pi-mega-compact 0.6.9 → 0.7.1

package/extensions/dashboard-server.ts

@@ -294,14 +294,15 @@ function readSnapshot(snapshotPath: string) {
       tier: "unknown",
       presetTier: "unknown",
       pressure: 0,
-      config: { fastGatePct: 80, thresholdTokens: 100_000, anchorUserMessages: 1, preserveRecent: 2, auto: true, autoInlineK: 3 },
+      config: { fastGatePct: 80, thresholdTokens: 100_000, tierPct: null, effectiveThresholdPct: null, anchorUserMessages: 1, preserveRecent: 2, auto: true, autoInlineK: 3 },
       session: { id: null, state: null, persistedThisSession: false, lastCheckpointId: null, lastCompactedFrom: 0 },
       context: { tokens: null, percent: null, contextWindow: 0 },
-      trigger: { armed: false, ready: false, currentTokens: null, thresholdTokens: 100_000, fastGatePct: 80 },
+      trigger: { armed: false, ready: false, currentTokens: null, thresholdTokens: 100_000, fastGatePct: 80, tierPct: null, effectiveThresholdPct: null },
       store: { checkpointCount: 0, totalTokenEstimate: 0, originalTokens: 0, tokensSaved: 0, injectedCount: 0, dedupHitRate: 0, storageDedupRate: 0, dedupCollapsed: 0 },
       crew: { activeAgents: 0, currentTurn: 0 },
       repo: { checkpointCount: 0, totalTokenEstimate: 0, originalTokens: 0, tokensSaved: 0, sessionCount: 0, dedupAttempts: 0, dedupCollapsed: 0, storageDedupRate: 0 },
       integrity: { regionsRetained: 0, compressedOriginalBytes: 0, duplicatesCollapsed: 0, bytesPermanentlyDeleted: 0 },
+      compression: { session: { tokensIn: 0, tokensOut: 0, tokensFreed: 0, compressionPct: 0, dedupPct: 0 }, repo: { tokensIn: 0, tokensOut: 0, tokensFreed: 0, compressionPct: 0, dedupPct: 0 } },
       model: undefined,
     } as Snapshot;
   }
@@ -488,9 +489,9 @@ function dashboardHtml(tierName: string): string {
     <div class="conf-grid">
       <span class="label" title="Live pressure band — climbs low→mega as context fills the window.">Tier (live)</span><span class="value" id="cf-tier">${tierName}</span>
       <span class="label" title="The env-resolved base compaction preset (low/medium/high/ultra/mega) that set the token threshold.">Preset</span><span class="value" id="cf-preset">—</span>
-      <span class="label" title="Live pressure = currentTokens / thresholdTokens (0–100%).">Pressure</span><span class="value" id="cf-pressure">—</span>
-      <span class="label">Threshold</span><span class="value" id="cf-threshold">—</span>
-      <span class="label">Fast Gate</span><span class="value" id="cf-gate">—</span>
+      <span class="label" title="Live pressure = currentTokens / threshold — % of the model context window (threshold fires at the tier's % of window).">Pressure</span><span class="value" id="cf-pressure">—</span>
+      <span class="label" title="Compaction threshold = tierPct × model context window — mega-compact trims BELOW pi's native ~80% auto-compact for any model size.">Threshold</span><span class="value" id="cf-threshold">—</span>
+      <span class="label" title="Fast-gate arming floor — the live trim arms once context passes this % of the window.">Fast Gate</span><span class="value" id="cf-gate">—</span>
       <span class="label">Auto</span><span class="value" id="cf-auto">—</span>
       <span class="label">Anchor</span><span class="value" id="cf-anchor">—</span>
     </div>
@@ -711,7 +712,17 @@ function dashboardHtml(tierName: string): string {
     document.getElementById('cf-tier').textContent = d.tier + ' (live)';
     document.getElementById('cf-preset').textContent = d.presetTier;
     document.getElementById('cf-pressure').textContent = Math.round((d.pressure || 0) * 100) + '%';
-    document.getElementById('cf-threshold').textContent = d.config.thresholdTokens.toLocaleString();
+    // (b) Threshold: show the effective token threshold AND the % of the model
+    // context window it represents (percentage-based tiers). d.config.tierPct
+    // is present on the live snapshot written by the runtime (Phase-1/2a).
+    var cfgPct = d.config.tierPct;
+    var cw = d.context.contextWindow || 0;
+    var thresholdTxt = d.config.thresholdTokens.toLocaleString();
+    if (cfgPct != null && cw > 0) {
+      thresholdTxt += ' (' + Math.round(cfgPct * 100) + '% of ' + cw.toLocaleString() + ')';
+    }
+    document.getElementById('cf-threshold').textContent = thresholdTxt;
+    // (c) Fast Gate: arming floor — live trim arms once context passes this %.
     document.getElementById('cf-gate').textContent = d.config.fastGatePct + '%';
     document.getElementById('cf-auto').textContent = d.config.auto ? 'enabled' : 'disabled';
     document.getElementById('cf-anchor').textContent = d.config.anchorUserMessages;

