mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00

Files

T

gt-oai 5662eb8b75 Load exec policy rules from requirements (#10190 )

`requirements.toml` should be able to specify rules which always run. 

My intention here was that these rules could only ever be restrictive,
which means the decision can be "prompt" or "forbidden" but never
"allow". A requirement of "you must always allow this command" didn't
make sense to me, but happy to be gaveled otherwise.

Rules already applies the most restrictive decision, so we can safely
merge these with rules found in other config folders.

5662eb8b75 · 2026-01-30 18:04:09 +00:00

History

src

Load exec policy rules from requirements (#10190 )

2026-01-30 18:04:09 +00:00

templates

chore(personality) new schema with fallbacks (#10147 )

2026-01-30 00:10:12 -07:00

tests

fix: make sure the shell exists (#10222 )

2026-01-30 14:18:31 +01:00

BUILD.bazel

merge remote models (#9547 )

2026-01-20 14:02:07 -08:00

Cargo.toml

feat: sqlite 1 (#10004 )

2026-01-28 15:29:14 +01:00

config.schema.json

feat(app-server): support external auth mode (#10012 )

2026-01-29 23:46:04 +00:00

gpt_5_1_prompt.md

Assemble sandbox/approval/network prompts dynamically (#8961 )

2026-01-12 23:12:59 +00:00

gpt_5_2_prompt.md

Assemble sandbox/approval/network prompts dynamically (#8961 )

2026-01-12 23:12:59 +00:00

gpt_5_codex_prompt.md

Assemble sandbox/approval/network prompts dynamically (#8961 )

2026-01-12 23:12:59 +00:00

gpt-5.1-codex-max_prompt.md

Assemble sandbox/approval/network prompts dynamically (#8961 )

2026-01-12 23:12:59 +00:00

gpt-5.2-codex_prompt.md

Assemble sandbox/approval/network prompts dynamically (#8961 )

2026-01-12 23:12:59 +00:00

hierarchical_agents_message.md

Add hierarchical agent prompt (#8996 )

2026-01-09 13:47:37 -08:00

models.json

Update models.json (#9726 )

2026-01-23 00:44:47 +00:00

prompt_with_apply_patch_instructions.md

Assemble sandbox/approval/network prompts dynamically (#8961 )

2026-01-12 23:12:59 +00:00

prompt.md

Assemble sandbox/approval/network prompts dynamically (#8961 )

2026-01-12 23:12:59 +00:00

README.md

feat: add support for read-only bind mounts in the linux sandbox (#9112 )

2026-01-14 08:30:46 -08:00

review_prompt.md

docs: Fix markdown list item spacing in codex-rs/core/review_prompt.md (#4144 )

2025-10-30 17:39:21 -07:00

README.md

codex-core

This crate implements the business logic for Codex. It is designed to be used by the various Codex UIs written in Rust.

Dependencies

Note that codex-core makes some assumptions about certain helper utilities being available in the environment. Currently, this support matrix is:

macOS

Expects /usr/bin/sandbox-exec to be present.

When using the workspace-write sandbox policy, the Seatbelt profile allows writes under the configured writable roots while keeping .git (directory or pointer file), the resolved gitdir: target, and .codex read-only.

Linux

Expects the binary containing codex-core to run the equivalent of codex sandbox linux (legacy alias: codex debug landlock) when arg0 is codex-linux-sandbox. See the codex-arg0 crate for details.

All Platforms

Expects the binary containing codex-core to simulate the virtual apply_patch CLI when arg1 is --codex-run-as-apply-patch. See the codex-arg0 crate for details.