mudrii · mudrii · May 13, 2026 · May 13, 2026 · May 13, 2026 · May 13, 2026
diff --git a/AGENT_README.md b/AGENT_README.md
@@ -4,7 +4,7 @@
 > Designed for AI agents and human contributors.
 > This document **complements** `AGENTS.md` (the repo's canonical agent guidelines file, symlinked as `CLAUDE.md`). Load both before starting work. When build/test commands differ, `AGENTS.md` is authoritative.
 > Tracks published OpenClaw releases. Current package version: check `package.json` (`"version"`). Gotchas are versioned — read only the sections that apply to the release you are targeting.
-> **Current docs version: v2026.5.7-2 (2026-05-11).** Latest published upstream stable release: v2026.5.7 (published 2026-05-07 20:57:43 UTC).
+> **Current docs version: v2026.5.7-3 (2026-05-13).** Latest published upstream stable release: v2026.5.7 (published 2026-05-07 20:57:43 UTC).
 
 ---
 

diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
@@ -1,6 +1,6 @@
 # OpenClaw — Master Architecture Document
 
-> Updated: 2026-05-11 (docs snapshot: v2026.5.7-2) | Released baseline: GitHub `v2026.5.7` (published 2026-05-07 20:57:43 UTC)
+> Updated: 2026-05-13 (docs snapshot: v2026.5.7-3) | Released baseline: GitHub `v2026.5.7` (published 2026-05-07 20:57:43 UTC)
 
 ---
 

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,6 +6,25 @@ Release policy: this file tracks published releases only (stable tags). It does
 
 ---
 
+## OpenClaw v2026.5.7-3 — Docs Correction Summary
+
+> **Released:** 2026-05-13 (docs correction) | upstream GitHub release `v2026.5.7` unchanged, published 2026-05-07 20:57:43 UTC | **Validated against:** `v2026.5.7`
+
+### Corrections
+
+- **Channels (`v2026.5.7`):** corrected `telegram` error policy enum (`always|once|silent`) and the 14400000 ms (4 h) default cooldown; `feishu` outbound chunking default raised to `4000` chars and pairing default flagged; `matrix` streaming mode enum now lists `progress`; `tlon` private-network knob renamed to `network.dangerouslyAllowPrivateNetwork`; `bluebubbles` audio fallback default flipped to `true`; `qqbot` voice docs narrowed to STT-only (no TTS in v2026.5.7 source).
+- **Providers (`v2026.5.7`):** Anthropic CLI default model bumped to `claude-opus-4-7`; OpenAI default TTS voice corrected from `coral` to `alloy`; Groq catalog example replaced (`Mixtral 8x7B` → `Mistral Saba 24B`); Mistral page stray Z.AI auth line removed; Moonshot endpoint table accepts both `MOONSHOT_API_KEY` and `KIMI_API_KEY`; Z.AI auth surface adds `Z_AI_API_KEY` alias; xAI legacy `grok-4.20-experimental-beta-0304-{reasoning,non-reasoning}` aliases restored; OpenRouter ref list reworded as illustrative (manifest has no static catalog).
+- **Plugins/SDK (`v2026.5.7`):** added 5 missing source-only plugins (active-memory, device-pair, phone-control, talk-voice, thread-ownership) to plugin inventory and reference tables; SDK overview tightened to clarify channel-branded subpaths (`discord`, `matrix`, `telegram-account`, `telegram-command-config`) are bundled-plugin internal seams — Slack/Signal/WhatsApp seams do not exist.
+- **Analysis snapshots:** restamped 10 analysis pages from the `v2026.5.5` baseline to `v2026.5.7` (2026-05-13), keeping in-body historical release-window references intact.
+- **Tools and snippets:** documented the `timeout` clamp on `exec` poll and the `hex`/`literal` send-keys variants per `bash-tools.schemas.ts`; refreshed `snippets/plugin-publish/minimal-package.json` to the `v2026.5.7` plugin manifest compat/build baseline.
+- **Prerelease exclusion note:** refreshed the stable-docs note to exclude current upstream prereleases through the latest GitHub-published prerelease `v2026.5.12-beta.3` (source tag `v2026.5.10-beta.6` exists in the upstream tree but is not published as a GitHub release).
+
+### Prerelease Note
+
+- Upstream `v2026.5.9-beta.1`, `v2026.5.10-beta.1` through `v2026.5.10-beta.5`, and `v2026.5.12-beta.1` through `v2026.5.12-beta.3` are prereleases. Source tag `v2026.5.10-beta.6` exists in the upstream git tree but is not a GitHub release. All are intentionally excluded from this stable docs snapshot.
+
+---
+
 ## OpenClaw v2026.5.7-2 — Docs Correction Summary
 