package/extensions/mega-commands.ts

@@ -125,10 +125,21 @@ export function registerCommands(pi: ExtensionAPI, runtime: MegaRuntime, config:
         repoCount = listRepoRegistry(process.env.MEGACOMPACT_INDEX_DIR).length;
       } catch { /* non-fatal */ }
       const crossRepoStr = `${crossRepoInjections} cross-repo injections recorded · ${repoCount} repos indexed`;
+      // Effective compaction threshold = tierPct × model context window (kept
+      // BELOW pi's native ~80% auto-compact for any model size). Falls back to
+      // the boot token value when the window is unknown (custom tier / pre-
+      // model-select). Display matches the dashboard's percentage-based view.
+      const effThreshold = config.tierPct != null && ctxWindow > 0
+        ? Math.round(config.tierPct * ctxWindow)
+        : config.thresholdTokens;
+      const winStr = ctxWindow > 0
+        ? (ctxWindow >= 1_000_000 ? `${Math.round(ctxWindow / 1_000_000)}M` : `${Math.round(ctxWindow / 1_000)}k`)
+        : "?";
+      const tierPctStr = config.tierPct != null ? `${Math.round(config.tierPct * 100)}%` : "n/a";
       ctx.ui.notify(
         `[mega-compact] pct=${pct} tokens=${tokens} tier=${runtime.pressureBand} (live) preset=${config.tier} ` +
           `pressure=${Math.round(runtime.pressure * 100)}% fastGate=${config.fastGatePct}% ` +
-          `threshold=${config.thresholdTokens} auto=${config.auto} autoInline=${config.autoInline}\n` +
+          `threshold=${effThreshold.toLocaleString()} (${tierPctStr} of ${winStr} window) tierPct=${config.tierPct != null ? config.tierPct.toFixed(2) : "n/a"} auto=${config.auto} autoInline=${config.autoInline}\n` +
           `[mega-compact] store: ${st.checkpointCount} chkpt · ` +
           `${st.totalTokenEstimate} tok · last=${st.lastCheckpointId ?? "—"} · ` +
           `injected=${st.injectedCount} · dedup=${(st.dedupHitRate * 100).toFixed(0)}%\n` +

package/extensions/mega-compact-driver.ts

@@ -30,13 +30,13 @@ import type { MegaConfig } from "./mega-config.js";
 import { recallRaptorRootSummary } from "../src/dedup/raptor/index.js";
 
 export interface NativeCompactionResult {
-  /** Our trimmed summary + the pi entry to keep from (durable trim). */
-  compaction: {
-    summary: string;
-    firstKeptEntryId: string;
-    tokensBefore: number;
-    estimatedTokensAfter: number;
-  };
+	/** Our trimmed summary + the pi entry to keep from (durable trim). */
+	compaction: {
+		summary: string;
+		firstKeptEntryId: string;
+		tokensBefore: number;
+		estimatedTokensAfter: number;
+	};
 }
 
 /**
@@ -46,60 +46,61 @@ export interface NativeCompactionResult {
  * own native compaction, or skip). Never throws for "empty" — best-effort.
  */
 export function driveNativeCompaction(
-  event: SessionBeforeCompactEvent,
-  runtime: MegaRuntime,
-  config: MegaConfig,
+	event: SessionBeforeCompactEvent,
+	runtime: MegaRuntime,
+	config: MegaConfig,
 ): NativeCompactionResult | undefined {
-  const prep = event.preparation;
-  if (!prep) return undefined;
+	const prep = event.preparation;
+	if (!prep) return undefined;
 
