feat(cache): per-key isolation, cache_control bypass, chunked stream replay (#65)

* docs(governance): ADR 0005 (no multi-provider) + cache upgrade spec

Governance prelude for the cache upgrade work:

- docs/adr/0005-no-multi-provider.md — locks in the decision that
  OCP stays single-provider (Anthropic via cli.js spawn). Cache
  improvements are explicitly in scope (decision §3); multi-provider
  refactor is explicitly out of scope, with three documented trigger
  conditions for revisiting.

- docs/adr/README.md — index updated to reference 0005.

- docs/superpowers/specs/2026-05-07-cache-upgrade-design.md — design
  for the cache upgrade work split into PR-A (per-key isolation,
  cache_control bypass, chunked stream replay) and PR-B (singleflight
  stampede protection). Each design decision has a written rationale.

server.mjs is not modified; this commit is doc-only and therefore
exempt from the cli.js citation requirement (ALIGNMENT.md Rule 5
applies only to commits that touch server.mjs).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(cache): per-key isolation, cache_control bypass, chunked stream replay

cli.js does not perform response caching at the proxy layer. OCP's response
cache is a value-add operation internal to OCP, between the wire and the
cli.js spawn. It does not introduce, rename, or alter any endpoint, header,
request field, or response field that cli.js emits or expects — this change
qualifies under ALIGNMENT.md Rule 2's value-add carve-out for non-wire-
affecting proxy operations. no client-observable wire shape change.

Spec: docs/superpowers/specs/2026-05-07-cache-upgrade-design.md

D1 — Per-key cache isolation (cacheHash v2 format)
  keys.mjs: prepend `v2|k:<keyId or "anon">|` before existing hash fields.
  Backward-compatible: absent/null/empty keyId folds to "anon".
  v1-format rows in response_cache are abandoned naturally; TTL cleanup at
  server.mjs:185 reaps them within one window. No migration needed.
  server.mjs: pass keyId: req._authKeyId at the single cacheHash call site
  (line ~1221).

D2 — cache_control bypass
  keys.mjs: export hasCacheControl(messages) — walks messages and nested
  content arrays for presence of cache_control field.
  server.mjs: if hasCacheControl(messages) is true, set req._cacheHash = null
  and log cache_skipped{reason: cache_control_present}; existing
  `if (CACHE_TTL > 0 && req._cacheHash)` guards on write-back handle the skip.

D3 — Chunked stream replay (80 codepoints/chunk, no artificial delay)
  server.mjs: replace single-chunk cached.response emission with an
  Array.from(cached.response) loop in steps of CACHE_REPLAY_CHUNK_SIZE=80.
  Array.from ensures multibyte UTF-8 codepoints (e.g. CJK) are never split.

