jeo-code 0.7.13 → 0.7.15

package/CHANGELOG.md

@@ -6,6 +6,26 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 The README mirrors the latest 5 entries — regenerate with `bun run changelog:sync`.
 
+
+## [0.7.15] - 2026-06-25
+_Rollback release: the runtime source and test suite are restored to the **0.7.9** state. The intervening 0.7.10–0.7.14 runtime changes (quiet-mode/`-q`, `/resume` transcript rework, `mutatedFiles` plumbing, Ollama `num_ctx`, tmux REPL reaping, and related engine/provider/TUI edits) are reverted. Published as a new version because npm cannot re-issue an existing version number; `latest` now serves code identical to 0.7.9._
+
+### Changed
+- **`src/` and `test/` reverted to the v0.7.9 tree.** Every runtime and test file is byte-identical to the `v0.7.9` tag; the post-0.7.9 test `test/mutated-files-artifacts.test.ts` is removed along with the feature it covered.
+
+### Notes
+- Release tooling (`scripts/ci-release-build-binaries.ts`, keeping the `bun-darwin-x64-baseline` target for older-CPU compatibility) and documentation history (this CHANGELOG, READMEs) are intentionally **not** rolled back, since they are not part of the user-facing runtime and reverting them would regress binary compatibility or erase the record of what was shipped.
+
+## [0.7.14] - 2026-06-25
+_Quieter, cleaner output: a new `-q`/`--quiet` flag strips launch banners and courtesy logs, `/resume` no longer dumps walls of raw escaped JSON into scrollback, and a turn that edits files now reliably surfaces those paths to orchestrators._
+
+### Added
+- **`-q`/`--quiet` suppresses startup chrome.** `jeo launch -q` (and one-shot `-p`) skips the welcome box, the "what's new" release notes, the `(plain output)` / resume-hint footers, and the background "session memory distilling" line — so piped, CI, and minimal-terminal runs get just the agent's output instead of the full interactive banner set. The flag is wired through the runner (`-q`/`--quiet` help + launch-only flag set) and `parseFlags`.
+
+### Fixed
+- **`/resume` no longer renders a wall of raw escaped JSON.** The transcript formatter extracts an embedded tool call from anywhere in an assistant message (mirroring the engine's own `extractJsonObject`) instead of only when the content begins with `{`, and distinguishes a genuine prose-prefixed call (followed by its `Tool [x] result`) from an illustrative JSON snippet quoted inside prose. Pre-call narration is kept (dimmed) and a leading `"reasoning"` field is surfaced clipped; the raw multi-line edit/write payloads never reach scrollback.
+- **A turn that actually edits files now surfaces those paths, fixing the orchestrator "Agent finished but made zero valid code changes (finalArtifacts is empty)" failure.** `runAgentLoop` records every file a turn SUCCESSFULLY writes/edits and returns it as `AgentLoopResult.mutatedFiles` (repo-relative, sorted, de-duped; omitted when nothing mutated). The `task` subagent (`src/agent/task-tool.ts`) and the `team` executor (`src/commands/team.ts`) now derive their change set from this concrete list instead of an out-of-band tool counter, append a "Changed files (N): …" note to the subagent report, and base the parent UNVERIFIED/verify-independently audit on it — so a caller (or an external orchestrator like jeo-claw) collects the run's real code artifacts rather than inferring an empty change set after real edits. `.specify/` is also un-ignored in `.gitignore` so spec/plan artifacts written there are visible to a git-based artifact collector.
+
 ## [0.7.9] - 2026-06-24
 _Local model providers actually run, and OAuth/login hygiene: Ollama requests now carry an explicit `num_ctx` so jeo's large system prompt no longer overflows Ollama's small default window (the "ollama 모델이 안 돌아간다" blocker), LM Studio reasoning models that emit the whole reply on the reasoning channel are recovered instead of dying empty, GGUF chat templates that can't render the `tools` array are retried with native tools stripped, the OAuth success tab auto-closes with a clear hint, the effective-credential picker prefers a verified OAuth login over a stray API key, and abandoned idle `jeo` tmux REPL sessions are reaped on launch._
 

package/README.ja.md

@@ -149,6 +149,18 @@ jeo ultragoal
 `jeo` は `.jeo/memory/` 配下に **ローカルファースト・蒸留されたプロジェクトメモリ** を保持します(リモートバックエンドなし、ネイティブ依存ゼロ)。過去のセッションは [OKF](docs/okf_mem/) コンセプトバンドルへ蒸留され、次のセッションは関連性の高い予算内のスライスだけをシステムプロンプトへ再注入します — 指示ではなく DATA として堅牢化されます。`JEO_NO_MEMORY=1` ですべて無効化。
 
