clone/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-04-24 14:45:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

code_mode: document default exec token truncation limit

Browse Source
This commit is contained in:
pakrym-oai
2026-03-12 10:17:30 -07:00
parent 450befac37
commit cde541cc23
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
codex-rs/core/src/tools/code_mode/description.md
View File

@@ -13,6 +13,6 @@
- `store(key: string, value: any)`: stores a serializeable value under a string key for later `exec` calls in the same session.
- `load(key: stirng)`: returns the stored value for a string key, or `undefined` if it is missing.
- `set_max_output_tokens_per_exec_call(value)`: sets the token budget for direct `exec` results.
- `set_max_output_tokens_per_exec_call(value)`: sets the token budget for direct `exec` results. By default the result is trucated to 10000 tokens.
- `set_yield_time(value)`: asks `exec` to yield early after that many milliseconds if the script is still running.
- `yield_control()`: yields the accumulated output to the model immidiately while the script keeps running.