Tests: 12 new cases in test-features.mjs (36 total, 0 failed).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: dtzp555 <dtzp555@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
dtzp555-max
2026-05-07 13:50:50 +10:00
committed by GitHub
co-authored by taodeng Claude Opus 4.7
parent c998d21a4f
commit 16eeb66557
6 changed files with 386 additions and 25 deletions
+102 -1
View File
@@ -3,7 +3,8 @@
* Integration test for Quota + Cache features.
* Tests database layer functions directly — no server needed.
*/
import { getDb, createKey, listKeys, validateKey, recordUsage, checkQuota, updateKeyQuota, getKeyQuota, findKey, cacheHash, getCachedResponse, setCachedResponse, clearCache, getCacheStats, closeDb } from "./keys.mjs";
import { getDb, createKey, listKeys, validateKey, recordUsage, checkQuota, updateKeyQuota, getKeyQuota, findKey, cacheHash, getCachedResponse, setCachedResponse, clearCache, getCacheStats, closeDb, hasCacheControl } from "./keys.mjs";
import { createHash } from "node:crypto";
import { strict as assert } from "node:assert";
import { unlinkSync } from "node:fs";
import { join } from "node:path";
@@ -253,6 +254,106 @@ test("clearCache with TTL only removes old entries", () => {
clearCache();
});
// ── PR-A: Per-key isolation (D1), cache_control bypass (D2), chunked replay (D3) ──
console.log("\nPR-A Cache Upgrade:");
const msgsBase = [{ role: "user", content: "Shared prompt text" }];
test("D1: cacheHash with two distinct keyIds produces different hashes", () => {
const h1 = cacheHash("sonnet", msgsBase, { keyId: "key-aaa" });
const h2 = cacheHash("sonnet", msgsBase, { keyId: "key-bbb" });
assert.notEqual(h1, h2);
});
test("D1: cacheHash with keyId=undefined and keyId='anon' produce the same hash", () => {
const hUndef = cacheHash("sonnet", msgsBase, { keyId: undefined });
const hAnon = cacheHash("sonnet", msgsBase, { keyId: "anon" });
assert.equal(hUndef, hAnon);
});
test("D1: cacheHash with keyId=null and keyId='anon' produce the same hash", () => {
const hNull = cacheHash("sonnet", msgsBase, { keyId: null });
const hAnon = cacheHash("sonnet", msgsBase, { keyId: "anon" });
assert.equal(hNull, hAnon);
});
test("D1: v2 prefix — hash differs from a v1-style baseline (no prefix)", () => {
// Reproduce a v1-style hash manually to confirm v2 differs
const v1 = createHash("sha256")
.update("sonnet")
.update(msgsBase[0].role)
.update(msgsBase[0].content)
.digest("hex");
const v2 = cacheHash("sonnet", msgsBase, { keyId: "anon" });
assert.notEqual(v1, v2);
});
test("D1: cacheHash is reproducible for same keyId (determinism)", () => {
const h1 = cacheHash("sonnet", msgsBase, { keyId: "key-xyz" });
const h2 = cacheHash("sonnet", msgsBase, { keyId: "key-xyz" });
assert.equal(h1, h2);
});
test("D2: hasCacheControl returns true for top-level cache_control on message", () => {
const msgs = [{ role: "user", cache_control: { type: "ephemeral" }, content: "hello" }];
assert.equal(hasCacheControl(msgs), true);
});
test("D2: hasCacheControl returns true for nested cache_control in content array", () => {
const msgs = [{ role: "user", content: [{ type: "text", text: "x", cache_control: { type: "ephemeral" } }] }];
assert.equal(hasCacheControl(msgs), true);
});
test("D2: hasCacheControl returns false for plain string content", () => {
const msgs = [{ role: "user", content: "plain string" }];
assert.equal(hasCacheControl(msgs), false);
});
test("D2: hasCacheControl returns false for content array without cache_control", () => {
const msgs = [{ role: "user", content: [{ type: "text", text: "x" }] }];
assert.equal(hasCacheControl(msgs), false);
});
test("D2: hasCacheControl handles null/empty input gracefully", () => {
assert.equal(hasCacheControl(null), false);
assert.equal(hasCacheControl([]), false);
assert.equal(hasCacheControl([null, undefined]), false);
});
// D3: chunked stream replay — verify the logic by simulating what server.mjs does
test("D3: 160-char cached response produces 2 chunks at 80 codepoints/chunk", () => {
const content = "a".repeat(160);
const CACHE_REPLAY_CHUNK_SIZE = 80;
const codepoints = Array.from(content);
const chunks = [];
for (let i = 0; i < codepoints.length; i += CACHE_REPLAY_CHUNK_SIZE) {
chunks.push(codepoints.slice(i, i + CACHE_REPLAY_CHUNK_SIZE).join(""));
}
assert.equal(chunks.length, 2);
assert.equal(chunks[0].length, 80);
assert.equal(chunks[1].length, 80);
});
test("D3: chunked replay uses Array.from — multibyte codepoints stay intact", () => {
// Each Chinese character is 1 codepoint but 3 UTF-8 bytes
const chinese = "你好世界".repeat(25); // 100 codepoints
const CACHE_REPLAY_CHUNK_SIZE = 80;
const codepoints = Array.from(chinese);
const chunks = [];
for (let i = 0; i < codepoints.length; i += CACHE_REPLAY_CHUNK_SIZE) {
chunks.push(codepoints.slice(i, i + CACHE_REPLAY_CHUNK_SIZE).join(""));
}
assert.equal(chunks.length, 2);
assert.equal(Array.from(chunks[0]).length, 80);
assert.equal(Array.from(chunks[1]).length, 20);
// Verify each character is a complete codepoint (no mojibake)
for (const chunk of chunks) {
for (const cp of Array.from(chunk)) {
assert.equal(cp.length <= 2, true); // surrogate pairs are length 2, single chars length 1
}
}
});
// ── Cleanup ──
closeDb();