OpenBMB / OpenBMB/PilotDeck

【BUG】router: cache-aware switching can block judge-requested tier upgrades

Open
#594 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
4k
Forks
453
Avg merge
12h 30m
Merged PRs (30d)
46

Description

Description

When automatic model selection and smart routing are enabled, a conversation can become stuck on the simple tier.

After an earlier request selects a simple model and gets a cache hit, later requests that require a stronger tier may still use the same simple model. The cache-aware switching logic compares costs without distinguishing between upgrades and downgrades. Since upgrading is normally more expensive, the previous cached model may keep winning the comparison.

The screenshot below shows three turns using the same simple model. The final request asks for in-depth research and a long report, but the router still keeps it on simple.

Image

Expected behavior

Cache cost should not prevent a judge-requested tier upgrade. It should only affect downgrade decisions.

Contributor guide

No contributing guide indexed for this repository

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.

Research direction

Start at the router's cache-aware switching logic and reproduce a conversation where a cached simple-model result is followed by a request requiring a stronger tier. Done means cache cost no longer blocks judge-requested upgrades while still influencing downgrade decisions.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai, backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
65/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.