claude-code-cache-fix 1.1.0 → 1.3.0

package/README.md

@@ -131,6 +131,7 @@ Logs are written to `~/.claude/cache-fix-debug.log`. Look for:
 - `BUDGET WARNING: tool result chars at N / 200,000 threshold` — approaching budget cap
 - `FALSE RATE LIMIT: synthetic model detected` — client-side false rate limit
 - `GROWTHBOOK FLAGS: {...}` — server-controlled feature flags on first call
+- `PROMPT SIZE: system=N tools=N injected=N (skills=N mcp=N ...)` — per-call prompt size breakdown
 - `SKIPPED: resume relocation (not a resume or already correct)` — no fix needed
 
 ### Prefix diff mode
@@ -170,6 +171,7 @@ Snapshots are saved to `~/.claude/cache-fix-snapshots/` and diff reports are gen
 ## Related research
 
 - **[@ArkNill/claude-code-hidden-problem-analysis](https://github.com/ArkNill/claude-code-hidden-problem-analysis)** — Systematic proxy-based analysis of 7 bugs including microcompact, budget enforcement, false rate limiter, and extended thinking quota impact. The monitoring features in v1.1.0 are informed by this research.
+- **[@Renvect/X-Ray-Claude-Code-Interceptor](https://github.com/Renvect/X-Ray-Claude-Code-Interceptor)** — Diagnostic HTTPS proxy with real-time dashboard, system prompt section diffing, per-tool stripping thresholds, and multi-stream JSONL logging. Works with any Claude client that supports `ANTHROPIC_BASE_URL` (CLI, VS Code extension, desktop app), complementing this package's CLI-only `NODE_OPTIONS` approach.
 
 ## Contributors
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-cache-fix",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "description": "Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions",
   "type": "module",
   "exports": "./preload.mjs",

package/preload.mjs

@@ -731,6 +731,37 @@ globalThis.fetch = async function (url, options) {
         monitorContextDegradation(payload.messages);
       }
 
+      // Prompt size measurement — log system prompt, tools, and injected block sizes
+      if (DEBUG && payload.system && payload.tools && payload.messages) {
+        const sysChars = JSON.stringify(payload.system).length;
+        const toolsChars = JSON.stringify(payload.tools).length;
+        const firstUserIdx = payload.messages.findIndex(m => m.role === "user");
+        if (firstUserIdx !== -1) {
+          const msg0 = payload.messages[firstUserIdx];
+          if (Array.isArray(msg0.content)) {
+            let skillsChars = 0;
+            let mcpChars = 0;
+            let deferredChars = 0;
+            let hooksChars = 0;
+            for (const block of msg0.content) {
+              const text = block.text || "";
+              if (isSkillsBlock(text)) skillsChars += text.length;
+              else if (isMcpBlock(text)) mcpChars += text.length;
+              else if (isDeferredToolsBlock(text)) deferredChars += text.length;
+              else if (isHooksBlock(text)) hooksChars += text.length;
+            }
+            const injectedTotal = skillsChars + mcpChars + deferredChars + hooksChars;
+            if (injectedTotal > 0) {
+              debugLog(
+                `PROMPT SIZE: system=${sysChars} tools=${toolsChars}`,
+                `injected=${injectedTotal} (skills=${skillsChars} mcp=${mcpChars}`,
+                `deferred=${deferredChars} hooks=${hooksChars})`
+              );
+            }
+          }
+        }
+      }
+
       // Capture prefix snapshot for cross-process diff analysis
       snapshotPrefix(payload);