@just-every/code 0.6.66 → 0.6.68

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +20 -1
  2. package/package.json +6 -6
package/README.md CHANGED
@@ -5,7 +5,26 @@
5
5
  **Every Code** (Code for short) is a fast, local coding agent for your terminal. It's a community-driven fork of `openai/codex` focused on real developer ergonomics: Browser integration, multi-agents, theming, and reasoning control — all while staying compatible with upstream.
6
6
 
7
7
   
8
- ## What's new in v0.6.0 (December 2025)
8
+ ## What's new
9
+
10
+ - **Latest long-session stability sweep** (post-0.6): Auto Drive and Auto Review are now decoupled so background reviews no longer block the command flow. `Esc` returns control immediately and typing works while review finalization continues.
11
+
12
+ - **Operational upgrades in this cycle**
13
+ - Auto Review metadata (branch/worktree context) remains queryable through the active Auto Drive session after completion.
14
+ - Terminal agents are compacted and archived so heavy payloads are reduced while review linkage is preserved.
15
+ - Core `core`, coordinator, and TUI state maps now have hard caps with bounded drop/trim behavior.
16
+ - Auto Drive conversation/update queues are bounded in the coordinator; TUI has bounded prompt/agent/runtime caches.
17
+ - Background review notes are added as non-blocking history-visible notes instead of foreground task-injection.
18
+ - TUI housekeeping lifecycle is bounded with deterministic stop control.
19
+ - Stress tests now cover heavy agent churn plus concurrent Auto Review + Esc/typing responsiveness.
20
+
21
+ - **New/updated models and agents**
22
+ - Auto Drive CLI model support includes `gpt-5.3-codex` (planning/problem-solving) and `gpt-5.3-codex-spark` (fast coding/fix loops), with `medium | high | xhigh` reasoning controls.
23
+ - Frontline and alias-aware agent model handling now includes `code-gpt-5.3-codex` and `code-gpt-5.3-codex-spark`, with compatibility alias upgrades for `gpt-5.1-codex`, `gpt-5.1-codex-mini`, `gpt-5.2-codex`, etc.
24
+ - Auto Drive decision schema and coordinator payloads now enforce bounded history while preserving goal and recent context.
25
+
26
+ See commit `60727b068` and related Auto Drive hardening commits in git history for details.
27
+
9
28
 
10
29
  - **Auto Review** – background ghost-commit watcher runs reviews in a separate worktree whenever a turn changes code; uses `codex-5.1-mini-high` and reports issues plus ready-to-apply fixes without blocking the main thread.
11
30
  - **Code Bridge** – Sentry-style local bridge that streams errors, console, screenshots, and control from running apps into Code; ships an MCP server; install by asking Code to pull `https://github.com/just-every/code-bridge`.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@just-every/code",
3
- "version": "0.6.66",
3
+ "version": "0.6.68",
4
4
  "license": "Apache-2.0",
5
5
  "description": "Lightweight coding agent that runs in your terminal - fork of OpenAI Codex",
6
6
  "bin": {
@@ -35,10 +35,10 @@
35
35
  "prettier": "^3.3.3"
36
36
  },
37
37
  "optionalDependencies": {
38
- "@just-every/code-darwin-arm64": "0.6.66",
39
- "@just-every/code-darwin-x64": "0.6.66",
40
- "@just-every/code-linux-x64-musl": "0.6.66",
41
- "@just-every/code-linux-arm64-musl": "0.6.66",
42
- "@just-every/code-win32-x64": "0.6.66"
38
+ "@just-every/code-darwin-arm64": "0.6.68",
39
+ "@just-every/code-darwin-x64": "0.6.68",
40
+ "@just-every/code-linux-x64-musl": "0.6.68",
41
+ "@just-every/code-linux-arm64-musl": "0.6.68",
42
+ "@just-every/code-win32-x64": "0.6.68"
43
43
  }
44
44
  }