cacheRead", "cacheWrite", "totalTokens"] as const) result[key] += second[key];
 	for (const key of ["reasoning", "cacheWrite1h"] as const) if (first[key] !== undefined || second[key] !== undefined) result[key] = (first[key] ?? 0) + (second[key] ?? 0);
 	for (const key of ["input", "output", "cacheRead", "cacheWrite", "total"] as const) result.cost[key] += second.cost[key];
+	result.cost.totalFromProvider = first.cost.totalFromProvider === true && second.cost.totalFromProvider === true;
 	return result;
 }
 
@@ -157,7 +158,7 @@ export default function (pi: ExtensionAPI): void {
 	// hook/privacy policy, even if the visible summary text happens to match.
 	// Older hosts in the native adapter's supported range lack getSettings.
 	// Keep their existing native path; cache preferences require that host API.
-	const configuration = () => typeof pi.getSettings === "function" ? cacheConfig(pi.getSettings()) : { cachedSummaries: false, outcomeNotifications: false, cacheRetention: undefined };
+	const configuration = () => typeof pi.getSettings === "function" ? cacheConfig(pi.getSettings()) : { cachedSummaries: false, cacheRetention: undefined };
 	const secret = randomBytes(32);
 	const routeDigest = (value: unknown) => createHmac("sha256", secret).update(JSON.stringify(value)).digest("hex");
 	let runtimeId = randomUUID();
@@ -493,9 +494,6 @@ export default function (pi: ExtensionAPI): void {
 		const recorded = isObject(event.compactionEntry.details) ? event.compactionEntry.details.providerCompaction : undefined;
 		const owned = isObject(recorded) && equal(recorded, lastOutcome);
 		if (!owned && !fallbackReason && readNativeCompactionDetails(event.compactionEntry.details)?.version !== 3) fallback("another handler supplied the committed result");
-		if (owned) {
-			if (configuration().outcomeNotifications && lastOutcome) context.ui.notify(`Compacted via ${lastOutcome.path} in ${(lastOutcome.elapsedMs / 1000).toFixed(1)}s${lastOutcome.usage ? `; cache read ${lastOutcome.usage.cacheRead}, write ${lastOutcome.usage.cacheWrite}; estimated cost $${lastOutcome.usage.cost.total.toFixed(6)}` : ""}`, "info");
-		}
 		// Only static diagnostics are persisted, never request/auth data or error text.
 		if (fallbackReason) pi.appendEntry("pi-provider-compaction:diagnostic", { status: `portable: ${fallbackReason}` });
 		active = undefined; snapshot = undefined; cache = undefined;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nijaru/pi-provider-compaction",
-  "version": "0.0.11",
+  "version": "0.0.13",
   "type": "module",
   "description": "Provider-native context compaction adapters for Pi",
   "keywords": [
@@ -46,11 +46,12 @@
     "LICENSE"
   ],
   "devDependencies": {
-    "@earendil-works/pi-ai": "1.4.0",
-    "@earendil-works/pi-agent-core": "1.4.0",
-    "@earendil-works/pi-coding-agent": "1.4.0",
+    "@earendil-works/pi-ai": "1.5.0",
+    "@earendil-works/pi-agent-core": "1.5.0",
+    "@earendil-works/pi-coding-agent": "1.5.0",
     "@types/bun": "latest",
     "oxlint": "^1.81.0",
+    "typebox": "^1.3.0",
     "typescript": "^6.0.3"
   },
   "peerDependencies": {