 > **Released:** 2026-05-11 (docs correction) | upstream GitHub release `v2026.5.7` unchanged, published 2026-05-07 20:57:43 UTC | **Validated against:** `v2026.5.7`

diff --git a/README.md b/README.md
@@ -3,7 +3,7 @@
 Comprehensive codebase documentation for [OpenClaw](https://github.com/openclaw/openclaw) — the open-source AI agent platform.
 
 **Latest published upstream stable release: v2026.5.7 (published 2026-05-07 20:57:43 UTC).**
-**Current validated docs snapshot: v2026.5.7-2 (validated against `v2026.5.7`).**
+**Current validated docs snapshot: v2026.5.7-3 (validated against `v2026.5.7`).**
 
 **Scope policy:** this repository documents published releases only. It does not document unreleased `main` branch changes, betas, or speculative future behavior.
 
@@ -56,6 +56,7 @@ Both models independently confirmed the reference doc significantly reduced time
 ## Versioning
 
 Each documented release tracks an OpenClaw stable release line. Docs-only rereleases append a suffix like `-1`, `-2`, etc. while keeping the same validated upstream release; same-base npm correction builds are noted inside the matching docs snapshot rather than treated as separate published GitHub releases:
+- `v2026.5.7-3` (2026-05-13, docs correction) - Same upstream baseline as `v2026.5.7`; corrected channel defaults and key names (telegram error policy enum/cooldown, feishu pairing/chunking, matrix streaming `progress`, tlon `network.dangerouslyAllowPrivateNetwork`, bluebubbles audio default, qqbot STT-only), provider catalogs and aliases (anthropic CLI default to `claude-opus-4-7`, OpenAI TTS default to `alloy`, Groq catalog example, Moonshot `KIMI_API_KEY` alias, Z.AI `Z_AI_API_KEY` alias, xAI legacy aliases, OpenRouter ref list wording), added 5 missing source-only plugin entries (active-memory, device-pair, phone-control, talk-voice, thread-ownership), tightened SDK channel-branded seam list, restamped 10 analysis pages from `v2026.5.5` baseline to `v2026.5.7`, documented `exec` `timeout` clamp and `hex`/`literal` send-keys variants, refreshed plugin-publish snippet to `v2026.5.7` baseline, and refreshed prerelease exclusion notes through `v2026.5.12-beta.3` (source tag `v2026.5.10-beta.6` excluded). No upstream stable behavior changes.
 - `v2026.5.7-2` (2026-05-11, docs correction) - Same upstream baseline as `v2026.5.7`; restored released `v2026.5.7` docs pages that were missing or stale in the publish repo across channels, providers, plugins, CLI, reference, automation, concepts, gateway, tools, and web docs; refreshed prerelease exclusion notes through source tag `v2026.5.10-beta.4`. No upstream stable behavior changes.
 - `v2026.5.7-1` (2026-05-11, docs correction) - Same upstream baseline as `v2026.5.7`; corrected release metadata for upstream `v2026.5.5` to use the GitHub `publishedAt` timestamp (`2026-05-06 09:00:55 UTC`), refreshed prerelease exclusion notes through `v2026.5.10-beta.3`, and corrected stable inventory counts to use the released `v2026.5.7` tag instead of unreleased branch data. No upstream behavior changes.
 - `v2026.5.7` (2026-05-10, docs release) - Synced snapshot to upstream `v2026.5.7` (published 2026-05-07 20:57:43 UTC; window `v2026.5.5..v2026.5.7`, 93 commits). Pure fix sync covering stable `v2026.5.6` and `v2026.5.7`. Key fixes: `openai/chat-latest` direct API-key model override; `cron list --json` and `cron show --json` computed `status`; `channels list` channel-only output plus `--all`; native command owner enforcement; admin-only global Active Memory toggles; stale skills snapshot clearing during `/new` and `sessions.reset`; before-tool-call authorization for inline skill dispatch; Tavily SecretRef runtime resolution; managed plugin npm override/peer handling; context-engine cache invalidation; Discord provider-prefixed channel targets and voice permission audits; compaction max-token clamping; cron doctor repair for invalid persisted model sentinels; Telegram access-group allowlists, polling watchdog, same-chat message delivery, and dotted provider-id model buttons; stale Gateway task/reload reconciliation; WhatsApp LID mapping and media directive dedupe; Codex/native approval decision validation; model provider replay and APNG/Gemini/custom-key fixes.

