mirror of
https://github.com/openai/codex.git
synced 2026-10-31 19:28:49 +00:00
felixxia-oai
624b45c4dc
## Why A conversation classifier waiting for preparation or full response completion can block newer classifications. Concurrent reviews also need to prevent a later action's evidence or low-risk score from being reused for an earlier action. ## What changed - Run conversation classifications independently, forking the latest compatible completed history from an earlier action. Only a valid completion with a newer action index can replace retained history. - Keep admission and observation ordering atomic, and hold capacity permits through full response completion. - Reject cached low-risk scores from later actions for tool-linked approvals, including initial approval checks. - Track originating tool-call IDs separately from approval display IDs, preserving stdin write provenance and excluding synthetic MCP elicitation IDs from tool ordering. ## Testing Add regression coverage for delayed preparation, capacity admission, out-of-order completion, cancellation, invalid retained output, and history snapshots. Exercise pending approval ordering in both `snapshot` and `conversation` modes, and verify linked and unlinked MCP elicitation provenance. GitOrigin-RevId: 097476ccb3b8718369a69f55c3c39132f7f1a4c1
15 lines
453 B
Python
15 lines
453 B
Python
load("//:defs.bzl", "codex_rust_crate")
|
|
|
|
# Core's context-adapter unit tests compile the same setup function with their Config type.
|
|
exports_files(
|
|
["src/sync_reviewer/reviewer_config.rs"],
|
|
visibility = ["//codex-rs/core:__pkg__"],
|
|
)
|
|
|
|
codex_rust_crate(
|
|
name = "guardian-v2",
|
|
crate_name = "codex_guardian_v2",
|
|
extra_binaries = ["//codex-rs/code-mode-host:codex-code-mode-host"],
|
|
test_data_extra = glob(["src/**/snapshots/**"]),
|
|
)
|