惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

WordPress大学
WordPress大学
Engineering at Meta
Engineering at Meta
D
DataBreaches.Net
月光博客
月光博客
Recent Announcements
Recent Announcements
Google DeepMind News
Google DeepMind News
U
Unit 42
腾讯CDC
爱范儿
爱范儿
J
Java Code Geeks
有赞技术团队
有赞技术团队
Blog — PlanetScale
Blog — PlanetScale
N
Netflix TechBlog - Medium
B
Blog
Stack Overflow Blog
Stack Overflow Blog
GbyAI
GbyAI
T
The Blog of Author Tim Ferriss
小众软件
小众软件
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Y
Y Combinator Blog
大猫的无限游戏
大猫的无限游戏
Microsoft Azure Blog
Microsoft Azure Blog
T
Tailwind CSS Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4
docs: typography hygiene + dup H1 across 5 pages (cli/gat...
vincentkoc · 2026-05-06 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -118,7 +118,7 @@ Permission model (client debug mode):

118118

- `read` auto-approval is scoped to the current working directory (`--cwd` when set).

119119

- ACP only auto-approves narrow readonly classes: scoped `read` calls under the active cwd plus readonly search tools (`search`, `web_search`, `memory_search`). Unknown/non-core tools, out-of-scope reads, exec-capable tools, control-plane tools, mutating tools, and interactive flows always require explicit prompt approval.

120120

- Server-provided `toolCall.kind` is treated as untrusted metadata (not an authorization source).

121-

- This ACP bridge policy is separate from ACPX harness permissions. If you run OpenClaw through the `acpx` backend, `plugins.entries.acpx.config.permissionMode=approve-all` is the break-glass yolo switch for that harness session.

121+

- This ACP bridge policy is separate from ACPX harness permissions. If you run OpenClaw through the `acpx` backend, `plugins.entries.acpx.config.permissionMode=approve-all` is the break-glass "yolo" switch for that harness session.

122122
123123

## How to use this

124124

@@ -218,7 +218,7 @@ pull contextual information from an OpenClaw agent without scraping a terminal.

218218
219219

## Zed editor setup

220220
221-

Add a custom ACP agent in `~/.config/zed/settings.json` (or use Zeds Settings UI):

221+

Add a custom ACP agent in `~/.config/zed/settings.json` (or use Zed's Settings UI):

222222
223223

```json

224224

{

@@ -256,7 +256,7 @@ To target a specific Gateway or agent:

256256

}

257257

```

258258
259-

In Zed, open the Agent panel and select OpenClaw ACP to start a thread.

259+

In Zed, open the Agent panel and select "OpenClaw ACP" to start a thread.

260260
261261

## Session mapping

262262
Original file line numberDiff line numberDiff line change

@@ -2,12 +2,10 @@

22

summary: "CLI reference for `openclaw status` (diagnostics, probes, usage snapshots)"

33

read_when:

44

- You want a quick diagnosis of channel health + recent session recipients

5-

- You want a pasteable all status for debugging

6-

title: "Status"

5+

- You want a pasteable "all" status for debugging

6+

title: "openclaw status"

77

---

88
9-

# `openclaw status`

10-
119

Diagnostics for channels + sessions.