diff --git a/analysis/agent-system.md b/analysis/agent-system.md
@@ -1,7 +1,7 @@
 # OpenClaw Codebase Analysis — Part 2: Agent System
 <!-- markdownlint-disable MD024 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5`
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7`
 
 ## 1. `src/agents/` — Agent Execution, Tool System, PI Tools
 

diff --git a/analysis/channels.md b/analysis/channels.md
@@ -1,7 +1,7 @@
 # OpenClaw Channels & Messaging — Comprehensive Analysis
 <!-- markdownlint-disable MD024 MD028 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5`
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7`
 > Modules analyzed: `extensions/telegram`, `extensions/discord`, `extensions/signal`, `extensions/slack`, `extensions/whatsapp`, `extensions/imessage`, `extensions/line`, `extensions/feishu`, `extensions/matrix`, `extensions/msteams`, `extensions/bluebubbles`, plus shared `src/channels` and `src/routing`
 
 > **Release boundary note:** current released implementations for Telegram, Discord, Slack, Signal, WhatsApp, iMessage, Feishu, Matrix, and QQ Bot live under `extensions/*`. Shared channel infrastructure remains in `src/channels`, `src/routing`, `src/line`, and adjacent core modules.

diff --git a/analysis/cli-config-infra.md b/analysis/cli-config-infra.md
@@ -1,7 +1,7 @@
 # OpenClaw CLI, Config & Infrastructure — Comprehensive Analysis
 <!-- markdownlint-disable MD024 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5` | Cluster: CLI, CONFIG & INFRASTRUCTURE
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7` | Cluster: CLI, CONFIG & INFRASTRUCTURE
 
 ---
 

diff --git a/analysis/cli-tools-media.md b/analysis/cli-tools-media.md
@@ -1,7 +1,7 @@
 # OpenClaw Codebase Analysis — PART 4: CLI, TOOLS & MEDIA
 <!-- markdownlint-disable MD024 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5`
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7`
 
 ## Overview
 

diff --git a/analysis/core-engine.md b/analysis/core-engine.md
@@ -1,7 +1,7 @@
 # OpenClaw Core Engine — Comprehensive Analysis
 <!-- markdownlint-disable MD024 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5`
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7`
 > Modules: agents (1,172 files), gateway (472 files), tasks (44 files), sessions (17 files), routing (11 files), hooks (52 files), context-engine (7 files)
 
 ---

diff --git a/analysis/gateway-config-infra.md b/analysis/gateway-config-infra.md
@@ -1,8 +1,8 @@
 # OpenClaw Core Architecture — Part 1: Module Analysis
 <!-- markdownlint-disable MD024 -->
 