 **移行(`jeo memory-migrate`、ワンショット・冪等).** レガシーの単一ドキュメント `MEMORY.md` をロスレスでバンドルへ変換します: `## 見出し → タイプ`、各箇条書き → タイプ別コンセプト、インデント行 → 本文; `index.md`/`log.md` を再構築し、元ファイルを `MEMORY.md.bak` にリネームします。バンドルにコンセプトができた後の再実行は no-op です。**ロールバック:** `JEO_MEMORY_LEGACY=1` はバンドルを無視し、同じ注入堅牢化を通して `MEMORY.md`/`.bak` を読みます(`JEO_NO_MEMORY=1` がすべてに優先)。
+## 既存のエージェントやボットとの連携 (Works beside your existing agent or bot)
+
+| ツールまたはボット | 推奨される jeo コマンド | 境界 |
+| ----------- | ----------------------- | -------- |
+| Codex CLI | `jeo --tmux` または `jeo` | 兄弟 tmux セッションまたはインラインで実行されます。 |
+| Claude Code | `jeo --tmux` または `jeo` | jeo は Claude Code の拡張機能にはなりません。 |
+| OpenCode | `jeo` または `jeo --tmux` | 外部ランナーのワークフローのみ。 |
+| Claw Code | `jeo --tmux` | jeo は Claw Code にインストールされたり、置き換えたりしません。 |
+| 外部コントローラー / ボット | `jeo` (またはカスタム統合) | 外部コントローラーは、標準のターミナル/CLI インターフェースを介して jeo を駆動します。 |
+
+`-q`/`--quiet` (または `JEO_QUIET=1`) を追加すると、起動バナー・ウェルカムアニメーション・リリースノート・再開ヒントが抑制され、jeo を別のエージェントと並べて実行したりボットから駆動したりできます。`-p`/`--print` は quiet を含みます。
+
 
 ## ローカルモデル
 
@@ -193,11 +205,11 @@ CI は `.github/workflows/npm-publish.yml` で公開します — GitHub リリ
 ## 変更履歴 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.7.15]** (2026-06-25) — Rollback release: the runtime source and test suite are restored to the **0.7.9** state. The intervening 0.7.10–0.7.14 runtime changes (quiet-mode/`-q`, `/resume` transcript rework, `mutatedFiles` plumbing, Ollama `num_ctx`, tmux REPL reaping, and related engine/provider/TUI edits) are reverted. Published as a new version because npm cannot re-issue an existing version number; `latest` now serves code identical to 0.7.9.
+- **[0.7.14]** (2026-06-25) — Quieter, cleaner output: a new `-q`/`--quiet` flag strips launch banners and courtesy logs, `/resume` no longer dumps walls of raw escaped JSON into scrollback, and a turn that edits files now reliably surfaces those paths to orchestrators.
 - **[0.7.9]** (2026-06-24) — Local model providers actually run, and OAuth/login hygiene: Ollama requests now carry an explicit `num_ctx` so jeo's large system prompt no longer overflows Ollama's small default window (the "ollama 모델이 안 돌아간다" blocker), LM Studio reasoning models that emit the whole reply on the reasoning channel are recovered instead of dying empty, GGUF chat templates that can't render the `tools` array are retried with native tools stripped, the OAuth success tab auto-closes with a clear hint, the effective-credential picker prefers a verified OAuth login over a stray API key, and abandoned idle `jeo` tmux REPL sessions are reaped on launch.
 - **[0.7.8]** (2026-06-24) — Long-session performance & resource hygiene: the detached memory-distill worker now always terminates itself (closing the `jeo memory-distill` orphan pileup that pinned each session's transcript in RSS), the live reasoning/output block re-wraps only its trailing window (O(tail) per frame instead of O(len²) over a long stream), the team loop stops reprinting the todo guide every iteration, and the readline caret stays aligned after an image attach.
 - **[0.7.7]** (2026-06-23) — Long-running-process hygiene & input robustness: backgrounded grandchildren (`next dev &`, daemons) are now reaped at the turn boundary via per-command process groups — closing the climbing `next-server` RSS leak — while the prompt gains recursive fuzzy `@path` search, ANSI-safe and idle-merged bracketed paste, a configurable OSC 52 clipboard cap, per-role ralplan model routing, and leaked-reasoning-tag stripping on salvaged answers.
-- **[0.7.6]** (2026-06-23) — Release & docs plumbing: the running version's release notes now travel inside the `--compile` single binary (so `/whats-new` works offline and from a global install), the in-TUI markdown table renderer stops splitting on escaped `\|` pipes, and the release pipeline gains a cross-compiled standalone-binary matrix — macOS/Linux **plus a first-class Windows x64 `.exe`** — built on one Linux runner and auto-attached to each GitHub release.
-- **[0.7.5]** (2026-06-23) — Startup & loop latency: redundant re-reads that fired on every subagent spawn and every loop step are now memoized behind cheap `stat`-signature caches, so cold paths stay correct (edits/deletes still picked up immediately) while warm paths skip the disk and the re-parse. Targets the per-turn and per-spawn overhead that dominates perceived slowness in team/ralph/autopilot fan-outs.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.ko.md

