fix(cache): fold a boot-config epoch into the response-cache key (#176) (#177)

The cache key hashed model + keyId + sampling params + raw messages, but the
ANSWER also depends on boot-time server config that shapes the composed prompt
and tool surface: CLAUDE_SYSTEM_PROMPT (newly load-bearing since #175),
OCP_SYSTEM_PROMPT_WRAPPER, CLAUDE_ALLOWED_TOOLS, and CLAUDE_NO_CONTEXT. The
cache store is SQLite-backed and survives restarts, so an operator who changed
any of these and restarted kept serving answers composed under the OLD config
until TTL expiry (found by the #175 independent reviewer).

Fix: server.mjs computes CONFIG_EPOCH once at boot — a 16-hex sha256 digest of
the four values — and passes it to cacheHash, which folds `ce:<epoch>|` into the
key. Any config change = instant whole-cache invalidation (the honest behavior).
Callers that omit configEpoch (tests, any older path) hash byte-identically to
before — asserted by test. Runtime-mutable settings (maxPromptChars via the
settings API) are deliberately excluded: a const epoch cannot track them, and
truncation drops context rather than changing the instruction set (noted in the
code comment).

One-time side effect on upgrade: existing cache entries no longer match (keys
now carry the epoch). Cache is off by default and TTL-bounded; a one-time miss
storm is the cost of never serving stale-config answers again.

ALIGNMENT.md Rule 2: no cli.js citation applies — cache-key composition is
OCP-internal (Class B); no endpoint, header, or wire field changes.

Tests: +2, mutation-proven (dropping the fold fails both). Suite 343/0.

Closes #176

Co-authored-by: dtzp555 <dtzp555@gmail.com>
Co-authored-by: Claude <claude-opus-4-8> <noreply@anthropic.com>

keys.mjs

@@ -355,6 +355,11 @@ export function cacheHash(model, messages, opts = {}) {
   if (opts.temperature != null) h.update(`t:${opts.temperature}`);
   if (opts.max_tokens != null) h.update(`mt:${opts.max_tokens}`);
   if (opts.top_p != null) h.update(`tp:${opts.top_p}`);
+  // #176: fold the server's boot-config epoch into the key, so a config change that shapes
+  // answers (operator system prompt, wrapper text, allowed tools, NO_CONTEXT) invalidates
+  // the persistent cache instead of serving answers composed under the old config. Callers
+  // that omit it (older paths, tests) hash byte-identically to before.
+  if (opts.configEpoch != null) h.update(`ce:${opts.configEpoch}|`);
   for (const m of messages) {
     h.update(m.role || "");
     h.update(typeof m.content === "string" ? m.content : JSON.stringify(m.content));

server.mjs

@@ -35,7 +35,7 @@
  */
 import { createServer } from "node:http";
 import { spawn, execFileSync, spawnSync } from "node:child_process";
-import { randomUUID, timingSafeEqual } from "node:crypto";
+import { randomUUID, timingSafeEqual, createHash as cryptoCreateHash } from "node:crypto";
 import { readFileSync, readdirSync, accessSync, existsSync, constants, chmodSync, statSync, mkdirSync, writeFileSync, rmSync } from "node:fs";
 import { fileURLToPath } from "node:url";
 import { dirname, join } from "node:path";
@@ -346,6 +346,19 @@ const BREAKER_HALF_OPEN_MAX = parseInt(process.env.CLAUDE_BREAKER_HALF_OPEN_MAX
 const HEARTBEAT_INTERVAL = parseInt(process.env.CLAUDE_HEARTBEAT_INTERVAL || "0", 10);
 const BIND_ADDRESS = process.env.CLAUDE_BIND || "127.0.0.1";
 const NO_CONTEXT = process.env.CLAUDE_NO_CONTEXT === "true";
+// Config epoch for the response cache (issue #176). The cache key hashes model + messages +
+// sampling params, but the ANSWER also depends on boot-time server config that shapes the
+// composed prompt / tool surface: the operator system prompt (#175), the OCP wrapper text,
+// the allowed-tools set, and NO_CONTEXT. The cache store is SQLite-backed and survives
+// restarts, so without this an operator who changes any of these and restarts keeps serving
+// answers composed under the OLD config until TTL expiry. Folding a digest of the four into
+// every cache key makes any change an instant, whole-cache invalidation — the honest behavior.
+// Deliberately boot-time-only: runtime-mutable settings (e.g. maxPromptChars via the settings
+// API) are excluded because a const epoch cannot track them; truncation also only drops
+// context rather than changing the instruction set.
+const CONFIG_EPOCH = cryptoCreateHash("sha256")
+  .update(JSON.stringify([SYSTEM_PROMPT, OCP_SYSTEM_PROMPT_WRAPPER, ALLOWED_TOOLS, NO_CONTEXT]))
+  .digest("hex").slice(0, 16);
 // Kill-switch for the FIX-③ default-path spawn-home isolation (see resolveSpawnHome /
 // spawnHomeMode below). When "1", the -p/stream-json spawn always runs in the operator's
 // real HOME with no cwd override — byte-for-byte the pre-isolation behaviour — even if an
@@ -2629,8 +2642,9 @@ async function handleChatCompletions(req, res) {
       req._cacheHash = null;
       logEvent("info", "cache_skipped", { reason: "cache_control_present" });
     } else {
-      // D1: include keyId in hash to isolate per-key cache pools (v2 format)
+      // D1: include keyId in hash to isolate per-key cache pools (v2 format).
-      const hash = cacheHash(model, messages, { keyId: req._authKeyId, temperature: parsed.temperature, max_tokens: parsed.max_tokens, top_p: parsed.top_p });
+      // configEpoch (#176): any boot-config change that shapes answers invalidates the cache.
+      const hash = cacheHash(model, messages, { keyId: req._authKeyId, temperature: parsed.temperature, max_tokens: parsed.max_tokens, top_p: parsed.top_p, configEpoch: CONFIG_EPOCH });
       req._cacheHash = hash; // store for later write-back
       try {
         const cached = getCachedResponse(hash, CACHE_TTL);

test-features.mjs

@@ -204,6 +204,23 @@ test("cacheHash includes temperature in hash", () => {
   assert.notEqual(h2, h3);
 });
 
+// ── configEpoch (#176): a boot-config change must invalidate the persistent cache ──
+// Mutation-proof: drop the `ce:` fold in keys.mjs and the first test goes green-to-red.
+test("cacheHash: different configEpoch → different key (config change invalidates)", () => {
+  const h1 = cacheHash("sonnet", msgs1, { configEpoch: "aaaa000011112222" });
+  const h2 = cacheHash("sonnet", msgs1, { configEpoch: "bbbb000011112222" });
+  assert.notEqual(h1, h2);
+});
+
+test("cacheHash: same configEpoch is stable; absent epoch hashes byte-identically to pre-#176", () => {
+  const e1 = cacheHash("sonnet", msgs1, { configEpoch: "aaaa000011112222" });
+  const e2 = cacheHash("sonnet", msgs1, { configEpoch: "aaaa000011112222" });
+  assert.equal(e1, e2);
+  // absent-epoch calls (older callers, all pre-existing tests) must not change behavior
+  assert.equal(cacheHash("sonnet", msgs1, {}), cacheHash("sonnet", msgs1));
+  assert.notEqual(e1, cacheHash("sonnet", msgs1), "epoch-carrying key differs from legacy key");
+});
+
 test("cacheHash includes max_tokens in hash", () => {
   const h1 = cacheHash("sonnet", msgs1, {});
   const h2 = cacheHash("sonnet", msgs1, { max_tokens: 100 });