-**Updated:** 2026-05-06 | **Version:** v2026.5.5
-**Codebase:** OpenClaw release tag `v2026.5.5`
+**Updated:** 2026-05-13 | **Version:** v2026.5.7
+**Codebase:** OpenClaw release tag `v2026.5.7`
 **Total lines (6 modules):** release-tag snapshot across gateway/config/infra/daemon/routing/types
 
 ---

diff --git a/analysis/memory-cron-media.md b/analysis/memory-cron-media.md
@@ -1,7 +1,7 @@
 # OpenClaw Analysis: Memory, Cron & Media Cluster
 <!-- markdownlint-disable MD024 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5`
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7`
 > Release note: the current released memory surface is split across `src/memory-host-sdk/` and `extensions/memory-core/src/memory/`. Historical `src/memory/` references below describe the older pre-split layout and should be read as historical context only.
 
 ---

diff --git a/analysis/security-plugins.md b/analysis/security-plugins.md
@@ -1,7 +1,7 @@
 # OpenClaw Codebase Analysis — PART 5: Security, Plugins & Extensions
 <!-- markdownlint-disable MD024 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5`
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7`
 
 ## 1. `src/security/` — Security Guards, Audit, SSRF, Auth
 

diff --git a/analysis/security-web-browser.md b/analysis/security-web-browser.md
@@ -1,7 +1,7 @@
 # OpenClaw Codebase Analysis: Security, Web Search, WhatsApp & Browser Cluster
 <!-- markdownlint-disable MD024 -->
 
-> Updated: 2026-05-06 | Version: v2026.5.5 | Codebase: OpenClaw release tag `v2026.5.5` | Modules: security, web-search, extensions/whatsapp, extensions/browser, canvas-host, plugins, plugin-sdk, acp
+> Updated: 2026-05-13 | Version: v2026.5.7 | Codebase: OpenClaw release tag `v2026.5.7` | Modules: security, web-search, extensions/whatsapp, extensions/browser, canvas-host, plugins, plugin-sdk, acp
 
 ---
 

diff --git a/analysis/utils-support.md b/analysis/utils-support.md
@@ -1,7 +1,7 @@
 # Utilities & Support Modules — Comprehensive Analysis
 <!-- markdownlint-disable MD024 -->
 
-**Updated:** 2026-05-06 | **Version:** v2026.5.5 | **Codebase:** OpenClaw release tag `v2026.5.5`
+**Updated:** 2026-05-13 | **Version:** v2026.5.7 | **Codebase:** OpenClaw release tag `v2026.5.7`
 **Cluster:** Utilities & Support Modules  
 **Total files analyzed:** stable release-line snapshot across 14 support modules plus `apps/macos`
 

diff --git a/docs/channels/bluebubbles.md b/docs/channels/bluebubbles.md
@@ -191,7 +191,7 @@ openclaw channels add bluebubbles --http-url http://192.168.1.100:1234 --passwor
 
 BlueBubbles group webhooks often only include raw participant addresses. If you want `GroupMembers` context to show local contact names instead, you can opt in to local Contacts enrichment on macOS:
 
-- `channels.bluebubbles.enrichGroupParticipantsFromContacts = true` enables the lookup. Default: `false`.
+- `channels.bluebubbles.enrichGroupParticipantsFromContacts = false` disables the lookup. Default: `true` (lookup enabled when running on macOS).
 - Lookups run only after group access, command authorization, and mention gating have allowed the message through.
 - Only unnamed phone participants are enriched.
 - Raw phone numbers remain as the fallback when no local match is found.
@@ -555,7 +555,7 @@ Full configuration: [Configuration](/gateway/configuration)
     - `channels.bluebubbles.allowFrom`: DM allowlist (handles, emails, E.164 numbers, `chat_id:*`, `chat_guid:*`).
     - `channels.bluebubbles.groupPolicy`: `open | allowlist | disabled` (default: `allowlist`).
     - `channels.bluebubbles.groupAllowFrom`: Group sender allowlist.
-    - `channels.bluebubbles.enrichGroupParticipantsFromContacts`: On macOS, optionally enrich unnamed group participants from local Contacts after gating passes. Default: `false`.
+    - `channels.bluebubbles.enrichGroupParticipantsFromContacts`: On macOS, enrich unnamed group participants from local Contacts after gating passes. Default: `true`.
     - `channels.bluebubbles.groups`: Per-group config (`requireMention`, etc.).
 