@@ -149,6 +149,18 @@ jeo ultragoal
 `jeo`는 `.jeo/memory/` 아래에 **로컬 우선·증류된 프로젝트 메모리**를 둡니다(원격 백엔드 없음, 네이티브 의존성 0). 지난 세션은 [OKF](docs/okf_mem/) 개념 번들로 증류되고, 다음 세션은 관련성 높은 예산 한도 내 일부만 시스템 프롬프트로 다시 주입합니다 — 지시가 아닌 DATA로 강화 처리됩니다. `JEO_NO_MEMORY=1`로 전체 비활성화.
 
 **마이그레이션 (`jeo memory-migrate`, 1회성 · 멱등).** 레거시 단일 문서 `MEMORY.md`를 무손실로 번들로 변환합니다: `## 헤딩 → 타입`, 각 불릿 → 타입별 개념, 들여쓴 줄 → 본문; `index.md`/`log.md`를 재생성하고 원본은 `MEMORY.md.bak`으로 이름을 바꿉니다. 번들에 개념이 생긴 뒤 재실행은 no-op입니다. **롤백:** `JEO_MEMORY_LEGACY=1`은 번들을 무시하고 동일한 주입 강화 처리로 `MEMORY.md`/`.bak`를 읽습니다(`JEO_NO_MEMORY=1`이 모든 것에 우선).
+## 기존 에이전트 또는 봇과 함께 작동 (Works beside your existing agent or bot)
+
+| 도구 또는 봇 | 권장 jeo 명령 | 경계 |
+| ----------- | ----------------------- | -------- |
+| Codex CLI | `jeo --tmux` 또는 `jeo` | 형제 tmux 세션 또는 인라인으로 실행됩니다. |
+| Claude Code | `jeo --tmux` 또는 `jeo` | jeo는 Claude Code 확장 프로그램이 되지 않습니다. |
+| OpenCode | `jeo` 또는 `jeo --tmux` | 현재는 외부 러너 워크플로만 지원합니다. |
+| Claw Code | `jeo --tmux` | jeo는 Claw Code에 설치되거나 대체되지 않습니다. |
+| 외부 컨트롤러 / 봇 | `jeo` (또는 사용자 정의 통합) | 외부 컨트롤러는 표준 터미널/CLI 인터페이스를 통해 jeo를 구동합니다. |
+
+`-q`/`--quiet` (또는 `JEO_QUIET=1`)를 추가하면 시작 배너, 환영 애니메이션, 릴리스 노트, 재개 힌트가 억제되어 jeo를 다른 에이전트와 나란히 실행하거나 봇으로 구동할 수 있습니다. `-p`/`--print`는 quiet를 함의합니다.
+
 
