mirror of
https://github.com/dtzp555-max/ocp.git
synced 2026-07-19 09:44:07 +00:00
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
+36
-23
@@ -34,7 +34,7 @@ import { readFileSync, accessSync, existsSync, constants } from "node:fs";
|
||||
import { fileURLToPath } from "node:url";
|
||||
import { dirname, join } from "node:path";
|
||||
import { homedir } from "node:os";
|
||||
import { validateKey, recordUsage, getUsageByKey, getUsageTimeline, getRecentUsage, createKey, listKeys, revokeKey, closeDb, checkQuota, updateKeyQuota, getKeyQuota, findKey, cacheHash, getCachedResponse, setCachedResponse, clearCache, getCacheStats } from "./keys.mjs";
|
||||
import { validateKey, recordUsage, getUsageByKey, getUsageTimeline, getRecentUsage, createKey, listKeys, revokeKey, closeDb, checkQuota, updateKeyQuota, getKeyQuota, findKey, cacheHash, getCachedResponse, setCachedResponse, clearCache, getCacheStats, hasCacheControl } from "./keys.mjs";
|
||||
|
||||
const __dirname = dirname(fileURLToPath(import.meta.url));
|
||||
const _pkg = JSON.parse(readFileSync(join(__dirname, "package.json"), "utf8"));
|
||||
@@ -1218,30 +1218,43 @@ async function handleChatCompletions(req, res) {
|
||||
|
||||
// Cache check (only when cache is enabled and no active conversation/session)
|
||||
if (CACHE_TTL > 0 && !conversationId) {
|
||||
const hash = cacheHash(model, messages, { temperature: parsed.temperature, max_tokens: parsed.max_tokens, top_p: parsed.top_p });
|
||||
req._cacheHash = hash; // store for later write-back
|
||||
try {
|
||||
const cached = getCachedResponse(hash, CACHE_TTL);
|
||||
if (cached) {
|
||||
logEvent("info", "cache_hit", { model, hash: hash.slice(0, 12), hits: cached.hits });
|
||||
if (stream) {
|
||||
// Simulate streaming for cached response
|
||||
const id = `chatcmpl-${randomUUID()}`;
|
||||
const created = Math.floor(Date.now() / 1000);
|
||||
res.writeHead(200, { "Content-Type": "text/event-stream", "Cache-Control": "no-cache", "Connection": "keep-alive", "X-Accel-Buffering": "no" });
|
||||
sendSSE(res, { id, object: "chat.completion.chunk", created, model, choices: [{ index: 0, delta: { role: "assistant" }, finish_reason: null }] });
|
||||
sendSSE(res, { id, object: "chat.completion.chunk", created, model, choices: [{ index: 0, delta: { content: cached.response }, finish_reason: null }] });
|
||||
sendSSE(res, { id, object: "chat.completion.chunk", created, model, choices: [{ index: 0, delta: {}, finish_reason: "stop" }] });
|
||||
res.write("data: [DONE]\n\n");
|
||||
res.end();
|
||||
return;
|
||||
} else {
|
||||
const id = `chatcmpl-${randomUUID()}`;
|
||||
return completionResponse(res, id, model, cached.response);
|
||||
// D2: skip OCP cache entirely when messages carry cache_control annotations;
|
||||
// the client is requesting Anthropic-side prompt caching, not OCP-layer caching.
|
||||
if (hasCacheControl(messages)) {
|
||||
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)
|
||||
const hash = cacheHash(model, messages, { keyId: req._authKeyId, temperature: parsed.temperature, max_tokens: parsed.max_tokens, top_p: parsed.top_p });
|
||||
req._cacheHash = hash; // store for later write-back
|
||||
try {
|
||||
const cached = getCachedResponse(hash, CACHE_TTL);
|
||||
if (cached) {
|
||||
logEvent("info", "cache_hit", { model, hash: hash.slice(0, 12), hits: cached.hits });
|
||||
if (stream) {
|
||||
// D3: replay cached content as chunked SSE stream (80 codepoints/chunk)
|
||||
const CACHE_REPLAY_CHUNK_SIZE = 80;
|
||||
const id = `chatcmpl-${randomUUID()}`;
|
||||
const created = Math.floor(Date.now() / 1000);
|
||||
res.writeHead(200, { "Content-Type": "text/event-stream", "Cache-Control": "no-cache", "Connection": "keep-alive", "X-Accel-Buffering": "no" });
|
||||
sendSSE(res, { id, object: "chat.completion.chunk", created, model, choices: [{ index: 0, delta: { role: "assistant" }, finish_reason: null }] });
|
||||
const codepoints = Array.from(cached.response);
|
||||
for (let i = 0; i < codepoints.length; i += CACHE_REPLAY_CHUNK_SIZE) {
|
||||
const chunk = codepoints.slice(i, i + CACHE_REPLAY_CHUNK_SIZE).join("");
|
||||
sendSSE(res, { id, object: "chat.completion.chunk", created, model, choices: [{ index: 0, delta: { content: chunk }, finish_reason: null }] });
|
||||
}
|
||||
sendSSE(res, { id, object: "chat.completion.chunk", created, model, choices: [{ index: 0, delta: {}, finish_reason: "stop" }] });
|
||||
res.write("data: [DONE]\n\n");
|
||||
res.end();
|
||||
return;
|
||||
} else {
|
||||
const id = `chatcmpl-${randomUUID()}`;
|
||||
return completionResponse(res, id, model, cached.response);
|
||||
}
|
||||
}
|
||||
} catch (e) {
|
||||
logEvent("error", "cache_check_failed", { error: e.message });
|
||||
}
|
||||
} catch (e) {
|
||||
logEvent("error", "cache_check_failed", { error: e.message });
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user