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

博客园 - Franky
Microsoft Azure Blog
Microsoft Azure Blog
阮一峰的网络日志
阮一峰的网络日志
宝玉的分享
宝玉的分享
量子位
N
Netflix TechBlog - Medium
M
MIT News - Artificial intelligence
GbyAI
GbyAI
Apple Machine Learning Research
Apple Machine Learning Research
博客园_首页
博客园 - 叶小钗
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
酷 壳 – CoolShell
酷 壳 – CoolShell
T
Tailwind CSS Blog
Y
Y Combinator Blog
L
LangChain Blog
The Cloudflare Blog
T
The Blog of Author Tim Ferriss
U
Unit 42
Martin Fowler
Martin Fowler
aimingoo的专栏
aimingoo的专栏
G
Google Developers Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
月光博客
月光博客

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 across 6 pages · openclaw/opencl...
vincentkoc · 2026-05-06 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -181,7 +181,7 @@ Details: [Configuration](/gateway/config-agents#messages) and channel docs.

181181
182182

## Silent replies

183183
184-

The exact silent token `NO_REPLY` / `no_reply` means do not deliver a user-visible reply.

184+

The exact silent token `NO_REPLY` / `no_reply` means "do not deliver a user-visible reply".

185185

When a turn also has pending tool media, such as generated TTS audio, OpenClaw

186186

strips the silent text but still delivers the media attachment.

187187

OpenClaw resolves that behavior by conversation type:

Original file line numberDiff line numberDiff line change

@@ -106,7 +106,7 @@ When a provider has multiple profiles, OpenClaw chooses an order like this:

106106

</Step>

107107

</Steps>

108108
109-

If no explicit order is configured, OpenClaw uses a roundrobin order:

109+

If no explicit order is configured, OpenClaw uses a round-robin order:

110110
111111

- **Primary key:** profile type (**OAuth before API keys**).

112112

- **Secondary key:** `usageStats.lastUsed` (oldest first, within each type).

@@ -128,7 +128,7 @@ Auto-pinned profiles (selected by the session router) are treated as a **prefere

128128
129129

### Why OAuth can "look lost"

130130
131-

If you have both an OAuth profile and an API key profile for the same provider, roundrobin can switch between them across messages unless pinned. To force a single profile:

131+

If you have both an OAuth profile and an API key profile for the same provider, round-robin can switch between them across messages unless pinned. To force a single profile:

132132
133133

- Pin with `auth.order[provider] = ["provider:profileId"]`, or

134134

- Use a per-session override via `/model …` with a profile override (when supported by your UI/chat surface).

Original file line numberDiff line numberDiff line change

@@ -113,7 +113,7 @@ keys.

113113
114114

## Troubleshooting

115115
116-

- If commands seem stuck, enable verbose logs and look for queued for …ms” lines to confirm the queue is draining.

116+

- If commands seem stuck, enable verbose logs and look for "queued for ...ms" lines to confirm the queue is draining.

117117

- If you need queue depth, enable verbose logs and watch for queue timing lines.

118118

- Codex app-server runs that accept a turn and then stop emitting progress are interrupted by the Codex adapter so the active session lane can release instead of waiting for the outer run timeout.

119119

- When diagnostics are enabled, sessions that remain in `processing` past `diagnostics.stuckSessionWarnMs` with no observed reply, tool, status, block, or ACP progress are classified by current activity. Active work logs as `session.long_running`; active work with no recent progress logs as `session.stalled`; `session.stuck` is reserved for stale session bookkeeping with no active work, and only that path can release the affected session lane so queued work drains. Repeated `session.stuck` diagnostics back off while the session remains unchanged.

Original file line numberDiff line numberDiff line change

@@ -22,7 +22,7 @@ For credential eligibility/reason-code rules used by `models status --probe`, se

2222
2323

## Recommended setup (API key, any provider)

2424
25-

If youre running a long-lived gateway, start with an API key for your chosen

25+

If you're running a long-lived gateway, start with an API key for your chosen

2626

provider.

2727

For Anthropic specifically, API key auth is still the most predictable server

2828

setup, but OpenClaw also supports reusing a local Claude CLI login.

@@ -51,7 +51,7 @@ openclaw models status

5151

openclaw doctor

5252

```

5353
54-

If youd rather not manage env vars yourself, onboarding can store

54+

If you'd rather not manage env vars yourself, onboarding can store

5555

API keys for daemon use: `openclaw onboard`.

5656
5757

See [Help](/help) for details on env inheritance (`env.shellEnv`,

@@ -187,7 +187,7 @@ Use `/model` (or `/model list`) for a compact picker; use `/model status` for th

187187
188188

### Per-agent (CLI override)

189189
190-

Set an explicit auth profile order override for an agent (stored in that agents `auth-state.json`):

190+

Set an explicit auth profile order override for an agent (stored in that agent's `auth-state.json`):

191191
192192

```bash

193193

openclaw models auth order get --provider anthropic

Original file line numberDiff line numberDiff line change

@@ -83,7 +83,7 @@ After the first successful load, the running process serves the active in-memory

8383
8484

## OpenAI-compatible endpoints

8585
86-

OpenClaws highest-leverage compatibility surface is now:

86+

OpenClaw's highest-leverage compatibility surface is now:

8787
8888

- `GET /v1/models`

8989

- `GET /v1/models/{id}`

Original file line numberDiff line numberDiff line change

@@ -96,7 +96,7 @@ Notes:

9696

## Config

9797
9898

- `tools.exec.notifyOnExit` (default: true): when true, backgrounded exec sessions enqueue a system event and request a heartbeat on exit.

99-

- `tools.exec.approvalRunningNoticeMs` (default: 10000): emit a single running notice when an approval-gated exec runs longer than this (0 disables).

99+

- `tools.exec.approvalRunningNoticeMs` (default: 10000): emit a single "running" notice when an approval-gated exec runs longer than this (0 disables).

100100

- `tools.exec.timeoutSec` (default: 1800): default per-command exec timeout in seconds. Per-call `timeout` overrides it; per-call `timeout: 0` disables the exec process timeout.

101101

- `tools.exec.host` (default: `auto`; resolves to `sandbox` when sandbox runtime is active, `gateway` otherwise)

102102

- `tools.exec.security` (default: `deny` for sandbox, `full` for gateway + node when unset)

@@ -143,7 +143,7 @@ openclaw config get agents.list

143143

openclaw config set agents.list[0].tools.exec.node "node-id-or-name"

144144

```

145145
146-

Control UI: the Nodes tab includes a small Exec node binding panel for the same settings.

146+

Control UI: the Nodes tab includes a small "Exec node binding" panel for the same settings.

147147
148148

## Session overrides (`/exec`)

149149