 ## 로컬 모델
 
@@ -193,11 +205,11 @@ CI는 `.github/workflows/npm-publish.yml`로 배포합니다 — GitHub 릴리
 ## 변경 이력 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.7.15]** (2026-06-25) — Rollback release: the runtime source and test suite are restored to the **0.7.9** state. The intervening 0.7.10–0.7.14 runtime changes (quiet-mode/`-q`, `/resume` transcript rework, `mutatedFiles` plumbing, Ollama `num_ctx`, tmux REPL reaping, and related engine/provider/TUI edits) are reverted. Published as a new version because npm cannot re-issue an existing version number; `latest` now serves code identical to 0.7.9.
+- **[0.7.14]** (2026-06-25) — Quieter, cleaner output: a new `-q`/`--quiet` flag strips launch banners and courtesy logs, `/resume` no longer dumps walls of raw escaped JSON into scrollback, and a turn that edits files now reliably surfaces those paths to orchestrators.
 - **[0.7.9]** (2026-06-24) — Local model providers actually run, and OAuth/login hygiene: Ollama requests now carry an explicit `num_ctx` so jeo's large system prompt no longer overflows Ollama's small default window (the "ollama 모델이 안 돌아간다" blocker), LM Studio reasoning models that emit the whole reply on the reasoning channel are recovered instead of dying empty, GGUF chat templates that can't render the `tools` array are retried with native tools stripped, the OAuth success tab auto-closes with a clear hint, the effective-credential picker prefers a verified OAuth login over a stray API key, and abandoned idle `jeo` tmux REPL sessions are reaped on launch.
 - **[0.7.8]** (2026-06-24) — Long-session performance & resource hygiene: the detached memory-distill worker now always terminates itself (closing the `jeo memory-distill` orphan pileup that pinned each session's transcript in RSS), the live reasoning/output block re-wraps only its trailing window (O(tail) per frame instead of O(len²) over a long stream), the team loop stops reprinting the todo guide every iteration, and the readline caret stays aligned after an image attach.
 - **[0.7.7]** (2026-06-23) — Long-running-process hygiene & input robustness: backgrounded grandchildren (`next dev &`, daemons) are now reaped at the turn boundary via per-command process groups — closing the climbing `next-server` RSS leak — while the prompt gains recursive fuzzy `@path` search, ANSI-safe and idle-merged bracketed paste, a configurable OSC 52 clipboard cap, per-role ralplan model routing, and leaked-reasoning-tag stripping on salvaged answers.
-- **[0.7.6]** (2026-06-23) — Release & docs plumbing: the running version's release notes now travel inside the `--compile` single binary (so `/whats-new` works offline and from a global install), the in-TUI markdown table renderer stops splitting on escaped `\|` pipes, and the release pipeline gains a cross-compiled standalone-binary matrix — macOS/Linux **plus a first-class Windows x64 `.exe`** — built on one Linux runner and auto-attached to each GitHub release.
-- **[0.7.5]** (2026-06-23) — Startup & loop latency: redundant re-reads that fired on every subagent spawn and every loop step are now memoized behind cheap `stat`-signature caches, so cold paths stay correct (edits/deletes still picked up immediately) while warm paths skip the disk and the re-parse. Targets the per-turn and per-spawn overhead that dominates perceived slowness in team/ralph/autopilot fan-outs.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.md

@@ -150,6 +150,18 @@ Non-zero hook output is appended to the tool result the model reads (deduped per
 `jeo` keeps a **local-first, distilled project memory** under `.jeo/memory/` (no remote backend, zero native deps). Past sessions are distilled into an [OKF](docs/okf_mem/) concept bundle, and the next session injects only the relevant, budget-bounded slice back into the system prompt — hardened as DATA, never as instructions. Disable everything with `JEO_NO_MEMORY=1`.
 