   </Accordion>

diff --git a/docs/channels/feishu.md b/docs/channels/feishu.md
@@ -44,7 +44,7 @@ Requires OpenClaw 2026.4.25 or above. Run `openclaw --version` to check. Upgrade
 Configure `dmPolicy` to control who can DM the bot:
 
 - `"pairing"` — unknown users receive a pairing code; approve via CLI
-- `"allowlist"` — only users listed in `allowFrom` can chat (default: bot owner only)
+- `"allowlist"` — only users listed in `allowFrom` can chat
 - `"open"` — allow public DMs only when `allowFrom` includes `"*"`; with restrictive entries, only matching users can chat
 - `"disabled"` — disable all DMs
 
@@ -418,14 +418,14 @@ Full configuration: [Gateway configuration](/gateway/configuration)
 | `channels.feishu.accounts.<id>.appSecret`         | App Secret                                                                       | —                |
 | `channels.feishu.accounts.<id>.domain`            | Per-account domain override                                                      | `feishu`         |
 | `channels.feishu.accounts.<id>.tts`               | Per-account TTS override                                                         | `messages.tts`   |
-| `channels.feishu.dmPolicy`                        | DM policy                                                                        | `allowlist`      |
-| `channels.feishu.allowFrom`                       | DM allowlist (open_id list)                                                      | [BotOwnerId]     |
+| `channels.feishu.dmPolicy`                        | DM policy                                                                        | `pairing`        |
+| `channels.feishu.allowFrom`                       | DM allowlist (open_id list)                                                      | —                |
 | `channels.feishu.groupPolicy`                     | Group policy                                                                     | `allowlist`      |
 | `channels.feishu.groupAllowFrom`                  | Group allowlist                                                                  | —                |
 | `channels.feishu.requireMention`                  | Require @mention in groups                                                       | `true`           |
 | `channels.feishu.groups.<chat_id>.requireMention` | Per-group @mention override; explicit IDs also admit the group in allowlist mode | inherited        |
 | `channels.feishu.groups.<chat_id>.enabled`        | Enable/disable a specific group                                                  | `true`           |
-| `channels.feishu.textChunkLimit`                  | Message chunk size                                                               | `2000`           |
+| `channels.feishu.textChunkLimit`                  | Message chunk size                                                               | `4000`           |
 | `channels.feishu.mediaMaxMb`                      | Media size limit                                                                 | `30`             |
 | `channels.feishu.streaming`                       | Streaming card output                                                            | `true`           |
 | `channels.feishu.blockStreaming`                  | Completed-block reply streaming                                                  | `false`          |

diff --git a/docs/channels/matrix.md b/docs/channels/matrix.md
@@ -214,6 +214,7 @@ form:
 | `"off"` (default) | Wait for the full reply, send once. `true` ↔ `"partial"`, `false` ↔ `"off"`.                                                                                        |
 | `"partial"`       | Edit one normal text message in place as the model writes the current block. Stock Matrix clients may notify on the first preview, not the final edit.              |
 | `"quiet"`         | Same as `"partial"` but the message is a non-notifying notice. Recipients only get a notification once a per-user push rule matches the finalized edit (see below). |
+| `"progress"`      | Live "thinking" / tool-progress label edits in place (uses `streaming.progress.labels`, `maxLines`, `toolProgress`). Falls back to final-only delivery once the answer arrives.                                                                                                                                                                                                       |
 
 `blockStreaming` is independent of `streaming`: