ARCHITECTURE DIAGRAM
CODEX / CLAUDE CODEOFFICIAL TYPESAFE SKILLWORKFLOW CODE + DOCS
Overview & Result
fast-jev-codex uses Jev to score tool history and lets the plugin restore verbatim context after Codex compacts a long session.
How Jev fits in the loop
- The plugin observes prior conversation and tool-call history.
- Jev judges which historical items remain useful for the current task.
- The plugin restores selected original text so Codex can continue with the preserved evidence.
How to reproduce
- Read the repository README and review how it hooks into Codex context handling.
- Run a deliberately long coding session containing tool calls, errors, and an important earlier constraint.
- Check whether the important context remains verbatim after compaction and record any omissions.
Why this build matters
It isolates a concrete failure mode of long-running coding agents: context compaction can be lossy even when the exact error or path matters.
Limitations
- The short post does not specify the scoring rubric or a retention benchmark.
- Context pruning can still remove information if the state representation or threshold is wrong.
- Treat the repository behavior as community observed until JevForAgents reproduces it.