 **Migration (`jeo memory-migrate`, one-shot · idempotent).** A legacy single-doc `MEMORY.md` is converted losslessly into the bundle: `## heading → type`, each bullet → a typed concept, indented lines → body; `index.md`/`log.md` are rebuilt and the original is renamed to `MEMORY.md.bak`. Re-running is a no-op once the bundle has concepts. **Rollback:** `JEO_MEMORY_LEGACY=1` ignores the bundle and reads `MEMORY.md`/`.bak` through the same injection-hardening (`JEO_NO_MEMORY=1` still wins over everything).
+## Works beside your existing agent or bot
+
+| Tool or bot | Recommended jeo command | Boundary |
+| ----------- | ----------------------- | -------- |
+| Codex CLI | `jeo --tmux` or `jeo` | Runs in a sibling tmux session or inline. |
+| Claude Code | `jeo --tmux` or `jeo` | jeo does not become a Claude Code extension. |
+| OpenCode | `jeo` or `jeo --tmux` | External-runner workflow only. |
+| Claw Code | `jeo --tmux` | jeo does not install into or replace Claw Code. |
+| External controller / bot | `jeo` (or custom integrations) | External controllers drive jeo through standard terminal/CLI interfaces. |
+
+Add `-q`/`--quiet` (or `JEO_QUIET=1`) to suppress startup banners, welcome animation, release notes, and resume hints so jeo can run cleanly beside another agent or be driven by a bot. `-p`/`--print` implies quiet.
+
 
 ## Local models
 
@@ -195,11 +207,11 @@ Huge thanks to [gajae-code](https://github.com/Yeachan-Heo/gajae-code) for the i
 ## Changelog
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.7.15]** (2026-06-25) — Rollback release: the runtime source and test suite are restored to the **0.7.9** state. The intervening 0.7.10–0.7.14 runtime changes (quiet-mode/`-q`, `/resume` transcript rework, `mutatedFiles` plumbing, Ollama `num_ctx`, tmux REPL reaping, and related engine/provider/TUI edits) are reverted. Published as a new version because npm cannot re-issue an existing version number; `latest` now serves code identical to 0.7.9.
+- **[0.7.14]** (2026-06-25) — Quieter, cleaner output: a new `-q`/`--quiet` flag strips launch banners and courtesy logs, `/resume` no longer dumps walls of raw escaped JSON into scrollback, and a turn that edits files now reliably surfaces those paths to orchestrators.
 - **[0.7.9]** (2026-06-24) — Local model providers actually run, and OAuth/login hygiene: Ollama requests now carry an explicit `num_ctx` so jeo's large system prompt no longer overflows Ollama's small default window (the "ollama 모델이 안 돌아간다" blocker), LM Studio reasoning models that emit the whole reply on the reasoning channel are recovered instead of dying empty, GGUF chat templates that can't render the `tools` array are retried with native tools stripped, the OAuth success tab auto-closes with a clear hint, the effective-credential picker prefers a verified OAuth login over a stray API key, and abandoned idle `jeo` tmux REPL sessions are reaped on launch.
 - **[0.7.8]** (2026-06-24) — Long-session performance & resource hygiene: the detached memory-distill worker now always terminates itself (closing the `jeo memory-distill` orphan pileup that pinned each session's transcript in RSS), the live reasoning/output block re-wraps only its trailing window (O(tail) per frame instead of O(len²) over a long stream), the team loop stops reprinting the todo guide every iteration, and the readline caret stays aligned after an image attach.
 - **[0.7.7]** (2026-06-23) — Long-running-process hygiene & input robustness: backgrounded grandchildren (`next dev &`, daemons) are now reaped at the turn boundary via per-command process groups — closing the climbing `next-server` RSS leak — while the prompt gains recursive fuzzy `@path` search, ANSI-safe and idle-merged bracketed paste, a configurable OSC 52 clipboard cap, per-role ralplan model routing, and leaked-reasoning-tag stripping on salvaged answers.
-- **[0.7.6]** (2026-06-23) — Release & docs plumbing: the running version's release notes now travel inside the `--compile` single binary (so `/whats-new` works offline and from a global install), the in-TUI markdown table renderer stops splitting on escaped `\|` pipes, and the release pipeline gains a cross-compiled standalone-binary matrix — macOS/Linux **plus a first-class Windows x64 `.exe`** — built on one Linux runner and auto-attached to each GitHub release.
-- **[0.7.5]** (2026-06-23) — Startup & loop latency: redundant re-reads that fired on every subagent spawn and every loop step are now memoized behind cheap `stat`-signature caches, so cold paths stay correct (edits/deletes still picked up immediately) while warm paths skip the disk and the re-parse. Targets the per-turn and per-spawn overhead that dominates perceived slowness in team/ralph/autopilot fan-outs.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.zh.md

