Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

[Feature]: Keep a JEV combo on one target per session so provider prompt caches stay warm

Open
  • Is something wrong?
#7,525 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
45/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
typescript
Domain
backend-api-design

Research direction

Start with src/cli/combo.ts to see how combo options are parsed and where the current round-robin-only stickyLimit restriction is enforced. Then trace JEV target selection and the session key derivation, and inspect how decisions are recorded in usage data. Done means an opt-in session pin keeps a successful target for the configured duration or turns, breaks for the listed conditions, and exposes the pin decision while default behavior stays the same.

Written by the indexing model from the issue text.

Description

enhancement

What are you trying to accomplish?

Keep provider-side prompt caching effective when a strategy: jev combo (jev-auto) is used for long agent sessions. Today JEV re-decides the target on almost every request, so consecutive turns of one conversation land on different providers and each switch starts with a cold prompt cache.

What prevents this today?

  • JEV has no notion of session affinity. The only pinning knob, stickyLimit, is accepted only for strategy: round-robin (src/cli/combo.ts: --sticky applies only to round-robin).
  • Related but broader: #6665 (demand-level routing, per-session pinning). This issue is the narrow cache-stability case and can be satisfied by a plain per-session pin.

Observed on a single-operator hub, last 24 h, jev-auto usage ledger (aggregated, no request bodies):

JEV-selected target Requests Input tokens (M) Cache read / input
anthropic/claude-haiku-5-5 635 90.7 85%
google-antigravity/gemini-3.8-flash 412 56.2 90%
anthropic/claude-sonnet-5-5 135 21.8 78%
openai/gpt-6.1-sol 381 36.4 23%
openai/gpt-5.6-terra 251 17.4 18%

Six different targets appear within a single day. In the OPENCODEX_CACHE_DEBUG=1 fingerprints (171 records, 36 min), the first divergent block is instructions[0] in 117 of 171 records, so consecutive requests from the same client often diverge at the very start of the prefix. Part of that is a separate problem (see "Related observation" below), part is switching targets.

What should OpenCodex do?

  • Add a JEV combo option, for example stickyTurns / sessionPin (default off), that keeps the last successful target for a session key (caller prompt_cache_key, or the existing session derivation) for N turns or T minutes.
  • Break the pin only on: upstream error or 429 that exhausts retries, the target being removed or disabled, or the request exceeding that target's context window.
  • Expose the pin decision in the decision/usage record (jevDecision.pinned: true, pinReason) so the ledger shows it.
  • Default behaviour must stay exactly as today.

Example usage or interface

Proposed interface (does not exist today):

ocx combo set jev-auto --strategy jev --session-pin 20m --json

{ "id": "jev-auto", "strategy": "jev", "sessionPin": { "ttlMs": 1200000 } }

Alternatives or workarounds

  • Shrink the JEV target list to providers with high cache reuse. Works, but loses the cross-provider escalation JEV exists for.
  • Split combos per client so each combo's instructions prefix stays stable. Helps the instructions[0] divergence, does not fix target churn.

Related observation (separate, for triage)

Direct test through the hub, openai/gpt-6.1-sol, identical ~13.5k-token instructions repeated 3–4 times at 2 s and 20 s spacing, store: false:

  • with prompt_cache_key forwarded (verified inbound == outbound in the cache-debug record): cached_tokens = 0 on every request;
  • without the key: cached_tokens = 0 on every request;
  • all requests were served by the same pooled account.

So the forwarded key did not produce a hit in this run. It is unclear whether this is expected for pooled ChatGPT-backed accounts, or whether caching only engages for some accounts. Production shows partial OpenAI cache reads (18–33%), which suggests account-dependence. Happy to provide the exact request body and fingerprints on request; no keys included.

Related: #6665, #4546, #6520, #6627, #6481.

Dominant language
TypeScript
Stars
16.9k
Forks
1.3k
Avg merge
7h 46m
Merged PRs (30d)
638

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from lidge-jun/opencodex

All issues in lidge-jun/opencodex

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.