mirror of
https://github.com/openai/codex.git
synced 2026-05-03 12:52:11 +03:00
01ab25dbb5
## Why This PR make the `morpheus` agent (memory phase 2) use a git diff to start it's consolidation. The workflow is the following: 1. The agent acquire a lock 2. If `.codex/memories` does not exist or is not a git root, initialize everything (and make a first empty commit) 3. Update `raw_memories.md` and `rollout_summaries/` as before. Basically we select max N phase 1 memories based on a given policy 4. We use git (`gix`) to get a diff between the current state of `.codex/memories` and the last commit. 5. Dump the diff in `phase2_workspace_diff.md` 6. Spawn `morpheus` and point it to `phase2_workspace_diff.md` 7. Wait for `morpheus` to be done 8. Re-create a new `.git` and make one single commit on it. We do this because we don't want to preserve history through `.git` and this is cheap anyway 9. We release the lock On top of this, we keep the retry policies etc etc The goals of this new workflow are: * Better support of any memory extensions such as `chronicle` * Allow the user to manually edit memories and this will be considered by the phase 2 agent As a follow-up we will need to add support for user's edition while `morpheus` is running ## What Changed - Added memory workspace helpers that prepare the git baseline, compute the diff, write `phase2_workspace_diff.md`, and reset the baseline after successful consolidation. - Updated Phase 2 to sync current inputs into `raw_memories.md` and `rollout_summaries/`, prune old extension resources, skip clean workspaces, and run the consolidation subagent only when the workspace has changes. - Tightened Phase 2 job ownership around long-running consolidation with heartbeats and an ownership check before resetting the baseline. - Simplified the prompt and state APIs so DB watermarks are bookkeeping, while workspace dirtiness decides whether consolidation work exists. - Updated the memory pipeline README and tests for workspace diffs, extension-resource cleanup, pollution-driven forgetting, selection ranking, and baseline persistence. ## Verification - Added/updated coverage in `core/src/memories/tests.rs`, `core/src/memories/workspace_tests.rs`, `state/src/runtime/memories.rs`, and `core/tests/suite/memories.rs`. --------- Co-authored-by: Codex <noreply@openai.com>
codex-git-utils
Helpers for interacting with git, including patch application and worktree
snapshot utilities. The crate also exposes a lightweight baseline API for
internal directories that use git only as a resettable diff mechanism:
ensure_git_baseline_repository preserves a usable root/.git baseline or
creates one when it is missing or unusable, reset_git_repository replaces
root/.git with a fresh one-commit baseline, and diff_since_latest_init
returns structured file changes plus a unified diff from that baseline to the
current directory contents.
use std::path::Path;
use codex_git_utils::{
apply_git_patch, create_ghost_commit, restore_ghost_commit, ApplyGitRequest,
CreateGhostCommitOptions,
};
let repo = Path::new("/path/to/repo");
// Apply a patch (omitted here) to the repository.
let request = ApplyGitRequest {
cwd: repo.to_path_buf(),
diff: String::from("...diff contents..."),
revert: false,
preflight: false,
};
let result = apply_git_patch(&request)?;
// Capture the current working tree as an unreferenced commit.
let ghost = create_ghost_commit(&CreateGhostCommitOptions::new(repo))?;
// Later, undo back to that state.
restore_ghost_commit(repo, &ghost)?;
Pass a custom message with .message("…") or force-include ignored files with
.force_include(["ignored.log".into()]).