-  const sid = runtime.rt.sessionId;
-  const messagesToSummarize: AgentMessage[] = prep.messagesToSummarize ?? [];
-  if (messagesToSummarize.length === 0) return undefined;
+	const sid = runtime.rt.sessionId;
+	const messagesToSummarize: AgentMessage[] = prep.messagesToSummarize ?? [];
+	if (messagesToSummarize.length === 0) return undefined;
 
-  const engineView = toEngineMessages(messagesToSummarize);
-  // We don't drop anything here — pi keeps from prep.firstKeptEntryId. We only
-  // summarize the region pi is about to discard.
-  const keepFrom = engineView.length;
+	const engineView = toEngineMessages(messagesToSummarize);
+	// We don't drop anything here — pi keeps from prep.firstKeptEntryId. We only
+	// summarize the region pi is about to discard.
+	const keepFrom = engineView.length;
 
-  const result = compactSession(
-    {
-      sessionId: sid,
-      messages: engineView,
-      keepFrom,
-      timestamp: Date.now(),
-      useExtractiveSummary: true,
-    },
-    runtime.store,
-  );
-  if (result.skipped) return undefined;
+	const result = compactSession(
+		{
+			sessionId: sid,
+			messages: engineView,
+			keepFrom,
+			timestamp: Date.now(),
+			useExtractiveSummary: true,
+		},
+		runtime.store,
+	);
+	if (result.skipped) return undefined;
 
-  // Prefer the RAPTOR root summary when the tree is built + enabled (Fix D):
-  // it is a session-level compressed summary, broader than one slice's. Fall
-  // back to the extractive topicSummary of this slice.
-  let summary = result.summary;
-  if (config.raptorEnabled) {
-    const root = recallRaptorRootSummary(sid, runtime.currentStateDir);
-    if (root) summary = root;
-  }
+	// Prefer the RAPTOR root summary when the tree is built + enabled (Fix D):
+	// it is a session-level compressed summary, broader than one slice's. Fall
+	// back to the extractive topicSummary of this slice.
+	let summary = result.summary;
+	if (config.raptorEnabled) {
+		const root = recallRaptorRootSummary(sid, runtime.currentStateDir);
+		if (root) summary = root;
+	}
 
-  const tokensBefore = prep.tokensBefore ?? estimateSessionTokens(engineView);
-  const summaryTokens = estimateBlockTokens(summary);
-  // pi keeps the tail from firstKeptEntryId; our summary replaces the discarded
-  // region. Honest saved = discarded-region tokens − our summary tokens.
-  const savedTokens = Math.max(0, tokensBefore - summaryTokens);
+	const tokensBefore = prep.tokensBefore ?? estimateSessionTokens(engineView);
+	const summaryTokens = estimateBlockTokens(summary);
+	// pi keeps the tail from firstKeptEntryId; our summary replaces the discarded
+	// region. Honest saved = discarded-region tokens − our summary tokens.
+	const savedTokens = Math.max(0, tokensBefore - summaryTokens);
 
-  runtime.rt.lastCompactedFrom = keepFrom;
-  runtime.rt.lastCompactedTokens = tokensBefore;
-  runtime.rt.tokensSaved += savedTokens;
-  runtime.rt.persistedThisSession = true;
+	runtime.rt.lastCompactedFrom = keepFrom;
+	runtime.rt.lastCompactedTokens = tokensBefore;
+	runtime.rt.tokensSaved += savedTokens;
+	runtime.rt.lastCompactAt = Date.now();
+	runtime.rt.persistedThisSession = true;
 
-  return {
-    compaction: {
-      summary,
-      firstKeptEntryId: prep.firstKeptEntryId,
-      tokensBefore,
-      estimatedTokensAfter: summaryTokens,
-    },
-  };
+	return {
+		compaction: {
+			summary,
+			firstKeptEntryId: prep.firstKeptEntryId,
+			tokensBefore,
+			estimatedTokensAfter: summaryTokens,
+		},
+	};
 }