1210
1311

```bash

@@ -34,8 +32,8 @@ Notes:

3432

- Overview includes update channel + git SHA (for source checkouts).

3533

- Update info surfaces in the Overview; if an update is available, status prints a hint to run `openclaw update` (see [Updating](/install/updating)).

3634

- Read-only status surfaces (`status`, `status --json`, `status --all`) resolve supported SecretRefs for their targeted config paths when possible.

37-

- If a supported channel SecretRef is configured but unavailable in the current command path, status stays read-only and reports degraded output instead of crashing. Human output shows warnings such as configured token unavailable in this command path, and JSON output includes `secretDiagnostics`.

38-

- When command-local SecretRef resolution succeeds, status prefers the resolved snapshot and clears transient secret unavailable channel markers from the final output.

35+

- If a supported channel SecretRef is configured but unavailable in the current command path, status stays read-only and reports degraded output instead of crashing. Human output shows warnings such as "configured token unavailable in this command path", and JSON output includes `secretDiagnostics`.

36+

- When command-local SecretRef resolution succeeds, status prefers the resolved snapshot and clears transient "secret unavailable" channel markers from the final output.

3937

- `status --all` includes a Secrets overview row and a diagnosis section that summarizes secret diagnostics (truncated for readability) without stopping report generation.

4038
4139

## Related

Original file line numberDiff line numberDiff line change

@@ -6,16 +6,14 @@ read_when:

66

title: "Background exec and process tool"

77

---

88
9-

# Background Exec + Process Tool

10-
11-

OpenClaw runs shell commands through the `exec` tool and keeps long‑running tasks in memory. The `process` tool manages those background sessions.

9+

OpenClaw runs shell commands through the `exec` tool and keeps long-running tasks in memory. The `process` tool manages those background sessions.

1210
1311

## exec tool

1412
1513

Key parameters:

1614
1715

- `command` (required)

18-

- `yieldMs` (default 10000): autobackground after this delay

16+

- `yieldMs` (default 10000): auto-background after this delay

1917

- `background` (bool): background immediately

2018

- `timeout` (seconds, default `tools.exec.timeoutSec`): kill the process after this timeout; set `timeout: 0` only to disable the exec process timeout for that call

2119

- `elevated` (bool): run outside the sandbox if elevated mode is enabled/allowed (`gateway` by default, or `node` when the exec target is `node`)

@@ -45,7 +43,7 @@ When spawning long-running child processes outside the exec/process tools (for e

4543

Environment overrides:

4644
4745

- `PI_BASH_YIELD_MS`: default yield (ms)

48-

- `PI_BASH_MAX_OUTPUT_CHARS`: inmemory output cap (chars)

46+

- `PI_BASH_MAX_OUTPUT_CHARS`: in-memory output cap (chars)

4947

- `OPENCLAW_BASH_PENDING_MAX_OUTPUT_CHARS`: pending stdout/stderr cap per stream (chars)

5048

- `PI_BASH_JOB_TTL_MS`: TTL for finished sessions (ms, bounded to 1m–3h)

5149
Original file line numberDiff line numberDiff line change

@@ -17,7 +17,7 @@ rate-limited, or temporarily misbehaving. This is intentionally conservative:

1717

- **Images can be passed through** if the CLI accepts image paths.

1818
1919

This is designed as a **safety net** rather than a primary path. Use it when you

20-

want always works text responses without relying on external APIs.

20+

want "always works" text responses without relying on external APIs.

2121
2222

If you want a full harness runtime with ACP session controls, background tasks,

2323

thread/conversation binding, and persistent external coding sessions, use

@@ -49,7 +49,7 @@ command path:

4949

}

5050

```

5151
52-

Thats it. No keys, no extra auth config needed beyond the CLI itself.

52+

That's it. No keys, no extra auth config needed beyond the CLI itself.

5353
5454

If you use a bundled CLI backend as the **primary message provider** on a

5555

gateway host, OpenClaw now auto-loads the owning bundled plugin when your config

@@ -397,7 +397,7 @@ children and Streamable HTTP/SSE streams do not outlive the run.

397397

`bundleMcp: true`.

398398

- **Streaming is backend-specific.** Some backends stream JSONL; others buffer

399399

until exit.

400-

- **Structured outputs** depend on the CLIs JSON format.

400+

- **Structured outputs** depend on the CLI's JSON format.

401401

- **Codex CLI sessions** resume via text output (no JSONL), which is less

402402

structured than the initial `--json` run. OpenClaw sessions still work

403403

normally.

Original file line numberDiff line numberDiff line change

@@ -203,7 +203,7 @@ pnpm gateway:dev

203203

OPENCLAW_PROFILE=dev openclaw tui

204204

```

205205
206-

If you dont have a global install yet, run the CLI via `pnpm openclaw ...`.

206+

If you don't have a global install yet, run the CLI via `pnpm openclaw ...`.

207207
208208

What this does:

209209

@@ -219,7 +219,7 @@ What this does:

219219

- Sets `agent.skipBootstrap=true` (no BOOTSTRAP.md).

220220

- Seeds the workspace files if missing:

221221

`AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`.

222-

- Default identity: **C3PO** (protocol droid).

222+

- Default identity: **C3-PO** (protocol droid).

223223

- Skips channel providers in dev mode (`OPENCLAW_SKIP_CHANNELS=1`).

224224
225225

Reset flow (fresh start):

@@ -297,7 +297,7 @@ Default file:

297297
298298

`~/.pi-mono/logs/raw-openai-completions.jsonl`

299299
300-

> Note: this is only emitted by processes using pi-monos

300+

> Note: this is only emitted by processes using pi-mono's

301301

> `openai-completions` provider.

302302
303303

## Safety notes