Persist js_repl codex helpers across cells (#14503)

## Summary

This changes `js_repl` so saved references to `codex.tool(...)` and
`codex.emitImage(...)` keep working across cells.

Previously, those helpers were recreated per exec and captured that
exec's `message.id`. If a persisted object or saved closure reused an
old helper in a later cell, the nested tool/image call could fail with
`js_repl exec context not found`.

This patch:
- keeps stable `codex.tool` and `codex.emitImage` helper identities in
the kernel
- resolves the current exec dynamically at call time using
`AsyncLocalStorage`
- adds regression coverage for persisted helper references across cells
- updates the js_repl docs and project-doc instructions to describe the
new behavior and its limits

## Why

We already support persistent top-level bindings across `js_repl` cells,
so persisted objects should be able to reuse `codex` helpers in later
active cells. The bug was that helper identity was exec-scoped, not
kernel-scoped.

Using `AsyncLocalStorage` fixes the cross-cell reuse case without
falling back to a single global active exec that could accidentally
attribute stale background callbacks to the wrong cell.
This commit is contained in:
Curtis 'Fjord' Hawthorne
2026-03-12 15:41:54 -07:00
committed by GitHub
Unverified
parent a314c7d3ae
commit b560494c9f
5 changed files with 276 additions and 66 deletions
+1
View File
@@ -79,6 +79,7 @@ imported local file. They are not resolved relative to the imported file's locat
- `codex.tmpDir`: per-session scratch directory path.
- `codex.tool(name, args?)`: executes a normal Codex tool call from inside `js_repl` (including shell tools like `shell` / `shell_command` when available).
- `codex.emitImage(imageLike)`: explicitly adds one image to the outer `js_repl` function output each time you call it.
- `codex.tool(...)` and `codex.emitImage(...)` keep stable helper identities across cells. Saved references and persisted objects can reuse them in later cells, but async callbacks that fire after a cell finishes still fail because no exec is active.
- Imported local files run in the same VM context, so they can also access `codex.*`, the captured `console`, and Node-like `import.meta` helpers.
- Each `codex.tool(...)` call emits a bounded summary at `info` level from the `codex_core::tools::js_repl` logger. At `trace` level, the same path also logs the exact raw response object or error string seen by JavaScript.
- Nested `codex.tool(...)` outputs stay inside JavaScript unless you emit them explicitly.