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

B
Blog
D
Docker
J
Java Code Geeks
腾讯CDC
Blog — PlanetScale
Blog — PlanetScale
G
Google Developers Blog
M
MIT News - Artificial intelligence
L
LangChain Blog
T
The Blog of Author Tim Ferriss
P
Proofpoint News Feed
MyScale Blog
MyScale Blog
博客园 - Franky
GbyAI
GbyAI
Hugging Face - Blog
Hugging Face - Blog
aimingoo的专栏
aimingoo的专栏
Last Week in AI
Last Week in AI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 聂微东
N
Netflix TechBlog - Medium
B
Blog RSS Feed
Y
Y Combinator Blog
阮一峰的网络日志
阮一峰的网络日志
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Google DeepMind News
Google DeepMind News

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: normalize mintlify component closings · openclaw/op...
steipete · 2026-04-28 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -278,7 +278,7 @@ Keep hook endpoints behind loopback, tailnet, or trusted reverse proxy.

278278

- Keep `hooks.allowRequestSessionKey=false` unless you require caller-selected sessions.

279279

- If you enable `hooks.allowRequestSessionKey`, also set `hooks.allowedSessionKeyPrefixes` to constrain allowed session key shapes.

280280

- Hook payloads are wrapped with safety boundaries by default.

281-

</Warning>

281+

</Warning>

282282
283283

## Gmail PubSub integration

284284

@@ -382,7 +382,7 @@ Model override note:

382382

- Configured fallback chains still apply because cron `--model` is a job primary, not a session `/model` override.

383383

- Payload `fallbacks` replaces configured fallbacks for that job; `fallbacks: []` disables fallback and makes the run strict.

384384

- A plain `--model` with no explicit or configured fallback list does not fall through to the agent primary as a silent extra retry target.

385-

</Note>

385+

</Note>

386386
387387

## Configuration

388388
Original file line numberDiff line numberDiff line change

@@ -66,7 +66,7 @@ Current OpenClaw releases bundle BlueBubbles, so normal packaged builds do not n

6666

- Always set a webhook password.

6767

- Webhook authentication is always required. OpenClaw rejects BlueBubbles webhook requests unless they include a password/guid that matches `channels.bluebubbles.password` (for example `?password=<password>` or `x-password`), regardless of loopback/proxy topology.

6868

- Password authentication is checked before reading/parsing full webhook bodies.

69-

</Warning>

69+

</Warning>

7070
7171

## Keeping Messages.app alive (VM / headless setups)

7272
Original file line numberDiff line numberDiff line change

@@ -26,7 +26,7 @@ Translation: allowlisted senders can trigger OpenClaw by mentioning it.

2626

- **DM access** is controlled by `*.allowFrom`.

2727

- **Group access** is controlled by `*.groupPolicy` + allowlists (`*.groups`, `*.groupAllowFrom`).

2828

- **Reply triggering** is controlled by mention gating (`requireMention`, `/activation`).

29-

</Note>

29+

</Note>

3030
3131

Quick flow (what happens to a group message):

3232
Original file line numberDiff line numberDiff line change

@@ -418,7 +418,7 @@ External scripts and webhooks can post buttons directly via the Mattermost REST

418418

4. Action `id` must be **alphanumeric only** (`[a-zA-Z0-9]`). Hyphens and underscores break Mattermost's server-side action routing (returns 404). Strip them before use.

419419

5. `context.action_id` must match the button's `id` so the confirmation message shows the button name (e.g., "Approve") instead of a raw ID.

420420

6. `context.action_id` is required — the interaction handler returns 400 without it.

421-

</Warning>

421+

</Warning>

422422
423423

**HMAC token generation**

424424
Original file line numberDiff line numberDiff line change

@@ -127,7 +127,7 @@ This happens **before** a normal reply is generated, so the message can feel lik

127127

- Add the model to `agents.defaults.models`, or

128128

- Clear the allowlist (remove `agents.defaults.models`), or

129129

- Pick a model from `/model list`.

130-

</Warning>

130+

</Warning>

131131
132132

Example allowlist config:

133133
Original file line numberDiff line numberDiff line change

@@ -235,7 +235,7 @@ Use `accountId` to target a specific account on multi-account channels like Tele

235235

- `main` (default): agent main session.

236236

- Explicit session key (copy from `openclaw sessions --json` or the [sessions CLI](/cli/sessions)).

237237

- Session key formats: see [Sessions](/concepts/session) and [Groups](/channels/groups).

238-

</ParamField>

238+

</ParamField>

239239

<ParamField path="target" type="string">

240240

- `last`: deliver to the last used external channel.

241241

- explicit channel: any configured channel or plugin id, for example `discord`, `matrix`, `telegram`, or `whatsapp`.

Original file line numberDiff line numberDiff line change

@@ -82,7 +82,7 @@ Node pairing is a trust and identity flow plus token issuance. It does **not** p

8282
8383

- Live node commands come from what the node declares on connect after the gateway's global node command policy (`gateway.nodes.allowCommands` and `denyCommands`) is applied.

8484

- Per-node `system.run` allow and ask policy lives on the node in `exec.approvals.node.*`, not in the pairing record.

85-

</Warning>

85+

</Warning>

8686
8787

## Node command gating (2026.3.31+)

8888
Original file line numberDiff line numberDiff line change

@@ -349,7 +349,7 @@ Example (read-only source + an extra data directory):

349349

- Sensitive mounts (secrets, SSH keys, service credentials) should be `:ro` unless absolutely required.

350350

- Combine with `workspaceAccess: "ro"` if you only need read access to the workspace; bind modes stay independent.

351351

- See [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) for how binds interact with tool policy and elevated exec.

352-

</Warning>

352+

</Warning>

353353
354354

## Images and setup

355355
Original file line numberDiff line numberDiff line change

@@ -99,7 +99,7 @@ Implications:

9999

- Internal Gateway clients that do not travel through the reverse proxy should use `gateway.auth.password` / `OPENCLAW_GATEWAY_PASSWORD`, not trusted-proxy identity headers.

100100

- Non-loopback Control UI deployments still need explicit `gateway.controlUi.allowedOrigins`.

101101

- **Forwarded-header evidence overrides loopback locality for local direct fallback.** If a request arrives on loopback but carries `X-Forwarded-For` / `X-Forwarded-Host` / `X-Forwarded-Proto` headers pointing at a non-local origin, that evidence disqualifies local-direct password fallback and device-identity gating. With `allowLoopback: true`, trusted-proxy auth can still accept the request as a same-host proxy request, while `requiredHeaders` and `allowUsers` continue to apply.

102-

</Warning>

102+

</Warning>

103103
104104

### Configuration reference

105105
Original file line numberDiff line numberDiff line change

@@ -259,7 +259,7 @@ For CLI entries, **set `capabilities` explicitly** to avoid surprising matches.

259259
260260

- `minimax` and `minimax-portal` image understanding comes from the plugin-owned `MiniMax-VL-01` media provider.

261261

- The bundled MiniMax text catalog still starts text-only; explicit `models.providers.minimax` entries materialize image-capable M2.7 chat refs.

262-

</Note>

262+

</Note>

263263
264264

## Model selection guidance

265265