@@ -149,6 +149,18 @@ jeo ultragoal
 `jeo` 在 `.jeo/memory/` 下保存 **本地优先、蒸馏后的项目内存**(无远程后端,零原生依赖)。过往会话被蒸馏为 [OKF](docs/okf_mem/) 概念包,下一次会话仅把相关的、受预算约束的切片重新注入系统提示 —— 作为 DATA 而非指令加固。用 `JEO_NO_MEMORY=1` 完全禁用。
 
 **迁移(`jeo memory-migrate`,一次性 · 幂等).** 把旧版单文档 `MEMORY.md` 无损转换为概念包: `## 标题 → 类型`,每个项目符号 → 一个类型化概念,缩进行 → 正文; 重建 `index.md`/`log.md`,并把原文件重命名为 `MEMORY.md.bak`。一旦概念包中已有概念,再次运行即为 no-op。**回滚:** `JEO_MEMORY_LEGACY=1` 忽略概念包,通过相同的注入加固读取 `MEMORY.md`/`.bak`(`JEO_NO_MEMORY=1` 仍优先于一切)。
+## 与您现有的代理或机器人协同工作 (Works beside your existing agent or bot)
+
+| 工具或机器人 | 推荐的 jeo 命令 | 边界 |
+| ----------- | ----------------------- | -------- |
+| Codex CLI | `jeo --tmux` 或 `jeo` | 在同级 tmux 会话中运行或内联运行。 |
+| Claude Code | `jeo --tmux` 或 `jeo` | jeo 不会成为 Claude Code 的扩展。 |
+| OpenCode | `jeo` 或 `jeo --tmux` | 仅限外部运行器工作流。 |
+| Claw Code | `jeo --tmux` | jeo 不会安装到或替换 Claw Code。 |
+| 外部控制器 / 机器人 | `jeo` (或自定义集成) | 外部控制器通过标准终端/CLI 接口驱动 jeo。 |
+
+添加 `-q`/`--quiet`（或 `JEO_QUIET=1`）可抑制启动横幅、欢迎动画、发布说明和恢复提示，使 jeo 能够与其他代理并行运行或由机器人驱动。`-p`/`--print` 隐含 quiet。
+
 
 ## 本地模型
 
@@ -193,11 +205,11 @@ CI 通过 `.github/workflows/npm-publish.yml` 发布 — GitHub 发布 release
 ## 更新日志 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.7.15]** (2026-06-25) — Rollback release: the runtime source and test suite are restored to the **0.7.9** state. The intervening 0.7.10–0.7.14 runtime changes (quiet-mode/`-q`, `/resume` transcript rework, `mutatedFiles` plumbing, Ollama `num_ctx`, tmux REPL reaping, and related engine/provider/TUI edits) are reverted. Published as a new version because npm cannot re-issue an existing version number; `latest` now serves code identical to 0.7.9.
+- **[0.7.14]** (2026-06-25) — Quieter, cleaner output: a new `-q`/`--quiet` flag strips launch banners and courtesy logs, `/resume` no longer dumps walls of raw escaped JSON into scrollback, and a turn that edits files now reliably surfaces those paths to orchestrators.
 - **[0.7.9]** (2026-06-24) — Local model providers actually run, and OAuth/login hygiene: Ollama requests now carry an explicit `num_ctx` so jeo's large system prompt no longer overflows Ollama's small default window (the "ollama 모델이 안 돌아간다" blocker), LM Studio reasoning models that emit the whole reply on the reasoning channel are recovered instead of dying empty, GGUF chat templates that can't render the `tools` array are retried with native tools stripped, the OAuth success tab auto-closes with a clear hint, the effective-credential picker prefers a verified OAuth login over a stray API key, and abandoned idle `jeo` tmux REPL sessions are reaped on launch.
 - **[0.7.8]** (2026-06-24) — Long-session performance & resource hygiene: the detached memory-distill worker now always terminates itself (closing the `jeo memory-distill` orphan pileup that pinned each session's transcript in RSS), the live reasoning/output block re-wraps only its trailing window (O(tail) per frame instead of O(len²) over a long stream), the team loop stops reprinting the todo guide every iteration, and the readline caret stays aligned after an image attach.
 - **[0.7.7]** (2026-06-23) — Long-running-process hygiene & input robustness: backgrounded grandchildren (`next dev &`, daemons) are now reaped at the turn boundary via per-command process groups — closing the climbing `next-server` RSS leak — while the prompt gains recursive fuzzy `@path` search, ANSI-safe and idle-merged bracketed paste, a configurable OSC 52 clipboard cap, per-role ralplan model routing, and leaked-reasoning-tag stripping on salvaged answers.
-- **[0.7.6]** (2026-06-23) — Release & docs plumbing: the running version's release notes now travel inside the `--compile` single binary (so `/whats-new` works offline and from a global install), the in-TUI markdown table renderer stops splitting on escaped `\|` pipes, and the release pipeline gains a cross-compiled standalone-binary matrix — macOS/Linux **plus a first-class Windows x64 `.exe`** — built on one Linux runner and auto-attached to each GitHub release.
-- **[0.7.5]** (2026-06-23) — Startup & loop latency: redundant re-reads that fired on every subagent spawn and every loop step are now memoized behind cheap `stat`-signature caches, so cold paths stay correct (edits/deletes still picked up immediately) while warm paths skip the disk and the re-parse. Targets the per-turn and per-spawn overhead that dominates perceived slowness in team/ralph/autopilot fan-outs.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jeo-code",
-  "version": "0.7.13",
+  "version": "0.7.15",
   "description": "Clean, highly optimized AI coding agent using spec-first loop",
   "type": "module",
   "main": "src/cli.ts",

package/src/agent/tool-output.ts

@@ -83,7 +83,7 @@ export async function spillToolResult(tool: string, output: string, cwd: string)
   await fs.mkdir(dir, { recursive: true });
   const safeTool = tool.replace(/[^a-zA-Z0-9_-]/g, "_").slice(0, 32) || "tool";
   const stamp = `${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
-  const rel = `.jeo/artifacts/tool-results/${stamp}-${safeTool}.txt`;
+  const rel = path.join(".jeo", "artifacts", "tool-results", `${stamp}-${safeTool}.txt`);
   await fs.writeFile(path.join(cwd, rel), output, "utf-8");
   // Retention so a long session can't grow the artifact dir without bound.
   await pruneToolArtifacts(dir);

package/src/ai/model-manager.ts

@@ -533,8 +533,7 @@ export function streamIdleMs(env?: Record<string, string | undefined>): number {
  *  built-in default. Mirrors streamIdleMs so a slow non-interactive turn (callLlm without
  *  onToken) can relax the cap via JEO_CALL_TIMEOUT_MS without a code change. */
 export function callTimeoutMs(env?: Record<string, string | undefined>): number {
-  const e = env ?? process.env;
-  const raw = jeoEnv("CALL_TIMEOUT_MS", e) ?? e["ANTHROPIC_TIMEOUT"];
+  const raw = jeoEnv("CALL_TIMEOUT_MS", env);
   const n = raw !== undefined ? parseInt(raw, 10) : NaN;
   return Number.isFinite(n) && n > 0 ? n : DEFAULT_CALL_TIMEOUT_MS;
 }

package/src/ai/providers/anthropic.ts

@@ -135,7 +135,7 @@ function anthropicThinkingMode(model: string): AnthropicThinkingMode {
   const v = parseAnthropicVersion(model);
   if (!v) return "budget";
   if (v.major > 4 || (v.major === 4 && v.minor >= 6)) return "adaptive";
-  
+  if (v.major === 4 && v.minor === 5) return "budget-effort";
   return "budget";
 }
 
@@ -266,7 +266,7 @@ export function anthropicPayload(
       // Budget-based extended thinking. `display: "summarized"` keeps human-readable thought
       // streaming. The 4.5 (budget-effort) transport also carries an output_config effort.
       payload.thinking = { type: "enabled", budget_tokens: thinkingBudget, display: "summarized" };
-      
+      if (thinkingMode === "budget-effort") payload.output_config = { effort: anthropicAdaptiveEffort(effort) };
     }
   } else if (includeTemperature && options.temperature !== undefined) {
     payload.temperature = options.temperature;
@@ -281,7 +281,6 @@ export function anthropicPayload(
   if (stream) payload.stream = true;
   const system = anthropicSystemBlocks(systemPrompt, model, credential, payload);
   if (system) payload.system = system;
-  console.log("PAYLOAD:", JSON.stringify(payload));
   return JSON.stringify(payload);
 }