@nxuss/lemma 1.4.0 → 1.6.0

package/dist/esm/cli/lemma-proxy.js

@@ -580,6 +580,31 @@ async function loadUsage() {
 async function loadStats() {
     return readJson(STATS_FILE, {});
 }
+/**
+ * Tokens a cache hit actually avoided regenerating, measured from the cached payload
+ * that was served instead of an LLM call. Replaces the old hardcoded 2000 guess.
+ */
+function measureCachedTokens(data) {
+    try {
+        const chars = JSON.stringify(data)?.length;
+        if (!chars)
+            return undefined;
+        return Math.floor(chars / 4);
+    }
+    catch {
+        return undefined;
+    }
+}
+/**
+ * @param tokensSaved  Measured tokens saved. When omitted for a cache hit, stats.json
+ *   still falls back to a 2000-token placeholder for dashboard continuity, but that
+ *   guess is deliberately NOT written to the savings ledger — the ledger only accepts
+ *   measured values, otherwise its net position is built on invented numbers.
+ *
+ * Note: a cache *miss* is not charged to the cost ledger. The lookup is local (no LLM
+ * round-trip), so a miss costs latency, not tokens. Charging it a fabricated token
+ * figure would repeat exactly the error the cost ledger exists to correct.
+ */
 async function recordStat(stats, project, fromCache, latencyMs, provider, tokensSaved) {
     if (!stats[project]) {
         stats[project] = { total: 0, hits: 0, misses: 0, totalLatency: 0, totalTokensSaved: 0, providers: {} };
@@ -593,9 +618,11 @@ async function recordStat(stats, project, fromCache, latencyMs, provider, tokens
     if (!s.providers[provider])
         s.providers[provider] = { hits: 0, misses: 0 };
     fromCache ? s.providers[provider].hits++ : s.providers[provider].misses++;
-    if (fromCache && tkSaved > 0) {
-        // Automatically report cache hits directly to the server session ledger for absolute sync consistency
-        savingsLedger.recordTokens('cache', tkSaved);
+    // Only measured savings reach the ledger. `tokensSaved === undefined` means the
+    // caller never counted, so tkSaved is the 2000 placeholder — usable for the
+    // dashboard, not for a net-position claim.
+    if (fromCache && typeof tokensSaved === 'number' && tokensSaved > 0) {
+        savingsLedger.recordTokens('cache', tokensSaved);
     }
     logEvent({
         type: fromCache ? 'cache:hit' : 'cache:miss',
@@ -1501,6 +1528,23 @@ class LemmaServer {
                 }
                 res.json({ ok: true, snapshot: savingsLedger.getSnapshot().total });
             });
+            // Cost Record Endpoint — the counterpart to /api/savings-record. Without it the
+            // ledger only ever counts wins, which makes its totals unfalsifiable.
+            this.app.post('/api/cost-record', (req, res) => {
+                const { source, tokens, chars } = req.body || {};
+                const validSources = ['mcpInstructions', 'toolResult', 'cacheMiss'];
+                if (!source || !validSources.includes(source)) {
+                    return res.status(400).json({ error: 'Invalid cost source' });
+                }
+                if (typeof tokens === 'number' && tokens > 0) {
+                    savingsLedger.recordCost(source, tokens);
+                }
+                else if (typeof chars === 'number' && chars > 0) {
+                    savingsLedger.recordCostChars(source, chars);
+                }
+                const snap = savingsLedger.getSnapshot();
+                res.json({ ok: true, totalCost: snap.totalCost, net: snap.net });
+            });
             // MCP Tool Event Endpoint — called by MCP server when tools execute
             this.app.post('/api/mcp-event', (req, res) => {
                 try {
@@ -1726,7 +1770,7 @@ class LemmaServer {
             const semHit = await semanticGet(provider, prompt, this.projectName);
             if (semHit) {
                 if (semHit.similarity >= 0.90) {
-                    await recordStat(this.stats, this.projectName, true, Date.now() - t0, provider, 2000);
+                    await recordStat(this.stats, this.projectName, true, Date.now() - t0, provider, measureCachedTokens(semHit.data));
                     const unmaskedData = semanticScrubber.unmask(semHit.data, tokenMap);
                     const cacheHeader = semHit.hiveMind ? 'HIT-HIVE-MIND' : 'HIT';
                     if (isStream)
@@ -1777,7 +1821,7 @@ Adjusted Answer:`;
                                 else if (provider === 'anthropic') {
                                     synthesizedData.content[0].text = adjustedText;
                                 }
-                                await recordStat(this.stats, this.projectName, true, Date.now() - t0, provider, 2000);
+                                await recordStat(this.stats, this.projectName, true, Date.now() - t0, provider, measureCachedTokens(synthesizedData));
                                 const unmaskedData = semanticScrubber.unmask(synthesizedData, tokenMap);
                                 if (isStream) {
                                     return SseRelay.simulateHit(res, unmaskedData, { provider: provider, tier, similarity: semHit.similarity });
@@ -1797,7 +1841,7 @@ Adjusted Answer:`;
             const cloudHit = await cloudSync.get(prompt);
             if (cloudHit) {
                 cacheSet(provider, prompt, cloudHit.data);
-                await recordStat(this.stats, this.projectName, true, Date.now() - t0, provider, 2000);
+                await recordStat(this.stats, this.projectName, true, Date.now() - t0, provider, measureCachedTokens(cloudHit.data));
                 const unmaskedData = semanticScrubber.unmask(cloudHit.data, tokenMap);
                 if (isStream)
                     return SseRelay.simulateHit(res, unmaskedData, { provider: provider, tier, similarity: cloudHit.similarity || 0.95 });